unsupervised feature extraction: Topics by Science.gov

Sample records for unsupervised feature extraction

Feature Extraction Using an Unsupervised Neural Network

DTIC Science & Technology

1991-05-03

with this neural netowrk is given and its connection to exploratory projection pursuit methods is established. DD I 2 P JA d 73 EDITIONj Of I NOV 6s...IS OBSOLETE $IN 0102- LF- 014- 6601 SECURITY CLASSIFICATION OF THIS PAGE (When Daoes Enlered) Feature Extraction using an Unsupervised Neural Network
Principal component analysis-based unsupervised feature extraction applied to in silico drug discovery for posttraumatic stress disorder-mediated heart disease.

PubMed

Taguchi, Y-h; Iwadate, Mitsuo; Umeyama, Hideaki

2015-04-30

Feature extraction (FE) is difficult, particularly if there are more features than samples, as small sample numbers often result in biased outcomes or overfitting. Furthermore, multiple sample classes often complicate FE because evaluating performance, which is usual in supervised FE, is generally harder than the two-class problem. Developing sample classification independent unsupervised methods would solve many of these problems. Two principal component analysis (PCA)-based FE, specifically, variational Bayes PCA (VBPCA) was extended to perform unsupervised FE, and together with conventional PCA (CPCA)-based unsupervised FE, were tested as sample classification independent unsupervised FE methods. VBPCA- and CPCA-based unsupervised FE both performed well when applied to simulated data, and a posttraumatic stress disorder (PTSD)-mediated heart disease data set that had multiple categorical class observations in mRNA/microRNA expression of stressed mouse heart. A critical set of PTSD miRNAs/mRNAs were identified that show aberrant expression between treatment and control samples, and significant, negative correlation with one another. Moreover, greater stability and biological feasibility than conventional supervised FE was also demonstrated. Based on the results obtained, in silico drug discovery was performed as translational validation of the methods. Our two proposed unsupervised FE methods (CPCA- and VBPCA-based) worked well on simulated data, and outperformed two conventional supervised FE methods on a real data set. Thus, these two methods have suggested equivalence for FE on categorical multiclass data sets, with potential translational utility for in silico drug discovery.
Unsupervised Feature Learning for Heart Sounds Classification Using Autoencoder

NASA Astrophysics Data System (ADS)

Hu, Wei; Lv, Jiancheng; Liu, Dongbo; Chen, Yao

2018-04-01

Cardiovascular disease seriously threatens the health of many people. It is usually diagnosed during cardiac auscultation, which is a fast and efficient method of cardiovascular disease diagnosis. In recent years, deep learning approach using unsupervised learning has made significant breakthroughs in many fields. However, to our knowledge, deep learning has not yet been used for heart sound classification. In this paper, we first use the average Shannon energy to extract the envelope of the heart sounds, then find the highest point of S1 to extract the cardiac cycle. We convert the time-domain signals of the cardiac cycle into spectrograms and apply principal component analysis whitening to reduce the dimensionality of the spectrogram. Finally, we apply a two-layer autoencoder to extract the features of the spectrogram. The experimental results demonstrate that the features from the autoencoder are suitable for heart sound classification.
Infrared vehicle recognition using unsupervised feature learning based on K-feature

NASA Astrophysics Data System (ADS)

Lin, Jin; Tan, Yihua; Xia, Haijiao; Tian, Jinwen

2018-02-01

Subject to the complex battlefield environment, it is difficult to establish a complete knowledge base in practical application of vehicle recognition algorithms. The infrared vehicle recognition is always difficult and challenging, which plays an important role in remote sensing. In this paper we propose a new unsupervised feature learning method based on K-feature to recognize vehicle in infrared images. First, we use the target detection algorithm which is based on the saliency to detect the initial image. Then, the unsupervised feature learning based on K-feature, which is generated by Kmeans clustering algorithm that extracted features by learning a visual dictionary from a large number of samples without label, is calculated to suppress the false alarm and improve the accuracy. Finally, the vehicle target recognition image is finished by some post-processing. Large numbers of experiments demonstrate that the proposed method has satisfy recognition effectiveness and robustness for vehicle recognition in infrared images under complex backgrounds, and it also improve the reliability of it.
Noise-robust unsupervised spike sorting based on discriminative subspace learning with outlier handling.

PubMed

Keshtkaran, Mohammad Reza; Yang, Zhi

2017-06-01

Spike sorting is a fundamental preprocessing step for many neuroscience studies which rely on the analysis of spike trains. Most of the feature extraction and dimensionality reduction techniques that have been used for spike sorting give a projection subspace which is not necessarily the most discriminative one. Therefore, the clusters which appear inherently separable in some discriminative subspace may overlap if projected using conventional feature extraction approaches leading to a poor sorting accuracy especially when the noise level is high. In this paper, we propose a noise-robust and unsupervised spike sorting algorithm based on learning discriminative spike features for clustering. The proposed algorithm uses discriminative subspace learning to extract low dimensional and most discriminative features from the spike waveforms and perform clustering with automatic detection of the number of the clusters. The core part of the algorithm involves iterative subspace selection using linear discriminant analysis and clustering using Gaussian mixture model with outlier detection. A statistical test in the discriminative subspace is proposed to automatically detect the number of the clusters. Comparative results on publicly available simulated and real in vivo datasets demonstrate that our algorithm achieves substantially improved cluster distinction leading to higher sorting accuracy and more reliable detection of clusters which are highly overlapping and not detectable using conventional feature extraction techniques such as principal component analysis or wavelets. By providing more accurate information about the activity of more number of individual neurons with high robustness to neural noise and outliers, the proposed unsupervised spike sorting algorithm facilitates more detailed and accurate analysis of single- and multi-unit activities in neuroscience and brain machine interface studies.
Noise-robust unsupervised spike sorting based on discriminative subspace learning with outlier handling

NASA Astrophysics Data System (ADS)

Keshtkaran, Mohammad Reza; Yang, Zhi

2017-06-01

Objective. Spike sorting is a fundamental preprocessing step for many neuroscience studies which rely on the analysis of spike trains. Most of the feature extraction and dimensionality reduction techniques that have been used for spike sorting give a projection subspace which is not necessarily the most discriminative one. Therefore, the clusters which appear inherently separable in some discriminative subspace may overlap if projected using conventional feature extraction approaches leading to a poor sorting accuracy especially when the noise level is high. In this paper, we propose a noise-robust and unsupervised spike sorting algorithm based on learning discriminative spike features for clustering. Approach. The proposed algorithm uses discriminative subspace learning to extract low dimensional and most discriminative features from the spike waveforms and perform clustering with automatic detection of the number of the clusters. The core part of the algorithm involves iterative subspace selection using linear discriminant analysis and clustering using Gaussian mixture model with outlier detection. A statistical test in the discriminative subspace is proposed to automatically detect the number of the clusters. Main results. Comparative results on publicly available simulated and real in vivo datasets demonstrate that our algorithm achieves substantially improved cluster distinction leading to higher sorting accuracy and more reliable detection of clusters which are highly overlapping and not detectable using conventional feature extraction techniques such as principal component analysis or wavelets. Significance. By providing more accurate information about the activity of more number of individual neurons with high robustness to neural noise and outliers, the proposed unsupervised spike sorting algorithm facilitates more detailed and accurate analysis of single- and multi-unit activities in neuroscience and brain machine interface studies.
Intelligent Fault Diagnosis of Rotary Machinery Based on Unsupervised Multiscale Representation Learning

NASA Astrophysics Data System (ADS)

Jiang, Guo-Qian; Xie, Ping; Wang, Xiao; Chen, Meng; He, Qun

2017-11-01

The performance of traditional vibration based fault diagnosis methods greatly depends on those handcrafted features extracted using signal processing algorithms, which require significant amounts of domain knowledge and human labor, and do not generalize well to new diagnosis domains. Recently, unsupervised representation learning provides an alternative promising solution to feature extraction in traditional fault diagnosis due to its superior learning ability from unlabeled data. Given that vibration signals usually contain multiple temporal structures, this paper proposes a multiscale representation learning (MSRL) framework to learn useful features directly from raw vibration signals, with the aim to capture rich and complementary fault pattern information at different scales. In our proposed approach, a coarse-grained procedure is first employed to obtain multiple scale signals from an original vibration signal. Then, sparse filtering, a newly developed unsupervised learning algorithm, is applied to automatically learn useful features from each scale signal, respectively, and then the learned features at each scale to be concatenated one by one to obtain multiscale representations. Finally, the multiscale representations are fed into a supervised classifier to achieve diagnosis results. Our proposed approach is evaluated using two different case studies: motor bearing and wind turbine gearbox fault diagnosis. Experimental results show that the proposed MSRL approach can take full advantages of the availability of unlabeled data to learn discriminative features and achieved better performance with higher accuracy and stability compared to the traditional approaches.
Predicting protein complexes using a supervised learning method combined with local structural information.

PubMed

Dong, Yadong; Sun, Yongqi; Qin, Chao

2018-01-01

The existing protein complex detection methods can be broadly divided into two categories: unsupervised and supervised learning methods. Most of the unsupervised learning methods assume that protein complexes are in dense regions of protein-protein interaction (PPI) networks even though many true complexes are not dense subgraphs. Supervised learning methods utilize the informative properties of known complexes; they often extract features from existing complexes and then use the features to train a classification model. The trained model is used to guide the search process for new complexes. However, insufficient extracted features, noise in the PPI data and the incompleteness of complex data make the classification model imprecise. Consequently, the classification model is not sufficient for guiding the detection of complexes. Therefore, we propose a new robust score function that combines the classification model with local structural information. Based on the score function, we provide a search method that works both forwards and backwards. The results from experiments on six benchmark PPI datasets and three protein complex datasets show that our approach can achieve better performance compared with the state-of-the-art supervised, semi-supervised and unsupervised methods for protein complex detection, occasionally significantly outperforming such methods.
Discrete Wavelet Transform-Based Whole-Spectral and Subspectral Analysis for Improved Brain Tumor Clustering Using Single Voxel MR Spectroscopy.

PubMed

Yang, Guang; Nawaz, Tahir; Barrick, Thomas R; Howe, Franklyn A; Slabaugh, Greg

2015-12-01

Many approaches have been considered for automatic grading of brain tumors by means of pattern recognition with magnetic resonance spectroscopy (MRS). Providing an improved technique which can assist clinicians in accurately identifying brain tumor grades is our main objective. The proposed technique, which is based on the discrete wavelet transform (DWT) of whole-spectral or subspectral information of key metabolites, combined with unsupervised learning, inspects the separability of the extracted wavelet features from the MRS signal to aid the clustering. In total, we included 134 short echo time single voxel MRS spectra (SV MRS) in our study that cover normal controls, low grade and high grade tumors. The combination of DWT-based whole-spectral or subspectral analysis and unsupervised clustering achieved an overall clustering accuracy of 94.8% and a balanced error rate of 7.8%. To the best of our knowledge, it is the first study using DWT combined with unsupervised learning to cluster brain SV MRS. Instead of dimensionality reduction on SV MRS or feature selection using model fitting, our study provides an alternative method of extracting features to obtain promising clustering results.
Integrative analysis of gene expression and DNA methylation using unsupervised feature extraction for detecting candidate cancer biomarkers.

PubMed

Moon, Myungjin; Nakai, Kenta

2018-04-01

Currently, cancer biomarker discovery is one of the important research topics worldwide. In particular, detecting significant genes related to cancer is an important task for early diagnosis and treatment of cancer. Conventional studies mostly focus on genes that are differentially expressed in different states of cancer; however, noise in gene expression datasets and insufficient information in limited datasets impede precise analysis of novel candidate biomarkers. In this study, we propose an integrative analysis of gene expression and DNA methylation using normalization and unsupervised feature extractions to identify candidate biomarkers of cancer using renal cell carcinoma RNA-seq datasets. Gene expression and DNA methylation datasets are normalized by Box-Cox transformation and integrated into a one-dimensional dataset that retains the major characteristics of the original datasets by unsupervised feature extraction methods, and differentially expressed genes are selected from the integrated dataset. Use of the integrated dataset demonstrated improved performance as compared with conventional approaches that utilize gene expression or DNA methylation datasets alone. Validation based on the literature showed that a considerable number of top-ranked genes from the integrated dataset have known relationships with cancer, implying that novel candidate biomarkers can also be acquired from the proposed analysis method. Furthermore, we expect that the proposed method can be expanded for applications involving various types of multi-omics datasets.
Emotional textile image classification based on cross-domain convolutional sparse autoencoders with feature selection

NASA Astrophysics Data System (ADS)

Li, Zuhe; Fan, Yangyu; Liu, Weihua; Yu, Zeqi; Wang, Fengqin

2017-01-01

We aim to apply sparse autoencoder-based unsupervised feature learning to emotional semantic analysis for textile images. To tackle the problem of limited training data, we present a cross-domain feature learning scheme for emotional textile image classification using convolutional autoencoders. We further propose a correlation-analysis-based feature selection method for the weights learned by sparse autoencoders to reduce the number of features extracted from large size images. First, we randomly collect image patches on an unlabeled image dataset in the source domain and learn local features with a sparse autoencoder. We then conduct feature selection according to the correlation between different weight vectors corresponding to the autoencoder's hidden units. We finally adopt a convolutional neural network including a pooling layer to obtain global feature activations of textile images in the target domain and send these global feature vectors into logistic regression models for emotional image classification. The cross-domain unsupervised feature learning method achieves 65% to 78% average accuracy in the cross-validation experiments corresponding to eight emotional categories and performs better than conventional methods. Feature selection can reduce the computational cost of global feature extraction by about 50% while improving classification performance.
Unsupervised Feature Learning With Winner-Takes-All Based STDP

PubMed Central

Ferré, Paul; Mamalet, Franck; Thorpe, Simon J.

2018-01-01

We present a novel strategy for unsupervised feature learning in image applications inspired by the Spike-Timing-Dependent-Plasticity (STDP) biological learning rule. We show equivalence between rank order coding Leaky-Integrate-and-Fire neurons and ReLU artificial neurons when applied to non-temporal data. We apply this to images using rank-order coding, which allows us to perform a full network simulation with a single feed-forward pass using GPU hardware. Next we introduce a binary STDP learning rule compatible with training on batches of images. Two mechanisms to stabilize the training are also presented : a Winner-Takes-All (WTA) framework which selects the most relevant patches to learn from along the spatial dimensions, and a simple feature-wise normalization as homeostatic process. This learning process allows us to train multi-layer architectures of convolutional sparse features. We apply our method to extract features from the MNIST, ETH80, CIFAR-10, and STL-10 datasets and show that these features are relevant for classification. We finally compare these results with several other state of the art unsupervised learning methods. PMID:29674961
A Novel Unsupervised Segmentation Quality Evaluation Method for Remote Sensing Images

PubMed Central

Tang, Yunwei; Jing, Linhai; Ding, Haifeng

2017-01-01

The segmentation of a high spatial resolution remote sensing image is a critical step in geographic object-based image analysis (GEOBIA). Evaluating the performance of segmentation without ground truth data, i.e., unsupervised evaluation, is important for the comparison of segmentation algorithms and the automatic selection of optimal parameters. This unsupervised strategy currently faces several challenges in practice, such as difficulties in designing effective indicators and limitations of the spectral values in the feature representation. This study proposes a novel unsupervised evaluation method to quantitatively measure the quality of segmentation results to overcome these problems. In this method, multiple spectral and spatial features of images are first extracted simultaneously and then integrated into a feature set to improve the quality of the feature representation of ground objects. The indicators designed for spatial stratified heterogeneity and spatial autocorrelation are included to estimate the properties of the segments in this integrated feature set. These two indicators are then combined into a global assessment metric as the final quality score. The trade-offs of the combined indicators are accounted for using a strategy based on the Mahalanobis distance, which can be exhibited geometrically. The method is tested on two segmentation algorithms and three testing images. The proposed method is compared with two existing unsupervised methods and a supervised method to confirm its capabilities. Through comparison and visual analysis, the results verified the effectiveness of the proposed method and demonstrated the reliability and improvements of this method with respect to other methods. PMID:29064416
Transformer fault diagnosis using continuous sparse autoencoder.

PubMed

Wang, Lukun; Zhao, Xiaoying; Pei, Jiangnan; Tang, Gongyou

2016-01-01

This paper proposes a novel continuous sparse autoencoder (CSAE) which can be used in unsupervised feature learning. The CSAE adds Gaussian stochastic unit into activation function to extract features of nonlinear data. In this paper, CSAE is applied to solve the problem of transformer fault recognition. Firstly, based on dissolved gas analysis method, IEC three ratios are calculated by the concentrations of dissolved gases. Then IEC three ratios data is normalized to reduce data singularity and improve training speed. Secondly, deep belief network is established by two layers of CSAE and one layer of back propagation (BP) network. Thirdly, CSAE is adopted to unsupervised training and getting features. Then BP network is used for supervised training and getting transformer fault. Finally, the experimental data from IEC TC 10 dataset aims to illustrate the effectiveness of the presented approach. Comparative experiments clearly show that CSAE can extract features from the original data, and achieve a superior correct differentiation rate on transformer fault diagnosis.
Unsupervised Fault Diagnosis of a Gear Transmission Chain Using a Deep Belief Network

PubMed Central

He, Jun; Yang, Shixi; Gan, Chunbiao

2017-01-01

Artificial intelligence (AI) techniques, which can effectively analyze massive amounts of fault data and automatically provide accurate diagnosis results, have been widely applied to fault diagnosis of rotating machinery. Conventional AI methods are applied using features selected by a human operator, which are manually extracted based on diagnostic techniques and field expertise. However, developing robust features for each diagnostic purpose is often labour-intensive and time-consuming, and the features extracted for one specific task may be unsuitable for others. In this paper, a novel AI method based on a deep belief network (DBN) is proposed for the unsupervised fault diagnosis of a gear transmission chain, and the genetic algorithm is used to optimize the structural parameters of the network. Compared to the conventional AI methods, the proposed method can adaptively exploit robust features related to the faults by unsupervised feature learning, thus requires less prior knowledge about signal processing techniques and diagnostic expertise. Besides, it is more powerful at modelling complex structured data. The effectiveness of the proposed method is validated using datasets from rolling bearings and gearbox. To show the superiority of the proposed method, its performance is compared with two well-known classifiers, i.e., back propagation neural network (BPNN) and support vector machine (SVM). The fault classification accuracies are 99.26% for rolling bearings and 100% for gearbox when using the proposed method, which are much higher than that of the other two methods. PMID:28677638
Unsupervised Fault Diagnosis of a Gear Transmission Chain Using a Deep Belief Network.

PubMed

He, Jun; Yang, Shixi; Gan, Chunbiao

2017-07-04

Artificial intelligence (AI) techniques, which can effectively analyze massive amounts of fault data and automatically provide accurate diagnosis results, have been widely applied to fault diagnosis of rotating machinery. Conventional AI methods are applied using features selected by a human operator, which are manually extracted based on diagnostic techniques and field expertise. However, developing robust features for each diagnostic purpose is often labour-intensive and time-consuming, and the features extracted for one specific task may be unsuitable for others. In this paper, a novel AI method based on a deep belief network (DBN) is proposed for the unsupervised fault diagnosis of a gear transmission chain, and the genetic algorithm is used to optimize the structural parameters of the network. Compared to the conventional AI methods, the proposed method can adaptively exploit robust features related to the faults by unsupervised feature learning, thus requires less prior knowledge about signal processing techniques and diagnostic expertise. Besides, it is more powerful at modelling complex structured data. The effectiveness of the proposed method is validated using datasets from rolling bearings and gearbox. To show the superiority of the proposed method, its performance is compared with two well-known classifiers, i.e., back propagation neural network (BPNN) and support vector machine (SVM). The fault classification accuracies are 99.26% for rolling bearings and 100% for gearbox when using the proposed method, which are much higher than that of the other two methods.
An unsupervised classification approach for analysis of Landsat data to monitor land reclamation in Belmont county, Ohio

NASA Technical Reports Server (NTRS)

Brumfield, J. O.; Bloemer, H. H. L.; Campbell, W. J.

1981-01-01

Two unsupervised classification procedures for analyzing Landsat data used to monitor land reclamation in a surface mining area in east central Ohio are compared for agreement with data collected from the corresponding locations on the ground. One procedure is based on a traditional unsupervised-clustering/maximum-likelihood algorithm sequence that assumes spectral groupings in the Landsat data in n-dimensional space; the other is based on a nontraditional unsupervised-clustering/canonical-transformation/clustering algorithm sequence that not only assumes spectral groupings in n-dimensional space but also includes an additional feature-extraction technique. It is found that the nontraditional procedure provides an appreciable improvement in spectral groupings and apparently increases the level of accuracy in the classification of land cover categories.
Identification of More Feasible MicroRNA-mRNA Interactions within Multiple Cancers Using Principal Component Analysis Based Unsupervised Feature Extraction.

PubMed

Taguchi, Y-H

2016-05-10

MicroRNA(miRNA)-mRNA interactions are important for understanding many biological processes, including development, differentiation and disease progression, but their identification is highly context-dependent. When computationally derived from sequence information alone, the identification should be verified by integrated analyses of mRNA and miRNA expression. The drawback of this strategy is the vast number of identified interactions, which prevents an experimental or detailed investigation of each pair. In this paper, we overcome this difficulty by the recently proposed principal component analysis (PCA)-based unsupervised feature extraction (FE), which reduces the number of identified miRNA-mRNA interactions that properly discriminate between patients and healthy controls without losing biological feasibility. The approach is applied to six cancers: hepatocellular carcinoma, non-small cell lung cancer, esophageal squamous cell carcinoma, prostate cancer, colorectal/colon cancer and breast cancer. In PCA-based unsupervised FE, the significance does not depend on the number of samples (as in the standard case) but on the number of features, which approximates the number of miRNAs/mRNAs. To our knowledge, we have newly identified miRNA-mRNA interactions in multiple cancers based on a single common (universal) criterion. Moreover, the number of identified interactions was sufficiently small to be sequentially curated by literature searches.
A harmonic linear dynamical system for prominent ECG feature extraction.

PubMed

Thi, Ngoc Anh Nguyen; Yang, Hyung-Jeong; Kim, SunHee; Do, Luu Ngoc

2014-01-01

Unsupervised mining of electrocardiography (ECG) time series is a crucial task in biomedical applications. To have efficiency of the clustering results, the prominent features extracted from preprocessing analysis on multiple ECG time series need to be investigated. In this paper, a Harmonic Linear Dynamical System is applied to discover vital prominent features via mining the evolving hidden dynamics and correlations in ECG time series. The discovery of the comprehensible and interpretable features of the proposed feature extraction methodology effectively represents the accuracy and the reliability of clustering results. Particularly, the empirical evaluation results of the proposed method demonstrate the improved performance of clustering compared to the previous main stream feature extraction approaches for ECG time series clustering tasks. Furthermore, the experimental results on real-world datasets show scalability with linear computation time to the duration of the time series.
A comparative evaluation of supervised and unsupervised representation learning approaches for anaplastic medulloblastoma differentiation

NASA Astrophysics Data System (ADS)

Cruz-Roa, Angel; Arevalo, John; Basavanhally, Ajay; Madabhushi, Anant; González, Fabio

2015-01-01

Learning data representations directly from the data itself is an approach that has shown great success in different pattern recognition problems, outperforming state-of-the-art feature extraction schemes for different tasks in computer vision, speech recognition and natural language processing. Representation learning applies unsupervised and supervised machine learning methods to large amounts of data to find building-blocks that better represent the information in it. Digitized histopathology images represents a very good testbed for representation learning since it involves large amounts of high complex, visual data. This paper presents a comparative evaluation of different supervised and unsupervised representation learning architectures to specifically address open questions on what type of learning architectures (deep or shallow), type of learning (unsupervised or supervised) is optimal. In this paper we limit ourselves to addressing these questions in the context of distinguishing between anaplastic and non-anaplastic medulloblastomas from routine haematoxylin and eosin stained images. The unsupervised approaches evaluated were sparse autoencoders and topographic reconstruct independent component analysis, and the supervised approach was convolutional neural networks. Experimental results show that shallow architectures with more neurons are better than deeper architectures without taking into account local space invariances and that topographic constraints provide useful invariant features in scale and rotations for efficient tumor differentiation.

SAR image segmentation using skeleton-based fuzzy clustering

NASA Astrophysics Data System (ADS)

Cao, Yun Yi; Chen, Yan Qiu

2003-06-01

SAR image segmentation can be converted to a clustering problem in which pixels or small patches are grouped together based on local feature information. In this paper, we present a novel framework for segmentation. The segmentation goal is achieved by unsupervised clustering upon characteristic descriptors extracted from local patches. The mixture model of characteristic descriptor, which combines intensity and texture feature, is investigated. The unsupervised algorithm is derived from the recently proposed Skeleton-Based Data Labeling method. Skeletons are constructed as prototypes of clusters to represent arbitrary latent structures in image data. Segmentation using Skeleton-Based Fuzzy Clustering is able to detect the types of surfaces appeared in SAR images automatically without any user input.
An Extended Spectral-Spatial Classification Approach for Hyperspectral Data

NASA Astrophysics Data System (ADS)

Akbari, D.

2017-11-01

In this paper an extended classification approach for hyperspectral imagery based on both spectral and spatial information is proposed. The spatial information is obtained by an enhanced marker-based minimum spanning forest (MSF) algorithm. Three different methods of dimension reduction are first used to obtain the subspace of hyperspectral data: (1) unsupervised feature extraction methods including principal component analysis (PCA), independent component analysis (ICA), and minimum noise fraction (MNF); (2) supervised feature extraction including decision boundary feature extraction (DBFE), discriminate analysis feature extraction (DAFE), and nonparametric weighted feature extraction (NWFE); (3) genetic algorithm (GA). The spectral features obtained are then fed into the enhanced marker-based MSF classification algorithm. In the enhanced MSF algorithm, the markers are extracted from the classification maps obtained by both SVM and watershed segmentation algorithm. To evaluate the proposed approach, the Pavia University hyperspectral data is tested. Experimental results show that the proposed approach using GA achieves an approximately 8 % overall accuracy higher than the original MSF-based algorithm.
Sparse alignment for robust tensor learning.

PubMed

Lai, Zhihui; Wong, Wai Keung; Xu, Yong; Zhao, Cairong; Sun, Mingming

2014-10-01

Multilinear/tensor extensions of manifold learning based algorithms have been widely used in computer vision and pattern recognition. This paper first provides a systematic analysis of the multilinear extensions for the most popular methods by using alignment techniques, thereby obtaining a general tensor alignment framework. From this framework, it is easy to show that the manifold learning based tensor learning methods are intrinsically different from the alignment techniques. Based on the alignment framework, a robust tensor learning method called sparse tensor alignment (STA) is then proposed for unsupervised tensor feature extraction. Different from the existing tensor learning methods, L1- and L2-norms are introduced to enhance the robustness in the alignment step of the STA. The advantage of the proposed technique is that the difficulty in selecting the size of the local neighborhood can be avoided in the manifold learning based tensor feature extraction algorithms. Although STA is an unsupervised learning method, the sparsity encodes the discriminative information in the alignment step and provides the robustness of STA. Extensive experiments on the well-known image databases as well as action and hand gesture databases by encoding object images as tensors demonstrate that the proposed STA algorithm gives the most competitive performance when compared with the tensor-based unsupervised learning methods.
Characterization of electroencephalography signals for estimating saliency features in videos.

PubMed

Liang, Zhen; Hamada, Yasuyuki; Oba, Shigeyuki; Ishii, Shin

2018-05-12

Understanding the functions of the visual system has been one of the major targets in neuroscience formany years. However, the relation between spontaneous brain activities and visual saliency in natural stimuli has yet to be elucidated. In this study, we developed an optimized machine learning-based decoding model to explore the possible relationships between the electroencephalography (EEG) characteristics and visual saliency. The optimal features were extracted from the EEG signals and saliency map which was computed according to an unsupervised saliency model ( Tavakoli and Laaksonen, 2017). Subsequently, various unsupervised feature selection/extraction techniques were examined using different supervised regression models. The robustness of the presented model was fully verified by means of ten-fold or nested cross validation procedure, and promising results were achieved in the reconstruction of saliency features based on the selected EEG characteristics. Through the successful demonstration of using EEG characteristics to predict the real-time saliency distribution in natural videos, we suggest the feasibility of quantifying visual content through measuring brain activities (EEG signals) in real environments, which would facilitate the understanding of cortical involvement in the processing of natural visual stimuli and application developments motivated by human visual processing. Copyright © 2018 Elsevier Ltd. All rights reserved.
Morphological Feature Extraction for Automatic Registration of Multispectral Images

NASA Technical Reports Server (NTRS)

Plaza, Antonio; LeMoigne, Jacqueline; Netanyahu, Nathan S.

2007-01-01

The task of image registration can be divided into two major components, i.e., the extraction of control points or features from images, and the search among the extracted features for the matching pairs that represent the same feature in the images to be matched. Manual extraction of control features can be subjective and extremely time consuming, and often results in few usable points. On the other hand, automated feature extraction allows using invariant target features such as edges, corners, and line intersections as relevant landmarks for registration purposes. In this paper, we present an extension of a recently developed morphological approach for automatic extraction of landmark chips and corresponding windows in a fully unsupervised manner for the registration of multispectral images. Once a set of chip-window pairs is obtained, a (hierarchical) robust feature matching procedure, based on a multiresolution overcomplete wavelet decomposition scheme, is used for registration purposes. The proposed method is validated on a pair of remotely sensed scenes acquired by the Advanced Land Imager (ALI) multispectral instrument and the Hyperion hyperspectral instrument aboard NASA's Earth Observing-1 satellite.
Video mining using combinations of unsupervised and supervised learning techniques

NASA Astrophysics Data System (ADS)

Divakaran, Ajay; Miyahara, Koji; Peker, Kadir A.; Radhakrishnan, Regunathan; Xiong, Ziyou

2003-12-01

We discuss the meaning and significance of the video mining problem, and present our work on some aspects of video mining. A simple definition of video mining is unsupervised discovery of patterns in audio-visual content. Such purely unsupervised discovery is readily applicable to video surveillance as well as to consumer video browsing applications. We interpret video mining as content-adaptive or "blind" content processing, in which the first stage is content characterization and the second stage is event discovery based on the characterization obtained in stage 1. We discuss the target applications and find that using a purely unsupervised approach are too computationally complex to be implemented on our product platform. We then describe various combinations of unsupervised and supervised learning techniques that help discover patterns that are useful to the end-user of the application. We target consumer video browsing applications such as commercial message detection, sports highlights extraction etc. We employ both audio and video features. We find that supervised audio classification combined with unsupervised unusual event discovery enables accurate supervised detection of desired events. Our techniques are computationally simple and robust to common variations in production styles etc.
Extraction of temporally correlated features from dynamic vision sensors with spike-timing-dependent plasticity.

PubMed

Bichler, Olivier; Querlioz, Damien; Thorpe, Simon J; Bourgoin, Jean-Philippe; Gamrat, Christian

2012-08-01

A biologically inspired approach to learning temporally correlated patterns from a spiking silicon retina is presented. Spikes are generated from the retina in response to relative changes in illumination at the pixel level and transmitted to a feed-forward spiking neural network. Neurons become sensitive to patterns of pixels with correlated activation times, in a fully unsupervised scheme. This is achieved using a special form of Spike-Timing-Dependent Plasticity which depresses synapses that did not recently contribute to the post-synaptic spike activation, regardless of their activation time. Competitive learning is implemented with lateral inhibition. When tested with real-life data, the system is able to extract complex and overlapping temporally correlated features such as car trajectories on a freeway, after only 10 min of traffic learning. Complete trajectories can be learned with a 98% detection rate using a second layer, still with unsupervised learning, and the system may be used as a car counter. The proposed neural network is extremely robust to noise and it can tolerate a high degree of synaptic and neuronal variability with little impact on performance. Such results show that a simple biologically inspired unsupervised learning scheme is capable of generating selectivity to complex meaningful events on the basis of relatively little sensory experience. Copyright © 2012 Elsevier Ltd. All rights reserved.
Semi-automated surface mapping via unsupervised classification

NASA Astrophysics Data System (ADS)

D'Amore, M.; Le Scaon, R.; Helbert, J.; Maturilli, A.

2017-09-01

Due to the increasing volume of the returned data from space mission, the human search for correlation and identification of interesting features becomes more and more unfeasible. Statistical extraction of features via machine learning methods will increase the scientific output of remote sensing missions and aid the discovery of yet unknown feature hidden in dataset. Those methods exploit algorithm trained on features from multiple instrument, returning classification maps that explore intra-dataset correlation, allowing for the discovery of unknown features. We present two applications, one for Mercury and one for Vesta.
Unsupervised symmetrical trademark image retrieval in soccer telecast using wavelet energy and quadtree decomposition

NASA Astrophysics Data System (ADS)

Ong, Swee Khai; Lim, Wee Keong; Soo, Wooi King

2013-04-01

Trademark, a distinctive symbol, is used to distinguish products or services provided by a particular person, group or organization from other similar entries. As trademark represents the reputation and credit standing of the owner, it is important to differentiate one trademark from another. Many methods have been proposed to identify, classify and retrieve trademarks. However, most methods required features database and sample sets for training prior to recognition and retrieval process. In this paper, a new feature on wavelet coefficients, the localized wavelet energy, is introduced to extract features of trademarks. With this, unsupervised content-based symmetrical trademark image retrieval is proposed without the database and prior training set. The feature analysis is done by an integration of the proposed localized wavelet energy and quadtree decomposed regional symmetrical vector. The proposed framework eradicates the dependence on query database and human participation during the retrieval process. In this paper, trademarks for soccer games sponsors are the intended trademark category. Video frames from soccer telecast are extracted and processed for this study. Reasonably good localization and retrieval results on certain categories of trademarks are achieved. A distinctive symbol is used to distinguish products or services provided by a particular person, group or organization from other similar entries.
On-line object feature extraction for multispectral scene representation

NASA Technical Reports Server (NTRS)

Ghassemian, Hassan; Landgrebe, David

1988-01-01

A new on-line unsupervised object-feature extraction method is presented that reduces the complexity and costs associated with the analysis of the multispectral image data and data transmission, storage, archival and distribution. The ambiguity in the object detection process can be reduced if the spatial dependencies, which exist among the adjacent pixels, are intelligently incorporated into the decision making process. The unity relation was defined that must exist among the pixels of an object. Automatic Multispectral Image Compaction Algorithm (AMICA) uses the within object pixel-feature gradient vector as a valuable contextual information to construct the object's features, which preserve the class separability information within the data. For on-line object extraction the path-hypothesis and the basic mathematical tools for its realization are introduced in terms of a specific similarity measure and adjacency relation. AMICA is applied to several sets of real image data, and the performance and reliability of features is evaluated.
Performance analysis of unsupervised optimal fuzzy clustering algorithm for MRI brain tumor segmentation.

PubMed

Blessy, S A Praylin Selva; Sulochana, C Helen

2015-01-01

Segmentation of brain tumor from Magnetic Resonance Imaging (MRI) becomes very complicated due to the structural complexities of human brain and the presence of intensity inhomogeneities. To propose a method that effectively segments brain tumor from MR images and to evaluate the performance of unsupervised optimal fuzzy clustering (UOFC) algorithm for segmentation of brain tumor from MR images. Segmentation is done by preprocessing the MR image to standardize intensity inhomogeneities followed by feature extraction, feature fusion and clustering. Different validation measures are used to evaluate the performance of the proposed method using different clustering algorithms. The proposed method using UOFC algorithm produces high sensitivity (96%) and low specificity (4%) compared to other clustering methods. Validation results clearly show that the proposed method with UOFC algorithm effectively segments brain tumor from MR images.
Unsupervised feature relevance analysis applied to improve ECG heartbeat clustering.

PubMed

Rodríguez-Sotelo, J L; Peluffo-Ordoñez, D; Cuesta-Frau, D; Castellanos-Domínguez, G

2012-10-01

The computer-assisted analysis of biomedical records has become an essential tool in clinical settings. However, current devices provide a growing amount of data that often exceeds the processing capacity of normal computers. As this amount of information rises, new demands for more efficient data extracting methods appear. This paper addresses the task of data mining in physiological records using a feature selection scheme. An unsupervised method based on relevance analysis is described. This scheme uses a least-squares optimization of the input feature matrix in a single iteration. The output of the algorithm is a feature weighting vector. The performance of the method was assessed using a heartbeat clustering test on real ECG records. The quantitative cluster validity measures yielded a correctly classified heartbeat rate of 98.69% (specificity), 85.88% (sensitivity) and 95.04% (general clustering performance), which is even higher than the performance achieved by other similar ECG clustering studies. The number of features was reduced on average from 100 to 18, and the temporal cost was a 43% lower than in previous ECG clustering schemes. Copyright © 2012 Elsevier Ireland Ltd. All rights reserved.
BlobContours: adapting Blobworld for supervised color- and texture-based image segmentation

NASA Astrophysics Data System (ADS)

Vogel, Thomas; Nguyen, Dinh Quyen; Dittmann, Jana

2006-01-01

Extracting features is the first and one of the most crucial steps in recent image retrieval process. While the color features and the texture features of digital images can be extracted rather easily, the shape features and the layout features depend on reliable image segmentation. Unsupervised image segmentation, often used in image analysis, works on merely syntactical basis. That is, what an unsupervised segmentation algorithm can segment is only regions, but not objects. To obtain high-level objects, which is desirable in image retrieval, human assistance is needed. Supervised image segmentations schemes can improve the reliability of segmentation and segmentation refinement. In this paper we propose a novel interactive image segmentation technique that combines the reliability of a human expert with the precision of automated image segmentation. The iterative procedure can be considered a variation on the Blobworld algorithm introduced by Carson et al. from EECS Department, University of California, Berkeley. Starting with an initial segmentation as provided by the Blobworld framework, our algorithm, namely BlobContours, gradually updates it by recalculating every blob, based on the original features and the updated number of Gaussians. Since the original algorithm has hardly been designed for interactive processing we had to consider additional requirements for realizing a supervised segmentation scheme on the basis of Blobworld. Increasing transparency of the algorithm by applying usercontrolled iterative segmentation, providing different types of visualization for displaying the segmented image and decreasing computational time of segmentation are three major requirements which are discussed in detail.
Tensor decomposition-based and principal-component-analysis-based unsupervised feature extraction applied to the gene expression and methylation profiles in the brains of social insects with multiple castes.

PubMed

Taguchi, Y-H

2018-05-08

Even though coexistence of multiple phenotypes sharing the same genomic background is interesting, it remains incompletely understood. Epigenomic profiles may represent key factors, with unknown contributions to the development of multiple phenotypes, and social-insect castes are a good model for elucidation of the underlying mechanisms. Nonetheless, previous studies have failed to identify genes associated with aberrant gene expression and methylation profiles because of the lack of suitable methodology that can address this problem properly. A recently proposed principal component analysis (PCA)-based and tensor decomposition (TD)-based unsupervised feature extraction (FE) can solve this problem because these two approaches can deal with gene expression and methylation profiles even when a small number of samples is available. PCA-based and TD-based unsupervised FE methods were applied to the analysis of gene expression and methylation profiles in the brains of two social insects, Polistes canadensis and Dinoponera quadriceps. Genes associated with differential expression and methylation between castes were identified, and analysis of enrichment of Gene Ontology terms confirmed reliability of the obtained sets of genes from the biological standpoint. Biologically relevant genes, shown to be associated with significant differential gene expression and methylation between castes, were identified here for the first time. The identification of these genes may help understand the mechanisms underlying epigenetic control of development of multiple phenotypes under the same genomic conditions.
Automatic Feature Extraction from Planetary Images

NASA Technical Reports Server (NTRS)

Troglio, Giulia; Le Moigne, Jacqueline; Benediktsson, Jon A.; Moser, Gabriele; Serpico, Sebastiano B.

2010-01-01

With the launch of several planetary missions in the last decade, a large amount of planetary images has already been acquired and much more will be available for analysis in the coming years. The image data need to be analyzed, preferably by automatic processing techniques because of the huge amount of data. Although many automatic feature extraction methods have been proposed and utilized for Earth remote sensing images, these methods are not always applicable to planetary data that often present low contrast and uneven illumination characteristics. Different methods have already been presented for crater extraction from planetary images, but the detection of other types of planetary features has not been addressed yet. Here, we propose a new unsupervised method for the extraction of different features from the surface of the analyzed planet, based on the combination of several image processing techniques, including a watershed segmentation and the generalized Hough Transform. The method has many applications, among which image registration and can be applied to arbitrary planetary images.
Data Exploration using Unsupervised Feature Extraction for Mixed Micro-Seismic Signals

NASA Astrophysics Data System (ADS)

Meyer, Matthias; Weber, Samuel; Beutel, Jan

2017-04-01

We present a system for the analysis of data originating in a multi-sensor and multi-year experiment focusing on slope stability and its underlying processes in fractured permafrost rock walls undertaken at 3500m a.s.l. on the Matterhorn Hörnligrat, (Zermatt, Switzerland). This system incorporates facilities for the transmission, management and storage of large-scales of data ( 7 GB/day), preprocessing and aggregation of multiple sensor types, machine-learning based automatic feature extraction for micro-seismic and acoustic emission data and interactive web-based visualization of the data. Specifically, a combination of three types of sensors are used to profile the frequency spectrum from 1 Hz to 80 kHz with the goal to identify the relevant destructive processes (e.g. micro-cracking and fracture propagation) leading to the eventual destabilization of large rock masses. The sensors installed for this profiling experiment (2 geophones, 1 accelerometers and 2 piezo-electric sensors for detecting acoustic emission), are further augmented with sensors originating from a previous activity focusing on long-term monitoring of temperature evolution and rock kinematics with the help of wireless sensor networks (crackmeters, cameras, weather station, rock temperature profiles, differential GPS) [Hasler2012]. In raw format, the data generated by the different types of sensors, specifically the micro-seismic and acoustic emission sensors, is strongly heterogeneous, in part unsynchronized and the storage and processing demand is large. Therefore, a purpose-built signal preprocessing and event-detection system is used. While the analysis of data from each individual sensor follows established methods, the application of all these sensor types in combination within a field experiment is unique. Furthermore, experience and methods from using such sensors in laboratory settings cannot be readily transferred to the mountain field site setting with its scale and full exposure to the natural environment. Consequently, many state-of-the-art algorithms for big data analysis and event classification requiring a ground truth dataset cannot be applied. The above mentioned challenges require a tool for data exploration. In the presented system, data exploration is supported by unsupervised feature learning based on convolutional neural networks, which is used to automatically extract common features for preliminary clustering and outlier detection. With this information, an interactive web-tool allows for a fast identification of interesting time segments on which segment-selective algorithms for visualization, feature extraction and statistics can be applied. The combination of manual labeling based and unsupervised feature extraction provides an event catalog for classification of different characteristic events related to internal progression of micro-crack in steep fractured bedrock permafrost. References Hasler, A., S. Gruber, and J. Beutel (2012), Kinematics of steep bedrock permafrost, J. Geophys. Res., 117, F01016, doi:10.1029/2011JF001981.
Machinery running state identification based on discriminant semi-supervised local tangent space alignment for feature fusion and extraction

NASA Astrophysics Data System (ADS)

Su, Zuqiang; Xiao, Hong; Zhang, Yi; Tang, Baoping; Jiang, Yonghua

2017-04-01

Extraction of sensitive features is a challenging but key task in data-driven machinery running state identification. Aimed at solving this problem, a method for machinery running state identification that applies discriminant semi-supervised local tangent space alignment (DSS-LTSA) for feature fusion and extraction is proposed. Firstly, in order to extract more distinct features, the vibration signals are decomposed by wavelet packet decomposition WPD, and a mixed-domain feature set consisted of statistical features, autoregressive (AR) model coefficients, instantaneous amplitude Shannon entropy and WPD energy spectrum is extracted to comprehensively characterize the properties of machinery running state(s). Then, the mixed-dimension feature set is inputted into DSS-LTSA for feature fusion and extraction to eliminate redundant information and interference noise. The proposed DSS-LTSA can extract intrinsic structure information of both labeled and unlabeled state samples, and as a result the over-fitting problem of supervised manifold learning and blindness problem of unsupervised manifold learning are overcome. Simultaneously, class discrimination information is integrated within the dimension reduction process in a semi-supervised manner to improve sensitivity of the extracted fusion features. Lastly, the extracted fusion features are inputted into a pattern recognition algorithm to achieve the running state identification. The effectiveness of the proposed method is verified by a running state identification case in a gearbox, and the results confirm the improved accuracy of the running state identification.
Spatial-time-state fusion algorithm for defect detection through eddy current pulsed thermography

NASA Astrophysics Data System (ADS)

Xiao, Xiang; Gao, Bin; Woo, Wai Lok; Tian, Gui Yun; Xiao, Xiao Ting

2018-05-01

Eddy Current Pulsed Thermography (ECPT) has received extensive attention due to its high sensitive of detectability on surface and subsurface cracks. However, it remains as a difficult challenge in unsupervised detection as to identify defects without knowing any prior knowledge. This paper presents a spatial-time-state features fusion algorithm to obtain fully profile of the defects by directional scanning. The proposed method is intended to conduct features extraction by using independent component analysis (ICA) and automatic features selection embedding genetic algorithm. Finally, the optimal feature of each step is fused to obtain defects reconstruction by applying common orthogonal basis extraction (COBE) method. Experiments have been conducted to validate the study and verify the efficacy of the proposed method on blind defect detection.
An effective biometric discretization approach to extract highly discriminative, informative, and privacy-protective binary representation

NASA Astrophysics Data System (ADS)

Lim, Meng-Hui; Teoh, Andrew Beng Jin

2011-12-01

Biometric discretization derives a binary string for each user based on an ordered set of biometric features. This representative string ought to be discriminative, informative, and privacy protective when it is employed as a cryptographic key in various security applications upon error correction. However, it is commonly believed that satisfying the first and the second criteria simultaneously is not feasible, and a tradeoff between them is always definite. In this article, we propose an effective fixed bit allocation-based discretization approach which involves discriminative feature extraction, discriminative feature selection, unsupervised quantization (quantization that does not utilize class information), and linearly separable subcode (LSSC)-based encoding to fulfill all the ideal properties of a binary representation extracted for cryptographic applications. In addition, we examine a number of discriminative feature-selection measures for discretization and identify the proper way of setting an important feature-selection parameter. Encouraging experimental results vindicate the feasibility of our approach.
Vessel extraction in retinal images using automatic thresholding and Gabor Wavelet.

PubMed

Ali, Aziah; Hussain, Aini; Wan Zaki, Wan Mimi Diyana

2017-07-01

Retinal image analysis has been widely used for early detection and diagnosis of multiple systemic diseases. Accurate vessel extraction in retinal image is a crucial step towards a fully automated diagnosis system. This work affords an efficient unsupervised method for extracting blood vessels from retinal images by combining existing Gabor Wavelet (GW) method with automatic thresholding. Green channel image is extracted from color retinal image and used to produce Gabor feature image using GW. Both green channel image and Gabor feature image undergo vessel-enhancement step in order to highlight blood vessels. Next, the two vessel-enhanced images are transformed to binary images using automatic thresholding before combined to produce the final vessel output. Combining the images results in significant improvement of blood vessel extraction performance compared to using individual image. Effectiveness of the proposed method was proven via comparative analysis with existing methods validated using publicly available database, DRIVE.

Unsupervised universal steganalyzer for high-dimensional steganalytic features

NASA Astrophysics Data System (ADS)

Hou, Xiaodan; Zhang, Tao

2016-11-01

The research in developing steganalytic features has been highly successful. These features are extremely powerful when applied to supervised binary classification problems. However, they are incompatible with unsupervised universal steganalysis because the unsupervised method cannot distinguish embedding distortion from varying levels of noises caused by cover variation. This study attempts to alleviate the problem by introducing similarity retrieval of image statistical properties (SRISP), with the specific aim of mitigating the effect of cover variation on the existing steganalytic features. First, cover images with some statistical properties similar to those of a given test image are searched from a retrieval cover database to establish an aided sample set. Then, unsupervised outlier detection is performed on a test set composed of the given test image and its aided sample set to determine the type (cover or stego) of the given test image. Our proposed framework, called SRISP-aided unsupervised outlier detection, requires no training. Thus, it does not suffer from model mismatch mess. Compared with prior unsupervised outlier detectors that do not consider SRISP, the proposed framework not only retains the universality but also exhibits superior performance when applied to high-dimensional steganalytic features.
Enhanced HMAX model with feedforward feature learning for multiclass categorization.

PubMed

Li, Yinlin; Wu, Wei; Zhang, Bo; Li, Fengfu

2015-01-01

In recent years, the interdisciplinary research between neuroscience and computer vision has promoted the development in both fields. Many biologically inspired visual models are proposed, and among them, the Hierarchical Max-pooling model (HMAX) is a feedforward model mimicking the structures and functions of V1 to posterior inferotemporal (PIT) layer of the primate visual cortex, which could generate a series of position- and scale- invariant features. However, it could be improved with attention modulation and memory processing, which are two important properties of the primate visual cortex. Thus, in this paper, based on recent biological research on the primate visual cortex, we still mimic the first 100-150 ms of visual cognition to enhance the HMAX model, which mainly focuses on the unsupervised feedforward feature learning process. The main modifications are as follows: (1) To mimic the attention modulation mechanism of V1 layer, a bottom-up saliency map is computed in the S1 layer of the HMAX model, which can support the initial feature extraction for memory processing; (2) To mimic the learning, clustering and short-term memory to long-term memory conversion abilities of V2 and IT, an unsupervised iterative clustering method is used to learn clusters with multiscale middle level patches, which are taken as long-term memory; (3) Inspired by the multiple feature encoding mode of the primate visual cortex, information including color, orientation, and spatial position are encoded in different layers of the HMAX model progressively. By adding a softmax layer at the top of the model, multiclass categorization experiments can be conducted, and the results on Caltech101 show that the enhanced model with a smaller memory size exhibits higher accuracy than the original HMAX model, and could also achieve better accuracy than other unsupervised feature learning methods in multiclass categorization task.
Feature-level sentiment analysis by using comparative domain corpora

NASA Astrophysics Data System (ADS)

Quan, Changqin; Ren, Fuji

2016-06-01

Feature-level sentiment analysis (SA) is able to provide more fine-grained SA on certain opinion targets and has a wider range of applications on E-business. This study proposes an approach based on comparative domain corpora for feature-level SA. The proposed approach makes use of word associations for domain-specific feature extraction. First, we assign a similarity score for each candidate feature to denote its similarity extent to a domain. Then we identify domain features based on their similarity scores on different comparative domain corpora. After that, dependency grammar and a general sentiment lexicon are applied to extract and expand feature-oriented opinion words. Lastly, the semantic orientation of a domain-specific feature is determined based on the feature-oriented opinion lexicons. In evaluation, we compare the proposed method with several state-of-the-art methods (including unsupervised and semi-supervised) using a standard product review test collection. The experimental results demonstrate the effectiveness of using comparative domain corpora.
Methods for automatically analyzing humpback song units.

PubMed

Rickwood, Peter; Taylor, Andrew

2008-03-01

This paper presents mathematical techniques for automatically extracting and analyzing bioacoustic signals. Automatic techniques are described for isolation of target signals from background noise, extraction of features from target signals and unsupervised classification (clustering) of the target signals based on these features. The only user-provided inputs, other than raw sound, is an initial set of signal processing and control parameters. Of particular note is that the number of signal categories is determined automatically. The techniques, applied to hydrophone recordings of humpback whales (Megaptera novaeangliae), produce promising initial results, suggesting that they may be of use in automated analysis of not only humpbacks, but possibly also in other bioacoustic settings where automated analysis is desirable.
Scale-invariant feature extraction of neural network and renormalization group flow

NASA Astrophysics Data System (ADS)

Iso, Satoshi; Shiba, Shotaro; Yokoo, Sumito

2018-05-01

Theoretical understanding of how a deep neural network (DNN) extracts features from input images is still unclear, but it is widely believed that the extraction is performed hierarchically through a process of coarse graining. It reminds us of the basic renormalization group (RG) concept in statistical physics. In order to explore possible relations between DNN and RG, we use the restricted Boltzmann machine (RBM) applied to an Ising model and construct a flow of model parameters (in particular, temperature) generated by the RBM. We show that the unsupervised RBM trained by spin configurations at various temperatures from T =0 to T =6 generates a flow along which the temperature approaches the critical value Tc=2.2 7 . This behavior is the opposite of the typical RG flow of the Ising model. By analyzing various properties of the weight matrices of the trained RBM, we discuss why it flows towards Tc and how the RBM learns to extract features of spin configurations.
Knee cartilage extraction and bone-cartilage interface analysis from 3D MRI data sets

NASA Astrophysics Data System (ADS)

Tamez-Pena, Jose G.; Barbu-McInnis, Monica; Totterman, Saara

2004-05-01

This works presents a robust methodology for the analysis of the knee joint cartilage and the knee bone-cartilage interface from fused MRI sets. The proposed approach starts by fusing a set of two 3D MR images the knee. Although the proposed method is not pulse sequence dependent, the first sequence should be programmed to achieve good contrast between bone and cartilage. The recommended second pulse sequence is one that maximizes the contrast between cartilage and surrounding soft tissues. Once both pulse sequences are fused, the proposed bone-cartilage analysis is done in four major steps. First, an unsupervised segmentation algorithm is used to extract the femur, the tibia, and the patella. Second, a knowledge based feature extraction algorithm is used to extract the femoral, tibia and patellar cartilages. Third, a trained user corrects cartilage miss-classifications done by the automated extracted cartilage. Finally, the final segmentation is the revisited using an unsupervised MAP voxel relaxation algorithm. This final segmentation has the property that includes the extracted bone tissue as well as all the cartilage tissue. This is an improvement over previous approaches where only the cartilage was segmented. Furthermore, this approach yields very reproducible segmentation results in a set of scan-rescan experiments. When these segmentations were coupled with a partial volume compensated surface extraction algorithm the volume, area, thickness measurements shows precisions around 2.6%
Low-dimensional dynamical characterization of human performance of cancer patients using motion data.

PubMed

Hasnain, Zaki; Li, Ming; Dorff, Tanya; Quinn, David; Ueno, Naoto T; Yennu, Sriram; Kolatkar, Anand; Shahabi, Cyrus; Nocera, Luciano; Nieva, Jorge; Kuhn, Peter; Newton, Paul K

2018-05-18

Biomechanical characterization of human performance with respect to fatigue and fitness is relevant in many settings, however is usually limited to either fully qualitative assessments or invasive methods which require a significant experimental setup consisting of numerous sensors, force plates, and motion detectors. Qualitative assessments are difficult to standardize due to their intrinsic subjective nature, on the other hand, invasive methods provide reliable metrics but are not feasible for large scale applications. Presented here is a dynamical toolset for detecting performance groups using a non-invasive system based on the Microsoft Kinect motion capture sensor, and a case study of 37 cancer patients performing two clinically monitored tasks before and after therapy regimens. Dynamical features are extracted from the motion time series data and evaluated based on their ability to i) cluster patients into coherent fitness groups using unsupervised learning algorithms and to ii) predict Eastern Cooperative Oncology Group performance status via supervised learning. The unsupervised patient clustering is comparable to clustering based on physician assigned Eastern Cooperative Oncology Group status in that they both have similar concordance with change in weight before and after therapy as well as unexpected hospitalizations throughout the study. The extracted dynamical features can predict physician, coordinator, and patient Eastern Cooperative Oncology Group status with an accuracy of approximately 80%. The non-invasive Microsoft Kinect sensor and the proposed dynamical toolset comprised of data preprocessing, feature extraction, dimensionality reduction, and machine learning offers a low-cost and general method for performance segregation and can complement existing qualitative clinical assessments. Copyright © 2018 Elsevier Ltd. All rights reserved.
Unsupervised Deep Hashing With Pseudo Labels for Scalable Image Retrieval.

PubMed

Zhang, Haofeng; Liu, Li; Long, Yang; Shao, Ling

2018-04-01

In order to achieve efficient similarity searching, hash functions are designed to encode images into low-dimensional binary codes with the constraint that similar features will have a short distance in the projected Hamming space. Recently, deep learning-based methods have become more popular, and outperform traditional non-deep methods. However, without label information, most state-of-the-art unsupervised deep hashing (DH) algorithms suffer from severe performance degradation for unsupervised scenarios. One of the main reasons is that the ad-hoc encoding process cannot properly capture the visual feature distribution. In this paper, we propose a novel unsupervised framework that has two main contributions: 1) we convert the unsupervised DH model into supervised by discovering pseudo labels; 2) the framework unifies likelihood maximization, mutual information maximization, and quantization error minimization so that the pseudo labels can maximumly preserve the distribution of visual features. Extensive experiments on three popular data sets demonstrate the advantages of the proposed method, which leads to significant performance improvement over the state-of-the-art unsupervised hashing algorithms.
Robust Joint Graph Sparse Coding for Unsupervised Spectral Feature Selection.

PubMed

Zhu, Xiaofeng; Li, Xuelong; Zhang, Shichao; Ju, Chunhua; Wu, Xindong

2017-06-01

In this paper, we propose a new unsupervised spectral feature selection model by embedding a graph regularizer into the framework of joint sparse regression for preserving the local structures of data. To do this, we first extract the bases of training data by previous dictionary learning methods and, then, map original data into the basis space to generate their new representations, by proposing a novel joint graph sparse coding (JGSC) model. In JGSC, we first formulate its objective function by simultaneously taking subspace learning and joint sparse regression into account, then, design a new optimization solution to solve the resulting objective function, and further prove the convergence of the proposed solution. Furthermore, we extend JGSC to a robust JGSC (RJGSC) via replacing the least square loss function with a robust loss function, for achieving the same goals and also avoiding the impact of outliers. Finally, experimental results on real data sets showed that both JGSC and RJGSC outperformed the state-of-the-art algorithms in terms of k -nearest neighbor classification performance.
Neurons with two sites of synaptic integration learn invariant representations.

PubMed

Körding, K P; König, P

2001-12-01

Neurons in mammalian cerebral cortex combine specific responses with respect to some stimulus features with invariant responses to other stimulus features. For example, in primary visual cortex, complex cells code for orientation of a contour but ignore its position to a certain degree. In higher areas, such as the inferotemporal cortex, translation-invariant, rotation-invariant, and even view point-invariant responses can be observed. Such properties are of obvious interest to artificial systems performing tasks like pattern recognition. It remains to be resolved how such response properties develop in biological systems. Here we present an unsupervised learning rule that addresses this problem. It is based on a neuron model with two sites of synaptic integration, allowing qualitatively different effects of input to basal and apical dendritic trees, respectively. Without supervision, the system learns to extract invariance properties using temporal or spatial continuity of stimuli. Furthermore, top-down information can be smoothly integrated in the same framework. Thus, this model lends a physiological implementation to approaches of unsupervised learning of invariant-response properties.
Quasi-Supervised Scoring of Human Sleep in Polysomnograms Using Augmented Input Variables

PubMed Central

Yaghouby, Farid; Sunderam, Sridhar

2015-01-01

The limitations of manual sleep scoring make computerized methods highly desirable. Scoring errors can arise from human rater uncertainty or inter-rater variability. Sleep scoring algorithms either come as supervised classifiers that need scored samples of each state to be trained, or as unsupervised classifiers that use heuristics or structural clues in unscored data to define states. We propose a quasi-supervised classifier that models observations in an unsupervised manner but mimics a human rater wherever training scores are available. EEG, EMG, and EOG features were extracted in 30s epochs from human-scored polysomnograms recorded from 42 healthy human subjects (18 to 79 years) and archived in an anonymized, publicly accessible database. Hypnograms were modified so that: 1. Some states are scored but not others; 2. Samples of all states are scored but not for transitional epochs; and 3. Two raters with 67% agreement are simulated. A framework for quasi-supervised classification was devised in which unsupervised statistical models—specifically Gaussian mixtures and hidden Markov models—are estimated from unlabeled training data, but the training samples are augmented with variables whose values depend on available scores. Classifiers were fitted to signal features incorporating partial scores, and used to predict scores for complete recordings. Performance was assessed using Cohen's K statistic. The quasi-supervised classifier performed significantly better than an unsupervised model and sometimes as well as a completely supervised model despite receiving only partial scores. The quasi-supervised algorithm addresses the need for classifiers that mimic scoring patterns of human raters while compensating for their limitations. PMID:25679475
Quasi-supervised scoring of human sleep in polysomnograms using augmented input variables.

PubMed

Yaghouby, Farid; Sunderam, Sridhar

2015-04-01

The limitations of manual sleep scoring make computerized methods highly desirable. Scoring errors can arise from human rater uncertainty or inter-rater variability. Sleep scoring algorithms either come as supervised classifiers that need scored samples of each state to be trained, or as unsupervised classifiers that use heuristics or structural clues in unscored data to define states. We propose a quasi-supervised classifier that models observations in an unsupervised manner but mimics a human rater wherever training scores are available. EEG, EMG, and EOG features were extracted in 30s epochs from human-scored polysomnograms recorded from 42 healthy human subjects (18-79 years) and archived in an anonymized, publicly accessible database. Hypnograms were modified so that: 1. Some states are scored but not others; 2. Samples of all states are scored but not for transitional epochs; and 3. Two raters with 67% agreement are simulated. A framework for quasi-supervised classification was devised in which unsupervised statistical models-specifically Gaussian mixtures and hidden Markov models--are estimated from unlabeled training data, but the training samples are augmented with variables whose values depend on available scores. Classifiers were fitted to signal features incorporating partial scores, and used to predict scores for complete recordings. Performance was assessed using Cohen's Κ statistic. The quasi-supervised classifier performed significantly better than an unsupervised model and sometimes as well as a completely supervised model despite receiving only partial scores. The quasi-supervised algorithm addresses the need for classifiers that mimic scoring patterns of human raters while compensating for their limitations. Copyright © 2015 Elsevier Ltd. All rights reserved.
Surface mapping via unsupervised classification of remote sensing: application to MESSENGER/MASCS and DAWN/VIRS data.

NASA Astrophysics Data System (ADS)

D'Amore, M.; Le Scaon, R.; Helbert, J.; Maturilli, A.

2017-12-01

Machine-learning achieved unprecedented results in high-dimensional data processing tasks with wide applications in various fields. Due to the growing number of complex nonlinear systems that have to be investigated in science and the bare raw size of data nowadays available, ML offers the unique ability to extract knowledge, regardless the specific application field. Examples are image segmentation, supervised/unsupervised/ semi-supervised classification, feature extraction, data dimensionality analysis/reduction.The MASCS instrument has mapped Mercury surface in the 400-1145 nm wavelength range during orbital observations by the MESSENGER spacecraft. We have conducted k-means unsupervised hierarchical clustering to identify and characterize spectral units from MASCS observations. The results display a dichotomy: a polar and equatorial units, possibly linked to compositional differences or weathering due to irradiation. To explore possible relations between composition and spectral behavior, we have compared the spectral provinces with elemental abundance maps derived from MESSENGER's X-Ray Spectrometer (XRS).For the Vesta application on DAWN Visible and infrared spectrometer (VIR) data, we explored several Machine Learning techniques: image segmentation method, stream algorithm and hierarchical clustering.The algorithm successfully separates the Olivine outcrops around two craters on Vesta's surface [1]. New maps summarizing the spectral and chemical signature of the surface could be automatically produced.We conclude that instead of hand digging in data, scientist could choose a subset of algorithms with well known feature (i.e. efficacy on the particular problem, speed, accuracy) and focus their effort in understanding what important characteristic of the groups found in the data mean. [1] E Ammannito et al. "Olivine in an unexpected location on Vesta's surface". In: Nature 504.7478 (2013), pp. 122-125.
Unsupervised semantic indoor scene classification for robot vision based on context of features using Gist and HSV-SIFT

NASA Astrophysics Data System (ADS)

Madokoro, H.; Yamanashi, A.; Sato, K.

2013-08-01

This paper presents an unsupervised scene classification method for actualizing semantic recognition of indoor scenes. Background and foreground features are respectively extracted using Gist and color scale-invariant feature transform (SIFT) as feature representations based on context. We used hue, saturation, and value SIFT (HSV-SIFT) because of its simple algorithm with low calculation costs. Our method creates bags of features for voting visual words created from both feature descriptors to a two-dimensional histogram. Moreover, our method generates labels as candidates of categories for time-series images while maintaining stability and plasticity together. Automatic labeling of category maps can be realized using labels created using adaptive resonance theory (ART) as teaching signals for counter propagation networks (CPNs). We evaluated our method for semantic scene classification using KTH's image database for robot localization (KTH-IDOL), which is popularly used for robot localization and navigation. The mean classification accuracies of Gist, gray SIFT, one class support vector machines (OC-SVM), position-invariant robust features (PIRF), and our method are, respectively, 39.7, 58.0, 56.0, 63.6, and 79.4%. The result of our method is 15.8% higher than that of PIRF. Moreover, we applied our method for fine classification using our original mobile robot. We obtained mean classification accuracy of 83.2% for six zones.
Deep SOMs for automated feature extraction and classification from big data streaming

NASA Astrophysics Data System (ADS)

Sakkari, Mohamed; Ejbali, Ridha; Zaied, Mourad

2017-03-01

In this paper, we proposed a deep self-organizing map model (Deep-SOMs) for automated features extracting and learning from big data streaming which we benefit from the framework Spark for real time streams and highly parallel data processing. The SOMs deep architecture is based on the notion of abstraction (patterns automatically extract from the raw data, from the less to more abstract). The proposed model consists of three hidden self-organizing layers, an input and an output layer. Each layer is made up of a multitude of SOMs, each map only focusing at local headmistress sub-region from the input image. Then, each layer trains the local information to generate more overall information in the higher layer. The proposed Deep-SOMs model is unique in terms of the layers architecture, the SOMs sampling method and learning. During the learning stage we use a set of unsupervised SOMs for feature extraction. We validate the effectiveness of our approach on large data sets such as Leukemia dataset and SRBCT. Results of comparison have shown that the Deep-SOMs model performs better than many existing algorithms for images classification.
A novel framework for feature extraction in multi-sensor action potential sorting.

PubMed

Wu, Shun-Chi; Swindlehurst, A Lee; Nenadic, Zoran

2015-09-30

Extracellular recordings of multi-unit neural activity have become indispensable in neuroscience research. The analysis of the recordings begins with the detection of the action potentials (APs), followed by a classification step where each AP is associated with a given neural source. A feature extraction step is required prior to classification in order to reduce the dimensionality of the data and the impact of noise, allowing source clustering algorithms to work more efficiently. In this paper, we propose a novel framework for multi-sensor AP feature extraction based on the so-called Matched Subspace Detector (MSD), which is shown to be a natural generalization of standard single-sensor algorithms. Clustering using both simulated data and real AP recordings taken in the locust antennal lobe demonstrates that the proposed approach yields features that are discriminatory and lead to promising results. Unlike existing methods, the proposed algorithm finds joint spatio-temporal feature vectors that match the dominant subspace observed in the two-dimensional data without needs for a forward propagation model and AP templates. The proposed MSD approach provides more discriminatory features for unsupervised AP sorting applications. Copyright © 2015 Elsevier B.V. All rights reserved.
Fabric defect detection based on visual saliency using deep feature and low-rank recovery

NASA Astrophysics Data System (ADS)

Liu, Zhoufeng; Wang, Baorui; Li, Chunlei; Li, Bicao; Dong, Yan

2018-04-01

Fabric defect detection plays an important role in improving the quality of fabric product. In this paper, a novel fabric defect detection method based on visual saliency using deep feature and low-rank recovery was proposed. First, unsupervised training is carried out by the initial network parameters based on MNIST large datasets. The supervised fine-tuning of fabric image library based on Convolutional Neural Networks (CNNs) is implemented, and then more accurate deep neural network model is generated. Second, the fabric images are uniformly divided into the image block with the same size, then we extract their multi-layer deep features using the trained deep network. Thereafter, all the extracted features are concentrated into a feature matrix. Third, low-rank matrix recovery is adopted to divide the feature matrix into the low-rank matrix which indicates the background and the sparse matrix which indicates the salient defect. In the end, the iterative optimal threshold segmentation algorithm is utilized to segment the saliency maps generated by the sparse matrix to locate the fabric defect area. Experimental results demonstrate that the feature extracted by CNN is more suitable for characterizing the fabric texture than the traditional LBP, HOG and other hand-crafted features extraction method, and the proposed method can accurately detect the defect regions of various fabric defects, even for the image with complex texture.
Perspective: Materials Informatics and Big Data: Realization of the Fourth Paradigm of Science in Materials Science

DTIC Science & Technology

2016-08-17

thereby opening up new avenues for accelerated materials discovery and design . The need for such data analytics has also been emphasized by the...and design . The construction of inverse models is typically formulated as an optimiza- tion problem wherein a property or performance metric of...discovery and design . extraction, feature selection, etc. Such data preprocessing can either be supervised or unsupervised, based on whether the
Automated age-related macular degeneration classification in OCT using unsupervised feature learning

NASA Astrophysics Data System (ADS)

Venhuizen, Freerk G.; van Ginneken, Bram; Bloemen, Bart; van Grinsven, Mark J. J. P.; Philipsen, Rick; Hoyng, Carel; Theelen, Thomas; Sánchez, Clara I.

2015-03-01

Age-related Macular Degeneration (AMD) is a common eye disorder with high prevalence in elderly people. The disease mainly affects the central part of the retina, and could ultimately lead to permanent vision loss. Optical Coherence Tomography (OCT) is becoming the standard imaging modality in diagnosis of AMD and the assessment of its progression. However, the evaluation of the obtained volumetric scan is time consuming, expensive and the signs of early AMD are easy to miss. In this paper we propose a classification method to automatically distinguish AMD patients from healthy subjects with high accuracy. The method is based on an unsupervised feature learning approach, and processes the complete image without the need for an accurate pre-segmentation of the retina. The method can be divided in two steps: an unsupervised clustering stage that extracts a set of small descriptive image patches from the training data, and a supervised training stage that uses these patches to create a patch occurrence histogram for every image on which a random forest classifier is trained. Experiments using 384 volume scans show that the proposed method is capable of identifying AMD patients with high accuracy, obtaining an area under the Receiver Operating Curve of 0:984. Our method allows for a quick and reliable assessment of the presence of AMD pathology in OCT volume scans without the need for accurate layer segmentation algorithms.
Rough-Fuzzy Clustering and Unsupervised Feature Selection for Wavelet Based MR Image Segmentation

PubMed Central

Maji, Pradipta; Roy, Shaswati

2015-01-01

Image segmentation is an indispensable process in the visualization of human tissues, particularly during clinical analysis of brain magnetic resonance (MR) images. For many human experts, manual segmentation is a difficult and time consuming task, which makes an automated brain MR image segmentation method desirable. In this regard, this paper presents a new segmentation method for brain MR images, integrating judiciously the merits of rough-fuzzy computing and multiresolution image analysis technique. The proposed method assumes that the major brain tissues, namely, gray matter, white matter, and cerebrospinal fluid from the MR images are considered to have different textural properties. The dyadic wavelet analysis is used to extract the scale-space feature vector for each pixel, while the rough-fuzzy clustering is used to address the uncertainty problem of brain MR image segmentation. An unsupervised feature selection method is introduced, based on maximum relevance-maximum significance criterion, to select relevant and significant textural features for segmentation problem, while the mathematical morphology based skull stripping preprocessing step is proposed to remove the non-cerebral tissues like skull. The performance of the proposed method, along with a comparison with related approaches, is demonstrated on a set of synthetic and real brain MR images using standard validity indices. PMID:25848961

Sparse Coding for N-Gram Feature Extraction and Training for File Fragment Classification

DOE Office of Scientific and Technical Information (OSTI.GOV)

Wang, Felix; Quach, Tu-Thach; Wheeler, Jason

File fragment classification is an important step in the task of file carving in digital forensics. In file carving, files must be reconstructed based on their content as a result of their fragmented storage on disk or in memory. Existing methods for classification of file fragments typically use hand-engineered features such as byte histograms or entropy measures. In this paper, we propose an approach using sparse coding that enables automated feature extraction. Sparse coding, or sparse dictionary learning, is an unsupervised learning algorithm, and is capable of extracting features based simply on how well those features can be used tomore » reconstruct the original data. With respect to file fragments, we learn sparse dictionaries for n-grams, continuous sequences of bytes, of different sizes. These dictionaries may then be used to estimate n-gram frequencies for a given file fragment, but for significantly larger n-gram sizes than are typically found in existing methods which suffer from combinatorial explosion. To demonstrate the capability of our sparse coding approach, we used the resulting features to train standard classifiers such as support vector machines (SVMs) over multiple file types. Experimentally, we achieved significantly better classification results with respect to existing methods, especially when the features were used in supplement to existing hand-engineered features.« less
Sparse Coding for N-Gram Feature Extraction and Training for File Fragment Classification

DOE PAGES

Wang, Felix; Quach, Tu-Thach; Wheeler, Jason; ...

2018-04-05

File fragment classification is an important step in the task of file carving in digital forensics. In file carving, files must be reconstructed based on their content as a result of their fragmented storage on disk or in memory. Existing methods for classification of file fragments typically use hand-engineered features such as byte histograms or entropy measures. In this paper, we propose an approach using sparse coding that enables automated feature extraction. Sparse coding, or sparse dictionary learning, is an unsupervised learning algorithm, and is capable of extracting features based simply on how well those features can be used tomore » reconstruct the original data. With respect to file fragments, we learn sparse dictionaries for n-grams, continuous sequences of bytes, of different sizes. These dictionaries may then be used to estimate n-gram frequencies for a given file fragment, but for significantly larger n-gram sizes than are typically found in existing methods which suffer from combinatorial explosion. To demonstrate the capability of our sparse coding approach, we used the resulting features to train standard classifiers such as support vector machines (SVMs) over multiple file types. Experimentally, we achieved significantly better classification results with respect to existing methods, especially when the features were used in supplement to existing hand-engineered features.« less
Acquiring Information from Wider Scope to Improve Event Extraction

DTIC Science & Technology

2012-05-01

solve all the problems might be hard or even impossible: Word sense disambiguation is already a hard NLP task, and normalizing different expressions...blindfolded woman seen being shot in the head by a hooded militant on a video obtained but not aired by the Arab television station Al-Jazeera. She...imbalance Why are we interested in unsupervised topic features? There is a problem that arises in the evaluation of almost all the tasks in NLP , concerning
Method for indexing and retrieving manufacturing-specific digital imagery based on image content

DOEpatents

Ferrell, Regina K.; Karnowski, Thomas P.; Tobin, Jr., Kenneth W.

2004-06-15

A method for indexing and retrieving manufacturing-specific digital images based on image content comprises three steps. First, at least one feature vector can be extracted from a manufacturing-specific digital image stored in an image database. In particular, each extracted feature vector corresponds to a particular characteristic of the manufacturing-specific digital image, for instance, a digital image modality and overall characteristic, a substrate/background characteristic, and an anomaly/defect characteristic. Notably, the extracting step includes generating a defect mask using a detection process. Second, using an unsupervised clustering method, each extracted feature vector can be indexed in a hierarchical search tree. Third, a manufacturing-specific digital image associated with a feature vector stored in the hierarchicial search tree can be retrieved, wherein the manufacturing-specific digital image has image content comparably related to the image content of the query image. More particularly, can include two data reductions, the first performed based upon a query vector extracted from a query image. Subsequently, a user can select relevant images resulting from the first data reduction. From the selection, a prototype vector can be calculated, from which a second-level data reduction can be performed. The second-level data reduction can result in a subset of feature vectors comparable to the prototype vector, and further comparable to the query vector. An additional fourth step can include managing the hierarchical search tree by substituting a vector average for several redundant feature vectors encapsulated by nodes in the hierarchical search tree.
Automatic extraction of road features in urban environments using dense ALS data

NASA Astrophysics Data System (ADS)

Soilán, Mario; Truong-Hong, Linh; Riveiro, Belén; Laefer, Debra

2018-02-01

This paper describes a methodology that automatically extracts semantic information from urban ALS data for urban parameterization and road network definition. First, building façades are segmented from the ground surface by combining knowledge-based information with both voxel and raster data. Next, heuristic rules and unsupervised learning are applied to the ground surface data to distinguish sidewalk and pavement points as a means for curb detection. Then radiometric information was employed for road marking extraction. Using high-density ALS data from Dublin, Ireland, this fully automatic workflow was able to generate a F-score close to 95% for pavement and sidewalk identification with a resolution of 20 cm and better than 80% for road marking detection.
[Terahertz Spectroscopic Identification with Deep Belief Network].

PubMed

Ma, Shuai; Shen, Tao; Wang, Rui-qi; Lai, Hua; Yu, Zheng-tao

2015-12-01

Feature extraction and classification are the key issues of terahertz spectroscopy identification. Because many materials have no apparent absorption peaks in the terahertz band, it is difficult to extract theirs terahertz spectroscopy feature and identify. To this end, a novel of identify terahertz spectroscopy approach with Deep Belief Network (DBN) was studied in this paper, which combines the advantages of DBN and K-Nearest Neighbors (KNN) classifier. Firstly, cubic spline interpolation and S-G filter were used to normalize the eight kinds of substances (ATP, Acetylcholine Bromide, Bifenthrin, Buprofezin, Carbazole, Bleomycin, Buckminster and Cylotriphosphazene) terahertz transmission spectra in the range of 0.9-6 THz. Secondly, the DBN model was built by two restricted Boltzmann machine (RBM) and then trained layer by layer using unsupervised approach. Instead of using handmade features, the DBN was employed to learn suitable features automatically with raw input data. Finally, a KNN classifier was applied to identify the terahertz spectrum. Experimental results show that using the feature learned by DBN can identify the terahertz spectrum of different substances with the recognition rate of over 90%, which demonstrates that the proposed method can automatically extract the effective features of terahertz spectrum. Furthermore, this KNN classifier was compared with others (BP neural network, SOM neural network and RBF neural network). Comparisons showed that the recognition rate of KNN classifier is better than the other three classifiers. Using the approach that automatic extract terahertz spectrum features by DBN can greatly reduce the workload of feature extraction. This proposed method shows a promising future in the application of identifying the mass terahertz spectroscopy.
Unsupervised Neural Network Quantifies the Cost of Visual Information Processing.

PubMed

Orbán, Levente L; Chartier, Sylvain

2015-01-01

Untrained, "flower-naïve" bumblebees display behavioural preferences when presented with visual properties such as colour, symmetry, spatial frequency and others. Two unsupervised neural networks were implemented to understand the extent to which these models capture elements of bumblebees' unlearned visual preferences towards flower-like visual properties. The computational models, which are variants of Independent Component Analysis and Feature-Extracting Bidirectional Associative Memory, use images of test-patterns that are identical to ones used in behavioural studies. Each model works by decomposing images of floral patterns into meaningful underlying factors. We reconstruct the original floral image using the components and compare the quality of the reconstructed image to the original image. Independent Component Analysis matches behavioural results substantially better across several visual properties. These results are interpreted to support a hypothesis that the temporal and energetic costs of information processing by pollinators served as a selective pressure on floral displays: flowers adapted to pollinators' cognitive constraints.
Physical Human Activity Recognition Using Wearable Sensors.

PubMed

Attal, Ferhat; Mohammed, Samer; Dedabrishvili, Mariam; Chamroukhi, Faicel; Oukhellou, Latifa; Amirat, Yacine

2015-12-11

This paper presents a review of different classification techniques used to recognize human activities from wearable inertial sensor data. Three inertial sensor units were used in this study and were worn by healthy subjects at key points of upper/lower body limbs (chest, right thigh and left ankle). Three main steps describe the activity recognition process: sensors' placement, data pre-processing and data classification. Four supervised classification techniques namely, k-Nearest Neighbor (k-NN), Support Vector Machines (SVM), Gaussian Mixture Models (GMM), and Random Forest (RF) as well as three unsupervised classification techniques namely, k-Means, Gaussian mixture models (GMM) and Hidden Markov Model (HMM), are compared in terms of correct classification rate, F-measure, recall, precision, and specificity. Raw data and extracted features are used separately as inputs of each classifier. The feature selection is performed using a wrapper approach based on the RF algorithm. Based on our experiments, the results obtained show that the k-NN classifier provides the best performance compared to other supervised classification algorithms, whereas the HMM classifier is the one that gives the best results among unsupervised classification algorithms. This comparison highlights which approach gives better performance in both supervised and unsupervised contexts. It should be noted that the obtained results are limited to the context of this study, which concerns the classification of the main daily living human activities using three wearable accelerometers placed at the chest, right shank and left ankle of the subject.
Physical Human Activity Recognition Using Wearable Sensors

PubMed Central

Attal, Ferhat; Mohammed, Samer; Dedabrishvili, Mariam; Chamroukhi, Faicel; Oukhellou, Latifa; Amirat, Yacine

2015-01-01

This paper presents a review of different classification techniques used to recognize human activities from wearable inertial sensor data. Three inertial sensor units were used in this study and were worn by healthy subjects at key points of upper/lower body limbs (chest, right thigh and left ankle). Three main steps describe the activity recognition process: sensors’ placement, data pre-processing and data classification. Four supervised classification techniques namely, k-Nearest Neighbor (k-NN), Support Vector Machines (SVM), Gaussian Mixture Models (GMM), and Random Forest (RF) as well as three unsupervised classification techniques namely, k-Means, Gaussian mixture models (GMM) and Hidden Markov Model (HMM), are compared in terms of correct classification rate, F-measure, recall, precision, and specificity. Raw data and extracted features are used separately as inputs of each classifier. The feature selection is performed using a wrapper approach based on the RF algorithm. Based on our experiments, the results obtained show that the k-NN classifier provides the best performance compared to other supervised classification algorithms, whereas the HMM classifier is the one that gives the best results among unsupervised classification algorithms. This comparison highlights which approach gives better performance in both supervised and unsupervised contexts. It should be noted that the obtained results are limited to the context of this study, which concerns the classification of the main daily living human activities using three wearable accelerometers placed at the chest, right shank and left ankle of the subject. PMID:26690450
A semantic model for multimodal data mining in healthcare information systems.

PubMed

Iakovidis, Dimitris; Smailis, Christos

2012-01-01

Electronic health records (EHRs) are representative examples of multimodal/multisource data collections; including measurements, images and free texts. The diversity of such information sources and the increasing amounts of medical data produced by healthcare institutes annually, pose significant challenges in data mining. In this paper we present a novel semantic model that describes knowledge extracted from the lowest-level of a data mining process, where information is represented by multiple features i.e. measurements or numerical descriptors extracted from measurements, images, texts or other medical data, forming multidimensional feature spaces. Knowledge collected by manual annotation or extracted by unsupervised data mining from one or more feature spaces is modeled through generalized qualitative spatial semantics. This model enables a unified representation of knowledge across multimodal data repositories. It contributes to bridging the semantic gap, by enabling direct links between low-level features and higher-level concepts e.g. describing body parts, anatomies and pathological findings. The proposed model has been developed in web ontology language based on description logics (OWL-DL) and can be applied to a variety of data mining tasks in medical informatics. It utility is demonstrated for automatic annotation of medical data.
Learning representation hierarchies by sharing visual features: a computational investigation of Persian character recognition with unsupervised deep learning.

PubMed

Sadeghi, Zahra; Testolin, Alberto

2017-08-01

In humans, efficient recognition of written symbols is thought to rely on a hierarchical processing system, where simple features are progressively combined into more abstract, high-level representations. Here, we present a computational model of Persian character recognition based on deep belief networks, where increasingly more complex visual features emerge in a completely unsupervised manner by fitting a hierarchical generative model to the sensory data. Crucially, high-level internal representations emerging from unsupervised deep learning can be easily read out by a linear classifier, achieving state-of-the-art recognition accuracy. Furthermore, we tested the hypothesis that handwritten digits and letters share many common visual features: A generative model that captures the statistical structure of the letters distribution should therefore also support the recognition of written digits. To this aim, deep networks trained on Persian letters were used to build high-level representations of Persian digits, which were indeed read out with high accuracy. Our simulations show that complex visual features, such as those mediating the identification of Persian symbols, can emerge from unsupervised learning in multilayered neural networks and can support knowledge transfer across related domains.
Weakly supervised visual dictionary learning by harnessing image attributes.

PubMed

Gao, Yue; Ji, Rongrong; Liu, Wei; Dai, Qionghai; Hua, Gang

2014-12-01

Bag-of-features (BoFs) representation has been extensively applied to deal with various computer vision applications. To extract discriminative and descriptive BoF, one important step is to learn a good dictionary to minimize the quantization loss between local features and codewords. While most existing visual dictionary learning approaches are engaged with unsupervised feature quantization, the latest trend has turned to supervised learning by harnessing the semantic labels of images or regions. However, such labels are typically too expensive to acquire, which restricts the scalability of supervised dictionary learning approaches. In this paper, we propose to leverage image attributes to weakly supervise the dictionary learning procedure without requiring any actual labels. As a key contribution, our approach establishes a generative hidden Markov random field (HMRF), which models the quantized codewords as the observed states and the image attributes as the hidden states, respectively. Dictionary learning is then performed by supervised grouping the observed states, where the supervised information is stemmed from the hidden states of the HMRF. In such a way, the proposed dictionary learning approach incorporates the image attributes to learn a semantic-preserving BoF representation without any genuine supervision. Experiments in large-scale image retrieval and classification tasks corroborate that our approach significantly outperforms the state-of-the-art unsupervised dictionary learning approaches.
Adaptive Water Sampling based on Unsupervised Clustering

NASA Astrophysics Data System (ADS)

Py, F.; Ryan, J.; Rajan, K.; Sherman, A.; Bird, L.; Fox, M.; Long, D.

2007-12-01

Autonomous Underwater Vehicles (AUVs) are widely used for oceanographic surveys, during which data is collected from a number of on-board sensors. Engineers and scientists at MBARI have extended this approach by developing a water sampler specialy for the AUV, which can sample a specific patch of water at a specific time. The sampler, named the Gulper, captures 2 liters of seawater in less than 2 seconds on a 21" MBARI Odyssey AUV. Each sample chamber of the Gulper is filled with seawater through a one-way valve, which protrudes through the fairing of the AUV. This new kind of device raises a new problem: when to trigger the gulper autonomously? For example, scientists interested in studying the mobilization and transport of shelf sediments would like to detect intermediate nepheloïd layers (INLs). To be able to detect this phenomenon we need to extract a model based on AUV sensors that can detect this feature in-situ. The formation of such a model is not obvious as identification of this feature is generally based on data from multiple sensors. We have developed an unsupervised data clustering technique to extract the different features which will then be used for on-board classification and triggering of the Gulper. We use a three phase approach: 1) use data from past missions to learn the different classes of data from sensor inputs. The clustering algorithm will then extract the set of features that can be distinguished within this large data set. 2) Scientists on shore then identify these features and point out which correspond to those of interest (e.g. nepheloïd layer, upwelling material etc) 3) Embed the corresponding classifier into the AUV control system to indicate the most probable feature of the water depending on sensory input. The triggering algorithm looks to this result and triggers the Gulper if the classifier indicates that we are within the feature of interest with a predetermined threshold of confidence. We have deployed this method of online classification and sampling based on AUV depth and HOBI Labs Hydroscat-2 sensor data. Using approximately 20,000 data samples the clustering algorithm generated 14 clusters with one identified as corresponding to a nepheloïd layer. We demonstrate that such a technique can be used to reliably and efficiently sample water based on multiple sources of data in real-time.
Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features.

PubMed

Nikfarjam, Azadeh; Sarker, Abeed; O'Connor, Karen; Ginn, Rachel; Gonzalez, Graciela

2015-05-01

Social media is becoming increasingly popular as a platform for sharing personal health-related information. This information can be utilized for public health monitoring tasks, particularly for pharmacovigilance, via the use of natural language processing (NLP) techniques. However, the language in social media is highly informal, and user-expressed medical concepts are often nontechnical, descriptive, and challenging to extract. There has been limited progress in addressing these challenges, and thus far, advanced machine learning-based NLP techniques have been underutilized. Our objective is to design a machine learning-based approach to extract mentions of adverse drug reactions (ADRs) from highly informal text in social media. We introduce ADRMine, a machine learning-based concept extraction system that uses conditional random fields (CRFs). ADRMine utilizes a variety of features, including a novel feature for modeling words' semantic similarities. The similarities are modeled by clustering words based on unsupervised, pretrained word representation vectors (embeddings) generated from unlabeled user posts in social media using a deep learning technique. ADRMine outperforms several strong baseline systems in the ADR extraction task by achieving an F-measure of 0.82. Feature analysis demonstrates that the proposed word cluster features significantly improve extraction performance. It is possible to extract complex medical concepts, with relatively high performance, from informal, user-generated content. Our approach is particularly scalable, suitable for social media mining, as it relies on large volumes of unlabeled data, thus diminishing the need for large, annotated training data sets. © The Author 2015. Published by Oxford University Press on behalf of the American Medical Informatics Association.
Space-Based Identification of Archaeological Illegal Excavations and a New Automatic Method for Looting Feature Extraction in Desert Areas

NASA Astrophysics Data System (ADS)

Lasaponara, Rosa; Masini, Nicola

2018-06-01

The identification and quantification of disturbance of archaeological sites has been generally approached by visual inspection of optical aerial or satellite pictures. In this paper, we briefly summarize the state of the art of the traditionally satellite-based approaches for looting identification and propose a new automatic method for archaeological looting feature extraction approach (ALFEA). It is based on three steps: the enhancement using spatial autocorrelation, unsupervised classification, and segmentation. ALFEA has been applied to Google Earth images of two test areas, selected in desert environs in Syria (Dura Europos), and in Peru (Cahuachi-Nasca). The reliability of ALFEA was assessed through field surveys in Peru and visual inspection for the Syrian case study. Results from the evaluation procedure showed satisfactory performance from both of the two analysed test cases with a rate of success higher than 90%.
Knowledge discovery by accuracy maximization

PubMed Central

Cacciatore, Stefano; Luchinat, Claudio; Tenori, Leonardo

2014-01-01

Here we describe KODAMA (knowledge discovery by accuracy maximization), an unsupervised and semisupervised learning algorithm that performs feature extraction from noisy and high-dimensional data. Unlike other data mining methods, the peculiarity of KODAMA is that it is driven by an integrated procedure of cross-validation of the results. The discovery of a local manifold’s topology is led by a classifier through a Monte Carlo procedure of maximization of cross-validated predictive accuracy. Briefly, our approach differs from previous methods in that it has an integrated procedure of validation of the results. In this way, the method ensures the highest robustness of the obtained solution. This robustness is demonstrated on experimental datasets of gene expression and metabolomics, where KODAMA compares favorably with other existing feature extraction methods. KODAMA is then applied to an astronomical dataset, revealing unexpected features. Interesting and not easily predictable features are also found in the analysis of the State of the Union speeches by American presidents: KODAMA reveals an abrupt linguistic transition sharply separating all post-Reagan from all pre-Reagan speeches. The transition occurs during Reagan’s presidency and not from its beginning. PMID:24706821
EEG-based driver fatigue detection using hybrid deep generic model.

PubMed

Phyo Phyo San; Sai Ho Ling; Rifai Chai; Tran, Yvonne; Craig, Ashley; Hung Nguyen

2016-08-01

Classification of electroencephalography (EEG)-based application is one of the important process for biomedical engineering. Driver fatigue is a major case of traffic accidents worldwide and considered as a significant problem in recent decades. In this paper, a hybrid deep generic model (DGM)-based support vector machine is proposed for accurate detection of driver fatigue. Traditionally, a probabilistic DGM with deep architecture is quite good at learning invariant features, but it is not always optimal for classification due to its trainable parameters are in the middle layer. Alternatively, Support Vector Machine (SVM) itself is unable to learn complicated invariance, but produces good decision surface when applied to well-behaved features. Consolidating unsupervised high-level feature extraction techniques, DGM and SVM classification makes the integrated framework stronger and enhance mutually in feature extraction and classification. The experimental results showed that the proposed DBN-based driver fatigue monitoring system achieves better testing accuracy of 73.29 % with 91.10 % sensitivity and 55.48 % specificity. In short, the proposed hybrid DGM-based SVM is an effective method for the detection of driver fatigue in EEG.
Unsupervised Pattern Classifier for Abnormality-Scaling of Vibration Features for Helicopter Gearbox Fault Diagnosis

NASA Technical Reports Server (NTRS)

Jammu, Vinay B.; Danai, Kourosh; Lewicki, David G.

1996-01-01

A new unsupervised pattern classifier is introduced for on-line detection of abnormality in features of vibration that are used for fault diagnosis of helicopter gearboxes. This classifier compares vibration features with their respective normal values and assigns them a value in (0, 1) to reflect their degree of abnormality. Therefore, the salient feature of this classifier is that it does not require feature values associated with faulty cases to identify abnormality. In order to cope with noise and changes in the operating conditions, an adaptation algorithm is incorporated that continually updates the normal values of the features. The proposed classifier is tested using experimental vibration features obtained from an OH-58A main rotor gearbox. The overall performance of this classifier is then evaluated by integrating the abnormality-scaled features for detection of faults. The fault detection results indicate that the performance of this classifier is comparable to the leading unsupervised neural networks: Kohonen's Feature Mapping and Adaptive Resonance Theory (AR72). This is significant considering that the independence of this classifier from fault-related features makes it uniquely suited to abnormality-scaling of vibration features for fault diagnosis.
An Example of Unsupervised Networks Kohonen's Self-Organizing Feature Map

NASA Technical Reports Server (NTRS)

Niebur, Dagmar

1995-01-01

Kohonen's self-organizing feature map belongs to a class of unsupervised artificial neural network commonly referred to as topographic maps. It serves two purposes, the quantization and dimensionality reduction of date. A short description of its history and its biological context is given. We show that the inherent classification properties of the feature map make it a suitable candidate for solving the classification task in power system areas like load forecasting, fault diagnosis and security assessment.
A single-layer network unsupervised feature learning method for white matter hyperintensity segmentation

NASA Astrophysics Data System (ADS)

Vijverberg, Koen; Ghafoorian, Mohsen; van Uden, Inge W. M.; de Leeuw, Frank-Erik; Platel, Bram; Heskes, Tom

2016-03-01

Cerebral small vessel disease (SVD) is a disorder frequently found among the old people and is associated with deterioration in cognitive performance, parkinsonism, motor and mood impairments. White matter hyperintensities (WMH) as well as lacunes, microbleeds and subcortical brain atrophy are part of the spectrum of image findings, related to SVD. Accurate segmentation of WMHs is important for prognosis and diagnosis of multiple neurological disorders such as MS and SVD. Almost all of the published (semi-)automated WMH detection models employ multiple complex hand-crafted features, which require in-depth domain knowledge. In this paper we propose to apply a single-layer network unsupervised feature learning (USFL) method to avoid hand-crafted features, but rather to automatically learn a more efficient set of features. Experimental results show that a computer aided detection system with a USFL system outperforms a hand-crafted approach. Moreover, since the two feature sets have complementary properties, a hybrid system that makes use of both hand-crafted and unsupervised learned features, shows a significant performance boost compared to each system separately, getting close to the performance of an independent human expert.

Clinical Named Entity Recognition Using Deep Learning Models.

PubMed

Wu, Yonghui; Jiang, Min; Xu, Jun; Zhi, Degui; Xu, Hua

2017-01-01

Clinical Named Entity Recognition (NER) is a critical natural language processing (NLP) task to extract important concepts (named entities) from clinical narratives. Researchers have extensively investigated machine learning models for clinical NER. Recently, there have been increasing efforts to apply deep learning models to improve the performance of current clinical NER systems. This study examined two popular deep learning architectures, the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN), to extract concepts from clinical texts. We compared the two deep neural network architectures with three baseline Conditional Random Fields (CRFs) models and two state-of-the-art clinical NER systems using the i2b2 2010 clinical concept extraction corpus. The evaluation results showed that the RNN model trained with the word embeddings achieved a new state-of-the- art performance (a strict F1 score of 85.94%) for the defined clinical NER task, outperforming the best-reported system that used both manually defined and unsupervised learning features. This study demonstrates the advantage of using deep neural network architectures for clinical concept extraction, including distributed feature representation, automatic feature learning, and long-term dependencies capture. This is one of the first studies to compare the two widely used deep learning models and demonstrate the superior performance of the RNN model for clinical NER.
Clinical Named Entity Recognition Using Deep Learning Models

PubMed Central

Wu, Yonghui; Jiang, Min; Xu, Jun; Zhi, Degui; Xu, Hua

2017-01-01

Clinical Named Entity Recognition (NER) is a critical natural language processing (NLP) task to extract important concepts (named entities) from clinical narratives. Researchers have extensively investigated machine learning models for clinical NER. Recently, there have been increasing efforts to apply deep learning models to improve the performance of current clinical NER systems. This study examined two popular deep learning architectures, the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN), to extract concepts from clinical texts. We compared the two deep neural network architectures with three baseline Conditional Random Fields (CRFs) models and two state-of-the-art clinical NER systems using the i2b2 2010 clinical concept extraction corpus. The evaluation results showed that the RNN model trained with the word embeddings achieved a new state-of-the- art performance (a strict F1 score of 85.94%) for the defined clinical NER task, outperforming the best-reported system that used both manually defined and unsupervised learning features. This study demonstrates the advantage of using deep neural network architectures for clinical concept extraction, including distributed feature representation, automatic feature learning, and long-term dependencies capture. This is one of the first studies to compare the two widely used deep learning models and demonstrate the superior performance of the RNN model for clinical NER. PMID:29854252
Image segmentation using fuzzy LVQ clustering networks

NASA Technical Reports Server (NTRS)

Tsao, Eric Chen-Kuo; Bezdek, James C.; Pal, Nikhil R.

1992-01-01

In this note we formulate image segmentation as a clustering problem. Feature vectors extracted from a raw image are clustered into subregions, thereby segmenting the image. A fuzzy generalization of a Kohonen learning vector quantization (LVQ) which integrates the Fuzzy c-Means (FCM) model with the learning rate and updating strategies of the LVQ is used for this task. This network, which segments images in an unsupervised manner, is thus related to the FCM optimization problem. Numerical examples on photographic and magnetic resonance images are given to illustrate this approach to image segmentation.
Improved Anomaly Detection using Integrated Supervised and Unsupervised Processing

NASA Astrophysics Data System (ADS)

Hunt, B.; Sheppard, D. G.; Wetterer, C. J.

There are two broad technologies of signal processing applicable to space object feature identification using nonresolved imagery: supervised processing analyzes a large set of data for common characteristics that can be then used to identify, transform, and extract information from new data taken of the same given class (e.g. support vector machine); unsupervised processing utilizes detailed physics-based models that generate comparison data that can then be used to estimate parameters presumed to be governed by the same models (e.g. estimation filters). Both processes have been used in non-resolved space object identification and yield similar results yet arrived at using vastly different processes. The goal of integrating the results of the two is to seek to achieve an even greater performance by building on the process diversity. Specifically, both supervised processing and unsupervised processing will jointly operate on the analysis of brightness (radiometric flux intensity) measurements reflected by space objects and observed by a ground station to determine whether a particular day conforms to a nominal operating mode (as determined from a training set) or exhibits anomalous behavior where a particular parameter (e.g. attitude, solar panel articulation angle) has changed in some way. It is demonstrated in a variety of different scenarios that the integrated process achieves a greater performance than each of the separate processes alone.
Information processing of motion in facial expression and the geometry of dynamical systems

NASA Astrophysics Data System (ADS)

Assadi, Amir H.; Eghbalnia, Hamid; McMenamin, Brenton W.

2005-01-01

An interesting problem in analysis of video data concerns design of algorithms that detect perceptually significant features in an unsupervised manner, for instance methods of machine learning for automatic classification of human expression. A geometric formulation of this genre of problems could be modeled with help of perceptual psychology. In this article, we outline one approach for a special case where video segments are to be classified according to expression of emotion or other similar facial motions. The encoding of realistic facial motions that convey expression of emotions for a particular person P forms a parameter space XP whose study reveals the "objective geometry" for the problem of unsupervised feature detection from video. The geometric features and discrete representation of the space XP are independent of subjective evaluations by observers. While the "subjective geometry" of XP varies from observer to observer, levels of sensitivity and variation in perception of facial expressions appear to share a certain level of universality among members of similar cultures. Therefore, statistical geometry of invariants of XP for a sample of population could provide effective algorithms for extraction of such features. In cases where frequency of events is sufficiently large in the sample data, a suitable framework could be provided to facilitate the information-theoretic organization and study of statistical invariants of such features. This article provides a general approach to encode motion in terms of a particular genre of dynamical systems and the geometry of their flow. An example is provided to illustrate the general theory.
Hierarchical Adaptive Means (HAM) clustering for hardware-efficient, unsupervised and real-time spike sorting.

PubMed

Paraskevopoulou, Sivylla E; Wu, Di; Eftekhar, Amir; Constandinou, Timothy G

2014-09-30

This work presents a novel unsupervised algorithm for real-time adaptive clustering of neural spike data (spike sorting). The proposed Hierarchical Adaptive Means (HAM) clustering method combines centroid-based clustering with hierarchical cluster connectivity to classify incoming spikes using groups of clusters. It is described how the proposed method can adaptively track the incoming spike data without requiring any past history, iteration or training and autonomously determines the number of spike classes. Its performance (classification accuracy) has been tested using multiple datasets (both simulated and recorded) achieving a near-identical accuracy compared to k-means (using 10-iterations and provided with the number of spike classes). Also, its robustness in applying to different feature extraction methods has been demonstrated by achieving classification accuracies above 80% across multiple datasets. Last but crucially, its low complexity, that has been quantified through both memory and computation requirements makes this method hugely attractive for future hardware implementation. Copyright © 2014 Elsevier B.V. All rights reserved.
Enhancing interpretability of automatically extracted machine learning features: application to a RBM-Random Forest system on brain lesion segmentation.

PubMed

Pereira, Sérgio; Meier, Raphael; McKinley, Richard; Wiest, Roland; Alves, Victor; Silva, Carlos A; Reyes, Mauricio

2018-02-01

Machine learning systems are achieving better performances at the cost of becoming increasingly complex. However, because of that, they become less interpretable, which may cause some distrust by the end-user of the system. This is especially important as these systems are pervasively being introduced to critical domains, such as the medical field. Representation Learning techniques are general methods for automatic feature computation. Nevertheless, these techniques are regarded as uninterpretable "black boxes". In this paper, we propose a methodology to enhance the interpretability of automatically extracted machine learning features. The proposed system is composed of a Restricted Boltzmann Machine for unsupervised feature learning, and a Random Forest classifier, which are combined to jointly consider existing correlations between imaging data, features, and target variables. We define two levels of interpretation: global and local. The former is devoted to understanding if the system learned the relevant relations in the data correctly, while the later is focused on predictions performed on a voxel- and patient-level. In addition, we propose a novel feature importance strategy that considers both imaging data and target variables, and we demonstrate the ability of the approach to leverage the interpretability of the obtained representation for the task at hand. We evaluated the proposed methodology in brain tumor segmentation and penumbra estimation in ischemic stroke lesions. We show the ability of the proposed methodology to unveil information regarding relationships between imaging modalities and extracted features and their usefulness for the task at hand. In both clinical scenarios, we demonstrate that the proposed methodology enhances the interpretability of automatically learned features, highlighting specific learning patterns that resemble how an expert extracts relevant data from medical images. Copyright © 2017 Elsevier B.V. All rights reserved.
IMMAN: free software for information theory-based chemometric analysis.

PubMed

Urias, Ricardo W Pino; Barigye, Stephen J; Marrero-Ponce, Yovani; García-Jacas, César R; Valdes-Martiní, José R; Perez-Gimenez, Facundo

2015-05-01

The features and theoretical background of a new and free computational program for chemometric analysis denominated IMMAN (acronym for Information theory-based CheMoMetrics ANalysis) are presented. This is multi-platform software developed in the Java programming language, designed with a remarkably user-friendly graphical interface for the computation of a collection of information-theoretic functions adapted for rank-based unsupervised and supervised feature selection tasks. A total of 20 feature selection parameters are presented, with the unsupervised and supervised frameworks represented by 10 approaches in each case. Several information-theoretic parameters traditionally used as molecular descriptors (MDs) are adapted for use as unsupervised rank-based feature selection methods. On the other hand, a generalization scheme for the previously defined differential Shannon's entropy is discussed, as well as the introduction of Jeffreys information measure for supervised feature selection. Moreover, well-known information-theoretic feature selection parameters, such as information gain, gain ratio, and symmetrical uncertainty are incorporated to the IMMAN software ( http://mobiosd-hub.com/imman-soft/ ), following an equal-interval discretization approach. IMMAN offers data pre-processing functionalities, such as missing values processing, dataset partitioning, and browsing. Moreover, single parameter or ensemble (multi-criteria) ranking options are provided. Consequently, this software is suitable for tasks like dimensionality reduction, feature ranking, as well as comparative diversity analysis of data matrices. Simple examples of applications performed with this program are presented. A comparative study between IMMAN and WEKA feature selection tools using the Arcene dataset was performed, demonstrating similar behavior. In addition, it is revealed that the use of IMMAN unsupervised feature selection methods improves the performance of both IMMAN and WEKA supervised algorithms. Graphic representation for Shannon's distribution of MD calculating software.
Unsupervised Extraction of Diagnosis Codes from EMRs Using Knowledge-Based and Extractive Text Summarization Techniques

PubMed Central

Kavuluru, Ramakanth; Han, Sifei; Harris, Daniel

2017-01-01

Diagnosis codes are extracted from medical records for billing and reimbursement and for secondary uses such as quality control and cohort identification. In the US, these codes come from the standard terminology ICD-9-CM derived from the international classification of diseases (ICD). ICD-9 codes are generally extracted by trained human coders by reading all artifacts available in a patient’s medical record following specific coding guidelines. To assist coders in this manual process, this paper proposes an unsupervised ensemble approach to automatically extract ICD-9 diagnosis codes from textual narratives included in electronic medical records (EMRs). Earlier attempts on automatic extraction focused on individual documents such as radiology reports and discharge summaries. Here we use a more realistic dataset and extract ICD-9 codes from EMRs of 1000 inpatient visits at the University of Kentucky Medical Center. Using named entity recognition (NER), graph-based concept-mapping of medical concepts, and extractive text summarization techniques, we achieve an example based average recall of 0.42 with average precision 0.47; compared with a baseline of using only NER, we notice a 12% improvement in recall with the graph-based approach and a 7% improvement in precision using the extractive text summarization approach. Although diagnosis codes are complex concepts often expressed in text with significant long range non-local dependencies, our present work shows the potential of unsupervised methods in extracting a portion of codes. As such, our findings are especially relevant for code extraction tasks where obtaining large amounts of training data is difficult. PMID:28748227
A proto-architecture for innate directionally selective visual maps.

PubMed

Adams, Samantha V; Harris, Chris M

2014-01-01

Self-organizing artificial neural networks are a popular tool for studying visual system development, in particular the cortical feature maps present in real systems that represent properties such as ocular dominance (OD), orientation-selectivity (OR) and direction selectivity (DS). They are also potentially useful in artificial systems, for example robotics, where the ability to extract and learn features from the environment in an unsupervised way is important. In this computational study we explore a DS map that is already latent in a simple artificial network. This latent selectivity arises purely from the cortical architecture without any explicit coding for DS and prior to any self-organising process facilitated by spontaneous activity or training. We find DS maps with local patchy regions that exhibit features similar to maps derived experimentally and from previous modeling studies. We explore the consequences of changes to the afferent and lateral connectivity to establish the key features of this proto-architecture that support DS.
Unsupervised Deep Learning Applied to Breast Density Segmentation and Mammographic Risk Scoring.

PubMed

Kallenberg, Michiel; Petersen, Kersten; Nielsen, Mads; Ng, Andrew Y; Pengfei Diao; Igel, Christian; Vachon, Celine M; Holland, Katharina; Winkel, Rikke Rass; Karssemeijer, Nico; Lillholm, Martin

2016-05-01

Mammographic risk scoring has commonly been automated by extracting a set of handcrafted features from mammograms, and relating the responses directly or indirectly to breast cancer risk. We present a method that learns a feature hierarchy from unlabeled data. When the learned features are used as the input to a simple classifier, two different tasks can be addressed: i) breast density segmentation, and ii) scoring of mammographic texture. The proposed model learns features at multiple scales. To control the models capacity a novel sparsity regularizer is introduced that incorporates both lifetime and population sparsity. We evaluated our method on three different clinical datasets. Our state-of-the-art results show that the learned breast density scores have a very strong positive relationship with manual ones, and that the learned texture scores are predictive of breast cancer. The model is easy to apply and generalizes to many other segmentation and scoring problems.
Prediction of enhancer-promoter interactions via natural language processing.

PubMed

Zeng, Wanwen; Wu, Mengmeng; Jiang, Rui

2018-05-09

Precise identification of three-dimensional genome organization, especially enhancer-promoter interactions (EPIs), is important to deciphering gene regulation, cell differentiation and disease mechanisms. Currently, it is a challenging task to distinguish true interactions from other nearby non-interacting ones since the power of traditional experimental methods is limited due to low resolution or low throughput. We propose a novel computational framework EP2vec to assay three-dimensional genomic interactions. We first extract sequence embedding features, defined as fixed-length vector representations learned from variable-length sequences using an unsupervised deep learning method in natural language processing. Then, we train a classifier to predict EPIs using the learned representations in supervised way. Experimental results demonstrate that EP2vec obtains F1 scores ranging from 0.841~ 0.933 on different datasets, which outperforms existing methods. We prove the robustness of sequence embedding features by carrying out sensitivity analysis. Besides, we identify motifs that represent cell line-specific information through analysis of the learned sequence embedding features by adopting attention mechanism. Last, we show that even superior performance with F1 scores 0.889~ 0.940 can be achieved by combining sequence embedding features and experimental features. EP2vec sheds light on feature extraction for DNA sequences of arbitrary lengths and provides a powerful approach for EPIs identification.
Slow feature analysis: unsupervised learning of invariances.

PubMed

Wiskott, Laurenz; Sejnowski, Terrence J

2002-04-01

Invariant features of temporally varying signals are useful for analysis and classification. Slow feature analysis (SFA) is a new method for learning invariant or slowly varying features from a vectorial input signal. It is based on a nonlinear expansion of the input signal and application of principal component analysis to this expanded signal and its time derivative. It is guaranteed to find the optimal solution within a family of functions directly and can learn to extract a large number of decorrelated features, which are ordered by their degree of invariance. SFA can be applied hierarchically to process high-dimensional input signals and extract complex features. SFA is applied first to complex cell tuning properties based on simple cell output, including disparity and motion. Then more complicated input-output functions are learned by repeated application of SFA. Finally, a hierarchical network of SFA modules is presented as a simple model of the visual system. The same unstructured network can learn translation, size, rotation, contrast, or, to a lesser degree, illumination invariance for one-dimensional objects, depending on only the training stimulus. Surprisingly, only a few training objects suffice to achieve good generalization to new objects. The generated representation is suitable for object recognition. Performance degrades if the network is trained to learn multiple invariances simultaneously.
Batch process fault detection and identification based on discriminant global preserving kernel slow feature analysis.

PubMed

Zhang, Hanyuan; Tian, Xuemin; Deng, Xiaogang; Cao, Yuping

2018-05-16

As an attractive nonlinear dynamic data analysis tool, global preserving kernel slow feature analysis (GKSFA) has achieved great success in extracting the high nonlinearity and inherently time-varying dynamics of batch process. However, GKSFA is an unsupervised feature extraction method and lacks the ability to utilize batch process class label information, which may not offer the most effective means for dealing with batch process monitoring. To overcome this problem, we propose a novel batch process monitoring method based on the modified GKSFA, referred to as discriminant global preserving kernel slow feature analysis (DGKSFA), by closely integrating discriminant analysis and GKSFA. The proposed DGKSFA method can extract discriminant feature of batch process as well as preserve global and local geometrical structure information of observed data. For the purpose of fault detection, a monitoring statistic is constructed based on the distance between the optimal kernel feature vectors of test data and normal data. To tackle the challenging issue of nonlinear fault variable identification, a new nonlinear contribution plot method is also developed to help identifying the fault variable after a fault is detected, which is derived from the idea of variable pseudo-sample trajectory projection in DGKSFA nonlinear biplot. Simulation results conducted on a numerical nonlinear dynamic system and the benchmark fed-batch penicillin fermentation process demonstrate that the proposed process monitoring and fault diagnosis approach can effectively detect fault and distinguish fault variables from normal variables. Copyright © 2018 ISA. Published by Elsevier Ltd. All rights reserved.
Visual texture perception via graph-based semi-supervised learning

NASA Astrophysics Data System (ADS)

Zhang, Qin; Dong, Junyu; Zhong, Guoqiang

2018-04-01

Perceptual features, for example direction, contrast and repetitiveness, are important visual factors for human to perceive a texture. However, it needs to perform psychophysical experiment to quantify these perceptual features' scale, which requires a large amount of human labor and time. This paper focuses on the task of obtaining perceptual features' scale of textures by small number of textures with perceptual scales through a rating psychophysical experiment (what we call labeled textures) and a mass of unlabeled textures. This is the scenario that the semi-supervised learning is naturally suitable for. This is meaningful for texture perception research, and really helpful for the perceptual texture database expansion. A graph-based semi-supervised learning method called random multi-graphs, RMG for short, is proposed to deal with this task. We evaluate different kinds of features including LBP, Gabor, and a kind of unsupervised deep features extracted by a PCA-based deep network. The experimental results show that our method can achieve satisfactory effects no matter what kind of texture features are used.
Extraction of features from medical images using a modular neural network approach that relies on learning by sample

NASA Astrophysics Data System (ADS)

Brahmi, Djamel; Serruys, Camille; Cassoux, Nathalie; Giron, Alain; Triller, Raoul; Lehoang, Phuc; Fertil, Bernard

2000-06-01

Medical images provide experienced physicians with meaningful visual stimuli but their features are frequently hard to decipher. The development of a computational model to mimic physicians' expertise is a demanding task, especially if a significant and sophisticated preprocessing of images is required. Learning from well-expertised images may be a more convenient approach, inasmuch a large and representative bunch of samples is available. A four-stage approach has been designed, which combines image sub-sampling with unsupervised image coding, supervised classification and image reconstruction in order to directly extract medical expertise from raw images. The system has been applied (1) to the detection of some features related to the diagnosis of black tumors of skin (a classification issue) and (2) to the detection of virus-infected and healthy areas in retina angiography in order to locate precisely the border between them and characterize the evolution of infection. For reasonably balanced training sets, we are able to obtained about 90% correct classification of features (black tumors). Boundaries generated by our system mimic reproducibility of hand-outlines drawn by experts (segmentation of virus-infected area).
Quantitative radiomic profiling of glioblastoma represents transcriptomic expression.

PubMed

Kong, Doo-Sik; Kim, Junhyung; Ryu, Gyuha; You, Hye-Jin; Sung, Joon Kyung; Han, Yong Hee; Shin, Hye-Mi; Lee, In-Hee; Kim, Sung-Tae; Park, Chul-Kee; Choi, Seung Hong; Choi, Jeong Won; Seol, Ho Jun; Lee, Jung-Il; Nam, Do-Hyun

2018-01-19

Quantitative imaging biomarkers have increasingly emerged in the field of research utilizing available imaging modalities. We aimed to identify good surrogate radiomic features that can represent genetic changes of tumors, thereby establishing noninvasive means for predicting treatment outcome. From May 2012 to June 2014, we retrospectively identified 65 patients with treatment-naïve glioblastoma with available clinical information from the Samsung Medical Center data registry. Preoperative MR imaging data were obtained for all 65 patients with primary glioblastoma. A total of 82 imaging features including first-order statistics, volume, and size features, were semi-automatically extracted from structural and physiologic images such as apparent diffusion coefficient and perfusion images. Using commercially available software, NordicICE, we performed quantitative imaging analysis and collected the dataset composed of radiophenotypic parameters. Unsupervised clustering methods revealed that the radiophenotypic dataset was composed of three clusters. Each cluster represented a distinct molecular classification of glioblastoma; classical type, proneural and neural types, and mesenchymal type. These clusters also reflected differential clinical outcomes. We found that extracted imaging signatures does not represent copy number variation and somatic mutation. Quantitative radiomic features provide a potential evidence to predict molecular phenotype and treatment outcome. Radiomic profiles represents transcriptomic phenotypes more well.
Psoriasis image representation using patch-based dictionary learning for erythema severity scoring.

PubMed

George, Yasmeen; Aldeen, Mohammad; Garnavi, Rahil

2018-06-01

Psoriasis is a chronic skin disease which can be life-threatening. Accurate severity scoring helps dermatologists to decide on the treatment. In this paper, we present a semi-supervised computer-aided system for automatic erythema severity scoring in psoriasis images. Firstly, the unsupervised stage includes a novel image representation method. We construct a dictionary, which is then used in the sparse representation for local feature extraction. To acquire the final image representation vector, an aggregation method is exploited over the local features. Secondly, the supervised phase is where various multi-class machine learning (ML) classifiers are trained for erythema severity scoring. Finally, we compare the proposed system with two popular unsupervised feature extractor methods, namely: bag of visual words model (BoVWs) and AlexNet pretrained model. Root mean square error (RMSE) and F1 score are used as performance measures for the learned dictionaries and the trained ML models, respectively. A psoriasis image set consisting of 676 images, is used in this study. Experimental results demonstrate that the use of the proposed procedure can provide a setup where erythema scoring is accurate and consistent. Also, it is revealed that dictionaries with large number of atoms and small patch sizes yield the best representative erythema severity features. Further, random forest (RF) outperforms other classifiers with F1 score 0.71, followed by support vector machine (SVM) and boosting with 0.66 and 0.64 scores, respectively. Furthermore, the conducted comparative studies confirm the effectiveness of the proposed approach with improvement of 9% and 12% over BoVWs and AlexNet based features, respectively. Crown Copyright © 2018. Published by Elsevier Ltd. All rights reserved.
Unsupervised classification of operator workload from brain signals.

PubMed

Schultze-Kraft, Matthias; Dähne, Sven; Gugler, Manfred; Curio, Gabriel; Blankertz, Benjamin

2016-06-01

In this study we aimed for the classification of operator workload as it is expected in many real-life workplace environments. We explored brain-signal based workload predictors that differ with respect to the level of label information required for training, including entirely unsupervised approaches. Subjects executed a task on a touch screen that required continuous effort of visual and motor processing with alternating difficulty. We first employed classical approaches for workload state classification that operate on the sensor space of EEG and compared those to the performance of three state-of-the-art spatial filtering methods: common spatial patterns (CSPs) analysis, which requires binary label information; source power co-modulation (SPoC) analysis, which uses the subjects' error rate as a target function; and canonical SPoC (cSPoC) analysis, which solely makes use of cross-frequency power correlations induced by different states of workload and thus represents an unsupervised approach. Finally, we investigated the effects of fusing brain signals and peripheral physiological measures (PPMs) and examined the added value for improving classification performance. Mean classification accuracies of 94%, 92% and 82% were achieved with CSP, SPoC, cSPoC, respectively. These methods outperformed the approaches that did not use spatial filtering and they extracted physiologically plausible components. The performance of the unsupervised cSPoC is significantly increased by augmenting it with PPM features. Our analyses ensured that the signal sources used for classification were of cortical origin and not contaminated with artifacts. Our findings show that workload states can be successfully differentiated from brain signals, even when less and less information from the experimental paradigm is used, thus paving the way for real-world applications in which label information may be noisy or entirely unavailable.
Unsupervised classification of operator workload from brain signals

NASA Astrophysics Data System (ADS)

Schultze-Kraft, Matthias; Dähne, Sven; Gugler, Manfred; Curio, Gabriel; Blankertz, Benjamin

2016-06-01

Objective. In this study we aimed for the classification of operator workload as it is expected in many real-life workplace environments. We explored brain-signal based workload predictors that differ with respect to the level of label information required for training, including entirely unsupervised approaches. Approach. Subjects executed a task on a touch screen that required continuous effort of visual and motor processing with alternating difficulty. We first employed classical approaches for workload state classification that operate on the sensor space of EEG and compared those to the performance of three state-of-the-art spatial filtering methods: common spatial patterns (CSPs) analysis, which requires binary label information; source power co-modulation (SPoC) analysis, which uses the subjects’ error rate as a target function; and canonical SPoC (cSPoC) analysis, which solely makes use of cross-frequency power correlations induced by different states of workload and thus represents an unsupervised approach. Finally, we investigated the effects of fusing brain signals and peripheral physiological measures (PPMs) and examined the added value for improving classification performance. Main results. Mean classification accuracies of 94%, 92% and 82% were achieved with CSP, SPoC, cSPoC, respectively. These methods outperformed the approaches that did not use spatial filtering and they extracted physiologically plausible components. The performance of the unsupervised cSPoC is significantly increased by augmenting it with PPM features. Significance. Our analyses ensured that the signal sources used for classification were of cortical origin and not contaminated with artifacts. Our findings show that workload states can be successfully differentiated from brain signals, even when less and less information from the experimental paradigm is used, thus paving the way for real-world applications in which label information may be noisy or entirely unavailable.

Multispectral and Panchromatic used Enhancement Resolution and Study Effective Enhancement on Supervised and Unsupervised Classification Land – Cover

NASA Astrophysics Data System (ADS)

Salman, S. S.; Abbas, W. A.

2018-05-01

The goal of the study is to support analysis Enhancement of Resolution and study effect on classification methods on bands spectral information of specific and quantitative approaches. In this study introduce a method to enhancement resolution Landsat 8 of combining the bands spectral of 30 meters resolution with panchromatic band 8 of 15 meters resolution, because of importance multispectral imagery to extracting land - cover. Classification methods used in this study to classify several lands -covers recorded from OLI- 8 imagery. Two methods of Data mining can be classified as either supervised or unsupervised. In supervised methods, there is a particular predefined target, that means the algorithm learn which values of the target are associated with which values of the predictor sample. K-nearest neighbors and maximum likelihood algorithms examine in this work as supervised methods. In other hand, no sample identified as target in unsupervised methods, the algorithm of data extraction searches for structure and patterns between all the variables, represented by Fuzzy C-mean clustering method as one of the unsupervised methods, NDVI vegetation index used to compare the results of classification method, the percent of dense vegetation in maximum likelihood method give a best results.
Unsupervised feature learning for autonomous rock image classification

NASA Astrophysics Data System (ADS)

Shu, Lei; McIsaac, Kenneth; Osinski, Gordon R.; Francis, Raymond

2017-09-01

Autonomous rock image classification can enhance the capability of robots for geological detection and enlarge the scientific returns, both in investigation on Earth and planetary surface exploration on Mars. Since rock textural images are usually inhomogeneous and manually hand-crafting features is not always reliable, we propose an unsupervised feature learning method to autonomously learn the feature representation for rock images. In our tests, rock image classification using the learned features shows that the learned features can outperform manually selected features. Self-taught learning is also proposed to learn the feature representation from a large database of unlabelled rock images of mixed class. The learned features can then be used repeatedly for classification of any subclass. This takes advantage of the large dataset of unlabelled rock images and learns a general feature representation for many kinds of rocks. We show experimental results supporting the feasibility of self-taught learning on rock images.
STDP-based spiking deep convolutional neural networks for object recognition.

PubMed

Kheradpisheh, Saeed Reza; Ganjtabesh, Mohammad; Thorpe, Simon J; Masquelier, Timothée

2018-03-01

Previous studies have shown that spike-timing-dependent plasticity (STDP) can be used in spiking neural networks (SNN) to extract visual features of low or intermediate complexity in an unsupervised manner. These studies, however, used relatively shallow architectures, and only one layer was trainable. Another line of research has demonstrated - using rate-based neural networks trained with back-propagation - that having many layers increases the recognition robustness, an approach known as deep learning. We thus designed a deep SNN, comprising several convolutional (trainable with STDP) and pooling layers. We used a temporal coding scheme where the most strongly activated neurons fire first, and less activated neurons fire later or not at all. The network was exposed to natural images. Thanks to STDP, neurons progressively learned features corresponding to prototypical patterns that were both salient and frequent. Only a few tens of examples per category were required and no label was needed. After learning, the complexity of the extracted features increased along the hierarchy, from edge detectors in the first layer to object prototypes in the last layer. Coding was very sparse, with only a few thousands spikes per image, and in some cases the object category could be reasonably well inferred from the activity of a single higher-order neuron. More generally, the activity of a few hundreds of such neurons contained robust category information, as demonstrated using a classifier on Caltech 101, ETH-80, and MNIST databases. We also demonstrate the superiority of STDP over other unsupervised techniques such as random crops (HMAX) or auto-encoders. Taken together, our results suggest that the combination of STDP with latency coding may be a key to understanding the way that the primate visual system learns, its remarkable processing speed and its low energy consumption. These mechanisms are also interesting for artificial vision systems, particularly for hardware solutions. Copyright © 2017 Elsevier Ltd. All rights reserved.
Identification of aberrant gene expression associated with aberrant promoter methylation in primordial germ cells between E13 and E16 rat F3 generation vinclozolin lineage.

PubMed

Taguchi, Y-h

2015-01-01

Transgenerational epigenetics (TGE) are currently considered important in disease, but the mechanisms involved are not yet fully understood. TGE abnormalities expected to cause disease are likely to be initiated during development and to be mediated by aberrant gene expression associated with aberrant promoter methylation that is heritable between generations. However, because methylation is removed and then re-established during development, it is not easy to identify promoter methylation abnormalities by comparing normal lineages with those expected to exhibit TGE abnormalities. This study applied the recently proposed principal component analysis (PCA)-based unsupervised feature extraction to previously reported and publically available gene expression/promoter methylation profiles of rat primordial germ cells, between E13 and E16 of the F3 generation vinclozolin lineage that are expected to exhibit TGE abnormalities, to identify multiple genes that exhibited aberrant gene expression/promoter methylation during development. The biological feasibility of the identified genes were tested via enrichment analyses of various biological concepts including pathway analysis, gene ontology terms and protein-protein interactions. All validations suggested superiority of the proposed method over three conventional and popular supervised methods that employed t test, limma and significance analysis of microarrays, respectively. The identified genes were globally related to tumors, the prostate, kidney, testis and the immune system and were previously reported to be related to various diseases caused by TGE. Among the genes reported by PCA-based unsupervised feature extraction, we propose that chemokine signaling pathways and leucine rich repeat proteins are key factors that initiate transgenerational epigenetic-mediated diseases, because multiple genes included in these two categories were identified in this study.
Identification of aberrant gene expression associated with aberrant promoter methylation in primordial germ cells between E13 and E16 rat F3 generation vinclozolin lineage

PubMed Central

2015-01-01

Background Transgenerational epigenetics (TGE) are currently considered important in disease, but the mechanisms involved are not yet fully understood. TGE abnormalities expected to cause disease are likely to be initiated during development and to be mediated by aberrant gene expression associated with aberrant promoter methylation that is heritable between generations. However, because methylation is removed and then re-established during development, it is not easy to identify promoter methylation abnormalities by comparing normal lineages with those expected to exhibit TGE abnormalities. Methods This study applied the recently proposed principal component analysis (PCA)-based unsupervised feature extraction to previously reported and publically available gene expression/promoter methylation profiles of rat primordial germ cells, between E13 and E16 of the F3 generation vinclozolin lineage that are expected to exhibit TGE abnormalities, to identify multiple genes that exhibited aberrant gene expression/promoter methylation during development. Results The biological feasibility of the identified genes were tested via enrichment analyses of various biological concepts including pathway analysis, gene ontology terms and protein-protein interactions. All validations suggested superiority of the proposed method over three conventional and popular supervised methods that employed t test, limma and significance analysis of microarrays, respectively. The identified genes were globally related to tumors, the prostate, kidney, testis and the immune system and were previously reported to be related to various diseases caused by TGE. Conclusions Among the genes reported by PCA-based unsupervised feature extraction, we propose that chemokine signaling pathways and leucine rich repeat proteins are key factors that initiate transgenerational epigenetic-mediated diseases, because multiple genes included in these two categories were identified in this study. PMID:26677731
Automatic segmentation of brain MRI in high-dimensional local and non-local feature space based on sparse representation.

PubMed

Khalilzadeh, Mohammad Mahdi; Fatemizadeh, Emad; Behnam, Hamid

2013-06-01

Automatic extraction of the varying regions of magnetic resonance images is required as a prior step in a diagnostic intelligent system. The sparsest representation and high-dimensional feature are provided based on learned dictionary. The classification is done by employing the technique that computes the reconstruction error locally and non-locally of each pixel. The acquired results from the real and simulated images are superior to the best MRI segmentation method with regard to the stability advantages. In addition, it is segmented exactly through a formula taken from the distance and sparse factors. Also, it is done automatically taking sparse factor in unsupervised clustering methods whose results have been improved. Copyright © 2013 Elsevier Inc. All rights reserved.
FRaC: a feature-modeling approach for semi-supervised and unsupervised anomaly detection.

PubMed

Noto, Keith; Brodley, Carla; Slonim, Donna

2012-01-01

Anomaly detection involves identifying rare data instances (anomalies) that come from a different class or distribution than the majority (which are simply called "normal" instances). Given a training set of only normal data, the semi-supervised anomaly detection task is to identify anomalies in the future. Good solutions to this task have applications in fraud and intrusion detection. The unsupervised anomaly detection task is different: Given unlabeled, mostly-normal data, identify the anomalies among them. Many real-world machine learning tasks, including many fraud and intrusion detection tasks, are unsupervised because it is impractical (or impossible) to verify all of the training data. We recently presented FRaC, a new approach for semi-supervised anomaly detection. FRaC is based on using normal instances to build an ensemble of feature models, and then identifying instances that disagree with those models as anomalous. In this paper, we investigate the behavior of FRaC experimentally and explain why FRaC is so successful. We also show that FRaC is a superior approach for the unsupervised as well as the semi-supervised anomaly detection task, compared to well-known state-of-the-art anomaly detection methods, LOF and one-class support vector machines, and to an existing feature-modeling approach.
FRaC: a feature-modeling approach for semi-supervised and unsupervised anomaly detection

PubMed Central

Brodley, Carla; Slonim, Donna

2011-01-01

Anomaly detection involves identifying rare data instances (anomalies) that come from a different class or distribution than the majority (which are simply called “normal” instances). Given a training set of only normal data, the semi-supervised anomaly detection task is to identify anomalies in the future. Good solutions to this task have applications in fraud and intrusion detection. The unsupervised anomaly detection task is different: Given unlabeled, mostly-normal data, identify the anomalies among them. Many real-world machine learning tasks, including many fraud and intrusion detection tasks, are unsupervised because it is impractical (or impossible) to verify all of the training data. We recently presented FRaC, a new approach for semi-supervised anomaly detection. FRaC is based on using normal instances to build an ensemble of feature models, and then identifying instances that disagree with those models as anomalous. In this paper, we investigate the behavior of FRaC experimentally and explain why FRaC is so successful. We also show that FRaC is a superior approach for the unsupervised as well as the semi-supervised anomaly detection task, compared to well-known state-of-the-art anomaly detection methods, LOF and one-class support vector machines, and to an existing feature-modeling approach. PMID:22639542
Unsupervised Medical Entity Recognition and Linking in Chinese Online Medical Text

PubMed Central

Gan, Liang; Cheng, Mian; Wu, Quanyuan

2018-01-01

Online medical text is full of references to medical entities (MEs), which are valuable in many applications, including medical knowledge-based (KB) construction, decision support systems, and the treatment of diseases. However, the diverse and ambiguous nature of the surface forms gives rise to a great difficulty for ME identification. Many existing solutions have focused on supervised approaches, which are often task-dependent. In other words, applying them to different kinds of corpora or identifying new entity categories requires major effort in data annotation and feature definition. In this paper, we propose unMERL, an unsupervised framework for recognizing and linking medical entities mentioned in Chinese online medical text. For ME recognition, unMERL first exploits a knowledge-driven approach to extract candidate entities from free text. Then, the categories of the candidate entities are determined using a distributed semantic-based approach. For ME linking, we propose a collaborative inference approach which takes full advantage of heterogenous entity knowledge and unstructured information in KB. Experimental results on real corpora demonstrate significant benefits compared to recent approaches with respect to both ME recognition and linking. PMID:29849994
Automatic segmentation of triaxial accelerometry signals for falls risk estimation.

PubMed

Redmond, Stephen J; Scalzi, Maria Elena; Narayanan, Michael R; Lord, Stephen R; Cerutti, Sergio; Lovell, Nigel H

2010-01-01

Falls-related injuries in the elderly population represent one of the most significant contributors to rising health care expense in developed countries. In recent years, falls detection technologies have become more common. However, very few have adopted a preferable falls prevention strategy through unsupervised monitoring in the free-living environment. The basis of the monitoring described herein was a self-administered directed-routine (DR) comprising three separate tests measured by way of a waist-mounted triaxial accelerometer. Using features extracted from the manually segmented signals, a reasonable estimate of falls risk can be achieved. We describe here a series of algorithms for automatically segmenting these recordings, enabling the use of the DR assessment in the unsupervised and home environments. The accelerometry signals, from 68 subjects performing the DR, were manually annotated by an observer. Using the proposed signal segmentation routines, an good agreement was observed between the manually annotated markers and the automatically estimated values. However, a decrease in the correlation with falls risk to 0.73 was observed using the automatic segmentation, compared to 0.81 when using markers manually placed by an observer.
Clustering for unsupervised fault diagnosis in nuclear turbine shut-down transients

NASA Astrophysics Data System (ADS)

Baraldi, Piero; Di Maio, Francesco; Rigamonti, Marco; Zio, Enrico; Seraoui, Redouane

2015-06-01

Empirical methods for fault diagnosis usually entail a process of supervised training based on a set of examples of signal evolutions "labeled" with the corresponding, known classes of fault. However, in practice, the signals collected during plant operation may be, very often, "unlabeled", i.e., the information on the corresponding type of occurred fault is not available. To cope with this practical situation, in this paper we develop a methodology for the identification of transient signals showing similar characteristics, under the conjecture that operational/faulty transient conditions of the same type lead to similar behavior in the measured signals evolution. The methodology is founded on a feature extraction procedure, which feeds a spectral clustering technique, embedding the unsupervised fuzzy C-means (FCM) algorithm, which evaluates the functional similarity among the different operational/faulty transients. A procedure for validating the plausibility of the obtained clusters is also propounded based on physical considerations. The methodology is applied to a real industrial case, on the basis of 148 shut-down transients of a Nuclear Power Plant (NPP) steam turbine.
Unsupervised Decoding of Long-Term, Naturalistic Human Neural Recordings with Automated Video and Audio Annotations

PubMed Central

Wang, Nancy X. R.; Olson, Jared D.; Ojemann, Jeffrey G.; Rao, Rajesh P. N.; Brunton, Bingni W.

2016-01-01

Fully automated decoding of human activities and intentions from direct neural recordings is a tantalizing challenge in brain-computer interfacing. Implementing Brain Computer Interfaces (BCIs) outside carefully controlled experiments in laboratory settings requires adaptive and scalable strategies with minimal supervision. Here we describe an unsupervised approach to decoding neural states from naturalistic human brain recordings. We analyzed continuous, long-term electrocorticography (ECoG) data recorded over many days from the brain of subjects in a hospital room, with simultaneous audio and video recordings. We discovered coherent clusters in high-dimensional ECoG recordings using hierarchical clustering and automatically annotated them using speech and movement labels extracted from audio and video. To our knowledge, this represents the first time techniques from computer vision and speech processing have been used for natural ECoG decoding. Interpretable behaviors were decoded from ECoG data, including moving, speaking and resting; the results were assessed by comparison with manual annotation. Discovered clusters were projected back onto the brain revealing features consistent with known functional areas, opening the door to automated functional brain mapping in natural settings. PMID:27148018
Texture analysis with statistical methods for wheat ear extraction

NASA Astrophysics Data System (ADS)

Bakhouche, M.; Cointault, F.; Gouton, P.

2007-01-01

In agronomic domain, the simplification of crop counting, necessary for yield prediction and agronomic studies, is an important project for technical institutes such as Arvalis. Although the main objective of our global project is to conceive a mobile robot for natural image acquisition directly in a field, Arvalis has proposed us first to detect by image processing the number of wheat ears in images before to count them, which will allow to obtain the first component of the yield. In this paper we compare different texture image segmentation techniques based on feature extraction by first and higher order statistical methods which have been applied on our images. The extracted features are used for unsupervised pixel classification to obtain the different classes in the image. So, the K-means algorithm is implemented before the choice of a threshold to highlight the ears. Three methods have been tested in this feasibility study with very average error of 6%. Although the evaluation of the quality of the detection is visually done, automatic evaluation algorithms are currently implementing. Moreover, other statistical methods of higher order will be implemented in the future jointly with methods based on spatio-frequential transforms and specific filtering.
Context-Aware Local Binary Feature Learning for Face Recognition.

PubMed

Duan, Yueqi; Lu, Jiwen; Feng, Jianjiang; Zhou, Jie

2018-05-01

In this paper, we propose a context-aware local binary feature learning (CA-LBFL) method for face recognition. Unlike existing learning-based local face descriptors such as discriminant face descriptor (DFD) and compact binary face descriptor (CBFD) which learn each feature code individually, our CA-LBFL exploits the contextual information of adjacent bits by constraining the number of shifts from different binary bits, so that more robust information can be exploited for face representation. Given a face image, we first extract pixel difference vectors (PDV) in local patches, and learn a discriminative mapping in an unsupervised manner to project each pixel difference vector into a context-aware binary vector. Then, we perform clustering on the learned binary codes to construct a codebook, and extract a histogram feature for each face image with the learned codebook as the final representation. In order to exploit local information from different scales, we propose a context-aware local binary multi-scale feature learning (CA-LBMFL) method to jointly learn multiple projection matrices for face representation. To make the proposed methods applicable for heterogeneous face recognition, we present a coupled CA-LBFL (C-CA-LBFL) method and a coupled CA-LBMFL (C-CA-LBMFL) method to reduce the modality gap of corresponding heterogeneous faces in the feature level, respectively. Extensive experimental results on four widely used face datasets clearly show that our methods outperform most state-of-the-art face descriptors.
Unsupervised chunking based on graph propagation from bilingual corpus.

PubMed

Zhu, Ling; Wong, Derek F; Chao, Lidia S

2014-01-01

This paper presents a novel approach for unsupervised shallow parsing model trained on the unannotated Chinese text of parallel Chinese-English corpus. In this approach, no information of the Chinese side is applied. The exploitation of graph-based label propagation for bilingual knowledge transfer, along with an application of using the projected labels as features in unsupervised model, contributes to a better performance. The experimental comparisons with the state-of-the-art algorithms show that the proposed approach is able to achieve impressive higher accuracy in terms of F-score.
Comparison of two satellite imaging platforms for evaluating quasi-circular vegetation patch in the Yellow River Delta, China

NASA Astrophysics Data System (ADS)

Liu, Qingsheng; Liang, Li; Liu, Gaohuan; Huang, Chong

2017-09-01

Vegetation often exists as patch in arid and semi-arid region throughout the world. Vegetation patch can be effectively monitored by remote sensing images. However, not all satellite platforms are suitable to study quasi-circular vegetation patch. This study compares fine (GF-1) and coarse (CBERS-04) resolution platforms, specifically focusing on the quasicircular vegetation patches in the Yellow River Delta (YRD), China. Vegetation patch features (area, shape) were extracted from GF-1 and CBERS-04 imagery using unsupervised classifier (K-Means) and object-oriented approach (Example-based feature extraction with SVM classifier) in order to analyze vegetation patterns. These features were then compared using vector overlay and differencing, and the Root Mean Squared Error (RMSE) was used to determine if the mapped vegetation patches were significantly different. Regardless of K-Means or Example-based feature extraction with SVM classification, it was found that the area of quasi-circular vegetation patches from visual interpretation from QuickBird image (ground truth data) was greater than that from both of GF-1 and CBERS-04, and the number of patches detected from GF-1 data was more than that of CBERS-04 image. It was seen that without expert's experience and professional training on object-oriented approach, K-Means was better than example-based feature extraction with SVM for detecting the patch. It indicated that CBERS-04 could be used to detect the patch with area of more than 300 m2, but GF-1 data was a sufficient source for patch detection in the YRD. However, in the future, finer resolution platforms such as Worldview are needed to gain more detailed insight on patch structures and components and formation mechanism.
Unsupervised iterative detection of land mines in highly cluttered environments.

PubMed

Batman, Sinan; Goutsias, John

2003-01-01

An unsupervised iterative scheme is proposed for land mine detection in heavily cluttered scenes. This scheme is based on iterating hybrid multispectral filters that consist of a decorrelating linear transform coupled with a nonlinear morphological detector. Detections extracted from the first pass are used to improve results in subsequent iterations. The procedure stops after a predetermined number of iterations. The proposed scheme addresses several weaknesses associated with previous adaptations of morphological approaches to land mine detection. Improvement in detection performance, robustness with respect to clutter inhomogeneities, a completely unsupervised operation, and computational efficiency are the main highlights of the method. Experimental results reveal excellent performance.
CNN universal machine as classificaton platform: an art-like clustering algorithm.

PubMed

Bálya, David

2003-12-01

Fast and robust classification of feature vectors is a crucial task in a number of real-time systems. A cellular neural/nonlinear network universal machine (CNN-UM) can be very efficient as a feature detector. The next step is to post-process the results for object recognition. This paper shows how a robust classification scheme based on adaptive resonance theory (ART) can be mapped to the CNN-UM. Moreover, this mapping is general enough to include different types of feed-forward neural networks. The designed analogic CNN algorithm is capable of classifying the extracted feature vectors keeping the advantages of the ART networks, such as robust, plastic and fault-tolerant behaviors. An analogic algorithm is presented for unsupervised classification with tunable sensitivity and automatic new class creation. The algorithm is extended for supervised classification. The presented binary feature vector classification is implemented on the existing standard CNN-UM chips for fast classification. The experimental evaluation shows promising performance after 100% accuracy on the training set.
Automatic Spatio-Temporal Flow Velocity Measurement in Small Rivers Using Thermal Image Sequences

NASA Astrophysics Data System (ADS)

Lin, D.; Eltner, A.; Sardemann, H.; Maas, H.-G.

2018-05-01

An automatic spatio-temporal flow velocity measurement approach, using an uncooled thermal camera, is proposed in this paper. The basic principle of the method is to track visible thermal features at the water surface in thermal camera image sequences. Radiometric and geometric calibrations are firstly implemented to remove vignetting effects in thermal imagery and to get the interior orientation parameters of the camera. An object-based unsupervised classification approach is then applied to detect the interest regions for data referencing and thermal feature tracking. Subsequently, GCPs are extracted to orient the river image sequences and local hot points are identified as tracking features. Afterwards, accurate dense tracking outputs are obtained using pyramidal Lucas-Kanade method. To validate the accuracy potential of the method, measurements obtained from thermal feature tracking are compared with reference measurements taken by a propeller gauge. Results show a great potential of automatic flow velocity measurement in small rivers using imagery from a thermal camera.
Learning Semantic Tags from Big Data for Clinical Text Representation.

PubMed

Li, Yanpeng; Liu, Hongfang

2015-01-01

In clinical text mining, it is one of the biggest challenges to represent medical terminologies and n-gram terms in sparse medical reports using either supervised or unsupervised methods. Addressing this issue, we propose a novel method for word and n-gram representation at semantic level. We first represent each word by its distance with a set of reference features calculated by reference distance estimator (RDE) learned from labeled and unlabeled data, and then generate new features using simple techniques of discretization, random sampling and merging. The new features are a set of binary rules that can be interpreted as semantic tags derived from word and n-grams. We show that the new features significantly outperform classical bag-of-words and n-grams in the task of heart disease risk factor extraction in i2b2 2014 challenge. It is promising to see that semantics tags can be used to replace the original text entirely with even better prediction performance as well as derive new rules beyond lexical level.

Unsupervised texture image segmentation by improved neural network ART2

NASA Technical Reports Server (NTRS)

Wang, Zhiling; Labini, G. Sylos; Mugnuolo, R.; Desario, Marco

1994-01-01

We here propose a segmentation algorithm of texture image for a computer vision system on a space robot. An improved adaptive resonance theory (ART2) for analog input patterns is adapted to classify the image based on a set of texture image features extracted by a fast spatial gray level dependence method (SGLDM). The nonlinear thresholding functions in input layer of the neural network have been constructed by two parts: firstly, to reduce the effects of image noises on the features, a set of sigmoid functions is chosen depending on the types of the feature; secondly, to enhance the contrast of the features, we adopt fuzzy mapping functions. The cluster number in output layer can be increased by an autogrowing mechanism constantly when a new pattern happens. Experimental results and original or segmented pictures are shown, including the comparison between this approach and K-means algorithm. The system written in C language is performed on a SUN-4/330 sparc-station with an image board IT-150 and a CCD camera.
Automatic age and gender classification using supervised appearance model

NASA Astrophysics Data System (ADS)

Bukar, Ali Maina; Ugail, Hassan; Connah, David

2016-11-01

Age and gender classification are two important problems that recently gained popularity in the research community, due to their wide range of applications. Research has shown that both age and gender information are encoded in the face shape and texture, hence the active appearance model (AAM), a statistical model that captures shape and texture variations, has been one of the most widely used feature extraction techniques for the aforementioned problems. However, AAM suffers from some drawbacks, especially when used for classification. This is primarily because principal component analysis (PCA), which is at the core of the model, works in an unsupervised manner, i.e., PCA dimensionality reduction does not take into account how the predictor variables relate to the response (class labels). Rather, it explores only the underlying structure of the predictor variables, thus, it is no surprise if PCA discards valuable parts of the data that represent discriminatory features. Toward this end, we propose a supervised appearance model (sAM) that improves on AAM by replacing PCA with partial least-squares regression. This feature extraction technique is then used for the problems of age and gender classification. Our experiments show that sAM has better predictive power than the conventional AAM.
Respiratory Artefact Removal in Forced Oscillation Measurements: A Machine Learning Approach.

PubMed

Pham, Thuy T; Thamrin, Cindy; Robinson, Paul D; McEwan, Alistair L; Leong, Philip H W

2017-08-01

Respiratory artefact removal for the forced oscillation technique can be treated as an anomaly detection problem. Manual removal is currently considered the gold standard, but this approach is laborious and subjective. Most existing automated techniques used simple statistics and/or rejected anomalous data points. Unfortunately, simple statistics are insensitive to numerous artefacts, leading to low reproducibility of results. Furthermore, rejecting anomalous data points causes an imbalance between the inspiratory and expiratory contributions. From a machine learning perspective, such methods are unsupervised and can be considered simple feature extraction. We hypothesize that supervised techniques can be used to find improved features that are more discriminative and more highly correlated with the desired output. Features thus found are then used for anomaly detection by applying quartile thresholding, which rejects complete breaths if one of its features is out of range. The thresholds are determined by both saliency and performance metrics rather than qualitative assumptions as in previous works. Feature ranking indicates that our new landmark features are among the highest scoring candidates regardless of age across saliency criteria. F1-scores, receiver operating characteristic, and variability of the mean resistance metrics show that the proposed scheme outperforms previous simple feature extraction approaches. Our subject-independent detector, 1IQR-SU, demonstrated approval rates of 80.6% for adults and 98% for children, higher than existing methods. Our new features are more relevant. Our removal is objective and comparable to the manual method. This is a critical work to automate forced oscillation technique quality control.
An Unsupervised Approach for Extraction of Blood Vessels from Fundus Images.

PubMed

Dash, Jyotiprava; Bhoi, Nilamani

2018-04-26

Pathological disorders may happen due to small changes in retinal blood vessels which may later turn into blindness. Hence, the accurate segmentation of blood vessels is becoming a challenging task for pathological analysis. This paper offers an unsupervised recursive method for extraction of blood vessels from ophthalmoscope images. First, a vessel-enhanced image is generated with the help of gamma correction and contrast-limited adaptive histogram equalization (CLAHE). Next, the vessels are extracted iteratively by applying an adaptive thresholding technique. At last, a final vessel segmented image is produced by applying a morphological cleaning operation. Evaluations are accompanied on the publicly available digital retinal images for vessel extraction (DRIVE) and Child Heart And Health Study in England (CHASE_DB1) databases using nine different measurements. The proposed method achieves average accuracies of 0.957 and 0.952 on DRIVE and CHASE_DB1 databases respectively.
Unsupervised laparoscopic appendicectomy by surgical trainees is safe and time-effective.

PubMed

Wong, Kenneth; Duncan, Tristram; Pearson, Andrew

2007-07-01

Open appendicectomy is the traditional standard treatment for appendicitis. Laparoscopic appendicectomy is perceived as a procedure with greater potential for complications and longer operative times. This paper examines the hypothesis that unsupervised laparoscopic appendicectomy by surgical trainees is a safe and time-effective valid alternative. Medical records, operating theatre records and histopathology reports of all patients undergoing laparoscopic and open appendicectomy over a 15-month period in two hospitals within an area health service were retrospectively reviewed. Data were analysed to compare patient features, pathology findings, operative times, complications, readmissions and mortality between laparoscopic and open groups and between unsupervised surgical trainee operators versus consultant surgeon operators. A total of 143 laparoscopic and 222 open appendicectomies were reviewed. Unsupervised trainees performed 64% of the laparoscopic appendicectomies and 55% of the open appendicectomies. There were no significant differences in complication rates, readmissions, mortality and length of stay between laparoscopic and open appendicectomy groups or between trainee and consultant surgeon operators. Conversion rates (laparoscopic to open approach) were similar for trainees and consultants. Unsupervised senior surgical trainees did not take significantly longer to perform laparoscopic appendicectomy when compared to unsupervised trainee-performed open appendicectomy. Unsupervised laparoscopic appendicectomy by surgical trainees is safe and time-effective.
DOE Office of Scientific and Technical Information (OSTI.GOV)

Parekh, V; Jacobs, MA

Purpose: Multiparametric radiological imaging is used for diagnosis in patients. Potentially extracting useful features specific to a patient’s pathology would be crucial step towards personalized medicine and assessing treatment options. In order to automatically extract features directly from multiparametric radiological imaging datasets, we developed an advanced unsupervised machine learning algorithm called the multidimensional imaging radiomics-geodesics(MIRaGe). Methods: Seventy-six breast tumor patients underwent 3T MRI breast imaging were used for this study. We tested the MIRaGe algorithm to extract features for classification of breast tumors into benign or malignant. The MRI parameters used were T1-weighted, T2-weighted, dynamic contrast enhanced MR imaging (DCE-MRI)more » and diffusion weighted imaging(DWI). The MIRaGe algorithm extracted the radiomics-geodesics features (RGFs) from multiparametric MRI datasets. This enable our method to learn the intrinsic manifold representations corresponding to the patients. To determine the informative RGF, a modified Isomap algorithm(t-Isomap) was created for a radiomics-geodesics feature space(tRGFS) to avoid overfitting. Final classification was performed using SVM. The predictive power of the RGFs was tested and validated using k-fold cross validation. Results: The RGFs extracted by the MIRaGe algorithm successfully classified malignant lesions from benign lesions with a sensitivity of 93% and a specificity of 91%. The top 50 RGFs identified as the most predictive by the t-Isomap procedure were consistent with the radiological parameters known to be associated with breast cancer diagnosis and were categorized as kinetic curve characterizing RGFs, wash-in rate characterizing RGFs, wash-out rate characterizing RGFs and morphology characterizing RGFs. Conclusion: In this paper, we developed a novel feature extraction algorithm for multiparametric radiological imaging. The results demonstrated the power of the MIRaGe algorithm at automatically discovering useful feature representations directly from the raw multiparametric MRI data. In conclusion, the MIRaGe informatics model provides a powerful tool with applicability in cancer diagnosis and a possibility of extension to other kinds of pathologies. NIH (P50CA103175, 5P30CA006973 (IRAT), R01CA190299, U01CA140204), Siemens Medical Systems (JHU-2012-MR-86-01) and Nivida Graphics Corporation.« less
Feature Selection for Ridge Regression with Provable Guarantees.

PubMed

Paul, Saurabh; Drineas, Petros

2016-04-01

We introduce single-set spectral sparsification as a deterministic sampling-based feature selection technique for regularized least-squares classification, which is the classification analog to ridge regression. The method is unsupervised and gives worst-case guarantees of the generalization power of the classification function after feature selection with respect to the classification function obtained using all features. We also introduce leverage-score sampling as an unsupervised randomized feature selection method for ridge regression. We provide risk bounds for both single-set spectral sparsification and leverage-score sampling on ridge regression in the fixed design setting and show that the risk in the sampled space is comparable to the risk in the full-feature space. We perform experiments on synthetic and real-world data sets; a subset of TechTC-300 data sets, to support our theory. Experimental results indicate that the proposed methods perform better than the existing feature selection methods.
SFRP1 is a possible candidate for epigenetic therapy in non-small cell lung cancer.

PubMed

Taguchi, Y-H; Iwadate, Mitsuo; Umeyama, Hideaki

2016-08-12

Non-small cell lung cancer (NSCLC) remains a lethal disease despite many proposed treatments. Recent studies have indicated that epigenetic therapy, which targets epigenetic effects, might be a new therapeutic methodology for NSCLC. However, it is not clear which objects (e.g., genes) this treatment specifically targets. Secreted frizzled-related proteins (SFRPs) are promising candidates for epigenetic therapy in many cancers, but there have been no reports of SFRPs targeted by epigenetic therapy for NSCLC. This study performed a meta-analysis of reprogrammed NSCLC cell lines instead of the direct examination of epigenetic therapy treatment to identify epigenetic therapy targets. In addition, mRNA expression/promoter methylation profiles were processed by recently proposed principal component analysis based unsupervised feature extraction and categorical regression analysis based feature extraction. The Wnt/β-catenin signalling pathway was extensively enriched among 32 genes identified by feature extraction. Among the genes identified, SFRP1 was specifically indicated to target β-catenin, and thus might be targeted by epigenetic therapy in NSCLC cell lines. A histone deacetylase inhibitor might reactivate SFRP1 based upon the re-analysis of a public domain data set. Numerical computation validated the binding of SFRP1 to WNT1 to suppress Wnt signalling pathway activation in NSCLC. The meta-analysis of reprogrammed NSCLC cell lines identified SFRP1 as a promising target of epigenetic therapy for NSCLC.
An Evaluation of Feature Learning Methods for High Resolution Image Classification

NASA Astrophysics Data System (ADS)

Tokarczyk, P.; Montoya, J.; Schindler, K.

2012-07-01

Automatic image classification is one of the fundamental problems of remote sensing research. The classification problem is even more challenging in high-resolution images of urban areas, where the objects are small and heterogeneous. Two questions arise, namely which features to extract from the raw sensor data to capture the local radiometry and image structure at each pixel or segment, and which classification method to apply to the feature vectors. While classifiers are nowadays well understood, selecting the right features remains a largely empirical process. Here we concentrate on the features. Several methods are evaluated which allow one to learn suitable features from unlabelled image data by analysing the image statistics. In a comparative study, we evaluate unsupervised feature learning with different linear and non-linear learning methods, including principal component analysis (PCA) and deep belief networks (DBN). We also compare these automatically learned features with popular choices of ad-hoc features including raw intensity values, standard combinations like the NDVI, a few PCA channels, and texture filters. The comparison is done in a unified framework using the same images, the target classes, reference data and a Random Forest classifier.
Convolutional neural network features based change detection in satellite images

NASA Astrophysics Data System (ADS)

Mohammed El Amin, Arabi; Liu, Qingjie; Wang, Yunhong

2016-07-01

With the popular use of high resolution remote sensing (HRRS) satellite images, a huge research efforts have been placed on change detection (CD) problem. An effective feature selection method can significantly boost the final result. While hand-designed features have proven difficulties to design features that effectively capture high and mid-level representations, the recent developments in machine learning (Deep Learning) omit this problem by learning hierarchical representation in an unsupervised manner directly from data without human intervention. In this letter, we propose approaching the change detection problem from a feature learning perspective. A novel deep Convolutional Neural Networks (CNN) features based HR satellite images change detection method is proposed. The main guideline is to produce a change detection map directly from two images using a pretrained CNN. This method can omit the limited performance of hand-crafted features. Firstly, CNN features are extracted through different convolutional layers. Then, a concatenation step is evaluated after an normalization step, resulting in a unique higher dimensional feature map. Finally, a change map was computed using pixel-wise Euclidean distance. Our method has been validated on real bitemporal HRRS satellite images according to qualitative and quantitative analyses. The results obtained confirm the interest of the proposed method.
Unsupervised quality estimation model for English to German translation and its application in extensive supervised evaluation.

PubMed

Han, Aaron L-F; Wong, Derek F; Chao, Lidia S; He, Liangye; Lu, Yi

2014-01-01

With the rapid development of machine translation (MT), the MT evaluation becomes very important to timely tell us whether the MT system makes any progress. The conventional MT evaluation methods tend to calculate the similarity between hypothesis translations offered by automatic translation systems and reference translations offered by professional translators. There are several weaknesses in existing evaluation metrics. Firstly, the designed incomprehensive factors result in language-bias problem, which means they perform well on some special language pairs but weak on other language pairs. Secondly, they tend to use no linguistic features or too many linguistic features, of which no usage of linguistic feature draws a lot of criticism from the linguists and too many linguistic features make the model weak in repeatability. Thirdly, the employed reference translations are very expensive and sometimes not available in the practice. In this paper, the authors propose an unsupervised MT evaluation metric using universal part-of-speech tagset without relying on reference translations. The authors also explore the performances of the designed metric on traditional supervised evaluation tasks. Both the supervised and unsupervised experiments show that the designed methods yield higher correlation scores with human judgments.
Statistical mechanics of unsupervised feature learning in a restricted Boltzmann machine with binary synapses

NASA Astrophysics Data System (ADS)

Huang, Haiping

2017-05-01

Revealing hidden features in unlabeled data is called unsupervised feature learning, which plays an important role in pretraining a deep neural network. Here we provide a statistical mechanics analysis of the unsupervised learning in a restricted Boltzmann machine with binary synapses. A message passing equation to infer the hidden feature is derived, and furthermore, variants of this equation are analyzed. A statistical analysis by replica theory describes the thermodynamic properties of the model. Our analysis confirms an entropy crisis preceding the non-convergence of the message passing equation, suggesting a discontinuous phase transition as a key characteristic of the restricted Boltzmann machine. Continuous phase transition is also confirmed depending on the embedded feature strength in the data. The mean-field result under the replica symmetric assumption agrees with that obtained by running message passing algorithms on single instances of finite sizes. Interestingly, in an approximate Hopfield model, the entropy crisis is absent, and a continuous phase transition is observed instead. We also develop an iterative equation to infer the hyper-parameter (temperature) hidden in the data, which in physics corresponds to iteratively imposing Nishimori condition. Our study provides insights towards understanding the thermodynamic properties of the restricted Boltzmann machine learning, and moreover important theoretical basis to build simplified deep networks.
Unsupervised segmentation of lungs from chest radiographs

NASA Astrophysics Data System (ADS)

Ghosh, Payel; Antani, Sameer K.; Long, L. Rodney; Thoma, George R.

2012-03-01

This paper describes our preliminary investigations for deriving and characterizing coarse-level textural regions present in the lung field on chest radiographs using unsupervised grow-cut (UGC), a cellular automaton based unsupervised segmentation technique. The segmentation has been performed on a publicly available data set of chest radiographs. The algorithm is useful for this application because it automatically converges to a natural segmentation of the image from random seed points using low-level image features such as pixel intensity values and texture features. Our goal is to develop a portable screening system for early detection of lung diseases for use in remote areas in developing countries. This involves developing automated algorithms for screening x-rays as normal/abnormal with a high degree of sensitivity, and identifying lung disease patterns on chest x-rays. Automatically deriving and quantitatively characterizing abnormal regions present in the lung field is the first step toward this goal. Therefore, region-based features such as geometrical and pixel-value measurements were derived from the segmented lung fields. In the future, feature selection and classification will be performed to identify pathological conditions such as pulmonary tuberculosis on chest radiographs. Shape-based features will also be incorporated to account for occlusions of the lung field and by other anatomical structures such as the heart and diaphragm.
Automatically identifying health- and clinical-related content in wikipedia.

PubMed

Liu, Feifan; Moosavinasab, Soheil; Agarwal, Shashank; Bennett, Andrew S; Yu, Hong

2013-01-01

Physicians are increasingly using the Internet for finding medical information related to patient care. Wikipedia is a valuable online medical resource to be integrated into existing clinical question answering (QA) systems. On the other hand, Wikipedia contains a full spectrum of world's knowledge and therefore comprises a large partition of non-health-related content, which makes disambiguation more challenging and consequently leads to large overhead for existing systems to effectively filter irrelevant information. To overcome this, we have developed both unsupervised and supervised approaches to identify health-related articles as well as clinically relevant articles. Furthermore, we explored novel features by extracting health related hierarchy from the Wikipedia category network, from which a variety of features were derived and evaluated. Our experiments show promising results and also demonstrate that employing the category hierarchy can effectively improve the system performance.
An illustration of new methods in machine condition monitoring, Part I: stochastic resonance

NASA Astrophysics Data System (ADS)

Worden, K.; Antoniadou, I.; Marchesiello, S.; Mba, C.; Garibaldi, L.

2017-05-01

There have been many recent developments in the application of data-based methods to machine condition monitoring. A powerful methodology based on machine learning has emerged, where diagnostics are based on a two-step procedure: extraction of damage-sensitive features, followed by unsupervised learning (novelty detection) or supervised learning (classification). The objective of the current pair of papers is simply to illustrate one state-of-the-art procedure for each step, using synthetic data representative of reality in terms of size and complexity. The first paper in the pair will deal with feature extraction. Although some papers have appeared in the recent past considering stochastic resonance as a means of amplifying damage information in signals, they have largely relied on ad hoc specifications of the resonator used. In contrast, the current paper will adopt a principled optimisation-based approach to the resonator design. The paper will also show that a discrete dynamical system can provide all the benefits of a continuous system, but also provide a considerable speed-up in terms of simulation time in order to facilitate the optimisation approach.
On the asymptotic improvement of supervised learning by utilizing additional unlabeled samples - Normal mixture density case

NASA Technical Reports Server (NTRS)

Shahshahani, Behzad M.; Landgrebe, David A.

1992-01-01

The effect of additional unlabeled samples in improving the supervised learning process is studied in this paper. Three learning processes. supervised, unsupervised, and combined supervised-unsupervised, are compared by studying the asymptotic behavior of the estimates obtained under each process. Upper and lower bounds on the asymptotic covariance matrices are derived. It is shown that under a normal mixture density assumption for the probability density function of the feature space, the combined supervised-unsupervised learning is always superior to the supervised learning in achieving better estimates. Experimental results are provided to verify the theoretical concepts.
Unsupervised classification of surface defects in wire rod production obtained by eddy current sensors.

PubMed

Saludes-Rodil, Sergio; Baeyens, Enrique; Rodríguez-Juan, Carlos P

2015-04-29

An unsupervised approach to classify surface defects in wire rod manufacturing is developed in this paper. The defects are extracted from an eddy current signal and classified using a clustering technique that uses the dynamic time warping distance as the dissimilarity measure. The new approach has been successfully tested using industrial data. It is shown that it outperforms other classification alternatives, such as the modified Fourier descriptors.
Simultaneous Local Binary Feature Learning and Encoding for Homogeneous and Heterogeneous Face Recognition.

PubMed

Lu, Jiwen; Erin Liong, Venice; Zhou, Jie

2017-08-09

In this paper, we propose a simultaneous local binary feature learning and encoding (SLBFLE) approach for both homogeneous and heterogeneous face recognition. Unlike existing hand-crafted face descriptors such as local binary pattern (LBP) and Gabor features which usually require strong prior knowledge, our SLBFLE is an unsupervised feature learning approach which automatically learns face representation from raw pixels. Unlike existing binary face descriptors such as the LBP, discriminant face descriptor (DFD), and compact binary face descriptor (CBFD) which use a two-stage feature extraction procedure, our SLBFLE jointly learns binary codes and the codebook for local face patches so that discriminative information from raw pixels from face images of different identities can be obtained by using a one-stage feature learning and encoding procedure. Moreover, we propose a coupled simultaneous local binary feature learning and encoding (C-SLBFLE) method to make the proposed approach suitable for heterogeneous face matching. Unlike most existing coupled feature learning methods which learn a pair of transformation matrices for each modality, we exploit both the common and specific information from heterogeneous face samples to characterize their underlying correlations. Experimental results on six widely used face datasets are presented to demonstrate the effectiveness of the proposed method.
Named Entity Recognition in Chinese Clinical Text Using Deep Neural Network.

PubMed

Wu, Yonghui; Jiang, Min; Lei, Jianbo; Xu, Hua

2015-01-01

Rapid growth in electronic health records (EHRs) use has led to an unprecedented expansion of available clinical data in electronic formats. However, much of the important healthcare information is locked in the narrative documents. Therefore Natural Language Processing (NLP) technologies, e.g., Named Entity Recognition that identifies boundaries and types of entities, has been extensively studied to unlock important clinical information in free text. In this study, we investigated a novel deep learning method to recognize clinical entities in Chinese clinical documents using the minimal feature engineering approach. We developed a deep neural network (DNN) to generate word embeddings from a large unlabeled corpus through unsupervised learning and another DNN for the NER task. The experiment results showed that the DNN with word embeddings trained from the large unlabeled corpus outperformed the state-of-the-art CRF's model in the minimal feature engineering setting, achieving the highest F1-score of 0.9280. Further analysis showed that word embeddings derived through unsupervised learning from large unlabeled corpus remarkably improved the DNN with randomized embedding, denoting the usefulness of unsupervised feature learning.
Unsupervised learning of discriminative edge measures for vehicle matching between nonoverlapping cameras.

PubMed

Shan, Ying; Sawhney, Harpreet S; Kumar, Rakesh

2008-04-01

This paper proposes a novel unsupervised algorithm learning discriminative features in the context of matching road vehicles between two non-overlapping cameras. The matching problem is formulated as a same-different classification problem, which aims to compute the probability of vehicle images from two distinct cameras being from the same vehicle or different vehicle(s). We employ a novel measurement vector that consists of three independent edge-based measures and their associated robust measures computed from a pair of aligned vehicle edge maps. The weight of each measure is determined by an unsupervised learning algorithm that optimally separates the same-different classes in the combined measurement space. This is achieved with a weak classification algorithm that automatically collects representative samples from same-different classes, followed by a more discriminative classifier based on Fisher' s Linear Discriminants and Gibbs Sampling. The robustness of the match measures and the use of unsupervised discriminant analysis in the classification ensures that the proposed method performs consistently in the presence of missing/false features, temporally and spatially changing illumination conditions, and systematic misalignment caused by different camera configurations. Extensive experiments based on real data of over 200 vehicles at different times of day demonstrate promising results.

Unsupervised Feature Selection Based on the Morisita Index for Hyperspectral Images

NASA Astrophysics Data System (ADS)

Golay, Jean; Kanevski, Mikhail

2017-04-01

Hyperspectral sensors are capable of acquiring images with hundreds of narrow and contiguous spectral bands. Compared with traditional multispectral imagery, the use of hyperspectral images allows better performance in discriminating between land-cover classes, but it also results in large redundancy and high computational data processing. To alleviate such issues, unsupervised feature selection techniques for redundancy minimization can be implemented. Their goal is to select the smallest subset of features (or bands) in such a way that all the information content of a data set is preserved as much as possible. The present research deals with the application to hyperspectral images of a recently introduced technique of unsupervised feature selection: the Morisita-Based filter for Redundancy Minimization (MBRM). MBRM is based on the (multipoint) Morisita index of clustering and on the Morisita estimator of Intrinsic Dimension (ID). The fundamental idea of the technique is to retain only the bands which contribute to increasing the ID of an image. In this way, redundant bands are disregarded, since they have no impact on the ID. Besides, MBRM has several advantages over benchmark techniques: in addition to its ability to deal with large data sets, it can capture highly-nonlinear dependences and its implementation is straightforward in any programming environment. Experimental results on freely available hyperspectral images show the good effectiveness of MBRM in remote sensing data processing. Comparisons with benchmark techniques are carried out and random forests are used to assess the performance of MBRM in reducing the data dimensionality without loss of relevant information. References [1] C. Traina Jr., A.J.M. Traina, L. Wu, C. Faloutsos, Fast feature selection using fractal dimension, in: Proceedings of the XV Brazilian Symposium on Databases, SBBD, pp. 158-171, 2000. [2] J. Golay, M. Kanevski, A new estimator of intrinsic dimension based on the multipoint Morisita index, Pattern Recognition 48(12), pp. 4070-4081, 2015. [3] J. Golay, M. Kanevski, Unsupervised feature selection based on the Morisita estimator of intrinsic dimension, arXiv:1608.05581, 2016.
Visualization of suspicious lesions in breast MRI based on intelligent neural systems

NASA Astrophysics Data System (ADS)

Twellmann, Thorsten; Lange, Oliver; Nattkemper, Tim Wilhelm; Meyer-Bäse, Anke

2006-05-01

Intelligent medical systems based on supervised and unsupervised artificial neural networks are applied to the automatic visualization and classification of suspicious lesions in breast MRI. These systems represent an important component of future sophisticated computer-aided diagnosis systems and enable the extraction of spatial and temporal features of dynamic MRI data stemming from patients with confirmed lesion diagnosis. By taking into account the heterogenity of the cancerous tissue, these techniques reveal the malignant, benign and normal kinetic signals and and provide a regional subclassification of pathological breast tissue. Intelligent medical systems are expected to have substantial implications in healthcare politics by contributing to the diagnosis of indeterminate breast lesions by non-invasive imaging.
Near ground level sensing for spatial analysis of vegetation

NASA Technical Reports Server (NTRS)

Sauer, Tom; Rasure, John; Gage, Charlie

1991-01-01

Measured changes in vegetation indicate the dynamics of ecological processes and can identify the impacts from disturbances. Traditional methods of vegetation analysis tend to be slow because they are labor intensive; as a result, these methods are often confined to small local area measurements. Scientists need new algorithms and instruments that will allow them to efficiently study environmental dynamics across a range of different spatial scales. A new methodology that addresses this problem is presented. This methodology includes the acquisition, processing, and presentation of near ground level image data and its corresponding spatial characteristics. The systematic approach taken encompasses a feature extraction process, a supervised and unsupervised classification process, and a region labeling process yielding spatial information.
Adaptive fuzzy leader clustering of complex data sets in pattern recognition

NASA Technical Reports Server (NTRS)

Newton, Scott C.; Pemmaraju, Surya; Mitra, Sunanda

1992-01-01

A modular, unsupervised neural network architecture for clustering and classification of complex data sets is presented. The adaptive fuzzy leader clustering (AFLC) architecture is a hybrid neural-fuzzy system that learns on-line in a stable and efficient manner. The initial classification is performed in two stages: a simple competitive stage and a distance metric comparison stage. The cluster prototypes are then incrementally updated by relocating the centroid positions from fuzzy C-means system equations for the centroids and the membership values. The AFLC algorithm is applied to the Anderson Iris data and laser-luminescent fingerprint image data. It is concluded that the AFLC algorithm successfully classifies features extracted from real data, discrete or continuous.
Automatic segmentation of amyloid plaques in MR images using unsupervised SVM

PubMed Central

Iordanescu, Gheorghe; Venkatasubramanian, Palamadai N.; Wyrwicz, Alice M.

2011-01-01

Deposition of the β-amyloid peptide (Aβ) is an important pathological hallmark of Alzheimer’s disease (AD). However, reliable quantification of amyloid plaques in both human and animal brains remains a challenge. We present here a novel automatic plaque segmentation algorithm based on the intrinsic MR signal characteristics of plaques. This algorithm identifies plaque candidates in MR data by using watershed transform, which extracts regions with low intensities completely surrounded by higher intensity neighbors. These candidates are classified as plaque or non-plaque by an unsupervised learning method using features derived from the MR data intensity. The algorithm performance is validated by comparison with histology. We also demonstrate the algorithm’s ability to detect age-related changes in plaque load ex vivo in 5×FAD APP transgenic mice. To our knowledge, this work represents the first quantitative method for characterizing amyloid plaques in MRI data. The proposed method can be used to describe the spatio-temporal progression of amyloid deposition, which is necessary for understanding the evolution of plaque pathology in mouse models of AD and to evaluate the efficacy of emergent amyloid-targeting therapies in preclinical trials. PMID:22189675
Unsupervised and self-mapping category formation and semantic object recognition for mobile robot vision used in an actual environment

NASA Astrophysics Data System (ADS)

Madokoro, H.; Tsukada, M.; Sato, K.

2013-07-01

This paper presents an unsupervised learning-based object category formation and recognition method for mobile robot vision. Our method has the following features: detection of feature points and description of features using a scale-invariant feature transform (SIFT), selection of target feature points using one class support vector machines (OC-SVMs), generation of visual words using self-organizing maps (SOMs), formation of labels using adaptive resonance theory 2 (ART-2), and creation and classification of categories on a category map of counter propagation networks (CPNs) for visualizing spatial relations between categories. Classification results of dynamic images using time-series images obtained using two different-size robots and according to movements respectively demonstrate that our method can visualize spatial relations of categories while maintaining time-series characteristics. Moreover, we emphasize the effectiveness of our method for category formation of appearance changes of objects.
Neural network-based multiple robot simultaneous localization and mapping.

PubMed

Saeedi, Sajad; Paull, Liam; Trentini, Michael; Li, Howard

2011-12-01

In this paper, a decentralized platform for simultaneous localization and mapping (SLAM) with multiple robots is developed. Each robot performs single robot view-based SLAM using an extended Kalman filter to fuse data from two encoders and a laser ranger. To extend this approach to multiple robot SLAM, a novel occupancy grid map fusion algorithm is proposed. Map fusion is achieved through a multistep process that includes image preprocessing, map learning (clustering) using neural networks, relative orientation extraction using norm histogram cross correlation and a Radon transform, relative translation extraction using matching norm vectors, and then verification of the results. The proposed map learning method is a process based on the self-organizing map. In the learning phase, the obstacles of the map are learned by clustering the occupied cells of the map into clusters. The learning is an unsupervised process which can be done on the fly without any need to have output training patterns. The clusters represent the spatial form of the map and make further analyses of the map easier and faster. Also, clusters can be interpreted as features extracted from the occupancy grid map so the map fusion problem becomes a task of matching features. Results of the experiments from tests performed on a real environment with multiple robots prove the effectiveness of the proposed solution.
Unsupervised Online Classifier in Sleep Scoring for Sleep Deprivation Studies

PubMed Central

Libourel, Paul-Antoine; Corneyllie, Alexandra; Luppi, Pierre-Hervé; Chouvet, Guy; Gervasoni, Damien

2015-01-01

Study Objective: This study was designed to evaluate an unsupervised adaptive algorithm for real-time detection of sleep and wake states in rodents. Design: We designed a Bayesian classifier that automatically extracts electroencephalogram (EEG) and electromyogram (EMG) features and categorizes non-overlapping 5-s epochs into one of the three major sleep and wake states without any human supervision. This sleep-scoring algorithm is coupled online with a new device to perform selective paradoxical sleep deprivation (PSD). Settings: Controlled laboratory settings for chronic polygraphic sleep recordings and selective PSD. Participants: Ten adult Sprague-Dawley rats instrumented for chronic polysomnographic recordings Measurements: The performance of the algorithm is evaluated by comparison with the score obtained by a human expert reader. Online detection of PS is then validated with a PSD protocol with duration of 72 hours. Results: Our algorithm gave a high concordance with human scoring with an average κ coefficient > 70%. Notably, the specificity to detect PS reached 92%. Selective PSD using real-time detection of PS strongly reduced PS amounts, leaving only brief PS bouts necessary for the detection of PS in EEG and EMG signals (4.7 ± 0.7% over 72 h, versus 8.9 ± 0.5% in baseline), and was followed by a significant PS rebound (23.3 ± 3.3% over 150 minutes). Conclusions: Our fully unsupervised data-driven algorithm overcomes some limitations of the other automated methods such as the selection of representative descriptors or threshold settings. When used online and coupled with our sleep deprivation device, it represents a better option for selective PSD than other methods like the tedious gentle handling or the platform method. Citation: Libourel PA, Corneyllie A, Luppi PH, Chouvet G, Gervasoni D. Unsupervised online classifier in sleep scoring for sleep deprivation studies. SLEEP 2015;38(5):815–828. PMID:25325478
Evaluation of solar angle variation over digital processing of LANDSAT imagery. [Brazil

NASA Technical Reports Server (NTRS)

Parada, N. D. J. (Principal Investigator); Novo, E. M. L. M.

1984-01-01

The effects of the seasonal variation of illumination over digital processing of LANDSAT images are evaluated. Original images are transformed by means of digital filtering to enhance their spatial features. The resulting images are used to obtain an unsupervised classification of relief units. After defining relief classes, which are supposed to be spectrally different, topographic variables (declivity, altitude, relief range and slope length) are used to identify the true relief units existing on the ground. The samples are also clustered by means of an unsupervised classification option. The results obtained for each LANDSAT overpass are compared. Digital processing is highly affected by illumination geometry. There is no correspondence between relief units as defined by spectral features and those resulting from topographic features.
A novel method for intelligent fault diagnosis of rolling bearings using ensemble deep auto-encoders

NASA Astrophysics Data System (ADS)

Shao, Haidong; Jiang, Hongkai; Lin, Ying; Li, Xingqiu

2018-03-01

Automatic and accurate identification of rolling bearings fault categories, especially for the fault severities and fault orientations, is still a major challenge in rotating machinery fault diagnosis. In this paper, a novel method called ensemble deep auto-encoders (EDAEs) is proposed for intelligent fault diagnosis of rolling bearings. Firstly, different activation functions are employed as the hidden functions to design a series of auto-encoders (AEs) with different characteristics. Secondly, EDAEs are constructed with various auto-encoders for unsupervised feature learning from the measured vibration signals. Finally, a combination strategy is designed to ensure accurate and stable diagnosis results. The proposed method is applied to analyze the experimental bearing vibration signals. The results confirm that the proposed method can get rid of the dependence on manual feature extraction and overcome the limitations of individual deep learning models, which is more effective than the existing intelligent diagnosis methods.
Comprehensive machine learning analysis of Hydra behavior reveals a stable basal behavioral repertoire

PubMed Central

Taralova, Ekaterina; Dupre, Christophe; Yuste, Rafael

2018-01-01

Animal behavior has been studied for centuries, but few efficient methods are available to automatically identify and classify it. Quantitative behavioral studies have been hindered by the subjective and imprecise nature of human observation, and the slow speed of annotating behavioral data. Here, we developed an automatic behavior analysis pipeline for the cnidarian Hydra vulgaris using machine learning. We imaged freely behaving Hydra, extracted motion and shape features from the videos, and constructed a dictionary of visual features to classify pre-defined behaviors. We also identified unannotated behaviors with unsupervised methods. Using this analysis pipeline, we quantified 6 basic behaviors and found surprisingly similar behavior statistics across animals within the same species, regardless of experimental conditions. Our analysis indicates that the fundamental behavioral repertoire of Hydra is stable. This robustness could reflect a homeostatic neural control of "housekeeping" behaviors which could have been already present in the earliest nervous systems. PMID:29589829
Feature extraction for ultrasonic sensor based defect detection in ceramic components

NASA Astrophysics Data System (ADS)

Kesharaju, Manasa; Nagarajah, Romesh

2014-02-01

High density silicon carbide materials are commonly used as the ceramic element of hard armour inserts used in traditional body armour systems to reduce their weight, while providing improved hardness, strength and elastic response to stress. Currently, armour ceramic tiles are inspected visually offline using an X-ray technique that is time consuming and very expensive. In addition, from X-rays multiple defects are also misinterpreted as single defects. Therefore, to address these problems the ultrasonic non-destructive approach is being investigated. Ultrasound based inspection would be far more cost effective and reliable as the methodology is applicable for on-line quality control including implementation of accept/reject criteria. This paper describes a recently developed methodology to detect, locate and classify various manufacturing defects in ceramic tiles using sub band coding of ultrasonic test signals. The wavelet transform is applied to the ultrasonic signal and wavelet coefficients in the different frequency bands are extracted and used as input features to an artificial neural network (ANN) for purposes of signal classification. Two different classifiers, using artificial neural networks (supervised) and clustering (un-supervised) are supplied with features selected using Principal Component Analysis(PCA) and their classification performance compared. This investigation establishes experimentally that Principal Component Analysis(PCA) can be effectively used as a feature selection method that provides superior results for classifying various defects in the context of ultrasonic inspection in comparison with the X-ray technique.
Unsupervised automated high throughput phenotyping of RNAi time-lapse movies.

PubMed

Failmezger, Henrik; Fröhlich, Holger; Tresch, Achim

2013-10-04

Gene perturbation experiments in combination with fluorescence time-lapse cell imaging are a powerful tool in reverse genetics. High content applications require tools for the automated processing of the large amounts of data. These tools include in general several image processing steps, the extraction of morphological descriptors, and the grouping of cells into phenotype classes according to their descriptors. This phenotyping can be applied in a supervised or an unsupervised manner. Unsupervised methods are suitable for the discovery of formerly unknown phenotypes, which are expected to occur in high-throughput RNAi time-lapse screens. We developed an unsupervised phenotyping approach based on Hidden Markov Models (HMMs) with multivariate Gaussian emissions for the detection of knockdown-specific phenotypes in RNAi time-lapse movies. The automated detection of abnormal cell morphologies allows us to assign a phenotypic fingerprint to each gene knockdown. By applying our method to the Mitocheck database, we show that a phenotypic fingerprint is indicative of a gene's function. Our fully unsupervised HMM-based phenotyping is able to automatically identify cell morphologies that are specific for a certain knockdown. Beyond the identification of genes whose knockdown affects cell morphology, phenotypic fingerprints can be used to find modules of functionally related genes.
Learning relevant features of data with multi-scale tensor networks

NASA Astrophysics Data System (ADS)

Miles Stoudenmire, E.

2018-07-01

Inspired by coarse-graining approaches used in physics, we show how similar algorithms can be adapted for data. The resulting algorithms are based on layered tree tensor networks and scale linearly with both the dimension of the input and the training set size. Computing most of the layers with an unsupervised algorithm, then optimizing just the top layer for supervised classification of the MNIST and fashion MNIST data sets gives very good results. We also discuss mixing a prior guess for supervised weights together with an unsupervised representation of the data, yielding a smaller number of features nevertheless able to give good performance.
An unsupervised technique for optimal feature selection in attribute profiles for spectral-spatial classification of hyperspectral images

NASA Astrophysics Data System (ADS)

Bhardwaj, Kaushal; Patra, Swarnajyoti

2018-04-01

Inclusion of spatial information along with spectral features play a significant role in classification of remote sensing images. Attribute profiles have already proved their ability to represent spatial information. In order to incorporate proper spatial information, multiple attributes are required and for each attribute large profiles need to be constructed by varying the filter parameter values within a wide range. Thus, the constructed profiles that represent spectral-spatial information of an hyperspectral image have huge dimension which leads to Hughes phenomenon and increases computational burden. To mitigate these problems, this work presents an unsupervised feature selection technique that selects a subset of filtered image from the constructed high dimensional multi-attribute profile which are sufficiently informative to discriminate well among classes. In this regard the proposed technique exploits genetic algorithms (GAs). The fitness function of GAs are defined in an unsupervised way with the help of mutual information. The effectiveness of the proposed technique is assessed using one-against-all support vector machine classifier. The experiments conducted on three hyperspectral data sets show the robustness of the proposed method in terms of computation time and classification accuracy.
The oligonucleotide frequency derived error gradient and its application to the binning of metagenome fragments

PubMed Central

2009-01-01

Background The characterisation, or binning, of metagenome fragments is an important first step to further downstream analysis of microbial consortia. Here, we propose a one-dimensional signature, OFDEG, derived from the oligonucleotide frequency profile of a DNA sequence, and show that it is possible to obtain a meaningful phylogenetic signal for relatively short DNA sequences. The one-dimensional signal is essentially a compact representation of higher dimensional feature spaces of greater complexity and is intended to improve on the tetranucleotide frequency feature space preferred by current compositional binning methods. Results We compare the fidelity of OFDEG against tetranucleotide frequency in both an unsupervised and semi-supervised setting on simulated metagenome benchmark data. Four tests were conducted using assembler output of Arachne and phrap, and for each, performance was evaluated on contigs which are greater than or equal to 8 kbp in length and contigs which are composed of at least 10 reads. Using both G-C content in conjunction with OFDEG gave an average accuracy of 96.75% (semi-supervised) and 95.19% (unsupervised), versus 94.25% (semi-supervised) and 82.35% (unsupervised) for tetranucleotide frequency. Conclusion We have presented an observation of an alternative characteristic of DNA sequences. The proposed feature representation has proven to be more beneficial than the existing tetranucleotide frequency space to the metagenome binning problem. We do note, however, that our observation of OFDEG deserves further anlaysis and investigation. Unsupervised clustering revealed OFDEG related features performed better than standard tetranucleotide frequency in representing a relevant organism specific signal. Further improvement in binning accuracy is given by semi-supervised classification using OFDEG. The emphasis on a feature-driven, bottom-up approach to the problem of binning reveals promising avenues for future development of techniques to characterise short environmental sequences without bias toward cultivable organisms. PMID:19958473
Incorporating High-Frequency Physiologic Data Using Computational Dictionary Learning Improves Prediction of Delayed Cerebral Ischemia Compared to Existing Methods.

PubMed

Megjhani, Murad; Terilli, Kalijah; Frey, Hans-Peter; Velazquez, Angela G; Doyle, Kevin William; Connolly, Edward Sander; Roh, David Jinou; Agarwal, Sachin; Claassen, Jan; Elhadad, Noemie; Park, Soojin

2018-01-01

Accurate prediction of delayed cerebral ischemia (DCI) after subarachnoid hemorrhage (SAH) can be critical for planning interventions to prevent poor neurological outcome. This paper presents a model using convolution dictionary learning to extract features from physiological data available from bedside monitors. We develop and validate a prediction model for DCI after SAH, demonstrating improved precision over standard methods alone. 488 consecutive SAH admissions from 2006 to 2014 to a tertiary care hospital were included. Models were trained on 80%, while 20% were set aside for validation testing. Modified Fisher Scale was considered the standard grading scale in clinical use; baseline features also analyzed included age, sex, Hunt-Hess, and Glasgow Coma Scales. An unsupervised approach using convolution dictionary learning was used to extract features from physiological time series (systolic blood pressure and diastolic blood pressure, heart rate, respiratory rate, and oxygen saturation). Classifiers (partial least squares and linear and kernel support vector machines) were trained on feature subsets of the derivation dataset. Models were applied to the validation dataset. The performances of the best classifiers on the validation dataset are reported by feature subset. Standard grading scale (mFS): AUC 0.54. Combined demographics and grading scales (baseline features): AUC 0.63. Kernel derived physiologic features: AUC 0.66. Combined baseline and physiologic features with redundant feature reduction: AUC 0.71 on derivation dataset and 0.78 on validation dataset. Current DCI prediction tools rely on admission imaging and are advantageously simple to employ. However, using an agnostic and computationally inexpensive learning approach for high-frequency physiologic time series data, we demonstrated that we could incorporate individual physiologic data to achieve higher classification accuracy.
Filtering large-scale event collections using a combination of supervised and unsupervised learning for event trigger classification.

PubMed

Mehryary, Farrokh; Kaewphan, Suwisa; Hakala, Kai; Ginter, Filip

2016-01-01

Biomedical event extraction is one of the key tasks in biomedical text mining, supporting various applications such as database curation and hypothesis generation. Several systems, some of which have been applied at a large scale, have been introduced to solve this task. Past studies have shown that the identification of the phrases describing biological processes, also known as trigger detection, is a crucial part of event extraction, and notable overall performance gains can be obtained by solely focusing on this sub-task. In this paper we propose a novel approach for filtering falsely identified triggers from large-scale event databases, thus improving the quality of knowledge extraction. Our method relies on state-of-the-art word embeddings, event statistics gathered from the whole biomedical literature, and both supervised and unsupervised machine learning techniques. We focus on EVEX, an event database covering the whole PubMed and PubMed Central Open Access literature containing more than 40 million extracted events. The top most frequent EVEX trigger words are hierarchically clustered, and the resulting cluster tree is pruned to identify words that can never act as triggers regardless of their context. For rarely occurring trigger words we introduce a supervised approach trained on the combination of trigger word classification produced by the unsupervised clustering method and manual annotation. The method is evaluated on the official test set of BioNLP Shared Task on Event Extraction. The evaluation shows that the method can be used to improve the performance of the state-of-the-art event extraction systems. This successful effort also translates into removing 1,338,075 of potentially incorrect events from EVEX, thus greatly improving the quality of the data. The method is not solely bound to the EVEX resource and can be thus used to improve the quality of any event extraction system or database. The data and source code for this work are available at: http://bionlp-www.utu.fi/trigger-clustering/.
Unsupervised segmentation of lung fields in chest radiographs using multiresolution fractal feature vector and deformable models.

PubMed

Lee, Wen-Li; Chang, Koyin; Hsieh, Kai-Sheng

2016-09-01

Segmenting lung fields in a chest radiograph is essential for automatically analyzing an image. We present an unsupervised method based on multiresolution fractal feature vector. The feature vector characterizes the lung field region effectively. A fuzzy c-means clustering algorithm is then applied to obtain a satisfactory initial contour. The final contour is obtained by deformable models. The results show the feasibility and high performance of the proposed method. Furthermore, based on the segmentation of lung fields, the cardiothoracic ratio (CTR) can be measured. The CTR is a simple index for evaluating cardiac hypertrophy. After identifying a suspicious symptom based on the estimated CTR, a physician can suggest that the patient undergoes additional extensive tests before a treatment plan is finalized.
Metric Learning for Hyperspectral Image Segmentation

NASA Technical Reports Server (NTRS)

Bue, Brian D.; Thompson, David R.; Gilmore, Martha S.; Castano, Rebecca

2011-01-01

We present a metric learning approach to improve the performance of unsupervised hyperspectral image segmentation. Unsupervised spatial segmentation can assist both user visualization and automatic recognition of surface features. Analysts can use spatially-continuous segments to decrease noise levels and/or localize feature boundaries. However, existing segmentation methods use tasks-agnostic measures of similarity. Here we learn task-specific similarity measures from training data, improving segment fidelity to classes of interest. Multiclass Linear Discriminate Analysis produces a linear transform that optimally separates a labeled set of training classes. The defines a distance metric that generalized to a new scenes, enabling graph-based segmentation that emphasizes key spectral features. We describe tests based on data from the Compact Reconnaissance Imaging Spectrometer (CRISM) in which learned metrics improve segment homogeneity with respect to mineralogical classes.

Land use and land cover classification for rural residential areas in China using soft-probability cascading of multifeatures

NASA Astrophysics Data System (ADS)

Zhang, Bin; Liu, Yueyan; Zhang, Zuyu; Shen, Yonglin

2017-10-01

A multifeature soft-probability cascading scheme to solve the problem of land use and land cover (LULC) classification using high-spatial-resolution images to map rural residential areas in China is proposed. The proposed method is used to build midlevel LULC features. Local features are frequently considered as low-level feature descriptors in a midlevel feature learning method. However, spectral and textural features, which are very effective low-level features, are neglected. The acquisition of the dictionary of sparse coding is unsupervised, and this phenomenon reduces the discriminative power of the midlevel feature. Thus, we propose to learn supervised features based on sparse coding, a support vector machine (SVM) classifier, and a conditional random field (CRF) model to utilize the different effective low-level features and improve the discriminability of midlevel feature descriptors. First, three kinds of typical low-level features, namely, dense scale-invariant feature transform, gray-level co-occurrence matrix, and spectral features, are extracted separately. Second, combined with sparse coding and the SVM classifier, the probabilities of the different LULC classes are inferred to build supervised feature descriptors. Finally, the CRF model, which consists of two parts: unary potential and pairwise potential, is employed to construct an LULC classification map. Experimental results show that the proposed classification scheme can achieve impressive performance when the total accuracy reached about 87%.
Weighted Distance Functions Improve Analysis of High-Dimensional Data: Application to Molecular Dynamics Simulations.

PubMed

Blöchliger, Nicolas; Caflisch, Amedeo; Vitalis, Andreas

2015-11-10

Data mining techniques depend strongly on how the data are represented and how distance between samples is measured. High-dimensional data often contain a large number of irrelevant dimensions (features) for a given query. These features act as noise and obfuscate relevant information. Unsupervised approaches to mine such data require distance measures that can account for feature relevance. Molecular dynamics simulations produce high-dimensional data sets describing molecules observed in time. Here, we propose to globally or locally weight simulation features based on effective rates. This emphasizes, in a data-driven manner, slow degrees of freedom that often report on the metastable states sampled by the molecular system. We couple this idea to several unsupervised learning protocols. Our approach unmasks slow side chain dynamics within the native state of a miniprotein and reveals additional metastable conformations of a protein. The approach can be combined with most algorithms for clustering or dimensionality reduction.
A graph lattice approach to maintaining and learning dense collections of subgraphs as image features.

PubMed

Saund, Eric

2013-10-01

Effective object and scene classification and indexing depend on extraction of informative image features. This paper shows how large families of complex image features in the form of subgraphs can be built out of simpler ones through construction of a graph lattice—a hierarchy of related subgraphs linked in a lattice. Robustness is achieved by matching many overlapping and redundant subgraphs, which allows the use of inexpensive exact graph matching, instead of relying on expensive error-tolerant graph matching to a minimal set of ideal model graphs. Efficiency in exact matching is gained by exploitation of the graph lattice data structure. Additionally, the graph lattice enables methods for adaptively growing a feature space of subgraphs tailored to observed data. We develop the approach in the domain of rectilinear line art, specifically for the practical problem of document forms recognition. We are especially interested in methods that require only one or very few labeled training examples per category. We demonstrate two approaches to using the subgraph features for this purpose. Using a bag-of-words feature vector we achieve essentially single-instance learning on a benchmark forms database, following an unsupervised clustering stage. Further performance gains are achieved on a more difficult dataset using a feature voting method and feature selection procedure.
Multilabel user classification using the community structure of online networks

PubMed Central

Papadopoulos, Symeon; Kompatsiaris, Yiannis

2017-01-01

We study the problem of semi-supervised, multi-label user classification of networked data in the online social platform setting. We propose a framework that combines unsupervised community extraction and supervised, community-based feature weighting before training a classifier. We introduce Approximate Regularized Commute-Time Embedding (ARCTE), an algorithm that projects the users of a social graph onto a latent space, but instead of packing the global structure into a matrix of predefined rank, as many spectral and neural representation learning methods do, it extracts local communities for all users in the graph in order to learn a sparse embedding. To this end, we employ an improvement of personalized PageRank algorithms for searching locally in each user’s graph structure. Then, we perform supervised community feature weighting in order to boost the importance of highly predictive communities. We assess our method performance on the problem of user classification by performing an extensive comparative study among various recent methods based on graph embeddings. The comparison shows that ARCTE significantly outperforms the competition in almost all cases, achieving up to 35% relative improvement compared to the second best competing method in terms of F1-score. PMID:28278242
Multilabel user classification using the community structure of online networks.

PubMed

Rizos, Georgios; Papadopoulos, Symeon; Kompatsiaris, Yiannis

2017-01-01

We study the problem of semi-supervised, multi-label user classification of networked data in the online social platform setting. We propose a framework that combines unsupervised community extraction and supervised, community-based feature weighting before training a classifier. We introduce Approximate Regularized Commute-Time Embedding (ARCTE), an algorithm that projects the users of a social graph onto a latent space, but instead of packing the global structure into a matrix of predefined rank, as many spectral and neural representation learning methods do, it extracts local communities for all users in the graph in order to learn a sparse embedding. To this end, we employ an improvement of personalized PageRank algorithms for searching locally in each user's graph structure. Then, we perform supervised community feature weighting in order to boost the importance of highly predictive communities. We assess our method performance on the problem of user classification by performing an extensive comparative study among various recent methods based on graph embeddings. The comparison shows that ARCTE significantly outperforms the competition in almost all cases, achieving up to 35% relative improvement compared to the second best competing method in terms of F1-score.
Detection of compensatory balance responses using wearable electromyography sensors for fall-risk assessment.

PubMed

Nouredanesh, Mina; Kukreja, Sunil L; Tung, James

2016-08-01

Loss of balance is prevalent in older adults and populations with gait and balance impairments. The present paper aims to develop a method to automatically distinguish compensatory balance responses (CBRs) from normal gait, based on activity patterns of muscles involved in maintaining balance. In this study, subjects were perturbed by lateral pushes while walking and surface electromyography (sEMG) signals were recorded from four muscles in their right leg. To extract sEMG time domain features, several filtering characteristics and segmentation approaches are examined. The performance of three classification methods, i.e., k-nearest neighbor, support vector machines, and random forests, were investigated for accurate detection of CBRs. Our results show that features extracted in the 50-200Hz band, segmented using peak sEMG amplitudes, and a random forest classifier detected CBRs with an accuracy of 92.35%. Moreover, our results support the important role of biceps femoris and rectus femoris muscles in stabilization and consequently discerning CBRs. This study contributes towards the development of wearable sensor systems to accurately and reliably monitor gait and balance control behavior in at-home settings (unsupervised conditions), over long periods of time, towards personalized fall risk assessment tools.
Automated extraction and classification of time-frequency contours in humpback vocalizations.

PubMed

Ou, Hui; Au, Whitlow W L; Zurk, Lisa M; Lammers, Marc O

2013-01-01

A time-frequency contour extraction and classification algorithm was created to analyze humpback whale vocalizations. The algorithm automatically extracted contours of whale vocalization units by searching for gray-level discontinuities in the spectrogram images. The unit-to-unit similarity was quantified by cross-correlating the contour lines. A library of distinctive humpback units was then generated by applying an unsupervised, cluster-based learning algorithm. The purpose of this study was to provide a fast and automated feature selection tool to describe the vocal signatures of animal groups. This approach could benefit a variety of applications such as species description, identification, and evolution of song structures. The algorithm was tested on humpback whale song data recorded at various locations in Hawaii from 2002 to 2003. Results presented in this paper showed low probability of false alarm (0%-4%) under noisy environments with small boat vessels and snapping shrimp. The classification algorithm was tested on a controlled set of 30 units forming six unit types, and all the units were correctly classified. In a case study on humpback data collected in the Auau Chanel, Hawaii, in 2002, the algorithm extracted 951 units, which were classified into 12 distinctive types.
Empirical Analysis of Exploiting Review Helpfulness for Extractive Summarization of Online Reviews

ERIC Educational Resources Information Center

Xiong, Wenting; Litman, Diane

2014-01-01

We propose a novel unsupervised extractive approach for summarizing online reviews by exploiting review helpfulness ratings. In addition to using the helpfulness ratings for review-level filtering, we suggest using them as the supervision of a topic model for sentence-level content scoring. The proposed method is metadata-driven, requiring no…
Object-oriented feature-tracking algorithms for SAR images of the marginal ice zone

NASA Technical Reports Server (NTRS)

Daida, Jason; Samadani, Ramin; Vesecky, John F.

1990-01-01

An unsupervised method that chooses and applies the most appropriate tracking algorithm from among different sea-ice tracking algorithms is reported. In contrast to current unsupervised methods, this method chooses and applies an algorithm by partially examining a sequential image pair to draw inferences about what was examined. Based on these inferences the reported method subsequently chooses which algorithm to apply to specific areas of the image pair where that algorithm should work best.
Unsupervised online classifier in sleep scoring for sleep deprivation studies.

PubMed

Libourel, Paul-Antoine; Corneyllie, Alexandra; Luppi, Pierre-Hervé; Chouvet, Guy; Gervasoni, Damien

2015-05-01

This study was designed to evaluate an unsupervised adaptive algorithm for real-time detection of sleep and wake states in rodents. We designed a Bayesian classifier that automatically extracts electroencephalogram (EEG) and electromyogram (EMG) features and categorizes non-overlapping 5-s epochs into one of the three major sleep and wake states without any human supervision. This sleep-scoring algorithm is coupled online with a new device to perform selective paradoxical sleep deprivation (PSD). Controlled laboratory settings for chronic polygraphic sleep recordings and selective PSD. Ten adult Sprague-Dawley rats instrumented for chronic polysomnographic recordings. The performance of the algorithm is evaluated by comparison with the score obtained by a human expert reader. Online detection of PS is then validated with a PSD protocol with duration of 72 hours. Our algorithm gave a high concordance with human scoring with an average κ coefficient > 70%. Notably, the specificity to detect PS reached 92%. Selective PSD using real-time detection of PS strongly reduced PS amounts, leaving only brief PS bouts necessary for the detection of PS in EEG and EMG signals (4.7 ± 0.7% over 72 h, versus 8.9 ± 0.5% in baseline), and was followed by a significant PS rebound (23.3 ± 3.3% over 150 minutes). Our fully unsupervised data-driven algorithm overcomes some limitations of the other automated methods such as the selection of representative descriptors or threshold settings. When used online and coupled with our sleep deprivation device, it represents a better option for selective PSD than other methods like the tedious gentle handling or the platform method. © 2015 Associated Professional Sleep Societies, LLC.
Classification of earth terrain using polarimetric synthetic aperture radar images

NASA Technical Reports Server (NTRS)

Lim, H. H.; Swartz, A. A.; Yueh, H. A.; Kong, J. A.; Shin, R. T.; Van Zyl, J. J.

1989-01-01

Supervised and unsupervised classification techniques are developed and used to classify the earth terrain components from SAR polarimetric images of San Francisco Bay and Traverse City, Michigan. The supervised techniques include the Bayes classifiers, normalized polarimetric classification, and simple feature classification using discriminates such as the absolute and normalized magnitude response of individual receiver channel returns and the phase difference between receiver channels. An algorithm is developed as an unsupervised technique which classifies terrain elements based on the relationship between the orientation angle and the handedness of the transmitting and receiving polariation states. It is found that supervised classification produces the best results when accurate classifier training data are used, while unsupervised classification may be applied when training data are not available.
Deep learning-based subdivision approach for large scale macromolecules structure recovery from electron cryo tomograms

PubMed Central

Xu, Min; Chai, Xiaoqi; Muthakana, Hariank; Liang, Xiaodan; Yang, Ge; Zeev-Ben-Mordehai, Tzviya; Xing, Eric P.

2017-01-01

Abstract Motivation: Cellular Electron CryoTomography (CECT) enables 3D visualization of cellular organization at near-native state and in sub-molecular resolution, making it a powerful tool for analyzing structures of macromolecular complexes and their spatial organizations inside single cells. However, high degree of structural complexity together with practical imaging limitations makes the systematic de novo discovery of structures within cells challenging. It would likely require averaging and classifying millions of subtomograms potentially containing hundreds of highly heterogeneous structural classes. Although it is no longer difficult to acquire CECT data containing such amount of subtomograms due to advances in data acquisition automation, existing computational approaches have very limited scalability or discrimination ability, making them incapable of processing such amount of data. Results: To complement existing approaches, in this article we propose a new approach for subdividing subtomograms into smaller but relatively homogeneous subsets. The structures in these subsets can then be separately recovered using existing computation intensive methods. Our approach is based on supervised structural feature extraction using deep learning, in combination with unsupervised clustering and reference-free classification. Our experiments show that, compared with existing unsupervised rotation invariant feature and pose-normalization based approaches, our new approach achieves significant improvements in both discrimination ability and scalability. More importantly, our new approach is able to discover new structural classes and recover structures that do not exist in training data. Availability and Implementation: Source code freely available at http://www.cs.cmu.edu/∼mxu1/software. Contact: mxu1@cs.cmu.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:28881965
Unsupervised learning of natural languages

PubMed Central

Solan, Zach; Horn, David; Ruppin, Eytan; Edelman, Shimon

2005-01-01

We address the problem, fundamental to linguistics, bioinformatics, and certain other disciplines, of using corpora of raw symbolic sequential data to infer underlying rules that govern their production. Given a corpus of strings (such as text, transcribed speech, chromosome or protein sequence data, sheet music, etc.), our unsupervised algorithm recursively distills from it hierarchically structured patterns. The adios (automatic distillation of structure) algorithm relies on a statistical method for pattern extraction and on structured generalization, two processes that have been implicated in language acquisition. It has been evaluated on artificial context-free grammars with thousands of rules, on natural languages as diverse as English and Chinese, and on protein data correlating sequence with function. This unsupervised algorithm is capable of learning complex syntax, generating grammatical novel sentences, and proving useful in other fields that call for structure discovery from raw data, such as bioinformatics. PMID:16087885
Unsupervised learning of natural languages.

PubMed

Solan, Zach; Horn, David; Ruppin, Eytan; Edelman, Shimon

2005-08-16

We address the problem, fundamental to linguistics, bioinformatics, and certain other disciplines, of using corpora of raw symbolic sequential data to infer underlying rules that govern their production. Given a corpus of strings (such as text, transcribed speech, chromosome or protein sequence data, sheet music, etc.), our unsupervised algorithm recursively distills from it hierarchically structured patterns. The adios (automatic distillation of structure) algorithm relies on a statistical method for pattern extraction and on structured generalization, two processes that have been implicated in language acquisition. It has been evaluated on artificial context-free grammars with thousands of rules, on natural languages as diverse as English and Chinese, and on protein data correlating sequence with function. This unsupervised algorithm is capable of learning complex syntax, generating grammatical novel sentences, and proving useful in other fields that call for structure discovery from raw data, such as bioinformatics.
Comparing the Behavior of Polarimetric SAR Imagery (TerraSAR-X and Radarsat-2) for Automated Sea Ice Classification

NASA Astrophysics Data System (ADS)

Ressel, Rudolf; Singha, Suman; Lehner, Susanne

2016-08-01

Arctic Sea ice monitoring has attracted increasing attention over the last few decades. Besides the scientific interest in sea ice, the operational aspect of ice charting is becoming more important due to growing navigational possibilities in an increasingly ice free Arctic. For this purpose, satellite borne SAR imagery has become an invaluable tool. In past, mostly single polarimetric datasets were investigated with supervised or unsupervised classification schemes for sea ice investigation. Despite proven sea ice classification achievements on single polarimetric data, a fully automatic, general purpose classifier for single-pol data has not been established due to large variation of sea ice manifestations and incidence angle impact. Recently, through the advent of polarimetric SAR sensors, polarimetric features have moved into the focus of ice classification research. The higher information content four polarimetric channels promises to offer greater insight into sea ice scattering mechanism and overcome some of the shortcomings of single- polarimetric classifiers. Two spatially and temporally coincident pairs of fully polarimetric acquisitions from the TerraSAR-X/TanDEM-X and RADARSAT-2 satellites are investigated. Proposed supervised classification algorithm consists of two steps: The first step comprises a feature extraction, the results of which are ingested into a neural network classifier in the second step. Based on the common coherency and covariance matrix, we extract a number of features and analyze the relevance and redundancy by means of mutual information for the purpose of sea ice classification. Coherency matrix based features which require an eigendecomposition are found to be either of low relevance or redundant to other covariance matrix based features. Among the most useful features for classification are matrix invariant based features (Geometric Intensity, Scattering Diversity, Surface Scattering Fraction).
Semi-supervised and unsupervised extreme learning machines.

PubMed

Huang, Gao; Song, Shiji; Gupta, Jatinder N D; Wu, Cheng

2014-12-01

Extreme learning machines (ELMs) have proven to be efficient and effective learning mechanisms for pattern classification and regression. However, ELMs are primarily applied to supervised learning problems. Only a few existing research papers have used ELMs to explore unlabeled data. In this paper, we extend ELMs for both semi-supervised and unsupervised tasks based on the manifold regularization, thus greatly expanding the applicability of ELMs. The key advantages of the proposed algorithms are as follows: 1) both the semi-supervised ELM (SS-ELM) and the unsupervised ELM (US-ELM) exhibit learning capability and computational efficiency of ELMs; 2) both algorithms naturally handle multiclass classification or multicluster clustering; and 3) both algorithms are inductive and can handle unseen data at test time directly. Moreover, it is shown in this paper that all the supervised, semi-supervised, and unsupervised ELMs can actually be put into a unified framework. This provides new perspectives for understanding the mechanism of random feature mapping, which is the key concept in ELM theory. Empirical study on a wide range of data sets demonstrates that the proposed algorithms are competitive with the state-of-the-art semi-supervised or unsupervised learning algorithms in terms of accuracy and efficiency.
Unsupervised Scalable Statistical Method for Identifying Influential Users in Online Social Networks.

PubMed

Azcorra, A; Chiroque, L F; Cuevas, R; Fernández Anta, A; Laniado, H; Lillo, R E; Romo, J; Sguera, C

2018-05-03

Billions of users interact intensively every day via Online Social Networks (OSNs) such as Facebook, Twitter, or Google+. This makes OSNs an invaluable source of information, and channel of actuation, for sectors like advertising, marketing, or politics. To get the most of OSNs, analysts need to identify influential users that can be leveraged for promoting products, distributing messages, or improving the image of companies. In this report we propose a new unsupervised method, Massive Unsupervised Outlier Detection (MUOD), based on outliers detection, for providing support in the identification of influential users. MUOD is scalable, and can hence be used in large OSNs. Moreover, it labels the outliers as of shape, magnitude, or amplitude, depending of their features. This allows classifying the outlier users in multiple different classes, which are likely to include different types of influential users. Applying MUOD to a subset of roughly 400 million Google+ users, it has allowed identifying and discriminating automatically sets of outlier users, which present features associated to different definitions of influential users, like capacity to attract engagement, capacity to attract a large number of followers, or high infection capacity.
Comparative study of feature selection with ensemble learning using SOM variants

NASA Astrophysics Data System (ADS)

Filali, Ameni; Jlassi, Chiraz; Arous, Najet

2017-03-01

Ensemble learning has succeeded in the growth of stability and clustering accuracy, but their runtime prohibits them from scaling up to real-world applications. This study deals the problem of selecting a subset of the most pertinent features for every cluster from a dataset. The proposed method is another extension of the Random Forests approach using self-organizing maps (SOM) variants to unlabeled data that estimates the out-of-bag feature importance from a set of partitions. Every partition is created using a various bootstrap sample and a random subset of the features. Then, we show that the process internal estimates are used to measure variable pertinence in Random Forests are also applicable to feature selection in unsupervised learning. This approach aims to the dimensionality reduction, visualization and cluster characterization at the same time. Hence, we provide empirical results on nineteen benchmark data sets indicating that RFS can lead to significant improvement in terms of clustering accuracy, over several state-of-the-art unsupervised methods, with a very limited subset of features. The approach proves promise to treat with very broad domains.
Prioritizing Scientific Data for Transmission

NASA Technical Reports Server (NTRS)

Castano, Rebecca; Anderson, Robert; Estlin, Tara; DeCoste, Dennis; Gaines, Daniel; Mazzoni, Dominic; Fisher, Forest; Judd, Michele

2004-01-01

A software system has been developed for prioritizing newly acquired geological data onboard a planetary rover. The system has been designed to enable efficient use of limited communication resources by transmitting the data likely to have the most scientific value. This software operates onboard a rover by analyzing collected data, identifying potential scientific targets, and then using that information to prioritize data for transmission to Earth. Currently, the system is focused on the analysis of acquired images, although the general techniques are applicable to a wide range of data modalities. Image prioritization is performed using two main steps. In the first step, the software detects features of interest from each image. In its current application, the system is focused on visual properties of rocks. Thus, rocks are located in each image and rock properties, such as shape, texture, and albedo, are extracted from the identified rocks. In the second step, the features extracted from a group of images are used to prioritize the images using three different methods: (1) identification of key target signature (finding specific rock features the scientist has identified as important), (2) novelty detection (finding rocks we haven t seen before), and (3) representative rock sampling (finding the most average sample of each rock type). These methods use techniques such as K-means unsupervised clustering and a discrimination-based kernel classifier to rank images based on their interest level.
Tree leaves extraction in natural images: comparative study of preprocessing tools and segmentation methods.

PubMed

Grand-Brochier, Manuel; Vacavant, Antoine; Cerutti, Guillaume; Kurtz, Camille; Weber, Jonathan; Tougne, Laure

2015-05-01

In this paper, we propose a comparative study of various segmentation methods applied to the extraction of tree leaves from natural images. This study follows the design of a mobile application, developed by Cerutti et al. (published in ReVeS Participation--Tree Species Classification Using Random Forests and Botanical Features. CLEF 2012), to highlight the impact of the choices made for segmentation aspects. All the tests are based on a database of 232 images of tree leaves depicted on natural background from smartphones acquisitions. We also propose to study the improvements, in terms of performance, using preprocessing tools, such as the interaction between the user and the application through an input stroke, as well as the use of color distance maps. The results presented in this paper shows that the method developed by Cerutti et al. (denoted Guided Active Contour), obtains the best score for almost all observation criteria. Finally, we detail our online benchmark composed of 14 unsupervised methods and 6 supervised ones.

Imaging nanoscale lattice variations by machine learning of x-ray diffraction microscopy data

DOE PAGES

Laanait, Nouamane; Zhang, Zhan; Schlepütz, Christian M.

2016-08-09

In this paper, we present a novel methodology based on machine learning to extract lattice variations in crystalline materials, at the nanoscale, from an x-ray Bragg diffraction-based imaging technique. By employing a full-field microscopy setup, we capture real space images of materials, with imaging contrast determined solely by the x-ray diffracted signal. The data sets that emanate from this imaging technique are a hybrid of real space information (image spatial support) and reciprocal lattice space information (image contrast), and are intrinsically multidimensional (5D). By a judicious application of established unsupervised machine learning techniques and multivariate analysis to this multidimensional datamore » cube, we show how to extract features that can be ascribed physical interpretations in terms of common structural distortions, such as lattice tilts and dislocation arrays. Finally, we demonstrate this 'big data' approach to x-ray diffraction microscopy by identifying structural defects present in an epitaxial ferroelectric thin-film of lead zirconate titanate.« less
Imaging nanoscale lattice variations by machine learning of x-ray diffraction microscopy data

DOE Office of Scientific and Technical Information (OSTI.GOV)

Laanait, Nouamane; Zhang, Zhan; Schlepütz, Christian M.

In this paper, we present a novel methodology based on machine learning to extract lattice variations in crystalline materials, at the nanoscale, from an x-ray Bragg diffraction-based imaging technique. By employing a full-field microscopy setup, we capture real space images of materials, with imaging contrast determined solely by the x-ray diffracted signal. The data sets that emanate from this imaging technique are a hybrid of real space information (image spatial support) and reciprocal lattice space information (image contrast), and are intrinsically multidimensional (5D). By a judicious application of established unsupervised machine learning techniques and multivariate analysis to this multidimensional datamore » cube, we show how to extract features that can be ascribed physical interpretations in terms of common structural distortions, such as lattice tilts and dislocation arrays. Finally, we demonstrate this 'big data' approach to x-ray diffraction microscopy by identifying structural defects present in an epitaxial ferroelectric thin-film of lead zirconate titanate.« less
Similarity preserving low-rank representation for enhanced data representation and effective subspace learning.

PubMed

Zhang, Zhao; Yan, Shuicheng; Zhao, Mingbo

2014-05-01

Latent Low-Rank Representation (LatLRR) delivers robust and promising results for subspace recovery and feature extraction through mining the so-called hidden effects, but the locality of both similar principal and salient features cannot be preserved in the optimizations. To solve this issue for achieving enhanced performance, a boosted version of LatLRR, referred to as Regularized Low-Rank Representation (rLRR), is proposed through explicitly including an appropriate Laplacian regularization that can maximally preserve the similarity among local features. Resembling LatLRR, rLRR decomposes given data matrix from two directions by seeking a pair of low-rank matrices. But the similarities of principal and salient features can be effectively preserved by rLRR. As a result, the correlated features are well grouped and the robustness of representations is also enhanced. Based on the outputted bi-directional low-rank codes by rLRR, an unsupervised subspace learning framework termed Low-rank Similarity Preserving Projections (LSPP) is also derived for feature learning. The supervised extension of LSPP is also discussed for discriminant subspace learning. The validity of rLRR is examined by robust representation and decomposition of real images. Results demonstrated the superiority of our rLRR and LSPP in comparison to other related state-of-the-art algorithms. Copyright © 2014 Elsevier Ltd. All rights reserved.
Automatic classification of animal vocalizations

NASA Astrophysics Data System (ADS)

Clemins, Patrick J.

2005-11-01

Bioacoustics, the study of animal vocalizations, has begun to use increasingly sophisticated analysis techniques in recent years. Some common tasks in bioacoustics are repertoire determination, call detection, individual identification, stress detection, and behavior correlation. Each research study, however, uses a wide variety of different measured variables, called features, and classification systems to accomplish these tasks. The well-established field of human speech processing has developed a number of different techniques to perform many of the aforementioned bioacoustics tasks. Melfrequency cepstral coefficients (MFCCs) and perceptual linear prediction (PLP) coefficients are two popular feature sets. The hidden Markov model (HMM), a statistical model similar to a finite autonoma machine, is the most commonly used supervised classification model and is capable of modeling both temporal and spectral variations. This research designs a framework that applies models from human speech processing for bioacoustic analysis tasks. The development of the generalized perceptual linear prediction (gPLP) feature extraction model is one of the more important novel contributions of the framework. Perceptual information from the species under study can be incorporated into the gPLP feature extraction model to represent the vocalizations as the animals might perceive them. By including this perceptual information and modifying parameters of the HMM classification system, this framework can be applied to a wide range of species. The effectiveness of the framework is shown by analyzing African elephant and beluga whale vocalizations. The features extracted from the African elephant data are used as input to a supervised classification system and compared to results from traditional statistical tests. The gPLP features extracted from the beluga whale data are used in an unsupervised classification system and the results are compared to labels assigned by experts. The development of a framework from which to build animal vocalization classifiers will provide bioacoustics researchers with a consistent platform to analyze and classify vocalizations. A common framework will also allow studies to compare results across species and institutions. In addition, the use of automated classification techniques can speed analysis and uncover behavioral correlations not readily apparent using traditional techniques.
An unsupervised video foreground co-localization and segmentation process by incorporating motion cues and frame features

NASA Astrophysics Data System (ADS)

Zhang, Chao; Zhang, Qian; Zheng, Chi; Qiu, Guoping

2018-04-01

Video foreground segmentation is one of the key problems in video processing. In this paper, we proposed a novel and fully unsupervised approach for foreground object co-localization and segmentation of unconstrained videos. We firstly compute both the actual edges and motion boundaries of the video frames, and then align them by their HOG feature maps. Then, by filling the occlusions generated by the aligned edges, we obtained more precise masks about the foreground object. Such motion-based masks could be derived as the motion-based likelihood. Moreover, the color-base likelihood is adopted for the segmentation process. Experimental Results show that our approach outperforms most of the State-of-the-art algorithms.
Urban Shanty Town Recognition Based on High-Resolution Remote Sensing Images and National Geographical Monitoring Features - a Case Study of Nanning City

NASA Astrophysics Data System (ADS)

He, Y.; He, Y.

2018-04-01

Urban shanty towns are communities that has contiguous old and dilapidated houses with more than 2000 square meters built-up area or more than 50 households. This study makes attempts to extract shanty towns in Nanning City using the product of Census and TripleSat satellite images. With 0.8-meter high-resolution remote sensing images, five texture characteristics (energy, contrast, maximum probability, and inverse difference moment) of shanty towns are trained and analyzed through GLCM. In this study, samples of shanty town are well classified with 98.2 % producer accuracy of unsupervised classification and 73.2 % supervised classification correctness. Low-rise and mid-rise residential blocks in Nanning City are classified into 4 different types by using k-means clustering and nearest neighbour classification respectively. This study initially establish texture feature descriptions of different types of residential areas, especially low-rise and mid-rise buildings, which would help city administrator evaluate residential blocks and reconstruction shanty towns.
Comprehensive machine learning analysis of Hydra behavior reveals a stable basal behavioral repertoire.

PubMed

Han, Shuting; Taralova, Ekaterina; Dupre, Christophe; Yuste, Rafael

2018-03-28

Animal behavior has been studied for centuries, but few efficient methods are available to automatically identify and classify it. Quantitative behavioral studies have been hindered by the subjective and imprecise nature of human observation, and the slow speed of annotating behavioral data. Here, we developed an automatic behavior analysis pipeline for the cnidarian Hydra vulgaris using machine learning. We imaged freely behaving Hydra , extracted motion and shape features from the videos, and constructed a dictionary of visual features to classify pre-defined behaviors. We also identified unannotated behaviors with unsupervised methods. Using this analysis pipeline, we quantified 6 basic behaviors and found surprisingly similar behavior statistics across animals within the same species, regardless of experimental conditions. Our analysis indicates that the fundamental behavioral repertoire of Hydra is stable. This robustness could reflect a homeostatic neural control of "housekeeping" behaviors which could have been already present in the earliest nervous systems. © 2018, Han et al.
A Tale of Two Paradigms: Disambiguating Extracted Entities with Applications to a Digital Library and the Web

ERIC Educational Resources Information Center

Huang, Jian

2010-01-01

With the increasing wealth of information on the Web, information integration is ubiquitous as the same real-world entity may appear in a variety of forms extracted from different sources. This dissertation proposes supervised and unsupervised algorithms that are naturally integrated in a scalable framework to solve the entity resolution problem,…
Perceptual Learning via Modification of Cortical Top-Down Signals

PubMed Central

Schäfer, Roland; Vasilaki, Eleni; Senn, Walter

2007-01-01

The primary visual cortex (V1) is pre-wired to facilitate the extraction of behaviorally important visual features. Collinear edge detectors in V1, for instance, mutually enhance each other to improve the perception of lines against a noisy background. The same pre-wiring that facilitates line extraction, however, is detrimental when subjects have to discriminate the brightness of different line segments. How is it possible to improve in one task by unsupervised practicing, without getting worse in the other task? The classical view of perceptual learning is that practicing modulates the feedforward input stream through synaptic modifications onto or within V1. However, any rewiring of V1 would deteriorate other perceptual abilities different from the trained one. We propose a general neuronal model showing that perceptual learning can modulate top-down input to V1 in a task-specific way while feedforward and lateral pathways remain intact. Consistent with biological data, the model explains how context-dependent brightness discrimination is improved by a top-down recruitment of recurrent inhibition and a top-down induced increase of the neuronal gain within V1. Both the top-down modulation of inhibition and of neuronal gain are suggested to be universal features of cortical microcircuits which enable perceptual learning. PMID:17715996
Unsupervised spatiotemporal analysis of fMRI data using graph-based visualizations of self-organizing maps.

PubMed

Katwal, Santosh B; Gore, John C; Marois, Rene; Rogers, Baxter P

2013-09-01

We present novel graph-based visualizations of self-organizing maps for unsupervised functional magnetic resonance imaging (fMRI) analysis. A self-organizing map is an artificial neural network model that transforms high-dimensional data into a low-dimensional (often a 2-D) map using unsupervised learning. However, a postprocessing scheme is necessary to correctly interpret similarity between neighboring node prototypes (feature vectors) on the output map and delineate clusters and features of interest in the data. In this paper, we used graph-based visualizations to capture fMRI data features based upon 1) the distribution of data across the receptive fields of the prototypes (density-based connectivity); and 2) temporal similarities (correlations) between the prototypes (correlation-based connectivity). We applied this approach to identify task-related brain areas in an fMRI reaction time experiment involving a visuo-manual response task, and we correlated the time-to-peak of the fMRI responses in these areas with reaction time. Visualization of self-organizing maps outperformed independent component analysis and voxelwise univariate linear regression analysis in identifying and classifying relevant brain regions. We conclude that the graph-based visualizations of self-organizing maps help in advanced visualization of cluster boundaries in fMRI data enabling the separation of regions with small differences in the timings of their brain responses.
Artificial neural networks for acoustic target recognition

NASA Astrophysics Data System (ADS)

Robertson, James A.; Mossing, John C.; Weber, Bruce A.

1995-04-01

Acoustic sensors can be used to detect, track and identify non-line-of-sight targets passively. Attempts to alter acoustic emissions often result in an undesirable performance degradation. This research project investigates the use of neural networks for differentiating between features extracted from the acoustic signatures of sources. Acoustic data were filtered and digitized using a commercially available analog-digital convertor. The digital data was transformed to the frequency domain for additional processing using the FFT. Narrowband peak detection algorithms were incorporated to select peaks above a user defined SNR. These peaks were then used to generate a set of robust features which relate specifically to target components in varying background conditions. The features were then used as input into a backpropagation neural network. A K-means unsupervised clustering algorithm was used to determine the natural clustering of the observations. Comparisons between a feature set consisting of the normalized amplitudes of the first 250 frequency bins of the power spectrum and a set of 11 harmonically related features were made. Initial results indicate that even though some different target types had a tendency to group in the same clusters, the neural network was able to differentiate the targets. Successful identification of acoustic sources under varying operational conditions with high confidence levels was achieved.
Physics-Based Image Segmentation Using First Order Statistical Properties and Genetic Algorithm for Inductive Thermography Imaging.

PubMed

Gao, Bin; Li, Xiaoqing; Woo, Wai Lok; Tian, Gui Yun

2018-05-01

Thermographic inspection has been widely applied to non-destructive testing and evaluation with the capabilities of rapid, contactless, and large surface area detection. Image segmentation is considered essential for identifying and sizing defects. To attain a high-level performance, specific physics-based models that describe defects generation and enable the precise extraction of target region are of crucial importance. In this paper, an effective genetic first-order statistical image segmentation algorithm is proposed for quantitative crack detection. The proposed method automatically extracts valuable spatial-temporal patterns from unsupervised feature extraction algorithm and avoids a range of issues associated with human intervention in laborious manual selection of specific thermal video frames for processing. An internal genetic functionality is built into the proposed algorithm to automatically control the segmentation threshold to render enhanced accuracy in sizing the cracks. Eddy current pulsed thermography will be implemented as a platform to demonstrate surface crack detection. Experimental tests and comparisons have been conducted to verify the efficacy of the proposed method. In addition, a global quantitative assessment index F-score has been adopted to objectively evaluate the performance of different segmentation algorithms.
A consensus embedding approach for segmentation of high resolution in vivo prostate magnetic resonance imagery

NASA Astrophysics Data System (ADS)

Viswanath, Satish; Rosen, Mark; Madabhushi, Anant

2008-03-01

Current techniques for localization of prostatic adenocarcinoma (CaP) via blinded trans-rectal ultrasound biopsy are associated with a high false negative detection rate. While high resolution endorectal in vivo Magnetic Resonance (MR) prostate imaging has been shown to have improved contrast and resolution for CaP detection over ultrasound, similarity in intensity characteristics between benign and cancerous regions on MR images contribute to a high false positive detection rate. In this paper, we present a novel unsupervised segmentation method that employs manifold learning via consensus schemes for detection of cancerous regions from high resolution 1.5 Tesla (T) endorectal in vivo prostate MRI. A significant contribution of this paper is a method to combine multiple weak, lower-dimensional representations of high dimensional feature data in a way analogous to classifier ensemble schemes, and hence create a stable and accurate reduced dimensional representation. After correcting for MR image intensity artifacts, such as bias field inhomogeneity and intensity non-standardness, our algorithm extracts over 350 3D texture features at every spatial location in the MR scene at multiple scales and orientations. Non-linear dimensionality reduction schemes such as Locally Linear Embedding (LLE) and Graph Embedding (GE) are employed to create multiple low dimensional data representations of this high dimensional texture feature space. Our novel consensus embedding method is used to average object adjacencies from within the multiple low dimensional projections so that class relationships are preserved. Unsupervised consensus clustering is then used to partition the objects in this consensus embedding space into distinct classes. Quantitative evaluation on 18 1.5 T prostate MR data against corresponding histology obtained from the multi-site ACRIN trials show a sensitivity of 92.65% and a specificity of 82.06%, which suggests that our method is successfully able to detect suspicious regions in the prostate.
An Event-Driven Classifier for Spiking Neural Networks Fed with Synthetic or Dynamic Vision Sensor Data.

PubMed

Stromatias, Evangelos; Soto, Miguel; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabé

2017-01-01

This paper introduces a novel methodology for training an event-driven classifier within a Spiking Neural Network (SNN) System capable of yielding good classification results when using both synthetic input data and real data captured from Dynamic Vision Sensor (DVS) chips. The proposed supervised method uses the spiking activity provided by an arbitrary topology of prior SNN layers to build histograms and train the classifier in the frame domain using the stochastic gradient descent algorithm. In addition, this approach can cope with leaky integrate-and-fire neuron models within the SNN, a desirable feature for real-world SNN applications, where neural activation must fade away after some time in the absence of inputs. Consequently, this way of building histograms captures the dynamics of spikes immediately before the classifier. We tested our method on the MNIST data set using different synthetic encodings and real DVS sensory data sets such as N-MNIST, MNIST-DVS, and Poker-DVS using the same network topology and feature maps. We demonstrate the effectiveness of our approach by achieving the highest classification accuracy reported on the N-MNIST (97.77%) and Poker-DVS (100%) real DVS data sets to date with a spiking convolutional network. Moreover, by using the proposed method we were able to retrain the output layer of a previously reported spiking neural network and increase its performance by 2%, suggesting that the proposed classifier can be used as the output layer in works where features are extracted using unsupervised spike-based learning methods. In addition, we also analyze SNN performance figures such as total event activity and network latencies, which are relevant for eventual hardware implementations. In summary, the paper aggregates unsupervised-trained SNNs with a supervised-trained SNN classifier, combining and applying them to heterogeneous sets of benchmarks, both synthetic and from real DVS chips.
A general prediction model for the detection of ADHD and Autism using structural and functional MRI.

PubMed

Sen, Bhaskar; Borle, Neil C; Greiner, Russell; Brown, Matthew R G

2018-01-01

This work presents a novel method for learning a model that can diagnose Attention Deficit Hyperactivity Disorder (ADHD), as well as Autism, using structural texture and functional connectivity features obtained from 3-dimensional structural magnetic resonance imaging (MRI) and 4-dimensional resting-state functional magnetic resonance imaging (fMRI) scans of subjects. We explore a series of three learners: (1) The LeFMS learner first extracts features from the structural MRI images using the texture-based filters produced by a sparse autoencoder. These filters are then convolved with the original MRI image using an unsupervised convolutional network. The resulting features are used as input to a linear support vector machine (SVM) classifier. (2) The LeFMF learner produces a diagnostic model by first computing spatial non-stationary independent components of the fMRI scans, which it uses to decompose each subject's fMRI scan into the time courses of these common spatial components. These features can then be used with a learner by themselves or in combination with other features to produce the model. Regardless of which approach is used, the final set of features are input to a linear support vector machine (SVM) classifier. (3) Finally, the overall LeFMSF learner uses the combined features obtained from the two feature extraction processes in (1) and (2) above as input to an SVM classifier, achieving an accuracy of 0.673 on the ADHD-200 holdout data and 0.643 on the ABIDE holdout data. Both of these results, obtained with the same LeFMSF framework, are the best known, over all hold-out accuracies on these datasets when only using imaging data-exceeding previously-published results by 0.012 for ADHD and 0.042 for Autism. Our results show that combining multi-modal features can yield good classification accuracy for diagnosis of ADHD and Autism, which is an important step towards computer-aided diagnosis of these psychiatric diseases and perhaps others as well.
Deep learning-based subdivision approach for large scale macromolecules structure recovery from electron cryo tomograms.

PubMed

Xu, Min; Chai, Xiaoqi; Muthakana, Hariank; Liang, Xiaodan; Yang, Ge; Zeev-Ben-Mordehai, Tzviya; Xing, Eric P

2017-07-15

Cellular Electron CryoTomography (CECT) enables 3D visualization of cellular organization at near-native state and in sub-molecular resolution, making it a powerful tool for analyzing structures of macromolecular complexes and their spatial organizations inside single cells. However, high degree of structural complexity together with practical imaging limitations makes the systematic de novo discovery of structures within cells challenging. It would likely require averaging and classifying millions of subtomograms potentially containing hundreds of highly heterogeneous structural classes. Although it is no longer difficult to acquire CECT data containing such amount of subtomograms due to advances in data acquisition automation, existing computational approaches have very limited scalability or discrimination ability, making them incapable of processing such amount of data. To complement existing approaches, in this article we propose a new approach for subdividing subtomograms into smaller but relatively homogeneous subsets. The structures in these subsets can then be separately recovered using existing computation intensive methods. Our approach is based on supervised structural feature extraction using deep learning, in combination with unsupervised clustering and reference-free classification. Our experiments show that, compared with existing unsupervised rotation invariant feature and pose-normalization based approaches, our new approach achieves significant improvements in both discrimination ability and scalability. More importantly, our new approach is able to discover new structural classes and recover structures that do not exist in training data. Source code freely available at http://www.cs.cmu.edu/∼mxu1/software . mxu1@cs.cmu.edu. Supplementary data are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com
Identifying quantum phase transitions with adversarial neural networks

NASA Astrophysics Data System (ADS)

Huembeli, Patrick; Dauphin, Alexandre; Wittek, Peter

2018-04-01

The identification of phases of matter is a challenging task, especially in quantum mechanics, where the complexity of the ground state appears to grow exponentially with the size of the system. Traditionally, physicists have to identify the relevant order parameters for the classification of the different phases. We here follow a radically different approach: we address this problem with a state-of-the-art deep learning technique, adversarial domain adaptation. We derive the phase diagram of the whole parameter space starting from a fixed and known subspace using unsupervised learning. This method has the advantage that the input of the algorithm can be directly the ground state without any ad hoc feature engineering. Furthermore, the dimension of the parameter space is unrestricted. More specifically, the input data set contains both labeled and unlabeled data instances. The first kind is a system that admits an accurate analytical or numerical solution, and one can recover its phase diagram. The second type is the physical system with an unknown phase diagram. Adversarial domain adaptation uses both types of data to create invariant feature extracting layers in a deep learning architecture. Once these layers are trained, we can attach an unsupervised learner to the network to find phase transitions. We show the success of this technique by applying it on several paradigmatic models: the Ising model with different temperatures, the Bose-Hubbard model, and the Su-Schrieffer-Heeger model with disorder. The method finds unknown transitions successfully and predicts transition points in close agreement with standard methods. This study opens the door to the classification of physical systems where the phase boundaries are complex such as the many-body localization problem or the Bose glass phase.
Training strategy for convolutional neural networks in pedestrian gender classification

NASA Astrophysics Data System (ADS)

Ng, Choon-Boon; Tay, Yong-Haur; Goi, Bok-Min

2017-06-01

In this work, we studied a strategy for training a convolutional neural network in pedestrian gender classification with limited amount of labeled training data. Unsupervised learning by k-means clustering on pedestrian images was used to learn the filters to initialize the first layer of the network. As a form of pre-training, supervised learning for the related task of pedestrian classification was performed. Finally, the network was fine-tuned for gender classification. We found that this strategy improved the network's generalization ability in gender classification, achieving better test results when compared to random weights initialization and slightly more beneficial than merely initializing the first layer filters by unsupervised learning. This shows that unsupervised learning followed by pre-training with pedestrian images is an effective strategy to learn useful features for pedestrian gender classification.
Automated egg grading system using computer vision: Investigation on weight measure versus shape parameters

NASA Astrophysics Data System (ADS)

Nasir, Ahmad Fakhri Ab; Suhaila Sabarudin, Siti; Majeed, Anwar P. P. Abdul; Ghani, Ahmad Shahrizan Abdul

2018-04-01

Chicken egg is a source of food of high demand by humans. Human operators cannot work perfectly and continuously when conducting egg grading. Instead of an egg grading system using weight measure, an automatic system for egg grading using computer vision (using egg shape parameter) can be used to improve the productivity of egg grading. However, early hypothesis has indicated that more number of egg classes will change when using egg shape parameter compared with using weight measure. This paper presents the comparison of egg classification by the two above-mentioned methods. Firstly, 120 images of chicken eggs of various grades (A–D) produced in Malaysia are captured. Then, the egg images are processed using image pre-processing techniques, such as image cropping, smoothing and segmentation. Thereafter, eight egg shape features, including area, major axis length, minor axis length, volume, diameter and perimeter, are extracted. Lastly, feature selection (information gain ratio) and feature extraction (principal component analysis) are performed using k-nearest neighbour classifier in the classification process. Two methods, namely, supervised learning (using weight measure as graded by egg supplier) and unsupervised learning (using egg shape parameters as graded by ourselves), are conducted to execute the experiment. Clustering results reveal many changes in egg classes after performing shape-based grading. On average, the best recognition results using shape-based grading label is 94.16% while using weight-based label is 44.17%. As conclusion, automated egg grading system using computer vision is better by implementing shape-based features since it uses image meanwhile the weight parameter is more suitable by using weight grading system.
EEG source space analysis of the supervised factor analytic approach for the classification of multi-directional arm movement

NASA Astrophysics Data System (ADS)

Shenoy Handiru, Vikram; Vinod, A. P.; Guan, Cuntai

2017-08-01

Objective. In electroencephalography (EEG)-based brain-computer interface (BCI) systems for motor control tasks the conventional practice is to decode motor intentions by using scalp EEG. However, scalp EEG only reveals certain limited information about the complex tasks of movement with a higher degree of freedom. Therefore, our objective is to investigate the effectiveness of source-space EEG in extracting relevant features that discriminate arm movement in multiple directions. Approach. We have proposed a novel feature extraction algorithm based on supervised factor analysis that models the data from source-space EEG. To this end, we computed the features from the source dipoles confined to Brodmann areas of interest (BA4a, BA4p and BA6). Further, we embedded class-wise labels of multi-direction (multi-class) source-space EEG to an unsupervised factor analysis to make it into a supervised learning method. Main Results. Our approach provided an average decoding accuracy of 71% for the classification of hand movement in four orthogonal directions, that is significantly higher (>10%) than the classification accuracy obtained using state-of-the-art spatial pattern features in sensor space. Also, the group analysis on the spectral characteristics of source-space EEG indicates that the slow cortical potentials from a set of cortical source dipoles reveal discriminative information regarding the movement parameter, direction. Significance. This study presents evidence that low-frequency components in the source space play an important role in movement kinematics, and thus it may lead to new strategies for BCI-based neurorehabilitation.

Unintentional Drowning

MedlinePlus

... area unsupervised. If you are in and around natural water settings: Use U.S. Coast Guard approved life ... Swimming Pools CDC Feature Article: Drowning Risks in Natural Water Settings CDC: Recreational Water Illnesses (RWIs) CDC ...
Space Object Classification Using Fused Features of Time Series Data

NASA Astrophysics Data System (ADS)

Jia, B.; Pham, K. D.; Blasch, E.; Shen, D.; Wang, Z.; Chen, G.

In this paper, a fused feature vector consisting of raw time series and texture feature information is proposed for space object classification. The time series data includes historical orbit trajectories and asteroid light curves. The texture feature is derived from recurrence plots using Gabor filters for both unsupervised learning and supervised learning algorithms. The simulation results show that the classification algorithms using the fused feature vector achieve better performance than those using raw time series or texture features only.
Unsupervised detection and removal of muscle artifacts from scalp EEG recordings using canonical correlation analysis, wavelets and random forests.

PubMed

Anastasiadou, Maria N; Christodoulakis, Manolis; Papathanasiou, Eleftherios S; Papacostas, Savvas S; Mitsis, Georgios D

2017-09-01

This paper proposes supervised and unsupervised algorithms for automatic muscle artifact detection and removal from long-term EEG recordings, which combine canonical correlation analysis (CCA) and wavelets with random forests (RF). The proposed algorithms first perform CCA and continuous wavelet transform of the canonical components to generate a number of features which include component autocorrelation values and wavelet coefficient magnitude values. A subset of the most important features is subsequently selected using RF and labelled observations (supervised case) or synthetic data constructed from the original observations (unsupervised case). The proposed algorithms are evaluated using realistic simulation data as well as 30min epochs of non-invasive EEG recordings obtained from ten patients with epilepsy. We assessed the performance of the proposed algorithms using classification performance and goodness-of-fit values for noisy and noise-free signal windows. In the simulation study, where the ground truth was known, the proposed algorithms yielded almost perfect performance. In the case of experimental data, where expert marking was performed, the results suggest that both the supervised and unsupervised algorithm versions were able to remove artifacts without affecting noise-free channels considerably, outperforming standard CCA, independent component analysis (ICA) and Lagged Auto-Mutual Information Clustering (LAMIC). The proposed algorithms achieved excellent performance for both simulation and experimental data. Importantly, for the first time to our knowledge, we were able to perform entirely unsupervised artifact removal, i.e. without using already marked noisy data segments, achieving performance that is comparable to the supervised case. Overall, the results suggest that the proposed algorithms yield significant future potential for improving EEG signal quality in research or clinical settings without the need for marking by expert neurophysiologists, EMG signal recording and user visual inspection. Copyright © 2017 International Federation of Clinical Neurophysiology. Published by Elsevier B.V. All rights reserved.
Natural-Annotation-based Unsupervised Construction of Korean-Chinese Domain Dictionary

NASA Astrophysics Data System (ADS)

Liu, Wuying; Wang, Lin

2018-03-01

The large-scale bilingual parallel resource is significant to statistical learning and deep learning in natural language processing. This paper addresses the automatic construction issue of the Korean-Chinese domain dictionary, and presents a novel unsupervised construction method based on the natural annotation in the raw corpus. We firstly extract all Korean-Chinese word pairs from Korean texts according to natural annotations, secondly transform the traditional Chinese characters into the simplified ones, and finally distill out a bilingual domain dictionary after retrieving the simplified Chinese words in an extra Chinese domain dictionary. The experimental results show that our method can automatically build multiple Korean-Chinese domain dictionaries efficiently.
Feature learning and change feature classification based on deep learning for ternary change detection in SAR images

NASA Astrophysics Data System (ADS)

Gong, Maoguo; Yang, Hailun; Zhang, Puzhao

2017-07-01

Ternary change detection aims to detect changes and group the changes into positive change and negative change. It is of great significance in the joint interpretation of spatial-temporal synthetic aperture radar images. In this study, sparse autoencoder, convolutional neural networks (CNN) and unsupervised clustering are combined to solve ternary change detection problem without any supervison. Firstly, sparse autoencoder is used to transform log-ratio difference image into a suitable feature space for extracting key changes and suppressing outliers and noise. And then the learned features are clustered into three classes, which are taken as the pseudo labels for training a CNN model as change feature classifier. The reliable training samples for CNN are selected from the feature maps learned by sparse autoencoder with certain selection rules. Having training samples and the corresponding pseudo labels, the CNN model can be trained by using back propagation with stochastic gradient descent. During its training procedure, CNN is driven to learn the concept of change, and more powerful model is established to distinguish different types of changes. Unlike the traditional methods, the proposed framework integrates the merits of sparse autoencoder and CNN to learn more robust difference representations and the concept of change for ternary change detection. Experimental results on real datasets validate the effectiveness and superiority of the proposed framework.
Exploring supervised and unsupervised methods to detect topics in biomedical text

PubMed Central

Lee, Minsuk; Wang, Weiqing; Yu, Hong

2006-01-01

Background Topic detection is a task that automatically identifies topics (e.g., "biochemistry" and "protein structure") in scientific articles based on information content. Topic detection will benefit many other natural language processing tasks including information retrieval, text summarization and question answering; and is a necessary step towards the building of an information system that provides an efficient way for biologists to seek information from an ocean of literature. Results We have explored the methods of Topic Spotting, a task of text categorization that applies the supervised machine-learning technique naïve Bayes to assign automatically a document into one or more predefined topics; and Topic Clustering, which apply unsupervised hierarchical clustering algorithms to aggregate documents into clusters such that each cluster represents a topic. We have applied our methods to detect topics of more than fifteen thousand of articles that represent over sixteen thousand entries in the Online Mendelian Inheritance in Man (OMIM) database. We have explored bag of words as the features. Additionally, we have explored semantic features; namely, the Medical Subject Headings (MeSH) that are assigned to the MEDLINE records, and the Unified Medical Language System (UMLS) semantic types that correspond to the MeSH terms, in addition to bag of words, to facilitate the tasks of topic detection. Our results indicate that incorporating the MeSH terms and the UMLS semantic types as additional features enhances the performance of topic detection and the naïve Bayes has the highest accuracy, 66.4%, for predicting the topic of an OMIM article as one of the total twenty-five topics. Conclusion Our results indicate that the supervised topic spotting methods outperformed the unsupervised topic clustering; on the other hand, the unsupervised topic clustering methods have the advantages of being robust and applicable in real world settings. PMID:16539745
Age and gender classification in the wild with unsupervised feature learning

NASA Astrophysics Data System (ADS)

Wan, Lihong; Huo, Hong; Fang, Tao

2017-03-01

Inspired by unsupervised feature learning (UFL) within the self-taught learning framework, we propose a method based on UFL, convolution representation, and part-based dimensionality reduction to handle facial age and gender classification, which are two challenging problems under unconstrained circumstances. First, UFL is introduced to learn selective receptive fields (filters) automatically by applying whitening transformation and spherical k-means on random patches collected from unlabeled data. The learning process is fast and has no hyperparameters to tune. Then, the input image is convolved with these filters to obtain filtering responses on which local contrast normalization is applied. Average pooling and feature concatenation are then used to form global face representation. Finally, linear discriminant analysis with part-based strategy is presented to reduce the dimensions of the global representation and to improve classification performances further. Experiments on three challenging databases, namely, Labeled faces in the wild, Gallagher group photos, and Adience, demonstrate the effectiveness of the proposed method relative to that of state-of-the-art approaches.
Unsupervised spike sorting based on discriminative subspace learning.

PubMed

Keshtkaran, Mohammad Reza; Yang, Zhi

2014-01-01

Spike sorting is a fundamental preprocessing step for many neuroscience studies which rely on the analysis of spike trains. In this paper, we present two unsupervised spike sorting algorithms based on discriminative subspace learning. The first algorithm simultaneously learns the discriminative feature subspace and performs clustering. It uses histogram of features in the most discriminative projection to detect the number of neurons. The second algorithm performs hierarchical divisive clustering that learns a discriminative 1-dimensional subspace for clustering in each level of the hierarchy until achieving almost unimodal distribution in the subspace. The algorithms are tested on synthetic and in-vivo data, and are compared against two widely used spike sorting methods. The comparative results demonstrate that our spike sorting methods can achieve substantially higher accuracy in lower dimensional feature space, and they are highly robust to noise. Moreover, they provide significantly better cluster separability in the learned subspace than in the subspace obtained by principal component analysis or wavelet transform.
MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification

NASA Astrophysics Data System (ADS)

Lin, Daoyu; Fu, Kun; Wang, Yang; Xu, Guangluan; Sun, Xian

2017-11-01

With the development of deep learning, supervised learning has frequently been adopted to classify remotely sensed images using convolutional networks (CNNs). However, due to the limited amount of labeled data available, supervised learning is often difficult to carry out. Therefore, we proposed an unsupervised model called multiple-layer feature-matching generative adversarial networks (MARTA GANs) to learn a representation using only unlabeled data. MARTA GANs consists of both a generative model $G$ and a discriminative model $D$. We treat $D$ as a feature extractor. To fit the complex properties of remote sensing data, we use a fusion layer to merge the mid-level and global features. $G$ can produce numerous images that are similar to the training data; therefore, $D$ can learn better representations of remotely sensed images using the training data provided by $G$. The classification results on two widely used remote sensing image databases show that the proposed method significantly improves the classification performance compared with other state-of-the-art methods.
A SOFTWARE PACKAGE FOR UNSUPERVISED PATTERN RECOGNITION AND SYNOPTIC REPRESENTATION OF RESULTS: APPLICATION TO VOLCANIC TREMOR DATA OF MT ETNA

NASA Astrophysics Data System (ADS)

Langer, H. K.; Falsaperla, S. M.; Behncke, B.; Messina, A.; Spampinato, S.

2009-12-01

Artificial Intelligence (AI) has found broad applications in volcano observatories worldwide with the aim of reducing volcanic hazard. The need to process larger and larger quantity of data makes indeed AI techniques appealing for monitoring purposes. Tools based on Artificial Neural Networks and Support Vector Machine have proved to be particularly successful in the classification of seismic events and volcanic tremor changes heralding eruptive activity, such as paroxysmal explosions and lava fountaining at Stromboli and Mt Etna, Italy (e.g., Falsaperla et al., 1996; Langer et al., 2009). Moving on from the excellent results obtained from these applications, we present KKAnalysis, a MATLAB based software which combines several unsupervised pattern classification methods, exploiting routines of the SOM Toolbox 2 for MATLAB (http://www.cis.hut.fi/projects/somtoolbox). KKAnalysis is based on Self Organizing Maps (SOM) and clustering methods consisting of K-Means, Fuzzy C-Means, and a scheme based on a metrics accounting for correlation between components of the feature vector. We show examples of applications of this tool to volcanic tremor data recorded at Mt Etna between 2007 and 2009. This time span - during which Strombolian explosions, 7 episodes of lava fountaining and effusive activity occurred - is particularly interesting, as it encompassed different states of volcanic activity (i.e., non-eruptive, eruptive according to different styles) for the unsupervised classifier to identify, highlighting their development in time. Even subtle changes in the signal characteristics allow the unsupervised classifier to recognize features belonging to the different classes and stages of volcanic activity. A convenient color-code representation shows up the temporal development of the different classes of signal, making this method extremely helpful for monitoring purposes and surveillance. Though being developed for volcanic tremor classification, KKAnalysis is generally applicable to any type of physical or chemical pattern, provided that feature vectors are given in numerical form. References: Falsaperla, S., S. Graziani, G. Nunnari, and S. Spampinato (1996). Automatic classification of volcanic earthquakes by using multy-layered neural networks. Natural Hazard, 13, 205-228. Langer, H., S. Falsaperla, M. Masotti, R. Campanini, S. Spampinato, and A. Messina (2008). Synopsis of supervised and unsupervised pattern classification techniques applied to volcanic tremor data at Mt Etna, Italy. Geophys. J. Int., doi:10.1111/j.1365-246X.2009.04179.x.
Multi-Source Multi-Target Dictionary Learning for Prediction of Cognitive Decline.

PubMed

Zhang, Jie; Li, Qingyang; Caselli, Richard J; Thompson, Paul M; Ye, Jieping; Wang, Yalin

2017-06-01

Alzheimer's Disease (AD) is the most common type of dementia. Identifying correct biomarkers may determine pre-symptomatic AD subjects and enable early intervention. Recently, Multi-task sparse feature learning has been successfully applied to many computer vision and biomedical informatics researches. It aims to improve the generalization performance by exploiting the shared features among different tasks. However, most of the existing algorithms are formulated as a supervised learning scheme. Its drawback is with either insufficient feature numbers or missing label information. To address these challenges, we formulate an unsupervised framework for multi-task sparse feature learning based on a novel dictionary learning algorithm. To solve the unsupervised learning problem, we propose a two-stage Multi-Source Multi-Target Dictionary Learning (MMDL) algorithm. In stage 1, we propose a multi-source dictionary learning method to utilize the common and individual sparse features in different time slots. In stage 2, supported by a rigorous theoretical analysis, we develop a multi-task learning method to solve the missing label problem. Empirical studies on an N = 3970 longitudinal brain image data set, which involves 2 sources and 5 targets, demonstrate the improved prediction accuracy and speed efficiency of MMDL in comparison with other state-of-the-art algorithms.
Computational phenotype discovery using unsupervised feature learning over noisy, sparse, and irregular clinical data.

PubMed

Lasko, Thomas A; Denny, Joshua C; Levy, Mia A

2013-01-01

Inferring precise phenotypic patterns from population-scale clinical data is a core computational task in the development of precision, personalized medicine. The traditional approach uses supervised learning, in which an expert designates which patterns to look for (by specifying the learning task and the class labels), and where to look for them (by specifying the input variables). While appropriate for individual tasks, this approach scales poorly and misses the patterns that we don't think to look for. Unsupervised feature learning overcomes these limitations by identifying patterns (or features) that collectively form a compact and expressive representation of the source data, with no need for expert input or labeled examples. Its rising popularity is driven by new deep learning methods, which have produced high-profile successes on difficult standardized problems of object recognition in images. Here we introduce its use for phenotype discovery in clinical data. This use is challenging because the largest source of clinical data - Electronic Medical Records - typically contains noisy, sparse, and irregularly timed observations, rendering them poor substrates for deep learning methods. Our approach couples dirty clinical data to deep learning architecture via longitudinal probability densities inferred using Gaussian process regression. From episodic, longitudinal sequences of serum uric acid measurements in 4368 individuals we produced continuous phenotypic features that suggest multiple population subtypes, and that accurately distinguished (0.97 AUC) the uric-acid signatures of gout vs. acute leukemia despite not being optimized for the task. The unsupervised features were as accurate as gold-standard features engineered by an expert with complete knowledge of the domain, the classification task, and the class labels. Our findings demonstrate the potential for achieving computational phenotype discovery at population scale. We expect such data-driven phenotypes to expose unknown disease variants and subtypes and to provide rich targets for genetic association studies.
Computational Phenotype Discovery Using Unsupervised Feature Learning over Noisy, Sparse, and Irregular Clinical Data

PubMed Central

Lasko, Thomas A.; Denny, Joshua C.; Levy, Mia A.

2013-01-01

Inferring precise phenotypic patterns from population-scale clinical data is a core computational task in the development of precision, personalized medicine. The traditional approach uses supervised learning, in which an expert designates which patterns to look for (by specifying the learning task and the class labels), and where to look for them (by specifying the input variables). While appropriate for individual tasks, this approach scales poorly and misses the patterns that we don’t think to look for. Unsupervised feature learning overcomes these limitations by identifying patterns (or features) that collectively form a compact and expressive representation of the source data, with no need for expert input or labeled examples. Its rising popularity is driven by new deep learning methods, which have produced high-profile successes on difficult standardized problems of object recognition in images. Here we introduce its use for phenotype discovery in clinical data. This use is challenging because the largest source of clinical data – Electronic Medical Records – typically contains noisy, sparse, and irregularly timed observations, rendering them poor substrates for deep learning methods. Our approach couples dirty clinical data to deep learning architecture via longitudinal probability densities inferred using Gaussian process regression. From episodic, longitudinal sequences of serum uric acid measurements in 4368 individuals we produced continuous phenotypic features that suggest multiple population subtypes, and that accurately distinguished (0.97 AUC) the uric-acid signatures of gout vs. acute leukemia despite not being optimized for the task. The unsupervised features were as accurate as gold-standard features engineered by an expert with complete knowledge of the domain, the classification task, and the class labels. Our findings demonstrate the potential for achieving computational phenotype discovery at population scale. We expect such data-driven phenotypes to expose unknown disease variants and subtypes and to provide rich targets for genetic association studies. PMID:23826094
Communications and control for electric power systems: Power flow classification for static security assessment

NASA Technical Reports Server (NTRS)

Niebur, D.; Germond, A.

1993-01-01

This report investigates the classification of power system states using an artificial neural network model, Kohonen's self-organizing feature map. The ultimate goal of this classification is to assess power system static security in real-time. Kohonen's self-organizing feature map is an unsupervised neural network which maps N-dimensional input vectors to an array of M neurons. After learning, the synaptic weight vectors exhibit a topological organization which represents the relationship between the vectors of the training set. This learning is unsupervised, which means that the number and size of the classes are not specified beforehand. In the application developed in this report, the input vectors used as the training set are generated by off-line load-flow simulations. The learning algorithm and the results of the organization are discussed.
A new simple /spl infin/OH neuron model as a biologically plausible principal component analyzer.

PubMed

Jankovic, M V

2003-01-01

A new approach to unsupervised learning in a single-layer neural network is discussed. An algorithm for unsupervised learning based upon the Hebbian learning rule is presented. A simple neuron model is analyzed. A dynamic neural model, which contains both feed-forward and feedback connections between the input and the output, has been adopted. The, proposed learning algorithm could be more correctly named self-supervised rather than unsupervised. The solution proposed here is a modified Hebbian rule, in which the modification of the synaptic strength is proportional not to pre- and postsynaptic activity, but instead to the presynaptic and averaged value of postsynaptic activity. It is shown that the model neuron tends to extract the principal component from a stationary input vector sequence. Usually accepted additional decaying terms for the stabilization of the original Hebbian rule are avoided. Implementation of the basic Hebbian scheme would not lead to unrealistic growth of the synaptic strengths, thanks to the adopted network structure.
Understanding of the Geomorphological Elements in Discrimination of Typical Mediterranean Land Cover Types

NASA Astrophysics Data System (ADS)

Elhag, Mohamed; Boteva, Silvena

2017-12-01

Quantification of geomorphometric features is the keystone concern of the current study. The quantification was based on the statistical approach in term of multivariate analysis of local topographic features. The implemented algorithm utilizes the Digital Elevation Model (DEM) to categorize and extract the geomorphometric features embedded in the topographic dataset. The morphological settings were exercised on the central pixel of 3x3 per-defined convolution kernel to evaluate the surrounding pixels under the right directional pour point model (D8) of the azimuth viewpoints. Realization of unsupervised classification algorithm in term of Iterative Self-Organizing Data Analysis Technique (ISODATA) was carried out on ASTER GDEM within the boundary of the designated study area to distinguish 10 morphometric classes. The morphometric classes expressed spatial distribution variation in the study area. The adopted methodology is successful to appreciate the spatial distribution of the geomorphometric features under investigation. The conducted results verified the superimposition of the delineated geomorphometric elements over a given remote sensing imagery to be further analyzed. Robust relationship between different Land Cover types and the geomorphological elements was established in the context of the study area. The domination and the relative association of different Land Cover types in corresponding to its geomorphological elements were demonstrated.
Segmentation of magnetic resonance images using fuzzy algorithms for learning vector quantization.

PubMed

Karayiannis, N B; Pai, P I

1999-02-01

This paper evaluates a segmentation technique for magnetic resonance (MR) images of the brain based on fuzzy algorithms for learning vector quantization (FALVQ). These algorithms perform vector quantization by updating all prototypes of a competitive network through an unsupervised learning process. Segmentation of MR images is formulated as an unsupervised vector quantization process, where the local values of different relaxation parameters form the feature vectors which are represented by a relatively small set of prototypes. The experiments evaluate a variety of FALVQ algorithms in terms of their ability to identify different tissues and discriminate between normal tissues and abnormalities.
An Unsupervised kNN Method to Systematically Detect Changes in Protein Localization in High-Throughput Microscopy Images.

PubMed

Lu, Alex Xijie; Moses, Alan M

2016-01-01

Despite the importance of characterizing genes that exhibit subcellular localization changes between conditions in proteome-wide imaging experiments, many recent studies still rely upon manual evaluation to assess the results of high-throughput imaging experiments. We describe and demonstrate an unsupervised k-nearest neighbours method for the detection of localization changes. Compared to previous classification-based supervised change detection methods, our method is much simpler and faster, and operates directly on the feature space to overcome limitations in needing to manually curate training sets that may not generalize well between screens. In addition, the output of our method is flexible in its utility, generating both a quantitatively ranked list of localization changes that permit user-defined cut-offs, and a vector for each gene describing feature-wise direction and magnitude of localization changes. We demonstrate that our method is effective at the detection of localization changes using the Δrpd3 perturbation in Saccharomyces cerevisiae, where we capture 71.4% of previously known changes within the top 10% of ranked genes, and find at least four new localization changes within the top 1% of ranked genes. The results of our analysis indicate that simple unsupervised methods may be able to identify localization changes in images without laborious manual image labelling steps.
Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval.

PubMed

Wei, Xiu-Shen; Luo, Jian-Hao; Wu, Jianxin; Zhou, Zhi-Hua

2017-06-01

Deep convolutional neural network models pre-trained for the ImageNet classification task have been successfully adopted to tasks in other domains, such as texture description and object proposal generation, but these tasks require annotations for images in the new domain. In this paper, we focus on a novel and challenging task in the pure unsupervised setting: fine-grained image retrieval. Even with image labels, fine-grained images are difficult to classify, letting alone the unsupervised retrieval task. We propose the selective convolutional descriptor aggregation (SCDA) method. The SCDA first localizes the main object in fine-grained images, a step that discards the noisy background and keeps useful deep descriptors. The selected descriptors are then aggregated and the dimensionality is reduced into a short feature vector using the best practices we found. The SCDA is unsupervised, using no image label or bounding box annotation. Experiments on six fine-grained data sets confirm the effectiveness of the SCDA for fine-grained image retrieval. Besides, visualization of the SCDA features shows that they correspond to visual attributes (even subtle ones), which might explain SCDA's high-mean average precision in fine-grained retrieval. Moreover, on general image retrieval data sets, the SCDA achieves comparable retrieval results with the state-of-the-art general image retrieval approaches.
Prediction task guided representation learning of medical codes in EHR.

PubMed

Cui, Liwen; Xie, Xiaolei; Shen, Zuojun

2018-06-18

There have been rapidly growing applications using machine learning models for predictive analytics in Electronic Health Records (EHR) to improve the quality of hospital services and the efficiency of healthcare resource utilization. A fundamental and crucial step in developing such models is to convert medical codes in EHR to feature vectors. These medical codes are used to represent diagnoses or procedures. Their vector representations have a tremendous impact on the performance of machine learning models. Recently, some researchers have utilized representation learning methods from Natural Language Processing (NLP) to learn vector representations of medical codes. However, most previous approaches are unsupervised, i.e. the generation of medical code vectors is independent from prediction tasks. Thus, the obtained feature vectors may be inappropriate for a specific prediction task. Moreover, unsupervised methods often require a lot of samples to obtain reliable results, but most practical problems have very limited patient samples. In this paper, we develop a new method called Prediction Task Guided Health Record Aggregation (PTGHRA), which aggregates health records guided by prediction tasks, to construct training corpus for various representation learning models. Compared with unsupervised approaches, representation learning models integrated with PTGHRA yield a significant improvement in predictive capability of generated medical code vectors, especially for limited training samples. Copyright © 2018. Published by Elsevier Inc.

Unsupervised user similarity mining in GSM sensor networks.

PubMed

Shad, Shafqat Ali; Chen, Enhong

2013-01-01

Mobility data has attracted the researchers for the past few years because of its rich context and spatiotemporal nature, where this information can be used for potential applications like early warning system, route prediction, traffic management, advertisement, social networking, and community finding. All the mentioned applications are based on mobility profile building and user trend analysis, where mobility profile building is done through significant places extraction, user's actual movement prediction, and context awareness. However, significant places extraction and user's actual movement prediction for mobility profile building are a trivial task. In this paper, we present the user similarity mining-based methodology through user mobility profile building by using the semantic tagging information provided by user and basic GSM network architecture properties based on unsupervised clustering approach. As the mobility information is in low-level raw form, our proposed methodology successfully converts it to a high-level meaningful information by using the cell-Id location information rather than previously used location capturing methods like GPS, Infrared, and Wifi for profile mining and user similarity mining.
Automated road network extraction from high spatial resolution multi-spectral imagery

NASA Astrophysics Data System (ADS)

Zhang, Qiaoping

For the last three decades, the Geomatics Engineering and Computer Science communities have considered automated road network extraction from remotely-sensed imagery to be a challenging and important research topic. The main objective of this research is to investigate the theory and methodology of automated feature extraction for image-based road database creation, refinement or updating, and to develop a series of algorithms for road network extraction from high resolution multi-spectral imagery. The proposed framework for road network extraction from multi-spectral imagery begins with an image segmentation using the k-means algorithm. This step mainly concerns the exploitation of the spectral information for feature extraction. The road cluster is automatically identified using a fuzzy classifier based on a set of predefined road surface membership functions. These membership functions are established based on the general spectral signature of road pavement materials and the corresponding normalized digital numbers on each multi-spectral band. Shape descriptors of the Angular Texture Signature are defined and used to reduce the misclassifications between roads and other spectrally similar objects (e.g., crop fields, parking lots, and buildings). An iterative and localized Radon transform is developed for the extraction of road centerlines from the classified images. The purpose of the transform is to accurately and completely detect the road centerlines. It is able to find short, long, and even curvilinear lines. The input image is partitioned into a set of subset images called road component images. An iterative Radon transform is locally applied to each road component image. At each iteration, road centerline segments are detected based on an accurate estimation of the line parameters and line widths. Three localization approaches are implemented and compared using qualitative and quantitative methods. Finally, the road centerline segments are grouped into a road network. The extracted road network is evaluated against a reference dataset using a line segment matching algorithm. The entire process is unsupervised and fully automated. Based on extensive experimentation on a variety of remotely-sensed multi-spectral images, the proposed methodology achieves a moderate success in automating road network extraction from high spatial resolution multi-spectral imagery.
Learning Compact Binary Face Descriptor for Face Recognition.

PubMed

Lu, Jiwen; Liong, Venice Erin; Zhou, Xiuzhuang; Zhou, Jie

2015-10-01

Binary feature descriptors such as local binary patterns (LBP) and its variations have been widely used in many face recognition systems due to their excellent robustness and strong discriminative power. However, most existing binary face descriptors are hand-crafted, which require strong prior knowledge to engineer them by hand. In this paper, we propose a compact binary face descriptor (CBFD) feature learning method for face representation and recognition. Given each face image, we first extract pixel difference vectors (PDVs) in local patches by computing the difference between each pixel and its neighboring pixels. Then, we learn a feature mapping to project these pixel difference vectors into low-dimensional binary vectors in an unsupervised manner, where 1) the variance of all binary codes in the training set is maximized, 2) the loss between the original real-valued codes and the learned binary codes is minimized, and 3) binary codes evenly distribute at each learned bin, so that the redundancy information in PDVs is removed and compact binary codes are obtained. Lastly, we cluster and pool these binary codes into a histogram feature as the final representation for each face image. Moreover, we propose a coupled CBFD (C-CBFD) method by reducing the modality gap of heterogeneous faces at the feature level to make our method applicable to heterogeneous face recognition. Extensive experimental results on five widely used face datasets show that our methods outperform state-of-the-art face descriptors.
Unsupervised Biomedical Named Entity Recognition: Experiments with Clinical and Biological Texts

PubMed Central

Zhang, Shaodian; Elhadad, Nóemie

2013-01-01

Named entity recognition is a crucial component of biomedical natural language processing, enabling information extraction and ultimately reasoning over and knowledge discovery from text. Much progress has been made in the design of rule-based and supervised tools, but they are often genre and task dependent. As such, adapting them to different genres of text or identifying new types of entities requires major effort in re-annotation or rule development. In this paper, we propose an unsupervised approach to extracting named entities from biomedical text. We describe a stepwise solution to tackle the challenges of entity boundary detection and entity type classification without relying on any handcrafted rules, heuristics, or annotated data. A noun phrase chunker followed by a filter based on inverse document frequency extracts candidate entities from free text. Classification of candidate entities into categories of interest is carried out by leveraging principles from distributional semantics. Experiments show that our system, especially the entity classification step, yields competitive results on two popular biomedical datasets of clinical notes and biological literature, and outperforms a baseline dictionary match approach. Detailed error analysis provides a road map for future work. PMID:23954592
Residential roof condition assessment system using deep learning

NASA Astrophysics Data System (ADS)

Wang, Fan; Kerekes, John P.; Xu, Zhuoyi; Wang, Yandong

2018-01-01

The emergence of high resolution (HR) and ultra high resolution (UHR) airborne remote sensing imagery is enabling humans to move beyond traditional land cover analysis applications to the detailed characterization of surface objects. A residential roof condition assessment method using techniques from deep learning is presented. The proposed method operates on individual roofs and divides the task into two stages: (1) roof segmentation, followed by (2) condition classification of the segmented roof regions. As the first step in this process, a self-tuning method is proposed to segment the images into small homogeneous areas. The segmentation is initialized with simple linear iterative clustering followed by deep learned feature extraction and region merging, with the optimal result selected by an unsupervised index, Q. After the segmentation, a pretrained residual network is fine-tuned on the augmented roof segments using a proposed k-pixel extension technique for classification. The effectiveness of the proposed algorithm was demonstrated on both HR and UHR imagery collected by EagleView over different study sites. The proposed algorithm has yielded promising results and has outperformed traditional machine learning methods using hand-crafted features.
Multilayer Extreme Learning Machine With Subnetwork Nodes for Representation Learning.

PubMed

Yang, Yimin; Wu, Q M Jonathan

2016-11-01

The extreme learning machine (ELM), which was originally proposed for "generalized" single-hidden layer feedforward neural networks, provides efficient unified learning solutions for the applications of clustering, regression, and classification. It presents competitive accuracy with superb efficiency in many applications. However, ELM with subnetwork nodes architecture has not attracted much research attentions. Recently, many methods have been proposed for supervised/unsupervised dimension reduction or representation learning, but these methods normally only work for one type of problem. This paper studies the general architecture of multilayer ELM (ML-ELM) with subnetwork nodes, showing that: 1) the proposed method provides a representation learning platform with unsupervised/supervised and compressed/sparse representation learning and 2) experimental results on ten image datasets and 16 classification datasets show that, compared to other conventional feature learning methods, the proposed ML-ELM with subnetwork nodes performs competitively or much better than other feature learning methods.
Linear unmixing of multidate hyperspectral imagery for crop yield estimation

USDA-ARS?s Scientific Manuscript database

In this paper, we have evaluated an unsupervised unmixing approach, vertex component analysis (VCA), for the application of crop yield estimation. The results show that abundance maps of the vegetation extracted by the approach are strongly correlated to the yield data (the correlation coefficients ...
AHIMSA - Ad hoc histogram information measure sensing algorithm for feature selection in the context of histogram inspired clustering techniques

NASA Technical Reports Server (NTRS)

Dasarathy, B. V.

1976-01-01

An algorithm is proposed for dimensionality reduction in the context of clustering techniques based on histogram analysis. The approach is based on an evaluation of the hills and valleys in the unidimensional histograms along the different features and provides an economical means of assessing the significance of the features in a nonparametric unsupervised data environment. The method has relevance to remote sensing applications.
Learning Microbial Community Structures with Supervised and Unsupervised Non-negative Matrix Factorization.

PubMed

Cai, Yun; Gu, Hong; Kenney, Toby

2017-08-31

Learning the structure of microbial communities is critical in understanding the different community structures and functions of microbes in distinct individuals. We view microbial communities as consisting of many subcommunities which are formed by certain groups of microbes functionally dependent on each other. The focus of this paper is on methods for extracting the subcommunities from the data, in particular Non-Negative Matrix Factorization (NMF). Our methods can be applied to both OTU data and functional metagenomic data. We apply the existing unsupervised NMF method and also develop a new supervised NMF method for extracting interpretable information from classification problems. The relevance of the subcommunities identified by NMF is demonstrated by their excellent performance for classification. Through three data examples, we demonstrate how to interpret the features identified by NMF to draw meaningful biological conclusions and discover hitherto unidentified patterns in the data. Comparing whole metagenomes of various mammals, (Muegge et al., Science 332:970-974, 2011), the biosynthesis of macrolides pathway is found in hindgut-fermenting herbivores, but not carnivores. This is consistent with results in veterinary science that macrolides should not be given to non-ruminant herbivores. For time series microbiome data from various body sites (Caporaso et al., Genome Biol 12:50, 2011), a shift in the microbial communities is identified for one individual. The shift occurs at around the same time in the tongue and gut microbiomes, indicating that the shift is a genuine biological trait, rather than an artefact of the method. For whole metagenome data from IBD patients and healthy controls (Qin et al., Nature 464:59-65, 2010), we identify differences in a number of pathways (some known, others new). NMF is a powerful tool for identifying the key features of microbial communities. These identified features can not only be used to perform difficult classification problems with a high degree of accuracy, they are also very interpretable and can lead to important biological insights into the structure of the communities. In addition, NMF is a dimension-reduction method (similar to PCA) in that it reduces the extremely complex microbial data into a low-dimensional representation, allowing a number of analyses to be performed more easily-for example, searching for temporal patterns in the microbiome. When we are interested in the differences between the structures of two groups of communities, supervised NMF provides a better way to do this, while retaining all the advantages of NMF-e.g. interpretability and a simple biological intuition.
Sequential visibility-graph motifs

NASA Astrophysics Data System (ADS)

Iacovacci, Jacopo; Lacasa, Lucas

2016-04-01

Visibility algorithms transform time series into graphs and encode dynamical information in their topology, paving the way for graph-theoretical time series analysis as well as building a bridge between nonlinear dynamics and network science. In this work we introduce and study the concept of sequential visibility-graph motifs, smaller substructures of n consecutive nodes that appear with characteristic frequencies. We develop a theory to compute in an exact way the motif profiles associated with general classes of deterministic and stochastic dynamics. We find that this simple property is indeed a highly informative and computationally efficient feature capable of distinguishing among different dynamics and robust against noise contamination. We finally confirm that it can be used in practice to perform unsupervised learning, by extracting motif profiles from experimental heart-rate series and being able, accordingly, to disentangle meditative from other relaxation states. Applications of this general theory include the automatic classification and description of physical, biological, and financial time series.
Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security.

PubMed

Kang, Min-Joo; Kang, Je-Won

2016-01-01

A novel intrusion detection system (IDS) using a deep neural network (DNN) is proposed to enhance the security of in-vehicular network. The parameters building the DNN structure are trained with probability-based feature vectors that are extracted from the in-vehicular network packets. For a given packet, the DNN provides the probability of each class discriminating normal and attack packets, and, thus the sensor can identify any malicious attack to the vehicle. As compared to the traditional artificial neural network applied to the IDS, the proposed technique adopts recent advances in deep learning studies such as initializing the parameters through the unsupervised pre-training of deep belief networks (DBN), therefore improving the detection accuracy. It is demonstrated with experimental results that the proposed technique can provide a real-time response to the attack with a significantly improved detection ratio in controller area network (CAN) bus.
Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security

PubMed Central

Kang, Min-Joo

2016-01-01

A novel intrusion detection system (IDS) using a deep neural network (DNN) is proposed to enhance the security of in-vehicular network. The parameters building the DNN structure are trained with probability-based feature vectors that are extracted from the in-vehicular network packets. For a given packet, the DNN provides the probability of each class discriminating normal and attack packets, and, thus the sensor can identify any malicious attack to the vehicle. As compared to the traditional artificial neural network applied to the IDS, the proposed technique adopts recent advances in deep learning studies such as initializing the parameters through the unsupervised pre-training of deep belief networks (DBN), therefore improving the detection accuracy. It is demonstrated with experimental results that the proposed technique can provide a real-time response to the attack with a significantly improved detection ratio in controller area network (CAN) bus. PMID:27271802
Epithelium-Stroma Classification via Convolutional Neural Networks and Unsupervised Domain Adaptation in Histopathological Images.

PubMed

Huang, Yue; Zheng, Han; Liu, Chi; Ding, Xinghao; Rohde, Gustavo K

2017-11-01

Epithelium-stroma classification is a necessary preprocessing step in histopathological image analysis. Current deep learning based recognition methods for histology data require collection of large volumes of labeled data in order to train a new neural network when there are changes to the image acquisition procedure. However, it is extremely expensive for pathologists to manually label sufficient volumes of data for each pathology study in a professional manner, which results in limitations in real-world applications. A very simple but effective deep learning method, that introduces the concept of unsupervised domain adaptation to a simple convolutional neural network (CNN), has been proposed in this paper. Inspired by transfer learning, our paper assumes that the training data and testing data follow different distributions, and there is an adaptation operation to more accurately estimate the kernels in CNN in feature extraction, in order to enhance performance by transferring knowledge from labeled data in source domain to unlabeled data in target domain. The model has been evaluated using three independent public epithelium-stroma datasets by cross-dataset validations. The experimental results demonstrate that for epithelium-stroma classification, the proposed framework outperforms the state-of-the-art deep neural network model, and it also achieves better performance than other existing deep domain adaptation methods. The proposed model can be considered to be a better option for real-world applications in histopathological image analysis, since there is no longer a requirement for large-scale labeled data in each specified domain.
Multi-Source Multi-Target Dictionary Learning for Prediction of Cognitive Decline

PubMed Central

Zhang, Jie; Li, Qingyang; Caselli, Richard J.; Thompson, Paul M.; Ye, Jieping; Wang, Yalin

2017-01-01

Alzheimer’s Disease (AD) is the most common type of dementia. Identifying correct biomarkers may determine pre-symptomatic AD subjects and enable early intervention. Recently, Multi-task sparse feature learning has been successfully applied to many computer vision and biomedical informatics researches. It aims to improve the generalization performance by exploiting the shared features among different tasks. However, most of the existing algorithms are formulated as a supervised learning scheme. Its drawback is with either insufficient feature numbers or missing label information. To address these challenges, we formulate an unsupervised framework for multi-task sparse feature learning based on a novel dictionary learning algorithm. To solve the unsupervised learning problem, we propose a two-stage Multi-Source Multi-Target Dictionary Learning (MMDL) algorithm. In stage 1, we propose a multi-source dictionary learning method to utilize the common and individual sparse features in different time slots. In stage 2, supported by a rigorous theoretical analysis, we develop a multi-task learning method to solve the missing label problem. Empirical studies on an N = 3970 longitudinal brain image data set, which involves 2 sources and 5 targets, demonstrate the improved prediction accuracy and speed efficiency of MMDL in comparison with other state-of-the-art algorithms. PMID:28943731
Feature Discovery by Competitive Learning.

ERIC Educational Resources Information Center

Rumelhart, David E.; Zipser, David

1985-01-01

Reports results of studies with an unsupervised learning paradigm called competitive learning which is examined using computer simulation and formal analysis. When competitive learning is applied to parallel networks of neuron-like elements, many potentially useful learning tasks can be accomplished. (Author)
Unsupervised Ontology Generation from Unstructured Text. CRESST Report 827

ERIC Educational Resources Information Center

Mousavi, Hamid; Kerr, Deirdre; Iseli, Markus R.

2013-01-01

Ontologies are a vital component of most knowledge acquisition systems, and recently there has been a huge demand for generating ontologies automatically since manual or supervised techniques are not scalable. In this paper, we introduce "OntoMiner", a rule-based, iterative method to extract and populate ontologies from unstructured or…
Subgraph augmented non-negative tensor factorization (SANTF) for modeling clinical narrative text

PubMed Central

Xin, Yu; Hochberg, Ephraim; Joshi, Rohit; Uzuner, Ozlem; Szolovits, Peter

2015-01-01

Objective Extracting medical knowledge from electronic medical records requires automated approaches to combat scalability limitations and selection biases. However, existing machine learning approaches are often regarded by clinicians as black boxes. Moreover, training data for these automated approaches at often sparsely annotated at best. The authors target unsupervised learning for modeling clinical narrative text, aiming at improving both accuracy and interpretability. Methods The authors introduce a novel framework named subgraph augmented non-negative tensor factorization (SANTF). In addition to relying on atomic features (e.g., words in clinical narrative text), SANTF automatically mines higher-order features (e.g., relations of lymphoid cells expressing antigens) from clinical narrative text by converting sentences into a graph representation and identifying important subgraphs. The authors compose a tensor using patients, higher-order features, and atomic features as its respective modes. We then apply non-negative tensor factorization to cluster patients, and simultaneously identify latent groups of higher-order features that link to patient clusters, as in clinical guidelines where a panel of immunophenotypic features and laboratory results are used to specify diagnostic criteria. Results and Conclusion SANTF demonstrated over 10% improvement in averaged F-measure on patient clustering compared to widely used non-negative matrix factorization (NMF) and k-means clustering methods. Multiple baselines were established by modeling patient data using patient-by-features matrices with different feature configurations and then performing NMF or k-means to cluster patients. Feature analysis identified latent groups of higher-order features that lead to medical insights. We also found that the latent groups of atomic features help to better correlate the latent groups of higher-order features. PMID:25862765
A Deep Convolutional Coupling Network for Change Detection Based on Heterogeneous Optical and Radar Images.

PubMed

Liu, Jia; Gong, Maoguo; Qin, Kai; Zhang, Puzhao

2018-03-01

We propose an unsupervised deep convolutional coupling network for change detection based on two heterogeneous images acquired by optical sensors and radars on different dates. Most existing change detection methods are based on homogeneous images. Due to the complementary properties of optical and radar sensors, there is an increasing interest in change detection based on heterogeneous images. The proposed network is symmetric with each side consisting of one convolutional layer and several coupling layers. The two input images connected with the two sides of the network, respectively, are transformed into a feature space where their feature representations become more consistent. In this feature space, the different map is calculated, which then leads to the ultimate detection map by applying a thresholding algorithm. The network parameters are learned by optimizing a coupling function. The learning process is unsupervised, which is different from most existing change detection methods based on heterogeneous images. Experimental results on both homogenous and heterogeneous images demonstrate the promising performance of the proposed network compared with several existing approaches.
Analyzing Distributional Learning of Phonemic Categories in Unsupervised Deep Neural Networks

PubMed Central

Räsänen, Okko; Nagamine, Tasha; Mesgarani, Nima

2017-01-01

Infants’ speech perception adapts to the phonemic categories of their native language, a process assumed to be driven by the distributional properties of speech. This study investigates whether deep neural networks (DNNs), the current state-of-the-art in distributional feature learning, are capable of learning phoneme-like representations of speech in an unsupervised manner. We trained DNNs with unlabeled and labeled speech and analyzed the activations of each layer with respect to the phones in the input segments. The analyses reveal that the emergence of phonemic invariance in DNNs is dependent on the availability of phonemic labeling of the input during the training. No increased phonemic selectivity of the hidden layers was observed in the purely unsupervised networks despite successful learning of low-dimensional representations for speech. This suggests that additional learning constraints or more sophisticated models are needed to account for the emergence of phone-like categories in distributional learning operating on natural speech. PMID:29359204
Wavelet-based unsupervised learning method for electrocardiogram suppression in surface electromyograms.

PubMed

Niegowski, Maciej; Zivanovic, Miroslav

2016-03-01

We present a novel approach aimed at removing electrocardiogram (ECG) perturbation from single-channel surface electromyogram (EMG) recordings by means of unsupervised learning of wavelet-based intensity images. The general idea is to combine the suitability of certain wavelet decomposition bases which provide sparse electrocardiogram time-frequency representations, with the capacity of non-negative matrix factorization (NMF) for extracting patterns from images. In order to overcome convergence problems which often arise in NMF-related applications, we design a novel robust initialization strategy which ensures proper signal decomposition in a wide range of ECG contamination levels. Moreover, the method can be readily used because no a priori knowledge or parameter adjustment is needed. The proposed method was evaluated on real surface EMG signals against two state-of-the-art unsupervised learning algorithms and a singular spectrum analysis based method. The results, expressed in terms of high-to-low energy ratio, normalized median frequency, spectral power difference and normalized average rectified value, suggest that the proposed method enables better ECG-EMG separation quality than the reference methods. Copyright © 2015 IPEM. Published by Elsevier Ltd. All rights reserved.

Unsupervised consensus cluster analysis of [18F]-fluoroethyl-L-tyrosine positron emission tomography identified textural features for the diagnosis of pseudoprogression in high-grade glioma.

PubMed

Kebir, Sied; Khurshid, Zain; Gaertner, Florian C; Essler, Markus; Hattingen, Elke; Fimmers, Rolf; Scheffler, Björn; Herrlinger, Ulrich; Bundschuh, Ralph A; Glas, Martin

2017-01-31

Timely detection of pseudoprogression (PSP) is crucial for the management of patients with high-grade glioma (HGG) but remains difficult. Textural features of O-(2-[18F]fluoroethyl)-L-tyrosine positron emission tomography (FET-PET) mirror tumor uptake heterogeneity; some of them may be associated with tumor progression. Fourteen patients with HGG and suspected of PSP underwent FET-PET imaging. A set of 19 conventional and textural FET-PET features were evaluated and subjected to unsupervised consensus clustering. The final diagnosis of true progression vs. PSP was based on follow-up MRI using RANO criteria. Three robust clusters have been identified based on 10 predominantly textural FET-PET features. None of the patients with PSP fell into cluster 2, which was associated with high values for textural FET-PET markers of uptake heterogeneity. Three out of 4 patients with PSP were assigned to cluster 3 that was largely associated with low values of textural FET-PET features. By comparison, tumor-to-normal brain ratio (TNRmax) at the optimal cutoff 2.1 was less predictive of PSP (negative predictive value 57% for detecting true progression, p=0.07 vs. 75% with cluster 3, p=0.04). Clustering based on textural O-(2-[18F]fluoroethyl)-L-tyrosine PET features may provide valuable information in assessing the elusive phenomenon of pseudoprogression.
Unsupervised method for automatic construction of a disease dictionary from a large free text collection.

PubMed

Xu, Rong; Supekar, Kaustubh; Morgan, Alex; Das, Amar; Garber, Alan

2008-11-06

Concept specific lexicons (e.g. diseases, drugs, anatomy) are a critical source of background knowledge for many medical language-processing systems. However, the rapid pace of biomedical research and the lack of constraints on usage ensure that such dictionaries are incomplete. Focusing on disease terminology, we have developed an automated, unsupervised, iterative pattern learning approach for constructing a comprehensive medical dictionary of disease terms from randomized clinical trial (RCT) abstracts, and we compared different ranking methods for automatically extracting con-textual patterns and concept terms. When used to identify disease concepts from 100 randomly chosen, manually annotated clinical abstracts, our disease dictionary shows significant performance improvement (F1 increased by 35-88%) over available, manually created disease terminologies.
Unsupervised Method for Automatic Construction of a Disease Dictionary from a Large Free Text Collection

PubMed Central

Xu, Rong; Supekar, Kaustubh; Morgan, Alex; Das, Amar; Garber, Alan

2008-01-01

Concept specific lexicons (e.g. diseases, drugs, anatomy) are a critical source of background knowledge for many medical language-processing systems. However, the rapid pace of biomedical research and the lack of constraints on usage ensure that such dictionaries are incomplete. Focusing on disease terminology, we have developed an automated, unsupervised, iterative pattern learning approach for constructing a comprehensive medical dictionary of disease terms from randomized clinical trial (RCT) abstracts, and we compared different ranking methods for automatically extracting contextual patterns and concept terms. When used to identify disease concepts from 100 randomly chosen, manually annotated clinical abstracts, our disease dictionary shows significant performance improvement (F1 increased by 35–88%) over available, manually created disease terminologies. PMID:18999169
A Benchmark Dataset and Saliency-guided Stacked Autoencoders for Video-based Salient Object Detection.

PubMed

Li, Jia; Xia, Changqun; Chen, Xiaowu

2017-10-12

Image-based salient object detection (SOD) has been extensively studied in past decades. However, video-based SOD is much less explored due to the lack of large-scale video datasets within which salient objects are unambiguously defined and annotated. Toward this end, this paper proposes a video-based SOD dataset that consists of 200 videos. In constructing the dataset, we manually annotate all objects and regions over 7,650 uniformly sampled keyframes and collect the eye-tracking data of 23 subjects who free-view all videos. From the user data, we find that salient objects in a video can be defined as objects that consistently pop-out throughout the video, and objects with such attributes can be unambiguously annotated by combining manually annotated object/region masks with eye-tracking data of multiple subjects. To the best of our knowledge, it is currently the largest dataset for videobased salient object detection. Based on this dataset, this paper proposes an unsupervised baseline approach for video-based SOD by using saliencyguided stacked autoencoders. In the proposed approach, multiple spatiotemporal saliency cues are first extracted at the pixel, superpixel and object levels. With these saliency cues, stacked autoencoders are constructed in an unsupervised manner that automatically infers a saliency score for each pixel by progressively encoding the high-dimensional saliency cues gathered from the pixel and its spatiotemporal neighbors. In experiments, the proposed unsupervised approach is compared with 31 state-of-the-art models on the proposed dataset and outperforms 30 of them, including 19 imagebased classic (unsupervised or non-deep learning) models, six image-based deep learning models, and five video-based unsupervised models. Moreover, benchmarking results show that the proposed dataset is very challenging and has the potential to boost the development of video-based SOD.
Automated Interpretation of Subcellular Patterns in Fluorescence Microscope Images for Location Proteomics

PubMed Central

Chen, Xiang; Velliste, Meel; Murphy, Robert F.

2010-01-01

Proteomics, the large scale identification and characterization of many or all proteins expressed in a given cell type, has become a major area of biological research. In addition to information on protein sequence, structure and expression levels, knowledge of a protein’s subcellular location is essential to a complete understanding of its functions. Currently subcellular location patterns are routinely determined by visual inspection of fluorescence microscope images. We review here research aimed at creating systems for automated, systematic determination of location. These employ numerical feature extraction from images, feature reduction to identify the most useful features, and various supervised learning (classification) and unsupervised learning (clustering) methods. These methods have been shown to perform significantly better than human interpretation of the same images. When coupled with technologies for tagging large numbers of proteins and high-throughput microscope systems, the computational methods reviewed here enable the new subfield of location proteomics. This subfield will make critical contributions in two related areas. First, it will provide structured, high-resolution information on location to enable Systems Biology efforts to simulate cell behavior from the gene level on up. Second, it will provide tools for Cytomics projects aimed at characterizing the behaviors of all cell types before, during and after the onset of various diseases. PMID:16752421
Comparing supervised learning techniques on the task of physical activity recognition.

PubMed

Dalton, A; OLaighin, G

2013-01-01

The objective of this study was to compare the performance of base-level and meta-level classifiers on the task of physical activity recognition. Five wireless kinematic sensors were attached to each subject (n = 25) while they completed a range of basic physical activities in a controlled laboratory setting. Subjects were then asked to carry out similar self-annotated physical activities in a random order and in an unsupervised environment. A combination of time-domain and frequency-domain features were extracted from the sensor data including the first four central moments, zero-crossing rate, average magnitude, sensor cross-correlation, sensor auto-correlation, spectral entropy and dominant frequency components. A reduced feature set was generated using a wrapper subset evaluation technique with a linear forward search and this feature set was employed for classifier comparison. The meta-level classifier AdaBoostM1 with C4.5 Graft as its base-level classifier achieved an overall accuracy of 95%. Equal sized datasets of subject independent data and subject dependent data were used to train this classifier and high recognition rates could be achieved without the need for user specific training. Furthermore, it was found that an accuracy of 88% could be achieved using data from the ankle and wrist sensors only.
Differentiation of Uterine Leiomyosarcoma from Atypical Leiomyoma: Diagnostic Accuracy of Qualitative MR Imaging Features and Feasibility of Texture Analysis.

PubMed

Lakhman, Yulia; Veeraraghavan, Harini; Chaim, Joshua; Feier, Diana; Goldman, Debra A; Moskowitz, Chaya S; Nougaret, Stephanie; Sosa, Ramon E; Vargas, Hebert Alberto; Soslow, Robert A; Abu-Rustum, Nadeem R; Hricak, Hedvig; Sala, Evis

2017-07-01

To investigate whether qualitative magnetic resonance (MR) features can distinguish leiomyosarcoma (LMS) from atypical leiomyoma (ALM) and assess the feasibility of texture analysis (TA). This retrospective study included 41 women (ALM = 22, LMS = 19) imaged with MRI prior to surgery. Two readers (R1, R2) evaluated each lesion for qualitative MR features. Associations between MR features and LMS were evaluated with Fisher's exact test. Accuracy measures were calculated for the four most significant features. TA was performed for 24 patients (ALM = 14, LMS = 10) with uniform imaging following lesion segmentation on axial T2-weighted images. Texture features were pre-selected using Wilcoxon signed-rank test with Bonferroni correction and analyzed with unsupervised clustering to separate LMS from ALM. Four qualitative MR features most strongly associated with LMS were nodular borders, haemorrhage, "T2 dark" area(s), and central unenhanced area(s) (p ≤ 0.0001 each feature/reader). The highest sensitivity [1.00 (95%CI:0.82-1.00)/0.95 (95%CI: 0.74-1.00)] and specificity [0.95 (95%CI:0.77-1.00)/1.00 (95%CI:0.85-1.00)] were achieved for R1/R2, respectively, when a lesion had ≥3 of these four features. Sixteen texture features differed significantly between LMS and ALM (p-values: <0.001-0.036). Unsupervised clustering achieved accuracy of 0.75 (sensitivity: 0.70; specificity: 0.79). Combination of ≥3 qualitative MR features accurately distinguished LMS from ALM. TA was feasible. • Four qualitative MR features demonstrated the strongest statistical association with LMS. • Combination of ≥3 these features could accurately differentiate LMS from ALM. • Texture analysis was a feasible semi-automated approach for lesion categorization.
Bayesian Fusion of Color and Texture Segmentations

NASA Technical Reports Server (NTRS)

Manduchi, Roberto

2000-01-01

In many applications one would like to use information from both color and texture features in order to segment an image. We propose a novel technique to combine "soft" segmentations computed for two or more features independently. Our algorithm merges models according to a mean entropy criterion, and allows to choose the appropriate number of classes for the final grouping. This technique also allows to improve the quality of supervised classification based on one feature (e.g. color) by merging information from unsupervised segmentation based on another feature (e.g., texture.)
Analysis of a Probabilistic Model of Redundancy in Unsupervised Information Extraction

DTIC Science & Technology

2010-08-25

5f. WORK UNIT NUMBER 7. PERFORMING ORGANIZATION NAME(S) AND ADDRESS( ES ) University of Washington,Department of Computer Science and Engineering...Box 352350,Seattle,WA,98195 8. PERFORMING ORGANIZATION REPORT NUMBER 9. SPONSORING/MONITORING AGENCY NAME(S) AND ADDRESS( ES ) 10. SPONSOR/MONITOR’S...approximation, with algebra we have: PUSC(x ∈ C|x appears k times inndraws) ≈ 1 1 + |E||C| ( pE pC )ken(pC−pE) . (2) In general, we expect the extraction
Evaluating suitability of Pol-SAR (TerraSAR-X, Radarsat-2) for automated sea ice classification

NASA Astrophysics Data System (ADS)

Ressel, Rudolf; Singha, Suman; Lehner, Susanne

2016-05-01

Satellite borne SAR imagery has become an invaluable tool in the field of sea ice monitoring. Previously, single polarimetric imagery were employed in supervised and unsupervised classification schemes for sea ice investigation, which was preceded by image processing techniques such as segmentation and textural features. Recently, through the advent of polarimetric SAR sensors, investigation of polarimetric features in sea ice has attracted increased attention. While dual-polarimetric data has already been investigated in a number of works, full-polarimetric data has so far not been a major scientific focus. To explore the possibilities of full-polarimetric data and compare the differences in C- and X-bands, we endeavor to analyze in detail an array of datasets, simultaneously acquired, in C-band (RADARSAT-2) and X-band (TerraSAR-X) over ice infested areas. First, we propose an array of polarimetric features (Pauli and lexicographic based). Ancillary data from national ice services, SMOS data and expert judgement were utilized to identify the governing ice regimes. Based on these observations, we then extracted mentioned features. The subsequent supervised classification approach was based on an Artificial Neural Network (ANN). To gain quantitative insight into the quality of the features themselves (and reduce a possible impact of the Hughes phenomenon), we employed mutual information to unearth the relevance and redundancy of features. The results of this information theoretic analysis guided a pruning process regarding the optimal subset of features. In the last step we compared the classified results of all sensors and images, stated respective accuracies and discussed output discrepancies in the cases of simultaneous acquisitions.
Scalable High Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning

PubMed Central

Wu, Guorong; Kim, Minjeong; Wang, Qian; Munsell, Brent C.

2015-01-01

Feature selection is a critical step in deformable image registration. In particular, selecting the most discriminative features that accurately and concisely describe complex morphological patterns in image patches improves correspondence detection, which in turn improves image registration accuracy. Furthermore, since more and more imaging modalities are being invented to better identify morphological changes in medical imaging data,, the development of deformable image registration method that scales well to new image modalities or new image applications with little to no human intervention would have a significant impact on the medical image analysis community. To address these concerns, a learning-based image registration framework is proposed that uses deep learning to discover compact and highly discriminative features upon observed imaging data. Specifically, the proposed feature selection method uses a convolutional stacked auto-encoder to identify intrinsic deep feature representations in image patches. Since deep learning is an unsupervised learning method, no ground truth label knowledge is required. This makes the proposed feature selection method more flexible to new imaging modalities since feature representations can be directly learned from the observed imaging data in a very short amount of time. Using the LONI and ADNI imaging datasets, image registration performance was compared to two existing state-of-the-art deformable image registration methods that use handcrafted features. To demonstrate the scalability of the proposed image registration framework image registration experiments were conducted on 7.0-tesla brain MR images. In all experiments, the results showed the new image registration framework consistently demonstrated more accurate registration results when compared to state-of-the-art. PMID:26552069
Scalable High-Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning.

PubMed

Wu, Guorong; Kim, Minjeong; Wang, Qian; Munsell, Brent C; Shen, Dinggang

2016-07-01

Feature selection is a critical step in deformable image registration. In particular, selecting the most discriminative features that accurately and concisely describe complex morphological patterns in image patches improves correspondence detection, which in turn improves image registration accuracy. Furthermore, since more and more imaging modalities are being invented to better identify morphological changes in medical imaging data, the development of deformable image registration method that scales well to new image modalities or new image applications with little to no human intervention would have a significant impact on the medical image analysis community. To address these concerns, a learning-based image registration framework is proposed that uses deep learning to discover compact and highly discriminative features upon observed imaging data. Specifically, the proposed feature selection method uses a convolutional stacked autoencoder to identify intrinsic deep feature representations in image patches. Since deep learning is an unsupervised learning method, no ground truth label knowledge is required. This makes the proposed feature selection method more flexible to new imaging modalities since feature representations can be directly learned from the observed imaging data in a very short amount of time. Using the LONI and ADNI imaging datasets, image registration performance was compared to two existing state-of-the-art deformable image registration methods that use handcrafted features. To demonstrate the scalability of the proposed image registration framework, image registration experiments were conducted on 7.0-T brain MR images. In all experiments, the results showed that the new image registration framework consistently demonstrated more accurate registration results when compared to state of the art.
High Throughput Multispectral Image Processing with Applications in Food Science.

PubMed

Tsakanikas, Panagiotis; Pavlidis, Dimitris; Nychas, George-John

2015-01-01

Recently, machine vision is gaining attention in food science as well as in food industry concerning food quality assessment and monitoring. Into the framework of implementation of Process Analytical Technology (PAT) in the food industry, image processing can be used not only in estimation and even prediction of food quality but also in detection of adulteration. Towards these applications on food science, we present here a novel methodology for automated image analysis of several kinds of food products e.g. meat, vanilla crème and table olives, so as to increase objectivity, data reproducibility, low cost information extraction and faster quality assessment, without human intervention. Image processing's outcome will be propagated to the downstream analysis. The developed multispectral image processing method is based on unsupervised machine learning approach (Gaussian Mixture Models) and a novel unsupervised scheme of spectral band selection for segmentation process optimization. Through the evaluation we prove its efficiency and robustness against the currently available semi-manual software, showing that the developed method is a high throughput approach appropriate for massive data extraction from food samples.
Unsupervised User Similarity Mining in GSM Sensor Networks

PubMed Central

Shad, Shafqat Ali; Chen, Enhong

2013-01-01

Mobility data has attracted the researchers for the past few years because of its rich context and spatiotemporal nature, where this information can be used for potential applications like early warning system, route prediction, traffic management, advertisement, social networking, and community finding. All the mentioned applications are based on mobility profile building and user trend analysis, where mobility profile building is done through significant places extraction, user's actual movement prediction, and context awareness. However, significant places extraction and user's actual movement prediction for mobility profile building are a trivial task. In this paper, we present the user similarity mining-based methodology through user mobility profile building by using the semantic tagging information provided by user and basic GSM network architecture properties based on unsupervised clustering approach. As the mobility information is in low-level raw form, our proposed methodology successfully converts it to a high-level meaningful information by using the cell-Id location information rather than previously used location capturing methods like GPS, Infrared, and Wifi for profile mining and user similarity mining. PMID:23576905
Semi-automatic mapping of linear-trending bedforms using 'Self-Organizing Maps' algorithm

NASA Astrophysics Data System (ADS)

Foroutan, M.; Zimbelman, J. R.

2017-09-01

Increased application of high resolution spatial data such as high resolution satellite or Unmanned Aerial Vehicle (UAV) images from Earth, as well as High Resolution Imaging Science Experiment (HiRISE) images from Mars, makes it necessary to increase automation techniques capable of extracting detailed geomorphologic elements from such large data sets. Model validation by repeated images in environmental management studies such as climate-related changes as well as increasing access to high-resolution satellite images underline the demand for detailed automatic image-processing techniques in remote sensing. This study presents a methodology based on an unsupervised Artificial Neural Network (ANN) algorithm, known as Self Organizing Maps (SOM), to achieve the semi-automatic extraction of linear features with small footprints on satellite images. SOM is based on competitive learning and is efficient for handling huge data sets. We applied the SOM algorithm to high resolution satellite images of Earth and Mars (Quickbird, Worldview and HiRISE) in order to facilitate and speed up image analysis along with the improvement of the accuracy of results. About 98% overall accuracy and 0.001 quantization error in the recognition of small linear-trending bedforms demonstrate a promising framework.
e-IQ and IQ knowledge mining for generalized LDA

NASA Astrophysics Data System (ADS)

Jenkins, Jeffrey; van Bergem, Rutger; Sweet, Charles; Vietsch, Eveline; Szu, Harold

2015-05-01

How can the human brain uncover patterns, associations and features in real-time, real-world data? There must be a general strategy used to transform raw signals into useful features, but representing this generalization in the context of our information extraction tool set is lacking. In contrast to Big Data (BD), Large Data Analysis (LDA) has become a reachable multi-disciplinary goal in recent years due in part to high performance computers and algorithm development, as well as the availability of large data sets. However, the experience of Machine Learning (ML) and information communities has not been generalized into an intuitive framework that is useful to researchers across disciplines. The data exploration phase of data mining is a prime example of this unspoken, ad-hoc nature of ML - the Computer Scientist works with a Subject Matter Expert (SME) to understand the data, and then build tools (i.e. classifiers, etc.) which can benefit the SME and the rest of the researchers in that field. We ask, why is there not a tool to represent information in a meaningful way to the researcher asking the question? Meaning is subjective and contextual across disciplines, so to ensure robustness, we draw examples from several disciplines and propose a generalized LDA framework for independent data understanding of heterogeneous sources which contribute to Knowledge Discovery in Databases (KDD). Then, we explore the concept of adaptive Information resolution through a 6W unsupervised learning methodology feedback system. In this paper, we will describe the general process of man-machine interaction in terms of an asymmetric directed graph theory (digging for embedded knowledge), and model the inverse machine-man feedback (digging for tacit knowledge) as an ANN unsupervised learning methodology. Finally, we propose a collective learning framework which utilizes a 6W semantic topology to organize heterogeneous knowledge and diffuse information to entities within a society in a personalized way.
VizieR Online Data Catalog: Redshift reliability flags (VVDS data) (Jamal+, 2018)

NASA Astrophysics Data System (ADS)

Jamal, S.; Le Brun, V.; Le Fevre, O.; Vibert, D.; Schmitt, A.; Surace, C.; Copin, Y.; Garilli, B.; Moresco, M.; Pozzetti, L.

2017-09-01

The VIMOS VLT Deep Survey (Le Fevre et al. 2013A&A...559A..14L) is a combination of 3 i-band magnitude limited surveys: Wide (17.5<=iAB<=22.5; 8.6deg2), Deep (17.5<=iAB<=24; 0.6deg2) and Ultra-Deep (23<=iAB<=24.75; 512arcmin2), that produced a total of 35526 spectroscopic galaxy redshifts between 0 and 6.7 (22434 in Wide, 12051 in Deep and 1041 in UDeep). We supplement spectra of the VIMOS VLT Deep Survey (VVDS) with newly-defined redshift reliability flags obtained from clustering (unsupervised classification in Machine Learning) a set of descriptors from individual zPDFs. In this paper, we exploit a set of 24519 spectra from the VVDS database. After computing zPDFs for each individual spectrum, a set of (8) descriptors of the zPDF are extracted to build a feature matrix X (dimension = 24519 rows, 8 columns). Then, we use a clustering (unsupervised algorithms in Machine Learning) algorithm to partition the feature space into distinct clusters (5 clusters: C1,C2,C3,C4,C5), each depicting a different level of confidence to associate with the measured redshift zMAP (Maximum-A-Posteriori estimate that corresponds to the maximum of the redshift PDF). The clustering results (C1,C2,C3,C4,C5) reported in the table are those used in the paper (Jamal et al, 2017) to present the new methodology of automating the zspec reliability assessment. In particular, we would like to point out that they were obtained from first tests conducted on the VVDS spectroscopic data (end of 2016). Therefore, the table does not depict immutable results (on-going improvements). Future updates of the VVDS redshift reliability flags can be expected. (1 data file).
Wide field imaging - I. Applications of neural networks to object detection and star/galaxy classification

NASA Astrophysics Data System (ADS)

Andreon, S.; Gargiulo, G.; Longo, G.; Tagliaferri, R.; Capuano, N.

2000-12-01

Astronomical wide-field imaging performed with new large-format CCD detectors poses data reduction problems of unprecedented scale, which are difficult to deal with using traditional interactive tools. We present here NExt (Neural Extractor), a new neural network (NN) based package capable of detecting objects and performing both deblending and star/galaxy classification in an automatic way. Traditionally, in astronomical images, objects are first distinguished from the noisy background by searching for sets of connected pixels having brightnesses above a given threshold; they are then classified as stars or as galaxies through diagnostic diagrams having variables chosen according to the astronomer's taste and experience. In the extraction step, assuming that images are well sampled, NExt requires only the simplest a priori definition of `what an object is' (i.e. it keeps all structures composed of more than one pixel) and performs the detection via an unsupervised NN, approaching detection as a clustering problem that has been thoroughly studied in the artificial intelligence literature. The first part of the NExt procedure consists of an optimal compression of the redundant information contained in the pixels via a mapping from pixel intensities to a subspace individualized through principal component analysis. At magnitudes fainter than the completeness limit, stars are usually almost indistinguishable from galaxies, and therefore the parameters characterizing the two classes do not lie in disconnected subspaces, thus preventing the use of unsupervised methods. We therefore adopted a supervised NN (i.e. a NN that first finds the rules to classify objects from examples and then applies them to the whole data set). In practice, each object is classified depending on its membership of the regions mapping the input feature space in the training set. In order to obtain an objective and reliable classification, instead of using an arbitrarily defined set of features we use a NN to select the most significant features among the large number of measured ones, and then we use these selected features to perform the classification task. In order to optimize the performance of the system, we implemented and tested several different models of NN. The comparison of the NExt performance with that of the best detection and classification package known to the authors (SExtractor) shows that NExt is at least as effective as the best traditional packages.
Color normalization of histology slides using graph regularized sparse NMF

NASA Astrophysics Data System (ADS)

Sha, Lingdao; Schonfeld, Dan; Sethi, Amit

2017-03-01

Computer based automatic medical image processing and quantification are becoming popular in digital pathology. However, preparation of histology slides can vary widely due to differences in staining equipment, procedures and reagents, which can reduce the accuracy of algorithms that analyze their color and texture information. To re- duce the unwanted color variations, various supervised and unsupervised color normalization methods have been proposed. Compared with supervised color normalization methods, unsupervised color normalization methods have advantages of time and cost efficient and universal applicability. Most of the unsupervised color normaliza- tion methods for histology are based on stain separation. Based on the fact that stain concentration cannot be negative and different parts of the tissue absorb different stains, nonnegative matrix factorization (NMF), and particular its sparse version (SNMF), are good candidates for stain separation. However, most of the existing unsupervised color normalization method like PCA, ICA, NMF and SNMF fail to consider important information about sparse manifolds that its pixels occupy, which could potentially result in loss of texture information during color normalization. Manifold learning methods like Graph Laplacian have proven to be very effective in interpreting high-dimensional data. In this paper, we propose a novel unsupervised stain separation method called graph regularized sparse nonnegative matrix factorization (GSNMF). By considering the sparse prior of stain concentration together with manifold information from high-dimensional image data, our method shows better performance in stain color deconvolution than existing unsupervised color deconvolution methods, especially in keeping connected texture information. To utilized the texture information, we construct a nearest neighbor graph between pixels within a spatial area of an image based on their distances using heat kernal in lαβ space. The representation of a pixel in the stain density space is constrained to follow the feature distance of the pixel to pixels in the neighborhood graph. Utilizing color matrix transfer method with the stain concentrations found using our GSNMF method, the color normalization performance was also better than existing methods.
DOE Office of Scientific and Technical Information (OSTI.GOV)

Rios Velazquez, E; Parmar, C; Narayan, V

Purpose: To compare the complementary value of quantitative radiomic features to that of radiologist-annotated semantic features in predicting EGFR mutations in lung adenocarcinomas. Methods: Pre-operative CT images of 258 lung adenocarcinoma patients were available. Tumors were segmented using the sing-click ensemble segmentation algorithm. A set of radiomic features was extracted using 3D-Slicer. Test-retest reproducibility and unsupervised dimensionality reduction were applied to select a subset of reproducible and independent radiomic features. Twenty semantic annotations were scored by an expert radiologist, describing the tumor, surrounding tissue and associated findings. Minimum-redundancy-maximum-relevance (MRMR) was used to identify the most informative radiomic and semantic featuresmore » in 172 patients (training-set, temporal split). Radiomic, semantic and combined radiomic-semantic logistic regression models to predict EGFR mutations were evaluated in and independent validation dataset of 86 patients using the area under the receiver operating curve (AUC). Results: EGFR mutations were found in 77/172 (45%) and 39/86 (45%) of the training and validation sets, respectively. Univariate AUCs showed a similar range for both feature types: radiomics median AUC = 0.57 (range: 0.50 – 0.62); semantic median AUC = 0.53 (range: 0.50 – 0.64, Wilcoxon p = 0.55). After MRMR feature selection, the best-performing radiomic, semantic, and radiomic-semantic logistic regression models, for EGFR mutations, showed a validation AUC of 0.56 (p = 0.29), 0.63 (p = 0.063) and 0.67 (p = 0.004), respectively. Conclusion: Quantitative volumetric and textural Radiomic features complement the qualitative and semi-quantitative radiologist annotations. The prognostic value of informative qualitative semantic features such as cavitation and lobulation is increased with the addition of quantitative textural features from the tumor region.« less

Image-based spectroscopy for environmental monitoring

NASA Astrophysics Data System (ADS)

Bachmakov, Eduard; Molina, Carolyn; Wynne, Rosalind

2014-03-01

An image-processing algorithm for use with a nano-featured spectrometer chemical agent detection configuration is presented. The spectrometer chip acquired from Nano-Optic DevicesTM can reduce the size of the spectrometer down to a coin. The nanospectrometer chip was aligned with a 635nm laser source, objective lenses, and a CCD camera. The images from a nanospectrometer chip were collected and compared to reference spectra. Random background noise contributions were isolated and removed from the diffraction pattern image analysis via a threshold filter. Results are provided for the image-based detection of the diffraction pattern produced by the nanospectrometer. The featured PCF spectrometer has the potential to measure optical absorption spectra in order to detect trace amounts of contaminants. MATLAB tools allow for implementation of intelligent, automatic detection of the relevant sub-patterns in the diffraction patterns and subsequent extraction of the parameters using region-detection algorithms such as the generalized Hough transform, which detects specific shapes within the image. This transform is a method for detecting curves by exploiting the duality between points on a curve and parameters of that curve. By employing this imageprocessing technique, future sensor systems will benefit from new applications such as unsupervised environmental monitoring of air or water quality.
Application of self-organizing feature maps to analyze the relationships between ignitable liquids and selected mass spectral ions.

PubMed

Frisch-Daiello, Jessica L; Williams, Mary R; Waddell, Erin E; Sigman, Michael E

2014-03-01

The unsupervised artificial neural networks method of self-organizing feature maps (SOFMs) is applied to spectral data of ignitable liquids to visualize the grouping of similar ignitable liquids with respect to their American Society for Testing and Materials (ASTM) class designations and to determine the ions associated with each group. The spectral data consists of extracted ion spectra (EIS), defined as the time-averaged mass spectrum across the chromatographic profile for select ions, where the selected ions are a subset of ions from Table 2 of the ASTM standard E1618-11. Utilization of the EIS allows for inter-laboratory comparisons without the concern of retention time shifts. The trained SOFM demonstrates clustering of the ignitable liquid samples according to designated ASTM classes. The EIS of select samples designated as miscellaneous or oxygenated as well as ignitable liquid residues from fire debris samples are projected onto the SOFM. The results indicate the similarities and differences between the variables of the newly projected data compared to those of the data used to train the SOFM. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.
pyAudioAnalysis: An Open-Source Python Library for Audio Signal Analysis.

PubMed

Giannakopoulos, Theodoros

2015-01-01

Audio information plays a rather important role in the increasing digital content that is available today, resulting in a need for methodologies that automatically analyze such content: audio event recognition for home automations and surveillance systems, speech recognition, music information retrieval, multimodal analysis (e.g. audio-visual analysis of online videos for content-based recommendation), etc. This paper presents pyAudioAnalysis, an open-source Python library that provides a wide range of audio analysis procedures including: feature extraction, classification of audio signals, supervised and unsupervised segmentation and content visualization. pyAudioAnalysis is licensed under the Apache License and is available at GitHub (https://github.com/tyiannak/pyAudioAnalysis/). Here we present the theoretical background behind the wide range of the implemented methodologies, along with evaluation metrics for some of the methods. pyAudioAnalysis has been already used in several audio analysis research applications: smart-home functionalities through audio event detection, speech emotion recognition, depression classification based on audio-visual features, music segmentation, multimodal content-based movie recommendation and health applications (e.g. monitoring eating habits). The feedback provided from all these particular audio applications has led to practical enhancement of the library.
Informatics and machine learning to define the phenotype.

PubMed

Basile, Anna Okula; Ritchie, Marylyn DeRiggi

2018-03-01

For the past decade, the focus of complex disease research has been the genotype. From technological advancements to the development of analysis methods, great progress has been made. However, advances in our definition of the phenotype have remained stagnant. Phenotype characterization has recently emerged as an exciting area of informatics and machine learning. The copious amounts of diverse biomedical data that have been collected may be leveraged with data-driven approaches to elucidate trait-related features and patterns. Areas covered: In this review, the authors discuss the phenotype in traditional genetic associations and the challenges this has imposed.Approaches for phenotype refinement that can aid in more accurate characterization of traits are also discussed. Further, the authors highlight promising machine learning approaches for establishing a phenotype and the challenges of electronic health record (EHR)-derived data. Expert commentary: The authors hypothesize that through unsupervised machine learning, data-driven approaches can be used to define phenotypes rather than relying on expert clinician knowledge. Through the use of machine learning and an unbiased set of features extracted from clinical repositories, researchers will have the potential to further understand complex traits and identify patient subgroups. This knowledge may lead to more preventative and precise clinical care.
pyAudioAnalysis: An Open-Source Python Library for Audio Signal Analysis

PubMed Central

Giannakopoulos, Theodoros

2015-01-01

Audio information plays a rather important role in the increasing digital content that is available today, resulting in a need for methodologies that automatically analyze such content: audio event recognition for home automations and surveillance systems, speech recognition, music information retrieval, multimodal analysis (e.g. audio-visual analysis of online videos for content-based recommendation), etc. This paper presents pyAudioAnalysis, an open-source Python library that provides a wide range of audio analysis procedures including: feature extraction, classification of audio signals, supervised and unsupervised segmentation and content visualization. pyAudioAnalysis is licensed under the Apache License and is available at GitHub (https://github.com/tyiannak/pyAudioAnalysis/). Here we present the theoretical background behind the wide range of the implemented methodologies, along with evaluation metrics for some of the methods. pyAudioAnalysis has been already used in several audio analysis research applications: smart-home functionalities through audio event detection, speech emotion recognition, depression classification based on audio-visual features, music segmentation, multimodal content-based movie recommendation and health applications (e.g. monitoring eating habits). The feedback provided from all these particular audio applications has led to practical enhancement of the library. PMID:26656189
Unsupervised consensus cluster analysis of [18F]-fluoroethyl-L-tyrosine positron emission tomography identified textural features for the diagnosis of pseudoprogression in high-grade glioma

PubMed Central

Kebir, Sied; Khurshid, Zain; Gaertner, Florian C.; Essler, Markus; Hattingen, Elke; Fimmers, Rolf; Scheffler, Björn; Herrlinger, Ulrich; Bundschuh, Ralph A.; Glas, Martin

2017-01-01

Rationale Timely detection of pseudoprogression (PSP) is crucial for the management of patients with high-grade glioma (HGG) but remains difficult. Textural features of O-(2-[18F]fluoroethyl)-L-tyrosine positron emission tomography (FET-PET) mirror tumor uptake heterogeneity; some of them may be associated with tumor progression. Methods Fourteen patients with HGG and suspected of PSP underwent FET-PET imaging. A set of 19 conventional and textural FET-PET features were evaluated and subjected to unsupervised consensus clustering. The final diagnosis of true progression vs. PSP was based on follow-up MRI using RANO criteria. Results Three robust clusters have been identified based on 10 predominantly textural FET-PET features. None of the patients with PSP fell into cluster 2, which was associated with high values for textural FET-PET markers of uptake heterogeneity. Three out of 4 patients with PSP were assigned to cluster 3 that was largely associated with low values of textural FET-PET features. By comparison, tumor-to-normal brain ratio (TNRmax) at the optimal cutoff 2.1 was less predictive of PSP (negative predictive value 57% for detecting true progression, p=0.07 vs. 75% with cluster 3, p=0.04). Principal Conclusions Clustering based on textural O-(2-[18F]fluoroethyl)-L-tyrosine PET features may provide valuable information in assessing the elusive phenomenon of pseudoprogression. PMID:28030820
Identifying local structural states in atomic imaging by computer vision

DOE Office of Scientific and Technical Information (OSTI.GOV)

Laanait, Nouamane; Ziatdinov, Maxim; He, Qian

The availability of atomically resolved imaging modalities enables an unprecedented view into the local structural states of materials, which manifest themselves by deviations from the fundamental assumptions of periodicity and symmetry. Consequently, approaches that aim to extract these local structural states from atomic imaging data with minimal assumptions regarding the average crystallographic configuration of a material are indispensable to advances in structural and chemical investigations of materials. Here, we present an approach to identify and classify local structural states that is rooted in computer vision. This approach introduces a definition of a structural state that is composed of both localmore » and non-local information extracted from atomically resolved images, and is wholly untethered from the familiar concepts of symmetry and periodicity. Instead, this approach relies on computer vision techniques such as feature detection, and concepts such as scale-invariance. We present the fundamental aspects of local structural state extraction and classification by application to simulated scanning transmission electron microscopy images, and analyze the robustness of this approach in the presence of common instrumental factors such as noise, limited spatial resolution, and weak contrast. Finally, we apply this computer vision-based approach for the unsupervised detection and classification of local structural states in an experimental electron micrograph of a complex oxides interface, and a scanning tunneling micrograph of a defect engineered multilayer graphene surface.« less
Identifying local structural states in atomic imaging by computer vision

DOE PAGES

Laanait, Nouamane; Ziatdinov, Maxim; He, Qian; ...

2016-11-02

The availability of atomically resolved imaging modalities enables an unprecedented view into the local structural states of materials, which manifest themselves by deviations from the fundamental assumptions of periodicity and symmetry. Consequently, approaches that aim to extract these local structural states from atomic imaging data with minimal assumptions regarding the average crystallographic configuration of a material are indispensable to advances in structural and chemical investigations of materials. Here, we present an approach to identify and classify local structural states that is rooted in computer vision. This approach introduces a definition of a structural state that is composed of both localmore » and non-local information extracted from atomically resolved images, and is wholly untethered from the familiar concepts of symmetry and periodicity. Instead, this approach relies on computer vision techniques such as feature detection, and concepts such as scale-invariance. We present the fundamental aspects of local structural state extraction and classification by application to simulated scanning transmission electron microscopy images, and analyze the robustness of this approach in the presence of common instrumental factors such as noise, limited spatial resolution, and weak contrast. Finally, we apply this computer vision-based approach for the unsupervised detection and classification of local structural states in an experimental electron micrograph of a complex oxides interface, and a scanning tunneling micrograph of a defect engineered multilayer graphene surface.« less
CNN: a speaker recognition system using a cascaded neural network.

PubMed

Zaki, M; Ghalwash, A; Elkouny, A A

1996-05-01

The main emphasis of this paper is to present an approach for combining supervised and unsupervised neural network models to the issue of speaker recognition. To enhance the overall operation and performance of recognition, the proposed strategy integrates the two techniques, forming one global model called the cascaded model. We first present a simple conventional technique based on the distance measured between a test vector and a reference vector for different speakers in the population. This particular distance metric has the property of weighting down the components in those directions along which the intraspeaker variance is large. The reason for presenting this method is to clarify the discrepancy in performance between the conventional and neural network approach. We then introduce the idea of using unsupervised learning technique, presented by the winner-take-all model, as a means of recognition. Due to several tests that have been conducted and in order to enhance the performance of this model, dealing with noisy patterns, we have preceded it with a supervised learning model--the pattern association model--which acts as a filtration stage. This work includes both the design and implementation of both conventional and neural network approaches to recognize the speakers templates--which are introduced to the system via a voice master card and preprocessed before extracting the features used in the recognition. The conclusion indicates that the system performance in case of neural network is better than that of the conventional one, achieving a smooth degradation in respect of noisy patterns, and higher performance in respect of noise-free patterns.
Hyperspectral image segmentation using a cooperative nonparametric approach

NASA Astrophysics Data System (ADS)

Taher, Akar; Chehdi, Kacem; Cariou, Claude

2013-10-01

In this paper a new unsupervised nonparametric cooperative and adaptive hyperspectral image segmentation approach is presented. The hyperspectral images are partitioned band by band in parallel and intermediate classification results are evaluated and fused, to get the final segmentation result. Two unsupervised nonparametric segmentation methods are used in parallel cooperation, namely the Fuzzy C-means (FCM) method, and the Linde-Buzo-Gray (LBG) algorithm, to segment each band of the image. The originality of the approach relies firstly on its local adaptation to the type of regions in an image (textured, non-textured), and secondly on the introduction of several levels of evaluation and validation of intermediate segmentation results before obtaining the final partitioning of the image. For the management of similar or conflicting results issued from the two classification methods, we gradually introduced various assessment steps that exploit the information of each spectral band and its adjacent bands, and finally the information of all the spectral bands. In our approach, the detected textured and non-textured regions are treated separately from feature extraction step, up to the final classification results. This approach was first evaluated on a large number of monocomponent images constructed from the Brodatz album. Then it was evaluated on two real applications using a respectively multispectral image for Cedar trees detection in the region of Baabdat (Lebanon) and a hyperspectral image for identification of invasive and non invasive vegetation in the region of Cieza (Spain). A correct classification rate (CCR) for the first application is over 97% and for the second application the average correct classification rate (ACCR) is over 99%.
Comparing supervised and unsupervised multiresolution segmentation approaches for extracting buildings from very high resolution imagery.

PubMed

Belgiu, Mariana; Dr Guţ, Lucian

2014-10-01

Although multiresolution segmentation (MRS) is a powerful technique for dealing with very high resolution imagery, some of the image objects that it generates do not match the geometries of the target objects, which reduces the classification accuracy. MRS can, however, be guided to produce results that approach the desired object geometry using either supervised or unsupervised approaches. Although some studies have suggested that a supervised approach is preferable, there has been no comparative evaluation of these two approaches. Therefore, in this study, we have compared supervised and unsupervised approaches to MRS. One supervised and two unsupervised segmentation methods were tested on three areas using QuickBird and WorldView-2 satellite imagery. The results were assessed using both segmentation evaluation methods and an accuracy assessment of the resulting building classifications. Thus, differences in the geometries of the image objects and in the potential to achieve satisfactory thematic accuracies were evaluated. The two approaches yielded remarkably similar classification results, with overall accuracies ranging from 82% to 86%. The performance of one of the unsupervised methods was unexpectedly similar to that of the supervised method; they identified almost identical scale parameters as being optimal for segmenting buildings, resulting in very similar geometries for the resulting image objects. The second unsupervised method produced very different image objects from the supervised method, but their classification accuracies were still very similar. The latter result was unexpected because, contrary to previously published findings, it suggests a high degree of independence between the segmentation results and classification accuracy. The results of this study have two important implications. The first is that object-based image analysis can be automated without sacrificing classification accuracy, and the second is that the previously accepted idea that classification is dependent on segmentation is challenged by our unexpected results, casting doubt on the value of pursuing 'optimal segmentation'. Our results rather suggest that as long as under-segmentation remains at acceptable levels, imperfections in segmentation can be ruled out, so that a high level of classification accuracy can still be achieved.
An evaluation of unsupervised and supervised learning algorithms for clustering landscape types in the United States

USGS Publications Warehouse

Wendel, Jochen; Buttenfield, Barbara P.; Stanislawski, Larry V.

2016-01-01

Knowledge of landscape type can inform cartographic generalization of hydrographic features, because landscape characteristics provide an important geographic context that affects variation in channel geometry, flow pattern, and network configuration. Landscape types are characterized by expansive spatial gradients, lacking abrupt changes between adjacent classes; and as having a limited number of outliers that might confound classification. The US Geological Survey (USGS) is exploring methods to automate generalization of features in the National Hydrography Data set (NHD), to associate specific sequences of processing operations and parameters with specific landscape characteristics, thus obviating manual selection of a unique processing strategy for every NHD watershed unit. A chronology of methods to delineate physiographic regions for the United States is described, including a recent maximum likelihood classification based on seven input variables. This research compares unsupervised and supervised algorithms applied to these seven input variables, to evaluate and possibly refine the recent classification. Evaluation metrics for unsupervised methods include the Davies–Bouldin index, the Silhouette index, and the Dunn index as well as quantization and topographic error metrics. Cross validation and misclassification rate analysis are used to evaluate supervised classification methods. The paper reports the comparative analysis and its impact on the selection of landscape regions. The compared solutions show problems in areas of high landscape diversity. There is some indication that additional input variables, additional classes, or more sophisticated methods can refine the existing classification.
On the Implementation of a Land Cover Classification System for SAR Images Using Khoros

NASA Technical Reports Server (NTRS)

Medina Revera, Edwin J.; Espinosa, Ramon Vasquez

1997-01-01

The Synthetic Aperture Radar (SAR) sensor is widely used to record data about the ground under all atmospheric conditions. The SAR acquired images have very good resolution which necessitates the development of a classification system that process the SAR images to extract useful information for different applications. In this work, a complete system for the land cover classification was designed and programmed using the Khoros, a data flow visual language environment, taking full advantages of the polymorphic data services that it provides. Image analysis was applied to SAR images to improve and automate the processes of recognition and classification of the different regions like mountains and lakes. Both unsupervised and supervised classification utilities were used. The unsupervised classification routines included the use of several Classification/Clustering algorithms like the K-means, ISO2, Weighted Minimum Distance, and the Localized Receptive Field (LRF) training/classifier. Different texture analysis approaches such as Invariant Moments, Fractal Dimension and Second Order statistics were implemented for supervised classification of the images. The results and conclusions for SAR image classification using the various unsupervised and supervised procedures are presented based on their accuracy and performance.
Unsupervised algorithms for intrusion detection and identification in wireless ad hoc sensor networks

NASA Astrophysics Data System (ADS)

Hortos, William S.

2009-05-01

In previous work by the author, parameters across network protocol layers were selected as features in supervised algorithms that detect and identify certain intrusion attacks on wireless ad hoc sensor networks (WSNs) carrying multisensor data. The algorithms improved the residual performance of the intrusion prevention measures provided by any dynamic key-management schemes and trust models implemented among network nodes. The approach of this paper does not train algorithms on the signature of known attack traffic, but, instead, the approach is based on unsupervised anomaly detection techniques that learn the signature of normal network traffic. Unsupervised learning does not require the data to be labeled or to be purely of one type, i.e., normal or attack traffic. The approach can be augmented to add any security attributes and quantified trust levels, established during data exchanges among nodes, to the set of cross-layer features from the WSN protocols. A two-stage framework is introduced for the security algorithms to overcome the problems of input size and resource constraints. The first stage is an unsupervised clustering algorithm which reduces the payload of network data packets to a tractable size. The second stage is a traditional anomaly detection algorithm based on a variation of support vector machines (SVMs), whose efficiency is improved by the availability of data in the packet payload. In the first stage, selected algorithms are adapted to WSN platforms to meet system requirements for simple parallel distributed computation, distributed storage and data robustness. A set of mobile software agents, acting like an ant colony in securing the WSN, are distributed at the nodes to implement the algorithms. The agents move among the layers involved in the network response to the intrusions at each active node and trustworthy neighborhood, collecting parametric values and executing assigned decision tasks. This minimizes the need to move large amounts of audit-log data through resource-limited nodes and locates routines closer to that data. Performance of the unsupervised algorithms is evaluated against the network intrusions of black hole, flooding, Sybil and other denial-of-service attacks in simulations of published scenarios. Results for scenarios with intentionally malfunctioning sensors show the robustness of the two-stage approach to intrusion anomalies.
Image fusion using sparse overcomplete feature dictionaries

DOEpatents

Brumby, Steven P.; Bettencourt, Luis; Kenyon, Garrett T.; Chartrand, Rick; Wohlberg, Brendt

2015-10-06

Approaches for deciding what individuals in a population of visual system "neurons" are looking for using sparse overcomplete feature dictionaries are provided. A sparse overcomplete feature dictionary may be learned for an image dataset and a local sparse representation of the image dataset may be built using the learned feature dictionary. A local maximum pooling operation may be applied on the local sparse representation to produce a translation-tolerant representation of the image dataset. An object may then be classified and/or clustered within the translation-tolerant representation of the image dataset using a supervised classification algorithm and/or an unsupervised clustering algorithm.
Probability density function learning by unsupervised neurons.

PubMed

Fiori, S

2001-10-01

In a recent work, we introduced the concept of pseudo-polynomial adaptive activation function neuron (FAN) and presented an unsupervised information-theoretic learning theory for such structure. The learning model is based on entropy optimization and provides a way of learning probability distributions from incomplete data. The aim of the present paper is to illustrate some theoretical features of the FAN neuron, to extend its learning theory to asymmetrical density function approximation, and to provide an analytical and numerical comparison with other known density function estimation methods, with special emphasis to the universal approximation ability. The paper also provides a survey of PDF learning from incomplete data, as well as results of several experiments performed on real-world problems and signals.
Semi-Supervised Clustering for High-Dimensional and Sparse Features

ERIC Educational Resources Information Center

Yan, Su

2010-01-01

Clustering is one of the most common data mining tasks, used frequently for data organization and analysis in various application domains. Traditional machine learning approaches to clustering are fully automated and unsupervised where class labels are unknown a priori. In real application domains, however, some "weak" form of side…
VHR satellite multitemporal data to extract cultural landscape changes in the roman site of Grumentum

NASA Astrophysics Data System (ADS)

masini, nicola; Lasaponara, Rosa

2013-04-01

The papers deals with the use of VHR satellite multitemporal data set to extract cultural landscape changes in the roman site of Grumentum Grumentum is an ancient town, 50 km south of Potenza, located near the roman road of Via Herculea which connected the Venusia, in the north est of Basilicata, with Heraclea in the Ionian coast. The first settlement date back to the 6th century BC. It was resettled by the Romans in the 3rd century BC. Its urban fabric which evidences a long history from the Republican age to late Antiquity (III BC-V AD) is composed of the typical urban pattern of cardi and decumani. Its excavated ruins include a large amphitheatre, a theatre, the thermae, the Forum and some temples. There are many techniques nowadays available to capture and record differences in two or more images. In this paper we focus and apply the two main approaches which can be distinguished into : (i) unsupervised and (ii) supervised change detection methods. Unsupervised change detection methods are generally based on the transformation of the two multispectral images in to a single band or multiband image which are further analyzed to identify changes Unsupervised change detection techniques are generally based on three basic steps (i) the preprocessing step, (ii) a pixel-by-pixel comparison is performed, (iii). Identification of changes according to the magnitude an direction (positive /negative). Unsupervised change detection are generally based on the transformation of the two multispectral images into a single band or multiband image which are further analyzed to identify changes. Than the separation between changed and unchanged classes is obtained from the magnitude of the resulting spectral change vectors by means of empirical or theoretical well founded approaches Supervised change detection methods are generally based on supervised classification methods, which require the availability of a suitable training set for the learning process of the classifiers. Unsupervised change detection techniques are generally based on three basic steps (i) the preprocessing step, (ii) supervised classification is performed on the single dates or on the map obtained as the difference of two dates, (iii). Identification of changes according to the magnitude an direction (positive /negative). Supervised change detection are generally based on supervised classification methods, which require the availability of a suitable training set for the learning process of the classifiers, therefore these algorithms require a preliminary knowledge necessary: (i) to generate representative parameters for each class of interest; and (ii) to carry out the training stage Advantages and disadvantages of the supervised and unsupervised approaches are discuss. Finally results from the the satellite multitemporal dataset was also integrated with aerial photos from historical archive in order to expand the time window of the investigation and capture landscape changes occurred from the Agrarian Reform, in the 50s, up today.
Texture analysis based on the Hermite transform for image classification and segmentation

NASA Astrophysics Data System (ADS)

Estudillo-Romero, Alfonso; Escalante-Ramirez, Boris; Savage-Carmona, Jesus

2012-06-01

Texture analysis has become an important task in image processing because it is used as a preprocessing stage in different research areas including medical image analysis, industrial inspection, segmentation of remote sensed imaginary, multimedia indexing and retrieval. In order to extract visual texture features a texture image analysis technique is presented based on the Hermite transform. Psychovisual evidence suggests that the Gaussian derivatives fit the receptive field profiles of mammalian visual systems. The Hermite transform describes locally basic texture features in terms of Gaussian derivatives. Multiresolution combined with several analysis orders provides detection of patterns that characterizes every texture class. The analysis of the local maximum energy direction and steering of the transformation coefficients increase the method robustness against the texture orientation. This method presents an advantage over classical filter bank design because in the latter a fixed number of orientations for the analysis has to be selected. During the training stage, a subset of the Hermite analysis filters is chosen in order to improve the inter-class separability, reduce dimensionality of the feature vectors and computational cost during the classification stage. We exhaustively evaluated the correct classification rate of real randomly selected training and testing texture subsets using several kinds of common used texture features. A comparison between different distance measurements is also presented. Results of the unsupervised real texture segmentation using this approach and comparison with previous approaches showed the benefits of our proposal.
Deep Learning Representation from Electroencephalography of Early-Stage Creutzfeldt-Jakob Disease and Features for Differentiation from Rapidly Progressive Dementia.

PubMed

Morabito, Francesco Carlo; Campolo, Maurizio; Mammone, Nadia; Versaci, Mario; Franceschetti, Silvana; Tagliavini, Fabrizio; Sofia, Vito; Fatuzzo, Daniela; Gambardella, Antonio; Labate, Angelo; Mumoli, Laura; Tripodi, Giovanbattista Gaspare; Gasparini, Sara; Cianci, Vittoria; Sueri, Chiara; Ferlazzo, Edoardo; Aguglia, Umberto

2017-03-01

A novel technique of quantitative EEG for differentiating patients with early-stage Creutzfeldt-Jakob disease (CJD) from other forms of rapidly progressive dementia (RPD) is proposed. The discrimination is based on the extraction of suitable features from the time-frequency representation of the EEG signals through continuous wavelet transform (CWT). An average measure of complexity of the EEG signal obtained by permutation entropy (PE) is also included. The dimensionality of the feature space is reduced through a multilayer processing system based on the recently emerged deep learning (DL) concept. The DL processor includes a stacked auto-encoder, trained by unsupervised learning techniques, and a classifier whose parameters are determined in a supervised way by associating the known category labels to the reduced vector of high-level features generated by the previous processing blocks. The supervised learning step is carried out by using either support vector machines (SVM) or multilayer neural networks (MLP-NN). A subset of EEG from patients suffering from Alzheimer's Disease (AD) and healthy controls (HC) is considered for differentiating CJD patients. When fine-tuning the parameters of the global processing system by a supervised learning procedure, the proposed system is able to achieve an average accuracy of 89%, an average sensitivity of 92%, and an average specificity of 89% in differentiating CJD from RPD. Similar results are obtained for CJD versus AD and CJD versus HC.

Task-dependent recurrent dynamics in visual cortex

PubMed Central

Tajima, Satohiro; Koida, Kowa; Tajima, Chihiro I; Suzuki, Hideyuki; Aihara, Kazuyuki; Komatsu, Hidehiko

2017-01-01

The capacity for flexible sensory-action association in animals has been related to context-dependent attractor dynamics outside the sensory cortices. Here, we report a line of evidence that flexibly modulated attractor dynamics during task switching are already present in the higher visual cortex in macaque monkeys. With a nonlinear decoding approach, we can extract the particular aspect of the neural population response that reflects the task-induced emergence of bistable attractor dynamics in a neural population, which could be obscured by standard unsupervised dimensionality reductions such as PCA. The dynamical modulation selectively increases the information relevant to task demands, indicating that such modulation is beneficial for perceptual decisions. A computational model that features nonlinear recurrent interaction among neurons with a task-dependent background input replicates the key properties observed in the experimental data. These results suggest that the context-dependent attractor dynamics involving the sensory cortex can underlie flexible perceptual abilities. DOI: http://dx.doi.org/10.7554/eLife.26868.001 PMID:28737487
Object-based change detection method using refined Markov random field

NASA Astrophysics Data System (ADS)

Peng, Daifeng; Zhang, Yongjun

2017-01-01

In order to fully consider the local spatial constraints between neighboring objects in object-based change detection (OBCD), an OBCD approach is presented by introducing a refined Markov random field (MRF). First, two periods of images are stacked and segmented to produce image objects. Second, object spectral and textual histogram features are extracted and G-statistic is implemented to measure the distance among different histogram distributions. Meanwhile, object heterogeneity is calculated by combining spectral and textual histogram distance using adaptive weight. Third, an expectation-maximization algorithm is applied for determining the change category of each object and the initial change map is then generated. Finally, a refined change map is produced by employing the proposed refined object-based MRF method. Three experiments were conducted and compared with some state-of-the-art unsupervised OBCD methods to evaluate the effectiveness of the proposed method. Experimental results demonstrate that the proposed method obtains the highest accuracy among the methods used in this paper, which confirms its validness and effectiveness in OBCD.
Blind image quality assessment via probabilistic latent semantic analysis.

PubMed

Yang, Xichen; Sun, Quansen; Wang, Tianshu

2016-01-01

We propose a blind image quality assessment that is highly unsupervised and training free. The new method is based on the hypothesis that the effect caused by distortion can be expressed by certain latent characteristics. Combined with probabilistic latent semantic analysis, the latent characteristics can be discovered by applying a topic model over a visual word dictionary. Four distortion-affected features are extracted to form the visual words in the dictionary: (1) the block-based local histogram; (2) the block-based local mean value; (3) the mean value of contrast within a block; (4) the variance of contrast within a block. Based on the dictionary, the latent topics in the images can be discovered. The discrepancy between the frequency of the topics in an unfamiliar image and a large number of pristine images is applied to measure the image quality. Experimental results for four open databases show that the newly proposed method correlates well with human subjective judgments of diversely distorted images.
shiftNMFk 1.1: Robust Nonnegative matrix factorization with kmeans clustering and signal shift, for allocation of unknown physical sources, toy version for open sourcing with publications

DOE Office of Scientific and Technical Information (OSTI.GOV)

Alexandrov, Boian S.; Lliev, Filip L.; Stanev, Valentin G.

This code is a toy (short) version of CODE-2016-83. From a general perspective, the code represents an unsupervised adaptive machine learning algorithm that allows efficient and high performance de-mixing and feature extraction of a multitude of non-negative signals mixed and recorded by a network of uncorrelated sensor arrays. The code identifies the number of the mixed original signals and their locations. Further, the code also allows deciphering of signals that have been delayed in regards to the mixing process in each sensor. This code is high customizable and it can be efficiently used for a fast macro-analyses of data. Themore » code is applicable to a plethora of distinct problems: chemical decomposition, pressure transient decomposition, unknown sources/signal allocation, EM signal decomposition. An additional procedure for allocation of the unknown sources is incorporated in the code.« less
Robust Head-Pose Estimation Based on Partially-Latent Mixture of Linear Regressions.

PubMed

Drouard, Vincent; Horaud, Radu; Deleforge, Antoine; Ba, Sileye; Evangelidis, Georgios

2017-03-01

Head-pose estimation has many applications, such as social event analysis, human-robot and human-computer interaction, driving assistance, and so forth. Head-pose estimation is challenging, because it must cope with changing illumination conditions, variabilities in face orientation and in appearance, partial occlusions of facial landmarks, as well as bounding-box-to-face alignment errors. We propose to use a mixture of linear regressions with partially-latent output. This regression method learns to map high-dimensional feature vectors (extracted from bounding boxes of faces) onto the joint space of head-pose angles and bounding-box shifts, such that they are robustly predicted in the presence of unobservable phenomena. We describe in detail the mapping method that combines the merits of unsupervised manifold learning techniques and of mixtures of regressions. We validate our method with three publicly available data sets and we thoroughly benchmark four variants of the proposed algorithm with several state-of-the-art head-pose estimation methods.
Robust extraction of basis functions for simultaneous and proportional myoelectric control via sparse non-negative matrix factorization

NASA Astrophysics Data System (ADS)

Lin, Chuang; Wang, Binghui; Jiang, Ning; Farina, Dario

2018-04-01

Objective. This paper proposes a novel simultaneous and proportional multiple degree of freedom (DOF) myoelectric control method for active prostheses. Approach. The approach is based on non-negative matrix factorization (NMF) of surface EMG signals with the inclusion of sparseness constraints. By applying a sparseness constraint to the control signal matrix, it is possible to extract the basis information from arbitrary movements (quasi-unsupervised approach) for multiple DOFs concurrently. Main Results. In online testing based on target hitting, able-bodied subjects reached a greater throughput (TP) when using sparse NMF (SNMF) than with classic NMF or with linear regression (LR). Accordingly, the completion time (CT) was shorter for SNMF than NMF or LR. The same observations were made in two patients with unilateral limb deficiencies. Significance. The addition of sparseness constraints to NMF allows for a quasi-unsupervised approach to myoelectric control with superior results with respect to previous methods for the simultaneous and proportional control of multi-DOF. The proposed factorization algorithm allows robust simultaneous and proportional control, is superior to previous supervised algorithms, and, because of minimal supervision, paves the way to online adaptation in myoelectric control.
Reduction of capsule endoscopy reading times by unsupervised image mining.

PubMed

Iakovidis, D K; Tsevas, S; Polydorou, A

2010-09-01

The screening of the small intestine has become painless and easy with wireless capsule endoscopy (WCE) that is a revolutionary, relatively non-invasive imaging technique performed by a wireless swallowable endoscopic capsule transmitting thousands of video frames per examination. The average time required for the visual inspection of a full 8-h WCE video ranges from 45 to 120min, depending on the experience of the examiner. In this paper, we propose a novel approach to WCE reading time reduction by unsupervised mining of video frames. The proposed methodology is based on a data reduction algorithm which is applied according to a novel scheme for the extraction of representative video frames from a full length WCE video. It can be used either as a video summarization or as a video bookmarking tool, providing the comparative advantage of being general, unbounded by the finiteness of a training set. The number of frames extracted is controlled by a parameter that can be tuned automatically. Comprehensive experiments on real WCE videos indicate that a significant reduction in the reading times is feasible. In the case of the WCE videos used this reduction reached 85% without any loss of abnormalities.
Unsupervised classification of major depression using functional connectivity MRI.

PubMed

Zeng, Ling-Li; Shen, Hui; Liu, Li; Hu, Dewen

2014-04-01

The current diagnosis of psychiatric disorders including major depressive disorder based largely on self-reported symptoms and clinical signs may be prone to patients' behaviors and psychiatrists' bias. This study aims at developing an unsupervised machine learning approach for the accurate identification of major depression based on single resting-state functional magnetic resonance imaging scans in the absence of clinical information. Twenty-four medication-naive patients with major depression and 29 demographically similar healthy individuals underwent resting-state functional magnetic resonance imaging. We first clustered the voxels within the perigenual cingulate cortex into two subregions, a subgenual region and a pregenual region, according to their distinct resting-state functional connectivity patterns and showed that a maximum margin clustering-based unsupervised machine learning approach extracted sufficient information from the subgenual cingulate functional connectivity map to differentiate depressed patients from healthy controls with a group-level clustering consistency of 92.5% and an individual-level classification consistency of 92.5%. It was also revealed that the subgenual cingulate functional connectivity network with the highest discriminative power primarily included the ventrolateral and ventromedial prefrontal cortex, superior temporal gyri and limbic areas, indicating that these connections may play critical roles in the pathophysiology of major depression. The current study suggests that subgenual cingulate functional connectivity network signatures may provide promising objective biomarkers for the diagnosis of major depression and that maximum margin clustering-based unsupervised machine learning approaches may have the potential to inform clinical practice and aid in research on psychiatric disorders. Copyright © 2013 Wiley Periodicals, Inc.
Early pest detection in soy plantations from hyperspectral measurements: a case study for caterpillar detection

NASA Astrophysics Data System (ADS)

Tailanián, Matías; Castiglioni, Enrique; Musé, Pablo; Fernández Flores, Germán.; Lema, Gabriel; Mastrángelo, Pedro; Almansa, Mónica; Fernández Liñares, Ignacio; Fernández Liñares, Germán.

2015-10-01

Soybean producers suffer from caterpillar damage in many areas of the world. Estimated average economic losses are annually 500 million USD in Brazil, Argentina, Paraguay and Uruguay. Designing efficient pest control management using selective and targeted pesticide applications is extremely important both from economic and environmental perspectives. With that in mind, we conducted a research program during the 2013-2014 and 2014-2015 planting seasons in a 4,000 ha soybean farm, seeking to achieve early pest detection. Nowadays pest presence is evaluated using manual, labor-intensive counting methods based on sampling strategies which are time consuming and imprecise. The experiment was conducted as follows. Using manual counting methods as ground-truth, a spectrometer capturing reflectance from 400 to 1100 nm was used to measure the reflectance of soy plants. A first conclusion, resulting from measuring the spectral response at leaves level, showed that stress was a property of plants since different leaves with different levels of damage yielded the same spectral response. Then, to assess the applicability of unsupervised classification of plants as healthy, biotic-stressed or abiotic-stressed, feature extraction and selection from leaves spectral signatures, combined with a Supported Vector Machine classifier was designed. Optimization of SVM parameters using grid search with cross-validation, along with classification evaluation by ten-folds cross-validation showed a correct classification rate of 95%, consistently on both seasons. Controlled experiments using cages with different numbers of caterpillars--including caterpillar-free plants--were also conducted to evaluate consistency in trends of the spectral response as well as the extracted features.
Performance comparison of machine learning algorithms and number of independent components used in fMRI decoding of belief vs. disbelief.

PubMed

Douglas, P K; Harris, Sam; Yuille, Alan; Cohen, Mark S

2011-05-15

Machine learning (ML) has become a popular tool for mining functional neuroimaging data, and there are now hopes of performing such analyses efficiently in real-time. Towards this goal, we compared accuracy of six different ML algorithms applied to neuroimaging data of persons engaged in a bivariate task, asserting their belief or disbelief of a variety of propositional statements. We performed unsupervised dimension reduction and automated feature extraction using independent component (IC) analysis and extracted IC time courses. Optimization of classification hyperparameters across each classifier occurred prior to assessment. Maximum accuracy was achieved at 92% for Random Forest, followed by 91% for AdaBoost, 89% for Naïve Bayes, 87% for a J48 decision tree, 86% for K*, and 84% for support vector machine. For real-time decoding applications, finding a parsimonious subset of diagnostic ICs might be useful. We used a forward search technique to sequentially add ranked ICs to the feature subspace. For the current data set, we determined that approximately six ICs represented a meaningful basis set for classification. We then projected these six IC spatial maps forward onto a later scanning session within subject. We then applied the optimized ML algorithms to these new data instances, and found that classification accuracy results were reproducible. Additionally, we compared our classification method to our previously published general linear model results on this same data set. The highest ranked IC spatial maps show similarity to brain regions associated with contrasts for belief > disbelief, and disbelief < belief. Copyright © 2010 Elsevier Inc. All rights reserved.
A Granular Self-Organizing Map for Clustering and Gene Selection in Microarray Data.

PubMed

Ray, Shubhra Sankar; Ganivada, Avatharam; Pal, Sankar K

2016-09-01

A new granular self-organizing map (GSOM) is developed by integrating the concept of a fuzzy rough set with the SOM. While training the GSOM, the weights of a winning neuron and the neighborhood neurons are updated through a modified learning procedure. The neighborhood is newly defined using the fuzzy rough sets. The clusters (granules) evolved by the GSOM are presented to a decision table as its decision classes. Based on the decision table, a method of gene selection is developed. The effectiveness of the GSOM is shown in both clustering samples and developing an unsupervised fuzzy rough feature selection (UFRFS) method for gene selection in microarray data. While the superior results of the GSOM, as compared with the related clustering methods, are provided in terms of β -index, DB-index, Dunn-index, and fuzzy rough entropy, the genes selected by the UFRFS are not only better in terms of classification accuracy and a feature evaluation index, but also statistically more significant than the related unsupervised methods. The C-codes of the GSOM and UFRFS are available online at http://avatharamg.webs.com/software-code.
Nonlinear dimension reduction and clustering by Minimum Curvilinearity unfold neuropathic pain and tissue embryological classes.

PubMed

Cannistraci, Carlo Vittorio; Ravasi, Timothy; Montevecchi, Franco Maria; Ideker, Trey; Alessio, Massimo

2010-09-15

Nonlinear small datasets, which are characterized by low numbers of samples and very high numbers of measures, occur frequently in computational biology, and pose problems in their investigation. Unsupervised hybrid-two-phase (H2P) procedures-specifically dimension reduction (DR), coupled with clustering-provide valuable assistance, not only for unsupervised data classification, but also for visualization of the patterns hidden in high-dimensional feature space. 'Minimum Curvilinearity' (MC) is a principle that-for small datasets-suggests the approximation of curvilinear sample distances in the feature space by pair-wise distances over their minimum spanning tree (MST), and thus avoids the introduction of any tuning parameter. MC is used to design two novel forms of nonlinear machine learning (NML): Minimum Curvilinear embedding (MCE) for DR, and Minimum Curvilinear affinity propagation (MCAP) for clustering. Compared with several other unsupervised and supervised algorithms, MCE and MCAP, whether individually or combined in H2P, overcome the limits of classical approaches. High performance was attained in the visualization and classification of: (i) pain patients (proteomic measurements) in peripheral neuropathy; (ii) human organ tissues (genomic transcription factor measurements) on the basis of their embryological origin. MC provides a valuable framework to estimate nonlinear distances in small datasets. Its extension to large datasets is prefigured for novel NMLs. Classification of neuropathic pain by proteomic profiles offers new insights for future molecular and systems biology characterization of pain. Improvements in tissue embryological classification refine results obtained in an earlier study, and suggest a possible reinterpretation of skin attribution as mesodermal. https://sites.google.com/site/carlovittoriocannistraci/home.
Unsupervised Detection of Planetary Craters by a Marked Point Process

NASA Technical Reports Server (NTRS)

Troglio, G.; Benediktsson, J. A.; Le Moigne, J.; Moser, G.; Serpico, S. B.

2011-01-01

With the launch of several planetary missions in the last decade, a large amount of planetary images is being acquired. Preferably, automatic and robust processing techniques need to be used for data analysis because of the huge amount of the acquired data. Here, the aim is to achieve a robust and general methodology for crater detection. A novel technique based on a marked point process is proposed. First, the contours in the image are extracted. The object boundaries are modeled as a configuration of an unknown number of random ellipses, i.e., the contour image is considered as a realization of a marked point process. Then, an energy function is defined, containing both an a priori energy and a likelihood term. The global minimum of this function is estimated by using reversible jump Monte-Carlo Markov chain dynamics and a simulated annealing scheme. The main idea behind marked point processes is to model objects within a stochastic framework: Marked point processes represent a very promising current approach in the stochastic image modeling and provide a powerful and methodologically rigorous framework to efficiently map and detect objects and structures in an image with an excellent robustness to noise. The proposed method for crater detection has several feasible applications. One such application area is image registration by matching the extracted features.
Semi-automatic ground truth generation using unsupervised clustering and limited manual labeling: Application to handwritten character recognition

PubMed Central

Vajda, Szilárd; Rangoni, Yves; Cecotti, Hubert

2015-01-01

For training supervised classifiers to recognize different patterns, large data collections with accurate labels are necessary. In this paper, we propose a generic, semi-automatic labeling technique for large handwritten character collections. In order to speed up the creation of a large scale ground truth, the method combines unsupervised clustering and minimal expert knowledge. To exploit the potential discriminant complementarities across features, each character is projected into five different feature spaces. After clustering the images in each feature space, the human expert labels the cluster centers. Each data point inherits the label of its cluster’s center. A majority (or unanimity) vote decides the label of each character image. The amount of human involvement (labeling) is strictly controlled by the number of clusters – produced by the chosen clustering approach. To test the efficiency of the proposed approach, we have compared, and evaluated three state-of-the art clustering methods (k-means, self-organizing maps, and growing neural gas) on the MNIST digit data set, and a Lampung Indonesian character data set, respectively. Considering a k-nn classifier, we show that labeling manually only 1.3% (MNIST), and 3.2% (Lampung) of the training data, provides the same range of performance than a completely labeled data set would. PMID:25870463
National-scale cropland mapping based on spectral-temporal features and outdated land cover information.

PubMed

Waldner, François; Hansen, Matthew C; Potapov, Peter V; Löw, Fabian; Newby, Terence; Ferreira, Stefanus; Defourny, Pierre

2017-01-01

The lack of sufficient ground truth data has always constrained supervised learning, thereby hindering the generation of up-to-date satellite-derived thematic maps. This is all the more true for those applications requiring frequent updates over large areas such as cropland mapping. Therefore, we present a method enabling the automated production of spatially consistent cropland maps at the national scale, based on spectral-temporal features and outdated land cover information. Following an unsupervised approach, this method extracts reliable calibration pixels based on their labels in the outdated map and their spectral signatures. To ensure spatial consistency and coherence in the map, we first propose to generate seamless input images by normalizing the time series and deriving spectral-temporal features that target salient cropland characteristics. Second, we reduce the spatial variability of the class signatures by stratifying the country and by classifying each stratum independently. Finally, we remove speckle with a weighted majority filter accounting for per-pixel classification confidence. Capitalizing on a wall-to-wall validation data set, the method was tested in South Africa using a 16-year old land cover map and multi-sensor Landsat time series. The overall accuracy of the resulting cropland map reached 92%. A spatially explicit validation revealed large variations across the country and suggests that intensive grain-growing areas were better characterized than smallholder farming systems. Informative features in the classification process vary from one stratum to another but features targeting the minimum of vegetation as well as short-wave infrared features were consistently important throughout the country. Overall, the approach showed potential for routinely delivering consistent cropland maps over large areas as required for operational crop monitoring.
Multi-channel EEG-based sleep stage classification with joint collaborative representation and multiple kernel learning.

PubMed

Shi, Jun; Liu, Xiao; Li, Yan; Zhang, Qi; Li, Yingjie; Ying, Shihui

2015-10-30

Electroencephalography (EEG) based sleep staging is commonly used in clinical routine. Feature extraction and representation plays a crucial role in EEG-based automatic classification of sleep stages. Sparse representation (SR) is a state-of-the-art unsupervised feature learning method suitable for EEG feature representation. Collaborative representation (CR) is an effective data coding method used as a classifier. Here we use CR as a data representation method to learn features from the EEG signal. A joint collaboration model is established to develop a multi-view learning algorithm, and generate joint CR (JCR) codes to fuse and represent multi-channel EEG signals. A two-stage multi-view learning-based sleep staging framework is then constructed, in which JCR and joint sparse representation (JSR) algorithms first fuse and learning the feature representation from multi-channel EEG signals, respectively. Multi-view JCR and JSR features are then integrated and sleep stages recognized by a multiple kernel extreme learning machine (MK-ELM) algorithm with grid search. The proposed two-stage multi-view learning algorithm achieves superior performance for sleep staging. With a K-means clustering based dictionary, the mean classification accuracy, sensitivity and specificity are 81.10 ± 0.15%, 71.42 ± 0.66% and 94.57 ± 0.07%, respectively; while with the dictionary learned using the submodular optimization method, they are 80.29 ± 0.22%, 71.26 ± 0.78% and 94.38 ± 0.10%, respectively. The two-stage multi-view learning based sleep staging framework outperforms all other classification methods compared in this work, while JCR is superior to JSR. The proposed multi-view learning framework has the potential for sleep staging based on multi-channel or multi-modality polysomnography signals. Copyright © 2015 Elsevier B.V. All rights reserved.
National-scale cropland mapping based on spectral-temporal features and outdated land cover information

PubMed Central

Hansen, Matthew C.; Potapov, Peter V.; Löw, Fabian; Newby, Terence; Ferreira, Stefanus; Defourny, Pierre

2017-01-01

The lack of sufficient ground truth data has always constrained supervised learning, thereby hindering the generation of up-to-date satellite-derived thematic maps. This is all the more true for those applications requiring frequent updates over large areas such as cropland mapping. Therefore, we present a method enabling the automated production of spatially consistent cropland maps at the national scale, based on spectral-temporal features and outdated land cover information. Following an unsupervised approach, this method extracts reliable calibration pixels based on their labels in the outdated map and their spectral signatures. To ensure spatial consistency and coherence in the map, we first propose to generate seamless input images by normalizing the time series and deriving spectral-temporal features that target salient cropland characteristics. Second, we reduce the spatial variability of the class signatures by stratifying the country and by classifying each stratum independently. Finally, we remove speckle with a weighted majority filter accounting for per-pixel classification confidence. Capitalizing on a wall-to-wall validation data set, the method was tested in South Africa using a 16-year old land cover map and multi-sensor Landsat time series. The overall accuracy of the resulting cropland map reached 92%. A spatially explicit validation revealed large variations across the country and suggests that intensive grain-growing areas were better characterized than smallholder farming systems. Informative features in the classification process vary from one stratum to another but features targeting the minimum of vegetation as well as short-wave infrared features were consistently important throughout the country. Overall, the approach showed potential for routinely delivering consistent cropland maps over large areas as required for operational crop monitoring. PMID:28817618
Review assessment support in Open Journal System using TextRank

NASA Astrophysics Data System (ADS)

Manalu, S. R.; Willy; Sundjaja, A. M.; Noerlina

2017-01-01

In this paper, a review assessment support in Open Journal System (OJS) using TextRank is proposed. OJS is an open-source journal management platform that provides a streamlined journal publishing workflow. TextRank is an unsupervised, graph-based ranking model commonly used as extractive auto summarization of text documents. This study applies the TextRank algorithm to summarize 50 article reviews from an OJS-based international journal. The resulting summaries are formed using the most representative sentences extracted from the reviews. The summaries are then used to help OJS editors in assessing a review’s quality.
Computational efficient unsupervised coastline detection from single-polarization 1-look SAR images of complex coastal environments

NASA Astrophysics Data System (ADS)

Garzelli, Andrea; Zoppetti, Claudia; Pinelli, Gianpaolo

2017-10-01

Coastline detection in synthetic aperture radar (SAR) images is crucial in many application fields, from coastal erosion monitoring to navigation, from damage assessment to security planning for port facilities. The backscattering difference between land and sea is not always documented in SAR imagery, due to the severe speckle noise, especially in 1-look data with high spatial resolution, high sea state, or complex coastal environments. This paper presents an unsupervised, computationally efficient solution to extract the coastline acquired by only one single-polarization 1-look SAR image. Extensive tests on Spotlight COSMO-SkyMed images of complex coastal environments and objective assessment demonstrate the validity of the proposed procedure which is compared to state-of-the-art methods through visual results and with an objective evaluation of the distance between the detected and the true coastline provided by regional authorities.
Photoacoustic spectroscopy based investigatory approach to discriminate breast cancer from normal: a pilot study

NASA Astrophysics Data System (ADS)

Priya, Mallika; Rao, Bola Sadashiva Satish; Chandra, Subhash; Ray, Satadru; Mathew, Stanley; Datta, Anirbit; Nayak, Subramanya G.; Mahato, Krishna Kishore

2016-02-01

In spite of many efforts for early detection of breast cancer, there is still lack of technology for immediate implementation. In the present study, the potential photoacoustic spectroscopy was evaluated in discriminating breast cancer from normal, involving blood serum samples seeking early detection. Three photoacoustic spectra in time domain were recorded from each of 20 normal and 20 malignant samples at 281nm pulsed laser excitations and a total of 120 spectra were generated. The time domain spectra were then Fast Fourier Transformed into frequency domain and 116.5625 - 206.875 kHz region was selected for further analysis using a combinational approach of wavelet, PCA and logistic regression. Initially, wavelet analysis was performed on the FFT data and seven features (mean, median, area under the curve, variance, standard deviation, skewness and kurtosis) from each were extracted. PCA was then performed on the feature matrix (7x120) for discriminating malignant samples from the normal by plotting a decision boundary using logistic regression analysis. The unsupervised mode of classification used in the present study yielded specificity and sensitivity values of 100% in each respectively with a ROC - AUC value of 1. The results obtained have clearly demonstrated the capability of photoacoustic spectroscopy in discriminating cancer from the normal, suggesting its possible clinical implications.

Landslide Detection in the Carlyon Beach, WA Peninsula: Analysis Of High Resolution DEMs

NASA Astrophysics Data System (ADS)

Fayne, J.; Tran, C.; Mora, O. E.

2017-12-01

Landslides are geological events caused by slope instability and degradation, leading to the sliding of large masses of rock and soil down a mountain or hillside. These events are influenced by topography, geology, weather and human activity, and can cause extensive damage to the environment and infrastructure, such as the destruction of transportation networks, homes, and businesses. It is therefore imperative to detect early-warning signs of landslide hazards as a means of mitigation and disaster prevention. Traditional landslide surveillance consists of field mapping, but the process is expensive and time consuming. This study uses Light Detection and Ranging (LiDAR) derived Digital Elevation Models (DEMs) and k-means clustering and Gaussian Mixture Model (GMM) to analyze surface roughness and extract spatial features and patterns of landslides and landslide-prone areas. The methodology based on several feature extractors employs an unsupervised classifier on the Carlyon Beach Peninsula in the state of Washington to attempt to identify slide potential terrain. When compared with the independently compiled landslide inventory map, the proposed algorithm correctly classifies up to 87% of the terrain. These results suggest that the proposed methods and LiDAR-derived DEMs can provide important surface information and be used as efficient tools for digital terrain analysis to create accurate landslide maps.
Hierarchical clustering of EMD based interest points for road sign detection

NASA Astrophysics Data System (ADS)

Khan, Jesmin; Bhuiyan, Sharif; Adhami, Reza

2014-04-01

This paper presents an automatic road traffic signs detection and recognition system based on hierarchical clustering of interest points and joint transform correlation. The proposed algorithm consists of the three following stages: interest points detection, clustering of those points and similarity search. At the first stage, good discriminative, rotation and scale invariant interest points are selected from the image edges based on the 1-D empirical mode decomposition (EMD). We propose a two-step unsupervised clustering technique, which is adaptive and based on two criterion. In this context, the detected points are initially clustered based on the stable local features related to the brightness and color, which are extracted using Gabor filter. Then points belonging to each partition are reclustered depending on the dispersion of the points in the initial cluster using position feature. This two-step hierarchical clustering yields the possible candidate road signs or the region of interests (ROIs). Finally, a fringe-adjusted joint transform correlation (JTC) technique is used for matching the unknown signs with the existing known reference road signs stored in the database. The presented framework provides a novel way to detect a road sign from the natural scenes and the results demonstrate the efficacy of the proposed technique, which yields a very low false hit rate.
Efficient coding of spectrotemporal binaural sounds leads to emergence of the auditory space representation

PubMed Central

Młynarski, Wiktor

2014-01-01

To date a number of studies have shown that receptive field shapes of early sensory neurons can be reproduced by optimizing coding efficiency of natural stimulus ensembles. A still unresolved question is whether the efficient coding hypothesis explains formation of neurons which explicitly represent environmental features of different functional importance. This paper proposes that the spatial selectivity of higher auditory neurons emerges as a direct consequence of learning efficient codes for natural binaural sounds. Firstly, it is demonstrated that a linear efficient coding transform—Independent Component Analysis (ICA) trained on spectrograms of naturalistic simulated binaural sounds extracts spatial information present in the signal. A simple hierarchical ICA extension allowing for decoding of sound position is proposed. Furthermore, it is shown that units revealing spatial selectivity can be learned from a binaural recording of a natural auditory scene. In both cases a relatively small subpopulation of learned spectrogram features suffices to perform accurate sound localization. Representation of the auditory space is therefore learned in a purely unsupervised way by maximizing the coding efficiency and without any task-specific constraints. This results imply that efficient coding is a useful strategy for learning structures which allow for making behaviorally vital inferences about the environment. PMID:24639644
Class imbalance in unsupervised change detection - A diagnostic analysis from urban remote sensing

NASA Astrophysics Data System (ADS)

Leichtle, Tobias; Geiß, Christian; Lakes, Tobia; Taubenböck, Hannes

2017-08-01

Automatic monitoring of changes on the Earth's surface is an intrinsic capability and simultaneously a persistent methodological challenge in remote sensing, especially regarding imagery with very-high spatial resolution (VHR) and complex urban environments. In order to enable a high level of automatization, the change detection problem is solved in an unsupervised way to alleviate efforts associated with collection of properly encoded prior knowledge. In this context, this paper systematically investigates the nature and effects of class distribution and class imbalance in an unsupervised binary change detection application based on VHR imagery over urban areas. For this purpose, a diagnostic framework for sensitivity analysis of a large range of possible degrees of class imbalance is presented, which is of particular importance with respect to unsupervised approaches where the content of images and thus the occurrence and the distribution of classes are generally unknown a priori. Furthermore, this framework can serve as a general technique to evaluate model transferability in any two-class classification problem. The applied change detection approach is based on object-based difference features calculated from VHR imagery and subsequent unsupervised two-class clustering using k-means, genetic k-means and self-organizing map (SOM) clustering. The results from two test sites with different structural characteristics of the built environment demonstrated that classification performance is generally worse in imbalanced class distribution settings while best results were reached in balanced or close to balanced situations. Regarding suitable accuracy measures for evaluating model performance in imbalanced settings, this study revealed that the Kappa statistics show significant response to class distribution while the true skill statistic was widely insensitive to imbalanced classes. In general, the genetic k-means clustering algorithm achieved the most robust results with respect to class imbalance while the SOM clustering exhibited a distinct optimization towards a balanced distribution of classes.
Word sense disambiguation in the clinical domain: a comparison of knowledge-rich and knowledge-poor unsupervised methods

PubMed Central

Chasin, Rachel; Rumshisky, Anna; Uzuner, Ozlem; Szolovits, Peter

2014-01-01

Objective To evaluate state-of-the-art unsupervised methods on the word sense disambiguation (WSD) task in the clinical domain. In particular, to compare graph-based approaches relying on a clinical knowledge base with bottom-up topic-modeling-based approaches. We investigate several enhancements to the topic-modeling techniques that use domain-specific knowledge sources. Materials and methods The graph-based methods use variations of PageRank and distance-based similarity metrics, operating over the Unified Medical Language System (UMLS). Topic-modeling methods use unlabeled data from the Multiparameter Intelligent Monitoring in Intensive Care (MIMIC II) database to derive models for each ambiguous word. We investigate the impact of using different linguistic features for topic models, including UMLS-based and syntactic features. We use a sense-tagged clinical dataset from the Mayo Clinic for evaluation. Results The topic-modeling methods achieve 66.9% accuracy on a subset of the Mayo Clinic's data, while the graph-based methods only reach the 40–50% range, with a most-frequent-sense baseline of 56.5%. Features derived from the UMLS semantic type and concept hierarchies do not produce a gain over bag-of-words features in the topic models, but identifying phrases from UMLS and using syntax does help. Discussion Although topic models outperform graph-based methods, semantic features derived from the UMLS prove too noisy to improve performance beyond bag-of-words. Conclusions Topic modeling for WSD provides superior results in the clinical domain; however, integration of knowledge remains to be effectively exploited. PMID:24441986
Extracting aerobic system dynamics during unsupervised activities of daily living using wearable sensor machine learning models.

PubMed

Beltrame, Thomas; Amelard, Robert; Wong, Alexander; Hughson, Richard L

2018-02-01

Physical activity levels are related through algorithms to the energetic demand, with no information regarding the integrity of the multiple physiological systems involved in the energetic supply. Longitudinal analysis of the oxygen uptake (V̇o 2 ) by wearable sensors in realistic settings might permit development of a practical tool for the study of the longitudinal aerobic system dynamics (i.e., V̇o 2 kinetics). This study evaluated aerobic system dynamics based on predicted V̇o 2 data obtained from wearable sensors during unsupervised activities of daily living (μADL). Thirteen healthy men performed a laboratory-controlled moderate exercise protocol and were monitored for ≈6 h/day for 4 days (μADL data). Variables derived from hip accelerometer (ACC HIP ), heart rate monitor, and respiratory bands during μADL were extracted and processed by a validated random forest regression model to predict V̇o 2 . The aerobic system analysis was based on the frequency-domain analysis of ACC HIP and predicted V̇o 2 data obtained during μADL. Optimal samples for frequency domain analysis (constrained to ≤0.01 Hz) were selected when ACC HIP was higher than 0.05 g at a given frequency (i.e., participants were active). The temporal characteristics of predicted V̇o 2 data during μADL correlated with the temporal characteristics of measured V̇o 2 data during laboratory-controlled protocol ([Formula: see text] = 0.82, P < 0.001, n = 13). In conclusion, aerobic system dynamics can be investigated during unsupervised activities of daily living by wearable sensors. Although speculative, these algorithms have the potential to be incorporated into wearable systems for early detection of changes in health status in realistic environments by detecting changes in aerobic response dynamics. NEW & NOTEWORTHY The early detection of subclinical aerobic system impairments might be indicative of impaired physiological reserves that impact the capacity for physical activity. This study is the first to use wearable sensors in unsupervised activities of daily living in combination with novel machine learning algorithms to investigate the aerobic system dynamics with the potential to contribute to models of functional health status and guide future individualized health care in the normal population.
TU-AB-BRA-10: Prognostic Value of Intra-Radiation Treatment FDG-PET and CT Imaging Features in Locally Advanced Head and Neck Cancer

DOE Office of Scientific and Technical Information (OSTI.GOV)

Song, J; Pollom, E; Durkee, B

2015-06-15

Purpose: To predict response to radiation treatment using computational FDG-PET and CT images in locally advanced head and neck cancer (HNC). Methods: 68 patients with State III-IVB HNC treated with chemoradiation were included in this retrospective study. For each patient, we analyzed primary tumor and lymph nodes on PET and CT scans acquired both prior to and during radiation treatment, which led to 8 combinations of image datasets. From each image set, we extracted high-throughput, radiomic features of the following types: statistical, morphological, textural, histogram, and wavelet, resulting in a total of 437 features. We then performed unsupervised redundancy removalmore » and stability test on these features. To avoid over-fitting, we trained a logistic regression model with simultaneous feature selection based on least absolute shrinkage and selection operator (LASSO). To objectively evaluate the prediction ability, we performed 5-fold cross validation (CV) with 50 random repeats of stratified bootstrapping. Feature selection and model training was solely conducted on the training set and independently validated on the holdout test set. Receiver operating characteristic (ROC) curve of the pooled Result and the area under the ROC curve (AUC) was calculated as figure of merit. Results: For predicting local-regional recurrence, our model built on pre-treatment PET of lymph nodes achieved the best performance (AUC=0.762) on 5-fold CV, which compared favorably with node volume and SUVmax (AUC=0.704 and 0.449, p<0.001). Wavelet coefficients turned out to be the most predictive features. Prediction of distant recurrence showed a similar trend, in which pre-treatment PET features of lymph nodes had the highest AUC of 0.705. Conclusion: The radiomics approach identified novel imaging features that are predictive to radiation treatment response. If prospectively validated in larger cohorts, they could aid in risk-adaptive treatment of HNC.« less
Biologically Inspired Model for Visual Cognition Achieving Unsupervised Episodic and Semantic Feature Learning.

PubMed

Qiao, Hong; Li, Yinlin; Li, Fengfu; Xi, Xuanyang; Wu, Wei

2016-10-01

Recently, many biologically inspired visual computational models have been proposed. The design of these models follows the related biological mechanisms and structures, and these models provide new solutions for visual recognition tasks. In this paper, based on the recent biological evidence, we propose a framework to mimic the active and dynamic learning and recognition process of the primate visual cortex. From principle point of view, the main contributions are that the framework can achieve unsupervised learning of episodic features (including key components and their spatial relations) and semantic features (semantic descriptions of the key components), which support higher level cognition of an object. From performance point of view, the advantages of the framework are as follows: 1) learning episodic features without supervision-for a class of objects without a prior knowledge, the key components, their spatial relations and cover regions can be learned automatically through a deep neural network (DNN); 2) learning semantic features based on episodic features-within the cover regions of the key components, the semantic geometrical values of these components can be computed based on contour detection; 3) forming the general knowledge of a class of objects-the general knowledge of a class of objects can be formed, mainly including the key components, their spatial relations and average semantic values, which is a concise description of the class; and 4) achieving higher level cognition and dynamic updating-for a test image, the model can achieve classification and subclass semantic descriptions. And the test samples with high confidence are selected to dynamically update the whole model. Experiments are conducted on face images, and a good performance is achieved in each layer of the DNN and the semantic description learning process. Furthermore, the model can be generalized to recognition tasks of other objects with learning ability.
On Quantitative Biomarkers of VNS Therapy Using EEG and ECG Signals.

PubMed

Ravan, Maryam; Sabesan, Shivkumar; D'Cruz, O'Neill

2017-02-01

The goal of this work is to objectively evaluate the effectiveness of neuromodulation therapies, specifically, Vagus nerve stimulation (VNS) in reducing the severity of seizures in patients with medically refractory epilepsy. Using novel quantitative features obtained from combination of electroencephalographic (EEG) and electrocardiographic (ECG) signals around seizure events in 16 patients who underwent implantation of closed-loop VNS therapy system, namely AspireSR, we evaluated if automated delivery of VNS at the time of seizure onset reduces the severity of seizures by reducing EEG spatial synchronization as well as the duration and magnitude of heart rate increase. Unsupervised classification was subsequently applied to test the discriminative ability and validity of these features to measure responsiveness to VNS therapy. Results of application of this methodology to compare 105 pre-VNS treatment and 107 post-VNS treatment seizures revealed that seizures that were acutely stimulated using VNS had a reduced ictal spread as well as reduced impact on cardiovascular function compared to the ones that occurred prior to any treatment. Furthermore, application of an unsupervised fuzzy-c-mean classifier to evaluate the ability of the combined EEG-ECG based features to classify pre and post-treatment seizures achieved a classification accuracy of 85.85%. These results indicate the importance of timely delivery of VNS to reduce seizure severity and thus help achieve better seizure control for patients with epilepsy. The proposed set of quantitative features could be used as potential biomarkers for predicting long-term response to VNS therapy.
Land cover classification in multispectral imagery using clustering of sparse approximations over learned feature dictionaries

DOE PAGES

Moody, Daniela I.; Brumby, Steven P.; Rowland, Joel C.; ...

2014-12-09

We present results from an ongoing effort to extend neuromimetic machine vision algorithms to multispectral data using adaptive signal processing combined with compressive sensing and machine learning techniques. Our goal is to develop a robust classification methodology that will allow for automated discretization of the landscape into distinct units based on attributes such as vegetation, surface hydrological properties, and topographic/geomorphic characteristics. We use a Hebbian learning rule to build spectral-textural dictionaries that are tailored for classification. We learn our dictionaries from millions of overlapping multispectral image patches and then use a pursuit search to generate classification features. Land cover labelsmore » are automatically generated using unsupervised clustering of sparse approximations (CoSA). We demonstrate our method on multispectral WorldView-2 data from a coastal plain ecosystem in Barrow, Alaska. We explore learning from both raw multispectral imagery and normalized band difference indices. We explore a quantitative metric to evaluate the spectral properties of the clusters in order to potentially aid in assigning land cover categories to the cluster labels. In this study, our results suggest CoSA is a promising approach to unsupervised land cover classification in high-resolution satellite imagery.« less
Unsupervised Learning of Overlapping Image Components Using Divisive Input Modulation

PubMed Central

Spratling, M. W.; De Meyer, K.; Kompass, R.

2009-01-01

This paper demonstrates that nonnegative matrix factorisation is mathematically related to a class of neural networks that employ negative feedback as a mechanism of competition. This observation inspires a novel learning algorithm which we call Divisive Input Modulation (DIM). The proposed algorithm provides a mathematically simple and computationally efficient method for the unsupervised learning of image components, even in conditions where these elementary features overlap considerably. To test the proposed algorithm, a novel artificial task is introduced which is similar to the frequently-used bars problem but employs squares rather than bars to increase the degree of overlap between components. Using this task, we investigate how the proposed method performs on the parsing of artificial images composed of overlapping features, given the correct representation of the individual components; and secondly, we investigate how well it can learn the elementary components from artificial training images. We compare the performance of the proposed algorithm with its predecessors including variations on these algorithms that have produced state-of-the-art performance on the bars problem. The proposed algorithm is more successful than its predecessors in dealing with overlap and occlusion in the artificial task that has been used to assess performance. PMID:19424442
Classification of damage in structural systems using time series analysis and supervised and unsupervised pattern recognition techniques

NASA Astrophysics Data System (ADS)

Omenzetter, Piotr; de Lautour, Oliver R.

2010-04-01

Developed for studying long, periodic records of various measured quantities, time series analysis methods are inherently suited and offer interesting possibilities for Structural Health Monitoring (SHM) applications. However, their use in SHM can still be regarded as an emerging application and deserves more studies. In this research, Autoregressive (AR) models were used to fit experimental acceleration time histories from two experimental structural systems, a 3- storey bookshelf-type laboratory structure and the ASCE Phase II SHM Benchmark Structure, in healthy and several damaged states. The coefficients of the AR models were chosen as damage sensitive features. Preliminary visual inspection of the large, multidimensional sets of AR coefficients to check the presence of clusters corresponding to different damage severities was achieved using Sammon mapping - an efficient nonlinear data compression technique. Systematic classification of damage into states based on the analysis of the AR coefficients was achieved using two supervised classification techniques: Nearest Neighbor Classification (NNC) and Learning Vector Quantization (LVQ), and one unsupervised technique: Self-organizing Maps (SOM). This paper discusses the performance of AR coefficients as damage sensitive features and compares the efficiency of the three classification techniques using experimental data.
A recurrent neural network for classification of unevenly sampled variable stars

NASA Astrophysics Data System (ADS)

Naul, Brett; Bloom, Joshua S.; Pérez, Fernando; van der Walt, Stéfan

2018-02-01

Astronomical surveys of celestial sources produce streams of noisy time series measuring flux versus time (`light curves'). Unlike in many other physical domains, however, large (and source-specific) temporal gaps in data arise naturally due to intranight cadence choices as well as diurnal and seasonal constraints1-5. With nightly observations of millions of variable stars and transients from upcoming surveys4,6, efficient and accurate discovery and classification techniques on noisy, irregularly sampled data must be employed with minimal human-in-the-loop involvement. Machine learning for inference tasks on such data traditionally requires the laborious hand-coding of domain-specific numerical summaries of raw data (`features')7. Here, we present a novel unsupervised autoencoding recurrent neural network8 that makes explicit use of sampling times and known heteroskedastic noise properties. When trained on optical variable star catalogues, this network produces supervised classification models that rival other best-in-class approaches. We find that autoencoded features learned in one time-domain survey perform nearly as well when applied to another survey. These networks can continue to learn from new unlabelled observations and may be used in other unsupervised tasks, such as forecasting and anomaly detection.
Unsupervised machine-learning method for improving the performance of ambulatory fall-detection systems

PubMed Central

2012-01-01

Background Falls can cause trauma, disability and death among older people. Ambulatory accelerometer devices are currently capable of detecting falls in a controlled environment. However, research suggests that most current approaches can tend to have insufficient sensitivity and specificity in non-laboratory environments, in part because impacts can be experienced as part of ordinary daily living activities. Method We used a waist-worn wireless tri-axial accelerometer combined with digital signal processing, clustering and neural network classifiers. The method includes the application of Discrete Wavelet Transform, Regrouping Particle Swarm Optimization, Gaussian Distribution of Clustered Knowledge and an ensemble of classifiers including a multilayer perceptron and Augmented Radial Basis Function (ARBF) neural networks. Results Preliminary testing with 8 healthy individuals in a home environment yields 98.6% sensitivity to falls and 99.6% specificity for routine Activities of Daily Living (ADL) data. Single ARB and MLP classifiers were compared with a combined classifier. The combined classifier offers the greatest sensitivity, with a slight reduction in specificity for routine ADL and an increased specificity for exercise activities. In preliminary tests, the approach achieves 100% sensitivity on in-group falls, 97.65% on out-group falls, 99.33% specificity on routine ADL, and 96.59% specificity on exercise ADL. Conclusion The pre-processing and feature-extraction steps appear to simplify the signal while successfully extracting the essential features that are required to characterize a fall. The results suggest this combination of classifiers can perform better than MLP alone. Preliminary testing suggests these methods may be useful for researchers who are attempting to improve the performance of ambulatory fall-detection systems. PMID:22336100
An artificial intelligence approach fit for tRNA gene studies in the era of big sequence data.

PubMed

Iwasaki, Yuki; Abe, Takashi; Wada, Kennosuke; Wada, Yoshiko; Ikemura, Toshimichi

2017-09-12

Unsupervised data mining capable of extracting a wide range of knowledge from big data without prior knowledge or particular models is a timely application in the era of big sequence data accumulation in genome research. By handling oligonucleotide compositions as high-dimensional data, we have previously modified the conventional self-organizing map (SOM) for genome informatics and established BLSOM, which can analyze more than ten million sequences simultaneously. Here, we develop BLSOM specialized for tRNA genes (tDNAs) that can cluster (self-organize) more than one million microbial tDNAs according to their cognate amino acid solely depending on tetra- and pentanucleotide compositions. This unsupervised clustering can reveal combinatorial oligonucleotide motifs that are responsible for the amino acid-dependent clustering, as well as other functionally and structurally important consensus motifs, which have been evolutionarily conserved. BLSOM is also useful for identifying tDNAs as phylogenetic markers for special phylotypes. When we constructed BLSOM with 'species-unknown' tDNAs from metagenomic sequences plus 'species-known' microbial tDNAs, a large portion of metagenomic tDNAs self-organized with species-known tDNAs, yielding information on microbial communities in environmental samples. BLSOM can also enhance accuracy in the tDNA database obtained from big sequence data. This unsupervised data mining should become important for studying numerous functionally unclear RNAs obtained from a wide range of organisms.
Liberal Entity Extraction: Rapid Construction of Fine-Grained Entity Typing Systems.

PubMed

Huang, Lifu; May, Jonathan; Pan, Xiaoman; Ji, Heng; Ren, Xiang; Han, Jiawei; Zhao, Lin; Hendler, James A

2017-03-01

The ability of automatically recognizing and typing entities in natural language without prior knowledge (e.g., predefined entity types) is a major challenge in processing such data. Most existing entity typing systems are limited to certain domains, genres, and languages. In this article, we propose a novel unsupervised entity-typing framework by combining symbolic and distributional semantics. We start from learning three types of representations for each entity mention: general semantic representation, specific context representation, and knowledge representation based on knowledge bases. Then we develop a novel joint hierarchical clustering and linking algorithm to type all mentions using these representations. This framework does not rely on any annotated data, predefined typing schema, or handcrafted features; therefore, it can be quickly adapted to a new domain, genre, and/or language. Experiments on genres (news and discussion forum) show comparable performance with state-of-the-art supervised typing systems trained from a large amount of labeled data. Results on various languages (English, Chinese, Japanese, Hausa, and Yoruba) and domains (general and biomedical) demonstrate the portability of our framework.
Learning about individuals' health from aggregate data.

PubMed

Colbaugh, Rich; Glass, Kristin

2017-07-01

There is growing awareness that user-generated social media content contains valuable health-related information and is more convenient to collect than typical health data. For example, Twitter has been employed to predict aggregate-level outcomes, such as regional rates of diabetes and child poverty, and to identify individual cases of depression and food poisoning. Models which make aggregate-level inferences can be induced from aggregate data, and consequently are straightforward to build. In contrast, learning models that produce individual-level (IL) predictions, which are more informative, usually requires a large number of difficult-to-acquire labeled IL examples. This paper presents a new machine learning method which achieves the best of both worlds, enabling IL models to be learned from aggregate labels. The algorithm makes predictions by combining unsupervised feature extraction, aggregate-based modeling, and optimal integration of aggregate-level and IL information. Two case studies illustrate how to learn health-relevant IL prediction models using only aggregate labels, and show that these models perform as well as state-of-the-art models trained on hundreds or thousands of labeled individuals.
Liberal Entity Extraction: Rapid Construction of Fine-Grained Entity Typing Systems

PubMed Central

Huang, Lifu; May, Jonathan; Pan, Xiaoman; Ji, Heng; Ren, Xiang; Han, Jiawei; Zhao, Lin; Hendler, James A.

2017-01-01

Abstract The ability of automatically recognizing and typing entities in natural language without prior knowledge (e.g., predefined entity types) is a major challenge in processing such data. Most existing entity typing systems are limited to certain domains, genres, and languages. In this article, we propose a novel unsupervised entity-typing framework by combining symbolic and distributional semantics. We start from learning three types of representations for each entity mention: general semantic representation, specific context representation, and knowledge representation based on knowledge bases. Then we develop a novel joint hierarchical clustering and linking algorithm to type all mentions using these representations. This framework does not rely on any annotated data, predefined typing schema, or handcrafted features; therefore, it can be quickly adapted to a new domain, genre, and/or language. Experiments on genres (news and discussion forum) show comparable performance with state-of-the-art supervised typing systems trained from a large amount of labeled data. Results on various languages (English, Chinese, Japanese, Hausa, and Yoruba) and domains (general and biomedical) demonstrate the portability of our framework. PMID:28328252
ShiftNMFk 1.2

DOE Office of Scientific and Technical Information (OSTI.GOV)

Alexandrov, Boian S.; Vesselinov, Velimir V.; Stanev, Valentin

The ShiftNMFk1.2 code, or as we call it, GreenNMFk, represents a hybrid algorithm combining unsupervised adaptive machine learning and Green's function inverse method. GreenNMFk allows an efficient and high performance de-mixing and feature extraction of a multitude of nonnegative signals that change their shape propagating through the medium. The signals are mixed and recorded by a network of uncorrelated sensors. The code couples Non-negative Matrix Factorization (NMF) and inverse-analysis Green's functions method. GreenNMF synergistically performs decomposition of the recorded mixtures, finds the number of the unknown sources and uses the Green's function of the governing partial differential equation to identifymore » the unknown sources and their charecteristics. GreenNMF can be applied directly to any problem controlled by a known partial-differential parabolic equation where mixtures of an unknown number of sources are measured at multiple locations. Full GreenNMFk method is a subject LANL U.S. Patent application S133364.000 August, 2017. The ShiftNMFk 1.2 version here is a toy version of this method that can work with a limited number of unknown sources (4 or less).« less
Big Data Analytics for Scanning Transmission Electron Microscopy Ptychography

NASA Astrophysics Data System (ADS)

Jesse, S.; Chi, M.; Belianinov, A.; Beekman, C.; Kalinin, S. V.; Borisevich, A. Y.; Lupini, A. R.

2016-05-01

Electron microscopy is undergoing a transition; from the model of producing only a few micrographs, through the current state where many images and spectra can be digitally recorded, to a new mode where very large volumes of data (movies, ptychographic and multi-dimensional series) can be rapidly obtained. Here, we discuss the application of so-called “big-data” methods to high dimensional microscopy data, using unsupervised multivariate statistical techniques, in order to explore salient image features in a specific example of BiFeO3 domains. Remarkably, k-means clustering reveals domain differentiation despite the fact that the algorithm is purely statistical in nature and does not require any prior information regarding the material, any coexisting phases, or any differentiating structures. While this is a somewhat trivial case, this example signifies the extraction of useful physical and structural information without any prior bias regarding the sample or the instrumental modality. Further interpretation of these types of results may still require human intervention. However, the open nature of this algorithm and its wide availability, enable broad collaborations and exploratory work necessary to enable efficient data analysis in electron microscopy.

Generalized Self-Organizing Maps for Automatic Determination of the Number of Clusters and Their Multiprototypes in Cluster Analysis.

PubMed

Gorzalczany, Marian B; Rudzinski, Filip

2017-06-07

This paper presents a generalization of self-organizing maps with 1-D neighborhoods (neuron chains) that can be effectively applied to complex cluster analysis problems. The essence of the generalization consists in introducing mechanisms that allow the neuron chain--during learning--to disconnect into subchains, to reconnect some of the subchains again, and to dynamically regulate the overall number of neurons in the system. These features enable the network--working in a fully unsupervised way (i.e., using unlabeled data without a predefined number of clusters)--to automatically generate collections of multiprototypes that are able to represent a broad range of clusters in data sets. First, the operation of the proposed approach is illustrated on some synthetic data sets. Then, this technique is tested using several real-life, complex, and multidimensional benchmark data sets available from the University of California at Irvine (UCI) Machine Learning repository and the Knowledge Extraction based on Evolutionary Learning data set repository. A sensitivity analysis of our approach to changes in control parameters and a comparative analysis with an alternative approach are also performed.
A neuromorphic approach to satellite image understanding

NASA Astrophysics Data System (ADS)

Partsinevelos, Panagiotis; Perakakis, Manolis

2014-05-01

Remote sensing satellite imagery provides high altitude, top viewing aspects of large geographic regions and as such the depicted features are not always easily recognizable. Nevertheless, geoscientists familiar to remote sensing data, gradually gain experience and enhance their satellite image interpretation skills. The aim of this study is to devise a novel computational neuro-centered classification approach for feature extraction and image understanding. Object recognition through image processing practices is related to a series of known image/feature based attributes including size, shape, association, texture, etc. The objective of the study is to weight these attribute values towards the enhancement of feature recognition. The key cognitive experimentation concern is to define the point when a user recognizes a feature as it varies in terms of the above mentioned attributes and relate it with their corresponding values. Towards this end, we have set up an experimentation methodology that utilizes cognitive data from brain signals (EEG) and eye gaze data (eye tracking) of subjects watching satellite images of varying attributes; this allows the collection of rich real-time data that will be used for designing the image classifier. Since the data are already labeled by users (using an input device) a first step is to compare the performance of various machine-learning algorithms on the collected data. On the long-run, the aim of this work would be to investigate the automatic classification of unlabeled images (unsupervised learning) based purely on image attributes. The outcome of this innovative process is twofold: First, in an abundance of remote sensing image datasets we may define the essential image specifications in order to collect the appropriate data for each application and improve processing and resource efficiency. E.g. for a fault extraction application in a given scale a medium resolution 4-band image, may be more effective than costly, multispectral, very high resolution imagery. Second, we attempt to relate the experienced against the non-experienced user understanding in order to indirectly assess the possible limits of purely computational systems. In other words, obtain the conceptual limits of computation vs human cognition concerning feature recognition from satellite imagery. Preliminary results of this pilot study show relations between collected data and differentiation of the image attributes which indicates that our methodology can lead to important results.
Unsupervised Machine Learning for Developing Personalised Behaviour Models Using Activity Data.

PubMed

Fiorini, Laura; Cavallo, Filippo; Dario, Paolo; Eavis, Alexandra; Caleb-Solly, Praminda

2017-05-04

The goal of this study is to address two major issues that undermine the large scale deployment of smart home sensing solutions in people's homes. These include the costs associated with having to install and maintain a large number of sensors, and the pragmatics of annotating numerous sensor data streams for activity classification. Our aim was therefore to propose a method to describe individual users' behavioural patterns starting from unannotated data analysis of a minimal number of sensors and a "blind" approach for activity recognition. The methodology included processing and analysing sensor data from 17 older adults living in community-based housing to extract activity information at different times of the day. The findings illustrate that 55 days of sensor data from a sensor configuration comprising three sensors, and extracting appropriate features including a "busyness" measure, are adequate to build robust models which can be used for clustering individuals based on their behaviour patterns with a high degree of accuracy (>85%). The obtained clusters can be used to describe individual behaviour over different times of the day. This approach suggests a scalable solution to support optimising the personalisation of care by utilising low-cost sensing and analysis. This approach could be used to track a person's needs over time and fine-tune their care plan on an ongoing basis in a cost-effective manner.
Model-based approach to the detection and classification of mines in sidescan sonar.

PubMed

Reed, Scott; Petillot, Yvan; Bell, Judith

2004-01-10

This paper presents a model-based approach to mine detection and classification by use of sidescan sonar. Advances in autonomous underwater vehicle technology have increased the interest in automatic target recognition systems in an effort to automate a process that is currently carried out by a human operator. Current automated systems generally require training and thus produce poor results when the test data set is different from the training set. This has led to research into unsupervised systems, which are able to cope with the large variability in conditions and terrains seen in sidescan imagery. The system presented in this paper first detects possible minelike objects using a Markov random field model, which operates well on noisy images, such as sidescan, and allows a priori information to be included through the use of priors. The highlight and shadow regions of the object are then extracted with a cooperating statistical snake, which assumes these regions are statistically separate from the background. Finally, a classification decision is made using Dempster-Shafer theory, where the extracted features are compared with synthetic realizations generated with a sidescan sonar simulator model. Results for the entire process are shown on real sidescan sonar data. Similarities between the sidescan sonar and synthetic aperture radar (SAR) imaging processes ensure that the approach outlined here could be made applied to SAR image analysis.
Unsupervised Machine Learning for Developing Personalised Behaviour Models Using Activity Data

PubMed Central

Fiorini, Laura; Cavallo, Filippo; Dario, Paolo; Eavis, Alexandra; Caleb-Solly, Praminda

2017-01-01

The goal of this study is to address two major issues that undermine the large scale deployment of smart home sensing solutions in people’s homes. These include the costs associated with having to install and maintain a large number of sensors, and the pragmatics of annotating numerous sensor data streams for activity classification. Our aim was therefore to propose a method to describe individual users’ behavioural patterns starting from unannotated data analysis of a minimal number of sensors and a ”blind” approach for activity recognition. The methodology included processing and analysing sensor data from 17 older adults living in community-based housing to extract activity information at different times of the day. The findings illustrate that 55 days of sensor data from a sensor configuration comprising three sensors, and extracting appropriate features including a “busyness” measure, are adequate to build robust models which can be used for clustering individuals based on their behaviour patterns with a high degree of accuracy (>85%). The obtained clusters can be used to describe individual behaviour over different times of the day. This approach suggests a scalable solution to support optimising the personalisation of care by utilising low-cost sensing and analysis. This approach could be used to track a person’s needs over time and fine-tune their care plan on an ongoing basis in a cost-effective manner. PMID:28471405
Unsupervised learning of temporal features for word categorization in a spiking neural network model of the auditory brain.

PubMed

Higgins, Irina; Stringer, Simon; Schnupp, Jan

2017-01-01

The nature of the code used in the auditory cortex to represent complex auditory stimuli, such as naturally spoken words, remains a matter of debate. Here we argue that such representations are encoded by stable spatio-temporal patterns of firing within cell assemblies known as polychronous groups, or PGs. We develop a physiologically grounded, unsupervised spiking neural network model of the auditory brain with local, biologically realistic, spike-time dependent plasticity (STDP) learning, and show that the plastic cortical layers of the network develop PGs which convey substantially more information about the speaker independent identity of two naturally spoken word stimuli than does rate encoding that ignores the precise spike timings. We furthermore demonstrate that such informative PGs can only develop if the input spatio-temporal spike patterns to the plastic cortical areas of the model are relatively stable.
Metric Learning to Enhance Hyperspectral Image Segmentation

NASA Technical Reports Server (NTRS)

Thompson, David R.; Castano, Rebecca; Bue, Brian; Gilmore, Martha S.

2013-01-01

Unsupervised hyperspectral image segmentation can reveal spatial trends that show the physical structure of the scene to an analyst. They highlight borders and reveal areas of homogeneity and change. Segmentations are independently helpful for object recognition, and assist with automated production of symbolic maps. Additionally, a good segmentation can dramatically reduce the number of effective spectra in an image, enabling analyses that would otherwise be computationally prohibitive. Specifically, using an over-segmentation of the image instead of individual pixels can reduce noise and potentially improve the results of statistical post-analysis. In this innovation, a metric learning approach is presented to improve the performance of unsupervised hyperspectral image segmentation. The prototype demonstrations attempt a superpixel segmentation in which the image is conservatively over-segmented; that is, the single surface features may be split into multiple segments, but each individual segment, or superpixel, is ensured to have homogenous mineralogy.
Unsupervised learning of temporal features for word categorization in a spiking neural network model of the auditory brain

PubMed Central

Stringer, Simon

2017-01-01

The nature of the code used in the auditory cortex to represent complex auditory stimuli, such as naturally spoken words, remains a matter of debate. Here we argue that such representations are encoded by stable spatio-temporal patterns of firing within cell assemblies known as polychronous groups, or PGs. We develop a physiologically grounded, unsupervised spiking neural network model of the auditory brain with local, biologically realistic, spike-time dependent plasticity (STDP) learning, and show that the plastic cortical layers of the network develop PGs which convey substantially more information about the speaker independent identity of two naturally spoken word stimuli than does rate encoding that ignores the precise spike timings. We furthermore demonstrate that such informative PGs can only develop if the input spatio-temporal spike patterns to the plastic cortical areas of the model are relatively stable. PMID:28797034
Spectral gene set enrichment (SGSE).

PubMed

Frost, H Robert; Li, Zhigang; Moore, Jason H

2015-03-03

Gene set testing is typically performed in a supervised context to quantify the association between groups of genes and a clinical phenotype. In many cases, however, a gene set-based interpretation of genomic data is desired in the absence of a phenotype variable. Although methods exist for unsupervised gene set testing, they predominantly compute enrichment relative to clusters of the genomic variables with performance strongly dependent on the clustering algorithm and number of clusters. We propose a novel method, spectral gene set enrichment (SGSE), for unsupervised competitive testing of the association between gene sets and empirical data sources. SGSE first computes the statistical association between gene sets and principal components (PCs) using our principal component gene set enrichment (PCGSE) method. The overall statistical association between each gene set and the spectral structure of the data is then computed by combining the PC-level p-values using the weighted Z-method with weights set to the PC variance scaled by Tracy-Widom test p-values. Using simulated data, we show that the SGSE algorithm can accurately recover spectral features from noisy data. To illustrate the utility of our method on real data, we demonstrate the superior performance of the SGSE method relative to standard cluster-based techniques for testing the association between MSigDB gene sets and the variance structure of microarray gene expression data. Unsupervised gene set testing can provide important information about the biological signal held in high-dimensional genomic data sets. Because it uses the association between gene sets and samples PCs to generate a measure of unsupervised enrichment, the SGSE method is independent of cluster or network creation algorithms and, most importantly, is able to utilize the statistical significance of PC eigenvalues to ignore elements of the data most likely to represent noise.
A Framework for Land Cover Classification Using Discrete Return LiDAR Data: Adopting Pseudo-Waveform and Hierarchical Segmentation

NASA Technical Reports Server (NTRS)

Jung, Jinha; Pasolli, Edoardo; Prasad, Saurabh; Tilton, James C.; Crawford, Melba M.

2014-01-01

Acquiring current, accurate land-use information is critical for monitoring and understanding the impact of anthropogenic activities on natural environments.Remote sensing technologies are of increasing importance because of their capability to acquire information for large areas in a timely manner, enabling decision makers to be more effective in complex environments. Although optical imagery has demonstrated to be successful for land cover classification, active sensors, such as light detection and ranging (LiDAR), have distinct capabilities that can be exploited to improve classification results. However, utilization of LiDAR data for land cover classification has not been fully exploited. Moreover, spatial-spectral classification has recently gained significant attention since classification accuracy can be improved by extracting additional information from the neighboring pixels. Although spatial information has been widely used for spectral data, less attention has been given to LiDARdata. In this work, a new framework for land cover classification using discrete return LiDAR data is proposed. Pseudo-waveforms are generated from the LiDAR data and processed by hierarchical segmentation. Spatial featuresare extracted in a region-based way using a new unsupervised strategy for multiple pruning of the segmentation hierarchy. The proposed framework is validated experimentally on a real dataset acquired in an urban area. Better classification results are exhibited by the proposed framework compared to the cases in which basic LiDAR products such as digital surface model and intensity image are used. Moreover, the proposed region-based feature extraction strategy results in improved classification accuracies in comparison with a more traditional window-based approach.
Unsupervised Clustering of Subcellular Protein Expression Patterns in High-Throughput Microscopy Images Reveals Protein Complexes and Functional Relationships between Proteins

PubMed Central

Handfield, Louis-François; Chong, Yolanda T.; Simmons, Jibril; Andrews, Brenda J.; Moses, Alan M.

2013-01-01

Protein subcellular localization has been systematically characterized in budding yeast using fluorescently tagged proteins. Based on the fluorescence microscopy images, subcellular localization of many proteins can be classified automatically using supervised machine learning approaches that have been trained to recognize predefined image classes based on statistical features. Here, we present an unsupervised analysis of protein expression patterns in a set of high-resolution, high-throughput microscope images. Our analysis is based on 7 biologically interpretable features which are evaluated on automatically identified cells, and whose cell-stage dependency is captured by a continuous model for cell growth. We show that it is possible to identify most previously identified localization patterns in a cluster analysis based on these features and that similarities between the inferred expression patterns contain more information about protein function than can be explained by a previous manual categorization of subcellular localization. Furthermore, the inferred cell-stage associated to each fluorescence measurement allows us to visualize large groups of proteins entering the bud at specific stages of bud growth. These correspond to proteins localized to organelles, revealing that the organelles must be entering the bud in a stereotypical order. We also identify and organize a smaller group of proteins that show subtle differences in the way they move around the bud during growth. Our results suggest that biologically interpretable features based on explicit models of cell morphology will yield unprecedented power for pattern discovery in high-resolution, high-throughput microscopy images. PMID:23785265
LICRE: unsupervised feature correlation reduction for lipidomics.

PubMed

Wong, Gerard; Chan, Jeffrey; Kingwell, Bronwyn A; Leckie, Christopher; Meikle, Peter J

2014-10-01

Recent advances in high-throughput lipid profiling by liquid chromatography electrospray ionization tandem mass spectrometry (LC-ESI-MS/MS) have made it possible to quantify hundreds of individual molecular lipid species (e.g. fatty acyls, glycerolipids, glycerophospholipids, sphingolipids) in a single experimental run for hundreds of samples. This enables the lipidome of large cohorts of subjects to be profiled to identify lipid biomarkers significantly associated with disease risk, progression and treatment response. Clinically, these lipid biomarkers can be used to construct classification models for the purpose of disease screening or diagnosis. However, the inclusion of a large number of highly correlated biomarkers within a model may reduce classification performance, unnecessarily inflate associated costs of a diagnosis or a screen and reduce the feasibility of clinical translation. An unsupervised feature reduction approach can reduce feature redundancy in lipidomic biomarkers by limiting the number of highly correlated lipids while retaining informative features to achieve good classification performance for various clinical outcomes. Good predictive models based on a reduced number of biomarkers are also more cost effective and feasible from a clinical translation perspective. The application of LICRE to various lipidomic datasets in diabetes and cardiovascular disease demonstrated superior discrimination in terms of the area under the receiver operator characteristic curve while using fewer lipid markers when predicting various clinical outcomes. The MATLAB implementation of LICRE is available from http://ww2.cs.mu.oz.au/∼gwong/LICRE © The Author 2014. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.
Case-based fracture image retrieval.

PubMed

Zhou, Xin; Stern, Richard; Müller, Henning

2012-05-01

Case-based fracture image retrieval can assist surgeons in decisions regarding new cases by supplying visually similar past cases. This tool may guide fracture fixation and management through comparison of long-term outcomes in similar cases. A fracture image database collected over 10 years at the orthopedic service of the University Hospitals of Geneva was used. This database contains 2,690 fracture cases associated with 43 classes (based on the AO/OTA classification). A case-based retrieval engine was developed and evaluated using retrieval precision as a performance metric. Only cases in the same class as the query case are considered as relevant. The scale-invariant feature transform (SIFT) is used for image analysis. Performance evaluation was computed in terms of mean average precision (MAP) and early precision (P10, P30). Retrieval results produced with the GNU image finding tool (GIFT) were used as a baseline. Two sampling strategies were evaluated. One used a dense 40 × 40 pixel grid sampling, and the second one used the standard SIFT features. Based on dense pixel grid sampling, three unsupervised feature selection strategies were introduced to further improve retrieval performance. With dense pixel grid sampling, the image is divided into 1,600 (40 × 40) square blocks. The goal is to emphasize the salient regions (blocks) and ignore irrelevant regions. Regions are considered as important when a high variance of the visual features is found. The first strategy is to calculate the variance of all descriptors on the global database. The second strategy is to calculate the variance of all descriptors for each case. A third strategy is to perform a thumbnail image clustering in a first step and then to calculate the variance for each cluster. Finally, a fusion between a SIFT-based system and GIFT is performed. A first comparison on the selection of sampling strategies using SIFT features shows that dense sampling using a pixel grid (MAP = 0.18) outperformed the SIFT detector-based sampling approach (MAP = 0.10). In a second step, three unsupervised feature selection strategies were evaluated. A grid parameter search is applied to optimize parameters for feature selection and clustering. Results show that using half of the regions (700 or 800) obtains the best performance for all three strategies. Increasing the number of clusters in clustering can also improve the retrieval performance. The SIFT descriptor variance in each case gave the best indication of saliency for the regions (MAP = 0.23), better than the other two strategies (MAP = 0.20 and 0.21). Combining GIFT (MAP = 0.23) and the best SIFT strategy (MAP = 0.23) produced significantly better results (MAP = 0.27) than each system alone. A case-based fracture retrieval engine was developed and is available for online demonstration. SIFT is used to extract local features, and three feature selection strategies were introduced and evaluated. A baseline using the GIFT system was used to evaluate the salient point-based approaches. Without supervised learning, SIFT-based systems with optimized parameters slightly outperformed the GIFT system. A fusion of the two approaches shows that the information contained in the two approaches is complementary. Supervised learning on the feature space is foreseen as the next step of this study.
Remote Sensing Application to Land Use Classification in a Rapidly Changing Agricultural/Urban Area: City of Virginia Beach, Virginia. Ph.D. Thesis

NASA Technical Reports Server (NTRS)

Odenyo, V. A. O.

1975-01-01

Remote sensing data on computer-compatible tapes of LANDSAT 1 multispectral scanner imager were analyzed to generate a land use map of the City of Virginia Beach. All four bands were used in both the supervised and unsupervised approaches with the LAYSYS software system. Color IR imagery of a U-2 flight of the same area was also digitized and two sample areas were analyzed via the unsupervised approach. The relationships between the mapped land use and the soils of the area were investigated. A land use land cover map at a scale of 1:24,000 was obtained from the supervised analysis of LANDSAT 1 data. It was concluded that machine analysis of remote sensing data to produce land use maps was feasible; that the LAYSYS software system was usable for this purpose; and that the machine analysis was capable of extracting detailed information from the relatively small scale LANDSAT data in a much shorter time without compromising accuracy.
Unsupervised, Robust Estimation-based Clustering for Multispectral Images

NASA Technical Reports Server (NTRS)

Netanyahu, Nathan S.

1997-01-01

To prepare for the challenge of handling the archiving and querying of terabyte-sized scientific spatial databases, the NASA Goddard Space Flight Center's Applied Information Sciences Branch (AISB, Code 935) developed a number of characterization algorithms that rely on supervised clustering techniques. The research reported upon here has been aimed at continuing the evolution of some of these supervised techniques, namely the neural network and decision tree-based classifiers, plus extending the approach to incorporating unsupervised clustering algorithms, such as those based on robust estimation (RE) techniques. The algorithms developed under this task should be suited for use by the Intelligent Information Fusion System (IIFS) metadata extraction modules, and as such these algorithms must be fast, robust, and anytime in nature. Finally, so that the planner/schedule module of the IlFS can oversee the use and execution of these algorithms, all information required by the planner/scheduler must be provided to the IIFS development team to ensure the timely integration of these algorithms into the overall system.
Unsupervised Learning (Clustering) of Odontocete Echolocation Clicks

DTIC Science & Technology

2015-09-30

of their bandwidth. Results on Risso’s dolphins (Grampus griseus), Pacific white-sided dolphins (Lagenorhynchus obliquidens), and Cuvier’s beaked...acoustic encounters to see which ones appeared to be closely related to one another. We noted that some of the Pacific white-sided and Risso’s dolphin ...should be clusterable. The group of odontocetes that we cannot label reliably by their acoustic features, primarily common dolphins (Delphinus spp
Unsupervised learning in persistent sensing for target recognition by wireless ad hoc networks of ground-based sensors

NASA Astrophysics Data System (ADS)

Hortos, William S.

2008-04-01

In previous work by the author, effective persistent and pervasive sensing for recognition and tracking of battlefield targets were seen to be achieved, using intelligent algorithms implemented by distributed mobile agents over a composite system of unmanned aerial vehicles (UAVs) for persistence and a wireless network of unattended ground sensors for pervasive coverage of the mission environment. While simulated performance results for the supervised algorithms of the composite system are shown to provide satisfactory target recognition over relatively brief periods of system operation, this performance can degrade by as much as 50% as target dynamics in the environment evolve beyond the period of system operation in which the training data are representative. To overcome this limitation, this paper applies the distributed approach using mobile agents to the network of ground-based wireless sensors alone, without the UAV subsystem, to provide persistent as well as pervasive sensing for target recognition and tracking. The supervised algorithms used in the earlier work are supplanted by unsupervised routines, including competitive-learning neural networks (CLNNs) and new versions of support vector machines (SVMs) for characterization of an unknown target environment. To capture the same physical phenomena from battlefield targets as the composite system, the suite of ground-based sensors can be expanded to include imaging and video capabilities. The spatial density of deployed sensor nodes is increased to allow more precise ground-based location and tracking of detected targets by active nodes. The "swarm" mobile agents enabling WSN intelligence are organized in a three processing stages: detection, recognition and sustained tracking of ground targets. Features formed from the compressed sensor data are down-selected according to an information-theoretic algorithm that reduces redundancy within the feature set, reducing the dimension of samples used in the target recognition and tracking routines. Target tracking is based on simplified versions of Kalman filtration. Accuracy of recognition and tracking of implemented versions of the proposed suite of unsupervised algorithms is somewhat degraded from the ideal. Target recognition and tracking by supervised routines and by unsupervised SVM and CLNN routines in the ground-based WSN is evaluated in simulations using published system values and sensor data from vehicular targets in ground-surveillance scenarios. Results are compared with previously published performance for the system of the ground-based sensor network (GSN) and UAV swarm.
Deep learning algorithms for detecting explosive hazards in ground penetrating radar data

NASA Astrophysics Data System (ADS)

Besaw, Lance E.; Stimac, Philip J.

2014-05-01

Buried explosive hazards (BEHs) have been, and continue to be, one of the most deadly threats in modern conflicts. Current handheld sensors rely on a highly trained operator for them to be effective in detecting BEHs. New algorithms are needed to reduce the burden on the operator and improve the performance of handheld BEH detectors. Traditional anomaly detection and discrimination algorithms use "hand-engineered" feature extraction techniques to characterize and classify threats. In this work we use a Deep Belief Network (DBN) to transcend the traditional approaches of BEH detection (e.g., principal component analysis and real-time novelty detection techniques). DBNs are pretrained using an unsupervised learning algorithm to generate compressed representations of unlabeled input data and form feature detectors. They are then fine-tuned using a supervised learning algorithm to form a predictive model. Using ground penetrating radar (GPR) data collected by a robotic cart swinging a handheld detector, our research demonstrates that relatively small DBNs can learn to model GPR background signals and detect BEHs with an acceptable false alarm rate (FAR). In this work, our DBNs achieved 91% probability of detection (Pd) with 1.4 false alarms per square meter when evaluated on anti-tank and anti-personnel targets at temperate and arid test sites. This research demonstrates that DBNs are a viable approach to detect and classify BEHs.
A Fast Multimodal Ectopic Beat Detection Method Applied for Blood Pressure Estimation Based on Pulse Wave Velocity Measurements in Wearable Sensors.

PubMed

Pflugradt, Maik; Geissdoerfer, Kai; Goernig, Matthias; Orglmeister, Reinhold

2017-01-14

Automatic detection of ectopic beats has become a thoroughly researched topic, with literature providing manifold proposals typically incorporating morphological analysis of the electrocardiogram (ECG). Although being well understood, its utilization is often neglected, especially in practical monitoring situations like online evaluation of signals acquired in wearable sensors. Continuous blood pressure estimation based on pulse wave velocity considerations is a prominent example, which depends on careful fiducial point extraction and is therefore seriously affected during periods of increased occurring extrasystoles. In the scope of this work, a novel ectopic beat discriminator with low computational complexity has been developed, which takes advantage of multimodal features derived from ECG and pulse wave relating measurements, thereby providing additional information on the underlying cardiac activity. Moreover, the blood pressure estimations' vulnerability towards ectopic beats is closely examined on records drawn from the Physionet database as well as signals recorded in a small field study conducted in a geriatric facility for the elderly. It turns out that a reliable extrasystole identification is essential to unsupervised blood pressure estimation, having a significant impact on the overall accuracy. The proposed method further convinces by its applicability to battery driven hardware systems with limited processing power and is a favorable choice when access to multimodal signal features is given anyway.
Comparison of Unsupervised Vegetation Classification Methods from Vhr Images after Shadows Removal by Innovative Algorithms

NASA Astrophysics Data System (ADS)

Movia, A.; Beinat, A.; Crosilla, F.

2015-04-01

The recognition of vegetation by the analysis of very high resolution (VHR) aerial images provides meaningful information about environmental features; nevertheless, VHR images frequently contain shadows that generate significant problems for the classification of the image components and for the extraction of the needed information. The aim of this research is to classify, from VHR aerial images, vegetation involved in the balance process of the environmental biochemical cycle, and to discriminate it with respect to urban and agricultural features. Three classification algorithms have been experimented in order to better recognize vegetation, and compared to NDVI index; unfortunately all these methods are conditioned by the presence of shadows on the images. Literature presents several algorithms to detect and remove shadows in the scene: most of them are based on the RGB to HSI transformations. In this work some of them have been implemented and compared with one based on RGB bands. Successively, in order to remove shadows and restore brightness on the images, some innovative algorithms, based on Procrustes theory, have been implemented and applied. Among these, we evaluate the capability of the so called "not-centered oblique Procrustes" and "anisotropic Procrustes" methods to efficiently restore brightness with respect to a linear correlation correction based on the Cholesky decomposition. Some experimental results obtained by different classification methods after shadows removal carried out with the innovative algorithms are presented and discussed.

Unsupervised Spatio-Temporal Data Mining Framework for Burned Area Mapping

NASA Technical Reports Server (NTRS)

Kumar, Vipin (Inventor); Boriah, Shyam (Inventor); Mithal, Varun (Inventor); Khandelwal, Ankush (Inventor)

2016-01-01

A method reduces processing time required to identify locations burned by fire by receiving a feature value for each pixel in an image, each pixel representing a sub-area of a location. Pixels are then grouped based on similarities of the feature values to form candidate burn events. For each candidate burn event, a probability that the candidate burn event is a true burn event is determined based on at least one further feature value for each pixel in the candidate burn event. Candidate burn events that have a probability below a threshold are removed from further consideration as burn events to produce a set of remaining candidate burn events.
A Case Study on Sepsis Using PubMed and Deep Learning for Ontology Learning.

PubMed

Arguello Casteleiro, Mercedes; Maseda Fernandez, Diego; Demetriou, George; Read, Warren; Fernandez Prieto, Maria Jesus; Des Diz, Julio; Nenadic, Goran; Keane, John; Stevens, Robert

2017-01-01

We investigate the application of distributional semantics models for facilitating unsupervised extraction of biomedical terms from unannotated corpora. Term extraction is used as the first step of an ontology learning process that aims to (semi-)automatic annotation of biomedical concepts and relations from more than 300K PubMed titles and abstracts. We experimented with both traditional distributional semantics methods such as Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA) as well as the neural language models CBOW and Skip-gram from Deep Learning. The evaluation conducted concentrates on sepsis, a major life-threatening condition, and shows that Deep Learning models outperform LSA and LDA with much higher precision.
Identifying product order with restricted Boltzmann machines

NASA Astrophysics Data System (ADS)

Rao, Wen-Jia; Li, Zhenyu; Zhu, Qiong; Luo, Mingxing; Wan, Xin

2018-03-01

Unsupervised machine learning via a restricted Boltzmann machine is a useful tool in distinguishing an ordered phase from a disordered phase. Here we study its application on the two-dimensional Ashkin-Teller model, which features a partially ordered product phase. We train the neural network with spin configuration data generated by Monte Carlo simulations and show that distinct features of the product phase can be learned from nonergodic samples resulting from symmetry breaking. Careful analysis of the weight matrices inspires us to define a nontrivial machine-learning motivated quantity of the product form, which resembles the conventional product order parameter.
Unsupervised definition of the tibia-femoral joint regions of the human knee and its applications to cartilage analysis

NASA Astrophysics Data System (ADS)

Tamez-Peña, José G.; Barbu-McInnis, Monica; Totterman, Saara

2006-03-01

Abnormal MR findings including cartilage defects, cartilage denuded areas, osteophytes, and bone marrow edema (BME) are used in staging and evaluating the degree of osteoarthritis (OA) in the knee. The locations of the abnormal findings have been correlated to the degree of pain and stiffness of the joint in the same location. The definition of the anatomic region in MR images is not always an objective task, due to the lack of clear anatomical features. This uncertainty causes variance in the location of the abnormality between readers and time points. Therefore, it is important to have a reproducible system to define the anatomic regions. This works present a computerized approach to define the different anatomic knee regions. The approach is based on an algorithm that uses unique features of the femur and its spatial relation in the extended knee. The femur features are found from three dimensional segmentation maps of the knee. From the segmentation maps, the algorithm automatically divides the femur cartilage into five anatomic regions: trochlea, medial weight bearing area, lateral weight bearing area, posterior medial femoral condyle, and posterior lateral femoral condyle. Furthermore, the algorithm automatically labels the medial and lateral tibia cartilage. The unsupervised definition of the knee regions allows a reproducible way to evaluate regional OA changes. This works will present the application of this automated algorithm for the regional analysis of the cartilage tissue.
Accuracy of un-supervised versus provider-supervised self-administered HIV testing in Uganda: A randomized implementation trial.

PubMed

Asiimwe, Stephen; Oloya, James; Song, Xiao; Whalen, Christopher C

2014-12-01

Unsupervised HIV self-testing (HST) has potential to increase knowledge of HIV status; however, its accuracy is unknown. To estimate the accuracy of unsupervised HST in field settings in Uganda, we performed a non-blinded, randomized controlled, non-inferiority trial of unsupervised compared with supervised HST among selected high HIV risk fisherfolk (22.1 % HIV Prevalence) in three fishing villages in Uganda between July and September 2013. The study enrolled 246 participants and randomized them in a 1:1 ratio to unsupervised HST or provider-supervised HST. In an intent-to-treat analysis, the HST sensitivity was 90 % in the unsupervised arm and 100 % among the provider-supervised, yielding a difference 0f -10 % (90 % CI -21, 1 %); non-inferiority was not shown. In a per protocol analysis, the difference in sensitivity was -5.6 % (90 % CI -14.4, 3.3 %) and did show non-inferiority. We conclude that unsupervised HST is feasible in rural Africa and may be non-inferior to provider-supervised HST.
Spike sorting using locality preserving projection with gap statistics and landmark-based spectral clustering.

PubMed

Nguyen, Thanh; Khosravi, Abbas; Creighton, Douglas; Nahavandi, Saeid

2014-12-30

Understanding neural functions requires knowledge from analysing electrophysiological data. The process of assigning spikes of a multichannel signal into clusters, called spike sorting, is one of the important problems in such analysis. There have been various automated spike sorting techniques with both advantages and disadvantages regarding accuracy and computational costs. Therefore, developing spike sorting methods that are highly accurate and computationally inexpensive is always a challenge in the biomedical engineering practice. An automatic unsupervised spike sorting method is proposed in this paper. The method uses features extracted by the locality preserving projection (LPP) algorithm. These features afterwards serve as inputs for the landmark-based spectral clustering (LSC) method. Gap statistics (GS) is employed to evaluate the number of clusters before the LSC can be performed. The proposed LPP-LSC is highly accurate and computationally inexpensive spike sorting approach. LPP spike features are very discriminative; thereby boost the performance of clustering methods. Furthermore, the LSC method exhibits its efficiency when integrated with the cluster evaluator GS. The proposed method's accuracy is approximately 13% superior to that of the benchmark combination between wavelet transformation and superparamagnetic clustering (WT-SPC). Additionally, LPP-LSC computing time is six times less than that of the WT-SPC. LPP-LSC obviously demonstrates a win-win spike sorting solution meeting both accuracy and computational cost criteria. LPP and LSC are linear algorithms that help reduce computational burden and thus their combination can be applied into real-time spike analysis. Copyright © 2014 Elsevier B.V. All rights reserved.
Change detection and change monitoring of natural and man-made features in multispectral and hyperspectral satellite imagery

DOE Office of Scientific and Technical Information (OSTI.GOV)

Moody, Daniela Irina

An approach for land cover classification, seasonal and yearly change detection and monitoring, and identification of changes in man-made features may use a clustering of sparse approximations (CoSA) on sparse representations in learned dictionaries. A Hebbian learning rule may be used to build multispectral or hyperspectral, multiresolution dictionaries that are adapted to regional satellite image data. Sparse image representations of pixel patches over the learned dictionaries may be used to perform unsupervised k-means clustering into land cover categories. The clustering process behaves as a classifier in detecting real variability. This approach may combine spectral and spatial textural characteristics to detectmore » geologic, vegetative, hydrologic, and man-made features, as well as changes in these features over time.« less
Automated unsupervised multi-parametric classification of adipose tissue depots in skeletal muscle

PubMed Central

Valentinitsch, Alexander; Karampinos, Dimitrios C.; Alizai, Hamza; Subburaj, Karupppasamy; Kumar, Deepak; Link, Thomas M.; Majumdar, Sharmila

2012-01-01

Purpose To introduce and validate an automated unsupervised multi-parametric method for segmentation of the subcutaneous fat and muscle regions in order to determine subcutaneous adipose tissue (SAT) and intermuscular adipose tissue (IMAT) areas based on data from a quantitative chemical shift-based water-fat separation approach. Materials and Methods Unsupervised standard k-means clustering was employed to define sets of similar features (k = 2) within the whole multi-modal image after the water-fat separation. The automated image processing chain was composed of three primary stages including tissue, muscle and bone region segmentation. The algorithm was applied on calf and thigh datasets to compute SAT and IMAT areas and was compared to a manual segmentation. Results The IMAT area using the automatic segmentation had excellent agreement with the IMAT area using the manual segmentation for all the cases in the thigh (R2: 0.96) and for cases with up to moderate IMAT area in the calf (R2: 0.92). The group with the highest grade of muscle fat infiltration in the calf had the highest error in the inner SAT contour calculation. Conclusion The proposed multi-parametric segmentation approach combined with quantitative water-fat imaging provides an accurate and reliable method for an automated calculation of the SAT and IMAT areas reducing considerably the total post-processing time. PMID:23097409
Learning Long-Range Vision for an Offroad Robot

DTIC Science & Technology

2008-09-01

robot to perceive and navigate in an unstructured natural world is a difficult task. Without learning, navigation systems are short-range and extremely...unsupervised or weakly supervised learning methods are necessary for training general feature representations for natural scenes. The process was...the world looked dark, and Legos when I was weary. iii ABSTRACT Teaching a robot to perceive and navigate in an unstructured natural world is a
Three Dimensional Object Recognition Using an Unsupervised Neural Network: Understanding the Distinguishing Features

DTIC Science & Technology

1992-12-23

predominance of structural models of recognition, of which a recent example is the Recognition By Components (RBC) theory ( Biederman , 1987 ). Structural...related to recent statistical theory (Huber, 1985; Friedman, 1987 ) and is derived from a biologically motivated computational theory (Bienenstock et...dimensional object recognition (Intrator and Gold, 1991). The method is related to recent statistical theory (Huber, 1985; Friedman, 1987 ) and is derived
Binary Multidimensional Scaling for Hashing.

PubMed

Huang, Yameng; Lin, Zhouchen

2017-10-04

Hashing is a useful technique for fast nearest neighbor search due to its low storage cost and fast query speed. Unsupervised hashing aims at learning binary hash codes for the original features so that the pairwise distances can be best preserved. While several works have targeted on this task, the results are not satisfactory mainly due to the oversimplified model. In this paper, we propose a unified and concise unsupervised hashing framework, called Binary Multidimensional Scaling (BMDS), which is able to learn the hash code for distance preservation in both batch and online mode. In the batch mode, unlike most existing hashing methods, we do not need to simplify the model by predefining the form of hash map. Instead, we learn the binary codes directly based on the pairwise distances among the normalized original features by Alternating Minimization. This enables a stronger expressive power of the hash map. In the online mode, we consider the holistic distance relationship between current query example and those we have already learned, rather than only focusing on current data chunk. It is useful when the data come in a streaming fashion. Empirical results show that while being efficient for training, our algorithm outperforms state-of-the-art methods by a large margin in terms of distance preservation, which is practical for real-world applications.
Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records

PubMed Central

Miotto, Riccardo; Li, Li; Kidd, Brian A.; Dudley, Joel T.

2016-01-01

Secondary use of electronic health records (EHRs) promises to advance clinical research and better inform clinical decision making. Challenges in summarizing and representing patient data prevent widespread practice of predictive modeling using EHRs. Here we present a novel unsupervised deep feature learning method to derive a general-purpose patient representation from EHR data that facilitates clinical predictive modeling. In particular, a three-layer stack of denoising autoencoders was used to capture hierarchical regularities and dependencies in the aggregated EHRs of about 700,000 patients from the Mount Sinai data warehouse. The result is a representation we name “deep patient”. We evaluated this representation as broadly predictive of health states by assessing the probability of patients to develop various diseases. We performed evaluation using 76,214 test patients comprising 78 diseases from diverse clinical domains and temporal windows. Our results significantly outperformed those achieved using representations based on raw EHR data and alternative feature learning strategies. Prediction performance for severe diabetes, schizophrenia, and various cancers were among the top performing. These findings indicate that deep learning applied to EHRs can derive patient representations that offer improved clinical predictions, and could provide a machine learning framework for augmenting clinical decision systems. PMID:27185194
Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records

NASA Astrophysics Data System (ADS)

Miotto, Riccardo; Li, Li; Kidd, Brian A.; Dudley, Joel T.

2016-05-01

Secondary use of electronic health records (EHRs) promises to advance clinical research and better inform clinical decision making. Challenges in summarizing and representing patient data prevent widespread practice of predictive modeling using EHRs. Here we present a novel unsupervised deep feature learning method to derive a general-purpose patient representation from EHR data that facilitates clinical predictive modeling. In particular, a three-layer stack of denoising autoencoders was used to capture hierarchical regularities and dependencies in the aggregated EHRs of about 700,000 patients from the Mount Sinai data warehouse. The result is a representation we name “deep patient”. We evaluated this representation as broadly predictive of health states by assessing the probability of patients to develop various diseases. We performed evaluation using 76,214 test patients comprising 78 diseases from diverse clinical domains and temporal windows. Our results significantly outperformed those achieved using representations based on raw EHR data and alternative feature learning strategies. Prediction performance for severe diabetes, schizophrenia, and various cancers were among the top performing. These findings indicate that deep learning applied to EHRs can derive patient representations that offer improved clinical predictions, and could provide a machine learning framework for augmenting clinical decision systems.
DOE Office of Scientific and Technical Information (OSTI.GOV)

Lafata, K; Ren, L; Wu, Q

Purpose: To develop a data-mining methodology based on quantum clustering and machine learning to predict expected dosimetric endpoints for lung SBRT applications based on patient-specific anatomic features. Methods: Ninety-three patients who received lung SBRT at our clinic from 2011–2013 were retrospectively identified. Planning information was acquired for each patient, from which various features were extracted using in-house semi-automatic software. Anatomic features included tumor-to-OAR distances, tumor location, total-lung-volume, GTV and ITV. Dosimetric endpoints were adopted from RTOG-0195 recommendations, and consisted of various OAR-specific partial-volume doses and maximum point-doses. First, PCA analysis and unsupervised quantum-clustering was used to explore the feature-space tomore » identify potentially strong classifiers. Secondly, a multi-class logistic regression algorithm was developed and trained to predict dose-volume endpoints based on patient-specific anatomic features. Classes were defined by discretizing the dose-volume data, and the feature-space was zero-mean normalized. Fitting parameters were determined by minimizing a regularized cost function, and optimization was performed via gradient descent. As a pilot study, the model was tested on two esophageal dosimetric planning endpoints (maximum point-dose, dose-to-5cc), and its generalizability was evaluated with leave-one-out cross-validation. Results: Quantum-Clustering demonstrated a strong separation of feature-space at 15Gy across the first-and-second Principle Components of the data when the dosimetric endpoints were retrospectively identified. Maximum point dose prediction to the esophagus demonstrated a cross-validation accuracy of 87%, and the maximum dose to 5cc demonstrated a respective value of 79%. The largest optimized weighting factor was placed on GTV-to-esophagus distance (a factor of 10 greater than the second largest weighting factor), indicating an intuitively strong correlation between this feature and both endpoints. Conclusion: This pilot study shows that it is feasible to predict dose-volume endpoints based on patient-specific anatomic features. The developed methodology can potentially help to identify patients at risk for higher OAR doses, thus improving the efficiency of treatment planning. R01-184173.« less
Cascaded ensemble of convolutional neural networks and handcrafted features for mitosis detection

NASA Astrophysics Data System (ADS)

Wang, Haibo; Cruz-Roa, Angel; Basavanhally, Ajay; Gilmore, Hannah; Shih, Natalie; Feldman, Mike; Tomaszewski, John; Gonzalez, Fabio; Madabhushi, Anant

2014-03-01

Breast cancer (BCa) grading plays an important role in predicting disease aggressiveness and patient outcome. A key component of BCa grade is mitotic count, which involves quantifying the number of cells in the process of dividing (i.e. undergoing mitosis) at a specific point in time. Currently mitosis counting is done manually by a pathologist looking at multiple high power fields on a glass slide under a microscope, an extremely laborious and time consuming process. The development of computerized systems for automated detection of mitotic nuclei, while highly desirable, is confounded by the highly variable shape and appearance of mitoses. Existing methods use either handcrafted features that capture certain morphological, statistical or textural attributes of mitoses or features learned with convolutional neural networks (CNN). While handcrafted features are inspired by the domain and the particular application, the data-driven CNN models tend to be domain agnostic and attempt to learn additional feature bases that cannot be represented through any of the handcrafted features. On the other hand, CNN is computationally more complex and needs a large number of labeled training instances. Since handcrafted features attempt to model domain pertinent attributes and CNN approaches are largely unsupervised feature generation methods, there is an appeal to attempting to combine these two distinct classes of feature generation strategies to create an integrated set of attributes that can potentially outperform either class of feature extraction strategies individually. In this paper, we present a cascaded approach for mitosis detection that intelligently combines a CNN model and handcrafted features (morphology, color and texture features). By employing a light CNN model, the proposed approach is far less demanding computationally, and the cascaded strategy of combining handcrafted features and CNN-derived features enables the possibility of maximizing performance by leveraging the disconnected feature sets. Evaluation on the public ICPR12 mitosis dataset that has 226 mitoses annotated on 35 High Power Fields (HPF, x400 magnification) by several pathologists and 15 testing HPFs yielded an F-measure of 0.7345. Apart from this being the second best performance ever recorded for this MITOS dataset, our approach is faster and requires fewer computing resources compared to extant methods, making this feasible for clinical use.
Embedded security system for multi-modal surveillance in a railway carriage

NASA Astrophysics Data System (ADS)

Zouaoui, Rhalem; Audigier, Romaric; Ambellouis, Sébastien; Capman, François; Benhadda, Hamid; Joudrier, Stéphanie; Sodoyer, David; Lamarque, Thierry

2015-10-01

Public transport security is one of the main priorities of the public authorities when fighting against crime and terrorism. In this context, there is a great demand for autonomous systems able to detect abnormal events such as violent acts aboard passenger cars and intrusions when the train is parked at the depot. To this end, we present an innovative approach which aims at providing efficient automatic event detection by fusing video and audio analytics and reducing the false alarm rate compared to classical stand-alone video detection. The multi-modal system is composed of two microphones and one camera and integrates onboard video and audio analytics and fusion capabilities. On the one hand, for detecting intrusion, the system relies on the fusion of "unusual" audio events detection with intrusion detections from video processing. The audio analysis consists in modeling the normal ambience and detecting deviation from the trained models during testing. This unsupervised approach is based on clustering of automatically extracted segments of acoustic features and statistical Gaussian Mixture Model (GMM) modeling of each cluster. The intrusion detection is based on the three-dimensional (3D) detection and tracking of individuals in the videos. On the other hand, for violent events detection, the system fuses unsupervised and supervised audio algorithms with video event detection. The supervised audio technique detects specific events such as shouts. A GMM is used to catch the formant structure of a shout signal. Video analytics use an original approach for detecting aggressive motion by focusing on erratic motion patterns specific to violent events. As data with violent events is not easily available, a normality model with structured motions from non-violent videos is learned for one-class classification. A fusion algorithm based on Dempster-Shafer's theory analyses the asynchronous detection outputs and computes the degree of belief of each probable event.
Generating region proposals for histopathological whole slide image retrieval.

PubMed

Ma, Yibing; Jiang, Zhiguo; Zhang, Haopeng; Xie, Fengying; Zheng, Yushan; Shi, Huaqiang; Zhao, Yu; Shi, Jun

2018-06-01

Content-based image retrieval is an effective method for histopathological image analysis. However, given a database of huge whole slide images (WSIs), acquiring appropriate region-of-interests (ROIs) for training is significant and difficult. Moreover, histopathological images can only be annotated by pathologists, resulting in the lack of labeling information. Therefore, it is an important and challenging task to generate ROIs from WSI and retrieve image with few labels. This paper presents a novel unsupervised region proposing method for histopathological WSI based on Selective Search. Specifically, the WSI is over-segmented into regions which are hierarchically merged until the WSI becomes a single region. Nucleus-oriented similarity measures for region mergence and Nucleus-Cytoplasm color space for histopathological image are specially defined to generate accurate region proposals. Additionally, we propose a new semi-supervised hashing method for image retrieval. The semantic features of images are extracted with Latent Dirichlet Allocation and transformed into binary hashing codes with Supervised Hashing. The methods are tested on a large-scale multi-class database of breast histopathological WSIs. The results demonstrate that for one WSI, our region proposing method can generate 7.3 thousand contoured regions which fit well with 95.8% of the ROIs annotated by pathologists. The proposed hashing method can retrieve a query image among 136 thousand images in 0.29 s and reach precision of 91% with only 10% of images labeled. The unsupervised region proposing method can generate regions as predictions of lesions in histopathological WSI. The region proposals can also serve as the training samples to train machine-learning models for image retrieval. The proposed hashing method can achieve fast and precise image retrieval with small amount of labels. Furthermore, the proposed methods can be potentially applied in online computer-aided-diagnosis systems. Copyright © 2018 Elsevier B.V. All rights reserved.
Impact of feature saliency on visual category learning.

PubMed

Hammer, Rubi

2015-01-01

People have to sort numerous objects into a large number of meaningful categories while operating in varying contexts. This requires identifying the visual features that best predict the 'essence' of objects (e.g., edibility), rather than categorizing objects based on the most salient features in a given context. To gain this capacity, visual category learning (VCL) relies on multiple cognitive processes. These may include unsupervised statistical learning, that requires observing multiple objects for learning the statistics of their features. Other learning processes enable incorporating different sources of supervisory information, alongside the visual features of the categorized objects, from which the categorical relations between few objects can be deduced. These deductions enable inferring that objects from the same category may differ from one another in some high-saliency feature dimensions, whereas lower-saliency feature dimensions can best differentiate objects from distinct categories. Here I illustrate how feature saliency affects VCL, by also discussing kinds of supervisory information enabling reflective categorization. Arguably, principles debated here are often being ignored in categorization studies.
Impact of feature saliency on visual category learning

PubMed Central

Hammer, Rubi

2015-01-01

People have to sort numerous objects into a large number of meaningful categories while operating in varying contexts. This requires identifying the visual features that best predict the ‘essence’ of objects (e.g., edibility), rather than categorizing objects based on the most salient features in a given context. To gain this capacity, visual category learning (VCL) relies on multiple cognitive processes. These may include unsupervised statistical learning, that requires observing multiple objects for learning the statistics of their features. Other learning processes enable incorporating different sources of supervisory information, alongside the visual features of the categorized objects, from which the categorical relations between few objects can be deduced. These deductions enable inferring that objects from the same category may differ from one another in some high-saliency feature dimensions, whereas lower-saliency feature dimensions can best differentiate objects from distinct categories. Here I illustrate how feature saliency affects VCL, by also discussing kinds of supervisory information enabling reflective categorization. Arguably, principles debated here are often being ignored in categorization studies. PMID:25954220
Surface defect detection in tiling Industries using digital image processing methods: analysis and evaluation.

PubMed

Karimi, Mohammad H; Asemani, Davud

2014-05-01

Ceramic and tile industries should indispensably include a grading stage to quantify the quality of products. Actually, human control systems are often used for grading purposes. An automatic grading system is essential to enhance the quality control and marketing of the products. Since there generally exist six different types of defects originating from various stages of tile manufacturing lines with distinct textures and morphologies, many image processing techniques have been proposed for defect detection. In this paper, a survey has been made on the pattern recognition and image processing algorithms which have been used to detect surface defects. Each method appears to be limited for detecting some subgroup of defects. The detection techniques may be divided into three main groups: statistical pattern recognition, feature vector extraction and texture/image classification. The methods such as wavelet transform, filtering, morphology and contourlet transform are more effective for pre-processing tasks. Others including statistical methods, neural networks and model-based algorithms can be applied to extract the surface defects. Although, statistical methods are often appropriate for identification of large defects such as Spots, but techniques such as wavelet processing provide an acceptable response for detection of small defects such as Pinhole. A thorough survey is made in this paper on the existing algorithms in each subgroup. Also, the evaluation parameters are discussed including supervised and unsupervised parameters. Using various performance parameters, different defect detection algorithms are compared and evaluated. Copyright © 2013 ISA. Published by Elsevier Ltd. All rights reserved.

Radio Model-free Noise Reduction of Radio Transmissions with Convolutional Autoencoders

DTIC Science & Technology

2016-09-01

Encoder-Decoder Architecture for Image Segmentation .” Cornell University Library. Computing Research Repository (CoRR). abs/1511.00561. 2. Anthony J. Bell...Aaron C Courville, and Pascal Vincent. 2012. “Unsupervised Feature Learning and Deep Learning : A Review and New Perspectives.” Cornell University...Linux Journal 122(June):1–4. 5. Francois Chollet. 2015.“Keras: Deep Learning Library for TensorFlow and Theano.” Available online at https://github.com
An introduction to kernel-based learning algorithms.

PubMed

Müller, K R; Mika, S; Rätsch, G; Tsuda, K; Schölkopf, B

2001-01-01

This paper provides an introduction to support vector machines, kernel Fisher discriminant analysis, and kernel principal component analysis, as examples for successful kernel-based learning methods. We first give a short background about Vapnik-Chervonenkis theory and kernel feature spaces and then proceed to kernel based learning in supervised and unsupervised scenarios including practical and algorithmic considerations. We illustrate the usefulness of kernel algorithms by discussing applications such as optical character recognition and DNA analysis.
Unsupervised image matching based on manifold alignment.

PubMed

Pei, Yuru; Huang, Fengchun; Shi, Fuhao; Zha, Hongbin

2012-08-01

This paper challenges the issue of automatic matching between two image sets with similar intrinsic structures and different appearances, especially when there is no prior correspondence. An unsupervised manifold alignment framework is proposed to establish correspondence between data sets by a mapping function in the mutual embedding space. We introduce a local similarity metric based on parameterized distance curves to represent the connection of one point with the rest of the manifold. A small set of valid feature pairs can be found without manual interactions by matching the distance curve of one manifold with the curve cluster of the other manifold. To avoid potential confusions in image matching, we propose an extended affine transformation to solve the nonrigid alignment in the embedding space. The comparatively tight alignments and the structure preservation can be obtained simultaneously. The point pairs with the minimum distance after alignment are viewed as the matchings. We apply manifold alignment to image set matching problems. The correspondence between image sets of different poses, illuminations, and identities can be established effectively by our approach.
Model–Free Visualization of Suspicious Lesions in Breast MRI Based on Supervised and Unsupervised Learning

PubMed Central

Twellmann, Thorsten; Meyer-Baese, Anke; Lange, Oliver; Foo, Simon; Nattkemper, Tim W.

2008-01-01

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has become an important tool in breast cancer diagnosis, but evaluation of multitemporal 3D image data holds new challenges for human observers. To aid the image analysis process, we apply supervised and unsupervised pattern recognition techniques for computing enhanced visualizations of suspicious lesions in breast MRI data. These techniques represent an important component of future sophisticated computer-aided diagnosis (CAD) systems and support the visual exploration of spatial and temporal features of DCE-MRI data stemming from patients with confirmed lesion diagnosis. By taking into account the heterogeneity of cancerous tissue, these techniques reveal signals with malignant, benign and normal kinetics. They also provide a regional subclassification of pathological breast tissue, which is the basis for pseudo-color presentations of the image data. Intelligent medical systems are expected to have substantial implications in healthcare politics by contributing to the diagnosis of indeterminate breast lesions by non-invasive imaging. PMID:19255616
Unsupervised Word Spotting in Historical Handwritten Document Images using Document-oriented Local Features.

PubMed

Zagoris, Konstantinos; Pratikakis, Ioannis; Gatos, Basilis

2017-05-03

Word spotting strategies employed in historical handwritten documents face many challenges due to variation in the writing style and intense degradation. In this paper, a new method that permits effective word spotting in handwritten documents is presented that it relies upon document-oriented local features which take into account information around representative keypoints as well a matching process that incorporates spatial context in a local proximity search without using any training data. Experimental results on four historical handwritten datasets for two different scenarios (segmentation-based and segmentation-free) using standard evaluation measures show the improved performance achieved by the proposed methodology.
On the unsupervised analysis of domain-specific Chinese texts

PubMed Central

Deng, Ke; Bol, Peter K.; Li, Kate J.; Liu, Jun S.

2016-01-01

With the growing availability of digitized text data both publicly and privately, there is a great need for effective computational tools to automatically extract information from texts. Because the Chinese language differs most significantly from alphabet-based languages in not specifying word boundaries, most existing Chinese text-mining methods require a prespecified vocabulary and/or a large relevant training corpus, which may not be available in some applications. We introduce an unsupervised method, top-down word discovery and segmentation (TopWORDS), for simultaneously discovering and segmenting words and phrases from large volumes of unstructured Chinese texts, and propose ways to order discovered words and conduct higher-level context analyses. TopWORDS is particularly useful for mining online and domain-specific texts where the underlying vocabulary is unknown or the texts of interest differ significantly from available training corpora. When outputs from TopWORDS are fed into context analysis tools such as topic modeling, word embedding, and association pattern finding, the results are as good as or better than that from using outputs of a supervised segmentation method. PMID:27185919
Fusion of footsteps and face biometrics on an unsupervised and uncontrolled environment

NASA Astrophysics Data System (ADS)

Vera-Rodriguez, Ruben; Tome, Pedro; Fierrez, Julian; Ortega-Garcia, Javier

2012-06-01

This paper reports for the first time experiments on the fusion of footsteps and face on an unsupervised and not controlled environment for person authentication. Footstep recognition is a relatively new biometric based on signals extracted from people walking over floor sensors. The idea of the fusion between footsteps and face starts from the premise that in an area where footstep sensors are installed it is very simple to place a camera to capture also the face of the person that walks over the sensors. This setup may find application in scenarios like ambient assisted living, smart homes, eldercare, or security access. The paper reports a comparative assessment of both biometrics using the same database and experimental protocols. In the experimental work we consider two different applications: smart homes (small group of users with a large set of training data) and security access (larger group of users with a small set of training data) obtaining results of 0.9% and 5.8% EER respectively for the fusion of both modalities. This is a significant performance improvement compared with the results obtained by the individual systems.
Unsupervised Extraction of Stable Expression Signatures from Public Compendia with an Ensemble of Neural Networks.

PubMed

Tan, Jie; Doing, Georgia; Lewis, Kimberley A; Price, Courtney E; Chen, Kathleen M; Cady, Kyle C; Perchuk, Barret; Laub, Michael T; Hogan, Deborah A; Greene, Casey S

2017-07-26

Cross-experiment comparisons in public data compendia are challenged by unmatched conditions and technical noise. The ADAGE method, which performs unsupervised integration with denoising autoencoder neural networks, can identify biological patterns, but because ADAGE models, like many neural networks, are over-parameterized, different ADAGE models perform equally well. To enhance model robustness and better build signatures consistent with biological pathways, we developed an ensemble ADAGE (eADAGE) that integrated stable signatures across models. We applied eADAGE to a compendium of Pseudomonas aeruginosa gene expression profiling experiments performed in 78 media. eADAGE revealed a phosphate starvation response controlled by PhoB in media with moderate phosphate and predicted that a second stimulus provided by the sensor kinase, KinB, is required for this PhoB activation. We validated this relationship using both targeted and unbiased genetic approaches. eADAGE, which captures stable biological patterns, enables cross-experiment comparisons that can highlight measured but undiscovered relationships. Copyright © 2017 The Author(s). Published by Elsevier Inc. All rights reserved.
Graph-based unsupervised segmentation algorithm for cultured neuronal networks' structure characterization and modeling.

PubMed

de Santos-Sierra, Daniel; Sendiña-Nadal, Irene; Leyva, Inmaculada; Almendral, Juan A; Ayali, Amir; Anava, Sarit; Sánchez-Ávila, Carmen; Boccaletti, Stefano

2015-06-01

Large scale phase-contrast images taken at high resolution through the life of a cultured neuronal network are analyzed by a graph-based unsupervised segmentation algorithm with a very low computational cost, scaling linearly with the image size. The processing automatically retrieves the whole network structure, an object whose mathematical representation is a matrix in which nodes are identified neurons or neurons' clusters, and links are the reconstructed connections between them. The algorithm is also able to extract any other relevant morphological information characterizing neurons and neurites. More importantly, and at variance with other segmentation methods that require fluorescence imaging from immunocytochemistry techniques, our non invasive measures entitle us to perform a longitudinal analysis during the maturation of a single culture. Such an analysis furnishes the way of individuating the main physical processes underlying the self-organization of the neurons' ensemble into a complex network, and drives the formulation of a phenomenological model yet able to describe qualitatively the overall scenario observed during the culture growth. © 2014 International Society for Advancement of Cytometry.
Unsupervised clustering of gene expression data points at hypoxia as possible trigger for metabolic syndrome.

PubMed

Ptitsyn, Andrey; Hulver, Matthew; Cefalu, William; York, David; Smith, Steven R

2006-12-19

Classification of large volumes of data produced in a microarray experiment allows for the extraction of important clues as to the nature of a disease. Using multi-dimensional unsupervised FOREL (FORmal ELement) algorithm we have re-analyzed three public datasets of skeletal muscle gene expression in connection with insulin resistance and type 2 diabetes (DM2). Our analysis revealed the major line of variation between expression profiles of normal, insulin resistant, and diabetic skeletal muscle. A cluster of most "metabolically sound" samples occupied one end of this line. The distance along this line coincided with the classic markers of diabetes risk, namely obesity and insulin resistance, but did not follow the accepted clinical diagnosis of DM2 as defined by the presence or absence of hyperglycemia. Genes implicated in this expression pattern are those controlling skeletal muscle fiber type and glycolytic metabolism. Additionally myoglobin and hemoglobin were upregulated and ribosomal genes deregulated in insulin resistant patients. Our findings are concordant with the changes seen in skeletal muscle with altitude hypoxia. This suggests that hypoxia and shift to glycolytic metabolism may also drive insulin resistance.
Unsupervised Pathological Area Extraction using 3D T2 and FLAIR MR Images

NASA Astrophysics Data System (ADS)

Dvořák, Pavel; Bartušek, Karel; Smékal, Zdeněk

2014-12-01

This work discusses fully automated extraction of brain tumor and edema in 3D MR volumes. The goal of this work is the extraction of the whole pathological area using such an algorithm that does not require a human intervention. For the good visibility of these kinds of tissues both T2-weighted and FLAIR images were used. The proposed method was tested on 80 MR volumes of publicly available BRATS database, which contains high and low grade gliomas, both real and simulated. The performance was evaluated by the Dice coefficient, where the results were differentiated between high and low grade and real and simulated gliomas. The method reached promising results for all of the combinations of images: real high grade (0.73 ± 0.20), real low grade (0.81 ± 0.06), simulated high grade (0.81 ± 0.14), and simulated low grade (0.81 ± 0.04).
Spectral analysis of stellar light curves by means of neural networks

NASA Astrophysics Data System (ADS)

Tagliaferri, R.; Ciaramella, A.; Milano, L.; Barone, F.; Longo, G.

1999-06-01

Periodicity analysis of unevenly collected data is a relevant issue in several scientific fields. In astrophysics, for example, we have to find the fundamental period of light or radial velocity curves which are unevenly sampled observations of stars. Classical spectral analysis methods are unsatisfactory to solve the problem. In this paper we present a neural network based estimator system which performs well the frequency extraction in unevenly sampled signals. It uses an unsupervised Hebbian nonlinear neural algorithm to extract, from the interpolated signal, the principal components which, in turn, are used by the MUSIC frequency estimator algorithm to extract the frequencies. The neural network is tolerant to noise and works well also with few points in the sequence. We benchmark the system on synthetic and real signals with the Periodogram and with the Cramer-Rao lower bound. This work was been partially supported by IIASS, by MURST 40\\% and by the Italian Space Agency.
Quantification of Hepatorenal Index for Computer-Aided Fatty Liver Classification with Self-Organizing Map and Fuzzy Stretching from Ultrasonography.

PubMed

Kim, Kwang Baek; Kim, Chang Won

2015-01-01

Accurate measures of liver fat content are essential for investigating hepatic steatosis. For a noninvasive inexpensive ultrasonographic analysis, it is necessary to validate the quantitative assessment of liver fat content so that fully automated reliable computer-aided software can assist medical practitioners without any operator subjectivity. In this study, we attempt to quantify the hepatorenal index difference between the liver and the kidney with respect to the multiple severity status of hepatic steatosis. In order to do this, a series of carefully designed image processing techniques, including fuzzy stretching and edge tracking, are applied to extract regions of interest. Then, an unsupervised neural learning algorithm, the self-organizing map, is designed to establish characteristic clusters from the image, and the distribution of the hepatorenal index values with respect to the different levels of the fatty liver status is experimentally verified to estimate the differences in the distribution of the hepatorenal index. Such findings will be useful in building reliable computer-aided diagnostic software if combined with a good set of other characteristic feature sets and powerful machine learning classifiers in the future.
Quantum neural network-based EEG filtering for a brain-computer interface.

PubMed

Gandhi, Vaibhav; Prasad, Girijesh; Coyle, Damien; Behera, Laxmidhar; McGinnity, Thomas Martin

2014-02-01

A novel neural information processing architecture inspired by quantum mechanics and incorporating the well-known Schrodinger wave equation is proposed in this paper. The proposed architecture referred to as recurrent quantum neural network (RQNN) can characterize a nonstationary stochastic signal as time-varying wave packets. A robust unsupervised learning algorithm enables the RQNN to effectively capture the statistical behavior of the input signal and facilitates the estimation of signal embedded in noise with unknown characteristics. The results from a number of benchmark tests show that simple signals such as dc, staircase dc, and sinusoidal signals embedded within high noise can be accurately filtered and particle swarm optimization can be employed to select model parameters. The RQNN filtering procedure is applied in a two-class motor imagery-based brain-computer interface where the objective was to filter electroencephalogram (EEG) signals before feature extraction and classification to increase signal separability. A two-step inner-outer fivefold cross-validation approach is utilized to select the algorithm parameters subject-specifically for nine subjects. It is shown that the subject-specific RQNN EEG filtering significantly improves brain-computer interface performance compared to using only the raw EEG or Savitzky-Golay filtered EEG across multiple sessions.
An improved real time image detection system for elephant intrusion along the forest border areas.

PubMed

Sugumar, S J; Jayaparvathy, R

2014-01-01

Human-elephant conflict is a major problem leading to crop damage, human death and injuries caused by elephants, and elephants being killed by humans. In this paper, we propose an automated unsupervised elephant image detection system (EIDS) as a solution to human-elephant conflict in the context of elephant conservation. The elephant's image is captured in the forest border areas and is sent to a base station via an RF network. The received image is decomposed using Haar wavelet to obtain multilevel wavelet coefficients, with which we perform image feature extraction and similarity match between the elephant query image and the database image using image vision algorithms. A GSM message is sent to the forest officials indicating that an elephant has been detected in the forest border and is approaching human habitat. We propose an optimized distance metric to improve the image retrieval time from the database. We compare the optimized distance metric with the popular Euclidean and Manhattan distance methods. The proposed optimized distance metric retrieves more images with lesser retrieval time than the other distance metrics which makes the optimized distance method more efficient and reliable.
Quantification of Hepatorenal Index for Computer-Aided Fatty Liver Classification with Self-Organizing Map and Fuzzy Stretching from Ultrasonography

PubMed Central

Kim, Kwang Baek

2015-01-01

Accurate measures of liver fat content are essential for investigating hepatic steatosis. For a noninvasive inexpensive ultrasonographic analysis, it is necessary to validate the quantitative assessment of liver fat content so that fully automated reliable computer-aided software can assist medical practitioners without any operator subjectivity. In this study, we attempt to quantify the hepatorenal index difference between the liver and the kidney with respect to the multiple severity status of hepatic steatosis. In order to do this, a series of carefully designed image processing techniques, including fuzzy stretching and edge tracking, are applied to extract regions of interest. Then, an unsupervised neural learning algorithm, the self-organizing map, is designed to establish characteristic clusters from the image, and the distribution of the hepatorenal index values with respect to the different levels of the fatty liver status is experimentally verified to estimate the differences in the distribution of the hepatorenal index. Such findings will be useful in building reliable computer-aided diagnostic software if combined with a good set of other characteristic feature sets and powerful machine learning classifiers in the future. PMID:26247023
Big Data Analytics for Scanning Transmission Electron Microscopy Ptychography

DOE Office of Scientific and Technical Information (OSTI.GOV)

Jesse, S.; Chi, M.; Belianinov, A.

Electron microscopy is undergoing a transition; from the model of producing only a few micrographs, through the current state where many images and spectra can be digitally recorded, to a new mode where very large volumes of data (movies, ptychographic and multi-dimensional series) can be rapidly obtained. In this paper, we discuss the application of so-called “big-data” methods to high dimensional microscopy data, using unsupervised multivariate statistical techniques, in order to explore salient image features in a specific example of BiFeO 3 domains. Remarkably, k-means clustering reveals domain differentiation despite the fact that the algorithm is purely statistical in naturemore » and does not require any prior information regarding the material, any coexisting phases, or any differentiating structures. While this is a somewhat trivial case, this example signifies the extraction of useful physical and structural information without any prior bias regarding the sample or the instrumental modality. Further interpretation of these types of results may still require human intervention. Finally, however, the open nature of this algorithm and its wide availability, enable broad collaborations and exploratory work necessary to enable efficient data analysis in electron microscopy.« less
Semi-supervised manifold learning with affinity regularization for Alzheimer's disease identification using positron emission tomography imaging.

PubMed

Lu, Shen; Xia, Yong; Cai, Tom Weidong; Feng, David Dagan

2015-01-01

Dementia, Alzheimer's disease (AD) in particular is a global problem and big threat to the aging population. An image based computer-aided dementia diagnosis method is needed to providing doctors help during medical image examination. Many machine learning based dementia classification methods using medical imaging have been proposed and most of them achieve accurate results. However, most of these methods make use of supervised learning requiring fully labeled image dataset, which usually is not practical in real clinical environment. Using large amount of unlabeled images can improve the dementia classification performance. In this study we propose a new semi-supervised dementia classification method based on random manifold learning with affinity regularization. Three groups of spatial features are extracted from positron emission tomography (PET) images to construct an unsupervised random forest which is then used to regularize the manifold learning objective function. The proposed method, stat-of-the-art Laplacian support vector machine (LapSVM) and supervised SVM are applied to classify AD and normal controls (NC). The experiment results show that learning with unlabeled images indeed improves the classification performance. And our method outperforms LapSVM on the same dataset.
Big Data Analytics for Scanning Transmission Electron Microscopy Ptychography

DOE PAGES

Jesse, S.; Chi, M.; Belianinov, A.; ...

2016-05-23

Electron microscopy is undergoing a transition; from the model of producing only a few micrographs, through the current state where many images and spectra can be digitally recorded, to a new mode where very large volumes of data (movies, ptychographic and multi-dimensional series) can be rapidly obtained. In this paper, we discuss the application of so-called “big-data” methods to high dimensional microscopy data, using unsupervised multivariate statistical techniques, in order to explore salient image features in a specific example of BiFeO 3 domains. Remarkably, k-means clustering reveals domain differentiation despite the fact that the algorithm is purely statistical in naturemore » and does not require any prior information regarding the material, any coexisting phases, or any differentiating structures. While this is a somewhat trivial case, this example signifies the extraction of useful physical and structural information without any prior bias regarding the sample or the instrumental modality. Further interpretation of these types of results may still require human intervention. Finally, however, the open nature of this algorithm and its wide availability, enable broad collaborations and exploratory work necessary to enable efficient data analysis in electron microscopy.« less
nala: text mining natural language mutation mentions

PubMed Central

Cejuela, Juan Miguel; Bojchevski, Aleksandar; Uhlig, Carsten; Bekmukhametov, Rustem; Kumar Karn, Sanjeev; Mahmuti, Shpend; Baghudana, Ashish; Dubey, Ankit; Satagopam, Venkata P.; Rost, Burkhard

2017-01-01

Abstract Motivation: The extraction of sequence variants from the literature remains an important task. Existing methods primarily target standard (ST) mutation mentions (e.g. ‘E6V’), leaving relevant mentions natural language (NL) largely untapped (e.g. ‘glutamic acid was substituted by valine at residue 6’). Results: We introduced three new corpora suggesting named-entity recognition (NER) to be more challenging than anticipated: 28–77% of all articles contained mentions only available in NL. Our new method nala captured NL and ST by combining conditional random fields with word embedding features learned unsupervised from the entire PubMed. In our hands, nala substantially outperformed the state-of-the-art. For instance, we compared all unique mentions in new discoveries correctly detected by any of three methods (SETH, tmVar, or nala). Neither SETH nor tmVar discovered anything missed by nala, while nala uniquely tagged 33% mentions. For NL mentions the corresponding value shot up to 100% nala-only. Availability and Implementation: Source code, API and corpora freely available at: http://tagtog.net/-corpora/IDP4+. Contact: nala@rostlab.org Supplementary information: Supplementary data are available at Bioinformatics online. PMID:28200120

Big Data Analytics for Scanning Transmission Electron Microscopy Ptychography

PubMed Central

Jesse, S.; Chi, M.; Belianinov, A.; Beekman, C.; Kalinin, S. V.; Borisevich, A. Y.; Lupini, A. R.

2016-01-01

Electron microscopy is undergoing a transition; from the model of producing only a few micrographs, through the current state where many images and spectra can be digitally recorded, to a new mode where very large volumes of data (movies, ptychographic and multi-dimensional series) can be rapidly obtained. Here, we discuss the application of so-called “big-data” methods to high dimensional microscopy data, using unsupervised multivariate statistical techniques, in order to explore salient image features in a specific example of BiFeO3 domains. Remarkably, k-means clustering reveals domain differentiation despite the fact that the algorithm is purely statistical in nature and does not require any prior information regarding the material, any coexisting phases, or any differentiating structures. While this is a somewhat trivial case, this example signifies the extraction of useful physical and structural information without any prior bias regarding the sample or the instrumental modality. Further interpretation of these types of results may still require human intervention. However, the open nature of this algorithm and its wide availability, enable broad collaborations and exploratory work necessary to enable efficient data analysis in electron microscopy. PMID:27211523
Noninvasive Dissection of Mouse Sleep Using a Piezoelectric Motion Sensor

PubMed Central

Yaghouby, Farid; Donohue, Kevin D.; O’Hara, Bruce F.; Sunderam, Sridhar

2015-01-01

Background Changes in autonomic control cause regular breathing during NREM sleep to fluctuate during REM. Piezoelectric cage-floor sensors have been used to successfully discriminate sleep and wake states in mice based on signal features related to respiration and other movements. This study presents a classifier for noninvasively classifying REM and NREM using a piezoelectric sensor. New Method Vigilance state was scored manually in 4-second epochs for 24-hour EEG/EMG recordings in twenty mice. An unsupervised classifier clustered piezoelectric signal features quantifying movement and respiration into three states: one active; and two inactive with regular and irregular breathing respectively. These states were hypothesized to correspond to Wake, NREM, and REM respectively. States predicted by the classifier were compared against manual EEG/EMG scores to test this hypothesis. Results Using only piezoelectric signal features, an unsupervised classifier distinguished Wake with high (89% sensitivity, 96% specificity) and REM with moderate (73% sensitivity, 75% specificity) accuracy, but NREM with poor sensitivity (51%) and high specificity (96%). The classifier sometimes confused light NREM sleep—characterized by irregular breathing and moderate delta EEG power—with REM. A supervised classifier improved sensitivities to 90, 81, and 67% and all specificities to over 90% for Wake, NREM, and REM respectively. Comparison with Existing Methods Unlike most actigraphic techniques, which only differentiate sleep from wake, the proposed piezoelectric method further dissects sleep based on breathing regularity into states strongly correlated with REM and NREM. Conclusions This approach could facilitate large-sample screening for genes influencing different sleep traits, besides drug studies or other manipulations. PMID:26582569
Novel Histogram Based Unsupervised Classification Technique to Determine Natural Classes From Biophysically Relevant Fit Parameters to Hyperspectral Data

DOE PAGES

McCann, Cooper; Repasky, Kevin S.; Morin, Mikindra; ...

2017-05-23

Hyperspectral image analysis has benefited from an array of methods that take advantage of the increased spectral depth compared to multispectral sensors; however, the focus of these developments has been on supervised classification methods. Lack of a priori knowledge regarding land cover characteristics can make unsupervised classification methods preferable under certain circumstances. An unsupervised classification technique is presented in this paper that utilizes physically relevant basis functions to model the reflectance spectra. These fit parameters used to generate the basis functions allow clustering based on spectral characteristics rather than spectral channels and provide both noise and data reduction. Histogram splittingmore » of the fit parameters is then used as a means of producing an unsupervised classification. Unlike current unsupervised classification techniques that rely primarily on Euclidian distance measures to determine similarity, the unsupervised classification technique uses the natural splitting of the fit parameters associated with the basis functions creating clusters that are similar in terms of physical parameters. The data set used in this work utilizes the publicly available data collected at Indian Pines, Indiana. This data set provides reference data allowing for comparisons of the efficacy of different unsupervised data analysis. The unsupervised histogram splitting technique presented in this paper is shown to be better than the standard unsupervised ISODATA clustering technique with an overall accuracy of 34.3/19.0% before merging and 40.9/39.2% after merging. Finally, this improvement is also seen as an improvement of kappa before/after merging of 24.8/30.5 for the histogram splitting technique compared to 15.8/28.5 for ISODATA.« less
Novel Histogram Based Unsupervised Classification Technique to Determine Natural Classes From Biophysically Relevant Fit Parameters to Hyperspectral Data

DOE Office of Scientific and Technical Information (OSTI.GOV)

McCann, Cooper; Repasky, Kevin S.; Morin, Mikindra

Hyperspectral image analysis has benefited from an array of methods that take advantage of the increased spectral depth compared to multispectral sensors; however, the focus of these developments has been on supervised classification methods. Lack of a priori knowledge regarding land cover characteristics can make unsupervised classification methods preferable under certain circumstances. An unsupervised classification technique is presented in this paper that utilizes physically relevant basis functions to model the reflectance spectra. These fit parameters used to generate the basis functions allow clustering based on spectral characteristics rather than spectral channels and provide both noise and data reduction. Histogram splittingmore » of the fit parameters is then used as a means of producing an unsupervised classification. Unlike current unsupervised classification techniques that rely primarily on Euclidian distance measures to determine similarity, the unsupervised classification technique uses the natural splitting of the fit parameters associated with the basis functions creating clusters that are similar in terms of physical parameters. The data set used in this work utilizes the publicly available data collected at Indian Pines, Indiana. This data set provides reference data allowing for comparisons of the efficacy of different unsupervised data analysis. The unsupervised histogram splitting technique presented in this paper is shown to be better than the standard unsupervised ISODATA clustering technique with an overall accuracy of 34.3/19.0% before merging and 40.9/39.2% after merging. Finally, this improvement is also seen as an improvement of kappa before/after merging of 24.8/30.5 for the histogram splitting technique compared to 15.8/28.5 for ISODATA.« less
Unsupervised learning toward brain imaging data analysis: cigarette craving and resistance related neuronal activations from functional magnetic resonance imaging data analysis

NASA Astrophysics Data System (ADS)

Kim, Dong-Youl; Lee, Jong-Hwan

2014-05-01

A data-driven unsupervised learning such as an independent component analysis was gainfully applied to bloodoxygenation- level-dependent (BOLD) functional magnetic resonance imaging (fMRI) data compared to a model-based general linear model (GLM). This is due to an ability of this unsupervised learning method to extract a meaningful neuronal activity from BOLD signal that is a mixture of confounding non-neuronal artifacts such as head motions and physiological artifacts as well as neuronal signals. In this study, we support this claim by identifying neuronal underpinnings of cigarette craving and cigarette resistance. The fMRI data were acquired from heavy cigarette smokers (n = 14) while they alternatively watched images with and without cigarette smoking. During acquisition of two fMRI runs, they were asked to crave when they watched cigarette smoking images or to resist the urge to smoke. Data driven approaches of group independent component analysis (GICA) method based on temporal concatenation (TC) and TCGICA with an extension of iterative dual-regression (TC-GICA-iDR) were applied to the data. From the results, cigarette craving and cigarette resistance related neuronal activations were identified in the visual area and superior frontal areas, respectively with a greater statistical significance from the TC-GICA-iDR method than the TC-GICA method. On the other hand, the neuronal activity levels in many of these regions were not statistically different from the GLM method between the cigarette craving and cigarette resistance due to potentially aberrant BOLD signals.
Unsupervised neural spike sorting for high-density microelectrode arrays with convolutive independent component analysis.

PubMed

Leibig, Christian; Wachtler, Thomas; Zeck, Günther

2016-09-15

Unsupervised identification of action potentials in multi-channel extracellular recordings, in particular from high-density microelectrode arrays with thousands of sensors, is an unresolved problem. While independent component analysis (ICA) achieves rapid unsupervised sorting, it ignores the convolutive structure of extracellular data, thus limiting the unmixing to a subset of neurons. Here we present a spike sorting algorithm based on convolutive ICA (cICA) to retrieve a larger number of accurately sorted neurons than with instantaneous ICA while accounting for signal overlaps. Spike sorting was applied to datasets with varying signal-to-noise ratios (SNR: 3-12) and 27% spike overlaps, sampled at either 11.5 or 23kHz on 4365 electrodes. We demonstrate how the instantaneity assumption in ICA-based algorithms has to be relaxed in order to improve the spike sorting performance for high-density microelectrode array recordings. Reformulating the convolutive mixture as an instantaneous mixture by modeling several delayed samples jointly is necessary to increase signal-to-noise ratio. Our results emphasize that different cICA algorithms are not equivalent. Spike sorting performance was assessed with ground-truth data generated from experimentally derived templates. The presented spike sorter was able to extract ≈90% of the true spike trains with an error rate below 2%. It was superior to two alternative (c)ICA methods (≈80% accurately sorted neurons) and comparable to a supervised sorting. Our new algorithm represents a fast solution to overcome the current bottleneck in spike sorting of large datasets generated by simultaneous recording with thousands of electrodes. Copyright © 2016 Elsevier B.V. All rights reserved.
Unsupervised Categorization in a Sample of Children with Autism Spectrum Disorders

ERIC Educational Resources Information Center

Edwards, Darren J.; Perlman, Amotz; Reed, Phil

2012-01-01

Studies of supervised Categorization have demonstrated limited Categorization performance in participants with autism spectrum disorders (ASD), however little research has been conducted regarding unsupervised Categorization in this population. This study explored unsupervised Categorization using two stimulus sets that differed in their…
Incremental Ontology-Based Extraction and Alignment in Semi-structured Documents

NASA Astrophysics Data System (ADS)

Thiam, Mouhamadou; Bennacer, Nacéra; Pernelle, Nathalie; Lô, Moussa

SHIRIis an ontology-based system for integration of semi-structured documents related to a specific domain. The system’s purpose is to allow users to access to relevant parts of documents as answers to their queries. SHIRI uses RDF/OWL for representation of resources and SPARQL for their querying. It relies on an automatic, unsupervised and ontology-driven approach for extraction, alignment and semantic annotation of tagged elements of documents. In this paper, we focus on the Extract-Align algorithm which exploits a set of named entity and term patterns to extract term candidates to be aligned with the ontology. It proceeds in an incremental manner in order to populate the ontology with terms describing instances of the domain and to reduce the access to extern resources such as Web. We experiment it on a HTML corpus related to call for papers in computer science and the results that we obtain are very promising. These results show how the incremental behaviour of Extract-Align algorithm enriches the ontology and the number of terms (or named entities) aligned directly with the ontology increases.
Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP.

PubMed

Shim, Yoonsik; Philippides, Andrew; Staras, Kevin; Husbands, Phil

2016-10-01

We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP). The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM) networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture.
Methods for automatic detection of artifacts in microelectrode recordings.

PubMed

Bakštein, Eduard; Sieger, Tomáš; Wild, Jiří; Novák, Daniel; Schneider, Jakub; Vostatek, Pavel; Urgošík, Dušan; Jech, Robert

2017-10-01

Extracellular microelectrode recording (MER) is a prominent technique for studies of extracellular single-unit neuronal activity. In order to achieve robust results in more complex analysis pipelines, it is necessary to have high quality input data with a low amount of artifacts. We show that noise (mainly electromagnetic interference and motion artifacts) may affect more than 25% of the recording length in a clinical MER database. We present several methods for automatic detection of noise in MER signals, based on (i) unsupervised detection of stationary segments, (ii) large peaks in the power spectral density, and (iii) a classifier based on multiple time- and frequency-domain features. We evaluate the proposed methods on a manually annotated database of 5735 ten-second MER signals from 58 Parkinson's disease patients. The existing methods for artifact detection in single-channel MER that have been rigorously tested, are based on unsupervised change-point detection. We show on an extensive real MER database that the presented techniques are better suited for the task of artifact identification and achieve much better results. The best-performing classifiers (bagging and decision tree) achieved artifact classification accuracy of up to 89% on an unseen test set and outperformed the unsupervised techniques by 5-10%. This was close to the level of agreement among raters using manual annotation (93.5%). We conclude that the proposed methods are suitable for automatic MER denoising and may help in the efficient elimination of undesirable signal artifacts. Copyright © 2017 Elsevier B.V. All rights reserved.
Machine-Learned Data Structures of Lipid Marker Serum Concentrations in Multiple Sclerosis Patients Differ from Those in Healthy Subjects.

PubMed

Lötsch, Jörn; Thrun, Michael; Lerch, Florian; Brunkhorst, Robert; Schiffmann, Susanne; Thomas, Dominique; Tegder, Irmgard; Geisslinger, Gerd; Ultsch, Alfred

2017-06-07

Lipid metabolism has been suggested to be a major pathophysiological mechanism of multiple sclerosis (MS). With the increasing knowledge about lipid signaling, acquired data become increasingly complex making bioinformatics necessary in lipid research. We used unsupervised machine-learning to analyze lipid marker serum concentrations, pursuing the hypothesis that for the most relevant markers the emerging data structures will coincide with the diagnosis of MS. Machine learning was implemented as emergent self-organizing feature maps (ESOM) combined with the U*-matrix visualization technique. The data space consisted of serum concentrations of three main classes of lipid markers comprising eicosanoids ( d = 11 markers), ceramides ( d = 10), and lyosophosphatidic acids ( d = 6). They were analyzed in cohorts of MS patients ( n = 102) and healthy subjects ( n = 301). Clear data structures in the high-dimensional data space were observed in eicosanoid and ceramides serum concentrations whereas no clear structure could be found in lysophosphatidic acid concentrations. With ceramide concentrations, the structures that had emerged from unsupervised machine-learning almost completely overlapped with the known grouping of MS patients versus healthy subjects. This was only partly provided by eicosanoid serum concentrations. Thus, unsupervised machine-learning identified distinct data structures of bioactive lipid serum concentrations. These structures could be superimposed with the known grouping of MS patients versus healthy subjects, which was almost completely possible with ceramides. Therefore, based on the present analysis, ceramides are first-line candidates for further exploration as drug-gable targets or biomarkers in MS.
Detection of molecular signatures of oral squamous cell carcinoma and normal epithelium - application of a novel methodology for unsupervised segmentation of imaging mass spectrometry data.

PubMed

Widlak, Piotr; Mrukwa, Grzegorz; Kalinowska, Magdalena; Pietrowska, Monika; Chekan, Mykola; Wierzgon, Janusz; Gawin, Marta; Drazek, Grzegorz; Polanska, Joanna

2016-06-01

Intra-tumor heterogeneity is a vivid problem of molecular oncology that could be addressed by imaging mass spectrometry. Here we aimed to assess molecular heterogeneity of oral squamous cell carcinoma and to detect signatures discriminating normal and cancerous epithelium. Tryptic peptides were analyzed by MALDI-IMS in tissue specimens from five patients with oral cancer. Novel algorithm of IMS data analysis was developed and implemented, which included Gaussian mixture modeling for detection of spectral components and iterative k-means algorithm for unsupervised spectra clustering performed in domain reduced to a subset of the most dispersed components. About 4% of the detected peptides showed significantly different abundances between normal epithelium and tumor, and could be considered as a molecular signature of oral cancer. Moreover, unsupervised clustering revealed two major sub-regions within expert-defined tumor areas. One of them showed molecular similarity with histologically normal epithelium. The other one showed similarity with connective tissue, yet was markedly different from normal epithelium. Pathologist's re-inspection of tissue specimens confirmed distinct features in both tumor sub-regions: foci of actual cancer cells or cancer microenvironment-related cells prevailed in corresponding areas. Hence, molecular differences detected during automated segmentation of IMS data had an apparent reflection in real structures present in tumor. © 2016 The Authors. Proteomics Published by Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim.
Classification and analysis of the Rudaki's Area

NASA Astrophysics Data System (ADS)

Zambon, F.; De sanctis, M.; Capaccioni, F.; Filacchione, G.; Carli, C.; Ammannito, E.; Frigeri, A.

2011-12-01

During the first two MESSENGER flybys the Mercury Dual Imaging System (MDIS) has mapped 90% of the Mercury's surface. An effective way to study the different terrain on planetary surfaces is to apply classification methods. These are based on clustering algorithms and they can be divided in two categories: unsupervised and supervised. The unsupervised classifiers do not require the analyst feedback and the algorithm automatically organizes pixels values into classes. In the supervised method, instead, the analyst must choose the "training area" that define the pixels value of a given class. We applied an unsupervised classifier, ISODATA, to the WAC filter images of the Rudaki's area where several kind of terrain have been identified showing differences in albedo, topography and crater density. ISODATA classifier divides this region in four classes: 1) shadow regions, 2) rough regions, 3) smooth plane, 4) highest reflectance area. ISODATA can not distinguish the high albedo regions from highly reflective illuminated edge of the craters, however the algorithm identify four classes that can be considered different units mainly on the basis of their reflectances at the various wavelengths. Is not possible, instead, to extrapolate compositional information because of the absence of clear spectral features. An additional analysis was made using ISODATA to choose the "training area" for further supervised classifications. These approach would allow, for example, to separate more accurately the edge of the craters from the high reflectance areas and the low reflectance regions from the shadow areas.
Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP

PubMed Central

Staras, Kevin

2016-01-01

We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP). The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM) networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture. PMID:27760125
Availability of MudPIT data for classification of biological samples.

PubMed

Silvestre, Dario Di; Zoppis, Italo; Brambilla, Francesca; Bellettato, Valeria; Mauri, Giancarlo; Mauri, Pierluigi

2013-01-14

Mass spectrometry is an important analytical tool for clinical proteomics. Primarily employed for biomarker discovery, it is increasingly used for developing methods which may help to provide unambiguous diagnosis of biological samples. In this context, we investigated the classification of phenotypes by applying support vector machine (SVM) on experimental data obtained by MudPIT approach. In particular, we compared the performance capabilities of SVM by using two independent collection of complex samples and different data-types, such as mass spectra (m/z), peptides and proteins. Globally, protein and peptide data allowed a better discriminant informative content than experimental mass spectra (overall accuracy higher than 87% in both collection 1 and 2). These results indicate that sequencing of peptides and proteins reduces the experimental noise affecting the raw mass spectra, and allows the extraction of more informative features available for the effective classification of samples. In addition, proteins and peptides features selected by SVM matched for 80% with the differentially expressed proteins identified by the MAProMa software. These findings confirm the availability of the most label-free quantitative methods based on processing of spectral count and SEQUEST-based SCORE values. On the other hand, it stresses the usefulness of MudPIT data for a correct grouping of sample phenotypes, by applying both supervised and unsupervised learning algorithms. This capacity permit the evaluation of actual samples and it is a good starting point to translate proteomic methodology to clinical application.
Topographic attributes as a guide for automated detection or highlighting of geological features

NASA Astrophysics Data System (ADS)

Viseur, Sophie; Le Men, Thibaud; Guglielmi, Yves

2015-04-01

Photogrammetry or LIDAR technology combined with photography allow geoscientists to obtain 3D high-resolution numerical representations of outcrops, generally termed as Digital Outcrop Models (DOM). For over a decade, these 3D numerical outcrops serve as support for precise and accurate interpretations of geological features such as fracture traces or plans, strata, facies mapping, etc. These interpretations have the benefit to be directly georeferenced and embedded into the 3D space. They are then easily integrated into GIS or geomodeler softwares for modelling in 3D the subsurface geological structures. However, numerical outcrops generally represent huge data sets that are heavy to manipulate and hence to interpret. This may be particularly tedious as soon as several scales of geological features must be investigated or as geological features are very dense and imbricated. Automated tools for interpreting geological features from DOMs would be then a significant help to process these kinds of data. Such technologies are commonly used for interpreting seismic or medical data. However, it may be noticed that even if many efforts have been devoted to easily and accurately acquire 3D topographic point clouds and photos and to visualize accurate 3D textured DOMs, few attentions have been paid to the development of algorithms for automated detection of the geological structures from DOMs. The automatic detection of objects on numerical data generally assumes that signals or attributes computed from this data allows the recognition of the targeted object boundaries. The first step consists then in defining attributes that highlight the objects or their boundaries. For DOM interpretations, some authors proposed to use differential operators computed on the surface such as normal or curvatures. These methods generally extract polylines corresponding to fracture traces or bed limits. Other approaches rely on the PCA technology to segregate different topographic plans. This approach assume that structural or sedimentary features coincide with topographic surface parts. In this work, several topographic attributes are proposed to highlight geological features on outcrops. Among them, differential operators are used but also combined and processed to display particular topographic shapes. Moreover, two kinds of attributes are used: unsupervised and supervised attributes. The supervised attributes integrate an a priori knowledge about the objects to extract (e.g.: a preferential orientation of fracture surfaces, etc.). This strategy may be compared to the one used for seismic interpretation. Indeed, many seismic attributes have been proposed to highlight geological structures hardly observable due to data noise. The same issue exist with topographic data: plants, erosions, etc. generate noise that make interpretation sometimes hard. The proposed approach has been applied on real case studies to show how it could help the interpretation of geological features. The obtained 'topographic attributes' are shown and discussed.
Spatiotemporal information during unsupervised learning enhances viewpoint invariant object recognition

PubMed Central

Tian, Moqian; Grill-Spector, Kalanit

2015-01-01

Recognizing objects is difficult because it requires both linking views of an object that can be different and distinguishing objects with similar appearance. Interestingly, people can learn to recognize objects across views in an unsupervised way, without feedback, just from the natural viewing statistics. However, there is intense debate regarding what information during unsupervised learning is used to link among object views. Specifically, researchers argue whether temporal proximity, motion, or spatiotemporal continuity among object views during unsupervised learning is beneficial. Here, we untangled the role of each of these factors in unsupervised learning of novel three-dimensional (3-D) objects. We found that after unsupervised training with 24 object views spanning a 180° view space, participants showed significant improvement in their ability to recognize 3-D objects across rotation. Surprisingly, there was no advantage to unsupervised learning with spatiotemporal continuity or motion information than training with temporal proximity. However, we discovered that when participants were trained with just a third of the views spanning the same view space, unsupervised learning via spatiotemporal continuity yielded significantly better recognition performance on novel views than learning via temporal proximity. These results suggest that while it is possible to obtain view-invariant recognition just from observing many views of an object presented in temporal proximity, spatiotemporal information enhances performance by producing representations with broader view tuning than learning via temporal association. Our findings have important implications for theories of object recognition and for the development of computational algorithms that learn from examples. PMID:26024454
Integrative Data Analysis of Multi-Platform Cancer Data with a Multimodal Deep Learning Approach.

PubMed

Liang, Muxuan; Li, Zhizhong; Chen, Ting; Zeng, Jianyang

2015-01-01

Identification of cancer subtypes plays an important role in revealing useful insights into disease pathogenesis and advancing personalized therapy. The recent development of high-throughput sequencing technologies has enabled the rapid collection of multi-platform genomic data (e.g., gene expression, miRNA expression, and DNA methylation) for the same set of tumor samples. Although numerous integrative clustering approaches have been developed to analyze cancer data, few of them are particularly designed to exploit both deep intrinsic statistical properties of each input modality and complex cross-modality correlations among multi-platform input data. In this paper, we propose a new machine learning model, called multimodal deep belief network (DBN), to cluster cancer patients from multi-platform observation data. In our integrative clustering framework, relationships among inherent features of each single modality are first encoded into multiple layers of hidden variables, and then a joint latent model is employed to fuse common features derived from multiple input modalities. A practical learning algorithm, called contrastive divergence (CD), is applied to infer the parameters of our multimodal DBN model in an unsupervised manner. Tests on two available cancer datasets show that our integrative data analysis approach can effectively extract a unified representation of latent features to capture both intra- and cross-modality correlations, and identify meaningful disease subtypes from multi-platform cancer data. In addition, our approach can identify key genes and miRNAs that may play distinct roles in the pathogenesis of different cancer subtypes. Among those key miRNAs, we found that the expression level of miR-29a is highly correlated with survival time in ovarian cancer patients. These results indicate that our multimodal DBN based data analysis approach may have practical applications in cancer pathogenesis studies and provide useful guidelines for personalized cancer therapy.
Improving EEG-Based Driver Fatigue Classification Using Sparse-Deep Belief Networks.

PubMed

Chai, Rifai; Ling, Sai Ho; San, Phyo Phyo; Naik, Ganesh R; Nguyen, Tuan N; Tran, Yvonne; Craig, Ashley; Nguyen, Hung T

2017-01-01

This paper presents an improvement of classification performance for electroencephalography (EEG)-based driver fatigue classification between fatigue and alert states with the data collected from 43 participants. The system employs autoregressive (AR) modeling as the features extraction algorithm, and sparse-deep belief networks (sparse-DBN) as the classification algorithm. Compared to other classifiers, sparse-DBN is a semi supervised learning method which combines unsupervised learning for modeling features in the pre-training layer and supervised learning for classification in the following layer. The sparsity in sparse-DBN is achieved with a regularization term that penalizes a deviation of the expected activation of hidden units from a fixed low-level prevents the network from overfitting and is able to learn low-level structures as well as high-level structures. For comparison, the artificial neural networks (ANN), Bayesian neural networks (BNN), and original deep belief networks (DBN) classifiers are used. The classification results show that using AR feature extractor and DBN classifiers, the classification performance achieves an improved classification performance with a of sensitivity of 90.8%, a specificity of 90.4%, an accuracy of 90.6%, and an area under the receiver operating curve (AUROC) of 0.94 compared to ANN (sensitivity at 80.8%, specificity at 77.8%, accuracy at 79.3% with AUC-ROC of 0.83) and BNN classifiers (sensitivity at 84.3%, specificity at 83%, accuracy at 83.6% with AUROC of 0.87). Using the sparse-DBN classifier, the classification performance improved further with sensitivity of 93.9%, a specificity of 92.3%, and an accuracy of 93.1% with AUROC of 0.96. Overall, the sparse-DBN classifier improved accuracy by 13.8, 9.5, and 2.5% over ANN, BNN, and DBN classifiers, respectively.
Improving EEG-Based Driver Fatigue Classification Using Sparse-Deep Belief Networks

PubMed Central

Chai, Rifai; Ling, Sai Ho; San, Phyo Phyo; Naik, Ganesh R.; Nguyen, Tuan N.; Tran, Yvonne; Craig, Ashley; Nguyen, Hung T.

2017-01-01

This paper presents an improvement of classification performance for electroencephalography (EEG)-based driver fatigue classification between fatigue and alert states with the data collected from 43 participants. The system employs autoregressive (AR) modeling as the features extraction algorithm, and sparse-deep belief networks (sparse-DBN) as the classification algorithm. Compared to other classifiers, sparse-DBN is a semi supervised learning method which combines unsupervised learning for modeling features in the pre-training layer and supervised learning for classification in the following layer. The sparsity in sparse-DBN is achieved with a regularization term that penalizes a deviation of the expected activation of hidden units from a fixed low-level prevents the network from overfitting and is able to learn low-level structures as well as high-level structures. For comparison, the artificial neural networks (ANN), Bayesian neural networks (BNN), and original deep belief networks (DBN) classifiers are used. The classification results show that using AR feature extractor and DBN classifiers, the classification performance achieves an improved classification performance with a of sensitivity of 90.8%, a specificity of 90.4%, an accuracy of 90.6%, and an area under the receiver operating curve (AUROC) of 0.94 compared to ANN (sensitivity at 80.8%, specificity at 77.8%, accuracy at 79.3% with AUC-ROC of 0.83) and BNN classifiers (sensitivity at 84.3%, specificity at 83%, accuracy at 83.6% with AUROC of 0.87). Using the sparse-DBN classifier, the classification performance improved further with sensitivity of 93.9%, a specificity of 92.3%, and an accuracy of 93.1% with AUROC of 0.96. Overall, the sparse-DBN classifier improved accuracy by 13.8, 9.5, and 2.5% over ANN, BNN, and DBN classifiers, respectively. PMID:28326009

PANTHER. Trajectory Analysis

DOE Office of Scientific and Technical Information (OSTI.GOV)

Rintoul, Mark Daniel; Wilson, Andrew T.; Valicka, Christopher G.

We want to organize a body of trajectories in order to identify, search for, classify and predict behavior among objects such as aircraft and ships. Existing compari- son functions such as the Fr'echet distance are computationally expensive and yield counterintuitive results in some cases. We propose an approach using feature vectors whose components represent succinctly the salient information in trajectories. These features incorporate basic information such as total distance traveled and distance be- tween start/stop points as well as geometric features related to the properties of the convex hull, trajectory curvature and general distance geometry. Additionally, these features can generallymore » be mapped easily to behaviors of interest to humans that are searching large databases. Most of these geometric features are invariant under rigid transformation. We demonstrate the use of different subsets of these features to iden- tify trajectories similar to an exemplar, cluster a database of several hundred thousand trajectories, predict destination and apply unsupervised machine learning algorithms.« less
Using Wikipedia to learn semantic feature representations of concrete concepts in neuroimaging experiments

PubMed Central

Pereira, Francisco; Botvinick, Matthew; Detre, Greg

2012-01-01

In this paper we show that a corpus of a few thousand Wikipedia articles about concrete or visualizable concepts can be used to produce a low-dimensional semantic feature representation of those concepts. The purpose of such a representation is to serve as a model of the mental context of a subject during functional magnetic resonance imaging (fMRI) experiments. A recent study [19] showed that it was possible to predict fMRI data acquired while subjects thought about a concrete concept, given a representation of those concepts in terms of semantic features obtained with human supervision. We use topic models on our corpus to learn semantic features from text in an unsupervised manner, and show that those features can outperform those in [19] in demanding 12-way and 60-way classification tasks. We also show that these features can be used to uncover similarity relations in brain activation for different concepts which parallel those relations in behavioral data from human subjects. PMID:23243317
Predicting category intuitiveness with the rational model, the simplicity model, and the generalized context model.

PubMed

Pothos, Emmanuel M; Bailey, Todd M

2009-07-01

Naïve observers typically perceive some groupings for a set of stimuli as more intuitive than others. The problem of predicting category intuitiveness has been historically considered the remit of models of unsupervised categorization. In contrast, this article develops a measure of category intuitiveness from one of the most widely supported models of supervised categorization, the generalized context model (GCM). Considering different category assignments for a set of instances, the authors asked how well the GCM can predict the classification of each instance on the basis of all the other instances. The category assignment that results in the smallest prediction error is interpreted as the most intuitive for the GCM-the authors refer to this way of applying the GCM as "unsupervised GCM." The authors systematically compared predictions of category intuitiveness from the unsupervised GCM and two models of unsupervised categorization: the simplicity model and the rational model. The unsupervised GCM compared favorably with the simplicity model and the rational model. This success of the unsupervised GCM illustrates that the distinction between supervised and unsupervised categorization may need to be reconsidered. However, no model emerged as clearly superior, indicating that there is more work to be done in understanding and modeling category intuitiveness.
Exploring the time-frequency content of high frequency oscillations for automated identification of seizure onset zone in epilepsy.

PubMed

Liu, Su; Sha, Zhiyi; Sencer, Altay; Aydoseli, Aydin; Bebek, Nerse; Abosch, Aviva; Henry, Thomas; Gurses, Candan; Ince, Nuri Firat

2016-04-01

High frequency oscillations (HFOs) in intracranial electroencephalography (iEEG) recordings are considered as promising clinical biomarkers of epileptogenic regions in the brain. The aim of this study is to improve and automatize the detection of HFOs by exploring the time-frequency content of iEEG and to investigate the seizure onset zone (SOZ) detection accuracy during the sleep, awake and pre-ictal states in patients with epilepsy, for the purpose of assisting the localization of SOZ in clinical practice. Ten-minute iEEG segments were defined during different states in eight patients with refractory epilepsy. A three-stage algorithm was implemented to detect HFOs in these segments. First, an amplitude based initial detection threshold was used to generate a large pool of HFO candidates. Then distinguishing features were extracted from the time and time-frequency domain of the raw iEEG and used with a Gaussian mixture model clustering to isolate HFO events from other activities. The spatial distribution of HFO clusters was correlated with the seizure onset channels identified by neurologists in seven patient with good surgical outcome. The overlapping rates of localized channels and seizure onset locations were high in all states. The best result was obtained using the iEEG data during sleep, achieving a sensitivity of 81%, and a specificity of 96%. The channels with maximum number of HFOs identified epileptogenic areas where the seizures occurred more frequently. The current study was conducted using iEEG data collected in realistic clinical conditions without channel pre-exclusion. HFOs were investigated with novel features extracted from the entire frequency band, and were correlated with SOZ in different states. The results indicate that automatic HFO detection with unsupervised clustering methods exploring the time-frequency content of raw iEEG can be efficiently used to identify the epileptogenic zone with an accurate and efficient manner.
Automatic Detection of Seismocardiogram Sensor Misplacement for Robust Pre-Ejection Period Estimation in Unsupervised Settings.

PubMed

Ashouri, Hazar; Inan, Omer T

2017-06-15

Seismocardiography (SCG), the measurement of the local chest vibrations due to the movements of blood and the heart, is a non-invasive technique for assessing myocardial contractility via the pre-ejection period (PEP). Recently, SCG-based extraction of PEP has been shown to be an effective means of classifying decompensated from compensated heart failure patients, and thus can be potentially used for monitoring such patients at home. Accurate extraction of PEP from SCG signals hinges on lab-based population data (i.e., regression curves) linking particular time-domain features of the SCG signal to corresponding features from reference standard bulky instruments such as impedance cardiography (ICG). Such regression curves, in the case of SCG, have always been estimated based on the "ideal" positioning of the SCG sensor on the chest. However, in settings such as the home where users may position the SCG measurement hardware on the chest without supervision, it is likely that the sensor will not always be placed exactly on this "ideal" location on the sternum, but rather on other positions on the chest as well. In this study, we show for the first time that the regression curve for estimating PEP from SCG signals differs significantly as the position of the sensor changes. We further devise a method to automatically detect when the sensor is placed in any position other than the desired one in order to avoid inaccurate systolic time interval estimation. Our classification algorithm for this purpose resulted in 0.83 precision and 0.82 recall when classifying whether the sensor is placed in the desired position or not. The classifier was tested with heartbeats taken both at rest, and also during exercise recovery to ensure that waveform changes due to positioning could be accurately discriminated from those due to physiological effects.
Hybrid image representation learning model with invariant features for basal cell carcinoma detection

NASA Astrophysics Data System (ADS)

Arevalo, John; Cruz-Roa, Angel; González, Fabio A.

2013-11-01

This paper presents a novel method for basal-cell carcinoma detection, which combines state-of-the-art methods for unsupervised feature learning (UFL) and bag of features (BOF) representation. BOF, which is a form of representation learning, has shown a good performance in automatic histopathology image classi cation. In BOF, patches are usually represented using descriptors such as SIFT and DCT. We propose to use UFL to learn the patch representation itself. This is accomplished by applying a topographic UFL method (T-RICA), which automatically learns visual invariance properties of color, scale and rotation from an image collection. These learned features also reveals these visual properties associated to cancerous and healthy tissues and improves carcinoma detection results by 7% with respect to traditional autoencoders, and 6% with respect to standard DCT representations obtaining in average 92% in terms of F-score and 93% of balanced accuracy.
Image quality classification for DR screening using deep learning.

PubMed

FengLi Yu; Jing Sun; Annan Li; Jun Cheng; Cheng Wan; Jiang Liu

2017-07-01

The quality of input images significantly affects the outcome of automated diabetic retinopathy (DR) screening systems. Unlike the previous methods that only consider simple low-level features such as hand-crafted geometric and structural features, in this paper we propose a novel method for retinal image quality classification (IQC) that performs computational algorithms imitating the working of the human visual system. The proposed algorithm combines unsupervised features from saliency map and supervised features coming from convolutional neural networks (CNN), which are fed to an SVM to automatically detect high quality vs poor quality retinal fundus images. We demonstrate the superior performance of our proposed algorithm on a large retinal fundus image dataset and the method could achieve higher accuracy than other methods. Although retinal images are used in this study, the methodology is applicable to the image quality assessment and enhancement of other types of medical images.
An unsupervised machine learning model for discovering latent infectious diseases using social media data.

PubMed

Lim, Sunghoon; Tucker, Conrad S; Kumara, Soundar

2017-02-01

The authors of this work propose an unsupervised machine learning model that has the ability to identify real-world latent infectious diseases by mining social media data. In this study, a latent infectious disease is defined as a communicable disease that has not yet been formalized by national public health institutes and explicitly communicated to the general public. Most existing approaches to modeling infectious-disease-related knowledge discovery through social media networks are top-down approaches that are based on already known information, such as the names of diseases and their symptoms. In existing top-down approaches, necessary but unknown information, such as disease names and symptoms, is mostly unidentified in social media data until national public health institutes have formalized that disease. Most of the formalizing processes for latent infectious diseases are time consuming. Therefore, this study presents a bottom-up approach for latent infectious disease discovery in a given location without prior information, such as disease names and related symptoms. Social media messages with user and temporal information are extracted during the data preprocessing stage. An unsupervised sentiment analysis model is then presented. Users' expressions about symptoms, body parts, and pain locations are also identified from social media data. Then, symptom weighting vectors for each individual and time period are created, based on their sentiment and social media expressions. Finally, latent-infectious-disease-related information is retrieved from individuals' symptom weighting vectors. Twitter data from August 2012 to May 2013 are used to validate this study. Real electronic medical records for 104 individuals, who were diagnosed with influenza in the same period, are used to serve as ground truth validation. The results are promising, with the highest precision, recall, and F 1 score values of 0.773, 0.680, and 0.724, respectively. This work uses individuals' social media messages to identify latent infectious diseases, without prior information, quicker than when the disease(s) is formalized by national public health institutes. In particular, the unsupervised machine learning model using user, textual, and temporal information in social media data, along with sentiment analysis, identifies latent infectious diseases in a given location. Copyright Â© 2016 Elsevier Inc. All rights reserved.
Supervision and computerized neurocognitive baseline test performance in high school athletes: an initial investigation.

PubMed

Kuhn, Andrew Warren; Solomon, Gary S

2014-01-01

Computerized neuropsychological testing batteries have provided a time-efficient and cost-efficient way to assess and manage the neurocognitive aspects of patients with sport-related concussion. These tests are straightforward and mostly self-guided, reducing the degree of clinician involvement required by traditional clinical neuropsychological paper-and-pencil tests. To determine if self-reported supervision status affected computerized neurocognitive baseline test performance in high school athletes. Retrospective cohort study. Supervised testing took place in high school computer libraries or sports medicine clinics. Unsupervised testing took place at the participant's home or another location with computer access. From 2007 to 2012, high school athletes across middle Tennessee (n = 3771) completed computerized neurocognitive baseline testing (Immediate Post-Concussion Assessment and Cognitive Testing [ImPACT]). They reported taking the test either supervised by a sports medicine professional or unsupervised. These athletes (n = 2140) were subjected to inclusion and exclusion criteria and then matched based on age, sex, and number of prior concussions. We extracted demographic and performance-based data from each de-identified baseline testing record. Paired t tests were performed between the self-reported supervised and unsupervised groups, comparing the following ImPACT baseline composite scores: verbal memory, visual memory, visual motor (processing) speed, reaction time, impulse control, and total symptom score. For differences that reached P < .05, the Cohen d was calculated to measure the effect size. Lastly, a χ(2) analysis was conducted to compare the rate of invalid baseline testing between the groups. All statistical tests were performed at the 95% confidence interval level. Self-reported supervised athletes demonstrated better visual motor (processing) speed (P = .004; 95% confidence interval [0.28, 1.52]; d = 0.12) and faster reaction time (P < .001; 95% confidence interval [-0.026, -0.014]; d = 0.21) composite scores than self-reported unsupervised athletes. Speed-based tasks were most affected by self-reported supervision status, although the effect sizes were relatively small. These data lend credence to the hypothesis that supervision status may be a factor in the evaluation of ImPACT baseline test scores.
The influence of unsupervised time on elementary school children at high risk for inattention and problem behaviors.

PubMed

Na, Kyoung-Sae; Lee, Soyoung Irene; Hong, Hyun Ju; Oh, Myoung-Ja; Bahn, Geon Ho; Ha, Kyunghee; Shin, Yun Mi; Song, Jungeun; Park, Eun Jin; Yoo, Heejung; Kim, Hyunsoo; Kyung, Yun-Mi

2014-06-01

In the last few decades, changing socioeconomic and family structures have increasingly left children alone without adult supervision. Carefully prepared and limited periods of unsupervised time are not harmful for children. However, long unsupervised periods have harmful effects, particularly for those children at high risk for inattention and problem behaviors. In this study, we examined the influence of unsupervised time on behavior problems by studying a sample of elementary school children at high risk for inattention and problem behaviors. The study analyzed data from the Children's Mental Health Promotion Project, which was conducted in collaboration with education, government, and mental health professionals. The child behavior checklist (CBCL) was administered to assess problem behaviors among first- and fourth-grade children. Multivariate logistic regression analysis was used to evaluate the influence of unsupervised time on children's behavior. A total of 3,270 elementary school children (1,340 first-graders and 1,930 fourth-graders) were available for this study; 1,876 of the 3,270 children (57.4%) reportedly spent a significant amount of time unsupervised during the day. Unsupervised time that exceeded more than 2h per day increased the risk of delinquency, aggressive behaviors, and somatic complaints, as well as externalizing and internalizing problems. Carefully planned afterschool programming and care should be provided to children at high risk for inattention and problem behaviors. Also, a more comprehensive approach is needed to identify the possible mechanisms by which unsupervised time aggravates behavior problems in children predisposed for these behaviors. Copyright © 2013 Elsevier Ltd. All rights reserved.
Effect of scene illumination conditions on digital enhancement techniques of multispectral scanner LANDSAT images

NASA Technical Reports Server (NTRS)

Parada, N. D. J.; Novo, E. M. L. M.

1983-01-01

Two sets of MSS/LANDSAT data with solar elevation ranging from 22 deg to 41 deg were used at the Image-100 System to implement the Eliason et alii technique for extracting the topographic modulation component. An unsupervised cluster analysis was used to obtain an average brightness image for each channel. Analysis of the enhanced imaged shows that the technique for extracting topographic modulation component is more appropriated to MSS data obtained under high sun elevation ngles. Low sun elevation increases the variance of each cluster so that the average brightness doesn't represent its albedo proprties. The topographic modulation component applied to low sun elevation angle damages rather than enhance topographic information. Better results were produced for channels 4 and 5 than for channels 6 and 7.
Instructional Videos for Unsupervised Harvesting and Learning of Action Examples

DTIC Science & Technology

2014-11-03

collection of image or video anno - tations has been tackled in different ways, but most existing methods still require a human in the loop. The...the views of ARO and NSF. 7. REFERENCES [1] C.-C. Chang and C.- J . Lin. LIBSVM: A library for support vector machines. In ACM Transactions on...feature encoding methods. In BMVC, 2011. [3] J . Chen, Y. Cui, G. Ye, D. Liu, and S.-F. Chang. Event-driven semantic concept discovery by exploiting
Robust location and spread measures for nonparametric probability density function estimation.

PubMed

López-Rubio, Ezequiel

2009-10-01

Robustness against outliers is a desirable property of any unsupervised learning scheme. In particular, probability density estimators benefit from incorporating this feature. A possible strategy to achieve this goal is to substitute the sample mean and the sample covariance matrix by more robust location and spread estimators. Here we use the L1-median to develop a nonparametric probability density function (PDF) estimator. We prove its most relevant properties, and we show its performance in density estimation and classification applications.
Evaluating Unsupervised Methods to Size and Classify Suspended Particles Using Digital Holography

NASA Astrophysics Data System (ADS)

Davies, E. J.; Buscombe, D.; Graham, G.; Nimmo-Smith, A.

2013-12-01

The use of digital holography to image suspended particles in-situ using submersible systems is on the ascendancy. Such systems allow visualization of the in-focus particles without the depth-of-field issues associated with conventional imaging. The size and concentration of all particles, and each individual particle, can be rapidly and automatically assessed. The automated methods by which to extract these quantities can be readily evaluated using manual measurements. These methods are not possible using instruments based on optical and acoustic (back- or forward-) scattering, so-called 'sediment surrogate' methods, which are sensitive to the bulk quantities of all suspended particles in a sample volume, and rely on mathematically inverting a measured signal to derive the property of interest. Depending on the intended application, the number of holograms required to elucidate a process could range from tens to millions. Therefore manual particle extraction is not feasible for most data-sets. This has created a pressing need among the growing community of holography users, for accurate, automated processing which is comparable in output to more well-established in-situ sizing techniques such as laser diffraction. Here we discuss the computational considerations required to focus and segment individual particles from raw digital holograms, and then size and classify these particles by type; all using unsupervised (automated) image processing. To do so, we draw upon imagery from both controlled laboratory conditions to near-shore coastal environments, using different holographic system designs, and constituting a significant variety in particle types, sizes and shapes. We evaluate the success of these techniques, and suggest directions for future developments.
Comparison Between Supervised and Unsupervised Classifications of Neuronal Cell Types: A Case Study

PubMed Central

Guerra, Luis; McGarry, Laura M; Robles, Víctor; Bielza, Concha; Larrañaga, Pedro; Yuste, Rafael

2011-01-01

In the study of neural circuits, it becomes essential to discern the different neuronal cell types that build the circuit. Traditionally, neuronal cell types have been classified using qualitative descriptors. More recently, several attempts have been made to classify neurons quantitatively, using unsupervised clustering methods. While useful, these algorithms do not take advantage of previous information known to the investigator, which could improve the classification task. For neocortical GABAergic interneurons, the problem to discern among different cell types is particularly difficult and better methods are needed to perform objective classifications. Here we explore the use of supervised classification algorithms to classify neurons based on their morphological features, using a database of 128 pyramidal cells and 199 interneurons from mouse neocortex. To evaluate the performance of different algorithms we used, as a “benchmark,” the test to automatically distinguish between pyramidal cells and interneurons, defining “ground truth” by the presence or absence of an apical dendrite. We compared hierarchical clustering with a battery of different supervised classification algorithms, finding that supervised classifications outperformed hierarchical clustering. In addition, the selection of subsets of distinguishing features enhanced the classification accuracy for both sets of algorithms. The analysis of selected variables indicates that dendritic features were most useful to distinguish pyramidal cells from interneurons when compared with somatic and axonal morphological variables. We conclude that supervised classification algorithms are better matched to the general problem of distinguishing neuronal cell types when some information on these cell groups, in our case being pyramidal or interneuron, is known a priori. As a spin-off of this methodological study, we provide several methods to automatically distinguish neocortical pyramidal cells from interneurons, based on their morphologies. © 2010 Wiley Periodicals, Inc. Develop Neurobiol 71: 71–82, 2011 PMID:21154911
The Livermore Brain: Massive Deep Learning Networks Enabled by High Performance Computing

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chen, Barry Y.

The proliferation of inexpensive sensor technologies like the ubiquitous digital image sensors has resulted in the collection and sharing of vast amounts of unsorted and unexploited raw data. Companies and governments who are able to collect and make sense of large datasets to help them make better decisions more rapidly will have a competitive advantage in the information era. Machine Learning technologies play a critical role for automating the data understanding process; however, to be maximally effective, useful intermediate representations of the data are required. These representations or “features” are transformations of the raw data into a form where patternsmore » are more easily recognized. Recent breakthroughs in Deep Learning have made it possible to learn these features from large amounts of labeled data. The focus of this project is to develop and extend Deep Learning algorithms for learning features from vast amounts of unlabeled data and to develop the HPC neural network training platform to support the training of massive network models. This LDRD project succeeded in developing new unsupervised feature learning algorithms for images and video and created a scalable neural network training toolkit for HPC. Additionally, this LDRD helped create the world’s largest freely-available image and video dataset supporting open multimedia research and used this dataset for training our deep neural networks. This research helped LLNL capture several work-for-others (WFO) projects, attract new talent, and establish collaborations with leading academic and commercial partners. Finally, this project demonstrated the successful training of the largest unsupervised image neural network using HPC resources and helped establish LLNL leadership at the intersection of Machine Learning and HPC research.« less
Automated extraction and analysis of rock discontinuity characteristics from 3D point clouds

NASA Astrophysics Data System (ADS)

Bianchetti, Matteo; Villa, Alberto; Agliardi, Federico; Crosta, Giovanni B.

2016-04-01

A reliable characterization of fractured rock masses requires an exhaustive geometrical description of discontinuities, including orientation, spacing, and size. These are required to describe discontinuum rock mass structure, perform Discrete Fracture Network and DEM modelling, or provide input for rock mass classification or equivalent continuum estimate of rock mass properties. Although several advanced methodologies have been developed in the last decades, a complete characterization of discontinuity geometry in practice is still challenging, due to scale-dependent variability of fracture patterns and difficult accessibility to large outcrops. Recent advances in remote survey techniques, such as terrestrial laser scanning and digital photogrammetry, allow a fast and accurate acquisition of dense 3D point clouds, which promoted the development of several semi-automatic approaches to extract discontinuity features. Nevertheless, these often need user supervision on algorithm parameters which can be difficult to assess. To overcome this problem, we developed an original Matlab tool, allowing fast, fully automatic extraction and analysis of discontinuity features with no requirements on point cloud accuracy, density and homogeneity. The tool consists of a set of algorithms which: (i) process raw 3D point clouds, (ii) automatically characterize discontinuity sets, (iii) identify individual discontinuity surfaces, and (iv) analyse their spacing and persistence. The tool operates in either a supervised or unsupervised mode, starting from an automatic preliminary exploration data analysis. The identification and geometrical characterization of discontinuity features is divided in steps. First, coplanar surfaces are identified in the whole point cloud using K-Nearest Neighbor and Principal Component Analysis algorithms optimized on point cloud accuracy and specified typical facet size. Then, discontinuity set orientation is calculated using Kernel Density Estimation and principal vector similarity criteria. Poles to points are assigned to individual discontinuity objects using easy custom vector clustering and Jaccard distance approaches, and each object is segmented into planar clusters using an improved version of the DBSCAN algorithm. Modal set orientations are then recomputed by cluster-based orientation statistics to avoid the effects of biases related to cluster size and density heterogeneity of the point cloud. Finally, spacing values are measured between individual discontinuity clusters along scanlines parallel to modal pole vectors, whereas individual feature size (persistence) is measured using 3D convex hull bounding boxes. Spacing and size are provided both as raw population data and as summary statistics. The tool is optimized for parallel computing on 64bit systems, and a Graphic User Interface (GUI) has been developed to manage data processing, provide several outputs, including reclassified point clouds, tables, plots, derived fracture intensity parameters, and export to modelling software tools. We present test applications performed both on synthetic 3D data (simple 3D solids) and real case studies, validating the results with existing geomechanical datasets.
Interactive classification and content-based retrieval of tissue images

NASA Astrophysics Data System (ADS)

Aksoy, Selim; Marchisio, Giovanni B.; Tusk, Carsten; Koperski, Krzysztof

2002-11-01

We describe a system for interactive classification and retrieval of microscopic tissue images. Our system models tissues in pixel, region and image levels. Pixel level features are generated using unsupervised clustering of color and texture values. Region level features include shape information and statistics of pixel level feature values. Image level features include statistics and spatial relationships of regions. To reduce the gap between low-level features and high-level expert knowledge, we define the concept of prototype regions. The system learns the prototype regions in an image collection using model-based clustering and density estimation. Different tissue types are modeled using spatial relationships of these regions. Spatial relationships are represented by fuzzy membership functions. The system automatically selects significant relationships from training data and builds models which can also be updated using user relevance feedback. A Bayesian framework is used to classify tissues based on these models. Preliminary experiments show that the spatial relationship models we developed provide a flexible and powerful framework for classification and retrieval of tissue images.
Unsupervised self-care predicts conduct problems: The moderating roles of hostile aggression and gender.

PubMed

Atherton, Olivia E; Schofield, Thomas J; Sitka, Angela; Conger, Rand D; Robins, Richard W

2016-04-01

Despite widespread speculation about the detrimental effect of unsupervised self-care on adolescent outcomes, little is known about which children are particularly prone to problem behaviors when left at home without adult supervision. The present research used data from a longitudinal study of 674 Mexican-origin children residing in the United States to examine the prospective effect of unsupervised self-care on conduct problems, and the moderating roles of hostile aggression and gender. Results showed that unsupervised self-care was related to increases over time in conduct problems such as lying, stealing, and bullying. However, unsupervised self-care only led to conduct problems for boys and for children with an aggressive temperament. The main and interactive effects held for both mother-reported and observational-rated hostile aggression and after controlling for potential confounds. Copyright © 2016 The Foundation for Professionals in Services for Adolescents. Published by Elsevier Ltd. All rights reserved.
The cascaded moving k-means and fuzzy c-means clustering algorithms for unsupervised segmentation of malaria images

NASA Astrophysics Data System (ADS)

Abdul-Nasir, Aimi Salihah; Mashor, Mohd Yusoff; Halim, Nurul Hazwani Abd; Mohamed, Zeehaida

2015-05-01

Malaria is a life-threatening parasitic infectious disease that corresponds for nearly one million deaths each year. Due to the requirement of prompt and accurate diagnosis of malaria, the current study has proposed an unsupervised pixel segmentation based on clustering algorithm in order to obtain the fully segmented red blood cells (RBCs) infected with malaria parasites based on the thin blood smear images of P. vivax species. In order to obtain the segmented infected cell, the malaria images are first enhanced by using modified global contrast stretching technique. Then, an unsupervised segmentation technique based on clustering algorithm has been applied on the intensity component of malaria image in order to segment the infected cell from its blood cells background. In this study, cascaded moving k-means (MKM) and fuzzy c-means (FCM) clustering algorithms has been proposed for malaria slide image segmentation. After that, median filter algorithm has been applied to smooth the image as well as to remove any unwanted regions such as small background pixels from the image. Finally, seeded region growing area extraction algorithm has been applied in order to remove large unwanted regions that are still appeared on the image due to their size in which cannot be cleaned by using median filter. The effectiveness of the proposed cascaded MKM and FCM clustering algorithms has been analyzed qualitatively and quantitatively by comparing the proposed cascaded clustering algorithm with MKM and FCM clustering algorithms. Overall, the results indicate that segmentation using the proposed cascaded clustering algorithm has produced the best segmentation performances by achieving acceptable sensitivity as well as high specificity and accuracy values compared to the segmentation results provided by MKM and FCM algorithms.

One-Channel Surface Electromyography Decomposition for Muscle Force Estimation.

PubMed

Sun, Wentao; Zhu, Jinying; Jiang, Yinlai; Yokoi, Hiroshi; Huang, Qiang

2018-01-01

Estimating muscle force by surface electromyography (sEMG) is a non-invasive and flexible way to diagnose biomechanical diseases and control assistive devices such as prosthetic hands. To estimate muscle force using sEMG, a supervised method is commonly adopted. This requires simultaneous recording of sEMG signals and muscle force measured by additional devices to tune the variables involved. However, recording the muscle force of the lost limb of an amputee is challenging, and the supervised method has limitations in this regard. Although the unsupervised method does not require muscle force recording, it suffers from low accuracy due to a lack of reference data. To achieve accurate and easy estimation of muscle force by the unsupervised method, we propose a decomposition of one-channel sEMG signals into constituent motor unit action potentials (MUAPs) in two steps: (1) learning an orthogonal basis of sEMG signals through reconstruction independent component analysis; (2) extracting spike-like MUAPs from the basis vectors. Nine healthy subjects were recruited to evaluate the accuracy of the proposed approach in estimating muscle force of the biceps brachii. The results demonstrated that the proposed approach based on decomposed MUAPs explains more than 80% of the muscle force variability recorded at an arbitrary force level, while the conventional amplitude-based approach explains only 62.3% of this variability. With the proposed approach, we were also able to achieve grip force control of a prosthetic hand, which is one of the most important clinical applications of the unsupervised method. Experiments on two trans-radial amputees indicated that the proposed approach improves the performance of the prosthetic hand in grasping everyday objects.
AHaH computing-from metastable switches to attractors to machine learning.

PubMed

Nugent, Michael Alexander; Molter, Timothy Wesley

2014-01-01

Modern computing architecture based on the separation of memory and processing leads to a well known problem called the von Neumann bottleneck, a restrictive limit on the data bandwidth between CPU and RAM. This paper introduces a new approach to computing we call AHaH computing where memory and processing are combined. The idea is based on the attractor dynamics of volatile dissipative electronics inspired by biological systems, presenting an attractive alternative architecture that is able to adapt, self-repair, and learn from interactions with the environment. We envision that both von Neumann and AHaH computing architectures will operate together on the same machine, but that the AHaH computing processor may reduce the power consumption and processing time for certain adaptive learning tasks by orders of magnitude. The paper begins by drawing a connection between the properties of volatility, thermodynamics, and Anti-Hebbian and Hebbian (AHaH) plasticity. We show how AHaH synaptic plasticity leads to attractor states that extract the independent components of applied data streams and how they form a computationally complete set of logic functions. After introducing a general memristive device model based on collections of metastable switches, we show how adaptive synaptic weights can be formed from differential pairs of incremental memristors. We also disclose how arrays of synaptic weights can be used to build a neural node circuit operating AHaH plasticity. By configuring the attractor states of the AHaH node in different ways, high level machine learning functions are demonstrated. This includes unsupervised clustering, supervised and unsupervised classification, complex signal prediction, unsupervised robotic actuation and combinatorial optimization of procedures-all key capabilities of biological nervous systems and modern machine learning algorithms with real world application.
AHaH Computing–From Metastable Switches to Attractors to Machine Learning

PubMed Central

Nugent, Michael Alexander; Molter, Timothy Wesley

2014-01-01

Modern computing architecture based on the separation of memory and processing leads to a well known problem called the von Neumann bottleneck, a restrictive limit on the data bandwidth between CPU and RAM. This paper introduces a new approach to computing we call AHaH computing where memory and processing are combined. The idea is based on the attractor dynamics of volatile dissipative electronics inspired by biological systems, presenting an attractive alternative architecture that is able to adapt, self-repair, and learn from interactions with the environment. We envision that both von Neumann and AHaH computing architectures will operate together on the same machine, but that the AHaH computing processor may reduce the power consumption and processing time for certain adaptive learning tasks by orders of magnitude. The paper begins by drawing a connection between the properties of volatility, thermodynamics, and Anti-Hebbian and Hebbian (AHaH) plasticity. We show how AHaH synaptic plasticity leads to attractor states that extract the independent components of applied data streams and how they form a computationally complete set of logic functions. After introducing a general memristive device model based on collections of metastable switches, we show how adaptive synaptic weights can be formed from differential pairs of incremental memristors. We also disclose how arrays of synaptic weights can be used to build a neural node circuit operating AHaH plasticity. By configuring the attractor states of the AHaH node in different ways, high level machine learning functions are demonstrated. This includes unsupervised clustering, supervised and unsupervised classification, complex signal prediction, unsupervised robotic actuation and combinatorial optimization of procedures–all key capabilities of biological nervous systems and modern machine learning algorithms with real world application. PMID:24520315
Robust Real-Time Music Transcription with a Compositional Hierarchical Model.

PubMed

Pesek, Matevž; Leonardis, Aleš; Marolt, Matija

2017-01-01

The paper presents a new compositional hierarchical model for robust music transcription. Its main features are unsupervised learning of a hierarchical representation of input data, transparency, which enables insights into the learned representation, as well as robustness and speed which make it suitable for real-world and real-time use. The model consists of multiple layers, each composed of a number of parts. The hierarchical nature of the model corresponds well to hierarchical structures in music. The parts in lower layers correspond to low-level concepts (e.g. tone partials), while the parts in higher layers combine lower-level representations into more complex concepts (tones, chords). The layers are learned in an unsupervised manner from music signals. Parts in each layer are compositions of parts from previous layers based on statistical co-occurrences as the driving force of the learning process. In the paper, we present the model's structure and compare it to other hierarchical approaches in the field of music information retrieval. We evaluate the model's performance for the multiple fundamental frequency estimation. Finally, we elaborate on extensions of the model towards other music information retrieval tasks.
Using Fourier transform IR spectroscopy to analyze biological materials

PubMed Central

Baker, Matthew J; Trevisan, Júlio; Bassan, Paul; Bhargava, Rohit; Butler, Holly J; Dorling, Konrad M; Fielden, Peter R; Fogarty, Simon W; Fullwood, Nigel J; Heys, Kelly A; Hughes, Caryn; Lasch, Peter; Martin-Hirsch, Pierre L; Obinaju, Blessing; Sockalingum, Ganesh D; Sulé-Suso, Josep; Strong, Rebecca J; Walsh, Michael J; Wood, Bayden R; Gardner, Peter; Martin, Francis L

2015-01-01

IR spectroscopy is an excellent method for biological analyses. It enables the nonperturbative, label-free extraction of biochemical information and images toward diagnosis and the assessment of cell functionality. Although not strictly microscopy in the conventional sense, it allows the construction of images of tissue or cell architecture by the passing of spectral data through a variety of computational algorithms. Because such images are constructed from fingerprint spectra, the notion is that they can be an objective reflection of the underlying health status of the analyzed sample. One of the major difficulties in the field has been determining a consensus on spectral pre-processing and data analysis. This manuscript brings together as coauthors some of the leaders in this field to allow the standardization of methods and procedures for adapting a multistage approach to a methodology that can be applied to a variety of cell biological questions or used within a clinical setting for disease screening or diagnosis. We describe a protocol for collecting IR spectra and images from biological samples (e.g., fixed cytology and tissue sections, live cells or biofluids) that assesses the instrumental options available, appropriate sample preparation, different sampling modes as well as important advances in spectral data acquisition. After acquisition, data processing consists of a sequence of steps including quality control, spectral pre-processing, feature extraction and classification of the supervised or unsupervised type. A typical experiment can be completed and analyzed within hours. Example results are presented on the use of IR spectra combined with multivariate data processing. PMID:24992094
Fast detection of vascular plaque in optical coherence tomography images using a reduced feature set

NASA Astrophysics Data System (ADS)

Prakash, Ammu; Ocana Macias, Mariano; Hewko, Mark; Sowa, Michael; Sherif, Sherif

2018-03-01

Optical coherence tomography (OCT) images are capable of detecting vascular plaque by using the full set of 26 Haralick textural features and a standard K-means clustering algorithm. However, the use of the full set of 26 textural features is computationally expensive and may not be feasible for real time implementation. In this work, we identified a reduced set of 3 textural feature which characterizes vascular plaque and used a generalized Fuzzy C-means clustering algorithm. Our work involves three steps: 1) the reduction of a full set 26 textural feature to a reduced set of 3 textural features by using genetic algorithm (GA) optimization method 2) the implementation of an unsupervised generalized clustering algorithm (Fuzzy C-means) on the reduced feature space, and 3) the validation of our results using histology and actual photographic images of vascular plaque. Our results show an excellent match with histology and actual photographic images of vascular tissue. Therefore, our results could provide an efficient pre-clinical tool for the detection of vascular plaque in real time OCT imaging.
Classification of multispectral or hyperspectral satellite imagery using clustering of sparse approximations on sparse representations in learned dictionaries obtained using efficient convolutional sparse coding

DOEpatents

Moody, Daniela; Wohlberg, Brendt

2018-01-02

An approach for land cover classification, seasonal and yearly change detection and monitoring, and identification of changes in man-made features may use a clustering of sparse approximations (CoSA) on sparse representations in learned dictionaries. The learned dictionaries may be derived using efficient convolutional sparse coding to build multispectral or hyperspectral, multiresolution dictionaries that are adapted to regional satellite image data. Sparse image representations of images over the learned dictionaries may be used to perform unsupervised k-means clustering into land cover categories. The clustering process behaves as a classifier in detecting real variability. This approach may combine spectral and spatial textural characteristics to detect geologic, vegetative, hydrologic, and man-made features, as well as changes in these features over time.
Machine-Learned Data Structures of Lipid Marker Serum Concentrations in Multiple Sclerosis Patients Differ from Those in Healthy Subjects

PubMed Central

Lötsch, Jörn; Thrun, Michael; Lerch, Florian; Brunkhorst, Robert; Schiffmann, Susanne; Thomas, Dominique; Tegder, Irmgard; Geisslinger, Gerd; Ultsch, Alfred

2017-01-01

Lipid signaling has been suggested to be a major pathophysiological mechanism of multiple sclerosis (MS). With the increasing knowledge about lipid signaling, acquired data become increasingly complex making bioinformatics necessary in lipid research. We used unsupervised machine-learning to analyze lipid marker serum concentrations, pursuing the hypothesis that for the most relevant markers the emerging data structures will coincide with the diagnosis of MS. Machine learning was implemented as emergent self-organizing feature maps (ESOM) combined with the U*-matrix visualization technique. The data space consisted of serum concentrations of three main classes of lipid markers comprising eicosanoids (d = 11 markers), ceramides (d = 10), and lyosophosphatidic acids (d = 6). They were analyzed in cohorts of MS patients (n = 102) and healthy subjects (n = 301). Clear data structures in the high-dimensional data space were observed in eicosanoid and ceramides serum concentrations whereas no clear structure could be found in lysophosphatidic acid concentrations. With ceramide concentrations, the structures that had emerged from unsupervised machine-learning almost completely overlapped with the known grouping of MS patients versus healthy subjects. This was only partly provided by eicosanoid serum concentrations. Thus, unsupervised machine-learning identified distinct data structures of bioactive lipid serum concentrations. These structures could be superimposed with the known grouping of MS patients versus healthy subjects, which was almost completely possible with ceramides. Therefore, based on the present analysis, ceramides are first-line candidates for further exploration as drug-gable targets or biomarkers in MS. PMID:28590455
A Hybrid Supervised/Unsupervised Machine Learning Approach to Solar Flare Prediction

NASA Astrophysics Data System (ADS)

Benvenuto, Federico; Piana, Michele; Campi, Cristina; Massone, Anna Maria

2018-01-01

This paper introduces a novel method for flare forecasting, combining prediction accuracy with the ability to identify the most relevant predictive variables. This result is obtained by means of a two-step approach: first, a supervised regularization method for regression, namely, LASSO is applied, where a sparsity-enhancing penalty term allows the identification of the significance with which each data feature contributes to the prediction; then, an unsupervised fuzzy clustering technique for classification, namely, Fuzzy C-Means, is applied, where the regression outcome is partitioned through the minimization of a cost function and without focusing on the optimization of a specific skill score. This approach is therefore hybrid, since it combines supervised and unsupervised learning; realizes classification in an automatic, skill-score-independent way; and provides effective prediction performances even in the case of imbalanced data sets. Its prediction power is verified against NOAA Space Weather Prediction Center data, using as a test set, data in the range between 1996 August and 2010 December and as training set, data in the range between 1988 December and 1996 June. To validate the method, we computed several skill scores typically utilized in flare prediction and compared the values provided by the hybrid approach with the ones provided by several standard (non-hybrid) machine learning methods. The results showed that the hybrid approach performs classification better than all other supervised methods and with an effectiveness comparable to the one of clustering methods; but, in addition, it provides a reliable ranking of the weights with which the data properties contribute to the forecast.
A Novel Semi-Supervised Methodology for Extracting Tumor Type-Specific MRS Sources in Human Brain Data

PubMed Central

Ortega-Martorell, Sandra; Ruiz, Héctor; Vellido, Alfredo; Olier, Iván; Romero, Enrique; Julià-Sapé, Margarida; Martín, José D.; Jarman, Ian H.; Arús, Carles; Lisboa, Paulo J. G.

2013-01-01

Background The clinical investigation of human brain tumors often starts with a non-invasive imaging study, providing information about the tumor extent and location, but little insight into the biochemistry of the analyzed tissue. Magnetic Resonance Spectroscopy can complement imaging by supplying a metabolic fingerprint of the tissue. This study analyzes single-voxel magnetic resonance spectra, which represent signal information in the frequency domain. Given that a single voxel may contain a heterogeneous mix of tissues, signal source identification is a relevant challenge for the problem of tumor type classification from the spectroscopic signal. Methodology/Principal Findings Non-negative matrix factorization techniques have recently shown their potential for the identification of meaningful sources from brain tissue spectroscopy data. In this study, we use a convex variant of these methods that is capable of handling negatively-valued data and generating sources that can be interpreted as tumor class prototypes. A novel approach to convex non-negative matrix factorization is proposed, in which prior knowledge about class information is utilized in model optimization. Class-specific information is integrated into this semi-supervised process by setting the metric of a latent variable space where the matrix factorization is carried out. The reported experimental study comprises 196 cases from different tumor types drawn from two international, multi-center databases. The results indicate that the proposed approach outperforms a purely unsupervised process by achieving near perfect correlation of the extracted sources with the mean spectra of the tumor types. It also improves tissue type classification. Conclusions/Significance We show that source extraction by unsupervised matrix factorization benefits from the integration of the available class information, so operating in a semi-supervised learning manner, for discriminative source identification and brain tumor labeling from single-voxel spectroscopy data. We are confident that the proposed methodology has wider applicability for biomedical signal processing. PMID:24376744
Geological applications of machine learning on hyperspectral remote sensing data

NASA Astrophysics Data System (ADS)

Tse, C. H.; Li, Yi-liang; Lam, Edmund Y.

2015-02-01

The CRISM imaging spectrometer orbiting Mars has been producing a vast amount of data in the visible to infrared wavelengths in the form of hyperspectral data cubes. These data, compared with those obtained from previous remote sensing techniques, yield an unprecedented level of detailed spectral resolution in additional to an ever increasing level of spatial information. A major challenge brought about by the data is the burden of processing and interpreting these datasets and extract the relevant information from it. This research aims at approaching the challenge by exploring machine learning methods especially unsupervised learning to achieve cluster density estimation and classification, and ultimately devising an efficient means leading to identification of minerals. A set of software tools have been constructed by Python to access and experiment with CRISM hyperspectral cubes selected from two specific Mars locations. A machine learning pipeline is proposed and unsupervised learning methods were implemented onto pre-processed datasets. The resulting data clusters are compared with the published ASTER spectral library and browse data products from the Planetary Data System (PDS). The result demonstrated that this approach is capable of processing the huge amount of hyperspectral data and potentially providing guidance to scientists for more detailed studies.
A primitive study on unsupervised anomaly detection with an autoencoder in emergency head CT volumes

NASA Astrophysics Data System (ADS)

Sato, Daisuke; Hanaoka, Shouhei; Nomura, Yukihiro; Takenaga, Tomomi; Miki, Soichiro; Yoshikawa, Takeharu; Hayashi, Naoto; Abe, Osamu

2018-02-01

Purpose: The target disorders of emergency head CT are wide-ranging. Therefore, people working in an emergency department desire a computer-aided detection system for general disorders. In this study, we proposed an unsupervised anomaly detection method in emergency head CT using an autoencoder and evaluated the anomaly detection performance of our method in emergency head CT. Methods: We used a 3D convolutional autoencoder (3D-CAE), which contains 11 layers in the convolution block and 6 layers in the deconvolution block. In the training phase, we trained the 3D-CAE using 10,000 3D patches extracted from 50 normal cases. In the test phase, we calculated abnormalities of each voxel in 38 emergency head CT volumes (22 abnormal cases and 16 normal cases) for evaluation and evaluated the likelihood of lesion existence. Results: Our method achieved a sensitivity of 68% and a specificity of 88%, with an area under the curve of the receiver operating characteristic curve of 0.87. It shows that this method has a moderate accuracy to distinguish normal CT cases to abnormal ones. Conclusion: Our method has potentialities for anomaly detection in emergency head CT.
Co-occurrence graphs for word sense disambiguation in the biomedical domain.

PubMed

Duque, Andres; Stevenson, Mark; Martinez-Romo, Juan; Araujo, Lourdes

2018-05-01

Word sense disambiguation is a key step for many natural language processing tasks (e.g. summarization, text classification, relation extraction) and presents a challenge to any system that aims to process documents from the biomedical domain. In this paper, we present a new graph-based unsupervised technique to address this problem. The knowledge base used in this work is a graph built with co-occurrence information from medical concepts found in scientific abstracts, and hence adapted to the specific domain. Unlike other unsupervised approaches based on static graphs such as UMLS, in this work the knowledge base takes the context of the ambiguous terms into account. Abstracts downloaded from PubMed are used for building the graph and disambiguation is performed using the personalized PageRank algorithm. Evaluation is carried out over two test datasets widely explored in the literature. Different parameters of the system are also evaluated to test robustness and scalability. Results show that the system is able to outperform state-of-the-art knowledge-based systems, obtaining more than 10% of accuracy improvement in some cases, while only requiring minimal external resources. Copyright © 2018 Elsevier B.V. All rights reserved.
Disambiguating ambiguous biomedical terms in biomedical narrative text: an unsupervised method.

PubMed

Liu, H; Lussier, Y A; Friedman, C

2001-08-01

With the growing use of Natural Language Processing (NLP) techniques for information extraction and concept indexing in the biomedical domain, a method that quickly and efficiently assigns the correct sense of an ambiguous biomedical term in a given context is needed concurrently. The current status of word sense disambiguation (WSD) in the biomedical domain is that handcrafted rules are used based on contextual material. The disadvantages of this approach are (i) generating WSD rules manually is a time-consuming and tedious task, (ii) maintenance of rule sets becomes increasingly difficult over time, and (iii) handcrafted rules are often incomplete and perform poorly in new domains comprised of specialized vocabularies and different genres of text. This paper presents a two-phase unsupervised method to build a WSD classifier for an ambiguous biomedical term W. The first phase automatically creates a sense-tagged corpus for W, and the second phase derives a classifier for W using the derived sense-tagged corpus as a training set. A formative experiment was performed, which demonstrated that classifiers trained on the derived sense-tagged corpora achieved an overall accuracy of about 97%, with greater than 90% accuracy for each individual ambiguous term.
Current trends in geomorphological mapping

NASA Astrophysics Data System (ADS)

Seijmonsbergen, A. C.

2012-04-01

Geomorphological mapping is a world currently in motion, driven by technological advances and the availability of new high resolution data. As a consequence, classic (paper) geomorphological maps which were the standard for more than 50 years are rapidly being replaced by digital geomorphological information layers. This is witnessed by the following developments: 1. the conversion of classic paper maps into digital information layers, mainly performed in a digital mapping environment such as a Geographical Information System, 2. updating the location precision and the content of the converted maps, by adding more geomorphological details, taken from high resolution elevation data and/or high resolution image data, 3. (semi) automated extraction and classification of geomorphological features from digital elevation models, broadly separated into unsupervised and supervised classification techniques and 4. New digital visualization / cartographic techniques and reading interfaces. Newly digital geomorphological information layers can be based on manual digitization of polygons using DEMs and/or aerial photographs, or prepared through (semi) automated extraction and delineation of geomorphological features. DEMs are often used as basis to derive Land Surface Parameter information which is used as input for (un) supervised classification techniques. Especially when using high-res data, object-based classification is used as an alternative to traditional pixel-based classifications, to cluster grid cells into homogeneous objects, which can be classified as geomorphological features. Classic map content can also be used as training material for the supervised classification of geomorphological features. In the classification process, rule-based protocols, including expert-knowledge input, are used to map specific geomorphological features or entire landscapes. Current (semi) automated classification techniques are increasingly able to extract morphometric, hydrological, and in the near future also morphogenetic information. As a result, these new opportunities have changed the workflows for geomorphological mapmaking, and their focus have shifted from field-based techniques to using more computer-based techniques: for example, traditional pre-field air-photo based maps are now replaced by maps prepared in a digital mapping environment, and designated field visits using mobile GIS / digital mapping devices now focus on gathering location information and attribute inventories and are strongly time efficient. The resulting 'modern geomorphological maps' are digital collections of geomorphological information layers consisting of georeferenced vector, raster and tabular data which are stored in a digital environment such as a GIS geodatabase, and are easily visualized as e.g. 'birds' eye' views, as animated 3D displays, on virtual globes, or stored as GeoPDF maps in which georeferenced attribute information can be easily exchanged over the internet. Digital geomorphological information layers are increasingly accessed via web-based services distributed through remote servers. Information can be consulted - or even build using remote geoprocessing servers - by the end user. Therefore, it will not only be the geomorphologist anymore, but also the professional end user that dictates the applied use of digital geomorphological information layers.
Quantifying Human Visible Color Variation from High Definition Digital Images of Orb Web Spiders.

PubMed

Tapia-McClung, Horacio; Ajuria Ibarra, Helena; Rao, Dinesh

2016-01-01

Digital processing and analysis of high resolution images of 30 individuals of the orb web spider Verrucosa arenata were performed to extract and quantify human visible colors present on the dorsal abdomen of this species. Color extraction was performed with minimal user intervention using an unsupervised algorithm to determine groups of colors on each individual spider, which was then analyzed in order to quantify and classify the colors obtained, both spatially and using energy and entropy measures of the digital images. Analysis shows that the colors cover a small region of the visible spectrum, are not spatially homogeneously distributed over the patterns and from an entropic point of view, colors that cover a smaller region on the whole pattern carry more information than colors covering a larger region. This study demonstrates the use of processing tools to create automatic systems to extract valuable information from digital images that are precise, efficient and helpful for the understanding of the underlying biology.
Quantifying Human Visible Color Variation from High Definition Digital Images of Orb Web Spiders

PubMed Central

Ajuria Ibarra, Helena; Rao, Dinesh

2016-01-01

Digital processing and analysis of high resolution images of 30 individuals of the orb web spider Verrucosa arenata were performed to extract and quantify human visible colors present on the dorsal abdomen of this species. Color extraction was performed with minimal user intervention using an unsupervised algorithm to determine groups of colors on each individual spider, which was then analyzed in order to quantify and classify the colors obtained, both spatially and using energy and entropy measures of the digital images. Analysis shows that the colors cover a small region of the visible spectrum, are not spatially homogeneously distributed over the patterns and from an entropic point of view, colors that cover a smaller region on the whole pattern carry more information than colors covering a larger region. This study demonstrates the use of processing tools to create automatic systems to extract valuable information from digital images that are precise, efficient and helpful for the understanding of the underlying biology. PMID:27902724
Valley and channel networks extraction based on local topographic curvature and k-means clustering of contours

NASA Astrophysics Data System (ADS)

Hooshyar, Milad; Wang, Dingbao; Kim, Seoyoung; Medeiros, Stephen C.; Hagen, Scott C.

2016-10-01

A method for automatic extraction of valley and channel networks from high-resolution digital elevation models (DEMs) is presented. This method utilizes both positive (i.e., convergent topography) and negative (i.e., divergent topography) curvature to delineate the valley network. The valley and ridge skeletons are extracted using the pixels' curvature and the local terrain conditions. The valley network is generated by checking the terrain for the existence of at least one ridge between two intersecting valleys. The transition from unchannelized to channelized sections (i.e., channel head) in each first-order valley tributary is identified independently by categorizing the corresponding contours using an unsupervised approach based on k-means clustering. The method does not require a spatially constant channel initiation threshold (e.g., curvature or contributing area). Moreover, instead of a point attribute (e.g., curvature), the proposed clustering method utilizes the shape of contours, which reflects the entire cross-sectional profile including possible banks. The method was applied to three catchments: Indian Creek and Mid Bailey Run in Ohio and Feather River in California. The accuracy of channel head extraction from the proposed method is comparable to state-of-the-art channel extraction methods.
Advanced soft computing diagnosis method for tumour grading.

PubMed

Papageorgiou, E I; Spyridonos, P P; Stylios, C D; Ravazoula, P; Groumpos, P P; Nikiforidis, G N

2006-01-01

To develop an advanced diagnostic method for urinary bladder tumour grading. A novel soft computing modelling methodology based on the augmentation of fuzzy cognitive maps (FCMs) with the unsupervised active Hebbian learning (AHL) algorithm is applied. One hundred and twenty-eight cases of urinary bladder cancer were retrieved from the archives of the Department of Histopathology, University Hospital of Patras, Greece. All tumours had been characterized according to the classical World Health Organization (WHO) grading system. To design the FCM model for tumour grading, three experts histopathologists defined the main histopathological features (concepts) and their impact on grade characterization. The resulted FCM model consisted of nine concepts. Eight concepts represented the main histopathological features for tumour grading. The ninth concept represented the tumour grade. To increase the classification ability of the FCM model, the AHL algorithm was applied to adjust the weights of the FCM. The proposed FCM grading model achieved a classification accuracy of 72.5%, 74.42% and 95.55% for tumours of grades I, II and III, respectively. An advanced computerized method to support tumour grade diagnosis decision was proposed and developed. The novelty of the method is based on employing the soft computing method of FCMs to represent specialized knowledge on histopathology and on augmenting FCMs ability using an unsupervised learning algorithm, the AHL. The proposed method performs with reasonably high accuracy compared to other existing methods and at the same time meets the physicians' requirements for transparency and explicability.
FEX: A Knowledge-Based System For Planimetric Feature Extraction

NASA Astrophysics Data System (ADS)

Zelek, John S.

1988-10-01

Topographical planimetric features include natural surfaces (rivers, lakes) and man-made surfaces (roads, railways, bridges). In conventional planimetric feature extraction, a photointerpreter manually interprets and extracts features from imagery on a stereoplotter. Visual planimetric feature extraction is a very labour intensive operation. The advantages of automating feature extraction include: time and labour savings; accuracy improvements; and planimetric data consistency. FEX (Feature EXtraction) combines techniques from image processing, remote sensing and artificial intelligence for automatic feature extraction. The feature extraction process co-ordinates the information and knowledge in a hierarchical data structure. The system simulates the reasoning of a photointerpreter in determining the planimetric features. Present efforts have concentrated on the extraction of road-like features in SPOT imagery. Keywords: Remote Sensing, Artificial Intelligence (AI), SPOT, image understanding, knowledge base, apars.

Model-Based Learning of Local Image Features for Unsupervised Texture Segmentation

NASA Astrophysics Data System (ADS)

Kiechle, Martin; Storath, Martin; Weinmann, Andreas; Kleinsteuber, Martin

2018-04-01

Features that capture well the textural patterns of a certain class of images are crucial for the performance of texture segmentation methods. The manual selection of features or designing new ones can be a tedious task. Therefore, it is desirable to automatically adapt the features to a certain image or class of images. Typically, this requires a large set of training images with similar textures and ground truth segmentation. In this work, we propose a framework to learn features for texture segmentation when no such training data is available. The cost function for our learning process is constructed to match a commonly used segmentation model, the piecewise constant Mumford-Shah model. This means that the features are learned such that they provide an approximately piecewise constant feature image with a small jump set. Based on this idea, we develop a two-stage algorithm which first learns suitable convolutional features and then performs a segmentation. We note that the features can be learned from a small set of images, from a single image, or even from image patches. The proposed method achieves a competitive rank in the Prague texture segmentation benchmark, and it is effective for segmenting histological images.
Novel multiresolution mammographic density segmentation using pseudo 3D features and adaptive cluster merging

NASA Astrophysics Data System (ADS)

He, Wenda; Juette, Arne; Denton, Erica R. E.; Zwiggelaar, Reyer

2015-03-01

Breast cancer is the most frequently diagnosed cancer in women. Early detection, precise identification of women at risk, and application of appropriate disease prevention measures are by far the most effective ways to overcome the disease. Successful mammographic density segmentation is a key aspect in deriving correct tissue composition, ensuring an accurate mammographic risk assessment. However, mammographic densities have not yet been fully incorporated with non-image based risk prediction models, (e.g. the Gail and the Tyrer-Cuzick model), because of unreliable segmentation consistency and accuracy. This paper presents a novel multiresolution mammographic density segmentation, a concept of stack representation is proposed, and 3D texture features were extracted by adapting techniques based on classic 2D first-order statistics. An unsupervised clustering technique was employed to achieve mammographic segmentation, in which two improvements were made; 1) consistent segmentation by incorporating an optimal centroids initialisation step, and 2) significantly reduced the number of missegmentation by using an adaptive cluster merging technique. A set of full field digital mammograms was used in the evaluation. Visual assessment indicated substantial improvement on segmented anatomical structures and tissue specific areas, especially in low mammographic density categories. The developed method demonstrated an ability to improve the quality of mammographic segmentation via clustering, and results indicated an improvement of 26% in segmented image with good quality when compared with the standard clustering approach. This in turn can be found useful in early breast cancer detection, risk-stratified screening, and aiding radiologists in the process of decision making prior to surgery and/or treatment.
Domain adaptation via transfer component analysis.

PubMed

Pan, Sinno Jialin; Tsang, Ivor W; Kwok, James T; Yang, Qiang

2011-02-01

Domain adaptation allows knowledge from a source domain to be transferred to a different but related target domain. Intuitively, discovering a good feature representation across domains is crucial. In this paper, we first propose to find such a representation through a new learning method, transfer component analysis (TCA), for domain adaptation. TCA tries to learn some transfer components across domains in a reproducing kernel Hilbert space using maximum mean miscrepancy. In the subspace spanned by these transfer components, data properties are preserved and data distributions in different domains are close to each other. As a result, with the new representations in this subspace, we can apply standard machine learning methods to train classifiers or regression models in the source domain for use in the target domain. Furthermore, in order to uncover the knowledge hidden in the relations between the data labels from the source and target domains, we extend TCA in a semisupervised learning setting, which encodes label information into transfer components learning. We call this extension semisupervised TCA. The main contribution of our work is that we propose a novel dimensionality reduction framework for reducing the distance between domains in a latent space for domain adaptation. We propose both unsupervised and semisupervised feature extraction approaches, which can dramatically reduce the distance between domain distributions by projecting data onto the learned transfer components. Finally, our approach can handle large datasets and naturally lead to out-of-sample generalization. The effectiveness and efficiency of our approach are verified by experiments on five toy datasets and two real-world applications: cross-domain indoor WiFi localization and cross-domain text classification.
A Hessian-based methodology for automatic surface crack detection and classification from pavement images

NASA Astrophysics Data System (ADS)

Ghanta, Sindhu; Shahini Shamsabadi, Salar; Dy, Jennifer; Wang, Ming; Birken, Ralf

2015-04-01

Around 3,000,000 million vehicle miles are annually traveled utilizing the US transportation systems alone. In addition to the road traffic safety, maintaining the road infrastructure in a sound condition promotes a more productive and competitive economy. Due to the significant amounts of financial and human resources required to detect surface cracks by visual inspection, detection of these surface defects are often delayed resulting in deferred maintenance operations. This paper introduces an automatic system for acquisition, detection, classification, and evaluation of pavement surface cracks by unsupervised analysis of images collected from a camera mounted on the rear of a moving vehicle. A Hessian-based multi-scale filter has been utilized to detect ridges in these images at various scales. Post-processing on the extracted features has been implemented to produce statistics of length, width, and area covered by cracks, which are crucial for roadway agencies to assess pavement quality. This process has been realized on three sets of roads with different pavement conditions in the city of Brockton, MA. A ground truth dataset labeled manually is made available to evaluate this algorithm and results rendered more than 90% segmentation accuracy demonstrating the feasibility of employing this approach at a larger scale.
TINAGL1 and B3GALNT1 are potential therapy target genes to suppress metastasis in non-small cell lung cancer

PubMed Central

2014-01-01

Background Non-small cell lung cancer (NSCLC) remains lethal despite the development of numerous drug therapy technologies. About 85% to 90% of lung cancers are NSCLC and the 5-year survival rate is at best still below 50%. Thus, it is important to find drugable target genes for NSCLC to develop an effective therapy for NSCLC. Results Integrated analysis of publically available gene expression and promoter methylation patterns of two highly aggressive NSCLC cell lines generated by in vivo selection was performed. We selected eleven critical genes that may mediate metastasis using recently proposed principal component analysis based unsupervised feature extraction. The eleven selected genes were significantly related to cancer diagnosis. The tertiary protein structure of the selected genes was inferred by Full Automatic Modeling System, a profile-based protein structure inference software, to determine protein functions and to specify genes that could be potential drug targets. Conclusions We identified eleven potentially critical genes that may mediate NSCLC metastasis using bioinformatic analysis of publically available data sets. These genes are potential target genes for the therapy of NSCLC. Among the eleven genes, TINAGL1 and B3GALNT1 are possible candidates for drug compounds that inhibit their gene expression. PMID:25521548
Fast vessel segmentation in retinal images using multi-scale enhancement and second-order local entropy

NASA Astrophysics Data System (ADS)

Yu, H.; Barriga, S.; Agurto, C.; Zamora, G.; Bauman, W.; Soliz, P.

2012-03-01

Retinal vasculature is one of the most important anatomical structures in digital retinal photographs. Accurate segmentation of retinal blood vessels is an essential task in automated analysis of retinopathy. This paper presents a new and effective vessel segmentation algorithm that features computational simplicity and fast implementation. This method uses morphological pre-processing to decrease the disturbance of bright structures and lesions before vessel extraction. Next, a vessel probability map is generated by computing the eigenvalues of the second derivatives of Gaussian filtered image at multiple scales. Then, the second order local entropy thresholding is applied to segment the vessel map. Lastly, a rule-based decision step, which measures the geometric shape difference between vessels and lesions is applied to reduce false positives. The algorithm is evaluated on the low-resolution DRIVE and STARE databases and the publicly available high-resolution image database from Friedrich-Alexander University Erlangen-Nuremberg, Germany). The proposed method achieved comparable performance to state of the art unsupervised vessel segmentation methods with a competitive faster speed on the DRIVE and STARE databases. For the high resolution fundus image database, the proposed algorithm outperforms an existing approach both on performance and speed. The efficiency and robustness make the blood vessel segmentation method described here suitable for broad application in automated analysis of retinal images.
A prototype for unsupervised analysis of tissue microarrays for cancer research and diagnostics.

PubMed

Chen, Wenjin; Reiss, Michael; Foran, David J

2004-06-01

The tissue microarray (TMA) technique enables researchers to extract small cylinders of tissue from histological sections and arrange them in a matrix configuration on a recipient paraffin block such that hundreds can be analyzed simultaneously. TMA offers several advantages over traditional specimen preparation by maximizing limited tissue resources and providing a highly efficient means for visualizing molecular targets. By enabling researchers to reliably determine the protein expression profile for specific types of cancer, it may be possible to elucidate the mechanism by which healthy tissues are transformed into malignancies. Currently, the primary methods used to evaluate arrays involve the interactive review of TMA samples while they are viewed under a microscope, subjectively evaluated, and scored by a technician. This process is extremely slow, tedious, and prone to error. In order to facilitate large-scale, multi-institutional studies, a more automated and reliable means for analyzing TMAs is needed. We report here a web-based prototype which features automated imaging, registration, and distributed archiving of TMAs in multiuser network environments. The system utilizes a principal color decomposition approach to identify and characterize the predominant staining signatures of specimens in color space. This strategy was shown to be reliable for detecting and quantifying the immunohistochemical expression levels for TMAs.
Self-organizing neural networks--an alternative way of cluster analysis in clinical chemistry.

PubMed

Reibnegger, G; Wachter, H

1996-04-15

Supervised learning schemes have been employed by several workers for training neural networks designed to solve clinical problems. We demonstrate that unsupervised techniques can also produce interesting and meaningful results. Using a data set on the chemical composition of milk from 22 different mammals, we demonstrate that self-organizing feature maps (Kohonen networks) as well as a modified version of error backpropagation technique yield results mimicking conventional cluster analysis. Both techniques are able to project a potentially multi-dimensional input vector onto a two-dimensional space whereby neighborhood relationships remain conserved. Thus, these techniques can be used for reducing dimensionality of complicated data sets and for enhancing comprehensibility of features hidden in the data matrix.
Deep learning of joint myelin and T1w MRI features in normal-appearing brain tissue to distinguish between multiple sclerosis patients and healthy controls.

PubMed

Yoo, Youngjin; Tang, Lisa Y W; Brosch, Tom; Li, David K B; Kolind, Shannon; Vavasour, Irene; Rauscher, Alexander; MacKay, Alex L; Traboulsee, Anthony; Tam, Roger C

2018-01-01

Myelin imaging is a form of quantitative magnetic resonance imaging (MRI) that measures myelin content and can potentially allow demyelinating diseases such as multiple sclerosis (MS) to be detected earlier. Although focal lesions are the most visible signs of MS pathology on conventional MRI, it has been shown that even tissues that appear normal may exhibit decreased myelin content as revealed by myelin-specific images (i.e., myelin maps). Current methods for analyzing myelin maps typically use global or regional mean myelin measurements to detect abnormalities, but ignore finer spatial patterns that may be characteristic of MS. In this paper, we present a machine learning method to automatically learn, from multimodal MR images, latent spatial features that can potentially improve the detection of MS pathology at early stage. More specifically, 3D image patches are extracted from myelin maps and the corresponding T1-weighted (T1w) MRIs, and are used to learn a latent joint myelin-T1w feature representation via unsupervised deep learning. Using a data set of images from MS patients and healthy controls, a common set of patches are selected via a voxel-wise t -test performed between the two groups. In each MS image, any patches overlapping with focal lesions are excluded, and a feature imputation method is used to fill in the missing values. A feature selection process (LASSO) is then utilized to construct a sparse representation. The resulting normal-appearing features are used to train a random forest classifier. Using the myelin and T1w images of 55 relapse-remitting MS patients and 44 healthy controls in an 11-fold cross-validation experiment, the proposed method achieved an average classification accuracy of 87.9% (SD = 8.4%), which is higher and more consistent across folds than those attained by regional mean myelin (73.7%, SD = 13.7%) and T1w measurements (66.7%, SD = 10.6%), or deep-learned features in either the myelin (83.8%, SD = 11.0%) or T1w (70.1%, SD = 13.6%) images alone, suggesting that the proposed method has strong potential for identifying image features that are more sensitive and specific to MS pathology in normal-appearing brain tissues.
A novel feature extraction approach for microarray data based on multi-algorithm fusion

PubMed Central

Jiang, Zhu; Xu, Rong

2015-01-01

Feature extraction is one of the most important and effective method to reduce dimension in data mining, with emerging of high dimensional data such as microarray gene expression data. Feature extraction for gene selection, mainly serves two purposes. One is to identify certain disease-related genes. The other is to find a compact set of discriminative genes to build a pattern classifier with reduced complexity and improved generalization capabilities. Depending on the purpose of gene selection, two types of feature extraction algorithms including ranking-based feature extraction and set-based feature extraction are employed in microarray gene expression data analysis. In ranking-based feature extraction, features are evaluated on an individual basis, without considering inter-relationship between features in general, while set-based feature extraction evaluates features based on their role in a feature set by taking into account dependency between features. Just as learning methods, feature extraction has a problem in its generalization ability, which is robustness. However, the issue of robustness is often overlooked in feature extraction. In order to improve the accuracy and robustness of feature extraction for microarray data, a novel approach based on multi-algorithm fusion is proposed. By fusing different types of feature extraction algorithms to select the feature from the samples set, the proposed approach is able to improve feature extraction performance. The new approach is tested against gene expression dataset including Colon cancer data, CNS data, DLBCL data, and Leukemia data. The testing results show that the performance of this algorithm is better than existing solutions. PMID:25780277
A novel feature extraction approach for microarray data based on multi-algorithm fusion.

PubMed

Jiang, Zhu; Xu, Rong

2015-01-01

Feature extraction is one of the most important and effective method to reduce dimension in data mining, with emerging of high dimensional data such as microarray gene expression data. Feature extraction for gene selection, mainly serves two purposes. One is to identify certain disease-related genes. The other is to find a compact set of discriminative genes to build a pattern classifier with reduced complexity and improved generalization capabilities. Depending on the purpose of gene selection, two types of feature extraction algorithms including ranking-based feature extraction and set-based feature extraction are employed in microarray gene expression data analysis. In ranking-based feature extraction, features are evaluated on an individual basis, without considering inter-relationship between features in general, while set-based feature extraction evaluates features based on their role in a feature set by taking into account dependency between features. Just as learning methods, feature extraction has a problem in its generalization ability, which is robustness. However, the issue of robustness is often overlooked in feature extraction. In order to improve the accuracy and robustness of feature extraction for microarray data, a novel approach based on multi-algorithm fusion is proposed. By fusing different types of feature extraction algorithms to select the feature from the samples set, the proposed approach is able to improve feature extraction performance. The new approach is tested against gene expression dataset including Colon cancer data, CNS data, DLBCL data, and Leukemia data. The testing results show that the performance of this algorithm is better than existing solutions.
Automatic information extraction from unstructured mammography reports using distributed semantics.

PubMed

Gupta, Anupama; Banerjee, Imon; Rubin, Daniel L

2018-02-01

To date, the methods developed for automated extraction of information from radiology reports are mainly rule-based or dictionary-based, and, therefore, require substantial manual effort to build these systems. Recent efforts to develop automated systems for entity detection have been undertaken, but little work has been done to automatically extract relations and their associated named entities in narrative radiology reports that have comparable accuracy to rule-based methods. Our goal is to extract relations in a unsupervised way from radiology reports without specifying prior domain knowledge. We propose a hybrid approach for information extraction that combines dependency-based parse tree with distributed semantics for generating structured information frames about particular findings/abnormalities from the free-text mammography reports. The proposed IE system obtains a F 1 -score of 0.94 in terms of completeness of the content in the information frames, which outperforms a state-of-the-art rule-based system in this domain by a significant margin. The proposed system can be leveraged in a variety of applications, such as decision support and information retrieval, and may also easily scale to other radiology domains, since there is no need to tune the system with hand-crafted information extraction rules. Copyright © 2018 Elsevier Inc. All rights reserved.
Compact Representation of High-Dimensional Feature Vectors for Large-Scale Image Recognition and Retrieval.

PubMed

Zhang, Yu; Wu, Jianxin; Cai, Jianfei

2016-05-01

In large-scale visual recognition and image retrieval tasks, feature vectors, such as Fisher vector (FV) or the vector of locally aggregated descriptors (VLAD), have achieved state-of-the-art results. However, the combination of the large numbers of examples and high-dimensional vectors necessitates dimensionality reduction, in order to reduce its storage and CPU costs to a reasonable range. In spite of the popularity of various feature compression methods, this paper shows that the feature (dimension) selection is a better choice for high-dimensional FV/VLAD than the feature (dimension) compression methods, e.g., product quantization. We show that strong correlation among the feature dimensions in the FV and the VLAD may not exist, which renders feature selection a natural choice. We also show that, many dimensions in FV/VLAD are noise. Throwing them away using feature selection is better than compressing them and useful dimensions altogether using feature compression methods. To choose features, we propose an efficient importance sorting algorithm considering both the supervised and unsupervised cases, for visual recognition and image retrieval, respectively. Combining with the 1-bit quantization, feature selection has achieved both higher accuracy and less computational cost than feature compression methods, such as product quantization, on the FV and the VLAD image representations.
Synaptic State Matching: A Dynamical Architecture for Predictive Internal Representation and Feature Detection

PubMed Central

Tavazoie, Saeed

2013-01-01

Here we explore the possibility that a core function of sensory cortex is the generation of an internal simulation of sensory environment in real-time. A logical elaboration of this idea leads to a dynamical neural architecture that oscillates between two fundamental network states, one driven by external input, and the other by recurrent synaptic drive in the absence of sensory input. Synaptic strength is modified by a proposed synaptic state matching (SSM) process that ensures equivalence of spike statistics between the two network states. Remarkably, SSM, operating locally at individual synapses, generates accurate and stable network-level predictive internal representations, enabling pattern completion and unsupervised feature detection from noisy sensory input. SSM is a biologically plausible substrate for learning and memory because it brings together sequence learning, feature detection, synaptic homeostasis, and network oscillations under a single unifying computational framework. PMID:23991161
Cross-indexing of binary SIFT codes for large-scale image search.

PubMed

Liu, Zhen; Li, Houqiang; Zhang, Liyan; Zhou, Wengang; Tian, Qi

2014-05-01

In recent years, there has been growing interest in mapping visual features into compact binary codes for applications on large-scale image collections. Encoding high-dimensional data as compact binary codes reduces the memory cost for storage. Besides, it benefits the computational efficiency since the computation of similarity can be efficiently measured by Hamming distance. In this paper, we propose a novel flexible scale invariant feature transform (SIFT) binarization (FSB) algorithm for large-scale image search. The FSB algorithm explores the magnitude patterns of SIFT descriptor. It is unsupervised and the generated binary codes are demonstrated to be dispreserving. Besides, we propose a new searching strategy to find target features based on the cross-indexing in the binary SIFT space and original SIFT space. We evaluate our approach on two publicly released data sets. The experiments on large-scale partial duplicate image retrieval system demonstrate the effectiveness and efficiency of the proposed algorithm.
Analysis and application of ERTS-1 data for regional geological mapping

NASA Technical Reports Server (NTRS)

Gold, D. P.; Parizek, R. R.; Alexander, S. A.

1973-01-01

Combined visual and digital techniques of analysing ERTS-1 data for geologic information have been tried on selected areas in Pennsylvania. The major physiolographic and structural provinces show up well. Supervised mapping, following the imaged expression of known geologic features on ERTS band 5 enlargements (1:250,000) of parts of eastern Pennsylvania, delimited the Diabase Sills and the Precambrian rocks of the Reading Prong with remarkable accuracy. From unsupervised mapping, transgressive linear features are apparent in unexpected density, and exhibit strong control over river valley and stream channel directions. They are unaffected by bedrock type, age, or primary structural boundaries, which suggests they are either rejuvenated basement joint directions on different scales, or they are a recently impressed structure possibly associated with a drifting North American plate. With ground mapping and underflight data, 6 scales of linear features have been recognized.
Unsupervised categorization method of graphemes on handwritten manuscripts: application to style recognition

NASA Astrophysics Data System (ADS)

Daher, H.; Gaceb, D.; Eglin, V.; Bres, S.; Vincent, N.

2012-01-01

We present in this paper a feature selection and weighting method for medieval handwriting images that relies on codebooks of shapes of small strokes of characters (graphemes that are issued from the decomposition of manuscripts). These codebooks are important to simplify the automation of the analysis, the manuscripts transcription and the recognition of styles or writers. Our approach provides a precise features weighting by genetic algorithms and a highperformance methodology for the categorization of the shapes of graphemes by using graph coloring into codebooks which are applied in turn on CBIR (Content Based Image Retrieval) in a mixed handwriting database containing different pages from different writers, periods of the history and quality. We show how the coupling of these two mechanisms 'features weighting - graphemes classification' can offer a better separation of the forms to be categorized by exploiting their grapho-morphological, their density and their significant orientations particularities.
Mere exposure alters category learning of novel objects.

PubMed

Folstein, Jonathan R; Gauthier, Isabel; Palmeri, Thomas J

2010-01-01

We investigated how mere exposure to complex objects with correlated or uncorrelated object features affects later category learning of new objects not seen during exposure. Correlations among pre-exposed object dimensions influenced later category learning. Unlike other published studies, the collection of pre-exposed objects provided no information regarding the categories to be learned, ruling out unsupervised or incidental category learning during pre-exposure. Instead, results are interpreted with respect to statistical learning mechanisms, providing one of the first demonstrations of how statistical learning can influence visual object learning.
Mere Exposure Alters Category Learning of Novel Objects

PubMed Central

Folstein, Jonathan R.; Gauthier, Isabel; Palmeri, Thomas J.

2010-01-01

We investigated how mere exposure to complex objects with correlated or uncorrelated object features affects later category learning of new objects not seen during exposure. Correlations among pre-exposed object dimensions influenced later category learning. Unlike other published studies, the collection of pre-exposed objects provided no information regarding the categories to be learned, ruling out unsupervised or incidental category learning during pre-exposure. Instead, results are interpreted with respect to statistical learning mechanisms, providing one of the first demonstrations of how statistical learning can influence visual object learning. PMID:21833209
Radiogenomic analysis of hypoxia pathway reveals computerized MRI descriptors predictive of overall survival in glioblastoma

NASA Astrophysics Data System (ADS)

Beig, Niha; Patel, Jay; Prasanna, Prateek; Partovi, Sasan; Varadan, Vinay; Madabhushi, Anant; Tiwari, Pallavi

2017-03-01

Glioblastoma Multiforme (GBM) is a highly aggressive brain tumor with a median survival of 14 months. Hypoxia is a hallmark trait in GBM that is known to be associated with angiogenesis, tumor growth, and resistance to conventional therapy, thereby limiting treatment options for GBM patients. There is thus an urgent clinical need for non-invasively capturing tumor hypoxia in GBM towards identifying a subset of patients who would likely benefit from anti-angiogenic therapies (bevacizumab) in the adjuvant setting. In this study, we employed radiomic descriptors to (a) capture molecular variations of tumor hypoxia on routine MRI that are otherwise not appreciable; and (b) employ the radiomic correlates of hypoxia to discriminate patients with short-term survival (STS, overall survival (OS) < 7 months), mid-term survival (MTS) (7 months16 months). A total of 97 studies (25 STS, 36 MTS, 36 LTS) with Gadolinium T1-contrast (Gd-T1c), T2w, and FLAIR protocols with their corresponding gene expression profiles were obtained from the cancer genome atlas (TCGA) database. For each MRI study, necrotic, enhancing tumor, and edematous regions were segmented by an expert. A total of 30 radiomic descriptors (i.e. Haralick, Laws energy, Gabor) were extracted from every region across all three MRI protocols. By performing unsupervised clustering of the expression profile of hypoxia associated genes, a "low", "medium", or "high" index was defined for every study. Spearman correlation was then used to identify the most significantly correlated MRI features with the hypoxia index for every study. These features were further used to categorize each study as STS, MTS, and LTS using Kaplan-Meier (KM) analysis. Our results revealed that the most significant features (p < 0.05) were identified as Laws energy and Haralick features that capture image heterogeneity on FLAIR and Gd-T1w sequences. We also found these radiomic features to be significantly associated with survival, distinguishing MTS from LTS (p=.005) and STS from LTS (p=.0008).

Sequence-structure relationship study in all-α transmembrane proteins using an unsupervised learning approach.

PubMed

Esque, Jérémy; Urbain, Aurélie; Etchebest, Catherine; de Brevern, Alexandre G

2015-11-01

Transmembrane proteins (TMPs) are major drug targets, but the knowledge of their precise topology structure remains highly limited compared with globular proteins. In spite of the difficulties in obtaining their structures, an important effort has been made these last years to increase their number from an experimental and computational point of view. In view of this emerging challenge, the development of computational methods to extract knowledge from these data is crucial for the better understanding of their functions and in improving the quality of structural models. Here, we revisit an efficient unsupervised learning procedure, called Hybrid Protein Model (HPM), which is applied to the analysis of transmembrane proteins belonging to the all-α structural class. HPM method is an original classification procedure that efficiently combines sequence and structure learning. The procedure was initially applied to the analysis of globular proteins. In the present case, HPM classifies a set of overlapping protein fragments, extracted from a non-redundant databank of TMP 3D structure. After fine-tuning of the learning parameters, the optimal classification results in 65 clusters. They represent at best similar relationships between sequence and local structure properties of TMPs. Interestingly, HPM distinguishes among the resulting clusters two helical regions with distinct hydrophobic patterns. This underlines the complexity of the topology of these proteins. The HPM classification enlightens unusual relationship between amino acids in TMP fragments, which can be useful to elaborate new amino acids substitution matrices. Finally, two challenging applications are described: the first one aims at annotating protein functions (channel or not), the second one intends to assess the quality of the structures (X-ray or models) via a new scoring function deduced from the HPM classification.
A new scoring system in Cystic Fibrosis: statistical tools for database analysis - a preliminary report.

PubMed

Hafen, G M; Hurst, C; Yearwood, J; Smith, J; Dzalilov, Z; Robinson, P J

2008-10-05

Cystic fibrosis is the most common fatal genetic disorder in the Caucasian population. Scoring systems for assessment of Cystic fibrosis disease severity have been used for almost 50 years, without being adapted to the milder phenotype of the disease in the 21st century. The aim of this current project is to develop a new scoring system using a database and employing various statistical tools. This study protocol reports the development of the statistical tools in order to create such a scoring system. The evaluation is based on the Cystic Fibrosis database from the cohort at the Royal Children's Hospital in Melbourne. Initially, unsupervised clustering of the all data records was performed using a range of clustering algorithms. In particular incremental clustering algorithms were used. The clusters obtained were characterised using rules from decision trees and the results examined by clinicians. In order to obtain a clearer definition of classes expert opinion of each individual's clinical severity was sought. After data preparation including expert-opinion of an individual's clinical severity on a 3 point-scale (mild, moderate and severe disease), two multivariate techniques were used throughout the analysis to establish a method that would have a better success in feature selection and model derivation: 'Canonical Analysis of Principal Coordinates' and 'Linear Discriminant Analysis'. A 3-step procedure was performed with (1) selection of features, (2) extracting 5 severity classes out of a 3 severity class as defined per expert-opinion and (3) establishment of calibration datasets. (1) Feature selection: CAP has a more effective "modelling" focus than DA.(2) Extraction of 5 severity classes: after variables were identified as important in discriminating contiguous CF severity groups on the 3-point scale as mild/moderate and moderate/severe, Discriminant Function (DF) was used to determine the new groups mild, intermediate moderate, moderate, intermediate severe and severe disease. (3) Generated confusion tables showed a misclassification rate of 19.1% for males and 16.5% for females, with a majority of misallocations into adjacent severity classes particularly for males. Our preliminary data show that using CAP for detection of selection features and Linear DA to derive the actual model in a CF database might be helpful in developing a scoring system. However, there are several limitations, particularly more data entry points are needed to finalize a score and the statistical tools have further to be refined and validated, with re-running the statistical methods in the larger dataset.
Best friends' interactions and substance use: The role of friend pressure and unsupervised co-deviancy.

PubMed

Tsakpinoglou, Florence; Poulin, François

2017-10-01

Best friends exert a substantial influence on rising alcohol and marijuana use during adolescence. Two mechanisms occurring within friendship - friend pressure and unsupervised co-deviancy - may partially capture the way friends influence one another. The current study aims to: (1) examine the psychometric properties of a new instrument designed to assess pressure from a youth's best friend and unsupervised co-deviancy; (2) investigate the relative contribution of these processes to alcohol and marijuana use; and (3) determine whether gender moderates these associations. Data were collected through self-report questionnaires completed by 294 Canadian youths (62% female) across two time points (ages 15-16). Principal component analysis yielded a two-factor solution corresponding to friend pressure and unsupervised co-deviancy. Logistic regressions subsequently showed that unsupervised co-deviancy was predictive of an increase in marijuana use one year later. Neither process predicted an increase in alcohol use. Results did not differ as a function of gender. Copyright © 2017 The Foundation for Professionals in Services for Adolescents. Published by Elsevier Ltd. All rights reserved.
Cross-language opinion lexicon extraction using mutual-reinforcement label propagation.

PubMed

Lin, Zheng; Tan, Songbo; Liu, Yue; Cheng, Xueqi; Xu, Xueke

2013-01-01

There is a growing interest in automatically building opinion lexicon from sources such as product reviews. Most of these methods depend on abundant external resources such as WordNet, which limits the applicability of these methods. Unsupervised or semi-supervised learning provides an optional solution to multilingual opinion lexicon extraction. However, the datasets are imbalanced in different languages. For some languages, the high-quality corpora are scarce or hard to obtain, which limits the research progress. To solve the above problems, we explore a mutual-reinforcement label propagation framework. First, for each language, a label propagation algorithm is applied to a word relation graph, and then a bilingual dictionary is used as a bridge to transfer information between two languages. A key advantage of this model is its ability to make two languages learn from each other and boost each other. The experimental results show that the proposed approach outperforms baseline significantly.
Cross-Language Opinion Lexicon Extraction Using Mutual-Reinforcement Label Propagation

PubMed Central

Lin, Zheng; Tan, Songbo; Liu, Yue; Cheng, Xueqi; Xu, Xueke

2013-01-01

There is a growing interest in automatically building opinion lexicon from sources such as product reviews. Most of these methods depend on abundant external resources such as WordNet, which limits the applicability of these methods. Unsupervised or semi-supervised learning provides an optional solution to multilingual opinion lexicon extraction. However, the datasets are imbalanced in different languages. For some languages, the high-quality corpora are scarce or hard to obtain, which limits the research progress. To solve the above problems, we explore a mutual-reinforcement label propagation framework. First, for each language, a label propagation algorithm is applied to a word relation graph, and then a bilingual dictionary is used as a bridge to transfer information between two languages. A key advantage of this model is its ability to make two languages learn from each other and boost each other. The experimental results show that the proposed approach outperforms baseline significantly. PMID:24260190
Exploring nonlinear feature space dimension reduction and data representation in breast Cadx with Laplacian eigenmaps and t-SNE.

PubMed

Jamieson, Andrew R; Giger, Maryellen L; Drukker, Karen; Li, Hui; Yuan, Yading; Bhooshan, Neha

2010-01-01

In this preliminary study, recently developed unsupervised nonlinear dimension reduction (DR) and data representation techniques were applied to computer-extracted breast lesion feature spaces across three separate imaging modalities: Ultrasound (U.S.) with 1126 cases, dynamic contrast enhanced magnetic resonance imaging with 356 cases, and full-field digital mammography with 245 cases. Two methods for nonlinear DR were explored: Laplacian eigenmaps [M. Belkin and P. Niyogi, "Laplacian eigenmaps for dimensionality reduction and data representation," Neural Comput. 15, 1373-1396 (2003)] and t-distributed stochastic neighbor embedding (t-SNE) [L. van der Maaten and G. Hinton, "Visualizing data using t-SNE," J. Mach. Learn. Res. 9, 2579-2605 (2008)]. These methods attempt to map originally high dimensional feature spaces to more human interpretable lower dimensional spaces while preserving both local and global information. The properties of these methods as applied to breast computer-aided diagnosis (CADx) were evaluated in the context of malignancy classification performance as well as in the visual inspection of the sparseness within the two-dimensional and three-dimensional mappings. Classification performance was estimated by using the reduced dimension mapped feature output as input into both linear and nonlinear classifiers: Markov chain Monte Carlo based Bayesian artificial neural network (MCMC-BANN) and linear discriminant analysis. The new techniques were compared to previously developed breast CADx methodologies, including automatic relevance determination and linear stepwise (LSW) feature selection, as well as a linear DR method based on principal component analysis. Using ROC analysis and 0.632+bootstrap validation, 95% empirical confidence intervals were computed for the each classifier's AUC performance. In the large U.S. data set, sample high performance results include, AUC0.632+ = 0.88 with 95% empirical bootstrap interval [0.787;0.895] for 13 ARD selected features and AUC0.632+ = 0.87 with interval [0.817;0.906] for four LSW selected features compared to 4D t-SNE mapping (from the original 81D feature space) giving AUC0.632+ = 0.90 with interval [0.847;0.919], all using the MCMC-BANN. Preliminary results appear to indicate capability for the new methods to match or exceed classification performance of current advanced breast lesion CADx algorithms. While not appropriate as a complete replacement of feature selection in CADx problems, DR techniques offer a complementary approach, which can aid elucidation of additional properties associated with the data. Specifically, the new techniques were shown to possess the added benefit of delivering sparse lower dimensional representations for visual interpretation, revealing intricate data structure of the feature space.
Enhancement of Tropical Land Cover Mapping with Wavelet-Based Fusion and Unsupervised Clustering of SAR and Landsat Image Data

NASA Technical Reports Server (NTRS)

LeMoigne, Jacqueline; Laporte, Nadine; Netanyahuy, Nathan S.; Zukor, Dorothy (Technical Monitor)

2001-01-01

The characterization and the mapping of land cover/land use of forest areas, such as the Central African rainforest, is a very complex task. This complexity is mainly due to the extent of such areas and, as a consequence, to the lack of full and continuous cloud-free coverage of those large regions by one single remote sensing instrument, In order to provide improved vegetation maps of Central Africa and to develop forest monitoring techniques for applications at the local and regional scales, we propose to utilize multi-sensor remote sensing observations coupled with in-situ data. Fusion and clustering of multi-sensor data are the first steps towards the development of such a forest monitoring system. In this paper, we will describe some preliminary experiments involving the fusion of SAR and Landsat image data of the Lope Reserve in Gabon. Similarly to previous fusion studies, our fusion method is wavelet-based. The fusion provides a new image data set which contains more detailed texture features and preserves the large homogeneous regions that are observed by the Thematic Mapper sensor. The fusion step is followed by unsupervised clustering and provides a vegetation map of the area.
From image captioning to video summary using deep recurrent networks and unsupervised segmentation

NASA Astrophysics Data System (ADS)

Morosanu, Bogdan-Andrei; Lemnaru, Camelia

2018-04-01

Automatic captioning systems based on recurrent neural networks have been tremendously successful at providing realistic natural language captions for complex and varied image data. We explore methods for adapting existing models trained on large image caption data sets to a similar problem, that of summarising videos using natural language descriptions and frame selection. These architectures create internal high level representations of the input image that can be used to define probability distributions and distance metrics on these distributions. Specifically, we interpret each hidden unit inside a layer of the caption model as representing the un-normalised log probability of some unknown image feature of interest for the caption generation process. We can then apply well understood statistical divergence measures to express the difference between images and create an unsupervised segmentation of video frames, classifying consecutive images of low divergence as belonging to the same context, and those of high divergence as belonging to different contexts. To provide a final summary of the video, we provide a group of selected frames and a text description accompanying them, allowing a user to perform a quick exploration of large unlabeled video databases.
Mastication Evaluation With Unsupervised Learning: Using an Inertial Sensor-Based System.

PubMed

Lucena, Caroline Vieira; Lacerda, Marcelo; Caldas, Rafael; De Lima Neto, Fernando Buarque; Rativa, Diego

2018-01-01

There is a direct relationship between the prevalence of musculoskeletal disorders of the temporomandibular joint and orofacial disorders. A well-elaborated analysis of the jaw movements provides relevant information for healthcare professionals to conclude their diagnosis. Different approaches have been explored to track jaw movements such that the mastication analysis is getting less subjective; however, all methods are still highly subjective, and the quality of the assessments depends much on the experience of the health professional. In this paper, an accurate and non-invasive method based on a commercial low-cost inertial sensor (MPU6050) to measure jaw movements is proposed. The jaw-movement feature values are compared to the obtained with clinical analysis, showing no statistically significant difference between both methods. Moreover, We propose to use unsupervised paradigm approaches to cluster mastication patterns of healthy subjects and simulated patients with facial trauma. Two techniques were used in this paper to instantiate the method: Kohonen's Self-Organizing Maps and K-Means Clustering. Both algorithms have excellent performances to process jaw-movements data, showing encouraging results and potential to bring a full assessment of the masticatory function. The proposed method can be applied in real-time providing relevant dynamic information for health-care professionals.
Unsupervised active learning based on hierarchical graph-theoretic clustering.

PubMed

Hu, Weiming; Hu, Wei; Xie, Nianhua; Maybank, Steve

2009-10-01

Most existing active learning approaches are supervised. Supervised active learning has the following problems: inefficiency in dealing with the semantic gap between the distribution of samples in the feature space and their labels, lack of ability in selecting new samples that belong to new categories that have not yet appeared in the training samples, and lack of adaptability to changes in the semantic interpretation of sample categories. To tackle these problems, we propose an unsupervised active learning framework based on hierarchical graph-theoretic clustering. In the framework, two promising graph-theoretic clustering algorithms, namely, dominant-set clustering and spectral clustering, are combined in a hierarchical fashion. Our framework has some advantages, such as ease of implementation, flexibility in architecture, and adaptability to changes in the labeling. Evaluations on data sets for network intrusion detection, image classification, and video classification have demonstrated that our active learning framework can effectively reduce the workload of manual classification while maintaining a high accuracy of automatic classification. It is shown that, overall, our framework outperforms the support-vector-machine-based supervised active learning, particularly in terms of dealing much more efficiently with new samples whose categories have not yet appeared in the training samples.
An Unsupervised Online Spike-Sorting Framework.

PubMed

Knieling, Simeon; Sridharan, Kousik S; Belardinelli, Paolo; Naros, Georgios; Weiss, Daniel; Mormann, Florian; Gharabaghi, Alireza

2016-08-01

Extracellular neuronal microelectrode recordings can include action potentials from multiple neurons. To separate spikes from different neurons, they can be sorted according to their shape, a procedure referred to as spike-sorting. Several algorithms have been reported to solve this task. However, when clustering outcomes are unsatisfactory, most of them are difficult to adjust to achieve the desired results. We present an online spike-sorting framework that uses feature normalization and weighting to maximize the distinctiveness between different spike shapes. Furthermore, multiple criteria are applied to either facilitate or prevent cluster fusion, thereby enabling experimenters to fine-tune the sorting process. We compare our method to established unsupervised offline (Wave_Clus (WC)) and online (OSort (OS)) algorithms by examining their performance in sorting various test datasets using two different scoring systems (AMI and the Adamos metric). Furthermore, we evaluate sorting capabilities on intra-operative recordings using established quality metrics. Compared to WC and OS, our algorithm achieved comparable or higher scores on average and produced more convincing sorting results for intra-operative datasets. Thus, the presented framework is suitable for both online and offline analysis and could substantially improve the quality of microelectrode-based data evaluation for research and clinical application.
Recapitulation of Ayurveda constitution types by machine learning of phenotypic traits.

PubMed

Tiwari, Pradeep; Kutum, Rintu; Sethi, Tavpritesh; Shrivastava, Ankita; Girase, Bhushan; Aggarwal, Shilpi; Patil, Rutuja; Agarwal, Dhiraj; Gautam, Pramod; Agrawal, Anurag; Dash, Debasis; Ghosh, Saurabh; Juvekar, Sanjay; Mukerji, Mitali; Prasher, Bhavana

2017-01-01

In Ayurveda system of medicine individuals are classified into seven constitution types, "Prakriti", for assessing disease susceptibility and drug responsiveness. Prakriti evaluation involves clinical examination including questions about physiological and behavioural traits. A need was felt to develop models for accurately predicting Prakriti classes that have been shown to exhibit molecular differences. The present study was carried out on data of phenotypic attributes in 147 healthy individuals of three extreme Prakriti types, from a genetically homogeneous population of Western India. Unsupervised and supervised machine learning approaches were used to infer inherent structure of the data, and for feature selection and building classification models for Prakriti respectively. These models were validated in a North Indian population. Unsupervised clustering led to emergence of three natural clusters corresponding to three extreme Prakriti classes. The supervised modelling approaches could classify individuals, with distinct Prakriti types, in the training and validation sets. This study is the first to demonstrate that Prakriti types are distinct verifiable clusters within a multidimensional space of multiple interrelated phenotypic traits. It also provides a computational framework for predicting Prakriti classes from phenotypic attributes. This approach may be useful in precision medicine for stratification of endophenotypes in healthy and diseased populations.
Unsupervised Learning and Pattern Recognition of Biological Data Structures with Density Functional Theory and Machine Learning.

PubMed

Chen, Chien-Chang; Juan, Hung-Hui; Tsai, Meng-Yuan; Lu, Henry Horng-Shing

2018-01-11

By introducing the methods of machine learning into the density functional theory, we made a detour for the construction of the most probable density function, which can be estimated by learning relevant features from the system of interest. Using the properties of universal functional, the vital core of density functional theory, the most probable cluster numbers and the corresponding cluster boundaries in a studying system can be simultaneously and automatically determined and the plausibility is erected on the Hohenberg-Kohn theorems. For the method validation and pragmatic applications, interdisciplinary problems from physical to biological systems were enumerated. The amalgamation of uncharged atomic clusters validated the unsupervised searching process of the cluster numbers and the corresponding cluster boundaries were exhibited likewise. High accurate clustering results of the Fisher's iris dataset showed the feasibility and the flexibility of the proposed scheme. Brain tumor detections from low-dimensional magnetic resonance imaging datasets and segmentations of high-dimensional neural network imageries in the Brainbow system were also used to inspect the method practicality. The experimental results exhibit the successful connection between the physical theory and the machine learning methods and will benefit the clinical diagnoses.
Unsupervised EEG analysis for automated epileptic seizure detection

NASA Astrophysics Data System (ADS)

Birjandtalab, Javad; Pouyan, Maziyar Baran; Nourani, Mehrdad

2016-07-01

Epilepsy is a neurological disorder which can, if not controlled, potentially cause unexpected death. It is extremely crucial to have accurate automatic pattern recognition and data mining techniques to detect the onset of seizures and inform care-givers to help the patients. EEG signals are the preferred biosignals for diagnosis of epileptic patients. Most of the existing pattern recognition techniques used in EEG analysis leverage the notion of supervised machine learning algorithms. Since seizure data are heavily under-represented, such techniques are not always practical particularly when the labeled data is not sufficiently available or when disease progression is rapid and the corresponding EEG footprint pattern will not be robust. Furthermore, EEG pattern change is highly individual dependent and requires experienced specialists to annotate the seizure and non-seizure events. In this work, we present an unsupervised technique to discriminate seizures and non-seizures events. We employ power spectral density of EEG signals in different frequency bands that are informative features to accurately cluster seizure and non-seizure events. The experimental results tried so far indicate achieving more than 90% accuracy in clustering seizure and non-seizure events without having any prior knowledge on patient's history.
Data-Driven Information Extraction from Chinese Electronic Medical Records

PubMed Central

Zhao, Tianwan; Ge, Chen; Gao, Weiguo; Wei, Jia; Zhu, Kenny Q.

2015-01-01

Objective This study aims to propose a data-driven framework that takes unstructured free text narratives in Chinese Electronic Medical Records (EMRs) as input and converts them into structured time-event-description triples, where the description is either an elaboration or an outcome of the medical event. Materials and Methods Our framework uses a hybrid approach. It consists of constructing cross-domain core medical lexica, an unsupervised, iterative algorithm to accrue more accurate terms into the lexica, rules to address Chinese writing conventions and temporal descriptors, and a Support Vector Machine (SVM) algorithm that innovatively utilizes Normalized Google Distance (NGD) to estimate the correlation between medical events and their descriptions. Results The effectiveness of the framework was demonstrated with a dataset of 24,817 de-identified Chinese EMRs. The cross-domain medical lexica were capable of recognizing terms with an F1-score of 0.896. 98.5% of recorded medical events were linked to temporal descriptors. The NGD SVM description-event matching achieved an F1-score of 0.874. The end-to-end time-event-description extraction of our framework achieved an F1-score of 0.846. Discussion In terms of named entity recognition, the proposed framework outperforms state-of-the-art supervised learning algorithms (F1-score: 0.896 vs. 0.886). In event-description association, the NGD SVM is superior to SVM using only local context and semantic features (F1-score: 0.874 vs. 0.838). Conclusions The framework is data-driven, weakly supervised, and robust against the variations and noises that tend to occur in a large corpus. It addresses Chinese medical writing conventions and variations in writing styles through patterns used for discovering new terms and rules for updating the lexica. PMID:26295801
Passive IR flexi-scope with two spectral colors for household screening of gastrointestinal disorders

NASA Astrophysics Data System (ADS)

Byrd, Kenneth; Szu, Harold

2006-04-01

According to our generalized Shannon Sampling Theorem of developmental system biology, we should increase the sampling frequency of the passive Infrared (IR) spectrum ratio test, (I 8~12mm / I 3~5mm). This procedure proved to be effective in DCIS using the satellite-grade IR spectrum cameras for an early developmental symptom of the "angiogenesis" effect. Thus, we propose to augment the annual hospital checkup of, or biannual Colonoscopy, with an inexpensive non-imaging IR-Flexi-scope intensity measurement device which could be conducted regularly at a household residence without the need doctoral expertise or a data basis system. The only required component would be a smart PC, which would be used to compute the degree of thermal activities through the IR spectral ratio. It will also be used to keep track of the record and send to the medical center for tele-diagnosis. For the purpose of household screening, we propose to have two integrated passive IR probes of dual-IR-color spectrum inserted into the body via the IR fiber-optic device. In order to extract the percentage of malignancy, based on the ratio of dual color IR measurements, the key enabler is the unsupervised learning algorithm in the sense of the Duda & Hart Unlabelled Data Classifier without lookup table exemplars. This learning methodology belongs to the Natural Intelligence (NI) of the human brain, which can effortlessly reduce the redundancy of pair inputs and thereby enhance the Signal to Noise Ratio (SNR) better than any single sensor for the salient feature extraction. Thus, we can go beyond a closed data basis AI expert system to tailor to the individual ground truth without the biases of the prior knowledge.
Assigning clinical codes with data-driven concept representation on Dutch clinical free text.

PubMed

Scheurwegs, Elyne; Luyckx, Kim; Luyten, Léon; Goethals, Bart; Daelemans, Walter

2017-05-01

Clinical codes are used for public reporting purposes, are fundamental to determining public financing for hospitals, and form the basis for reimbursement claims to insurance providers. They are assigned to a patient stay to reflect the diagnosis and performed procedures during that stay. This paper aims to enrich algorithms for automated clinical coding by taking a data-driven approach and by using unsupervised and semi-supervised techniques for the extraction of multi-word expressions that convey a generalisable medical meaning (referred to as concepts). Several methods for extracting concepts from text are compared, two of which are constructed from a large unannotated corpus of clinical free text. A distributional semantic model (i.c. the word2vec skip-gram model) is used to generalize over concepts and retrieve relations between them. These methods are validated on three sets of patient stay data, in the disease areas of urology, cardiology, and gastroenterology. The datasets are in Dutch, which introduces a limitation on available concept definitions from expert-based ontologies (e.g. UMLS). The results show that when expert-based knowledge in ontologies is unavailable, concepts derived from raw clinical texts are a reliable alternative. Both concepts derived from raw clinical texts perform and concepts derived from expert-created dictionaries outperform a bag-of-words approach in clinical code assignment. Adding features based on tokens that appear in a semantically similar context has a positive influence for predicting diagnostic codes. Furthermore, the experiments indicate that a distributional semantics model can find relations between semantically related concepts in texts but also introduces erroneous and redundant relations, which can undermine clinical coding performance. Copyright © 2017. Published by Elsevier Inc.
Data-Driven Information Extraction from Chinese Electronic Medical Records.

PubMed

Xu, Dong; Zhang, Meizhuo; Zhao, Tianwan; Ge, Chen; Gao, Weiguo; Wei, Jia; Zhu, Kenny Q

2015-01-01

This study aims to propose a data-driven framework that takes unstructured free text narratives in Chinese Electronic Medical Records (EMRs) as input and converts them into structured time-event-description triples, where the description is either an elaboration or an outcome of the medical event. Our framework uses a hybrid approach. It consists of constructing cross-domain core medical lexica, an unsupervised, iterative algorithm to accrue more accurate terms into the lexica, rules to address Chinese writing conventions and temporal descriptors, and a Support Vector Machine (SVM) algorithm that innovatively utilizes Normalized Google Distance (NGD) to estimate the correlation between medical events and their descriptions. The effectiveness of the framework was demonstrated with a dataset of 24,817 de-identified Chinese EMRs. The cross-domain medical lexica were capable of recognizing terms with an F1-score of 0.896. 98.5% of recorded medical events were linked to temporal descriptors. The NGD SVM description-event matching achieved an F1-score of 0.874. The end-to-end time-event-description extraction of our framework achieved an F1-score of 0.846. In terms of named entity recognition, the proposed framework outperforms state-of-the-art supervised learning algorithms (F1-score: 0.896 vs. 0.886). In event-description association, the NGD SVM is superior to SVM using only local context and semantic features (F1-score: 0.874 vs. 0.838). The framework is data-driven, weakly supervised, and robust against the variations and noises that tend to occur in a large corpus. It addresses Chinese medical writing conventions and variations in writing styles through patterns used for discovering new terms and rules for updating the lexica.
Efficient hyperspectral image segmentation using geometric active contour formulation

NASA Astrophysics Data System (ADS)

Albalooshi, Fatema A.; Sidike, Paheding; Asari, Vijayan K.

2014-10-01

In this paper, we present a new formulation of geometric active contours that embeds the local hyperspectral image information for an accurate object region and boundary extraction. We exploit self-organizing map (SOM) unsupervised neural network to train our model. The segmentation process is achieved by the construction of a level set cost functional, in which, the dynamic variable is the best matching unit (BMU) coming from SOM map. In addition, we use Gaussian filtering to discipline the deviation of the level set functional from a signed distance function and this actually helps to get rid of the re-initialization step that is computationally expensive. By using the properties of the collective computational ability and energy convergence capability of the active control models (ACM) energy functional, our method optimizes the geometric ACM energy functional with lower computational time and smoother level set function. The proposed algorithm starts with feature extraction from raw hyperspectral images. In this step, the principal component analysis (PCA) transformation is employed, and this actually helps in reducing dimensionality and selecting best sets of the significant spectral bands. Then the modified geometric level set functional based ACM is applied on the optimal number of spectral bands determined by the PCA. By introducing local significant spectral band information, our proposed method is capable to force the level set functional to be close to a signed distance function, and therefore considerably remove the need of the expensive re-initialization procedure. To verify the effectiveness of the proposed technique, we use real-life hyperspectral images and test our algorithm in varying textural regions. This framework can be easily adapted to different applications for object segmentation in aerial hyperspectral imagery.
An efficient fully unsupervised video object segmentation scheme using an adaptive neural-network classifier architecture.

PubMed

Doulamis, A; Doulamis, N; Ntalianis, K; Kollias, S

2003-01-01

In this paper, an unsupervised video object (VO) segmentation and tracking algorithm is proposed based on an adaptable neural-network architecture. The proposed scheme comprises: 1) a VO tracking module and 2) an initial VO estimation module. Object tracking is handled as a classification problem and implemented through an adaptive network classifier, which provides better results compared to conventional motion-based tracking algorithms. Network adaptation is accomplished through an efficient and cost effective weight updating algorithm, providing a minimum degradation of the previous network knowledge and taking into account the current content conditions. A retraining set is constructed and used for this purpose based on initial VO estimation results. Two different scenarios are investigated. The first concerns extraction of human entities in video conferencing applications, while the second exploits depth information to identify generic VOs in stereoscopic video sequences. Human face/ body detection based on Gaussian distributions is accomplished in the first scenario, while segmentation fusion is obtained using color and depth information in the second scenario. A decision mechanism is also incorporated to detect time instances for weight updating. Experimental results and comparisons indicate the good performance of the proposed scheme even in sequences with complicated content (object bending, occlusion).

Research on the feature extraction and pattern recognition of the distributed optical fiber sensing signal

NASA Astrophysics Data System (ADS)

Wang, Bingjie; Sun, Qi; Pi, Shaohua; Wu, Hongyan

2014-09-01

In this paper, feature extraction and pattern recognition of the distributed optical fiber sensing signal have been studied. We adopt Mel-Frequency Cepstral Coefficient (MFCC) feature extraction, wavelet packet energy feature extraction and wavelet packet Shannon entropy feature extraction methods to obtain sensing signals (such as speak, wind, thunder and rain signals, etc.) characteristic vectors respectively, and then perform pattern recognition via RBF neural network. Performances of these three feature extraction methods are compared according to the results. We choose MFCC characteristic vector to be 12-dimensional. For wavelet packet feature extraction, signals are decomposed into six layers by Daubechies wavelet packet transform, in which 64 frequency constituents as characteristic vector are respectively extracted. In the process of pattern recognition, the value of diffusion coefficient is introduced to increase the recognition accuracy, while keeping the samples for testing algorithm the same. Recognition results show that wavelet packet Shannon entropy feature extraction method yields the best recognition accuracy which is up to 97%; the performance of 12-dimensional MFCC feature extraction method is less satisfactory; the performance of wavelet packet energy feature extraction method is the worst.
An assessment of Landsat MSS and TM data for urban and near-urban land-cover digital classification

NASA Technical Reports Server (NTRS)

Haack, Barry; Bryant, Nevin; Adams, Steven

1987-01-01

The information content of Landsat TM and MSS data was examined to assess the ability to digitally differentiate urban and near-urban land covers around Miami, FL. This examination included comparisons of unsupervised signature extractions for various cover types, training site statistics for intraclass and interclass separability, and band and band combination selection from an 11-band multisensor data set. The principal analytical tool used in this study was transformed divergence calculations. The TM digital data are typically more useful than the MSS data in the homogeneous near-urban land-covers and less useful in the heterogeneous urban areas.
DOE Office of Scientific and Technical Information (OSTI.GOV)

Harmon, S; Jeraj, R; Galavis, P

Purpose: Sensitivity of PET-derived texture features to reconstruction methods has been reported for features extracted from axial planes; however, studies often utilize three dimensional techniques. This work aims to quantify the impact of multi-plane (3D) vs. single-plane (2D) feature extraction on radiomics-based analysis, including sensitivity to reconstruction parameters and potential loss of spatial information. Methods: Twenty-three patients with solid tumors underwent [{sup 18}F]FDG PET/CT scans under identical protocols. PET data were reconstructed using five sets of reconstruction parameters. Tumors were segmented using an automatic, in-house algorithm robust to reconstruction variations. 50 texture features were extracted using two Methods: 2D patchesmore » along axial planes and 3D patches. For each method, sensitivity of features to reconstruction parameters was calculated as percent difference relative to the average value across reconstructions. Correlations between feature values were compared when using 2D and 3D extraction. Results: 21/50 features showed significantly different sensitivity to reconstruction parameters when extracted in 2D vs 3D (wilcoxon α<0.05), assessed by overall range of variation, Rangevar(%). Eleven showed greater sensitivity to reconstruction in 2D extraction, primarily first-order and co-occurrence features (average Rangevar increase 83%). The remaining ten showed higher variation in 3D extraction (average Range{sub var}increase 27%), mainly co-occurence and greylevel run-length features. Correlation of feature value extracted in 2D and feature value extracted in 3D was poor (R<0.5) in 12/50 features, including eight co-occurrence features. Feature-to-feature correlations in 2D were marginally higher than 3D, ∣R∣>0.8 in 16% and 13% of all feature combinations, respectively. Larger sensitivity to reconstruction parameters were seen for inter-feature correlation in 2D(σ=6%) than 3D (σ<1%) extraction. Conclusion: Sensitivity and correlation of various texture features were shown to significantly differ between 2D and 3D extraction. Additionally, inter-feature correlations were more sensitive to reconstruction variation using single-plane extraction. This work highlights a need for standardized feature extraction/selection techniques in radiomics.« less
Target recognition based on convolutional neural network

NASA Astrophysics Data System (ADS)

Wang, Liqiang; Wang, Xin; Xi, Fubiao; Dong, Jian

2017-11-01

One of the important part of object target recognition is the feature extraction, which can be classified into feature extraction and automatic feature extraction. The traditional neural network is one of the automatic feature extraction methods, while it causes high possibility of over-fitting due to the global connection. The deep learning algorithm used in this paper is a hierarchical automatic feature extraction method, trained with the layer-by-layer convolutional neural network (CNN), which can extract the features from lower layers to higher layers. The features are more discriminative and it is beneficial to the object target recognition.
Supervised versus unsupervised categorization: two sides of the same coin?

PubMed

Pothos, Emmanuel M; Edwards, Darren J; Perlman, Amotz

2011-09-01

Supervised and unsupervised categorization have been studied in separate research traditions. A handful of studies have attempted to explore a possible convergence between the two. The present research builds on these studies, by comparing the unsupervised categorization results of Pothos et al. ( 2011 ; Pothos et al., 2008 ) with the results from two procedures of supervised categorization. In two experiments, we tested 375 participants with nine different stimulus sets and examined the relation between ease of learning of a classification, memory for a classification, and spontaneous preference for a classification. After taking into account the role of the number of category labels (clusters) in supervised learning, we found the three variables to be closely associated with each other. Our results provide encouragement for researchers seeking unified theoretical explanations for supervised and unsupervised categorization, but raise a range of challenging theoretical questions.
Time-Frequency Learning Machines for Nonstationarity Detection Using Surrogates

NASA Astrophysics Data System (ADS)

Borgnat, Pierre; Flandrin, Patrick; Richard, Cédric; Ferrari, André; Amoud, Hassan; Honeine, Paul

2012-03-01

Time-frequency representations provide a powerful tool for nonstationary signal analysis and classification, supporting a wide range of applications [12]. As opposed to conventional Fourier analysis, these techniques reveal the evolution in time of the spectral content of signals. In Ref. [7,38], time-frequency analysis is used to test stationarity of any signal. The proposed method consists of a comparison between global and local time-frequency features. The originality is to make use of a family of stationary surrogate signals for defining the null hypothesis of stationarity and, based upon this information, to derive statistical tests. An open question remains, however, about how to choose relevant time-frequency features. Over the last decade, a number of new pattern recognition methods based on reproducing kernels have been introduced. These learning machines have gained popularity due to their conceptual simplicity and their outstanding performance [30]. Initiated by Vapnik’s support vector machines (SVM) [35], they offer now a wide class of supervised and unsupervised learning algorithms. In Ref. [17-19], the authors have shown how the most effective and innovative learning machines can be tuned to operate in the time-frequency domain. This chapter follows this line of research by taking advantage of learning machines to test and quantify stationarity. Based on one-class SVM, our approach uses the entire time-frequency representation and does not require arbitrary feature extraction. Applied to a set of surrogates, it provides the domain boundary that includes most of these stationarized signals. This allows us to test the stationarity of the signal under investigation. This chapter is organized as follows. In Section 22.2, we introduce the surrogate data method to generate stationarized signals, namely, the null hypothesis of stationarity. The concept of time-frequency learning machines is presented in Section 22.3, and applied to one-class SVM in order to derive a stationarity test in Section 22.4. The relevance of the latter is illustrated by simulation results in Section 22.5.
Blood Vessel Extraction in Color Retinal Fundus Images with Enhancement Filtering and Unsupervised Classification

PubMed Central

2017-01-01

Retinal blood vessels have a significant role in the diagnosis and treatment of various retinal diseases such as diabetic retinopathy, glaucoma, arteriosclerosis, and hypertension. For this reason, retinal vasculature extraction is important in order to help specialists for the diagnosis and treatment of systematic diseases. In this paper, a novel approach is developed to extract retinal blood vessel network. Our method comprises four stages: (1) preprocessing stage in order to prepare dataset for segmentation; (2) an enhancement procedure including Gabor, Frangi, and Gauss filters obtained separately before a top-hat transform; (3) a hard and soft clustering stage which includes K-means and Fuzzy C-means (FCM) in order to get binary vessel map; and (4) a postprocessing step which removes falsely segmented isolated regions. The method is tested on color retinal images obtained from STARE and DRIVE databases which are available online. As a result, Gabor filter followed by K-means clustering method achieves 95.94% and 95.71% of accuracy for STARE and DRIVE databases, respectively, which are acceptable for diagnosis systems. PMID:29065611
Vertical Feature Mask Feature Classification Flag Extraction

Atmospheric Science Data Center

2013-03-28

Vertical Feature Mask Feature Classification Flag Extraction This routine demonstrates extraction of the ... in a CALIPSO Lidar Level 2 Vertical Feature Mask feature classification flag value. It is written in Interactive Data Language (IDL) ...
Extracting features from protein sequences to improve deep extreme learning machine for protein fold recognition.

PubMed

Ibrahim, Wisam; Abadeh, Mohammad Saniee

2017-05-21

Protein fold recognition is an important problem in bioinformatics to predict three-dimensional structure of a protein. One of the most challenging tasks in protein fold recognition problem is the extraction of efficient features from the amino-acid sequences to obtain better classifiers. In this paper, we have proposed six descriptors to extract features from protein sequences. These descriptors are applied in the first stage of a three-stage framework PCA-DELM-LDA to extract feature vectors from the amino-acid sequences. Principal Component Analysis PCA has been implemented to reduce the number of extracted features. The extracted feature vectors have been used with original features to improve the performance of the Deep Extreme Learning Machine DELM in the second stage. Four new features have been extracted from the second stage and used in the third stage by Linear Discriminant Analysis LDA to classify the instances into 27 folds. The proposed framework is implemented on the independent and combined feature sets in SCOP datasets. The experimental results show that extracted feature vectors in the first stage could improve the performance of DELM in extracting new useful features in second stage. Copyright © 2017 Elsevier Ltd. All rights reserved.
Towards a new classification of stable phase schizophrenia into major and simple neuro-cognitive psychosis: Results of unsupervised machine learning analysis.

PubMed

Kanchanatawan, Buranee; Sriswasdi, Sira; Thika, Supaksorn; Stoyanov, Drozdstoy; Sirivichayakul, Sunee; Carvalho, André F; Geffard, Michel; Maes, Michael

2018-05-23

Deficit schizophrenia, as defined by the Schedule for Deficit Syndrome, may represent a distinct diagnostic class defined by neurocognitive impairments coupled with changes in IgA/IgM responses to tryptophan catabolites (TRYCATs). Adequate classifications should be based on supervised and unsupervised learning rather than on consensus criteria. This study used machine learning as means to provide a more accurate classification of patients with stable phase schizophrenia. We found that using negative symptoms as discriminatory variables, schizophrenia patients may be divided into two distinct classes modelled by (A) impairments in IgA/IgM responses to noxious and generally more protective tryptophan catabolites, (B) impairments in episodic and semantic memory, paired associative learning and false memory creation, and (C) psychotic, excitation, hostility, mannerism, negative, and affective symptoms. The first cluster shows increased negative, psychotic, excitation, hostility, mannerism, depression and anxiety symptoms, and more neuroimmune and cognitive disorders and is therefore called "major neurocognitive psychosis" (MNP). The second cluster, called "simple neurocognitive psychosis" (SNP) is discriminated from normal controls by the same features although the impairments are less well developed than in MNP. The latter is additionally externally validated by lowered quality of life, body mass (reflecting a leptosome body type), and education (reflecting lower cognitive reserve). Previous distinctions including "type 1" (positive)/"type 2" (negative) and DSM-IV-TR (eg, paranoid) schizophrenia could not be validated using machine learning techniques. Previous names of the illness, including schizophrenia, are not very adequate because they do not describe the features of the illness, namely, interrelated neuroimmune, cognitive, and clinical features. Stable-phase schizophrenia consists of 2 relevant qualitatively distinct categories or nosological entities with SNP being a less well-developed phenotype, while MNP is the full blown phenotype or core illness. Major neurocognitive psychosis and SNP should be added to the DSM-5 and incorporated into the Research Domain Criteria project. © 2018 John Wiley & Sons, Ltd.
Deep Supervised, but Not Unsupervised, Models May Explain IT Cortical Representation

PubMed Central

Khaligh-Razavi, Seyed-Mahdi; Kriegeskorte, Nikolaus

2014-01-01

Inferior temporal (IT) cortex in human and nonhuman primates serves visual object recognition. Computational object-vision models, although continually improving, do not yet reach human performance. It is unclear to what extent the internal representations of computational models can explain the IT representation. Here we investigate a wide range of computational model representations (37 in total), testing their categorization performance and their ability to account for the IT representational geometry. The models include well-known neuroscientific object-recognition models (e.g. HMAX, VisNet) along with several models from computer vision (e.g. SIFT, GIST, self-similarity features, and a deep convolutional neural network). We compared the representational dissimilarity matrices (RDMs) of the model representations with the RDMs obtained from human IT (measured with fMRI) and monkey IT (measured with cell recording) for the same set of stimuli (not used in training the models). Better performing models were more similar to IT in that they showed greater clustering of representational patterns by category. In addition, better performing models also more strongly resembled IT in terms of their within-category representational dissimilarities. Representational geometries were significantly correlated between IT and many of the models. However, the categorical clustering observed in IT was largely unexplained by the unsupervised models. The deep convolutional network, which was trained by supervision with over a million category-labeled images, reached the highest categorization performance and also best explained IT, although it did not fully explain the IT data. Combining the features of this model with appropriate weights and adding linear combinations that maximize the margin between animate and inanimate objects and between faces and other objects yielded a representation that fully explained our IT data. Overall, our results suggest that explaining IT requires computational features trained through supervised learning to emphasize the behaviorally important categorical divisions prominently reflected in IT. PMID:25375136
Unsupervised learning on scientific ocean drilling datasets from the South China Sea

NASA Astrophysics Data System (ADS)

Tse, Kevin C.; Chiu, Hon-Chim; Tsang, Man-Yin; Li, Yiliang; Lam, Edmund Y.

2018-06-01

Unsupervised learning methods were applied to explore data patterns in multivariate geophysical datasets collected from ocean floor sediment core samples coming from scientific ocean drilling in the South China Sea. Compared to studies on similar datasets, but using supervised learning methods which are designed to make predictions based on sample training data, unsupervised learning methods require no a priori information and focus only on the input data. In this study, popular unsupervised learning methods including K-means, self-organizing maps, hierarchical clustering and random forest were coupled with different distance metrics to form exploratory data clusters. The resulting data clusters were externally validated with lithologic units and geologic time scales assigned to the datasets by conventional methods. Compact and connected data clusters displayed varying degrees of correspondence with existing classification by lithologic units and geologic time scales. K-means and self-organizing maps were observed to perform better with lithologic units while random forest corresponded best with geologic time scales. This study sets a pioneering example of how unsupervised machine learning methods can be used as an automatic processing tool for the increasingly high volume of scientific ocean drilling data.
An Efficient Optimization Method for Solving Unsupervised Data Classification Problems.

PubMed

Shabanzadeh, Parvaneh; Yusof, Rubiyah

2015-01-01

Unsupervised data classification (or clustering) analysis is one of the most useful tools and a descriptive task in data mining that seeks to classify homogeneous groups of objects based on similarity and is used in many medical disciplines and various applications. In general, there is no single algorithm that is suitable for all types of data, conditions, and applications. Each algorithm has its own advantages, limitations, and deficiencies. Hence, research for novel and effective approaches for unsupervised data classification is still active. In this paper a heuristic algorithm, Biogeography-Based Optimization (BBO) algorithm, was adapted for data clustering problems by modifying the main operators of BBO algorithm, which is inspired from the natural biogeography distribution of different species. Similar to other population-based algorithms, BBO algorithm starts with an initial population of candidate solutions to an optimization problem and an objective function that is calculated for them. To evaluate the performance of the proposed algorithm assessment was carried on six medical and real life datasets and was compared with eight well known and recent unsupervised data classification algorithms. Numerical results demonstrate that the proposed evolutionary optimization algorithm is efficient for unsupervised data classification.
Hierarchical Representation Learning for Kinship Verification.

PubMed

Kohli, Naman; Vatsa, Mayank; Singh, Richa; Noore, Afzel; Majumdar, Angshul

2017-01-01

Kinship verification has a number of applications such as organizing large collections of images and recognizing resemblances among humans. In this paper, first, a human study is conducted to understand the capabilities of human mind and to identify the discriminatory areas of a face that facilitate kinship-cues. The visual stimuli presented to the participants determine their ability to recognize kin relationship using the whole face as well as specific facial regions. The effect of participant gender and age and kin-relation pair of the stimulus is analyzed using quantitative measures such as accuracy, discriminability index d' , and perceptual information entropy. Utilizing the information obtained from the human study, a hierarchical kinship verification via representation learning (KVRL) framework is utilized to learn the representation of different face regions in an unsupervised manner. We propose a novel approach for feature representation termed as filtered contractive deep belief networks (fcDBN). The proposed feature representation encodes relational information present in images using filters and contractive regularization penalty. A compact representation of facial images of kin is extracted as an output from the learned model and a multi-layer neural network is utilized to verify the kin accurately. A new WVU kinship database is created, which consists of multiple images per subject to facilitate kinship verification. The results show that the proposed deep learning framework (KVRL-fcDBN) yields the state-of-the-art kinship verification accuracy on the WVU kinship database and on four existing benchmark data sets. Furthermore, kinship information is used as a soft biometric modality to boost the performance of face verification via product of likelihood ratio and support vector machine based approaches. Using the proposed KVRL-fcDBN framework, an improvement of over 20% is observed in the performance of face verification.
Alzheimer disease detection from structural MR images using FCM based weighted probabilistic neural network.

PubMed

Duraisamy, Baskar; Shanmugam, Jayanthi Venkatraman; Annamalai, Jayanthi

2018-02-19

An early intervention of Alzheimer's disease (AD) is highly essential due to the fact that this neuro degenerative disease generates major life-threatening issues, especially memory loss among patients in society. Moreover, categorizing NC (Normal Control), MCI (Mild Cognitive Impairment) and AD early in course allows the patients to experience benefits from new treatments. Therefore, it is important to construct a reliable classification technique to discriminate the patients with or without AD from the bio medical imaging modality. Hence, we developed a novel FCM based Weighted Probabilistic Neural Network (FWPNN) classification algorithm and analyzed the brain images related to structural MRI modality for better discrimination of class labels. Initially our proposed framework begins with brain image normalization stage. In this stage, ROI regions related to Hippo-Campus (HC) and Posterior Cingulate Cortex (PCC) from the brain images are extracted using Automated Anatomical Labeling (AAL) method. Subsequently, nineteen highly relevant AD related features are selected through Multiple-criterion feature selection method. At last, our novel FWPNN classification algorithm is imposed to remove suspicious samples from the training data with an end goal to enhance the classification performance. This newly developed classification algorithm combines both the goodness of supervised and unsupervised learning techniques. The experimental validation is carried out with the ADNI subset and then to the Bordex-3 city dataset. Our proposed classification approach achieves an accuracy of about 98.63%, 95.4%, 96.4% in terms of classification with AD vs NC, MCI vs NC and AD vs MCI. The experimental results suggest that the removal of noisy samples from the training data can enhance the decision generation process of the expert systems.
Iris recognition based on key image feature extraction.

PubMed

Ren, X; Tian, Q; Zhang, J; Wu, S; Zeng, Y

2008-01-01

In iris recognition, feature extraction can be influenced by factors such as illumination and contrast, and thus the features extracted may be unreliable, which can cause a high rate of false results in iris pattern recognition. In order to obtain stable features, an algorithm was proposed in this paper to extract key features of a pattern from multiple images. The proposed algorithm built an iris feature template by extracting key features and performed iris identity enrolment. Simulation results showed that the selected key features have high recognition accuracy on the CASIA Iris Set, where both contrast and illumination variance exist.
An unsupervised classification technique for multispectral remote sensing data.

NASA Technical Reports Server (NTRS)

Su, M. Y.; Cummings, R. E.

1973-01-01

Description of a two-part clustering technique consisting of (a) a sequential statistical clustering, which is essentially a sequential variance analysis, and (b) a generalized K-means clustering. In this composite clustering technique, the output of (a) is a set of initial clusters which are input to (b) for further improvement by an iterative scheme. This unsupervised composite technique was employed for automatic classification of two sets of remote multispectral earth resource observations. The classification accuracy by the unsupervised technique is found to be comparable to that by traditional supervised maximum-likelihood classification techniques.
Unsupervised classification of earth resources data.

NASA Technical Reports Server (NTRS)

Su, M. Y.; Jayroe, R. R., Jr.; Cummings, R. E.

1972-01-01

A new clustering technique is presented. It consists of two parts: (a) a sequential statistical clustering which is essentially a sequential variance analysis and (b) a generalized K-means clustering. In this composite clustering technique, the output of (a) is a set of initial clusters which are input to (b) for further improvement by an iterative scheme. This unsupervised composite technique was employed for automatic classification of two sets of remote multispectral earth resource observations. The classification accuracy by the unsupervised technique is found to be comparable to that by existing supervised maximum liklihood classification technique.
Non-negative matrix factorisation methods for the spectral decomposition of MRS data from human brain tumours

PubMed Central

2012-01-01

Background In-vivo single voxel proton magnetic resonance spectroscopy (SV 1H-MRS), coupled with supervised pattern recognition (PR) methods, has been widely used in clinical studies of discrimination of brain tumour types and follow-up of patients bearing abnormal brain masses. SV 1H-MRS provides useful biochemical information about the metabolic state of tumours and can be performed at short (< 45 ms) or long (> 45 ms) echo time (TE), each with particular advantages. Short-TE spectra are more adequate for detecting lipids, while the long-TE provides a much flatter signal baseline in between peaks but also negative signals for metabolites such as lactate. Both, lipids and lactate, are respectively indicative of specific metabolic processes taking place. Ideally, the information provided by both TE should be of use for clinical purposes. In this study, we characterise the performance of a range of Non-negative Matrix Factorisation (NMF) methods in two respects: first, to derive sources correlated with the mean spectra of known tissue types (tumours and normal tissue); second, taking the best performing NMF method for source separation, we compare its accuracy for class assignment when using the mixing matrix directly as a basis for classification, as against using the method for dimensionality reduction (DR). For this, we used SV 1H-MRS data with positive and negative peaks, from a widely tested SV 1H-MRS human brain tumour database. Results The results reported in this paper reveal the advantage of using a recently described variant of NMF, namely Convex-NMF, as an unsupervised method of source extraction from SV1H-MRS. Most of the sources extracted in our experiments closely correspond to the mean spectra of some of the analysed tumour types. This similarity allows accurate diagnostic predictions to be made both in fully unsupervised mode and using Convex-NMF as a DR step previous to standard supervised classification. The obtained results are comparable to, or more accurate than those obtained with supervised techniques. Conclusions The unsupervised properties of Convex-NMF place this approach one step ahead of classical label-requiring supervised methods for the discrimination of brain tumour types, as it accounts for their increasingly recognised molecular subtype heterogeneity. The application of Convex-NMF in computer assisted decision support systems is expected to facilitate further improvements in the uptake of MRS-derived information by clinicians. PMID:22401579
Experience improves feature extraction in Drosophila.

PubMed

Peng, Yueqing; Xi, Wang; Zhang, Wei; Zhang, Ke; Guo, Aike

2007-05-09

Previous exposure to a pattern in the visual scene can enhance subsequent recognition of that pattern in many species from honeybees to humans. However, whether previous experience with a visual feature of an object, such as color or shape, can also facilitate later recognition of that particular feature from multiple visual features is largely unknown. Visual feature extraction is the ability to select the key component from multiple visual features. Using a visual flight simulator, we designed a novel protocol for visual feature extraction to investigate the effects of previous experience on visual reinforcement learning in Drosophila. We found that, after conditioning with a visual feature of objects among combinatorial shape-color features, wild-type flies exhibited poor ability to extract the correct visual feature. However, the ability for visual feature extraction was greatly enhanced in flies trained previously with that visual feature alone. Moreover, we demonstrated that flies might possess the ability to extract the abstract category of "shape" but not a particular shape. Finally, this experience-dependent feature extraction is absent in flies with defective MBs, one of the central brain structures in Drosophila. Our results indicate that previous experience can enhance visual feature extraction in Drosophila and that MBs are required for this experience-dependent visual cognition.

Some links on this page may take you to non-federal websites. Their policies may differ from this site.