Combining Feature Extraction Methods to Assist the Diagnosis of Alzheimer's Disease.

PubMed

Segovia, F; Górriz, J M; Ramírez, J; Phillips, C

2016-01-01

Neuroimaging data as (18)F-FDG PET is widely used to assist the diagnosis of Alzheimer's disease (AD). Looking for regions with hypoperfusion/ hypometabolism, clinicians may predict or corroborate the diagnosis of the patients. Modern computer aided diagnosis (CAD) systems based on the statistical analysis of whole neuroimages are more accurate than classical systems based on quantifying the uptake of some predefined regions of interests (ROIs). In addition, these new systems allow determining new ROIs and take advantage of the huge amount of information comprised in neuroimaging data. A major branch of modern CAD systems for AD is based on multivariate techniques, which analyse a neuroimage as a whole, considering not only the voxel intensities but also the relations among them. In order to deal with the vast dimensionality of the data, a number of feature extraction methods have been successfully applied. In this work, we propose a CAD system based on the combination of several feature extraction techniques. First, some commonly used feature extraction methods based on the analysis of the variance (as principal component analysis), on the factorization of the data (as non-negative matrix factorization) and on classical magnitudes (as Haralick features) were simultaneously applied to the original data. These feature sets were then combined by means of two different combination approaches: i) using a single classifier and a multiple kernel learning approach and ii) using an ensemble of classifier and selecting the final decision by majority voting. The proposed approach was evaluated using a labelled neuroimaging database along with a cross validation scheme. As conclusion, the proposed CAD system performed better than approaches using only one feature extraction technique. We also provide a fair comparison (using the same database) of the selected feature extraction methods.

A novel approach for SEMG signal classification with adaptive local binary patterns.

PubMed

Ertuğrul, Ömer Faruk; Kaya, Yılmaz; Tekin, Ramazan

2016-07-01

Feature extraction plays a major role in the pattern recognition process, and this paper presents a novel feature extraction approach, adaptive local binary pattern (aLBP). aLBP is built on the local binary pattern (LBP), which is an image processing method, and one-dimensional local binary pattern (1D-LBP). In LBP, each pixel is compared with its neighbors. Similarly, in 1D-LBP, each data in the raw is judged against its neighbors. 1D-LBP extracts feature based on local changes in the signal. Therefore, it has high a potential to be employed in medical purposes. Since, each action or abnormality, which is recorded in SEMG signals, has its own pattern, and via the 1D-LBP these (hidden) patterns may be detected. But, the positions of the neighbors in 1D-LBP are constant depending on the position of the data in the raw. Also, both LBP and 1D-LBP are very sensitive to noise. Therefore, its capacity in detecting hidden patterns is limited. To overcome these drawbacks, aLBP was proposed. In aLBP, the positions of the neighbors and their values can be assigned adaptively via the down-sampling and the smoothing coefficients. Therefore, the potential to detect (hidden) patterns, which may express an illness or an action, is really increased. To validate the proposed feature extraction approach, two different datasets were employed. Achieved accuracies by the proposed approach were higher than obtained results by employed popular feature extraction approaches and the reported results in the literature. Obtained accuracy results were brought out that the proposed method can be employed to investigate SEMG signals. In summary, this work attempts to develop an adaptive feature extraction scheme that can be utilized for extracting features from local changes in different categories of time-varying signals.

Bearing Fault Diagnosis Based on Statistical Locally Linear Embedding

PubMed Central

Wang, Xiang; Zheng, Yuan; Zhao, Zhenzhou; Wang, Jinping

2015-01-01

Fault diagnosis is essentially a kind of pattern recognition. The measured signal samples usually distribute on nonlinear low-dimensional manifolds embedded in the high-dimensional signal space, so how to implement feature extraction, dimensionality reduction and improve recognition performance is a crucial task. In this paper a novel machinery fault diagnosis approach based on a statistical locally linear embedding (S-LLE) algorithm which is an extension of LLE by exploiting the fault class label information is proposed. The fault diagnosis approach first extracts the intrinsic manifold features from the high-dimensional feature vectors which are obtained from vibration signals that feature extraction by time-domain, frequency-domain and empirical mode decomposition (EMD), and then translates the complex mode space into a salient low-dimensional feature space by the manifold learning algorithm S-LLE, which outperforms other feature reduction methods such as PCA, LDA and LLE. Finally in the feature reduction space pattern classification and fault diagnosis by classifier are carried out easily and rapidly. Rolling bearing fault signals are used to validate the proposed fault diagnosis approach. The results indicate that the proposed approach obviously improves the classification performance of fault pattern recognition and outperforms the other traditional approaches. PMID:26153771

Improving protein fold recognition by extracting fold-specific features from predicted residue-residue contacts.

PubMed

Zhu, Jianwei; Zhang, Haicang; Li, Shuai Cheng; Wang, Chao; Kong, Lupeng; Sun, Shiwei; Zheng, Wei-Mou; Bu, Dongbo

2017-12-01

Accurate recognition of protein fold types is a key step for template-based prediction of protein structures. The existing approaches to fold recognition mainly exploit the features derived from alignments of query protein against templates. These approaches have been shown to be successful for fold recognition at family level, but usually failed at superfamily/fold levels. To overcome this limitation, one of the key points is to explore more structurally informative features of proteins. Although residue-residue contacts carry abundant structural information, how to thoroughly exploit these information for fold recognition still remains a challenge. In this study, we present an approach (called DeepFR) to improve fold recognition at superfamily/fold levels. The basic idea of our approach is to extract fold-specific features from predicted residue-residue contacts of proteins using deep convolutional neural network (DCNN) technique. Based on these fold-specific features, we calculated similarity between query protein and templates, and then assigned query protein with fold type of the most similar template. DCNN has showed excellent performance in image feature extraction and image recognition; the rational underlying the application of DCNN for fold recognition is that contact likelihood maps are essentially analogy to images, as they both display compositional hierarchy. Experimental results on the LINDAHL dataset suggest that even using the extracted fold-specific features alone, our approach achieved success rate comparable to the state-of-the-art approaches. When further combining these features with traditional alignment-related features, the success rate of our approach increased to 92.3%, 82.5% and 78.8% at family, superfamily and fold levels, respectively, which is about 18% higher than the state-of-the-art approach at fold level, 6% higher at superfamily level and 1% higher at family level. An independent assessment on SCOP_TEST dataset showed consistent performance improvement, indicating robustness of our approach. Furthermore, bi-clustering results of the extracted features are compatible with fold hierarchy of proteins, implying that these features are fold-specific. Together, these results suggest that the features extracted from predicted contacts are orthogonal to alignment-related features, and the combination of them could greatly facilitate fold recognition at superfamily/fold levels and template-based prediction of protein structures. Source code of DeepFR is freely available through https://github.com/zhujianwei31415/deepfr, and a web server is available through http://protein.ict.ac.cn/deepfr. zheng@itp.ac.cn or dbu@ict.ac.cn. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Toward better public health reporting using existing off the shelf approaches: The value of medical dictionaries in automated cancer detection using plaintext medical data.

PubMed

Kasthurirathne, Suranga N; Dixon, Brian E; Gichoya, Judy; Xu, Huiping; Xia, Yuni; Mamlin, Burke; Grannis, Shaun J

2017-05-01

Existing approaches to derive decision models from plaintext clinical data frequently depend on medical dictionaries as the sources of potential features. Prior research suggests that decision models developed using non-dictionary based feature sourcing approaches and "off the shelf" tools could predict cancer with performance metrics between 80% and 90%. We sought to compare non-dictionary based models to models built using features derived from medical dictionaries. We evaluated the detection of cancer cases from free text pathology reports using decision models built with combinations of dictionary or non-dictionary based feature sourcing approaches, 4 feature subset sizes, and 5 classification algorithms. Each decision model was evaluated using the following performance metrics: sensitivity, specificity, accuracy, positive predictive value, and area under the receiver operating characteristics (ROC) curve. Decision models parameterized using dictionary and non-dictionary feature sourcing approaches produced performance metrics between 70 and 90%. The source of features and feature subset size had no impact on the performance of a decision model. Our study suggests there is little value in leveraging medical dictionaries for extracting features for decision model building. Decision models built using features extracted from the plaintext reports themselves achieve comparable results to those built using medical dictionaries. Overall, this suggests that existing "off the shelf" approaches can be leveraged to perform accurate cancer detection using less complex Named Entity Recognition (NER) based feature extraction, automated feature selection and modeling approaches. Copyright © 2017 Elsevier Inc. All rights reserved.

Spectral Regression Based Fault Feature Extraction for Bearing Accelerometer Sensor Signals

PubMed Central

Xia, Zhanguo; Xia, Shixiong; Wan, Ling; Cai, Shiyu

2012-01-01

Bearings are not only the most important element but also a common source of failures in rotary machinery. Bearing fault prognosis technology has been receiving more and more attention recently, in particular because it plays an increasingly important role in avoiding the occurrence of accidents. Therein, fault feature extraction (FFE) of bearing accelerometer sensor signals is essential to highlight representative features of bearing conditions for machinery fault diagnosis and prognosis. This paper proposes a spectral regression (SR)-based approach for fault feature extraction from original features including time, frequency and time-frequency domain features of bearing accelerometer sensor signals. SR is a novel regression framework for efficient regularized subspace learning and feature extraction technology, and it uses the least squares method to obtain the best projection direction, rather than computing the density matrix of features, so it also has the advantage in dimensionality reduction. The effectiveness of the SR-based method is validated experimentally by applying the acquired vibration signals data to bearings. The experimental results indicate that SR can reduce the computation cost and preserve more structure information about different bearing faults and severities, and it is demonstrated that the proposed feature extraction scheme has an advantage over other similar approaches. PMID:23202017

Novel Features for Brain-Computer Interfaces

PubMed Central

Woon, W. L.; Cichocki, A.

2007-01-01

While conventional approaches of BCI feature extraction are based on the power spectrum, we have tried using nonlinear features for classifying BCI data. In this paper, we report our test results and findings, which indicate that the proposed method is a potentially useful addition to current feature extraction techniques. PMID:18364991

A method of evolving novel feature extraction algorithms for detecting buried objects in FLIR imagery using genetic programming

NASA Astrophysics Data System (ADS)

Paino, A.; Keller, J.; Popescu, M.; Stone, K.

2014-06-01

In this paper we present an approach that uses Genetic Programming (GP) to evolve novel feature extraction algorithms for greyscale images. Our motivation is to create an automated method of building new feature extraction algorithms for images that are competitive with commonly used human-engineered features, such as Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG). The evolved feature extraction algorithms are functions defined over the image space, and each produces a real-valued feature vector of variable length. Each evolved feature extractor breaks up the given image into a set of cells centered on every pixel, performs evolved operations on each cell, and then combines the results of those operations for every cell using an evolved operator. Using this method, the algorithm is flexible enough to reproduce both LBP and HOG features. The dataset we use to train and test our approach consists of a large number of pre-segmented image "chips" taken from a Forward Looking Infrared Imagery (FLIR) camera mounted on the hood of a moving vehicle. The goal is to classify each image chip as either containing or not containing a buried object. To this end, we define the fitness of a candidate solution as the cross-fold validation accuracy of the features generated by said candidate solution when used in conjunction with a Support Vector Machine (SVM) classifier. In order to validate our approach, we compare the classification accuracy of an SVM trained using our evolved features with the accuracy of an SVM trained using mainstream feature extraction algorithms, including LBP and HOG.

Feature extraction based on semi-supervised kernel Marginal Fisher analysis and its application in bearing fault diagnosis

NASA Astrophysics Data System (ADS)

Jiang, Li; Xuan, Jianping; Shi, Tielin

2013-12-01

Generally, the vibration signals of faulty machinery are non-stationary and nonlinear under complicated operating conditions. Therefore, it is a big challenge for machinery fault diagnosis to extract optimal features for improving classification accuracy. This paper proposes semi-supervised kernel Marginal Fisher analysis (SSKMFA) for feature extraction, which can discover the intrinsic manifold structure of dataset, and simultaneously consider the intra-class compactness and the inter-class separability. Based on SSKMFA, a novel approach to fault diagnosis is put forward and applied to fault recognition of rolling bearings. SSKMFA directly extracts the low-dimensional characteristics from the raw high-dimensional vibration signals, by exploiting the inherent manifold structure of both labeled and unlabeled samples. Subsequently, the optimal low-dimensional features are fed into the simplest K-nearest neighbor (KNN) classifier to recognize different fault categories and severities of bearings. The experimental results demonstrate that the proposed approach improves the fault recognition performance and outperforms the other four feature extraction methods.

Hybrid Discrete Wavelet Transform and Gabor Filter Banks Processing for Features Extraction from Biomedical Images

PubMed Central

Lahmiri, Salim; Boukadoum, Mounir

2013-01-01

A new methodology for automatic feature extraction from biomedical images and subsequent classification is presented. The approach exploits the spatial orientation of high-frequency textural features of the processed image as determined by a two-step process. First, the two-dimensional discrete wavelet transform (DWT) is applied to obtain the HH high-frequency subband image. Then, a Gabor filter bank is applied to the latter at different frequencies and spatial orientations to obtain new Gabor-filtered image whose entropy and uniformity are computed. Finally, the obtained statistics are fed to a support vector machine (SVM) binary classifier. The approach was validated on mammograms, retina, and brain magnetic resonance (MR) images. The obtained classification accuracies show better performance in comparison to common approaches that use only the DWT or Gabor filter banks for feature extraction. PMID:27006906

Comparison of the application of B-mode and strain elastography ultrasound in the estimation of lymph node metastasis of papillary thyroid carcinoma based on a radiomics approach.

PubMed

Liu, Tongtong; Ge, Xifeng; Yu, Jinhua; Guo, Yi; Wang, Yuanyuan; Wang, Wenping; Cui, Ligang

2018-06-21

B-mode ultrasound (B-US) and strain elastography ultrasound (SE-US) images have a potential to distinguish thyroid tumor with different lymph node (LN) status. The purpose of our study is to investigate whether the application of multi-modality images including B-US and SE-US can improve the discriminability of thyroid tumor with LN metastasis based on a radiomics approach. Ultrasound (US) images including B-US and SE-US images of 75 papillary thyroid carcinoma (PTC) cases were retrospectively collected. A radiomics approach was developed in this study to estimate LNs status of PTC patients. The approach included image segmentation, quantitative feature extraction, feature selection and classification. Three feature sets were extracted from B-US, SE-US, and multi-modality containing B-US and SE-US. They were used to evaluate the contribution of different modalities. A total of 684 radiomics features have been extracted in our study. We used sparse representation coefficient-based feature selection method with 10-bootstrap to reduce the dimension of feature sets. Support vector machine with leave-one-out cross-validation was used to build the model for estimating LN status. Using features extracted from both B-US and SE-US, the radiomics-based model produced an area under the receiver operating characteristic curve (AUC) [Formula: see text] 0.90, accuracy (ACC) [Formula: see text] 0.85, sensitivity (SENS) [Formula: see text] 0.77 and specificity (SPEC) [Formula: see text] 0.88, which was better than using features extracted from B-US or SE-US separately. Multi-modality images provided more information in radiomics study. Combining use of B-US and SE-US could improve the LN metastasis estimation accuracy for PTC patients.

What is a Dune: Developing AN Automated Approach to Extracting Dunes from Digital Elevation Models

NASA Astrophysics Data System (ADS)

Taylor, H.; DeCuir, C.; Wernette, P. A.; Taube, C.; Eyler, R.; Thopson, S.

2016-12-01

Coastal dunes can absorb storm surge and mitigate inland erosion caused by elevated water levels during a storm. In order to understand how a dune responds to and recovers from a storm, it is important that we can first identify and differentiate the beach and dune from the rest of the landscape. Current literature does not provide a consistent definition of what the dune features (e.g. dune toe, dune crest) are or how they can be extracted. The purpose of this research is to develop enhanced approaches to extracting dunes from a digital elevation model (DEM). Manual delineation, convergence index, least-cost path, relative relief, and vegetation abundance were compared and contrasted on a small area of Padre Island National Seashore (PAIS), Preliminary results indicate that the method used to extract the dune greatly affects our interpretation of how the dune changes. The manual delineation method was time intensive and subjective, while the convergence index approach was useful to easily identify the dune crest through maximum and minimum values. The least-cost path method proved to be time intensive due to data clipping; however, this approach resulted in continuous geomorphic landscape features (e.g. dune toe, dune crest). While the relative relief approach shows the most features in multi resolution, it is difficult to assess the accuracy of the extracted features because extracted features appear as points that can vary widely in their location from one meter to the next. The vegetation approach was greatly impacted by the seasonal and annual fluctuations of growth but is advantageous in historical change studies because it can be used to extract consistent dune formation from historical aerial imagery. Improving our ability to more accurately assess dune response and recovery to a storm will enable coastal managers to more accurately predict how dunes may respond to future climate change scenarios.

Prediction of occult invasive disease in ductal carcinoma in situ using computer-extracted mammographic features

NASA Astrophysics Data System (ADS)

Shi, Bibo; Grimm, Lars J.; Mazurowski, Maciej A.; Marks, Jeffrey R.; King, Lorraine M.; Maley, Carlo C.; Hwang, E. Shelley; Lo, Joseph Y.

2017-03-01

Predicting the risk of occult invasive disease in ductal carcinoma in situ (DCIS) is an important task to help address the overdiagnosis and overtreatment problems associated with breast cancer. In this work, we investigated the feasibility of using computer-extracted mammographic features to predict occult invasive disease in patients with biopsy proven DCIS. We proposed a computer-vision algorithm based approach to extract mammographic features from magnification views of full field digital mammography (FFDM) for patients with DCIS. After an expert breast radiologist provided a region of interest (ROI) mask for the DCIS lesion, the proposed approach is able to segment individual microcalcifications (MCs), detect the boundary of the MC cluster (MCC), and extract 113 mammographic features from MCs and MCC within the ROI. In this study, we extracted mammographic features from 99 patients with DCIS (74 pure DCIS; 25 DCIS plus invasive disease). The predictive power of the mammographic features was demonstrated through binary classifications between pure DCIS and DCIS with invasive disease using linear discriminant analysis (LDA). Before classification, the minimum redundancy Maximum Relevance (mRMR) feature selection method was first applied to choose subsets of useful features. The generalization performance was assessed using Leave-One-Out Cross-Validation and Receiver Operating Characteristic (ROC) curve analysis. Using the computer-extracted mammographic features, the proposed model was able to distinguish DCIS with invasive disease from pure DCIS, with an average classification performance of AUC = 0.61 +/- 0.05. Overall, the proposed computer-extracted mammographic features are promising for predicting occult invasive disease in DCIS.

Visual words for lip-reading

NASA Astrophysics Data System (ADS)

Hassanat, Ahmad B. A.; Jassim, Sabah

2010-04-01

In this paper, the automatic lip reading problem is investigated, and an innovative approach to providing solutions to this problem has been proposed. This new VSR approach is dependent on the signature of the word itself, which is obtained from a hybrid feature extraction method dependent on geometric, appearance, and image transform features. The proposed VSR approach is termed "visual words". The visual words approach consists of two main parts, 1) Feature extraction/selection, and 2) Visual speech feature recognition. After localizing face and lips, several visual features for the lips where extracted. Such as the height and width of the mouth, mutual information and the quality measurement between the DWT of the current ROI and the DWT of the previous ROI, the ratio of vertical to horizontal features taken from DWT of ROI, The ratio of vertical edges to horizontal edges of ROI, the appearance of the tongue and the appearance of teeth. Each spoken word is represented by 8 signals, one of each feature. Those signals maintain the dynamic of the spoken word, which contains a good portion of information. The system is then trained on these features using the KNN and DTW. This approach has been evaluated using a large database for different people, and large experiment sets. The evaluation has proved the visual words efficiency, and shown that the VSR is a speaker dependent problem.

A novel murmur-based heart sound feature extraction technique using envelope-morphological analysis

NASA Astrophysics Data System (ADS)

Yao, Hao-Dong; Ma, Jia-Li; Fu, Bin-Bin; Wang, Hai-Yang; Dong, Ming-Chui

2015-07-01

Auscultation of heart sound (HS) signals serves as an important primary approach to diagnose cardiovascular diseases (CVDs) for centuries. Confronting the intrinsic drawbacks of traditional HS auscultation, computer-aided automatic HS auscultation based on feature extraction technique has witnessed explosive development. Yet, most existing HS feature extraction methods adopt acoustic or time-frequency features which exhibit poor relationship with diagnostic information, thus restricting the performance of further interpretation and analysis. Tackling such a bottleneck problem, this paper innovatively proposes a novel murmur-based HS feature extraction method since murmurs contain massive pathological information and are regarded as the first indications of pathological occurrences of heart valves. Adapting discrete wavelet transform (DWT) and Shannon envelope, the envelope-morphological characteristics of murmurs are obtained and three features are extracted accordingly. Validated by discriminating normal HS and 5 various abnormal HS signals with extracted features, the proposed method provides an attractive candidate in automatic HS auscultation.

Feature extraction with deep neural networks by a generalized discriminant analysis.

PubMed

Stuhlsatz, André; Lippel, Jens; Zielke, Thomas

2012-04-01

We present an approach to feature extraction that is a generalization of the classical linear discriminant analysis (LDA) on the basis of deep neural networks (DNNs). As for LDA, discriminative features generated from independent Gaussian class conditionals are assumed. This modeling has the advantages that the intrinsic dimensionality of the feature space is bounded by the number of classes and that the optimal discriminant function is linear. Unfortunately, linear transformations are insufficient to extract optimal discriminative features from arbitrarily distributed raw measurements. The generalized discriminant analysis (GerDA) proposed in this paper uses nonlinear transformations that are learnt by DNNs in a semisupervised fashion. We show that the feature extraction based on our approach displays excellent performance on real-world recognition and detection tasks, such as handwritten digit recognition and face detection. In a series of experiments, we evaluate GerDA features with respect to dimensionality reduction, visualization, classification, and detection. Moreover, we show that GerDA DNNs can preprocess truly high-dimensional input data to low-dimensional representations that facilitate accurate predictions even if simple linear predictors or measures of similarity are used.

An approach for automatic classification of grouper vocalizations with passive acoustic monitoring.

PubMed

Ibrahim, Ali K; Chérubin, Laurent M; Zhuang, Hanqi; Schärer Umpierre, Michelle T; Dalgleish, Fraser; Erdol, Nurgun; Ouyang, B; Dalgleish, A

2018-02-01

Grouper, a family of marine fishes, produce distinct vocalizations associated with their reproductive behavior during spawning aggregation. These low frequencies sounds (50-350 Hz) consist of a series of pulses repeated at a variable rate. In this paper, an approach is presented for automatic classification of grouper vocalizations from ambient sounds recorded in situ with fixed hydrophones based on weighted features and sparse classifier. Group sounds were labeled initially by humans for training and testing various feature extraction and classification methods. In the feature extraction phase, four types of features were used to extract features of sounds produced by groupers. Once the sound features were extracted, three types of representative classifiers were applied to categorize the species that produced these sounds. Experimental results showed that the overall percentage of identification using the best combination of the selected feature extractor weighted mel frequency cepstral coefficients and sparse classifier achieved 82.7% accuracy. The proposed algorithm has been implemented in an autonomous platform (wave glider) for real-time detection and classification of group vocalizations.

A Deep Learning Approach for Fault Diagnosis of Induction Motors in Manufacturing

NASA Astrophysics Data System (ADS)

Shao, Si-Yu; Sun, Wen-Jun; Yan, Ru-Qiang; Wang, Peng; Gao, Robert X.

2017-11-01

Extracting features from original signals is a key procedure for traditional fault diagnosis of induction motors, as it directly influences the performance of fault recognition. However, high quality features need expert knowledge and human intervention. In this paper, a deep learning approach based on deep belief networks (DBN) is developed to learn features from frequency distribution of vibration signals with the purpose of characterizing working status of induction motors. It combines feature extraction procedure with classification task together to achieve automated and intelligent fault diagnosis. The DBN model is built by stacking multiple-units of restricted Boltzmann machine (RBM), and is trained using layer-by-layer pre-training algorithm. Compared with traditional diagnostic approaches where feature extraction is needed, the presented approach has the ability of learning hierarchical representations, which are suitable for fault classification, directly from frequency distribution of the measurement data. The structure of the DBN model is investigated as the scale and depth of the DBN architecture directly affect its classification performance. Experimental study conducted on a machine fault simulator verifies the effectiveness of the deep learning approach for fault diagnosis of induction motors. This research proposes an intelligent diagnosis method for induction motor which utilizes deep learning model to automatically learn features from sensor data and realize working status recognition.

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.

[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.

A new breast cancer risk analysis approach using features extracted from multiple sub-regions on bilateral mammograms

NASA Astrophysics Data System (ADS)

Sun, Wenqing; Tseng, Tzu-Liang B.; Zheng, Bin; Zhang, Jianying; Qian, Wei

2015-03-01

A novel breast cancer risk analysis approach is proposed for enhancing performance of computerized breast cancer risk analysis using bilateral mammograms. Based on the intensity of breast area, five different sub-regions were acquired from one mammogram, and bilateral features were extracted from every sub-region. Our dataset includes 180 bilateral mammograms from 180 women who underwent routine screening examinations, all interpreted as negative and not recalled by the radiologists during the original screening procedures. A computerized breast cancer risk analysis scheme using four image processing modules, including sub-region segmentation, bilateral feature extraction, feature selection, and classification was designed to detect and compute image feature asymmetry between the left and right breasts imaged on the mammograms. The highest computed area under the curve (AUC) is 0.763 ± 0.021 when applying the multiple sub-region features to our testing dataset. The positive predictive value and the negative predictive value were 0.60 and 0.73, respectively. The study demonstrates that (1) features extracted from multiple sub-regions can improve the performance of our scheme compared to using features from whole breast area only; (2) a classifier using asymmetry bilateral features can effectively predict breast cancer risk; (3) incorporating texture and morphological features with density features can boost the classification accuracy.

Approximation-based common principal component for feature extraction in multi-class brain-computer interfaces.

PubMed

Hoang, Tuan; Tran, Dat; Huang, Xu

2013-01-01

Common Spatial Pattern (CSP) is a state-of-the-art method for feature extraction in Brain-Computer Interface (BCI) systems. However it is designed for 2-class BCI classification problems. Current extensions of this method to multiple classes based on subspace union and covariance matrix similarity do not provide a high performance. This paper presents a new approach to solving multi-class BCI classification problems by forming a subspace resembled from original subspaces and the proposed method for this approach is called Approximation-based Common Principal Component (ACPC). We perform experiments on Dataset 2a used in BCI Competition IV to evaluate the proposed method. This dataset was designed for motor imagery classification with 4 classes. Preliminary experiments show that the proposed ACPC feature extraction method when combining with Support Vector Machines outperforms CSP-based feature extraction methods on the experimental dataset.

Variability extraction and modeling for product variants.

PubMed

Linsbauer, Lukas; Lopez-Herrejon, Roberto Erick; Egyed, Alexander

2017-01-01

Fast-changing hardware and software technologies in addition to larger and more specialized customer bases demand software tailored to meet very diverse requirements. Software development approaches that aim at capturing this diversity on a single consolidated platform often require large upfront investments, e.g., time or budget. Alternatively, companies resort to developing one variant of a software product at a time by reusing as much as possible from already-existing product variants. However, identifying and extracting the parts to reuse is an error-prone and inefficient task compounded by the typically large number of product variants. Hence, more disciplined and systematic approaches are needed to cope with the complexity of developing and maintaining sets of product variants. Such approaches require detailed information about the product variants, the features they provide and their relations. In this paper, we present an approach to extract such variability information from product variants. It identifies traces from features and feature interactions to their implementation artifacts, and computes their dependencies. This work can be useful in many scenarios ranging from ad hoc development approaches such as clone-and-own to systematic reuse approaches such as software product lines. We applied our variability extraction approach to six case studies and provide a detailed evaluation. The results show that the extracted variability information is consistent with the variability in our six case study systems given by their variability models and available product variants.

Combining Model-Based and Feature-Driven Diagnosis Approaches - A Case Study on Electromechanical Actuators

NASA Technical Reports Server (NTRS)

Narasimhan, Sriram; Roychoudhury, Indranil; Balaban, Edward; Saxena, Abhinav

2010-01-01

Model-based diagnosis typically uses analytical redundancy to compare predictions from a model against observations from the system being diagnosed. However this approach does not work very well when it is not feasible to create analytic relations describing all the observed data, e.g., for vibration data which is usually sampled at very high rates and requires very detailed finite element models to describe its behavior. In such cases, features (in time and frequency domains) that contain diagnostic information are extracted from the data. Since this is a computationally intensive process, it is not efficient to extract all the features all the time. In this paper we present an approach that combines the analytic model-based and feature-driven diagnosis approaches. The analytic approach is used to reduce the set of possible faults and then features are chosen to best distinguish among the remaining faults. We describe an implementation of this approach on the Flyable Electro-mechanical Actuator (FLEA) test bed.

Automatic seizure detection based on the combination of newborn multi-channel EEG and HRV information

NASA Astrophysics Data System (ADS)

Mesbah, Mostefa; Balakrishnan, Malarvili; Colditz, Paul B.; Boashash, Boualem

2012-12-01

This article proposes a new method for newborn seizure detection that uses information extracted from both multi-channel electroencephalogram (EEG) and a single channel electrocardiogram (ECG). The aim of the study is to assess whether additional information extracted from ECG can improve the performance of seizure detectors based solely on EEG. Two different approaches were used to combine this extracted information. The first approach, known as feature fusion, involves combining features extracted from EEG and heart rate variability (HRV) into a single feature vector prior to feeding it to a classifier. The second approach, called classifier or decision fusion, is achieved by combining the independent decisions of the EEG and the HRV-based classifiers. Tested on recordings obtained from eight newborns with identified EEG seizures, the proposed neonatal seizure detection algorithms achieved 95.20% sensitivity and 88.60% specificity for the feature fusion case and 95.20% sensitivity and 94.30% specificity for the classifier fusion case. These results are considerably better than those involving classifiers using EEG only (80.90%, 86.50%) or HRV only (85.70%, 84.60%).

User-oriented summary extraction for soccer video based on multimodal analysis

NASA Astrophysics Data System (ADS)

Liu, Huayong; Jiang, Shanshan; He, Tingting

2011-11-01

An advanced user-oriented summary extraction method for soccer video is proposed in this work. Firstly, an algorithm of user-oriented summary extraction for soccer video is introduced. A novel approach that integrates multimodal analysis, such as extraction and analysis of the stadium features, moving object features, audio features and text features is introduced. By these features the semantic of the soccer video and the highlight mode are obtained. Then we can find the highlight position and put them together by highlight degrees to obtain the video summary. The experimental results for sports video of world cup soccer games indicate that multimodal analysis is effective for soccer video browsing and retrieval.

Concurrent evolution of feature extractors and modular artificial neural networks

NASA Astrophysics Data System (ADS)

Hannak, Victor; Savakis, Andreas; Yang, Shanchieh Jay; Anderson, Peter

2009-05-01

This paper presents a new approach for the design of feature-extracting recognition networks that do not require expert knowledge in the application domain. Feature-Extracting Recognition Networks (FERNs) are composed of interconnected functional nodes (feurons), which serve as feature extractors, and are followed by a subnetwork of traditional neural nodes (neurons) that act as classifiers. A concurrent evolutionary process (CEP) is used to search the space of feature extractors and neural networks in order to obtain an optimal recognition network that simultaneously performs feature extraction and recognition. By constraining the hill-climbing search functionality of the CEP on specific parts of the solution space, i.e., individually limiting the evolution of feature extractors and neural networks, it was demonstrated that concurrent evolution is a necessary component of the system. Application of this approach to a handwritten digit recognition task illustrates that the proposed methodology is capable of producing recognition networks that perform in-line with other methods without the need for expert knowledge in image processing.

Joint Feature Extraction and Classifier Design for ECG-Based Biometric Recognition.

PubMed

Gutta, Sandeep; Cheng, Qi

2016-03-01

Traditional biometric recognition systems often utilize physiological traits such as fingerprint, face, iris, etc. Recent years have seen a growing interest in electrocardiogram (ECG)-based biometric recognition techniques, especially in the field of clinical medicine. In existing ECG-based biometric recognition methods, feature extraction and classifier design are usually performed separately. In this paper, a multitask learning approach is proposed, in which feature extraction and classifier design are carried out simultaneously. Weights are assigned to the features within the kernel of each task. We decompose the matrix consisting of all the feature weights into sparse and low-rank components. The sparse component determines the features that are relevant to identify each individual, and the low-rank component determines the common feature subspace that is relevant to identify all the subjects. A fast optimization algorithm is developed, which requires only the first-order information. The performance of the proposed approach is demonstrated through experiments using the MIT-BIH Normal Sinus Rhythm database.

Classification of clinically useful sentences in clinical evidence resources.

PubMed

Morid, Mohammad Amin; Fiszman, Marcelo; Raja, Kalpana; Jonnalagadda, Siddhartha R; Del Fiol, Guilherme

2016-04-01

Most patient care questions raised by clinicians can be answered by online clinical knowledge resources. However, important barriers still challenge the use of these resources at the point of care. To design and assess a method for extracting clinically useful sentences from synthesized online clinical resources that represent the most clinically useful information for directly answering clinicians' information needs. We developed a Kernel-based Bayesian Network classification model based on different domain-specific feature types extracted from sentences in a gold standard composed of 18 UpToDate documents. These features included UMLS concepts and their semantic groups, semantic predications extracted by SemRep, patient population identified by a pattern-based natural language processing (NLP) algorithm, and cue words extracted by a feature selection technique. Algorithm performance was measured in terms of precision, recall, and F-measure. The feature-rich approach yielded an F-measure of 74% versus 37% for a feature co-occurrence method (p<0.001). Excluding predication, population, semantic concept or text-based features reduced the F-measure to 62%, 66%, 58% and 69% respectively (p<0.01). The classifier applied to Medline sentences reached an F-measure of 73%, which is equivalent to the performance of the classifier on UpToDate sentences (p=0.62). The feature-rich approach significantly outperformed general baseline methods. This approach significantly outperformed classifiers based on a single type of feature. Different types of semantic features provided a unique contribution to overall classification performance. The classifier's model and features used for UpToDate generalized well to Medline abstracts. Copyright © 2016 Elsevier Inc. All rights reserved.

Semi-Supervised Geographical Feature Detection

NASA Astrophysics Data System (ADS)

Yu, H.; Yu, L.; Kuo, K. S.

2016-12-01

Extraction and tracking geographical features is a fundamental requirement in many geoscience fields. However, this operation has become an increasingly challenging task for domain scientists when tackling a large amount of geoscience data. Although domain scientists may have a relatively clear definition of features, it is difficult to capture the presence of features in an accurate and efficient fashion. We propose a semi-supervised approach to address large geographical feature detection. Our approach has two main components. First, we represent a heterogeneous geoscience data in a unified high-dimensional space, which can facilitate us to evaluate the similarity of data points with respect to geolocation, time, and variable values. We characterize the data from these measures, and use a set of hash functions to parameterize the initial knowledge of the data. Second, for any user query, our approach can automatically extract the initial results based on the hash functions. To improve the accuracy of querying, our approach provides a visualization interface to display the querying results and allow users to interactively explore and refine them. The user feedback will be used to enhance our knowledge base in an iterative manner. In our implementation, we use high-performance computing techniques to accelerate the construction of hash functions. Our design facilitates a parallelization scheme for feature detection and extraction, which is a traditionally challenging problem for large-scale data. We evaluate our approach and demonstrate the effectiveness using both synthetic and real world datasets.

Contact-free palm-vein recognition based on local invariant features.

PubMed

Kang, Wenxiong; Liu, Yang; Wu, Qiuxia; Yue, Xishun

2014-01-01

Contact-free palm-vein recognition is one of the most challenging and promising areas in hand biometrics. In view of the existing problems in contact-free palm-vein imaging, including projection transformation, uneven illumination and difficulty in extracting exact ROIs, this paper presents a novel recognition approach for contact-free palm-vein recognition that performs feature extraction and matching on all vein textures distributed over the palm surface, including finger veins and palm veins, to minimize the loss of feature information. First, a hierarchical enhancement algorithm, which combines a DOG filter and histogram equalization, is adopted to alleviate uneven illumination and to highlight vein textures. Second, RootSIFT, a more stable local invariant feature extraction method in comparison to SIFT, is adopted to overcome the projection transformation in contact-free mode. Subsequently, a novel hierarchical mismatching removal algorithm based on neighborhood searching and LBP histograms is adopted to improve the accuracy of feature matching. Finally, we rigorously evaluated the proposed approach using two different databases and obtained 0.996% and 3.112% Equal Error Rates (EERs), respectively, which demonstrate the effectiveness of the proposed approach.

Contact-Free Palm-Vein Recognition Based on Local Invariant Features

PubMed Central

Kang, Wenxiong; Liu, Yang; Wu, Qiuxia; Yue, Xishun

2014-01-01

Contact-free palm-vein recognition is one of the most challenging and promising areas in hand biometrics. In view of the existing problems in contact-free palm-vein imaging, including projection transformation, uneven illumination and difficulty in extracting exact ROIs, this paper presents a novel recognition approach for contact-free palm-vein recognition that performs feature extraction and matching on all vein textures distributed over the palm surface, including finger veins and palm veins, to minimize the loss of feature information. First, a hierarchical enhancement algorithm, which combines a DOG filter and histogram equalization, is adopted to alleviate uneven illumination and to highlight vein textures. Second, RootSIFT, a more stable local invariant feature extraction method in comparison to SIFT, is adopted to overcome the projection transformation in contact-free mode. Subsequently, a novel hierarchical mismatching removal algorithm based on neighborhood searching and LBP histograms is adopted to improve the accuracy of feature matching. Finally, we rigorously evaluated the proposed approach using two different databases and obtained 0.996% and 3.112% Equal Error Rates (EERs), respectively, which demonstrate the effectiveness of the proposed approach. PMID:24866176

Detection of faults in rotating machinery using periodic time-frequency sparsity

NASA Astrophysics Data System (ADS)

Ding, Yin; He, Wangpeng; Chen, Binqiang; Zi, Yanyang; Selesnick, Ivan W.

2016-11-01

This paper addresses the problem of extracting periodic oscillatory features in vibration signals for detecting faults in rotating machinery. To extract the feature, we propose an approach in the short-time Fourier transform (STFT) domain where the periodic oscillatory feature manifests itself as a relatively sparse grid. To estimate the sparse grid, we formulate an optimization problem using customized binary weights in the regularizer, where the weights are formulated to promote periodicity. In order to solve the proposed optimization problem, we develop an algorithm called augmented Lagrangian majorization-minimization algorithm, which combines the split augmented Lagrangian shrinkage algorithm (SALSA) with majorization-minimization (MM), and is guaranteed to converge for both convex and non-convex formulation. As examples, the proposed approach is applied to simulated data, and used as a tool for diagnosing faults in bearings and gearboxes for real data, and compared to some state-of-the-art methods. The results show that the proposed approach can effectively detect and extract the periodical oscillatory features.

Skipping the real world: Classification of PolSAR images without explicit feature extraction

NASA Astrophysics Data System (ADS)

Hänsch, Ronny; Hellwich, Olaf

2018-06-01

The typical processing chain for pixel-wise classification from PolSAR images starts with an optional preprocessing step (e.g. speckle reduction), continues with extracting features projecting the complex-valued data into the real domain (e.g. by polarimetric decompositions) which are then used as input for a machine-learning based classifier, and ends in an optional postprocessing (e.g. label smoothing). The extracted features are usually hand-crafted as well as preselected and represent (a somewhat arbitrary) projection from the complex to the real domain in order to fit the requirements of standard machine-learning approaches such as Support Vector Machines or Artificial Neural Networks. This paper proposes to adapt the internal node tests of Random Forests to work directly on the complex-valued PolSAR data, which makes any explicit feature extraction obsolete. This approach leads to a classification framework with a significantly decreased computation time and memory footprint since no image features have to be computed and stored beforehand. The experimental results on one fully-polarimetric and one dual-polarimetric dataset show that, despite the simpler approach, accuracy can be maintained (decreased by only less than 2 % for the fully-polarimetric dataset) or even improved (increased by roughly 9 % for the dual-polarimetric dataset).

Comparison of machine learned approaches for thyroid nodule characterization from shear wave elastography images

NASA Astrophysics Data System (ADS)

Pereira, Carina; Dighe, Manjiri; Alessio, Adam M.

2018-02-01

Various Computer Aided Diagnosis (CAD) systems have been developed that characterize thyroid nodules using the features extracted from the B-mode ultrasound images and Shear Wave Elastography images (SWE). These features, however, are not perfect predictors of malignancy. In other domains, deep learning techniques such as Convolutional Neural Networks (CNNs) have outperformed conventional feature extraction based machine learning approaches. In general, fully trained CNNs require substantial volumes of data, motivating several efforts to use transfer learning with pre-trained CNNs. In this context, we sought to compare the performance of conventional feature extraction, fully trained CNNs, and transfer learning based, pre-trained CNNs for the detection of thyroid malignancy from ultrasound images. We compared these approaches applied to a data set of 964 B-mode and SWE images from 165 patients. The data were divided into 80% training/validation and 20% testing data. The highest accuracies achieved on the testing data for the conventional feature extraction, fully trained CNN, and pre-trained CNN were 0.80, 0.75, and 0.83 respectively. In this application, classification using a pre-trained network yielded the best performance, potentially due to the relatively limited sample size and sub-optimal architecture for the fully trained CNN.

Engagement Assessment Using EEG Signals

NASA Technical Reports Server (NTRS)

Li, Feng; Li, Jiang; McKenzie, Frederic; Zhang, Guangfan; Wang, Wei; Pepe, Aaron; Xu, Roger; Schnell, Thomas; Anderson, Nick; Heitkamp, Dean

2012-01-01

In this paper, we present methods to analyze and improve an EEG-based engagement assessment approach, consisting of data preprocessing, feature extraction and engagement state classification. During data preprocessing, spikes, baseline drift and saturation caused by recording devices in EEG signals are identified and eliminated, and a wavelet based method is utilized to remove ocular and muscular artifacts in the EEG recordings. In feature extraction, power spectrum densities with 1 Hz bin are calculated as features, and these features are analyzed using the Fisher score and the one way ANOVA method. In the classification step, a committee classifier is trained based on the extracted features to assess engagement status. Finally, experiment results showed that there exist significant differences in the extracted features among different subjects, and we have implemented a feature normalization procedure to mitigate the differences and significantly improved the engagement assessment performance.

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.

Statistical Methods for Proteomic Biomarker Discovery based on Feature Extraction or Functional Modeling Approaches.

PubMed

Morris, Jeffrey S

2012-01-01

In recent years, developments in molecular biotechnology have led to the increased promise of detecting and validating biomarkers, or molecular markers that relate to various biological or medical outcomes. Proteomics, the direct study of proteins in biological samples, plays an important role in the biomarker discovery process. These technologies produce complex, high dimensional functional and image data that present many analytical challenges that must be addressed properly for effective comparative proteomics studies that can yield potential biomarkers. Specific challenges include experimental design, preprocessing, feature extraction, and statistical analysis accounting for the inherent multiple testing issues. This paper reviews various computational aspects of comparative proteomic studies, and summarizes contributions I along with numerous collaborators have made. First, there is an overview of comparative proteomics technologies, followed by a discussion of important experimental design and preprocessing issues that must be considered before statistical analysis can be done. Next, the two key approaches to analyzing proteomics data, feature extraction and functional modeling, are described. Feature extraction involves detection and quantification of discrete features like peaks or spots that theoretically correspond to different proteins in the sample. After an overview of the feature extraction approach, specific methods for mass spectrometry ( Cromwell ) and 2D gel electrophoresis ( Pinnacle ) are described. The functional modeling approach involves modeling the proteomic data in their entirety as functions or images. A general discussion of the approach is followed by the presentation of a specific method that can be applied, wavelet-based functional mixed models, and its extensions. All methods are illustrated by application to two example proteomic data sets, one from mass spectrometry and one from 2D gel electrophoresis. While the specific methods presented are applied to two specific proteomic technologies, MALDI-TOF and 2D gel electrophoresis, these methods and the other principles discussed in the paper apply much more broadly to other expression proteomics technologies.

A 3D convolutional neural network approach to land cover classification using LiDAR and multi-temporal Landsat imagery

NASA Astrophysics Data System (ADS)

Xu, Z.; Guan, K.; Peng, B.; Casler, N. P.; Wang, S. W.

2017-12-01

Landscape has complex three-dimensional features. These 3D features are difficult to extract using conventional methods. Small-footprint LiDAR provides an ideal way for capturing these features. Existing approaches, however, have been relegated to raster or metric-based (two-dimensional) feature extraction from the upper or bottom layer, and thus are not suitable for resolving morphological and intensity features that could be important to fine-scale land cover mapping. Therefore, this research combines airborne LiDAR and multi-temporal Landsat imagery to classify land cover types of Williamson County, Illinois that has diverse and mixed landscape features. Specifically, we applied a 3D convolutional neural network (CNN) method to extract features from LiDAR point clouds by (1) creating occupancy grid, intensity grid at 1-meter resolution, and then (2) normalizing and incorporating data into a 3D CNN feature extractor for many epochs of learning. The learned features (e.g., morphological features, intensity features, etc) were combined with multi-temporal spectral data to enhance the performance of land cover classification based on a Support Vector Machine classifier. We used photo interpretation for training and testing data generation. The classification results show that our approach outperforms traditional methods using LiDAR derived feature maps, and promises to serve as an effective methodology for creating high-quality land cover maps through fusion of complementary types of remote sensing data.

Feature generation using genetic programming with application to fault classification.

PubMed

Guo, Hong; Jack, Lindsay B; Nandi, Asoke K

2005-02-01

One of the major challenges in pattern recognition problems is the feature extraction process which derives new features from existing features, or directly from raw data in order to reduce the cost of computation during the classification process, while improving classifier efficiency. Most current feature extraction techniques transform the original pattern vector into a new vector with increased discrimination capability but lower dimensionality. This is conducted within a predefined feature space, and thus, has limited searching power. Genetic programming (GP) can generate new features from the original dataset without prior knowledge of the probabilistic distribution. In this paper, a GP-based approach is developed for feature extraction from raw vibration data recorded from a rotating machine with six different conditions. The created features are then used as the inputs to a neural classifier for the identification of six bearing conditions. Experimental results demonstrate the ability of GP to discover autimatically the different bearing conditions using features expressed in the form of nonlinear functions. Furthermore, four sets of results--using GP extracted features with artificial neural networks (ANN) and support vector machines (SVM), as well as traditional features with ANN and SVM--have been obtained. This GP-based approach is used for bearing fault classification for the first time and exhibits superior searching power over other techniques. Additionaly, it significantly reduces the time for computation compared with genetic algorithm (GA), therefore, makes a more practical realization of the solution.

Feature Vector Construction Method for IRIS Recognition

NASA Astrophysics Data System (ADS)

Odinokikh, G.; Fartukov, A.; Korobkin, M.; Yoo, J.

2017-05-01

One of the basic stages of iris recognition pipeline is iris feature vector construction procedure. The procedure represents the extraction of iris texture information relevant to its subsequent comparison. Thorough investigation of feature vectors obtained from iris showed that not all the vector elements are equally relevant. There are two characteristics which determine the vector element utility: fragility and discriminability. Conventional iris feature extraction methods consider the concept of fragility as the feature vector instability without respect to the nature of such instability appearance. This work separates sources of the instability into natural and encodinginduced which helps deeply investigate each source of instability independently. According to the separation concept, a novel approach of iris feature vector construction is proposed. The approach consists of two steps: iris feature extraction using Gabor filtering with optimal parameters and quantization with separated preliminary optimized fragility thresholds. The proposed method has been tested on two different datasets of iris images captured under changing environmental conditions. The testing results show that the proposed method surpasses all the methods considered as a prior art by recognition accuracy on both datasets.

Classification of product inspection items using nonlinear features

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.; Lee, H.-W.

1998-03-01

Automated processing and classification of real-time x-ray images of randomly oriented touching pistachio nuts is discussed. The ultimate objective is the development of a system for automated non-invasive detection of defective product items on a conveyor belt. This approach involves two main steps: preprocessing and classification. Preprocessing locates individual items and segments ones that touch using a modified watershed algorithm. The second stage involves extraction of features that allow discrimination between damaged and clean items (pistachio nuts). This feature extraction and classification stage is the new aspect of this paper. We use a new nonlinear feature extraction scheme called the maximum representation and discriminating feature (MRDF) extraction method to compute nonlinear features that are used as inputs to a classifier. The MRDF is shown to provide better classification and a better ROC (receiver operating characteristic) curve than other methods.

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.

Fast Localization in Large-Scale Environments Using Supervised Indexing of Binary Features.

PubMed

Youji Feng; Lixin Fan; Yihong Wu

2016-01-01

The essence of image-based localization lies in matching 2D key points in the query image and 3D points in the database. State-of-the-art methods mostly employ sophisticated key point detectors and feature descriptors, e.g., Difference of Gaussian (DoG) and Scale Invariant Feature Transform (SIFT), to ensure robust matching. While a high registration rate is attained, the registration speed is impeded by the expensive key point detection and the descriptor extraction. In this paper, we propose to use efficient key point detectors along with binary feature descriptors, since the extraction of such binary features is extremely fast. The naive usage of binary features, however, does not lend itself to significant speedup of localization, since existing indexing approaches, such as hierarchical clustering trees and locality sensitive hashing, are not efficient enough in indexing binary features and matching binary features turns out to be much slower than matching SIFT features. To overcome this, we propose a much more efficient indexing approach for approximate nearest neighbor search of binary features. This approach resorts to randomized trees that are constructed in a supervised training process by exploiting the label information derived from that multiple features correspond to a common 3D point. In the tree construction process, node tests are selected in a way such that trees have uniform leaf sizes and low error rates, which are two desired properties for efficient approximate nearest neighbor search. To further improve the search efficiency, a probabilistic priority search strategy is adopted. Apart from the label information, this strategy also uses non-binary pixel intensity differences available in descriptor extraction. By using the proposed indexing approach, matching binary features is no longer much slower but slightly faster than matching SIFT features. Consequently, the overall localization speed is significantly improved due to the much faster key point detection and descriptor extraction. It is empirically demonstrated that the localization speed is improved by an order of magnitude as compared with state-of-the-art methods, while comparable registration rate and localization accuracy are still maintained.

An improved discriminative filter bank selection approach for motor imagery EEG signal classification using mutual information.

PubMed

Kumar, Shiu; Sharma, Alok; Tsunoda, Tatsuhiko

2017-12-28

Common spatial pattern (CSP) has been an effective technique for feature extraction in electroencephalography (EEG) based brain computer interfaces (BCIs). However, motor imagery EEG signal feature extraction using CSP generally depends on the selection of the frequency bands to a great extent. In this study, we propose a mutual information based frequency band selection approach. The idea of the proposed method is to utilize the information from all the available channels for effectively selecting the most discriminative filter banks. CSP features are extracted from multiple overlapping sub-bands. An additional sub-band has been introduced that cover the wide frequency band (7-30 Hz) and two different types of features are extracted using CSP and common spatio-spectral pattern techniques, respectively. Mutual information is then computed from the extracted features of each of these bands and the top filter banks are selected for further processing. Linear discriminant analysis is applied to the features extracted from each of the filter banks. The scores are fused together, and classification is done using support vector machine. The proposed method is evaluated using BCI Competition III dataset IVa, BCI Competition IV dataset I and BCI Competition IV dataset IIb, and it outperformed all other competing methods achieving the lowest misclassification rate and the highest kappa coefficient on all three datasets. Introducing a wide sub-band and using mutual information for selecting the most discriminative sub-bands, the proposed method shows improvement in motor imagery EEG signal classification.

Automatic identification of fault surfaces through Object Based Image Analysis of a Digital Elevation Model in the submarine area of the North Aegean Basin

NASA Astrophysics Data System (ADS)

Argyropoulou, Evangelia

2015-04-01

The current study was focused on the seafloor morphology of the North Aegean Basin in Greece, through Object Based Image Analysis (OBIA) using a Digital Elevation Model. The goal was the automatic extraction of morphologic and morphotectonic features, resulting into fault surface extraction. An Object Based Image Analysis approach was developed based on the bathymetric data and the extracted features, based on morphological criteria, were compared with the corresponding landforms derived through tectonic analysis. A digital elevation model of 150 meters spatial resolution was used. At first, slope, profile curvature, and percentile were extracted from this bathymetry grid. The OBIA approach was developed within the eCognition environment. Four segmentation levels were created having as a target "level 4". At level 4, the final classes of geomorphological features were classified: discontinuities, fault-like features and fault surfaces. On previous levels, additional landforms were also classified, such as continental platform and continental slope. The results of the developed approach were evaluated by two methods. At first, classification stability measures were computed within eCognition. Then, qualitative and quantitative comparison of the results took place with a reference tectonic map which has been created manually based on the analysis of seismic profiles. The results of this comparison were satisfactory, a fact which determines the correctness of the developed OBIA approach.

Local kernel nonparametric discriminant analysis for adaptive extraction of complex structures

NASA Astrophysics Data System (ADS)

Li, Quanbao; Wei, Fajie; Zhou, Shenghan

2017-05-01

The linear discriminant analysis (LDA) is one of popular means for linear feature extraction. It usually performs well when the global data structure is consistent with the local data structure. Other frequently-used approaches of feature extraction usually require linear, independence, or large sample condition. However, in real world applications, these assumptions are not always satisfied or cannot be tested. In this paper, we introduce an adaptive method, local kernel nonparametric discriminant analysis (LKNDA), which integrates conventional discriminant analysis with nonparametric statistics. LKNDA is adept in identifying both complex nonlinear structures and the ad hoc rule. Six simulation cases demonstrate that LKNDA have both parametric and nonparametric algorithm advantages and higher classification accuracy. Quartic unilateral kernel function may provide better robustness of prediction than other functions. LKNDA gives an alternative solution for discriminant cases of complex nonlinear feature extraction or unknown feature extraction. At last, the application of LKNDA in the complex feature extraction of financial market activities is proposed.

Non-negative matrix factorization in texture feature for classification of dementia with MRI data

NASA Astrophysics Data System (ADS)

Sarwinda, D.; Bustamam, A.; Ardaneswari, G.

2017-07-01

This paper investigates applications of non-negative matrix factorization as feature selection method to select the features from gray level co-occurrence matrix. The proposed approach is used to classify dementia using MRI data. In this study, texture analysis using gray level co-occurrence matrix is done to feature extraction. In the feature extraction process of MRI data, we found seven features from gray level co-occurrence matrix. Non-negative matrix factorization selected three features that influence of all features produced by feature extractions. A Naïve Bayes classifier is adapted to classify dementia, i.e. Alzheimer's disease, Mild Cognitive Impairment (MCI) and normal control. The experimental results show that non-negative factorization as feature selection method able to achieve an accuracy of 96.4% for classification of Alzheimer's and normal control. The proposed method also compared with other features selection methods i.e. Principal Component Analysis (PCA).

Decomposition and extraction: a new framework for visual classification.

PubMed

Fang, Yuqiang; Chen, Qiang; Sun, Lin; Dai, Bin; Yan, Shuicheng

2014-08-01

In this paper, we present a novel framework for visual classification based on hierarchical image decomposition and hybrid midlevel feature extraction. Unlike most midlevel feature learning methods, which focus on the process of coding or pooling, we emphasize that the mechanism of image composition also strongly influences the feature extraction. To effectively explore the image content for the feature extraction, we model a multiplicity feature representation mechanism through meaningful hierarchical image decomposition followed by a fusion step. In particularly, we first propose a new hierarchical image decomposition approach in which each image is decomposed into a series of hierarchical semantical components, i.e, the structure and texture images. Then, different feature extraction schemes can be adopted to match the decomposed structure and texture processes in a dissociative manner. Here, two schemes are explored to produce property related feature representations. One is based on a single-stage network over hand-crafted features and the other is based on a multistage network, which can learn features from raw pixels automatically. Finally, those multiple midlevel features are incorporated by solving a multiple kernel learning task. Extensive experiments are conducted on several challenging data sets for visual classification, and experimental results demonstrate the effectiveness of the proposed method.

Low complexity feature extraction for classification of harmonic signals

NASA Astrophysics Data System (ADS)

William, Peter E.

In this dissertation, feature extraction algorithms have been developed for extraction of characteristic features from harmonic signals. The common theme for all developed algorithms is the simplicity in generating a significant set of features directly from the time domain harmonic signal. The features are a time domain representation of the composite, yet sparse, harmonic signature in the spectral domain. The algorithms are adequate for low-power unattended sensors which perform sensing, feature extraction, and classification in a standalone scenario. The first algorithm generates the characteristic features using only the duration between successive zero-crossing intervals. The second algorithm estimates the harmonics' amplitudes of the harmonic structure employing a simplified least squares method without the need to estimate the true harmonic parameters of the source signal. The third algorithm, resulting from a collaborative effort with Daniel White at the DSP Lab, University of Nebraska-Lincoln, presents an analog front end approach that utilizes a multichannel analog projection and integration to extract the sparse spectral features from the analog time domain signal. Classification is performed using a multilayer feedforward neural network. Evaluation of the proposed feature extraction algorithms for classification through the processing of several acoustic and vibration data sets (including military vehicles and rotating electric machines) with comparison to spectral features shows that, for harmonic signals, time domain features are simpler to extract and provide equivalent or improved reliability over the spectral features in both the detection probabilities and false alarm rate.

Detection of facilities in satellite imagery using semi-supervised image classification and auxiliary contextual observables

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

Harvey, Neal R; Ruggiero, Christy E; Pawley, Norma H

2009-01-01

Detecting complex targets, such as facilities, in commercially available satellite imagery is a difficult problem that human analysts try to solve by applying world knowledge. Often there are known observables that can be extracted by pixel-level feature detectors that can assist in the facility detection process. Individually, each of these observables is not sufficient for an accurate and reliable detection, but in combination, these auxiliary observables may provide sufficient context for detection by a machine learning algorithm. We describe an approach for automatic detection of facilities that uses an automated feature extraction algorithm to extract auxiliary observables, and a semi-supervisedmore » assisted target recognition algorithm to then identify facilities of interest. We illustrate the approach using an example of finding schools in Quickbird image data of Albuquerque, New Mexico. We use Los Alamos National Laboratory's Genie Pro automated feature extraction algorithm to find a set of auxiliary features that should be useful in the search for schools, such as parking lots, large buildings, sports fields and residential areas and then combine these features using Genie Pro's assisted target recognition algorithm to learn a classifier that finds schools in the image data.« less

Object Tracking Using Adaptive Covariance Descriptor and Clustering-Based Model Updating for Visual Surveillance

PubMed Central

Qin, Lei; Snoussi, Hichem; Abdallah, Fahed

2014-01-01

We propose a novel approach for tracking an arbitrary object in video sequences for visual surveillance. The first contribution of this work is an automatic feature extraction method that is able to extract compact discriminative features from a feature pool before computing the region covariance descriptor. As the feature extraction method is adaptive to a specific object of interest, we refer to the region covariance descriptor computed using the extracted features as the adaptive covariance descriptor. The second contribution is to propose a weakly supervised method for updating the object appearance model during tracking. The method performs a mean-shift clustering procedure among the tracking result samples accumulated during a period of time and selects a group of reliable samples for updating the object appearance model. As such, the object appearance model is kept up-to-date and is prevented from contamination even in case of tracking mistakes. We conducted comparing experiments on real-world video sequences, which confirmed the effectiveness of the proposed approaches. The tracking system that integrates the adaptive covariance descriptor and the clustering-based model updating method accomplished stable object tracking on challenging video sequences. PMID:24865883

Content-based audio authentication using a hierarchical patchwork watermark embedding

NASA Astrophysics Data System (ADS)

Gulbis, Michael; Müller, Erika

2010-05-01

Content-based audio authentication watermarking techniques extract perceptual relevant audio features, which are robustly embedded into the audio file to protect. Manipulations of the audio file are detected on the basis of changes between the original embedded feature information and the anew extracted features during verification. The main challenges of content-based watermarking are on the one hand the identification of a suitable audio feature to distinguish between content preserving and malicious manipulations. On the other hand the development of a watermark, which is robust against content preserving modifications and able to carry the whole authentication information. The payload requirements are significantly higher compared to transaction watermarking or copyright protection. Finally, the watermark embedding should not influence the feature extraction to avoid false alarms. Current systems still lack a sufficient alignment of watermarking algorithm and feature extraction. In previous work we developed a content-based audio authentication watermarking approach. The feature is based on changes in DCT domain over time. A patchwork algorithm based watermark was used to embed multiple one bit watermarks. The embedding process uses the feature domain without inflicting distortions to the feature. The watermark payload is limited by the feature extraction, more precisely the critical bands. The payload is inverse proportional to segment duration of the audio file segmentation. Transparency behavior was analyzed in dependence of segment size and thus the watermark payload. At a segment duration of about 20 ms the transparency shows an optimum (measured in units of Objective Difference Grade). Transparency and/or robustness are fast decreased for working points beyond this area. Therefore, these working points are unsuitable to gain further payload, needed for the embedding of the whole authentication information. In this paper we present a hierarchical extension of the watermark method to overcome the limitations given by the feature extraction. The approach is a recursive application of the patchwork algorithm onto its own patches, with a modified patch selection to ensure a better signal to noise ratio for the watermark embedding. The robustness evaluation was done by compression (mp3, ogg, aac), normalization, and several attacks of the stirmark benchmark for audio suite. Compared on the base of same payload and transparency the hierarchical approach shows improved robustness.

Uniform competency-based local feature extraction for remote sensing images

NASA Astrophysics Data System (ADS)

Sedaghat, Amin; Mohammadi, Nazila

2018-01-01

Local feature detectors are widely used in many photogrammetry and remote sensing applications. The quantity and distribution of the local features play a critical role in the quality of the image matching process, particularly for multi-sensor high resolution remote sensing image registration. However, conventional local feature detectors cannot extract desirable matched features either in terms of the number of correct matches or the spatial and scale distribution in multi-sensor remote sensing images. To address this problem, this paper proposes a novel method for uniform and robust local feature extraction for remote sensing images, which is based on a novel competency criterion and scale and location distribution constraints. The proposed method, called uniform competency (UC) local feature extraction, can be easily applied to any local feature detector for various kinds of applications. The proposed competency criterion is based on a weighted ranking process using three quality measures, including robustness, spatial saliency and scale parameters, which is performed in a multi-layer gridding schema. For evaluation, five state-of-the-art local feature detector approaches, namely, scale-invariant feature transform (SIFT), speeded up robust features (SURF), scale-invariant feature operator (SFOP), maximally stable extremal region (MSER) and hessian-affine, are used. The proposed UC-based feature extraction algorithms were successfully applied to match various synthetic and real satellite image pairs, and the results demonstrate its capability to increase matching performance and to improve the spatial distribution. The code to carry out the UC feature extraction is available from href="https://www.researchgate.net/publication/317956777_UC-Feature_Extraction.

Masquerade Detection Using a Taxonomy-Based Multinomial Modeling Approach in UNIX Systems

DTIC Science & Technology

2008-08-25

primarily the modeling of statistical features , such as the frequency of events, the duration of events, the co- occurrence of multiple events...are identified, we can extract features representing such behavior while auditing the user’s behavior. Figure1: Taxonomy of Linux and Unix...achieved when the features are extracted just from simple commands. Method Hit Rate False Positive Rate ocSVM using simple cmds (freq.-based

Multi-task feature learning by using trace norm regularization

NASA Astrophysics Data System (ADS)

Jiangmei, Zhang; Binfeng, Yu; Haibo, Ji; Wang, Kunpeng

2017-11-01

Multi-task learning can extract the correlation of multiple related machine learning problems to improve performance. This paper considers applying the multi-task learning method to learn a single task. We propose a new learning approach, which employs the mixture of expert model to divide a learning task into several related sub-tasks, and then uses the trace norm regularization to extract common feature representation of these sub-tasks. A nonlinear extension of this approach by using kernel is also provided. Experiments conducted on both simulated and real data sets demonstrate the advantage of the proposed approach.

DARHT Multi-intelligence Seismic and Acoustic Data Analysis

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

Stevens, Garrison Nicole; Van Buren, Kendra Lu; Hemez, Francois M.

The purpose of this report is to document the analysis of seismic and acoustic data collected at the Dual-Axis Radiographic Hydrodynamic Test (DARHT) facility at Los Alamos National Laboratory for robust, multi-intelligence decision making. The data utilized herein is obtained from two tri-axial seismic sensors and three acoustic sensors, resulting in a total of nine data channels. The goal of this analysis is to develop a generalized, automated framework to determine internal operations at DARHT using informative features extracted from measurements collected external of the facility. Our framework involves four components: (1) feature extraction, (2) data fusion, (3) classification, andmore » finally (4) robustness analysis. Two approaches are taken for extracting features from the data. The first of these, generic feature extraction, involves extraction of statistical features from the nine data channels. The second approach, event detection, identifies specific events relevant to traffic entering and leaving the facility as well as explosive activities at DARHT and nearby explosive testing sites. Event detection is completed using a two stage method, first utilizing signatures in the frequency domain to identify outliers and second extracting short duration events of interest among these outliers by evaluating residuals of an autoregressive exogenous time series model. Features extracted from each data set are then fused to perform analysis with a multi-intelligence paradigm, where information from multiple data sets are combined to generate more information than available through analysis of each independently. The fused feature set is used to train a statistical classifier and predict the state of operations to inform a decision maker. We demonstrate this classification using both generic statistical features and event detection and provide a comparison of the two methods. Finally, the concept of decision robustness is presented through a preliminary analysis where uncertainty is added to the system through noise in the measurements.« less

Extracting valley-ridge lines from point-cloud-based 3D fingerprint models.

PubMed

Pang, Xufang; Song, Zhan; Xie, Wuyuan

2013-01-01

3D fingerprinting is an emerging technology with the distinct advantage of touchless operation. More important, 3D fingerprint models contain more biometric information than traditional 2D fingerprint images. However, current approaches to fingerprint feature detection usually must transform the 3D models to a 2D space through unwrapping or other methods, which might introduce distortions. A new approach directly extracts valley-ridge features from point-cloud-based 3D fingerprint models. It first applies the moving least-squares method to fit a local paraboloid surface and represent the local point cloud area. It then computes the local surface's curvatures and curvature tensors to facilitate detection of the potential valley and ridge points. The approach projects those points to the most likely valley-ridge lines, using statistical means such as covariance analysis and cross correlation. To finally extract the valley-ridge lines, it grows the polylines that approximate the projected feature points and removes the perturbations between the sampled points. Experiments with different 3D fingerprint models demonstrate this approach's feasibility and performance.

Supervised Extraction of Diagnosis Codes from EMRs: Role of Feature Selection, Data Selection, and Probabilistic Thresholding.

PubMed

Rios, Anthony; Kavuluru, Ramakanth

2013-09-01

Extracting diagnosis codes from medical records is a complex task carried out by trained coders by reading all the documents associated with a patient's visit. With the popularity of electronic medical records (EMRs), computational approaches to code extraction have been proposed in the recent years. Machine learning approaches to multi-label text classification provide an important methodology in this task given each EMR can be associated with multiple codes. In this paper, we study the the role of feature selection, training data selection, and probabilistic threshold optimization in improving different multi-label classification approaches. We conduct experiments based on two different datasets: a recent gold standard dataset used for this task and a second larger and more complex EMR dataset we curated from the University of Kentucky Medical Center. While conventional approaches achieve results comparable to the state-of-the-art on the gold standard dataset, on our complex in-house dataset, we show that feature selection, training data selection, and probabilistic thresholding provide significant gains in performance.

Assessing postural stability via the correlation patterns of vertical ground reaction force components.

PubMed

Hong, Chih-Yuan; Guo, Lan-Yuen; Song, Rong; Nagurka, Mark L; Sung, Jia-Li; Yen, Chen-Wen

2016-08-02

Many methods have been proposed to assess the stability of human postural balance by using a force plate. While most of these approaches characterize postural stability by extracting features from the trajectory of the center of pressure (COP), this work develops stability measures derived from components of the ground reaction force (GRF). In comparison with previous GRF-based approaches that extract stability features from the GRF resultant force, this study proposes three feature sets derived from the correlation patterns among the vertical GRF (VGRF) components. The first and second feature sets quantitatively assess the strength and changing speed of the correlation patterns, respectively. The third feature set is used to quantify the stabilizing effect of the GRF coordination patterns on the COP. In addition to experimentally demonstrating the reliability of the proposed features, the efficacy of the proposed features has also been tested by using them to classify two age groups (18-24 and 65-73 years) in quiet standing. The experimental results show that the proposed features are considerably more sensitive to aging than one of the most effective conventional COP features and two recently proposed COM features. By extracting information from the correlation patterns of the VGRF components, this study proposes three sets of features to assess human postural stability during quiet standing. As demonstrated by the experimental results, the proposed features are not only robust to inter-trial variability but also more accurate than the tested COP and COM features in classifying the older and younger age groups. An additional advantage of the proposed approach is that it reduces the force sensing requirement from 3D to 1D, substantially reducing the cost of the force plate measurement system.

Biomedical named entity extraction: some issues of corpus compatibilities.

PubMed

Ekbal, Asif; Saha, Sriparna; Sikdar, Utpal Kumar

2013-01-01

Named Entity (NE) extraction is one of the most fundamental and important tasks in biomedical information extraction. It involves identification of certain entities from text and their classification into some predefined categories. In the biomedical community, there is yet no general consensus regarding named entity (NE) annotation; thus, it is very difficult to compare the existing systems due to corpus incompatibilities. Due to this problem we can not also exploit the advantages of using different corpora together. In our present work we address the issues of corpus compatibilities, and use a single objective optimization (SOO) based classifier ensemble technique that uses the search capability of genetic algorithm (GA) for NE extraction in biomedicine. We hypothesize that the reliability of predictions of each classifier differs among the various output classes. We use Conditional Random Field (CRF) and Support Vector Machine (SVM) frameworks to build a number of models depending upon the various representations of the set of features and/or feature templates. It is to be noted that we tried to extract the features without using any deep domain knowledge and/or resources. In order to assess the challenges of corpus compatibilities, we experiment with the different benchmark datasets and their various combinations. Comparison results with the existing approaches prove the efficacy of the used technique. GA based ensemble achieves around 2% performance improvements over the individual classifiers. Degradation in performance on the integrated corpus clearly shows the difficulties of the task. In summary, our used ensemble based approach attains the state-of-the-art performance levels for entity extraction in three different kinds of biomedical datasets. The possible reasons behind the better performance in our used approach are the (i). use of variety and rich features as described in Subsection "Features for named entity extraction"; (ii) use of GA based classifier ensemble technique to combine the outputs of multiple classifiers.

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.

A novel approach for fire recognition using hybrid features and manifold learning-based classifier

NASA Astrophysics Data System (ADS)

Zhu, Rong; Hu, Xueying; Tang, Jiajun; Hu, Sheng

2018-03-01

Although image/video based fire recognition has received growing attention, an efficient and robust fire detection strategy is rarely explored. In this paper, we propose a novel approach to automatically identify the flame or smoke regions in an image. It is composed to three stages: (1) a block processing is applied to divide an image into several nonoverlapping image blocks, and these image blocks are identified as suspicious fire regions or not by using two color models and a color histogram-based similarity matching method in the HSV color space, (2) considering that compared to other information, the flame and smoke regions have significant visual characteristics, so that two kinds of image features are extracted for fire recognition, where local features are obtained based on the Scale Invariant Feature Transform (SIFT) descriptor and the Bags of Keypoints (BOK) technique, and texture features are extracted based on the Gray Level Co-occurrence Matrices (GLCM) and the Wavelet-based Analysis (WA) methods, and (3) a manifold learning-based classifier is constructed based on two image manifolds, which is designed via an improve Globular Neighborhood Locally Linear Embedding (GNLLE) algorithm, and the extracted hybrid features are used as input feature vectors to train the classifier, which is used to make decision for fire images or non fire images. Experiments and comparative analyses with four approaches are conducted on the collected image sets. The results show that the proposed approach is superior to the other ones in detecting fire and achieving a high recognition accuracy and a low error rate.

Extraction of linear features on SAR imagery

NASA Astrophysics Data System (ADS)

Liu, Junyi; Li, Deren; Mei, Xin

2006-10-01

Linear features are usually extracted from SAR imagery by a few edge detectors derived from the contrast ratio edge detector with a constant probability of false alarm. On the other hand, the Hough Transform is an elegant way of extracting global features like curve segments from binary edge images. Randomized Hough Transform can reduce the computation time and memory usage of the HT drastically. While Randomized Hough Transform will bring about a great deal of cells invalid during the randomized sample. In this paper, we propose a new approach to extract linear features on SAR imagery, which is an almost automatic algorithm based on edge detection and Randomized Hough Transform. The presented improved method makes full use of the directional information of each edge candidate points so as to solve invalid cumulate problems. Applied result is in good agreement with the theoretical study, and the main linear features on SAR imagery have been extracted automatically. The method saves storage space and computational time, which shows its effectiveness and applicability.

A New Approach to Automated Labeling of Internal Features of Hardwood Logs Using CT Images

Treesearch

Daniel L. Schmoldt; Pei Li; A. Lynn Abbott

1996-01-01

The feasibility of automatically identifying internal features of hardwood logs using CT imagery has been established previously. Features of primary interest are bark, knots, voids, decay, and clear wood. Our previous approach: filtered original CT images, applied histogram segmentation, grew volumes to extract 3-d regions, and applied a rule base, with Dempster-...

A multi-approach feature extractions for iris recognition

NASA Astrophysics Data System (ADS)

Sanpachai, H.; Settapong, M.

2014-04-01

Biometrics is a promising technique that is used to identify individual traits and characteristics. Iris recognition is one of the most reliable biometric methods. As iris texture and color is fully developed within a year of birth, it remains unchanged throughout a person's life. Contrary to fingerprint, which can be altered due to several aspects including accidental damage, dry or oily skin and dust. Although iris recognition has been studied for more than a decade, there are limited commercial products available due to its arduous requirement such as camera resolution, hardware size, expensive equipment and computational complexity. However, at the present time, technology has overcome these obstacles. Iris recognition can be done through several sequential steps which include pre-processing, features extractions, post-processing, and matching stage. In this paper, we adopted the directional high-low pass filter for feature extraction. A box-counting fractal dimension and Iris code have been proposed as feature representations. Our approach has been tested on CASIA Iris Image database and the results are considered successful.

Multispectra CWT-based algorithm (MCWT) in mass spectra for peak extraction.

PubMed

Hsueh, Huey-Miin; Kuo, Hsun-Chih; Tsai, Chen-An

2008-01-01

An important objective in mass spectrometry (MS) is to identify a set of biomarkers that can be used to potentially distinguish patients between distinct treatments (or conditions) from tens or hundreds of spectra. A common two-step approach involving peak extraction and quantification is employed to identify the features of scientific interest. The selected features are then used for further investigation to understand underlying biological mechanism of individual protein or for development of genomic biomarkers to early diagnosis. However, the use of inadequate or ineffective peak detection and peak alignment algorithms in peak extraction step may lead to a high rate of false positives. Also, it is crucial to reduce the false positive rate in detecting biomarkers from ten or hundreds of spectra. Here a new procedure is introduced for feature extraction in mass spectrometry data that extends the continuous wavelet transform-based (CWT-based) algorithm to multiple spectra. The proposed multispectra CWT-based algorithm (MCWT) not only can perform peak detection for multiple spectra but also carry out peak alignment at the same time. The author' MCWT algorithm constructs a reference, which integrates information of multiple raw spectra, for feature extraction. The algorithm is applied to a SELDI-TOF mass spectra data set provided by CAMDA 2006 with known polypeptide m/z positions. This new approach is easy to implement and it outperforms the existing peak extraction method from the Bioconductor PROcess package.

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

A new automated spectral feature extraction method and its application in spectral classification and defective spectra recovery

NASA Astrophysics Data System (ADS)

Wang, Ke; Guo, Ping; Luo, A.-Li

2017-03-01

Spectral feature extraction is a crucial procedure in automated spectral analysis. This procedure starts from the spectral data and produces informative and non-redundant features, facilitating the subsequent automated processing and analysis with machine-learning and data-mining techniques. In this paper, we present a new automated feature extraction method for astronomical spectra, with application in spectral classification and defective spectra recovery. The basic idea of our approach is to train a deep neural network to extract features of spectra with different levels of abstraction in different layers. The deep neural network is trained with a fast layer-wise learning algorithm in an analytical way without any iterative optimization procedure. We evaluate the performance of the proposed scheme on real-world spectral data. The results demonstrate that our method is superior regarding its comprehensive performance, and the computational cost is significantly lower than that for other methods. The proposed method can be regarded as a new valid alternative general-purpose feature extraction method for various tasks in spectral data analysis.

A Study for Texture Feature Extraction of High-Resolution Satellite Images Based on a Direction Measure and Gray Level Co-Occurrence Matrix Fusion Algorithm

PubMed Central

Zhang, Xin; Cui, Jintian; Wang, Weisheng; Lin, Chao

2017-01-01

To address the problem of image texture feature extraction, a direction measure statistic that is based on the directionality of image texture is constructed, and a new method of texture feature extraction, which is based on the direction measure and a gray level co-occurrence matrix (GLCM) fusion algorithm, is proposed in this paper. This method applies the GLCM to extract the texture feature value of an image and integrates the weight factor that is introduced by the direction measure to obtain the final texture feature of an image. A set of classification experiments for the high-resolution remote sensing images were performed by using support vector machine (SVM) classifier with the direction measure and gray level co-occurrence matrix fusion algorithm. Both qualitative and quantitative approaches were applied to assess the classification results. The experimental results demonstrated that texture feature extraction based on the fusion algorithm achieved a better image recognition, and the accuracy of classification based on this method has been significantly improved. PMID:28640181

Classification of EEG Signals Based on Pattern Recognition Approach.

PubMed

Amin, Hafeez Ullah; Mumtaz, Wajid; Subhani, Ahmad Rauf; Saad, Mohamad Naufal Mohamad; Malik, Aamir Saeed

2017-01-01

Feature extraction is an important step in the process of electroencephalogram (EEG) signal classification. The authors propose a "pattern recognition" approach that discriminates EEG signals recorded during different cognitive conditions. Wavelet based feature extraction such as, multi-resolution decompositions into detailed and approximate coefficients as well as relative wavelet energy were computed. Extracted relative wavelet energy features were normalized to zero mean and unit variance and then optimized using Fisher's discriminant ratio (FDR) and principal component analysis (PCA). A high density EEG dataset validated the proposed method (128-channels) by identifying two classifications: (1) EEG signals recorded during complex cognitive tasks using Raven's Advance Progressive Metric (RAPM) test; (2) EEG signals recorded during a baseline task (eyes open). Classifiers such as, K-nearest neighbors (KNN), Support Vector Machine (SVM), Multi-layer Perceptron (MLP), and Naïve Bayes (NB) were then employed. Outcomes yielded 99.11% accuracy via SVM classifier for coefficient approximations (A5) of low frequencies ranging from 0 to 3.90 Hz. Accuracy rates for detailed coefficients were 98.57 and 98.39% for SVM and KNN, respectively; and for detailed coefficients (D5) deriving from the sub-band range (3.90-7.81 Hz). Accuracy rates for MLP and NB classifiers were comparable at 97.11-89.63% and 91.60-81.07% for A5 and D5 coefficients, respectively. In addition, the proposed approach was also applied on public dataset for classification of two cognitive tasks and achieved comparable classification results, i.e., 93.33% accuracy with KNN. The proposed scheme yielded significantly higher classification performances using machine learning classifiers compared to extant quantitative feature extraction. These results suggest the proposed feature extraction method reliably classifies EEG signals recorded during cognitive tasks with a higher degree of accuracy.

Classification of EEG Signals Based on Pattern Recognition Approach

PubMed Central

Amin, Hafeez Ullah; Mumtaz, Wajid; Subhani, Ahmad Rauf; Saad, Mohamad Naufal Mohamad; Malik, Aamir Saeed

2017-01-01

Feature extraction is an important step in the process of electroencephalogram (EEG) signal classification. The authors propose a “pattern recognition” approach that discriminates EEG signals recorded during different cognitive conditions. Wavelet based feature extraction such as, multi-resolution decompositions into detailed and approximate coefficients as well as relative wavelet energy were computed. Extracted relative wavelet energy features were normalized to zero mean and unit variance and then optimized using Fisher's discriminant ratio (FDR) and principal component analysis (PCA). A high density EEG dataset validated the proposed method (128-channels) by identifying two classifications: (1) EEG signals recorded during complex cognitive tasks using Raven's Advance Progressive Metric (RAPM) test; (2) EEG signals recorded during a baseline task (eyes open). Classifiers such as, K-nearest neighbors (KNN), Support Vector Machine (SVM), Multi-layer Perceptron (MLP), and Naïve Bayes (NB) were then employed. Outcomes yielded 99.11% accuracy via SVM classifier for coefficient approximations (A5) of low frequencies ranging from 0 to 3.90 Hz. Accuracy rates for detailed coefficients were 98.57 and 98.39% for SVM and KNN, respectively; and for detailed coefficients (D5) deriving from the sub-band range (3.90–7.81 Hz). Accuracy rates for MLP and NB classifiers were comparable at 97.11–89.63% and 91.60–81.07% for A5 and D5 coefficients, respectively. In addition, the proposed approach was also applied on public dataset for classification of two cognitive tasks and achieved comparable classification results, i.e., 93.33% accuracy with KNN. The proposed scheme yielded significantly higher classification performances using machine learning classifiers compared to extant quantitative feature extraction. These results suggest the proposed feature extraction method reliably classifies EEG signals recorded during cognitive tasks with a higher degree of accuracy. PMID:29209190

ANN based Performance Evaluation of BDI for Condition Monitoring of Induction Motor Bearings

NASA Astrophysics Data System (ADS)

Patel, Raj Kumar; Giri, V. K.

2017-06-01

One of the critical parts in rotating machines is bearings and most of the failure arises from the defective bearings. Bearing failure leads to failure of a machine and the unpredicted productivity loss in the performance. Therefore, bearing fault detection and prognosis is an integral part of the preventive maintenance procedures. In this paper vibration signal for four conditions of a deep groove ball bearing; normal (N), inner race defect (IRD), ball defect (BD) and outer race defect (ORD) were acquired from a customized bearing test rig, under four different conditions and three different fault sizes. Two approaches have been opted for statistical feature extraction from the vibration signal. In the first approach, raw signal is used for statistical feature extraction and in the second approach statistical features extracted are based on bearing damage index (BDI). The proposed BDI technique uses wavelet packet node energy coefficients analysis method. Both the features are used as inputs to an ANN classifier to evaluate its performance. A comparison of ANN performance is made based on raw vibration data and data chosen by using BDI. The ANN performance has been found to be fairly higher when BDI based signals were used as inputs to the classifier.

A combinatorial feature selection approach to describe the QSAR of dual site inhibitors of acetylcholinesterase.

PubMed

Asadabadi, Ebrahim Barzegari; Abdolmaleki, Parviz; Barkooie, Seyyed Mohsen Hosseini; Jahandideh, Samad; Rezaei, Mohammad Ali

2009-12-01

Regarding the great potential of dual binding site inhibitors of acetylcholinesterase as the future potent drugs of Alzheimer's disease, this study was devoted to extraction of the most effective structural features of these inhibitors from among a large number of quantitative descriptors. To do this, we adopted a unique approach in quantitative structure-activity relationships. An efficient feature selection method was emphasized in such an approach, using the confirmative results of different routine and novel feature selection methods. The proposed methods generated quite consistent results ensuring the effectiveness of the selected structural features.

Automated Recognition of 3D Features in GPIR Images

NASA Technical Reports Server (NTRS)

Park, Han; Stough, Timothy; Fijany, Amir

2007-01-01

A method of automated recognition of three-dimensional (3D) features in images generated by ground-penetrating imaging radar (GPIR) is undergoing development. GPIR 3D images can be analyzed to detect and identify such subsurface features as pipes and other utility conduits. Until now, much of the analysis of GPIR images has been performed manually by expert operators who must visually identify and track each feature. The present method is intended to satisfy a need for more efficient and accurate analysis by means of algorithms that can automatically identify and track subsurface features, with minimal supervision by human operators. In this method, data from multiple sources (for example, data on different features extracted by different algorithms) are fused together for identifying subsurface objects. The algorithms of this method can be classified in several different ways. In one classification, the algorithms fall into three classes: (1) image-processing algorithms, (2) feature- extraction algorithms, and (3) a multiaxis data-fusion/pattern-recognition algorithm that includes a combination of machine-learning, pattern-recognition, and object-linking algorithms. The image-processing class includes preprocessing algorithms for reducing noise and enhancing target features for pattern recognition. The feature-extraction algorithms operate on preprocessed data to extract such specific features in images as two-dimensional (2D) slices of a pipe. Then the multiaxis data-fusion/ pattern-recognition algorithm identifies, classifies, and reconstructs 3D objects from the extracted features. In this process, multiple 2D features extracted by use of different algorithms and representing views along different directions are used to identify and reconstruct 3D objects. In object linking, which is an essential part of this process, features identified in successive 2D slices and located within a threshold radius of identical features in adjacent slices are linked in a directed-graph data structure. Relative to past approaches, this multiaxis approach offers the advantages of more reliable detections, better discrimination of objects, and provision of redundant information, which can be helpful in filling gaps in feature recognition by one of the component algorithms. The image-processing class also includes postprocessing algorithms that enhance identified features to prepare them for further scrutiny by human analysts (see figure). Enhancement of images as a postprocessing step is a significant departure from traditional practice, in which enhancement of images is a preprocessing step.

An X-Band Radar Terrain Feature Detection Method for Low-Altitude SVS Operations and Calibration Using LiDAR

NASA Technical Reports Server (NTRS)

Young, Steve; UijtdeHaag, Maarten; Campbell, Jacob

2004-01-01

To enable safe use of Synthetic Vision Systems at low altitudes, real-time range-to-terrain measurements may be required to ensure the integrity of terrain models stored in the system. This paper reviews and extends previous work describing the application of x-band radar to terrain model integrity monitoring. A method of terrain feature extraction and a transformation of the features to a common reference domain are proposed. Expected error distributions for the extracted features are required to establish appropriate thresholds whereby a consistency-checking function can trigger an alert. A calibration-based approach is presented that can be used to obtain these distributions. To verify the approach, NASA's DC-8 airborne science platform was used to collect data from two mapping sensors. An Airborne Laser Terrain Mapping (ALTM) sensor was installed in the cargo bay of the DC-8. After processing, the ALTM produced a reference terrain model with a vertical accuracy of less than one meter. Also installed was a commercial-off-the-shelf x-band radar in the nose radome of the DC-8. Although primarily designed to measure precipitation, the radar also provides estimates of terrain reflectivity at low altitudes. Using the ALTM data as the reference, errors in features extracted from the radar are estimated. A method to estimate errors in features extracted from the terrain model is also presented.

An integrated multi-sensor fusion-based deep feature learning approach for rotating machinery diagnosis

NASA Astrophysics Data System (ADS)

Liu, Jie; Hu, Youmin; Wang, Yan; Wu, Bo; Fan, Jikai; Hu, Zhongxu

2018-05-01

The diagnosis of complicated fault severity problems in rotating machinery systems is an important issue that affects the productivity and quality of manufacturing processes and industrial applications. However, it usually suffers from several deficiencies. (1) A considerable degree of prior knowledge and expertise is required to not only extract and select specific features from raw sensor signals, and but also choose a suitable fusion for sensor information. (2) Traditional artificial neural networks with shallow architectures are usually adopted and they have a limited ability to learn the complex and variable operating conditions. In multi-sensor-based diagnosis applications in particular, massive high-dimensional and high-volume raw sensor signals need to be processed. In this paper, an integrated multi-sensor fusion-based deep feature learning (IMSFDFL) approach is developed to identify the fault severity in rotating machinery processes. First, traditional statistics and energy spectrum features are extracted from multiple sensors with multiple channels and combined. Then, a fused feature vector is constructed from all of the acquisition channels. Further, deep feature learning with stacked auto-encoders is used to obtain the deep features. Finally, the traditional softmax model is applied to identify the fault severity. The effectiveness of the proposed IMSFDFL approach is primarily verified by a one-stage gearbox experimental platform that uses several accelerometers under different operating conditions. This approach can identify fault severity more effectively than the traditional approaches.

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.

Recognition of Similar Shaped Handwritten Marathi Characters Using Artificial Neural Network

NASA Astrophysics Data System (ADS)

Jane, Archana P.; Pund, Mukesh A.

2012-03-01

The growing need have handwritten Marathi character recognition in Indian offices such as passport, railways etc has made it vital area of a research. Similar shape characters are more prone to misclassification. In this paper a novel method is provided to recognize handwritten Marathi characters based on their features extraction and adaptive smoothing technique. Feature selections methods avoid unnecessary patterns in an image whereas adaptive smoothing technique form smooth shape of charecters.Combination of both these approaches leads to the better results. Previous study shows that, no one technique achieves 100% accuracy in handwritten character recognition area. This approach of combining both adaptive smoothing & feature extraction gives better results (approximately 75-100) and expected outcomes.

Building Facade Reconstruction by Fusing Terrestrial Laser Points and Images

PubMed Central

Pu, Shi; Vosselman, George

2009-01-01

Laser data and optical data have a complementary nature for three dimensional feature extraction. Efficient integration of the two data sources will lead to a more reliable and automated extraction of three dimensional features. This paper presents a semiautomatic building facade reconstruction approach, which efficiently combines information from terrestrial laser point clouds and close range images. A building facade's general structure is discovered and established using the planar features from laser data. Then strong lines in images are extracted using Canny extractor and Hough transformation, and compared with current model edges for necessary improvement. Finally, textures with optimal visibility are selected and applied according to accurate image orientations. Solutions to several challenge problems throughout the collaborated reconstruction, such as referencing between laser points and multiple images and automated texturing, are described. The limitations and remaining works of this approach are also discussed. PMID:22408539

A Genetic-Based Feature Selection Approach in the Identification of Left/Right Hand Motor Imagery for a Brain-Computer Interface

PubMed Central

Yaacoub, Charles; Mhanna, Georges; Rihana, Sandy

2017-01-01

Electroencephalography is a non-invasive measure of the brain electrical activity generated by millions of neurons. Feature extraction in electroencephalography analysis is a core issue that may lead to accurate brain mental state classification. This paper presents a new feature selection method that improves left/right hand movement identification of a motor imagery brain-computer interface, based on genetic algorithms and artificial neural networks used as classifiers. Raw electroencephalography signals are first preprocessed using appropriate filtering. Feature extraction is carried out afterwards, based on spectral and temporal signal components, and thus a feature vector is constructed. As various features might be inaccurate and mislead the classifier, thus degrading the overall system performance, the proposed approach identifies a subset of features from a large feature space, such that the classifier error rate is reduced. Experimental results show that the proposed method is able to reduce the number of features to as low as 0.5% (i.e., the number of ignored features can reach 99.5%) while improving the accuracy, sensitivity, specificity, and precision of the classifier. PMID:28124985

A Genetic-Based Feature Selection Approach in the Identification of Left/Right Hand Motor Imagery for a Brain-Computer Interface.

PubMed

Yaacoub, Charles; Mhanna, Georges; Rihana, Sandy

2017-01-23

Electroencephalography is a non-invasive measure of the brain electrical activity generated by millions of neurons. Feature extraction in electroencephalography analysis is a core issue that may lead to accurate brain mental state classification. This paper presents a new feature selection method that improves left/right hand movement identification of a motor imagery brain-computer interface, based on genetic algorithms and artificial neural networks used as classifiers. Raw electroencephalography signals are first preprocessed using appropriate filtering. Feature extraction is carried out afterwards, based on spectral and temporal signal components, and thus a feature vector is constructed. As various features might be inaccurate and mislead the classifier, thus degrading the overall system performance, the proposed approach identifies a subset of features from a large feature space, such that the classifier error rate is reduced. Experimental results show that the proposed method is able to reduce the number of features to as low as 0.5% (i.e., the number of ignored features can reach 99.5%) while improving the accuracy, sensitivity, specificity, and precision of the classifier.

An approach to predict Sudden Cardiac Death (SCD) using time domain and bispectrum features from HRV signal.

PubMed

Houshyarifar, Vahid; Chehel Amirani, Mehdi

2016-08-12

In this paper we present a method to predict Sudden Cardiac Arrest (SCA) with higher order spectral (HOS) and linear (Time) features extracted from heart rate variability (HRV) signal. Predicting the occurrence of SCA is important in order to avoid the probability of Sudden Cardiac Death (SCD). This work is a challenge to predict five minutes before SCA onset. The method consists of four steps: pre-processing, feature extraction, feature reduction, and classification. In the first step, the QRS complexes are detected from the electrocardiogram (ECG) signal and then the HRV signal is extracted. In second step, bispectrum features of HRV signal and time-domain features are obtained. Six features are extracted from bispectrum and two features from time-domain. In the next step, these features are reduced to one feature by the linear discriminant analysis (LDA) technique. Finally, KNN and support vector machine-based classifiers are used to classify the HRV signals. We used two database named, MIT/BIH Sudden Cardiac Death (SCD) Database and Physiobank Normal Sinus Rhythm (NSR). In this work we achieved prediction of SCD occurrence for six minutes before the SCA with the accuracy over 91%.

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.

Localized thin-section CT with radiomics feature extraction and machine learning to classify early-detected pulmonary nodules from lung cancer screening

NASA Astrophysics Data System (ADS)

Tu, Shu-Ju; Wang, Chih-Wei; Pan, Kuang-Tse; Wu, Yi-Cheng; Wu, Chen-Te

2018-03-01

Lung cancer screening aims to detect small pulmonary nodules and decrease the mortality rate of those affected. However, studies from large-scale clinical trials of lung cancer screening have shown that the false-positive rate is high and positive predictive value is low. To address these problems, a technical approach is greatly needed for accurate malignancy differentiation among these early-detected nodules. We studied the clinical feasibility of an additional protocol of localized thin-section CT for further assessment on recalled patients from lung cancer screening tests. Our approach of localized thin-section CT was integrated with radiomics features extraction and machine learning classification which was supervised by pathological diagnosis. Localized thin-section CT images of 122 nodules were retrospectively reviewed and 374 radiomics features were extracted. In this study, 48 nodules were benign and 74 malignant. There were nine patients with multiple nodules and four with synchronous multiple malignant nodules. Different machine learning classifiers with a stratified ten-fold cross-validation were used and repeated 100 times to evaluate classification accuracy. Of the image features extracted from the thin-section CT images, 238 (64%) were useful in differentiating between benign and malignant nodules. These useful features include CT density (p  =  0.002 518), sigma (p  =  0.002 781), uniformity (p  =  0.032 41), and entropy (p  =  0.006 685). The highest classification accuracy was 79% by the logistic classifier. The performance metrics of this logistic classification model was 0.80 for the positive predictive value, 0.36 for the false-positive rate, and 0.80 for the area under the receiver operating characteristic curve. Our approach of direct risk classification supervised by the pathological diagnosis with localized thin-section CT and radiomics feature extraction may support clinical physicians in determining truly malignant nodules and therefore reduce problems in lung cancer screening.

Localized thin-section CT with radiomics feature extraction and machine learning to classify early-detected pulmonary nodules from lung cancer screening.

PubMed

Tu, Shu-Ju; Wang, Chih-Wei; Pan, Kuang-Tse; Wu, Yi-Cheng; Wu, Chen-Te

2018-03-14

Lung cancer screening aims to detect small pulmonary nodules and decrease the mortality rate of those affected. However, studies from large-scale clinical trials of lung cancer screening have shown that the false-positive rate is high and positive predictive value is low. To address these problems, a technical approach is greatly needed for accurate malignancy differentiation among these early-detected nodules. We studied the clinical feasibility of an additional protocol of localized thin-section CT for further assessment on recalled patients from lung cancer screening tests. Our approach of localized thin-section CT was integrated with radiomics features extraction and machine learning classification which was supervised by pathological diagnosis. Localized thin-section CT images of 122 nodules were retrospectively reviewed and 374 radiomics features were extracted. In this study, 48 nodules were benign and 74 malignant. There were nine patients with multiple nodules and four with synchronous multiple malignant nodules. Different machine learning classifiers with a stratified ten-fold cross-validation were used and repeated 100 times to evaluate classification accuracy. Of the image features extracted from the thin-section CT images, 238 (64%) were useful in differentiating between benign and malignant nodules. These useful features include CT density (p  =  0.002 518), sigma (p  =  0.002 781), uniformity (p  =  0.032 41), and entropy (p  =  0.006 685). The highest classification accuracy was 79% by the logistic classifier. The performance metrics of this logistic classification model was 0.80 for the positive predictive value, 0.36 for the false-positive rate, and 0.80 for the area under the receiver operating characteristic curve. Our approach of direct risk classification supervised by the pathological diagnosis with localized thin-section CT and radiomics feature extraction may support clinical physicians in determining truly malignant nodules and therefore reduce problems in lung cancer screening.

Machine learning approach for automated screening of malaria parasite using light microscopic images.

PubMed

Das, Dev Kumar; Ghosh, Madhumala; Pal, Mallika; Maiti, Asok K; Chakraborty, Chandan

2013-02-01

The aim of this paper is to address the development of computer assisted malaria parasite characterization and classification using machine learning approach based on light microscopic images of peripheral blood smears. In doing this, microscopic image acquisition from stained slides, illumination correction and noise reduction, erythrocyte segmentation, feature extraction, feature selection and finally classification of different stages of malaria (Plasmodium vivax and Plasmodium falciparum) have been investigated. The erythrocytes are segmented using marker controlled watershed transformation and subsequently total ninety six features describing shape-size and texture of erythrocytes are extracted in respect to the parasitemia infected versus non-infected cells. Ninety four features are found to be statistically significant in discriminating six classes. Here a feature selection-cum-classification scheme has been devised by combining F-statistic, statistical learning techniques i.e., Bayesian learning and support vector machine (SVM) in order to provide the higher classification accuracy using best set of discriminating features. Results show that Bayesian approach provides the highest accuracy i.e., 84% for malaria classification by selecting 19 most significant features while SVM provides highest accuracy i.e., 83.5% with 9 most significant features. Finally, the performance of these two classifiers under feature selection framework has been compared toward malaria parasite classification. Copyright © 2012 Elsevier Ltd. All rights reserved.

A Deep Convolutional Neural Network for segmenting and classifying epithelial and stromal regions in histopathological images

PubMed Central

Xu, Jun; Luo, Xiaofei; Wang, Guanhao; Gilmore, Hannah; Madabhushi, Anant

2016-01-01

Epithelial (EP) and stromal (ST) are two types of tissues in histological images. Automated segmentation or classification of EP and ST tissues is important when developing computerized system for analyzing the tumor microenvironment. In this paper, a Deep Convolutional Neural Networks (DCNN) based feature learning is presented to automatically segment or classify EP and ST regions from digitized tumor tissue microarrays (TMAs). Current approaches are based on handcraft feature representation, such as color, texture, and Local Binary Patterns (LBP) in classifying two regions. Compared to handcrafted feature based approaches, which involve task dependent representation, DCNN is an end-to-end feature extractor that may be directly learned from the raw pixel intensity value of EP and ST tissues in a data driven fashion. These high-level features contribute to the construction of a supervised classifier for discriminating the two types of tissues. In this work we compare DCNN based models with three handcraft feature extraction based approaches on two different datasets which consist of 157 Hematoxylin and Eosin (H&E) stained images of breast cancer and 1376 immunohistological (IHC) stained images of colorectal cancer, respectively. The DCNN based feature learning approach was shown to have a F1 classification score of 85%, 89%, and 100%, accuracy (ACC) of 84%, 88%, and 100%, and Matthews Correlation Coefficient (MCC) of 86%, 77%, and 100% on two H&E stained (NKI and VGH) and IHC stained data, respectively. Our DNN based approach was shown to outperform three handcraft feature extraction based approaches in terms of the classification of EP and ST regions. PMID:28154470

A Deep Convolutional Neural Network for segmenting and classifying epithelial and stromal regions in histopathological images.

PubMed

Xu, Jun; Luo, Xiaofei; Wang, Guanhao; Gilmore, Hannah; Madabhushi, Anant

2016-05-26

Epithelial (EP) and stromal (ST) are two types of tissues in histological images. Automated segmentation or classification of EP and ST tissues is important when developing computerized system for analyzing the tumor microenvironment. In this paper, a Deep Convolutional Neural Networks (DCNN) based feature learning is presented to automatically segment or classify EP and ST regions from digitized tumor tissue microarrays (TMAs). Current approaches are based on handcraft feature representation, such as color, texture, and Local Binary Patterns (LBP) in classifying two regions. Compared to handcrafted feature based approaches, which involve task dependent representation, DCNN is an end-to-end feature extractor that may be directly learned from the raw pixel intensity value of EP and ST tissues in a data driven fashion. These high-level features contribute to the construction of a supervised classifier for discriminating the two types of tissues. In this work we compare DCNN based models with three handcraft feature extraction based approaches on two different datasets which consist of 157 Hematoxylin and Eosin (H&E) stained images of breast cancer and 1376 immunohistological (IHC) stained images of colorectal cancer, respectively. The DCNN based feature learning approach was shown to have a F1 classification score of 85%, 89%, and 100%, accuracy (ACC) of 84%, 88%, and 100%, and Matthews Correlation Coefficient (MCC) of 86%, 77%, and 100% on two H&E stained (NKI and VGH) and IHC stained data, respectively. Our DNN based approach was shown to outperform three handcraft feature extraction based approaches in terms of the classification of EP and ST regions.

Improving EMG based classification of basic hand movements using EMD.

PubMed

Sapsanis, Christos; Georgoulas, George; Tzes, Anthony; Lymberopoulos, Dimitrios

2013-01-01

This paper presents a pattern recognition approach for the identification of basic hand movements using surface electromyographic (EMG) data. The EMG signal is decomposed using Empirical Mode Decomposition (EMD) into Intrinsic Mode Functions (IMFs) and subsequently a feature extraction stage takes place. Various combinations of feature subsets are tested using a simple linear classifier for the detection task. Our results suggest that the use of EMD can increase the discrimination ability of the conventional feature sets extracted from the raw EMG signal.

Wearable Sensor-Based Human Activity Recognition Method with Multi-Features Extracted from Hilbert-Huang Transform.

PubMed

Xu, Huile; Liu, Jinyi; Hu, Haibo; Zhang, Yi

2016-12-02

Wearable sensors-based human activity recognition introduces many useful applications and services in health care, rehabilitation training, elderly monitoring and many other areas of human interaction. Existing works in this field mainly focus on recognizing activities by using traditional features extracted from Fourier transform (FT) or wavelet transform (WT). However, these signal processing approaches are suitable for a linear signal but not for a nonlinear signal. In this paper, we investigate the characteristics of the Hilbert-Huang transform (HHT) for dealing with activity data with properties such as nonlinearity and non-stationarity. A multi-features extraction method based on HHT is then proposed to improve the effect of activity recognition. The extracted multi-features include instantaneous amplitude (IA) and instantaneous frequency (IF) by means of empirical mode decomposition (EMD), as well as instantaneous energy density (IE) and marginal spectrum (MS) derived from Hilbert spectral analysis. Experimental studies are performed to verify the proposed approach by using the PAMAP2 dataset from the University of California, Irvine for wearable sensors-based activity recognition. Moreover, the effect of combining multi-features vs. a single-feature are investigated and discussed in the scenario of a dependent subject. The experimental results show that multi-features combination can further improve the performance measures. Finally, we test the effect of multi-features combination in the scenario of an independent subject. Our experimental results show that we achieve four performance indexes: recall, precision, F-measure, and accuracy to 0.9337, 0.9417, 0.9353, and 0.9377 respectively, which are all better than the achievements of related works.

Wearable Sensor-Based Human Activity Recognition Method with Multi-Features Extracted from Hilbert-Huang Transform

PubMed Central

Xu, Huile; Liu, Jinyi; Hu, Haibo; Zhang, Yi

2016-01-01

Wearable sensors-based human activity recognition introduces many useful applications and services in health care, rehabilitation training, elderly monitoring and many other areas of human interaction. Existing works in this field mainly focus on recognizing activities by using traditional features extracted from Fourier transform (FT) or wavelet transform (WT). However, these signal processing approaches are suitable for a linear signal but not for a nonlinear signal. In this paper, we investigate the characteristics of the Hilbert-Huang transform (HHT) for dealing with activity data with properties such as nonlinearity and non-stationarity. A multi-features extraction method based on HHT is then proposed to improve the effect of activity recognition. The extracted multi-features include instantaneous amplitude (IA) and instantaneous frequency (IF) by means of empirical mode decomposition (EMD), as well as instantaneous energy density (IE) and marginal spectrum (MS) derived from Hilbert spectral analysis. Experimental studies are performed to verify the proposed approach by using the PAMAP2 dataset from the University of California, Irvine for wearable sensors-based activity recognition. Moreover, the effect of combining multi-features vs. a single-feature are investigated and discussed in the scenario of a dependent subject. The experimental results show that multi-features combination can further improve the performance measures. Finally, we test the effect of multi-features combination in the scenario of an independent subject. Our experimental results show that we achieve four performance indexes: recall, precision, F-measure, and accuracy to 0.9337, 0.9417, 0.9353, and 0.9377 respectively, which are all better than the achievements of related works. PMID:27918414

A Framework for Final Drive Simultaneous Failure Diagnosis Based on Fuzzy Entropy and Sparse Bayesian Extreme Learning Machine

PubMed Central

Ye, Qing; Pan, Hao; Liu, Changhua

2015-01-01

This research proposes a novel framework of final drive simultaneous failure diagnosis containing feature extraction, training paired diagnostic models, generating decision threshold, and recognizing simultaneous failure modes. In feature extraction module, adopt wavelet package transform and fuzzy entropy to reduce noise interference and extract representative features of failure mode. Use single failure sample to construct probability classifiers based on paired sparse Bayesian extreme learning machine which is trained only by single failure modes and have high generalization and sparsity of sparse Bayesian learning approach. To generate optimal decision threshold which can convert probability output obtained from classifiers into final simultaneous failure modes, this research proposes using samples containing both single and simultaneous failure modes and Grid search method which is superior to traditional techniques in global optimization. Compared with other frequently used diagnostic approaches based on support vector machine and probability neural networks, experiment results based on F 1-measure value verify that the diagnostic accuracy and efficiency of the proposed framework which are crucial for simultaneous failure diagnosis are superior to the existing approach. PMID:25722717

Local binary pattern variants-based adaptive texture features analysis for posed and nonposed facial expression recognition

NASA Astrophysics Data System (ADS)

Sultana, Maryam; Bhatti, Naeem; Javed, Sajid; Jung, Soon Ki

2017-09-01

Facial expression recognition (FER) is an important task for various computer vision applications. The task becomes challenging when it requires the detection and encoding of macro- and micropatterns of facial expressions. We present a two-stage texture feature extraction framework based on the local binary pattern (LBP) variants and evaluate its significance in recognizing posed and nonposed facial expressions. We focus on the parametric limitations of the LBP variants and investigate their effects for optimal FER. The size of the local neighborhood is an important parameter of the LBP technique for its extraction in images. To make the LBP adaptive, we exploit the granulometric information of the facial images to find the local neighborhood size for the extraction of center-symmetric LBP (CS-LBP) features. Our two-stage texture representations consist of an LBP variant and the adaptive CS-LBP features. Among the presented two-stage texture feature extractions, the binarized statistical image features and adaptive CS-LBP features were found showing high FER rates. Evaluation of the adaptive texture features shows competitive and higher performance than the nonadaptive features and other state-of-the-art approaches, respectively.

An automated approach for extracting Barrier Island morphology from digital elevation models

NASA Astrophysics Data System (ADS)

Wernette, Phillipe; Houser, Chris; Bishop, Michael P.

2016-06-01

The response and recovery of a barrier island to extreme storms depends on the elevation of the dune base and crest, both of which can vary considerably alongshore and through time. Quantifying the response to and recovery from storms requires that we can first identify and differentiate the dune(s) from the beach and back-barrier, which in turn depends on accurate identification and delineation of the dune toe, crest and heel. The purpose of this paper is to introduce a multi-scale automated approach for extracting beach, dune (dune toe, dune crest and dune heel), and barrier island morphology. The automated approach introduced here extracts the shoreline and back-barrier shoreline based on elevation thresholds, and extracts the dune toe, dune crest and dune heel based on the average relative relief (RR) across multiple spatial scales of analysis. The multi-scale automated RR approach to extracting dune toe, dune crest, and dune heel based upon relative relief is more objective than traditional approaches because every pixel is analyzed across multiple computational scales and the identification of features is based on the calculated RR values. The RR approach out-performed contemporary approaches and represents a fast objective means to define important beach and dune features for predicting barrier island response to storms. The RR method also does not require that the dune toe, crest, or heel are spatially continuous, which is important because dune morphology is likely naturally variable alongshore.

Driver drowsiness classification using fuzzy wavelet-packet-based feature-extraction algorithm.

PubMed

Khushaba, Rami N; Kodagoda, Sarath; Lal, Sara; Dissanayake, Gamini

2011-01-01

Driver drowsiness and loss of vigilance are a major cause of road accidents. Monitoring physiological signals while driving provides the possibility of detecting and warning of drowsiness and fatigue. The aim of this paper is to maximize the amount of drowsiness-related information extracted from a set of electroencephalogram (EEG), electrooculogram (EOG), and electrocardiogram (ECG) signals during a simulation driving test. Specifically, we develop an efficient fuzzy mutual-information (MI)- based wavelet packet transform (FMIWPT) feature-extraction method for classifying the driver drowsiness state into one of predefined drowsiness levels. The proposed method estimates the required MI using a novel approach based on fuzzy memberships providing an accurate-information content-estimation measure. The quality of the extracted features was assessed on datasets collected from 31 drivers on a simulation test. The experimental results proved the significance of FMIWPT in extracting features that highly correlate with the different drowsiness levels achieving a classification accuracy of 95%-- 97% on an average across all subjects.

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

Liu, Richen; Guo, Hanqi; Yuan, Xiaoru

Most of the existing approaches to visualize vector field ensembles are to reveal the uncertainty of individual variables, for example, statistics, variability, etc. However, a user-defined derived feature like vortex or air mass is also quite significant, since they make more sense to domain scientists. In this paper, we present a new framework to extract user-defined derived features from different simulation runs. Specially, we use a detail-to-overview searching scheme to help extract vortex with a user-defined shape. We further compute the geometry information including the size, the geo-spatial location of the extracted vortexes. We also design some linked views tomore » compare them between different runs. At last, the temporal information such as the occurrence time of the feature is further estimated and compared. Results show that our method is capable of extracting the features across different runs and comparing them spatially and temporally.« less

Multisensor-based real-time quality monitoring by means of feature extraction, selection and modeling for Al alloy in arc welding

NASA Astrophysics Data System (ADS)

Zhang, Zhifen; Chen, Huabin; Xu, Yanling; Zhong, Jiyong; Lv, Na; Chen, Shanben

2015-08-01

Multisensory data fusion-based online welding quality monitoring has gained increasing attention in intelligent welding process. This paper mainly focuses on the automatic detection of typical welding defect for Al alloy in gas tungsten arc welding (GTAW) by means of analzing arc spectrum, sound and voltage signal. Based on the developed algorithms in time and frequency domain, 41 feature parameters were successively extracted from these signals to characterize the welding process and seam quality. Then, the proposed feature selection approach, i.e., hybrid fisher-based filter and wrapper was successfully utilized to evaluate the sensitivity of each feature and reduce the feature dimensions. Finally, the optimal feature subset with 19 features was selected to obtain the highest accuracy, i.e., 94.72% using established classification model. This study provides a guideline for feature extraction, selection and dynamic modeling based on heterogeneous multisensory data to achieve a reliable online defect detection system in arc welding.

Joint recognition and discrimination in nonlinear feature space

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.

1997-09-01

A new general method for linear and nonlinear feature extraction is presented. It is novel since it provides both representation and discrimination while most other methods are concerned with only one of these issues. We call this approach the maximum representation and discrimination feature (MRDF) method and show that the Bayes classifier and the Karhunen- Loeve transform are special cases of it. We refer to our nonlinear feature extraction technique as nonlinear eigen- feature extraction. It is new since it has a closed-form solution and produces nonlinear decision surfaces with higher rank than do iterative methods. Results on synthetic databases are shown and compared with results from standard Fukunaga- Koontz transform and Fisher discriminant function methods. The method is also applied to an automated product inspection problem (discrimination) and to the classification and pose estimation of two similar objects (representation and discrimination).

Classification of high-resolution multispectral satellite remote sensing images using extended morphological attribute profiles and independent component analysis

NASA Astrophysics Data System (ADS)

Wu, Yu; Zheng, Lijuan; Xie, Donghai; Zhong, Ruofei

2017-07-01

In this study, the extended morphological attribute profiles (EAPs) and independent component analysis (ICA) were combined for feature extraction of high-resolution multispectral satellite remote sensing images and the regularized least squares (RLS) approach with the radial basis function (RBF) kernel was further applied for the classification. Based on the major two independent components, the geometrical features were extracted using the EAPs method. In this study, three morphological attributes were calculated and extracted for each independent component, including area, standard deviation, and moment of inertia. The extracted geometrical features classified results using RLS approach and the commonly used LIB-SVM library of support vector machines method. The Worldview-3 and Chinese GF-2 multispectral images were tested, and the results showed that the features extracted by EAPs and ICA can effectively improve the accuracy of the high-resolution multispectral image classification, 2% larger than EAPs and principal component analysis (PCA) method, and 6% larger than APs and original high-resolution multispectral data. Moreover, it is also suggested that both the GURLS and LIB-SVM libraries are well suited for the multispectral remote sensing image classification. The GURLS library is easy to be used with automatic parameter selection but its computation time may be larger than the LIB-SVM library. This study would be helpful for the classification application of high-resolution multispectral satellite remote sensing images.

A new approach for automatic matching of ground control points in urban areas from heterogeneous images

NASA Astrophysics Data System (ADS)

Cong, Chao; Liu, Dingsheng; Zhao, Lingjun

2008-12-01

This paper discusses a new method for the automatic matching of ground control points (GCPs) between satellite remote sensing Image and digital raster graphic (DRG) in urban areas. The key of this method is to automatically extract tie point pairs according to geographic characters from such heterogeneous images. Since there are big differences between such heterogeneous images respect to texture and corner features, more detail analyzations are performed to find similarities and differences between high resolution remote sensing Image and (DRG). Furthermore a new algorithms based on the fuzzy-c means (FCM) method is proposed to extract linear feature in remote sensing Image. Based on linear feature, crossings and corners extracted from these features are chosen as GCPs. On the other hand, similar method was used to find same features from DRGs. Finally, Hausdorff Distance was adopted to pick matching GCPs from above two GCP groups. Experiences shown the method can extract GCPs from such images with a reasonable RMS error.

A wavelet-based approach for a continuous analysis of phonovibrograms.

PubMed

Unger, Jakob; Meyer, Tobias; Doellinger, Michael; Hecker, Dietmar J; Schick, Bernhard; Lohscheller, Joerg

2012-01-01

Recently, endoscopic high-speed laryngoscopy has been established for commercial use and constitutes a state-of-the-art technique to examine vocal fold dynamics. Despite overcoming many limitations of commonly applied stroboscopy it has not gained widespread clinical application, yet. A major drawback is a missing methodology of extracting valuable features to support visual assessment or computer-aided diagnosis. In this paper a compact and descriptive feature set is presented. The feature extraction routines are based on two-dimensional color graphs called phonovibrograms (PVG). These graphs contain the full spatio-temporal pattern of vocal fold dynamics and are therefore suited to derive features that comprehensively describe the vibration pattern of vocal folds. Within our approach, clinically relevant features such as glottal closure type, symmetry and periodicity are quantified in a set of 10 descriptive features. The suitability for classification tasks is shown using a clinical data set comprising 50 healthy and 50 paralytic subjects. A classification accuracy of 93.2% has been achieved.

Finger-Vein Verification Based on Multi-Features Fusion

PubMed Central

Qin, Huafeng; Qin, Lan; Xue, Lian; He, Xiping; Yu, Chengbo; Liang, Xinyuan

2013-01-01

This paper presents a new scheme to improve the performance of finger-vein identification systems. Firstly, a vein pattern extraction method to extract the finger-vein shape and orientation features is proposed. Secondly, to accommodate the potential local and global variations at the same time, a region-based matching scheme is investigated by employing the Scale Invariant Feature Transform (SIFT) matching method. Finally, the finger-vein shape, orientation and SIFT features are combined to further enhance the performance. The experimental results on databases of 426 and 170 fingers demonstrate the consistent superiority of the proposed approach. PMID:24196433

A Local DCT-II Feature Extraction Approach for Personal Identification Based on Palmprint

NASA Astrophysics Data System (ADS)

Choge, H. Kipsang; Oyama, Tadahiro; Karungaru, Stephen; Tsuge, Satoru; Fukumi, Minoru

Biometric applications based on the palmprint have recently attracted increased attention from various researchers. In this paper, a method is presented that differs from the commonly used global statistical and structural techniques by extracting and using local features instead. The middle palm area is extracted after preprocessing for rotation, position and illumination normalization. The segmented region of interest is then divided into blocks of either 8×8 or 16×16 pixels in size. The type-II Discrete Cosine Transform (DCT) is applied to transform the blocks into DCT space. A subset of coefficients that encode the low to medium frequency components is selected using the JPEG-style zigzag scanning method. Features from each block are subsequently concatenated into a compact feature vector and used in palmprint verification experiments with palmprints from the PolyU Palmprint Database. Results indicate that this approach achieves better results than many conventional transform-based methods, with an excellent recognition accuracy above 99% and an Equal Error Rate (EER) of less than 1.2% in palmprint verification.

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

Wang, Shaobu; Lu, Shuai; Zhou, Ning

In interconnected power systems, dynamic model reduction can be applied on generators outside the area of interest to mitigate the computational cost with transient stability studies. This paper presents an approach of deriving the reduced dynamic model of the external area based on dynamic response measurements, which comprises of three steps, dynamic-feature extraction, attribution and reconstruction (DEAR). In the DEAR approach, a feature extraction technique, such as singular value decomposition (SVD), is applied to the measured generator dynamics after a disturbance. Characteristic generators are then identified in the feature attribution step for matching the extracted dynamic features with the highestmore » similarity, forming a suboptimal ‘basis’ of system dynamics. In the reconstruction step, generator state variables such as rotor angles and voltage magnitudes are approximated with a linear combination of the characteristic generators, resulting in a quasi-nonlinear reduced model of the original external system. Network model is un-changed in the DEAR method. Tests on several IEEE standard systems show that the proposed method gets better reduction ratio and response errors than the traditional coherency aggregation methods.« less

Waveform fitting and geometry analysis for full-waveform lidar feature extraction

NASA Astrophysics Data System (ADS)

Tsai, Fuan; Lai, Jhe-Syuan; Cheng, Yi-Hsiu

2016-10-01

This paper presents a systematic approach that integrates spline curve fitting and geometry analysis to extract full-waveform LiDAR features for land-cover classification. The cubic smoothing spline algorithm is used to fit the waveform curve of the received LiDAR signals. After that, the local peak locations of the waveform curve are detected using a second derivative method. According to the detected local peak locations, commonly used full-waveform features such as full width at half maximum (FWHM) and amplitude can then be obtained. In addition, the number of peaks, time difference between the first and last peaks, and the average amplitude are also considered as features of LiDAR waveforms with multiple returns. Based on the waveform geometry, dynamic time-warping (DTW) is applied to measure the waveform similarity. The sum of the absolute amplitude differences that remain after time-warping can be used as a similarity feature in a classification procedure. An airborne full-waveform LiDAR data set was used to test the performance of the developed feature extraction method for land-cover classification. Experimental results indicate that the developed spline curve- fitting algorithm and geometry analysis can extract helpful full-waveform LiDAR features to produce better land-cover classification than conventional LiDAR data and feature extraction methods. In particular, the multiple-return features and the dynamic time-warping index can improve the classification results significantly.

Prostate cancer detection using machine learning techniques by employing combination of features extracting strategies.

PubMed

Hussain, Lal; Ahmed, Adeel; Saeed, Sharjil; Rathore, Saima; Awan, Imtiaz Ahmed; Shah, Saeed Arif; Majid, Abdul; Idris, Adnan; Awan, Anees Ahmed

2018-02-06

Prostate is a second leading causes of cancer deaths among men. Early detection of cancer can effectively reduce the rate of mortality caused by Prostate cancer. Due to high and multiresolution of MRIs from prostate cancer require a proper diagnostic systems and tools. In the past researchers developed Computer aided diagnosis (CAD) systems that help the radiologist to detect the abnormalities. In this research paper, we have employed novel Machine learning techniques such as Bayesian approach, Support vector machine (SVM) kernels: polynomial, radial base function (RBF) and Gaussian and Decision Tree for detecting prostate cancer. Moreover, different features extracting strategies are proposed to improve the detection performance. The features extracting strategies are based on texture, morphological, scale invariant feature transform (SIFT), and elliptic Fourier descriptors (EFDs) features. The performance was evaluated based on single as well as combination of features using Machine Learning Classification techniques. The Cross validation (Jack-knife k-fold) was performed and performance was evaluated in term of receiver operating curve (ROC) and specificity, sensitivity, Positive predictive value (PPV), negative predictive value (NPV), false positive rate (FPR). Based on single features extracting strategies, SVM Gaussian Kernel gives the highest accuracy of 98.34% with AUC of 0.999. While, using combination of features extracting strategies, SVM Gaussian kernel with texture + morphological, and EFDs + morphological features give the highest accuracy of 99.71% and AUC of 1.00.

Semantic attributes for people's appearance description: an appearance modality for video surveillance applications

NASA Astrophysics Data System (ADS)

Frikha, Mayssa; Fendri, Emna; Hammami, Mohamed

2017-09-01

Using semantic attributes such as gender, clothes, and accessories to describe people's appearance is an appealing modeling method for video surveillance applications. We proposed a midlevel appearance signature based on extracting a list of nameable semantic attributes describing the body in uncontrolled acquisition conditions. Conventional approaches extract the same set of low-level features to learn the semantic classifiers uniformly. Their critical limitation is the inability to capture the dominant visual characteristics for each trait separately. The proposed approach consists of extracting low-level features in an attribute-adaptive way by automatically selecting the most relevant features for each attribute separately. Furthermore, relying on a small training-dataset would easily lead to poor performance due to the large intraclass and interclass variations. We annotated large scale people images collected from different person reidentification benchmarks covering a large attribute sample and reflecting the challenges of uncontrolled acquisition conditions. These annotations were gathered into an appearance semantic attribute dataset that contains 3590 images annotated with 14 attributes. Various experiments prove that carefully designed features for learning the visual characteristics for an attribute provide an improvement of the correct classification accuracy and a reduction of both spatial and temporal complexities against state-of-the-art approaches.

Superpixel-Augmented Endmember Detection for Hyperspectral Images

NASA Technical Reports Server (NTRS)

Thompson, David R.; Castano, Rebecca; Gilmore, Martha

2011-01-01

Superpixels are homogeneous image regions comprised of several contiguous pixels. They are produced by shattering the image into contiguous, homogeneous regions that each cover between 20 and 100 image pixels. The segmentation aims for a many-to-one mapping from superpixels to image features; each image feature could contain several superpixels, but each superpixel occupies no more than one image feature. This conservative segmentation is relatively easy to automate in a robust fashion. Superpixel processing is related to the more general idea of improving hyperspectral analysis through spatial constraints, which can recognize subtle features at or below the level of noise by exploiting the fact that their spectral signatures are found in neighboring pixels. Recent work has explored spatial constraints for endmember extraction, showing significant advantages over techniques that ignore pixels relative positions. Methods such as AMEE (automated morphological endmember extraction) express spatial influence using fixed isometric relationships a local square window or Euclidean distance in pixel coordinates. In other words, two pixels covariances are based on their spatial proximity, but are independent of their absolute location in the scene. These isometric spatial constraints are most appropriate when spectral variation is smooth and constant over the image. Superpixels are simple to implement, efficient to compute, and are empirically effective. They can be used as a preprocessing step with any desired endmember extraction technique. Superpixels also have a solid theoretical basis in the hyperspectral linear mixing model, making them a principled approach for improving endmember extraction. Unlike existing approaches, superpixels can accommodate non-isometric covariance between image pixels (characteristic of discrete image features separated by step discontinuities). These kinds of image features are common in natural scenes. Analysts can substitute superpixels for image pixels during endmember analysis that leverages the spatial contiguity of scene features to enhance subtle spectral features. Superpixels define populations of image pixels that are independent samples from each image feature, permitting robust estimation of spectral properties, and reducing measurement noise in proportion to the area of the superpixel. This permits improved endmember extraction, and enables automated search for novel and constituent minerals in very noisy, hyperspatial images. This innovation begins with a graph-based segmentation based on the work of Felzenszwalb et al., but then expands their approach to the hyperspectral image domain with a Euclidean distance metric. Then, the mean spectrum of each segment is computed, and the resulting data cloud is used as input into sequential maximum angle convex cone (SMACC) endmember extraction.

An effective image classification method with the fusion of invariant feature and a new color descriptor

NASA Astrophysics Data System (ADS)

Mansourian, Leila; Taufik Abdullah, Muhamad; Nurliyana Abdullah, Lili; Azman, Azreen; Mustaffa, Mas Rina

2017-02-01

Pyramid Histogram of Words (PHOW), combined Bag of Visual Words (BoVW) with the spatial pyramid matching (SPM) in order to add location information to extracted features. However, different PHOW extracted from various color spaces, and they did not extract color information individually, that means they discard color information, which is an important characteristic of any image that is motivated by human vision. This article, concatenated PHOW Multi-Scale Dense Scale Invariant Feature Transform (MSDSIFT) histogram and a proposed Color histogram to improve the performance of existing image classification algorithms. Performance evaluation on several datasets proves that the new approach outperforms other existing, state-of-the-art methods.

A multiple kernel support vector machine scheme for feature selection and rule extraction from gene expression data of cancer tissue.

PubMed

Chen, Zhenyu; Li, Jianping; Wei, Liwei

2007-10-01

Recently, gene expression profiling using microarray techniques has been shown as a promising tool to improve the diagnosis and treatment of cancer. Gene expression data contain high level of noise and the overwhelming number of genes relative to the number of available samples. It brings out a great challenge for machine learning and statistic techniques. Support vector machine (SVM) has been successfully used to classify gene expression data of cancer tissue. In the medical field, it is crucial to deliver the user a transparent decision process. How to explain the computed solutions and present the extracted knowledge becomes a main obstacle for SVM. A multiple kernel support vector machine (MK-SVM) scheme, consisting of feature selection, rule extraction and prediction modeling is proposed to improve the explanation capacity of SVM. In this scheme, we show that the feature selection problem can be translated into an ordinary multiple parameters learning problem. And a shrinkage approach: 1-norm based linear programming is proposed to obtain the sparse parameters and the corresponding selected features. We propose a novel rule extraction approach using the information provided by the separating hyperplane and support vectors to improve the generalization capacity and comprehensibility of rules and reduce the computational complexity. Two public gene expression datasets: leukemia dataset and colon tumor dataset are used to demonstrate the performance of this approach. Using the small number of selected genes, MK-SVM achieves encouraging classification accuracy: more than 90% for both two datasets. Moreover, very simple rules with linguist labels are extracted. The rule sets have high diagnostic power because of their good classification performance.

Vaccine adverse event text mining system for extracting features from vaccine safety reports.

PubMed

Botsis, Taxiarchis; Buttolph, Thomas; Nguyen, Michael D; Winiecki, Scott; Woo, Emily Jane; Ball, Robert

2012-01-01

To develop and evaluate a text mining system for extracting key clinical features from vaccine adverse event reporting system (VAERS) narratives to aid in the automated review of adverse event reports. Based upon clinical significance to VAERS reviewing physicians, we defined the primary (diagnosis and cause of death) and secondary features (eg, symptoms) for extraction. We built a novel vaccine adverse event text mining (VaeTM) system based on a semantic text mining strategy. The performance of VaeTM was evaluated using a total of 300 VAERS reports in three sequential evaluations of 100 reports each. Moreover, we evaluated the VaeTM contribution to case classification; an information retrieval-based approach was used for the identification of anaphylaxis cases in a set of reports and was compared with two other methods: a dedicated text classifier and an online tool. The performance metrics of VaeTM were text mining metrics: recall, precision and F-measure. We also conducted a qualitative difference analysis and calculated sensitivity and specificity for classification of anaphylaxis cases based on the above three approaches. VaeTM performed best in extracting diagnosis, second level diagnosis, drug, vaccine, and lot number features (lenient F-measure in the third evaluation: 0.897, 0.817, 0.858, 0.874, and 0.914, respectively). In terms of case classification, high sensitivity was achieved (83.1%); this was equal and better compared to the text classifier (83.1%) and the online tool (40.7%), respectively. Our VaeTM implementation of a semantic text mining strategy shows promise in providing accurate and efficient extraction of key features from VAERS narratives.

Change Detection in Uav Video Mosaics Combining a Feature Based Approach and Extended Image Differencing

NASA Astrophysics Data System (ADS)

Saur, Günter; Krüger, Wolfgang

2016-06-01

Change detection is an important task when using unmanned aerial vehicles (UAV) for video surveillance. We address changes of short time scale using observations in time distances of a few hours. Each observation (previous and current) is a short video sequence acquired by UAV in near-Nadir view. Relevant changes are, e.g., recently parked or moved vehicles. Examples for non-relevant changes are parallaxes caused by 3D structures of the scene, shadow and illumination changes, and compression or transmission artifacts. In this paper we present (1) a new feature based approach to change detection, (2) a combination with extended image differencing (Saur et al., 2014), and (3) the application to video sequences using temporal filtering. In the feature based approach, information about local image features, e.g., corners, is extracted in both images. The label "new object" is generated at image points, where features occur in the current image and no or weaker features are present in the previous image. The label "vanished object" corresponds to missing or weaker features in the current image and present features in the previous image. This leads to two "directed" change masks and differs from image differencing where only one "undirected" change mask is extracted which combines both label types to the single label "changed object". The combination of both algorithms is performed by merging the change masks of both approaches. A color mask showing the different contributions is used for visual inspection by a human image interpreter.

Parallel Key Frame Extraction for Surveillance Video Service in a Smart City.

PubMed

Zheng, Ran; Yao, Chuanwei; Jin, Hai; Zhu, Lei; Zhang, Qin; Deng, Wei

2015-01-01

Surveillance video service (SVS) is one of the most important services provided in a smart city. It is very important for the utilization of SVS to provide design efficient surveillance video analysis techniques. Key frame extraction is a simple yet effective technique to achieve this goal. In surveillance video applications, key frames are typically used to summarize important video content. It is very important and essential to extract key frames accurately and efficiently. A novel approach is proposed to extract key frames from traffic surveillance videos based on GPU (graphics processing units) to ensure high efficiency and accuracy. For the determination of key frames, motion is a more salient feature in presenting actions or events, especially in surveillance videos. The motion feature is extracted in GPU to reduce running time. It is also smoothed to reduce noise, and the frames with local maxima of motion information are selected as the final key frames. The experimental results show that this approach can extract key frames more accurately and efficiently compared with several other methods.

Drunk driving detection based on classification of multivariate time series.

PubMed

Li, Zhenlong; Jin, Xue; Zhao, Xiaohua

2015-09-01

This paper addresses the problem of detecting drunk driving based on classification of multivariate time series. First, driving performance measures were collected from a test in a driving simulator located in the Traffic Research Center, Beijing University of Technology. Lateral position and steering angle were used to detect drunk driving. Second, multivariate time series analysis was performed to extract the features. A piecewise linear representation was used to represent multivariate time series. A bottom-up algorithm was then employed to separate multivariate time series. The slope and time interval of each segment were extracted as the features for classification. Third, a support vector machine classifier was used to classify driver's state into two classes (normal or drunk) according to the extracted features. The proposed approach achieved an accuracy of 80.0%. Drunk driving detection based on the analysis of multivariate time series is feasible and effective. The approach has implications for drunk driving detection. Copyright © 2015 Elsevier Ltd and National Safety Council. All rights reserved.

Feature Selection in Order to Extract Multiple Sclerosis Lesions Automatically in 3D Brain Magnetic Resonance Images Using Combination of Support Vector Machine and Genetic Algorithm.

PubMed

Khotanlou, Hassan; Afrasiabi, Mahlagha

2012-10-01

This paper presents a new feature selection approach for automatically extracting multiple sclerosis (MS) lesions in three-dimensional (3D) magnetic resonance (MR) images. Presented method is applicable to different types of MS lesions. In this method, T1, T2, and fluid attenuated inversion recovery (FLAIR) images are firstly preprocessed. In the next phase, effective features to extract MS lesions are selected by using a genetic algorithm (GA). The fitness function of the GA is the Similarity Index (SI) of a support vector machine (SVM) classifier. The results obtained on different types of lesions have been evaluated by comparison with manual segmentations. This algorithm is evaluated on 15 real 3D MR images using several measures. As a result, the SI between MS regions determined by the proposed method and radiologists was 87% on average. Experiments and comparisons with other methods show the effectiveness and the efficiency of the proposed approach.

Biomorphic networks: approach to invariant feature extraction and segmentation for ATR

NASA Astrophysics Data System (ADS)

Baek, Andrew; Farhat, Nabil H.

1998-10-01

Invariant features in two dimensional binary images are extracted in a single layer network of locally coupled spiking (pulsating) model neurons with prescribed synapto-dendritic response. The feature vector for an image is represented as invariant structure in the aggregate histogram of interspike intervals obtained by computing time intervals between successive spikes produced from each neuron over a given period of time and combining such intervals from all neurons in the network into a histogram. Simulation results show that the feature vectors are more pattern-specific and invariant under translation, rotation, and change in scale or intensity than achieved in earlier work. We also describe an application of such networks to segmentation of line (edge-enhanced or silhouette) images. The biomorphic spiking network's capabilities in segmentation and invariant feature extraction may prove to be, when they are combined, valuable in Automated Target Recognition (ATR) and other automated object recognition systems.

Improved EEG Event Classification Using Differential Energy.

PubMed

Harati, A; Golmohammadi, M; Lopez, S; Obeid, I; Picone, J

2015-12-01

Feature extraction for automatic classification of EEG signals typically relies on time frequency representations of the signal. Techniques such as cepstral-based filter banks or wavelets are popular analysis techniques in many signal processing applications including EEG classification. In this paper, we present a comparison of a variety of approaches to estimating and postprocessing features. To further aid in discrimination of periodic signals from aperiodic signals, we add a differential energy term. We evaluate our approaches on the TUH EEG Corpus, which is the largest publicly available EEG corpus and an exceedingly challenging task due to the clinical nature of the data. We demonstrate that a variant of a standard filter bank-based approach, coupled with first and second derivatives, provides a substantial reduction in the overall error rate. The combination of differential energy and derivatives produces a 24 % absolute reduction in the error rate and improves our ability to discriminate between signal events and background noise. This relatively simple approach proves to be comparable to other popular feature extraction approaches such as wavelets, but is much more computationally efficient.

Automated Image Registration Using Morphological Region of Interest Feature Extraction

NASA Technical Reports Server (NTRS)

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

2005-01-01

With the recent explosion in the amount of remotely sensed imagery and the corresponding interest in temporal change detection and modeling, image registration has become increasingly important as a necessary first step in the integration of multi-temporal and multi-sensor data for applications such as the analysis of seasonal and annual global climate changes, as well as land use/cover changes. The task of image registration can be divided into two major components: (1) the extraction of control points or features from images; and (2) the search among the extracted features for the matching pairs that represent the same feature in the images to be matched. Manual control feature extraction can be subjective and extremely time consuming, and often results in few usable points. Automated feature extraction is a solution to this problem, where desired target features are invariant, and represent evenly distributed landmarks such as edges, corners and line intersections. In this paper, we develop a novel automated registration approach based on the following steps. First, a mathematical morphology (MM)-based method is used to obtain a scale-orientation morphological profile at each image pixel. Next, a spectral dissimilarity metric such as the spectral information divergence is applied for automated extraction of landmark chips, followed by an initial approximate matching. This initial condition is then refined using a hierarchical robust feature matching (RFM) procedure. Experimental results reveal that the proposed registration technique offers a robust solution in the presence of seasonal changes and other interfering factors. Keywords-Automated image registration, multi-temporal imagery, mathematical morphology, robust feature matching.

Enhancing facial features by using clear facial features

NASA Astrophysics Data System (ADS)

Rofoo, Fanar Fareed Hanna

2017-09-01

The similarity of features between individuals of same ethnicity motivated the idea of this project. The idea of this project is to extract features of clear facial image and impose them on blurred facial image of same ethnic origin as an approach to enhance a blurred facial image. A database of clear images containing 30 individuals equally divided to five different ethnicities which were Arab, African, Chines, European and Indian. Software was built to perform pre-processing on images in order to align the features of clear and blurred images. And the idea was to extract features of clear facial image or template built from clear facial images using wavelet transformation to impose them on blurred image by using reverse wavelet. The results of this approach did not come well as all the features did not align together as in most cases the eyes were aligned but the nose or mouth were not aligned. Then we decided in the next approach to deal with features separately but in the result in some cases a blocky effect was present on features due to not having close matching features. In general the available small database did not help to achieve the goal results, because of the number of available individuals. The color information and features similarity could be more investigated to achieve better results by having larger database as well as improving the process of enhancement by the availability of closer matches in each ethnicity.

MindDigger: Feature Identification and Opinion Association for Chinese Movie Reviews

NASA Astrophysics Data System (ADS)

Zhao, Lili; Li, Chunping

In this paper, we present a prototype system called MindDigger, which can be used to analyze the opinions in Chinese movie reviews. Different from previous research that employed techniques on product reviews, we focus on Chinese movie reviews, in which opinions are expressed in subtle and varied ways. The system designed in this work aims to extract the opinion expressions and assign them to the corresponding features. The core tasks include feature and opinion extraction, and feature-opinion association. To deal with Chinese effectively, several novel approaches based on syntactic analysis are proposed in this paper. Running results show the performance is satisfactory.

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.

Thermal feature extraction of servers in a datacenter using thermal image registration

NASA Astrophysics Data System (ADS)

Liu, Hang; Ran, Jian; Xie, Ting; Gao, Shan

2017-09-01

Thermal cameras provide fine-grained thermal information that enhances monitoring and enables automatic thermal management in large datacenters. Recent approaches employing mobile robots or thermal camera networks can already identify the physical locations of hot spots. Other distribution information used to optimize datacenter management can also be obtained automatically using pattern recognition technology. However, most of the features extracted from thermal images, such as shape and gradient, may be affected by changes in the position and direction of the thermal camera. This paper presents a method for extracting the thermal features of a hot spot or a server in a container datacenter. First, thermal and visual images are registered based on textural characteristics extracted from images acquired in datacenters. Then, the thermal distribution of each server is standardized. The features of a hot spot or server extracted from the standard distribution can reduce the impact of camera position and direction. The results of experiments show that image registration is efficient for aligning the corresponding visual and thermal images in the datacenter, and the standardization procedure reduces the impacts of camera position and direction on hot spot or server features.

Extracting BI-RADS Features from Portuguese Clinical Texts.

PubMed

Nassif, Houssam; Cunha, Filipe; Moreira, Inês C; Cruz-Correia, Ricardo; Sousa, Eliana; Page, David; Burnside, Elizabeth; Dutra, Inês

2012-01-01

In this work we build the first BI-RADS parser for Portuguese free texts, modeled after existing approaches to extract BI-RADS features from English medical records. Our concept finder uses a semantic grammar based on the BIRADS lexicon and on iterative transferred expert knowledge. We compare the performance of our algorithm to manual annotation by a specialist in mammography. Our results show that our parser's performance is comparable to the manual method.

Thermal imaging as a biometrics approach to facial signature authentication.

PubMed

Guzman, A M; Goryawala, M; Wang, Jin; Barreto, A; Andrian, J; Rishe, N; Adjouadi, M

2013-01-01

A new thermal imaging framework with unique feature extraction and similarity measurements for face recognition is presented. The research premise is to design specialized algorithms that would extract vasculature information, create a thermal facial signature and identify the individual. The proposed algorithm is fully integrated and consolidates the critical steps of feature extraction through the use of morphological operators, registration using the Linear Image Registration Tool and matching through unique similarity measures designed for this task. The novel approach at developing a thermal signature template using four images taken at various instants of time ensured that unforeseen changes in the vasculature over time did not affect the biometric matching process as the authentication process relied only on consistent thermal features. Thirteen subjects were used for testing the developed technique on an in-house thermal imaging system. The matching using the similarity measures showed an average accuracy of 88.46% for skeletonized signatures and 90.39% for anisotropically diffused signatures. The highly accurate results obtained in the matching process clearly demonstrate the ability of the thermal infrared system to extend in application to other thermal imaging based systems. Empirical results applying this approach to an existing database of thermal images proves this assertion.

Feature-constrained surface reconstruction approach for point cloud data acquired with 3D laser scanner

NASA Astrophysics Data System (ADS)

Wang, Yongbo; Sheng, Yehua; Lu, Guonian; Tian, Peng; Zhang, Kai

2008-04-01

Surface reconstruction is an important task in the field of 3d-GIS, computer aided design and computer graphics (CAD & CG), virtual simulation and so on. Based on available incremental surface reconstruction methods, a feature-constrained surface reconstruction approach for point cloud is presented. Firstly features are extracted from point cloud under the rules of curvature extremes and minimum spanning tree. By projecting local sample points to the fitted tangent planes and using extracted features to guide and constrain the process of local triangulation and surface propagation, topological relationship among sample points can be achieved. For the constructed models, a process named consistent normal adjustment and regularization is adopted to adjust normal of each face so that the correct surface model is achieved. Experiments show that the presented approach inherits the convenient implementation and high efficiency of traditional incremental surface reconstruction method, meanwhile, it avoids improper propagation of normal across sharp edges, which means the applicability of incremental surface reconstruction is greatly improved. Above all, appropriate k-neighborhood can help to recognize un-sufficient sampled areas and boundary parts, the presented approach can be used to reconstruct both open and close surfaces without additional interference.

Shape Adaptive, Robust Iris Feature Extraction from Noisy Iris Images

PubMed Central

Ghodrati, Hamed; Dehghani, Mohammad Javad; Danyali, Habibolah

2013-01-01

In the current iris recognition systems, noise removing step is only used to detect noisy parts of the iris region and features extracted from there will be excluded in matching step. Whereas depending on the filter structure used in feature extraction, the noisy parts may influence relevant features. To the best of our knowledge, the effect of noise factors on feature extraction has not been considered in the previous works. This paper investigates the effect of shape adaptive wavelet transform and shape adaptive Gabor-wavelet for feature extraction on the iris recognition performance. In addition, an effective noise-removing approach is proposed in this paper. The contribution is to detect eyelashes and reflections by calculating appropriate thresholds by a procedure called statistical decision making. The eyelids are segmented by parabolic Hough transform in normalized iris image to decrease computational burden through omitting rotation term. The iris is localized by an accurate and fast algorithm based on coarse-to-fine strategy. The principle of mask code generation is to assign the noisy bits in an iris code in order to exclude them in matching step is presented in details. An experimental result shows that by using the shape adaptive Gabor-wavelet technique there is an improvement on the accuracy of recognition rate. PMID:24696801

Shape adaptive, robust iris feature extraction from noisy iris images.

PubMed

Ghodrati, Hamed; Dehghani, Mohammad Javad; Danyali, Habibolah

2013-10-01

In the current iris recognition systems, noise removing step is only used to detect noisy parts of the iris region and features extracted from there will be excluded in matching step. Whereas depending on the filter structure used in feature extraction, the noisy parts may influence relevant features. To the best of our knowledge, the effect of noise factors on feature extraction has not been considered in the previous works. This paper investigates the effect of shape adaptive wavelet transform and shape adaptive Gabor-wavelet for feature extraction on the iris recognition performance. In addition, an effective noise-removing approach is proposed in this paper. The contribution is to detect eyelashes and reflections by calculating appropriate thresholds by a procedure called statistical decision making. The eyelids are segmented by parabolic Hough transform in normalized iris image to decrease computational burden through omitting rotation term. The iris is localized by an accurate and fast algorithm based on coarse-to-fine strategy. The principle of mask code generation is to assign the noisy bits in an iris code in order to exclude them in matching step is presented in details. An experimental result shows that by using the shape adaptive Gabor-wavelet technique there is an improvement on the accuracy of recognition rate.

Comparison of ANN and SVM for classification of eye movements in EOG signals

NASA Astrophysics Data System (ADS)

Qi, Lim Jia; Alias, Norma

2018-03-01

Nowadays, electrooculogram is regarded as one of the most important biomedical signal in measuring and analyzing eye movement patterns. Thus, it is helpful in designing EOG-based Human Computer Interface (HCI). In this research, electrooculography (EOG) data was obtained from five volunteers. The (EOG) data was then preprocessed before feature extraction methods were employed to further reduce the dimensionality of data. Three feature extraction approaches were put forward, namely statistical parameters, autoregressive (AR) coefficients using Burg method, and power spectral density (PSD) using Yule-Walker method. These features would then become input to both artificial neural network (ANN) and support vector machine (SVM). The performance of the combination of different feature extraction methods and classifiers was presented and analyzed. It was found that statistical parameters + SVM achieved the highest classification accuracy of 69.75%.

A semi-supervised Support Vector Machine model for predicting the language outcomes following cochlear implantation based on pre-implant brain fMRI imaging.

PubMed

Tan, Lirong; Holland, Scott K; Deshpande, Aniruddha K; Chen, Ye; Choo, Daniel I; Lu, Long J

2015-12-01

We developed a machine learning model to predict whether or not a cochlear implant (CI) candidate will develop effective language skills within 2 years after the CI surgery by using the pre-implant brain fMRI data from the candidate. The language performance was measured 2 years after the CI surgery by the Clinical Evaluation of Language Fundamentals-Preschool, Second Edition (CELF-P2). Based on the CELF-P2 scores, the CI recipients were designated as either effective or ineffective CI users. For feature extraction from the fMRI data, we constructed contrast maps using the general linear model, and then utilized the Bag-of-Words (BoW) approach that we previously published to convert the contrast maps into feature vectors. We trained both supervised models and semi-supervised models to classify CI users as effective or ineffective. Compared with the conventional feature extraction approach, which used each single voxel as a feature, our BoW approach gave rise to much better performance for the classification of effective versus ineffective CI users. The semi-supervised model with the feature set extracted by the BoW approach from the contrast of speech versus silence achieved a leave-one-out cross-validation AUC as high as 0.97. Recursive feature elimination unexpectedly revealed that two features were sufficient to provide highly accurate classification of effective versus ineffective CI users based on our current dataset. We have validated the hypothesis that pre-implant cortical activation patterns revealed by fMRI during infancy correlate with language performance 2 years after cochlear implantation. The two brain regions highlighted by our classifier are potential biomarkers for the prediction of CI outcomes. Our study also demonstrated the superiority of the semi-supervised model over the supervised model. It is always worthwhile to try a semi-supervised model when unlabeled data are available.

Low-Rank Linear Dynamical Systems for Motor Imagery EEG.

PubMed

Zhang, Wenchang; Sun, Fuchun; Tan, Chuanqi; Liu, Shaobo

2016-01-01

The common spatial pattern (CSP) and other spatiospectral feature extraction methods have become the most effective and successful approaches to solve the problem of motor imagery electroencephalography (MI-EEG) pattern recognition from multichannel neural activity in recent years. However, these methods need a lot of preprocessing and postprocessing such as filtering, demean, and spatiospectral feature fusion, which influence the classification accuracy easily. In this paper, we utilize linear dynamical systems (LDSs) for EEG signals feature extraction and classification. LDSs model has lots of advantages such as simultaneous spatial and temporal feature matrix generation, free of preprocessing or postprocessing, and low cost. Furthermore, a low-rank matrix decomposition approach is introduced to get rid of noise and resting state component in order to improve the robustness of the system. Then, we propose a low-rank LDSs algorithm to decompose feature subspace of LDSs on finite Grassmannian and obtain a better performance. Extensive experiments are carried out on public dataset from "BCI Competition III Dataset IVa" and "BCI Competition IV Database 2a." The results show that our proposed three methods yield higher accuracies compared with prevailing approaches such as CSP and CSSP.

Appearance and characterization of fruit image textures for quality sorting using wavelet transform and genetic algorithms.

PubMed

Khoje, Suchitra

2018-02-01

Images of four qualities of mangoes and guavas are evaluated for color and textural features to characterize and classify them, and to model the fruit appearance grading. The paper discusses three approaches to identify most discriminating texture features of both the fruits. In the first approach, fruit's color and texture features are selected using Mahalanobis distance. A total of 20 color features and 40 textural features are extracted for analysis. Using Mahalanobis distance and feature intercorrelation analyses, one best color feature (mean of a* [L*a*b* color space]) and two textural features (energy a*, contrast of H*) are selected as features for Guava while two best color features (R std, H std) and one textural features (energy b*) are selected as features for mangoes with the highest discriminate power. The second approach studies some common wavelet families for searching the best classification model for fruit quality grading. The wavelet features extracted from five basic mother wavelets (db, bior, rbior, Coif, Sym) are explored to characterize fruits texture appearance. In third approach, genetic algorithm is used to select only those color and wavelet texture features that are relevant to the separation of the class, from a large universe of features. The study shows that image color and texture features which were identified using a genetic algorithm can distinguish between various qualities classes of fruits. The experimental results showed that support vector machine classifier is elected for Guava grading with an accuracy of 97.61% and artificial neural network is elected from Mango grading with an accuracy of 95.65%. The proposed method is nondestructive fruit quality assessment method. The experimental results has proven that Genetic algorithm along with wavelet textures feature has potential to discriminate fruit quality. Finally, it can be concluded that discussed method is an accurate, reliable, and objective tool to determine fruit quality namely Mango and Guava, and might be applicable to in-line sorting systems. © 2017 Wiley Periodicals, Inc.

Feature extraction using first and second derivative extrema (FSDE) for real-time and hardware-efficient spike sorting.

PubMed

Paraskevopoulou, Sivylla E; Barsakcioglu, Deren Y; Saberi, Mohammed R; Eftekhar, Amir; Constandinou, Timothy G

2013-04-30

Next generation neural interfaces aspire to achieve real-time multi-channel systems by integrating spike sorting on chip to overcome limitations in communication channel capacity. The feasibility of this approach relies on developing highly efficient algorithms for feature extraction and clustering with the potential of low-power hardware implementation. We are proposing a feature extraction method, not requiring any calibration, based on first and second derivative features of the spike waveform. The accuracy and computational complexity of the proposed method are quantified and compared against commonly used feature extraction methods, through simulation across four datasets (with different single units) at multiple noise levels (ranging from 5 to 20% of the signal amplitude). The average classification error is shown to be below 7% with a computational complexity of 2N-3, where N is the number of sample points of each spike. Overall, this method presents a good trade-off between accuracy and computational complexity and is thus particularly well-suited for hardware-efficient implementation. Copyright © 2013 Elsevier B.V. All rights reserved.

A new approach to untargeted integration of high resolution liquid chromatography-mass spectrometry data.

PubMed

van der Kloet, Frans M; Hendriks, Margriet; Hankemeier, Thomas; Reijmers, Theo

2013-11-01

Because of its high sensitivity and specificity, hyphenated mass spectrometry has become the predominant method to detect and quantify metabolites present in bio-samples relevant for all sorts of life science studies being executed. In contrast to targeted methods that are dedicated to specific features, global profiling acquisition methods allow new unspecific metabolites to be analyzed. The challenge with these so-called untargeted methods is the proper and automated extraction and integration of features that could be of relevance. We propose a new algorithm that enables untargeted integration of samples that are measured with high resolution liquid chromatography-mass spectrometry (LC-MS). In contrast to other approaches limited user interaction is needed allowing also less experienced users to integrate their data. The large amount of single features that are found within a sample is combined to a smaller list of, compound-related, grouped feature-sets representative for that sample. These feature-sets allow for easier interpretation and identification and as important, easier matching over samples. We show that the automatic obtained integration results for a set of known target metabolites match those generated with vendor software but that at least 10 times more feature-sets are extracted as well. We demonstrate our approach using high resolution LC-MS data acquired for 128 samples on a lipidomics platform. The data was also processed in a targeted manner (with a combination of automatic and manual integration) using vendor software for a set of 174 targets. As our untargeted extraction procedure is run per sample and per mass trace the implementation of it is scalable. Because of the generic approach, we envision that this data extraction lipids method will be used in a targeted as well as untargeted analysis of many different kinds of TOF-MS data, even CE- and GC-MS data or MRM. The Matlab package is available for download on request and efforts are directed toward a user-friendly Windows executable. Copyright © 2013 Elsevier B.V. All rights reserved.

Automatic Authorship Detection Using Textual Patterns Extracted from Integrated Syntactic Graphs

PubMed Central

Gómez-Adorno, Helena; Sidorov, Grigori; Pinto, David; Vilariño, Darnes; Gelbukh, Alexander

2016-01-01

We apply the integrated syntactic graph feature extraction methodology to the task of automatic authorship detection. This graph-based representation allows integrating different levels of language description into a single structure. We extract textual patterns based on features obtained from shortest path walks over integrated syntactic graphs and apply them to determine the authors of documents. On average, our method outperforms the state of the art approaches and gives consistently high results across different corpora, unlike existing methods. Our results show that our textual patterns are useful for the task of authorship attribution. PMID:27589740

Rule-guided human classification of Volunteered Geographic Information

NASA Astrophysics Data System (ADS)

Ali, Ahmed Loai; Falomir, Zoe; Schmid, Falko; Freksa, Christian

2017-05-01

During the last decade, web technologies and location sensing devices have evolved generating a form of crowdsourcing known as Volunteered Geographic Information (VGI). VGI acted as a platform of spatial data collection, in particular, when a group of public participants are involved in collaborative mapping activities: they work together to collect, share, and use information about geographic features. VGI exploits participants' local knowledge to produce rich data sources. However, the resulting data inherits problematic data classification. In VGI projects, the challenges of data classification are due to the following: (i) data is likely prone to subjective classification, (ii) remote contributions and flexible contribution mechanisms in most projects, and (iii) the uncertainty of spatial data and non-strict definitions of geographic features. These factors lead to various forms of problematic classification: inconsistent, incomplete, and imprecise data classification. This research addresses classification appropriateness. Whether the classification of an entity is appropriate or inappropriate is related to quantitative and/or qualitative observations. Small differences between observations may be not recognizable particularly for non-expert participants. Hence, in this paper, the problem is tackled by developing a rule-guided classification approach. This approach exploits data mining techniques of Association Classification (AC) to extract descriptive (qualitative) rules of specific geographic features. The rules are extracted based on the investigation of qualitative topological relations between target features and their context. Afterwards, the extracted rules are used to develop a recommendation system able to guide participants to the most appropriate classification. The approach proposes two scenarios to guide participants towards enhancing the quality of data classification. An empirical study is conducted to investigate the classification of grass-related features like forest, garden, park, and meadow. The findings of this study indicate the feasibility of the proposed approach.

Automatic detection of wheezes by evaluation of multiple acoustic feature extraction methods and C-weighted SVM

NASA Astrophysics Data System (ADS)

Sosa, Germán. D.; Cruz-Roa, Angel; González, Fabio A.

2015-01-01

This work addresses the problem of lung sound classification, in particular, the problem of distinguishing between wheeze and normal sounds. Wheezing sound detection is an important step to associate lung sounds with an abnormal state of the respiratory system, usually associated with tuberculosis or another chronic obstructive pulmonary diseases (COPD). The paper presents an approach for automatic lung sound classification, which uses different state-of-the-art sound features in combination with a C-weighted support vector machine (SVM) classifier that works better for unbalanced data. Feature extraction methods used here are commonly applied in speech recognition and related problems thanks to the fact that they capture the most informative spectral content from the original signals. The evaluated methods were: Fourier transform (FT), wavelet decomposition using Wavelet Packet Transform bank of filters (WPT) and Mel Frequency Cepstral Coefficients (MFCC). For comparison, we evaluated and contrasted the proposed approach against previous works using different combination of features and/or classifiers. The different methods were evaluated on a set of lung sounds including normal and wheezing sounds. A leave-two-out per-case cross-validation approach was used, which, in each fold, chooses as validation set a couple of cases, one including normal sounds and the other including wheezing sounds. Experimental results were reported in terms of traditional classification performance measures: sensitivity, specificity and balanced accuracy. Our best results using the suggested approach, C-weighted SVM and MFCC, achieve a 82.1% of balanced accuracy obtaining the best result for this problem until now. These results suggest that supervised classifiers based on kernel methods are able to learn better models for this challenging classification problem even using the same feature extraction methods.

Detecting epileptic seizure with different feature extracting strategies using robust machine learning classification techniques by applying advance parameter optimization approach.

PubMed

Hussain, Lal

2018-06-01

Epilepsy is a neurological disorder produced due to abnormal excitability of neurons in the brain. The research reveals that brain activity is monitored through electroencephalogram (EEG) of patients suffered from seizure to detect the epileptic seizure. The performance of EEG detection based epilepsy require feature extracting strategies. In this research, we have extracted varying features extracting strategies based on time and frequency domain characteristics, nonlinear, wavelet based entropy and few statistical features. A deeper study was undertaken using novel machine learning classifiers by considering multiple factors. The support vector machine kernels are evaluated based on multiclass kernel and box constraint level. Likewise, for K-nearest neighbors (KNN), we computed the different distance metrics, Neighbor weights and Neighbors. Similarly, the decision trees we tuned the paramours based on maximum splits and split criteria and ensemble classifiers are evaluated based on different ensemble methods and learning rate. For training/testing tenfold Cross validation was employed and performance was evaluated in form of TPR, NPR, PPV, accuracy and AUC. In this research, a deeper analysis approach was performed using diverse features extracting strategies using robust machine learning classifiers with more advanced optimal options. Support Vector Machine linear kernel and KNN with City block distance metric give the overall highest accuracy of 99.5% which was higher than using the default parameters for these classifiers. Moreover, highest separation (AUC = 0.9991, 0.9990) were obtained at different kernel scales using SVM. Additionally, the K-nearest neighbors with inverse squared distance weight give higher performance at different Neighbors. Moreover, to distinguish the postictal heart rate oscillations from epileptic ictal subjects, and highest performance of 100% was obtained using different machine learning classifiers.

Extracting BI-RADS Features from Portuguese Clinical Texts

PubMed Central

Nassif, Houssam; Cunha, Filipe; Moreira, Inês C.; Cruz-Correia, Ricardo; Sousa, Eliana; Page, David; Burnside, Elizabeth; Dutra, Inês

2013-01-01

In this work we build the first BI-RADS parser for Portuguese free texts, modeled after existing approaches to extract BI-RADS features from English medical records. Our concept finder uses a semantic grammar based on the BIRADS lexicon and on iterative transferred expert knowledge. We compare the performance of our algorithm to manual annotation by a specialist in mammography. Our results show that our parser’s performance is comparable to the manual method. PMID:23797461

Discriminative spatial-frequency-temporal feature extraction and classification of motor imagery EEG: An sparse regression and Weighted Naïve Bayesian Classifier-based approach.

PubMed

Miao, Minmin; Zeng, Hong; Wang, Aimin; Zhao, Changsen; Liu, Feixiang

2017-02-15

Common spatial pattern (CSP) is most widely used in motor imagery based brain-computer interface (BCI) systems. In conventional CSP algorithm, pairs of the eigenvectors corresponding to both extreme eigenvalues are selected to construct the optimal spatial filter. In addition, an appropriate selection of subject-specific time segments and frequency bands plays an important role in its successful application. This study proposes to optimize spatial-frequency-temporal patterns for discriminative feature extraction. Spatial optimization is implemented by channel selection and finding discriminative spatial filters adaptively on each time-frequency segment. A novel Discernibility of Feature Sets (DFS) criteria is designed for spatial filter optimization. Besides, discriminative features located in multiple time-frequency segments are selected automatically by the proposed sparse time-frequency segment common spatial pattern (STFSCSP) method which exploits sparse regression for significant features selection. Finally, a weight determined by the sparse coefficient is assigned for each selected CSP feature and we propose a Weighted Naïve Bayesian Classifier (WNBC) for classification. Experimental results on two public EEG datasets demonstrate that optimizing spatial-frequency-temporal patterns in a data-driven manner for discriminative feature extraction greatly improves the classification performance. The proposed method gives significantly better classification accuracies in comparison with several competing methods in the literature. The proposed approach is a promising candidate for future BCI systems. Copyright © 2016 Elsevier B.V. All rights reserved.

Robust Sensing of Approaching Vehicles Relying on Acoustic Cues

PubMed Central

Mizumachi, Mitsunori; Kaminuma, Atsunobu; Ono, Nobutaka; Ando, Shigeru

2014-01-01

The latest developments in automobile design have allowed them to be equipped with various sensing devices. Multiple sensors such as cameras and radar systems can be simultaneously used for active safety systems in order to overcome blind spots of individual sensors. This paper proposes a novel sensing technique for catching up and tracking an approaching vehicle relying on an acoustic cue. First, it is necessary to extract a robust spatial feature from noisy acoustical observations. In this paper, the spatio-temporal gradient method is employed for the feature extraction. Then, the spatial feature is filtered out through sequential state estimation. A particle filter is employed to cope with a highly non-linear problem. Feasibility of the proposed method has been confirmed with real acoustical observations, which are obtained by microphones outside a cruising vehicle. PMID:24887038

Object-oriented feature extraction approach for mapping supraglacial debris in Schirmacher Oasis using very high-resolution satellite data

NASA Astrophysics Data System (ADS)

Jawak, Shridhar D.; Jadhav, Ajay; Luis, Alvarinho J.

2016-05-01

Supraglacial debris was mapped in the Schirmacher Oasis, east Antarctica, by using WorldView-2 (WV-2) high resolution optical remote sensing data consisting of 8-band calibrated Gram Schmidt (GS)-sharpened and atmospherically corrected WV-2 imagery. This study is a preliminary attempt to develop an object-oriented rule set to extract supraglacial debris for Antarctic region using 8-spectral band imagery. Supraglacial debris was manually digitized from the satellite imagery to generate the ground reference data. Several trials were performed using few existing traditional pixel-based classification techniques and color-texture based object-oriented classification methods to extract supraglacial debris over a small domain of the study area. Multi-level segmentation and attributes such as scale, shape, size, compactness along with spectral information from the data were used for developing the rule set. The quantitative analysis of error was carried out against the manually digitized reference data to test the practicability of our approach over the traditional pixel-based methods. Our results indicate that OBIA-based approach (overall accuracy: 93%) for extracting supraglacial debris performed better than all the traditional pixel-based methods (overall accuracy: 80-85%). The present attempt provides a comprehensive improved method for semiautomatic feature extraction in supraglacial environment and a new direction in the cryospheric research.

Extraction of sandy bedforms features through geodesic morphometry

NASA Astrophysics Data System (ADS)

Debese, Nathalie; Jacq, Jean-José; Garlan, Thierry

2016-09-01

State-of-art echosounders reveal fine-scale details of mobile sandy bedforms, which are commonly found on continental shelfs. At present, their dynamics are still far from being completely understood. These bedforms are a serious threat to navigation security, anthropic structures and activities, placing emphasis on research breakthroughs. Bedform geometries and their dynamics are closely linked; therefore, one approach is to develop semi-automatic tools aiming at extracting their structural features from bathymetric datasets. Current approaches mimic manual processes or rely on morphological simplification of bedforms. The 1D and 2D approaches cannot address the wide ranges of both types and complexities of bedforms. In contrast, this work attempts to follow a 3D global semi-automatic approach based on a bathymetric TIN. The currently extracted primitives are the salient ridge and valley lines of the sand structures, i.e., waves and mega-ripples. The main difficulty is eliminating the ripples that are found to heavily overprint any observations. To this end, an anisotropic filter that is able to discard these structures while still enhancing the wave ridges is proposed. The second part of the work addresses the semi-automatic interactive extraction and 3D augmented display of the main lines structures. The proposed protocol also allows geoscientists to interactively insert topological constraints.

Optimizing Radiometric Processing and Feature Extraction of Drone Based Hyperspectral Frame Format Imagery for Estimation of Yield Quantity and Quality of a Grass Sward

NASA Astrophysics Data System (ADS)

Näsi, R.; Viljanen, N.; Oliveira, R.; Kaivosoja, J.; Niemeläinen, O.; Hakala, T.; Markelin, L.; Nezami, S.; Suomalainen, J.; Honkavaara, E.

2018-04-01

Light-weight 2D format hyperspectral imagers operable from unmanned aerial vehicles (UAV) have become common in various remote sensing tasks in recent years. Using these technologies, the area of interest is covered by multiple overlapping hypercubes, in other words multiview hyperspectral photogrammetric imagery, and each object point appears in many, even tens of individual hypercubes. The common practice is to calculate hyperspectral orthomosaics utilizing only the most nadir areas of the images. However, the redundancy of the data gives potential for much more versatile and thorough feature extraction. We investigated various options of extracting spectral features in the grass sward quantity evaluation task. In addition to the various sets of spectral features, we used photogrammetry-based ultra-high density point clouds to extract features describing the canopy 3D structure. Machine learning technique based on the Random Forest algorithm was used to estimate the fresh biomass. Results showed high accuracies for all investigated features sets. The estimation results using multiview data provided approximately 10 % better results than the most nadir orthophotos. The utilization of the photogrammetric 3D features improved estimation accuracy by approximately 40 % compared to approaches where only spectral features were applied. The best estimation RMSE of 239 kg/ha (6.0 %) was obtained with multiview anisotropy corrected data set and the 3D features.

A concept for extraction of habitat features from laser scanning and hypersprectral imaging for evaluation of Natura 2000 sites - the ChangeHabitats2 project approach

NASA Astrophysics Data System (ADS)

Székely, B.; Kania, A.; Pfeifer, N.; Heilmeier, H.; Tamás, J.; Szöllősi, N.; Mücke, W.

2012-04-01

The goal of the ChangeHabitats2 project is the development of cost- and time-efficient habitat assessment strategies by employing effective field work techniques supported by modern airborne remote sensing methods, i.e. hyperspectral imagery and laser scanning (LiDAR). An essential task of the project is the design of a novel field work technique that on the one hand fulfills the reporting requirements of the Flora-Fauna-Habitat (FFH-) directive and on the other hand serves as a reference for the aerial data analysis. Correlations between parameters derived from remotely sensed data and terrestrial field measurements shall be exploited in order to create half- or fully-automated methods for the extraction of relevant Natura2000 habitat parameters. As a result of these efforts a comprehensive conceptual model has been developed for extraction and integration of Natura 2000 relevant geospatial data. This scheme is an attempt to integrate various activities within ChangeHabitats2 project defining pathways of development, as well as encompassing existing data processing chains, theoretical approaches and field work. The conceptual model includes definition of processing levels (similar to those existing in remote sensing), whereas these levels cover the range from the raw data to the extracted habitat feature. For instance, the amount of dead wood (standing or lying on the surface) is an important evaluation criterion for the habitat. The tree trunks lying on the ground surface typically can be extracted from the LiDAR point cloud, and the amount of wood can be estimated accordingly. The final result will be considered as a habitat feature derived from laser scanning data. Furthermore, we are also interested not only in the determination of the specific habitat feature, but also in the detection of its variations (especially in deterioration). In this approach the variation of this important habitat feature is considered to be a differential habitat feature, that can be immediately used in the evaluation of the Natura 2000 sites. The goal of the project is the identification of many potential habitat features that can be extracted or implied from remotely sensed data, and the development of processing chains to provide data that can be used in the everyday field work of ecological site assessment. This is a contribution of ChangeHabitats2 project financed by the European Union within the Industry Academia Partnership Pathways (IAPP), as a part of FP7 Marie Curie Actions.

Automated Extraction of Secondary Flow Features

NASA Technical Reports Server (NTRS)

Dorney, Suzanne M.; Haimes, Robert

2005-01-01

The use of Computational Fluid Dynamics (CFD) has become standard practice in the design and development of the major components used for air and space propulsion. To aid in the post-processing and analysis phase of CFD many researchers now use automated feature extraction utilities. These tools can be used to detect the existence of such features as shocks, vortex cores and separation and re-attachment lines. The existence of secondary flow is another feature of significant importance to CFD engineers. Although the concept of secondary flow is relatively understood there is no commonly accepted mathematical definition for secondary flow. This paper will present a definition for secondary flow and one approach for automatically detecting and visualizing secondary flow.

Real-Time Detection and Measurement of Eye Features from Color Images

PubMed Central

Borza, Diana; Darabant, Adrian Sergiu; Danescu, Radu

2016-01-01

The accurate extraction and measurement of eye features is crucial to a variety of domains, including human-computer interaction, biometry, and medical research. This paper presents a fast and accurate method for extracting multiple features around the eyes: the center of the pupil, the iris radius, and the external shape of the eye. These features are extracted using a multistage algorithm. On the first stage the pupil center is localized using a fast circular symmetry detector and the iris radius is computed using radial gradient projections, and on the second stage the external shape of the eye (of the eyelids) is determined through a Monte Carlo sampling framework based on both color and shape information. Extensive experiments performed on a different dataset demonstrate the effectiveness of our approach. In addition, this work provides eye annotation data for a publicly-available database. PMID:27438838

Identifying seizure onset zone from electrocorticographic recordings: A machine learning approach based on phase locking value.

PubMed

Elahian, Bahareh; Yeasin, Mohammed; Mudigoudar, Basanagoud; Wheless, James W; Babajani-Feremi, Abbas

2017-10-01

Using a novel technique based on phase locking value (PLV), we investigated the potential for features extracted from electrocorticographic (ECoG) recordings to serve as biomarkers to identify the seizure onset zone (SOZ). We computed the PLV between the phase of the amplitude of high gamma activity (80-150Hz) and the phase of lower frequency rhythms (4-30Hz) from ECoG recordings obtained from 10 patients with epilepsy (21 seizures). We extracted five features from the PLV and used a machine learning approach based on logistic regression to build a model that classifies electrodes as SOZ or non-SOZ. More than 96% of electrodes identified as the SOZ by our algorithm were within the resected area in six seizure-free patients. In four non-seizure-free patients, more than 31% of the identified SOZ electrodes by our algorithm were outside the resected area. In addition, we observed that the seizure outcome in non-seizure-free patients correlated with the number of non-resected SOZ electrodes identified by our algorithm. This machine learning approach, based on features extracted from the PLV, effectively identified electrodes within the SOZ. The approach has the potential to assist clinicians in surgical decision-making when pre-surgical intracranial recordings are utilized. Copyright © 2017 British Epilepsy Association. Published by Elsevier Ltd. All rights reserved.

Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors.

PubMed

Li, Frédéric; Shirahama, Kimiaki; Nisar, Muhammad Adeel; Köping, Lukas; Grzegorzek, Marcin

2018-02-24

Getting a good feature representation of data is paramount for Human Activity Recognition (HAR) using wearable sensors. An increasing number of feature learning approaches-in particular deep-learning based-have been proposed to extract an effective feature representation by analyzing large amounts of data. However, getting an objective interpretation of their performances faces two problems: the lack of a baseline evaluation setup, which makes a strict comparison between them impossible, and the insufficiency of implementation details, which can hinder their use. In this paper, we attempt to address both issues: we firstly propose an evaluation framework allowing a rigorous comparison of features extracted by different methods, and use it to carry out extensive experiments with state-of-the-art feature learning approaches. We then provide all the codes and implementation details to make both the reproduction of the results reported in this paper and the re-use of our framework easier for other researchers. Our studies carried out on the OPPORTUNITY and UniMiB-SHAR datasets highlight the effectiveness of hybrid deep-learning architectures involving convolutional and Long-Short-Term-Memory (LSTM) to obtain features characterising both short- and long-term time dependencies in the data.

Mixed monofunctional extractants for trivalent actinide/lanthanide separations: TALSPEAK-MME

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

Johnson, Aaron T.; Nash, Kenneth L.

The basic features of an f-element extraction process based on a solvent composed of equimolar mixtures of Cyanex-923 (a mixed trialkyl phosphine oxide) and 2-ethylhexylphosphonic acid mono-2-ethylhexyl ester (HEH[EHP]) extractants in n-dodecane are investigated in this report. This system, which combines features of the TRPO and TALSPEAK processes, is based on co-extraction of trivalent lanthanides and actinides from 0.1 to 1.0 M HNO 3 followed by application of a buffered aminopolycarboxylate solution strip to accomplish a Reverse TALSPEAK selective removal of actinides. This mixed-extractant medium could enable a simplified approach to selective trivalent f-element extraction and actinide partitioning in amore » single process. As compared with other combined process applications in development for more compact actinide partitioning processes (DIAMEX-SANEX, GANEX, TRUSPEAK, ALSEP), this combination features only monofunctional extractants with high solubility limits and comparatively low molar mass. Selective actinide stripping from the loaded extractant phase is done using a glycine-buffered solution containing N-(2-hydroxyethyl)ethylenediaminetriacetic acid (HEDTA) or triethylenetetramine-N,N,N',N'',N''',N'''-hexaacetic acid (TTHA). Lastly, the results reported provide evidence for simplified interactions between the two extractants and demonstrate a pathway toward using mixed monofunctional extractants to separate trivalent actinides (An) from fission product lanthanides (Ln).« less

Mixed monofunctional extractants for trivalent actinide/lanthanide separations: TALSPEAK-MME

DOE PAGES

Johnson, Aaron T.; Nash, Kenneth L.

2015-08-20

The basic features of an f-element extraction process based on a solvent composed of equimolar mixtures of Cyanex-923 (a mixed trialkyl phosphine oxide) and 2-ethylhexylphosphonic acid mono-2-ethylhexyl ester (HEH[EHP]) extractants in n-dodecane are investigated in this report. This system, which combines features of the TRPO and TALSPEAK processes, is based on co-extraction of trivalent lanthanides and actinides from 0.1 to 1.0 M HNO 3 followed by application of a buffered aminopolycarboxylate solution strip to accomplish a Reverse TALSPEAK selective removal of actinides. This mixed-extractant medium could enable a simplified approach to selective trivalent f-element extraction and actinide partitioning in amore » single process. As compared with other combined process applications in development for more compact actinide partitioning processes (DIAMEX-SANEX, GANEX, TRUSPEAK, ALSEP), this combination features only monofunctional extractants with high solubility limits and comparatively low molar mass. Selective actinide stripping from the loaded extractant phase is done using a glycine-buffered solution containing N-(2-hydroxyethyl)ethylenediaminetriacetic acid (HEDTA) or triethylenetetramine-N,N,N',N'',N''',N'''-hexaacetic acid (TTHA). Lastly, the results reported provide evidence for simplified interactions between the two extractants and demonstrate a pathway toward using mixed monofunctional extractants to separate trivalent actinides (An) from fission product lanthanides (Ln).« less

WHU at TREC KBA Vital Filtering Track 2014

DTIC Science & Technology

2014-11-01

view the problem as a classification problem and use Stanford NLP Toolkit to extract necessary information. Various kinds of features are leveraged to...profile of an entity. Our approach is to view the problem as a classification problem and use Stanford NLP Toolkit to extract necessary information

Enhancing clinical concept extraction with distributional semantics

PubMed Central

Cohen, Trevor; Wu, Stephen; Gonzalez, Graciela

2011-01-01

Extracting concepts (such as drugs, symptoms, and diagnoses) from clinical narratives constitutes a basic enabling technology to unlock the knowledge within and support more advanced reasoning applications such as diagnosis explanation, disease progression modeling, and intelligent analysis of the effectiveness of treatment. The recent release of annotated training sets of de-identified clinical narratives has contributed to the development and refinement of concept extraction methods. However, as the annotation process is labor-intensive, training data are necessarily limited in the concepts and concept patterns covered, which impacts the performance of supervised machine learning applications trained with these data. This paper proposes an approach to minimize this limitation by combining supervised machine learning with empirical learning of semantic relatedness from the distribution of the relevant words in additional unannotated text. The approach uses a sequential discriminative classifier (Conditional Random Fields) to extract the mentions of medical problems, treatments and tests from clinical narratives. It takes advantage of all Medline abstracts indexed as being of the publication type “clinical trials” to estimate the relatedness between words in the i2b2/VA training and testing corpora. In addition to the traditional features such as dictionary matching, pattern matching and part-of-speech tags, we also used as a feature words that appear in similar contexts to the word in question (that is, words that have a similar vector representation measured with the commonly used cosine metric, where vector representations are derived using methods of distributional semantics). To the best of our knowledge, this is the first effort exploring the use of distributional semantics, the semantics derived empirically from unannotated text often using vector space models, for a sequence classification task such as concept extraction. Therefore, we first experimented with different sliding window models and found the model with parameters that led to best performance in a preliminary sequence labeling task. The evaluation of this approach, performed against the i2b2/VA concept extraction corpus, showed that incorporating features based on the distribution of words across a large unannotated corpus significantly aids concept extraction. Compared to a supervised-only approach as a baseline, the micro-averaged f-measure for exact match increased from 80.3% to 82.3% and the micro-averaged f-measure based on inexact match increased from 89.7% to 91.3%. These improvements are highly significant according to the bootstrap resampling method and also considering the performance of other systems. Thus, distributional semantic features significantly improve the performance of concept extraction from clinical narratives by taking advantage of word distribution information obtained from unannotated data. PMID:22085698

Comparison of Object-Based Image Analysis Approaches to Mapping New Buildings in Accra, Ghana Using Multi-Temporal QuickBird Satellite Imagery

PubMed Central

Tsai, Yu Hsin; Stow, Douglas; Weeks, John

2013-01-01

The goal of this study was to map and quantify the number of newly constructed buildings in Accra, Ghana between 2002 and 2010 based on high spatial resolution satellite image data. Two semi-automated feature detection approaches for detecting and mapping newly constructed buildings based on QuickBird very high spatial resolution satellite imagery were analyzed: (1) post-classification comparison; and (2) bi-temporal layerstack classification. Feature Analyst software based on a spatial contextual classifier and ENVI Feature Extraction that uses a true object-based image analysis approach of image segmentation and segment classification were evaluated. Final map products representing new building objects were compared and assessed for accuracy using two object-based accuracy measures, completeness and correctness. The bi-temporal layerstack method generated more accurate results compared to the post-classification comparison method due to less confusion with background objects. The spectral/spatial contextual approach (Feature Analyst) outperformed the true object-based feature delineation approach (ENVI Feature Extraction) due to its ability to more reliably delineate individual buildings of various sizes. Semi-automated, object-based detection followed by manual editing appears to be a reliable and efficient approach for detecting and enumerating new building objects. A bivariate regression analysis was performed using neighborhood-level estimates of new building density regressed on a census-derived measure of socio-economic status, yielding an inverse relationship with R2 = 0.31 (n = 27; p = 0.00). The primary utility of the new building delineation results is to support spatial analyses of land cover and land use and demographic change. PMID:24415810

Radiomics: Extracting more information from medical images using advanced feature analysis

PubMed Central

Lambin, Philippe; Rios-Velazquez, Emmanuel; Leijenaar, Ralph; Carvalho, Sara; van Stiphout, Ruud G.P.M.; Granton, Patrick; Zegers, Catharina M.L.; Gillies, Robert; Boellard, Ronald; Dekker, André; Aerts, Hugo J.W.L.

2015-01-01

Solid cancers are spatially and temporally heterogeneous. This limits the use of invasive biopsy based molecular assays but gives huge potential for medical imaging, which has the ability to capture intra-tumoural heterogeneity in a non-invasive way. During the past decades, medical imaging innovations with new hardware, new imaging agents and standardised protocols, allows the field to move towards quantitative imaging. Therefore, also the development of automated and reproducible analysis methodologies to extract more information from image-based features is a requirement. Radiomics – the high-throughput extraction of large amounts of image features from radiographic images – addresses this problem and is one of the approaches that hold great promises but need further validation in multi-centric settings and in the laboratory. PMID:22257792

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.

Spoken language identification based on the enhanced self-adjusting extreme learning machine approach.

PubMed

Albadr, Musatafa Abbas Abbood; Tiun, Sabrina; Al-Dhief, Fahad Taha; Sammour, Mahmoud A M

2018-01-01

Spoken Language Identification (LID) is the process of determining and classifying natural language from a given content and dataset. Typically, data must be processed to extract useful features to perform LID. The extracting features for LID, based on literature, is a mature process where the standard features for LID have already been developed using Mel-Frequency Cepstral Coefficients (MFCC), Shifted Delta Cepstral (SDC), the Gaussian Mixture Model (GMM) and ending with the i-vector based framework. However, the process of learning based on extract features remains to be improved (i.e. optimised) to capture all embedded knowledge on the extracted features. The Extreme Learning Machine (ELM) is an effective learning model used to perform classification and regression analysis and is extremely useful to train a single hidden layer neural network. Nevertheless, the learning process of this model is not entirely effective (i.e. optimised) due to the random selection of weights within the input hidden layer. In this study, the ELM is selected as a learning model for LID based on standard feature extraction. One of the optimisation approaches of ELM, the Self-Adjusting Extreme Learning Machine (SA-ELM) is selected as the benchmark and improved by altering the selection phase of the optimisation process. The selection process is performed incorporating both the Split-Ratio and K-Tournament methods, the improved SA-ELM is named Enhanced Self-Adjusting Extreme Learning Machine (ESA-ELM). The results are generated based on LID with the datasets created from eight different languages. The results of the study showed excellent superiority relating to the performance of the Enhanced Self-Adjusting Extreme Learning Machine LID (ESA-ELM LID) compared with the SA-ELM LID, with ESA-ELM LID achieving an accuracy of 96.25%, as compared to the accuracy of SA-ELM LID of only 95.00%.

Spoken language identification based on the enhanced self-adjusting extreme learning machine approach

PubMed Central

Tiun, Sabrina; AL-Dhief, Fahad Taha; Sammour, Mahmoud A. M.

2018-01-01

Spoken Language Identification (LID) is the process of determining and classifying natural language from a given content and dataset. Typically, data must be processed to extract useful features to perform LID. The extracting features for LID, based on literature, is a mature process where the standard features for LID have already been developed using Mel-Frequency Cepstral Coefficients (MFCC), Shifted Delta Cepstral (SDC), the Gaussian Mixture Model (GMM) and ending with the i-vector based framework. However, the process of learning based on extract features remains to be improved (i.e. optimised) to capture all embedded knowledge on the extracted features. The Extreme Learning Machine (ELM) is an effective learning model used to perform classification and regression analysis and is extremely useful to train a single hidden layer neural network. Nevertheless, the learning process of this model is not entirely effective (i.e. optimised) due to the random selection of weights within the input hidden layer. In this study, the ELM is selected as a learning model for LID based on standard feature extraction. One of the optimisation approaches of ELM, the Self-Adjusting Extreme Learning Machine (SA-ELM) is selected as the benchmark and improved by altering the selection phase of the optimisation process. The selection process is performed incorporating both the Split-Ratio and K-Tournament methods, the improved SA-ELM is named Enhanced Self-Adjusting Extreme Learning Machine (ESA-ELM). The results are generated based on LID with the datasets created from eight different languages. The results of the study showed excellent superiority relating to the performance of the Enhanced Self-Adjusting Extreme Learning Machine LID (ESA-ELM LID) compared with the SA-ELM LID, with ESA-ELM LID achieving an accuracy of 96.25%, as compared to the accuracy of SA-ELM LID of only 95.00%. PMID:29672546

Robust Point Set Matching for Partial Face Recognition.

PubMed

Weng, Renliang; Lu, Jiwen; Tan, Yap-Peng

2016-03-01

Over the past three decades, a number of face recognition methods have been proposed in computer vision, and most of them use holistic face images for person identification. In many real-world scenarios especially some unconstrained environments, human faces might be occluded by other objects, and it is difficult to obtain fully holistic face images for recognition. To address this, we propose a new partial face recognition approach to recognize persons of interest from their partial faces. Given a pair of gallery image and probe face patch, we first detect keypoints and extract their local textural features. Then, we propose a robust point set matching method to discriminatively match these two extracted local feature sets, where both the textural information and geometrical information of local features are explicitly used for matching simultaneously. Finally, the similarity of two faces is converted as the distance between these two aligned feature sets. Experimental results on four public face data sets show the effectiveness of the proposed approach.

Application of Wavelet Transform for PDZ Domain Classification

PubMed Central

Daqrouq, Khaled; Alhmouz, Rami; Balamesh, Ahmed; Memic, Adnan

2015-01-01

PDZ domains have been identified as part of an array of signaling proteins that are often unrelated, except for the well-conserved structural PDZ domain they contain. These domains have been linked to many disease processes including common Avian influenza, as well as very rare conditions such as Fraser and Usher syndromes. Historically, based on the interactions and the nature of bonds they form, PDZ domains have most often been classified into one of three classes (class I, class II and others - class III), that is directly dependent on their binding partner. In this study, we report on three unique feature extraction approaches based on the bigram and trigram occurrence and existence rearrangements within the domain's primary amino acid sequences in assisting PDZ domain classification. Wavelet packet transform (WPT) and Shannon entropy denoted by wavelet entropy (WE) feature extraction methods were proposed. Using 115 unique human and mouse PDZ domains, the existence rearrangement approach yielded a high recognition rate (78.34%), which outperformed our occurrence rearrangements based method. The recognition rate was (81.41%) with validation technique. The method reported for PDZ domain classification from primary sequences proved to be an encouraging approach for obtaining consistent classification results. We anticipate that by increasing the database size, we can further improve feature extraction and correct classification. PMID:25860375

An intelligent fault diagnosis method of rolling bearings based on regularized kernel Marginal Fisher analysis

NASA Astrophysics Data System (ADS)

Jiang, Li; Shi, Tielin; Xuan, Jianping

2012-05-01

Generally, the vibration signals of fault bearings are non-stationary and highly nonlinear under complicated operating conditions. Thus, it's a big challenge to extract optimal features for improving classification and simultaneously decreasing feature dimension. Kernel Marginal Fisher analysis (KMFA) is a novel supervised manifold learning algorithm for feature extraction and dimensionality reduction. In order to avoid the small sample size problem in KMFA, we propose regularized KMFA (RKMFA). A simple and efficient intelligent fault diagnosis method based on RKMFA is put forward and applied to fault recognition of rolling bearings. So as to directly excavate nonlinear features from the original high-dimensional vibration signals, RKMFA constructs two graphs describing the intra-class compactness and the inter-class separability, by combining traditional manifold learning algorithm with fisher criteria. Therefore, the optimal low-dimensional features are obtained for better classification and finally fed into the simplest K-nearest neighbor (KNN) classifier to recognize different fault categories of bearings. The experimental results demonstrate that the proposed approach improves the fault classification performance and outperforms the other conventional approaches.

Stability of deep features across CT scanners and field of view using a physical phantom

NASA Astrophysics Data System (ADS)

Paul, Rahul; Shafiq-ul-Hassan, Muhammad; Moros, Eduardo G.; Gillies, Robert J.; Hall, Lawrence O.; Goldgof, Dmitry B.

2018-02-01

Radiomics is the process of analyzing radiological images by extracting quantitative features for monitoring and diagnosis of various cancers. Analyzing images acquired from different medical centers is confounded by many choices in acquisition, reconstruction parameters and differences among device manufacturers. Consequently, scanning the same patient or phantom using various acquisition/reconstruction parameters as well as different scanners may result in different feature values. To further evaluate this issue, in this study, CT images from a physical radiomic phantom were used. Recent studies showed that some quantitative features were dependent on voxel size and that this dependency could be reduced or removed by the appropriate normalization factor. Deep features extracted from a convolutional neural network, may also provide additional features for image analysis. Using a transfer learning approach, we obtained deep features from three convolutional neural networks pre-trained on color camera images. An we examination of the dependency of deep features on image pixel size was done. We found that some deep features were pixel size dependent, and to remove this dependency we proposed two effective normalization approaches. For analyzing the effects of normalization, a threshold has been used based on the calculated standard deviation and average distance from a best fit horizontal line among the features' underlying pixel size before and after normalization. The inter and intra scanner dependency of deep features has also been evaluated.

Segmentation, feature extraction, and multiclass brain tumor classification.

PubMed

Sachdeva, Jainy; Kumar, Vinod; Gupta, Indra; Khandelwal, Niranjan; Ahuja, Chirag Kamal

2013-12-01

Multiclass brain tumor classification is performed by using a diversified dataset of 428 post-contrast T1-weighted MR images from 55 patients. These images are of primary brain tumors namely astrocytoma (AS), glioblastoma multiforme (GBM), childhood tumor-medulloblastoma (MED), meningioma (MEN), secondary tumor-metastatic (MET), and normal regions (NR). Eight hundred fifty-six regions of interest (SROIs) are extracted by a content-based active contour model. Two hundred eighteen intensity and texture features are extracted from these SROIs. In this study, principal component analysis (PCA) is used for reduction of dimensionality of the feature space. These six classes are then classified by artificial neural network (ANN). Hence, this approach is named as PCA-ANN approach. Three sets of experiments have been performed. In the first experiment, classification accuracy by ANN approach is performed. In the second experiment, PCA-ANN approach with random sub-sampling has been used in which the SROIs from the same patient may get repeated during testing. It is observed that the classification accuracy has increased from 77 to 91 %. PCA-ANN has delivered high accuracy for each class: AS-90.74 %, GBM-88.46 %, MED-85 %, MEN-90.70 %, MET-96.67 %, and NR-93.78 %. In the third experiment, to remove bias and to test the robustness of the proposed system, data is partitioned in a manner such that the SROIs from the same patient are not common for training and testing sets. In this case also, the proposed system has performed well by delivering an overall accuracy of 85.23 %. The individual class accuracy for each class is: AS-86.15 %, GBM-65.1 %, MED-63.36 %, MEN-91.5 %, MET-65.21 %, and NR-93.3 %. A computer-aided diagnostic system comprising of developed methods for segmentation, feature extraction, and classification of brain tumors can be beneficial to radiologists for precise localization, diagnosis, and interpretation of brain tumors on MR images.

Contextual Classification of Point Cloud Data by Exploiting Individual 3d Neigbourhoods

NASA Astrophysics Data System (ADS)

Weinmann, M.; Schmidt, A.; Mallet, C.; Hinz, S.; Rottensteiner, F.; Jutzi, B.

2015-03-01

The fully automated analysis of 3D point clouds is of great importance in photogrammetry, remote sensing and computer vision. For reliably extracting objects such as buildings, road inventory or vegetation, many approaches rely on the results of a point cloud classification, where each 3D point is assigned a respective semantic class label. Such an assignment, in turn, typically involves statistical methods for feature extraction and machine learning. Whereas the different components in the processing workflow have extensively, but separately been investigated in recent years, the respective connection by sharing the results of crucial tasks across all components has not yet been addressed. This connection not only encapsulates the interrelated issues of neighborhood selection and feature extraction, but also the issue of how to involve spatial context in the classification step. In this paper, we present a novel and generic approach for 3D scene analysis which relies on (i) individually optimized 3D neighborhoods for (ii) the extraction of distinctive geometric features and (iii) the contextual classification of point cloud data. For a labeled benchmark dataset, we demonstrate the beneficial impact of involving contextual information in the classification process and that using individual 3D neighborhoods of optimal size significantly increases the quality of the results for both pointwise and contextual classification.

Identification of chemogenomic features from drug–target interaction networks using interpretable classifiers

PubMed Central

Tabei, Yasuo; Pauwels, Edouard; Stoven, Véronique; Takemoto, Kazuhiro; Yamanishi, Yoshihiro

2012-01-01

Motivation: Drug effects are mainly caused by the interactions between drug molecules and their target proteins including primary targets and off-targets. Identification of the molecular mechanisms behind overall drug–target interactions is crucial in the drug design process. Results: We develop a classifier-based approach to identify chemogenomic features (the underlying associations between drug chemical substructures and protein domains) that are involved in drug–target interaction networks. We propose a novel algorithm for extracting informative chemogenomic features by using L1 regularized classifiers over the tensor product space of possible drug–target pairs. It is shown that the proposed method can extract a very limited number of chemogenomic features without loosing the performance of predicting drug–target interactions and the extracted features are biologically meaningful. The extracted substructure–domain association network enables us to suggest ligand chemical fragments specific for each protein domain and ligand core substructures important for a wide range of protein families. Availability: Softwares are available at the supplemental website. Contact: yamanishi@bioreg.kyushu-u.ac.jp Supplementary Information: Datasets and all results are available at http://cbio.ensmp.fr/~yyamanishi/l1binary/ . PMID:22962471

Emotion recognition based on multiple order features using fractional Fourier transform

NASA Astrophysics Data System (ADS)

Ren, Bo; Liu, Deyin; Qi, Lin

2017-07-01

In order to deal with the insufficiency of recently algorithms based on Two Dimensions Fractional Fourier Transform (2D-FrFT), this paper proposes a multiple order features based method for emotion recognition. Most existing methods utilize the feature of single order or a couple of orders of 2D-FrFT. However, different orders of 2D-FrFT have different contributions on the feature extraction of emotion recognition. Combination of these features can enhance the performance of an emotion recognition system. The proposed approach obtains numerous features that extracted in different orders of 2D-FrFT in the directions of x-axis and y-axis, and uses the statistical magnitudes as the final feature vectors for recognition. The Support Vector Machine (SVM) is utilized for the classification and RML Emotion database and Cohn-Kanade (CK) database are used for the experiment. The experimental results demonstrate the effectiveness of the proposed method.

Cognitive and artificial representations in handwriting recognition

NASA Astrophysics Data System (ADS)

Lenaghan, Andrew P.; Malyan, Ron

1996-03-01

Both cognitive processes and artificial recognition systems may be characterized by the forms of representation they build and manipulate. This paper looks at how handwriting is represented in current recognition systems and the psychological evidence for its representation in the cognitive processes responsible for reading. Empirical psychological work on feature extraction in early visual processing is surveyed to show that a sound psychological basis for feature extraction exists and to describe the features this approach leads to. The first stage of the development of an architecture for a handwriting recognition system which has been strongly influenced by the psychological evidence for the cognitive processes and representations used in early visual processing, is reported. This architecture builds a number of parallel low level feature maps from raw data. These feature maps are thresholded and a region labeling algorithm is used to generate sets of features. Fuzzy logic is used to quantify the uncertainty in the presence of individual features.

Automated feature extraction in color retinal images by a model based approach.

PubMed

Li, Huiqi; Chutatape, Opas

2004-02-01

Color retinal photography is an important tool to detect the evidence of various eye diseases. Novel methods to extract the main features in color retinal images have been developed in this paper. Principal component analysis is employed to locate optic disk; A modified active shape model is proposed in the shape detection of optic disk; A fundus coordinate system is established to provide a better description of the features in the retinal images; An approach to detect exudates by the combined region growing and edge detection is proposed. The success rates of disk localization, disk boundary detection, and fovea localization are 99%, 94%, and 100%, respectively. The sensitivity and specificity of exudate detection are 100% and 71%, correspondingly. The success of the proposed algorithms can be attributed to the utilization of the model-based methods. The detection and analysis could be applied to automatic mass screening and diagnosis of the retinal diseases.

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).

Color features as an approach for the automated screening of Salmonella strain

NASA Astrophysics Data System (ADS)

Trujillo, Alejandra Serrano; González, Viridiana Contreras; Andrade Rincón, Saulo E.; Palafox, Luis E.

2016-11-01

We present the implementation of a feature extraction approach for the automated screening of Salmonella sp., a task visually carried out by a microbiologist, where the resulting color characteristics of the culture media plate indicate the presence of this strain. The screening of Salmonella sp. is based on the inoculation and incubation of a sample on an agar plate, allowing the isolation of this strain, if present. This process uses three media: Xylose lysine deoxycholate, Salmonella Shigella, and Brilliant Green agar plates, which exhibit specific color characteristics over the colonies and over the surrounding medium for a presumed positive interpretation. Under a controlled illumination environment, images of plates are captured and the characteristics found over each agar are processed separately. Each agar is analyzed using statistical descriptors for texture, to determine the presence of colonies, followed by the extraction of color features. A comparison among the color features seen over the three media, according to the FDA Bacteriological Analytical Manual, determines the presence of Salmonella sp. on a given sample. The implemented process proves that the task addressed can be accomplished under an image processing approach, leading to the future validation and automation of additional screening processes.

Effects of preprocessing Landsat MSS data on derived features

NASA Technical Reports Server (NTRS)

Parris, T. M.; Cicone, R. C.

1983-01-01

Important to the use of multitemporal Landsat MSS data for earth resources monitoring, such as agricultural inventories, is the ability to minimize the effects of varying atmospheric and satellite viewing conditions, while extracting physically meaningful features from the data. In general, the approaches to the preprocessing problem have been derived from either physical or statistical models. This paper compares three proposed algorithms; XSTAR haze correction, Color Normalization, and Multiple Acquisition Mean Level Adjustment. These techniques represent physical, statistical, and hybrid physical-statistical models, respectively. The comparisons are made in the context of three feature extraction techniques; the Tasseled Cap, the Cate Color Cube. and Normalized Difference.

Integrating the Allen Brain Institute Cell Types Database into Automated Neuroscience Workflow.

PubMed

Stockton, David B; Santamaria, Fidel

2017-10-01

We developed software tools to download, extract features, and organize the Cell Types Database from the Allen Brain Institute (ABI) in order to integrate its whole cell patch clamp characterization data into the automated modeling/data analysis cycle. To expand the potential user base we employed both Python and MATLAB. The basic set of tools downloads selected raw data and extracts cell, sweep, and spike features, using ABI's feature extraction code. To facilitate data manipulation we added a tool to build a local specialized database of raw data plus extracted features. Finally, to maximize automation, we extended our NeuroManager workflow automation suite to include these tools plus a separate investigation database. The extended suite allows the user to integrate ABI experimental and modeling data into an automated workflow deployed on heterogeneous computer infrastructures, from local servers, to high performance computing environments, to the cloud. Since our approach is focused on workflow procedures our tools can be modified to interact with the increasing number of neuroscience databases being developed to cover all scales and properties of the nervous system.

A combination of feature extraction methods with an ensemble of different classifiers for protein structural class prediction problem.

PubMed

Dehzangi, Abdollah; Paliwal, Kuldip; Sharma, Alok; Dehzangi, Omid; Sattar, Abdul

2013-01-01

Better understanding of structural class of a given protein reveals important information about its overall folding type and its domain. It can also be directly used to provide critical information on general tertiary structure of a protein which has a profound impact on protein function determination and drug design. Despite tremendous enhancements made by pattern recognition-based approaches to solve this problem, it still remains as an unsolved issue for bioinformatics that demands more attention and exploration. In this study, we propose a novel feature extraction model that incorporates physicochemical and evolutionary-based information simultaneously. We also propose overlapped segmented distribution and autocorrelation-based feature extraction methods to provide more local and global discriminatory information. The proposed feature extraction methods are explored for 15 most promising attributes that are selected from a wide range of physicochemical-based attributes. Finally, by applying an ensemble of different classifiers namely, Adaboost.M1, LogitBoost, naive Bayes, multilayer perceptron (MLP), and support vector machine (SVM) we show enhancement of the protein structural class prediction accuracy for four popular benchmarks.

A Generic multi-dimensional feature extraction method using multiobjective genetic programming.

PubMed

Zhang, Yang; Rockett, Peter I

2009-01-01

In this paper, we present a generic feature extraction method for pattern classification using multiobjective genetic programming. This not only evolves the (near-)optimal set of mappings from a pattern space to a multi-dimensional decision space, but also simultaneously optimizes the dimensionality of that decision space. The presented framework evolves vector-to-vector feature extractors that maximize class separability. We demonstrate the efficacy of our approach by making statistically-founded comparisons with a wide variety of established classifier paradigms over a range of datasets and find that for most of the pairwise comparisons, our evolutionary method delivers statistically smaller misclassification errors. At very worst, our method displays no statistical difference in a few pairwise comparisons with established classifier/dataset combinations; crucially, none of the misclassification results produced by our method is worse than any comparator classifier. Although principally focused on feature extraction, feature selection is also performed as an implicit side effect; we show that both feature extraction and selection are important to the success of our technique. The presented method has the practical consequence of obviating the need to exhaustively evaluate a large family of conventional classifiers when faced with a new pattern recognition problem in order to attain a good classification accuracy.

Spectral-Spatial Scale Invariant Feature Transform for Hyperspectral Images.

PubMed

Al-Khafaji, Suhad Lateef; Jun Zhou; Zia, Ali; Liew, Alan Wee-Chung

2018-02-01

Spectral-spatial feature extraction is an important task in hyperspectral image processing. In this paper we propose a novel method to extract distinctive invariant features from hyperspectral images for registration of hyperspectral images with different spectral conditions. Spectral condition means images are captured with different incident lights, viewing angles, or using different hyperspectral cameras. In addition, spectral condition includes images of objects with the same shape but different materials. This method, which is named spectral-spatial scale invariant feature transform (SS-SIFT), explores both spectral and spatial dimensions simultaneously to extract spectral and geometric transformation invariant features. Similar to the classic SIFT algorithm, SS-SIFT consists of keypoint detection and descriptor construction steps. Keypoints are extracted from spectral-spatial scale space and are detected from extrema after 3D difference of Gaussian is applied to the data cube. Two descriptors are proposed for each keypoint by exploring the distribution of spectral-spatial gradient magnitude in its local 3D neighborhood. The effectiveness of the SS-SIFT approach is validated on images collected in different light conditions, different geometric projections, and using two hyperspectral cameras with different spectral wavelength ranges and resolutions. The experimental results show that our method generates robust invariant features for spectral-spatial image matching.

A novel automated spike sorting algorithm with adaptable feature extraction.

PubMed

Bestel, Robert; Daus, Andreas W; Thielemann, Christiane

2012-10-15

To study the electrophysiological properties of neuronal networks, in vitro studies based on microelectrode arrays have become a viable tool for analysis. Although in constant progress, a challenging task still remains in this area: the development of an efficient spike sorting algorithm that allows an accurate signal analysis at the single-cell level. Most sorting algorithms currently available only extract a specific feature type, such as the principal components or Wavelet coefficients of the measured spike signals in order to separate different spike shapes generated by different neurons. However, due to the great variety in the obtained spike shapes, the derivation of an optimal feature set is still a very complex issue that current algorithms struggle with. To address this problem, we propose a novel algorithm that (i) extracts a variety of geometric, Wavelet and principal component-based features and (ii) automatically derives a feature subset, most suitable for sorting an individual set of spike signals. Thus, there is a new approach that evaluates the probability distribution of the obtained spike features and consequently determines the candidates most suitable for the actual spike sorting. These candidates can be formed into an individually adjusted set of spike features, allowing a separation of the various shapes present in the obtained neuronal signal by a subsequent expectation maximisation clustering algorithm. Test results with simulated data files and data obtained from chick embryonic neurons cultured on microelectrode arrays showed an excellent classification result, indicating the superior performance of the described algorithm approach. Copyright © 2012 Elsevier B.V. All rights reserved.

Efficient iris texture analysis method based on Gabor ordinal measures

NASA Astrophysics Data System (ADS)

Tajouri, Imen; Aydi, Walid; Ghorbel, Ahmed; Masmoudi, Nouri

2017-07-01

With the remarkably increasing interest directed to the security dimension, the iris recognition process is considered to stand as one of the most versatile technique critically useful for the biometric identification and authentication process. This is mainly due to every individual's unique iris texture. A modestly conceived efficient approach relevant to the feature extraction process is proposed. In the first place, iris zigzag "collarette" is extracted from the rest of the image by means of the circular Hough transform, as it includes the most significant regions lying in the iris texture. In the second place, the linear Hough transform is used for the eyelids' detection purpose while the median filter is applied for the eyelashes' removal. Then, a special technique combining the richness of Gabor features and the compactness of ordinal measures is implemented for the feature extraction process, so that a discriminative feature representation for every individual can be achieved. Subsequently, the modified Hamming distance is used for the matching process. Indeed, the advanced procedure turns out to be reliable, as compared to some of the state-of-the-art approaches, with a recognition rate of 99.98%, 98.12%, and 95.02% on CASIAV1.0, CASIAV3.0, and IIT Delhi V1 iris databases, respectively.

Integrating dimension reduction and out-of-sample extension in automated classification of ex vivo human patellar cartilage on phase contrast X-ray computed tomography.

PubMed

Nagarajan, Mahesh B; Coan, Paola; Huber, Markus B; Diemoz, Paul C; Wismüller, Axel

2015-01-01

Phase contrast X-ray computed tomography (PCI-CT) has been demonstrated as a novel imaging technique that can visualize human cartilage with high spatial resolution and soft tissue contrast. Different textural approaches have been previously investigated for characterizing chondrocyte organization on PCI-CT to enable classification of healthy and osteoarthritic cartilage. However, the large size of feature sets extracted in such studies motivates an investigation into algorithmic feature reduction for computing efficient feature representations without compromising their discriminatory power. For this purpose, geometrical feature sets derived from the scaling index method (SIM) were extracted from 1392 volumes of interest (VOI) annotated on PCI-CT images of ex vivo human patellar cartilage specimens. The extracted feature sets were subject to linear and non-linear dimension reduction techniques as well as feature selection based on evaluation of mutual information criteria. The reduced feature set was subsequently used in a machine learning task with support vector regression to classify VOIs as healthy or osteoarthritic; classification performance was evaluated using the area under the receiver-operating characteristic (ROC) curve (AUC). Our results show that the classification performance achieved by 9-D SIM-derived geometric feature sets (AUC: 0.96 ± 0.02) can be maintained with 2-D representations computed from both dimension reduction and feature selection (AUC values as high as 0.97 ± 0.02). Thus, such feature reduction techniques can offer a high degree of compaction to large feature sets extracted from PCI-CT images while maintaining their ability to characterize the underlying chondrocyte patterns.

Improving the performance of univariate control charts for abnormal detection and classification

NASA Astrophysics Data System (ADS)

Yiakopoulos, Christos; Koutsoudaki, Maria; Gryllias, Konstantinos; Antoniadis, Ioannis

2017-03-01

Bearing failures in rotating machinery can cause machine breakdown and economical loss, if no effective actions are taken on time. Therefore, it is of prime importance to detect accurately the presence of faults, especially at their early stage, to prevent sequent damage and reduce costly downtime. The machinery fault diagnosis follows a roadmap of data acquisition, feature extraction and diagnostic decision making, in which mechanical vibration fault feature extraction is the foundation and the key to obtain an accurate diagnostic result. A challenge in this area is the selection of the most sensitive features for various types of fault, especially when the characteristics of failures are difficult to be extracted. Thus, a plethora of complex data-driven fault diagnosis methods are fed by prominent features, which are extracted and reduced through traditional or modern algorithms. Since most of the available datasets are captured during normal operating conditions, the last decade a number of novelty detection methods, able to work when only normal data are available, have been developed. In this study, a hybrid method combining univariate control charts and a feature extraction scheme is introduced focusing towards an abnormal change detection and classification, under the assumption that measurements under normal operating conditions of the machinery are available. The feature extraction method integrates the morphological operators and the Morlet wavelets. The effectiveness of the proposed methodology is validated on two different experimental cases with bearing faults, demonstrating that the proposed approach can improve the fault detection and classification performance of conventional control charts.

A practical salient region feature based 3D multi-modality registration method for medical images

NASA Astrophysics Data System (ADS)

Hahn, Dieter A.; Wolz, Gabriele; Sun, Yiyong; Hornegger, Joachim; Sauer, Frank; Kuwert, Torsten; Xu, Chenyang

2006-03-01

We present a novel representation of 3D salient region features and its integration into a hybrid rigid-body registration framework. We adopt scale, translation and rotation invariance properties of those intrinsic 3D features to estimate a transform between underlying mono- or multi-modal 3D medical images. Our method combines advantageous aspects of both feature- and intensity-based approaches and consists of three steps: an automatic extraction of a set of 3D salient region features on each image, a robust estimation of correspondences and their sub-pixel accurate refinement with outliers elimination. We propose a region-growing based approach for the extraction of 3D salient region features, a solution to the problem of feature clustering and a reduction of the correspondence search space complexity. Results of the developed algorithm are presented for both mono- and multi-modal intra-patient 3D image pairs (CT, PET and SPECT) that have been acquired for change detection, tumor localization, and time based intra-person studies. The accuracy of the method is clinically evaluated by a medical expert with an approach that measures the distance between a set of selected corresponding points consisting of both anatomical and functional structures or lesion sites. This demonstrates the robustness of the proposed method to image overlap, missing information and artefacts. We conclude by discussing potential medical applications and possibilities for integration into a non-rigid registration framework.

Hybrid Feature Extraction-based Approach for Facial Parts Representation and Recognition

NASA Astrophysics Data System (ADS)

Rouabhia, C.; Tebbikh, H.

2008-06-01

Face recognition is a specialized image processing which has attracted a considerable attention in computer vision. In this article, we develop a new facial recognition system from video sequences images dedicated to person identification whose face is partly occulted. This system is based on a hybrid image feature extraction technique called ACPDL2D (Rouabhia et al. 2007), it combines two-dimensional principal component analysis and two-dimensional linear discriminant analysis with neural network. We performed the feature extraction task on the eyes and the nose images separately then a Multi-Layers Perceptron classifier is used. Compared to the whole face, the results of simulation are in favor of the facial parts in terms of memory capacity and recognition (99.41% for the eyes part, 98.16% for the nose part and 97.25 % for the whole face).

Sentence alignment using feed forward neural network.

PubMed

Fattah, Mohamed Abdel; Ren, Fuji; Kuroiwa, Shingo

2006-12-01

Parallel corpora have become an essential resource for work in multi lingual natural language processing. However, sentence aligned parallel corpora are more efficient than non-aligned parallel corpora for cross language information retrieval and machine translation applications. In this paper, we present a new approach to align sentences in bilingual parallel corpora based on feed forward neural network classifier. A feature parameter vector is extracted from the text pair under consideration. This vector contains text features such as length, punctuate score, and cognate score values. A set of manually prepared training data has been assigned to train the feed forward neural network. Another set of data was used for testing. Using this new approach, we could achieve an error reduction of 60% over length based approach when applied on English-Arabic parallel documents. Moreover this new approach is valid for any language pair and it is quite flexible approach since the feature parameter vector may contain more/less or different features than that we used in our system such as lexical match feature.

ZK DrugResist 2.0: A TextMiner to extract semantic relations of drug resistance from PubMed.

PubMed

Khalid, Zoya; Sezerman, Osman Ugur

2017-05-01

Extracting useful knowledge from an unstructured textual data is a challenging task for biologists, since biomedical literature is growing exponentially on a daily basis. Building an automated method for such tasks is gaining much attention of researchers. ZK DrugResist is an online tool that automatically extracts mutations and expression changes associated with drug resistance from PubMed. In this study we have extended our tool to include semantic relations extracted from biomedical text covering drug resistance and established a server including both of these features. Our system was tested for three relations, Resistance (R), Intermediate (I) and Susceptible (S) by applying hybrid feature set. From the last few decades the focus has changed to hybrid approaches as it provides better results. In our case this approach combines rule-based methods with machine learning techniques. The results showed 97.67% accuracy with 96% precision, recall and F-measure. The results have outperformed the previously existing relation extraction systems thus can facilitate computational analysis of drug resistance against complex diseases and further can be implemented on other areas of biomedicine. Copyright © 2017 Elsevier Inc. All rights reserved.

[Research on the methods for multi-class kernel CSP-based feature extraction].

PubMed

Wang, Jinjia; Zhang, Lingzhi; Hu, Bei

2012-04-01

To relax the presumption of strictly linear patterns in the common spatial patterns (CSP), we studied the kernel CSP (KCSP). A new multi-class KCSP (MKCSP) approach was proposed in this paper, which combines the kernel approach with multi-class CSP technique. In this approach, we used kernel spatial patterns for each class against all others, and extracted signal components specific to one condition from EEG data sets of multiple conditions. Then we performed classification using the Logistic linear classifier. Brain computer interface (BCI) competition III_3a was used in the experiment. Through the experiment, it can be proved that this approach could decompose the raw EEG singles into spatial patterns extracted from multi-class of single trial EEG, and could obtain good classification results.

A bio-inspired method and system for visual object-based attention and segmentation

NASA Astrophysics Data System (ADS)

Huber, David J.; Khosla, Deepak

2010-04-01

This paper describes a method and system of human-like attention and object segmentation in visual scenes that (1) attends to regions in a scene in their rank of saliency in the image, (2) extracts the boundary of an attended proto-object based on feature contours, and (3) can be biased to boost the attention paid to specific features in a scene, such as those of a desired target object in static and video imagery. The purpose of the system is to identify regions of a scene of potential importance and extract the region data for processing by an object recognition and classification algorithm. The attention process can be performed in a default, bottom-up manner or a directed, top-down manner which will assign a preference to certain features over others. One can apply this system to any static scene, whether that is a still photograph or imagery captured from video. We employ algorithms that are motivated by findings in neuroscience, psychology, and cognitive science to construct a system that is novel in its modular and stepwise approach to the problems of attention and region extraction, its application of a flooding algorithm to break apart an image into smaller proto-objects based on feature density, and its ability to join smaller regions of similar features into larger proto-objects. This approach allows many complicated operations to be carried out by the system in a very short time, approaching real-time. A researcher can use this system as a robust front-end to a larger system that includes object recognition and scene understanding modules; it is engineered to function over a broad range of situations and can be applied to any scene with minimal tuning from the user.

Distant supervision for neural relation extraction integrated with word attention and property features.

PubMed

Qu, Jianfeng; Ouyang, Dantong; Hua, Wen; Ye, Yuxin; Li, Ximing

2018-04-01

Distant supervision for neural relation extraction is an efficient approach to extracting massive relations with reference to plain texts. However, the existing neural methods fail to capture the critical words in sentence encoding and meanwhile lack useful sentence information for some positive training instances. To address the above issues, we propose a novel neural relation extraction model. First, we develop a word-level attention mechanism to distinguish the importance of each individual word in a sentence, increasing the attention weights for those critical words. Second, we investigate the semantic information from word embeddings of target entities, which can be developed as a supplementary feature for the extractor. Experimental results show that our model outperforms previous state-of-the-art baselines. Copyright © 2018 Elsevier Ltd. All rights reserved.

MixDroid: A multi-features and multi-classifiers bagging system for Android malware detection

NASA Astrophysics Data System (ADS)

Huang, Weiqing; Hou, Erhang; Zheng, Liang; Feng, Weimiao

2018-05-01

In the past decade, Android platform has rapidly taken over the mobile market for its superior convenience and open source characteristics. However, with the popularity of Android, malwares targeting on Android devices are increasing rapidly, while the conventional rule-based and expert-experienced approaches are no longer able to handle such explosive growth. In this paper, combining with the theory of natural language processing and machine learning, we not only implement the basic feature extraction of permission application features, but also propose two innovative schemes of feature extraction: Dalvik opcode features and malicious code image, and implement an automatic Android malware detection system MixDroid which is based on multi-features and multi-classifiers. According to our experiment results on 20,000 Android applications, detection accuracy of MixDroid is 98.1%, which proves our schemes' effectiveness in Android malware detection.

A method for medulloblastoma tumor differentiation based on convolutional neural networks and transfer learning

NASA Astrophysics Data System (ADS)

Cruz-Roa, Angel; Arévalo, John; Judkins, Alexander; Madabhushi, Anant; González, Fabio

2015-12-01

Convolutional neural networks (CNN) have been very successful at addressing different computer vision tasks thanks to their ability to learn image representations directly from large amounts of labeled data. Features learned from a dataset can be used to represent images from a different dataset via an approach called transfer learning. In this paper we apply transfer learning to the challenging task of medulloblastoma tumor differentiation. We compare two different CNN models which were previously trained in two different domains (natural and histopathology images). The first CNN is a state-of-the-art approach in computer vision, a large and deep CNN with 16-layers, Visual Geometry Group (VGG) CNN. The second (IBCa-CNN) is a 2-layer CNN trained for invasive breast cancer tumor classification. Both CNNs are used as visual feature extractors of histopathology image regions of anaplastic and non-anaplastic medulloblastoma tumor from digitized whole-slide images. The features from the two models are used, separately, to train a softmax classifier to discriminate between anaplastic and non-anaplastic medulloblastoma image regions. Experimental results show that the transfer learning approach produce competitive results in comparison with the state of the art approaches for IBCa detection. Results also show that features extracted from the IBCa-CNN have better performance in comparison with features extracted from the VGG-CNN. The former obtains 89.8% while the latter obtains 76.6% in terms of average accuracy.

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.

Real-time implementation of optimized maximum noise fraction transform for feature extraction of hyperspectral images

NASA Astrophysics Data System (ADS)

Wu, Yuanfeng; Gao, Lianru; Zhang, Bing; Zhao, Haina; Li, Jun

2014-01-01

We present a parallel implementation of the optimized maximum noise fraction (G-OMNF) transform algorithm for feature extraction of hyperspectral images on commodity graphics processing units (GPUs). The proposed approach explored the algorithm data-level concurrency and optimized the computing flow. We first defined a three-dimensional grid, in which each thread calculates a sub-block data to easily facilitate the spatial and spectral neighborhood data searches in noise estimation, which is one of the most important steps involved in OMNF. Then, we optimized the processing flow and computed the noise covariance matrix before computing the image covariance matrix to reduce the original hyperspectral image data transmission. These optimization strategies can greatly improve the computing efficiency and can be applied to other feature extraction algorithms. The proposed parallel feature extraction algorithm was implemented on an Nvidia Tesla GPU using the compute unified device architecture and basic linear algebra subroutines library. Through the experiments on several real hyperspectral images, our GPU parallel implementation provides a significant speedup of the algorithm compared with the CPU implementation, especially for highly data parallelizable and arithmetically intensive algorithm parts, such as noise estimation. In order to further evaluate the effectiveness of G-OMNF, we used two different applications: spectral unmixing and classification for evaluation. Considering the sensor scanning rate and the data acquisition time, the proposed parallel implementation met the on-board real-time feature extraction.

An application of Chan-Vese method used to determine the ROI area in CT lung screening

NASA Astrophysics Data System (ADS)

Prokop, Paweł; Surtel, Wojciech

2016-09-01

The article presents two approaches of determining the ROI area in CT lung screening. First approach is based on a classic method of framing the image in order to determine the ROI by using a MaZda tool. Second approach is based on segmentation of CT images of the lungs and reducing the redundant information from the image. Of the two approaches of an Active Contour, it was decided to choose the Chan-Vese method. In order to determine the effectiveness of the approach, it was performed an analysis of received ROI texture and extraction of textural features. In order to determine the effectiveness of the method, it was performed an analysis of the received ROI textures and extraction of the texture features, by using a Mazda tool. The results were compared and presented in the form of the radar graphs. The second approach proved to be effective and appropriate and consequently it is used for further analysis of CT images, in the computer-aided diagnosis of sarcoidosis.

Extraction of Urban Trees from Integrated Airborne Based Digital Image and LIDAR Point Cloud Datasets - Initial Results

NASA Astrophysics Data System (ADS)

Dogon-yaro, M. A.; Kumar, P.; Rahman, A. Abdul; Buyuksalih, G.

2016-10-01

Timely and accurate acquisition of information on the condition and structural changes of urban trees serves as a tool for decision makers to better appreciate urban ecosystems and their numerous values which are critical to building up strategies for sustainable development. The conventional techniques used for extracting tree features include; ground surveying and interpretation of the aerial photography. However, these techniques are associated with some constraint, such as labour intensive field work, a lot of financial requirement, influences by weather condition and topographical covers which can be overcome by means of integrated airborne based LiDAR and very high resolution digital image datasets. This study presented a semi-automated approach for extracting urban trees from integrated airborne based LIDAR and multispectral digital image datasets over Istanbul city of Turkey. The above scheme includes detection and extraction of shadow free vegetation features based on spectral properties of digital images using shadow index and NDVI techniques and automated extraction of 3D information about vegetation features from the integrated processing of shadow free vegetation image and LiDAR point cloud datasets. The ability of the developed algorithms shows a promising result as an automated and cost effective approach to estimating and delineated 3D information of urban trees. The research also proved that integrated datasets is a suitable technology and a viable source of information for city managers to be used in urban trees management.

Face recognition using slow feature analysis and contourlet transform

NASA Astrophysics Data System (ADS)

Wang, Yuehao; Peng, Lingling; Zhe, Fuchuan

2018-04-01

In this paper we propose a novel face recognition approach based on slow feature analysis (SFA) in contourlet transform domain. This method firstly use contourlet transform to decompose the face image into low frequency and high frequency part, and then takes technological advantages of slow feature analysis for facial feature extraction. We named the new method combining the slow feature analysis and contourlet transform as CT-SFA. The experimental results on international standard face database demonstrate that the new face recognition method is effective and competitive.

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%.

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.

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.

Spatiotemporal modelling of groundwater extraction in semi-arid central Queensland, Australia

NASA Astrophysics Data System (ADS)

Keir, Greg; Bulovic, Nevenka; McIntyre, Neil

2016-04-01

The semi-arid Surat Basin in central Queensland, Australia, forms part of the Great Artesian Basin, a groundwater resource of national significance. While this area relies heavily on groundwater supply bores to sustain agricultural industries and rural life in general, measurement of groundwater extraction rates is very limited. Consequently, regional groundwater extraction rates are not well known, which may have implications for regional numerical groundwater modelling. However, flows from a small number of bores are metered, and less precise anecdotal estimates of extraction are increasingly available. There is also an increasing number of other spatiotemporal datasets which may help predict extraction rates (e.g. rainfall, temperature, soils, stocking rates etc.). These can be used to construct spatial multivariate regression models to estimate extraction. The data exhibit complicated statistical features, such as zero-valued observations, non-Gaussianity, and non-stationarity, which limit the use of many classical estimation techniques, such as kriging. As well, water extraction histories may exhibit temporal autocorrelation. To account for these features, we employ a separable space-time model to predict bore extraction rates using the R-INLA package for computationally efficient Bayesian inference. A joint approach is used to model both the probability (using a binomial likelihood) and magnitude (using a gamma likelihood) of extraction. The correlation between extraction rates in space and time is modelled using a Gaussian Markov Random Field (GMRF) with a Matérn spatial covariance function which can evolve over time according to an autoregressive model. To reduce computational burden, we allow the GMRF to be evaluated at a relatively coarse temporal resolution, while still allowing predictions to be made at arbitrarily small time scales. We describe the process of model selection and inference using an information criterion approach, and present some preliminary results from the study area. We conclude by discussing issues related with upscaling of the modelling approach to the entire basin, including merging of extraction rate observations with different precision, temporal resolution, and even potentially different likelihoods.

Personalized Offline and Pseudo-Online BCI Models to Detect Pedaling Intent

PubMed Central

Rodríguez-Ugarte, Marisol; Iáñez, Eduardo; Ortíz, Mario; Azorín, Jose M.

2017-01-01

The aim of this work was to design a personalized BCI model to detect pedaling intention through EEG signals. The approach sought to select the best among many possible BCI models for each subject. The choice was between different processing windows, feature extraction algorithms and electrode configurations. Moreover, data was analyzed offline and pseudo-online (in a way suitable for real-time applications), with a preference for the latter case. A process for selecting the best BCI model was described in detail. Results for the pseudo-online processing with the best BCI model of each subject were on average 76.7% of true positive rate, 4.94 false positives per minute and 55.1% of accuracy. The personalized BCI model approach was also found to be significantly advantageous when compared to the typical approach of using a fixed feature extraction algorithm and electrode configuration. The resulting approach could be used to more robustly interface with lower limb exoskeletons in the context of the rehabilitation of stroke patients. PMID:28744212

Arabic sign language recognition based on HOG descriptor

NASA Astrophysics Data System (ADS)

Ben Jmaa, Ahmed; Mahdi, Walid; Ben Jemaa, Yousra; Ben Hamadou, Abdelmajid

2017-02-01

We present in this paper a new approach for Arabic sign language (ArSL) alphabet recognition using hand gesture analysis. This analysis consists in extracting a histogram of oriented gradient (HOG) features from a hand image and then using them to generate an SVM Models. Which will be used to recognize the ArSL alphabet in real-time from hand gesture using a Microsoft Kinect camera. Our approach involves three steps: (i) Hand detection and localization using a Microsoft Kinect camera, (ii) hand segmentation and (iii) feature extraction using Arabic alphabet recognition. One each input image first obtained by using a depth sensor, we apply our method based on hand anatomy to segment hand and eliminate all the errors pixels. This approach is invariant to scale, to rotation and to translation of the hand. Some experimental results show the effectiveness of our new approach. Experiment revealed that the proposed ArSL system is able to recognize the ArSL with an accuracy of 90.12%.

Personalized Offline and Pseudo-Online BCI Models to Detect Pedaling Intent.

PubMed

Rodríguez-Ugarte, Marisol; Iáñez, Eduardo; Ortíz, Mario; Azorín, Jose M

2017-01-01

The aim of this work was to design a personalized BCI model to detect pedaling intention through EEG signals. The approach sought to select the best among many possible BCI models for each subject. The choice was between different processing windows, feature extraction algorithms and electrode configurations. Moreover, data was analyzed offline and pseudo-online (in a way suitable for real-time applications), with a preference for the latter case. A process for selecting the best BCI model was described in detail. Results for the pseudo-online processing with the best BCI model of each subject were on average 76.7% of true positive rate, 4.94 false positives per minute and 55.1% of accuracy. The personalized BCI model approach was also found to be significantly advantageous when compared to the typical approach of using a fixed feature extraction algorithm and electrode configuration. The resulting approach could be used to more robustly interface with lower limb exoskeletons in the context of the rehabilitation of stroke patients.

A statistical-textural-features based approach for classification of solid drugs using surface microscopic images.

PubMed

Tahir, Fahima; Fahiem, Muhammad Abuzar

2014-01-01

The quality of pharmaceutical products plays an important role in pharmaceutical industry as well as in our lives. Usage of defective tablets can be harmful for patients. In this research we proposed a nondestructive method to identify defective and nondefective tablets using their surface morphology. Three different environmental factors temperature, humidity and moisture are analyzed to evaluate the performance of the proposed method. Multiple textural features are extracted from the surface of the defective and nondefective tablets. These textural features are gray level cooccurrence matrix, run length matrix, histogram, autoregressive model and HAAR wavelet. Total textural features extracted from images are 281. We performed an analysis on all those 281, top 15, and top 2 features. Top 15 features are extracted using three different feature reduction techniques: chi-square, gain ratio and relief-F. In this research we have used three different classifiers: support vector machine, K-nearest neighbors and naïve Bayes to calculate the accuracies against proposed method using two experiments, that is, leave-one-out cross-validation technique and train test models. We tested each classifier against all selected features and then performed the comparison of their results. The experimental work resulted in that in most of the cases SVM performed better than the other two classifiers.

Content Based Image Retrieval by Using Color Descriptor and Discrete Wavelet Transform.

PubMed

Ashraf, Rehan; Ahmed, Mudassar; Jabbar, Sohail; Khalid, Shehzad; Ahmad, Awais; Din, Sadia; Jeon, Gwangil

2018-01-25

Due to recent development in technology, the complexity of multimedia is significantly increased and the retrieval of similar multimedia content is a open research problem. Content-Based Image Retrieval (CBIR) is a process that provides a framework for image search and low-level visual features are commonly used to retrieve the images from the image database. The basic requirement in any image retrieval process is to sort the images with a close similarity in term of visually appearance. The color, shape and texture are the examples of low-level image features. The feature plays a significant role in image processing. The powerful representation of an image is known as feature vector and feature extraction techniques are applied to get features that will be useful in classifying and recognition of images. As features define the behavior of an image, they show its place in terms of storage taken, efficiency in classification and obviously in time consumption also. In this paper, we are going to discuss various types of features, feature extraction techniques and explaining in what scenario, which features extraction technique will be better. The effectiveness of the CBIR approach is fundamentally based on feature extraction. In image processing errands like object recognition and image retrieval feature descriptor is an immense among the most essential step. The main idea of CBIR is that it can search related images to an image passed as query from a dataset got by using distance metrics. The proposed method is explained for image retrieval constructed on YCbCr color with canny edge histogram and discrete wavelet transform. The combination of edge of histogram and discrete wavelet transform increase the performance of image retrieval framework for content based search. The execution of different wavelets is additionally contrasted with discover the suitability of specific wavelet work for image retrieval. The proposed algorithm is prepared and tried to implement for Wang image database. For Image Retrieval Purpose, Artificial Neural Networks (ANN) is used and applied on standard dataset in CBIR domain. The execution of the recommended descriptors is assessed by computing both Precision and Recall values and compared with different other proposed methods with demonstrate the predominance of our method. The efficiency and effectiveness of the proposed approach outperforms the existing research in term of average precision and recall values.

Antepartum fetal heart rate feature extraction and classification using empirical mode decomposition and support vector machine

PubMed Central

2011-01-01

Background Cardiotocography (CTG) is the most widely used tool for fetal surveillance. The visual analysis of fetal heart rate (FHR) traces largely depends on the expertise and experience of the clinician involved. Several approaches have been proposed for the effective interpretation of FHR. In this paper, a new approach for FHR feature extraction based on empirical mode decomposition (EMD) is proposed, which was used along with support vector machine (SVM) for the classification of FHR recordings as 'normal' or 'at risk'. Methods The FHR were recorded from 15 subjects at a sampling rate of 4 Hz and a dataset consisting of 90 randomly selected records of 20 minutes duration was formed from these. All records were labelled as 'normal' or 'at risk' by two experienced obstetricians. A training set was formed by 60 records, the remaining 30 left as the testing set. The standard deviations of the EMD components are input as features to a support vector machine (SVM) to classify FHR samples. Results For the training set, a five-fold cross validation test resulted in an accuracy of 86% whereas the overall geometric mean of sensitivity and specificity was 94.8%. The Kappa value for the training set was .923. Application of the proposed method to the testing set (30 records) resulted in a geometric mean of 81.5%. The Kappa value for the testing set was .684. Conclusions Based on the overall performance of the system it can be stated that the proposed methodology is a promising new approach for the feature extraction and classification of FHR signals. PMID:21244712

Influence of nuclei segmentation on breast cancer malignancy classification

NASA Astrophysics Data System (ADS)

Jelen, Lukasz; Fevens, Thomas; Krzyzak, Adam

2009-02-01

Breast Cancer is one of the most deadly cancers affecting middle-aged women. Accurate diagnosis and prognosis are crucial to reduce the high death rate. Nowadays there are numerous diagnostic tools for breast cancer diagnosis. In this paper we discuss a role of nuclear segmentation from fine needle aspiration biopsy (FNA) slides and its influence on malignancy classification. Classification of malignancy plays a very important role during the diagnosis process of breast cancer. Out of all cancer diagnostic tools, FNA slides provide the most valuable information about the cancer malignancy grade which helps to choose an appropriate treatment. This process involves assessing numerous nuclear features and therefore precise segmentation of nuclei is very important. In this work we compare three powerful segmentation approaches and test their impact on the classification of breast cancer malignancy. The studied approaches involve level set segmentation, fuzzy c-means segmentation and textural segmentation based on co-occurrence matrix. Segmented nuclei were used to extract nuclear features for malignancy classification. For classification purposes four different classifiers were trained and tested with previously extracted features. The compared classifiers are Multilayer Perceptron (MLP), Self-Organizing Maps (SOM), Principal Component-based Neural Network (PCA) and Support Vector Machines (SVM). The presented results show that level set segmentation yields the best results over the three compared approaches and leads to a good feature extraction with a lowest average error rate of 6.51% over four different classifiers. The best performance was recorded for multilayer perceptron with an error rate of 3.07% using fuzzy c-means segmentation.

Detection of distorted frames in retinal video-sequences via machine learning

NASA Astrophysics Data System (ADS)

Kolar, Radim; Liberdova, Ivana; Odstrcilik, Jan; Hracho, Michal; Tornow, Ralf P.

2017-07-01

This paper describes detection of distorted frames in retinal sequences based on set of global features extracted from each frame. The feature vector is consequently used in classification step, in which three types of classifiers are tested. The best classification accuracy 96% has been achieved with support vector machine approach.

Application of texture analysis method for mammogram density classification

NASA Astrophysics Data System (ADS)

Nithya, R.; Santhi, B.

2017-07-01

Mammographic density is considered a major risk factor for developing breast cancer. This paper proposes an automated approach to classify breast tissue types in digital mammogram. The main objective of the proposed Computer-Aided Diagnosis (CAD) system is to investigate various feature extraction methods and classifiers to improve the diagnostic accuracy in mammogram density classification. Texture analysis methods are used to extract the features from the mammogram. Texture features are extracted by using histogram, Gray Level Co-Occurrence Matrix (GLCM), Gray Level Run Length Matrix (GLRLM), Gray Level Difference Matrix (GLDM), Local Binary Pattern (LBP), Entropy, Discrete Wavelet Transform (DWT), Wavelet Packet Transform (WPT), Gabor transform and trace transform. These extracted features are selected using Analysis of Variance (ANOVA). The features selected by ANOVA are fed into the classifiers to characterize the mammogram into two-class (fatty/dense) and three-class (fatty/glandular/dense) breast density classification. This work has been carried out by using the mini-Mammographic Image Analysis Society (MIAS) database. Five classifiers are employed namely, Artificial Neural Network (ANN), Linear Discriminant Analysis (LDA), Naive Bayes (NB), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). Experimental results show that ANN provides better performance than LDA, NB, KNN and SVM classifiers. The proposed methodology has achieved 97.5% accuracy for three-class and 99.37% for two-class density classification.

A Method for Extracting Suspected Parotid Lesions in CT Images using Feature-based Segmentation and Active Contours based on Stationary Wavelet Transform

NASA Astrophysics Data System (ADS)

Wu, T. Y.; Lin, S. F.

2013-10-01

Automatic suspected lesion extraction is an important application in computer-aided diagnosis (CAD). In this paper, we propose a method to automatically extract the suspected parotid regions for clinical evaluation in head and neck CT images. The suspected lesion tissues in low contrast tissue regions can be localized with feature-based segmentation (FBS) based on local texture features, and can be delineated with accuracy by modified active contour models (ACM). At first, stationary wavelet transform (SWT) is introduced. The derived wavelet coefficients are applied to derive the local features for FBS, and to generate enhanced energy maps for ACM computation. Geometric shape features (GSFs) are proposed to analyze each soft tissue region segmented by FBS; the regions with higher similarity GSFs with the lesions are extracted and the information is also applied as the initial conditions for fine delineation computation. Consequently, the suspected lesions can be automatically localized and accurately delineated for aiding clinical diagnosis. The performance of the proposed method is evaluated by comparing with the results outlined by clinical experts. The experiments on 20 pathological CT data sets show that the true-positive (TP) rate on recognizing parotid lesions is about 94%, and the dimension accuracy of delineation results can also approach over 93%.

Analysis and Recognition of Traditional Chinese Medicine Pulse Based on the Hilbert-Huang Transform and Random Forest in Patients with Coronary Heart Disease

PubMed Central

Wang, Yiqin; Yan, Hanxia; Yan, Jianjun; Yuan, Fengyin; Xu, Zhaoxia; Liu, Guoping; Xu, Wenjie

2015-01-01

Objective. This research provides objective and quantitative parameters of the traditional Chinese medicine (TCM) pulse conditions for distinguishing between patients with the coronary heart disease (CHD) and normal people by using the proposed classification approach based on Hilbert-Huang transform (HHT) and random forest. Methods. The energy and the sample entropy features were extracted by applying the HHT to TCM pulse by treating these pulse signals as time series. By using the random forest classifier, the extracted two types of features and their combination were, respectively, used as input data to establish classification model. Results. Statistical results showed that there were significant differences in the pulse energy and sample entropy between the CHD group and the normal group. Moreover, the energy features, sample entropy features, and their combination were inputted as pulse feature vectors; the corresponding average recognition rates were 84%, 76.35%, and 90.21%, respectively. Conclusion. The proposed approach could be appropriately used to analyze pulses of patients with CHD, which can lay a foundation for research on objective and quantitative criteria on disease diagnosis or Zheng differentiation. PMID:26180536

Analysis and Recognition of Traditional Chinese Medicine Pulse Based on the Hilbert-Huang Transform and Random Forest in Patients with Coronary Heart Disease.

PubMed

Guo, Rui; Wang, Yiqin; Yan, Hanxia; Yan, Jianjun; Yuan, Fengyin; Xu, Zhaoxia; Liu, Guoping; Xu, Wenjie

2015-01-01

Objective. This research provides objective and quantitative parameters of the traditional Chinese medicine (TCM) pulse conditions for distinguishing between patients with the coronary heart disease (CHD) and normal people by using the proposed classification approach based on Hilbert-Huang transform (HHT) and random forest. Methods. The energy and the sample entropy features were extracted by applying the HHT to TCM pulse by treating these pulse signals as time series. By using the random forest classifier, the extracted two types of features and their combination were, respectively, used as input data to establish classification model. Results. Statistical results showed that there were significant differences in the pulse energy and sample entropy between the CHD group and the normal group. Moreover, the energy features, sample entropy features, and their combination were inputted as pulse feature vectors; the corresponding average recognition rates were 84%, 76.35%, and 90.21%, respectively. Conclusion. The proposed approach could be appropriately used to analyze pulses of patients with CHD, which can lay a foundation for research on objective and quantitative criteria on disease diagnosis or Zheng differentiation.

Image search engine with selective filtering and feature-element-based classification

NASA Astrophysics Data System (ADS)

Li, Qing; Zhang, Yujin; Dai, Shengyang

2001-12-01

With the growth of Internet and storage capability in recent years, image has become a widespread information format in World Wide Web. However, it has become increasingly harder to search for images of interest, and effective image search engine for the WWW needs to be developed. We propose in this paper a selective filtering process and a novel approach for image classification based on feature element in the image search engine we developed for the WWW. First a selective filtering process is embedded in a general web crawler to filter out the meaningless images with GIF format. Two parameters that can be obtained easily are used in the filtering process. Our classification approach first extract feature elements from images instead of feature vectors. Compared with feature vectors, feature elements can better capture visual meanings of the image according to subjective perception of human beings. Different from traditional image classification method, our classification approach based on feature element doesn't calculate the distance between two vectors in the feature space, while trying to find associations between feature element and class attribute of the image. Experiments are presented to show the efficiency of the proposed approach.

Integrated Low-Rank-Based Discriminative Feature Learning for Recognition.

PubMed

Zhou, Pan; Lin, Zhouchen; Zhang, Chao

2016-05-01

Feature learning plays a central role in pattern recognition. In recent years, many representation-based feature learning methods have been proposed and have achieved great success in many applications. However, these methods perform feature learning and subsequent classification in two separate steps, which may not be optimal for recognition tasks. In this paper, we present a supervised low-rank-based approach for learning discriminative features. By integrating latent low-rank representation (LatLRR) with a ridge regression-based classifier, our approach combines feature learning with classification, so that the regulated classification error is minimized. In this way, the extracted features are more discriminative for the recognition tasks. Our approach benefits from a recent discovery on the closed-form solutions to noiseless LatLRR. When there is noise, a robust Principal Component Analysis (PCA)-based denoising step can be added as preprocessing. When the scale of a problem is large, we utilize a fast randomized algorithm to speed up the computation of robust PCA. Extensive experimental results demonstrate the effectiveness and robustness of our method.

Integrating Dimension Reduction and Out-of-Sample Extension in Automated Classification of Ex Vivo Human Patellar Cartilage on Phase Contrast X-Ray Computed Tomography

PubMed Central

Nagarajan, Mahesh B.; Coan, Paola; Huber, Markus B.; Diemoz, Paul C.; Wismüller, Axel

2015-01-01

Phase contrast X-ray computed tomography (PCI-CT) has been demonstrated as a novel imaging technique that can visualize human cartilage with high spatial resolution and soft tissue contrast. Different textural approaches have been previously investigated for characterizing chondrocyte organization on PCI-CT to enable classification of healthy and osteoarthritic cartilage. However, the large size of feature sets extracted in such studies motivates an investigation into algorithmic feature reduction for computing efficient feature representations without compromising their discriminatory power. For this purpose, geometrical feature sets derived from the scaling index method (SIM) were extracted from 1392 volumes of interest (VOI) annotated on PCI-CT images of ex vivo human patellar cartilage specimens. The extracted feature sets were subject to linear and non-linear dimension reduction techniques as well as feature selection based on evaluation of mutual information criteria. The reduced feature set was subsequently used in a machine learning task with support vector regression to classify VOIs as healthy or osteoarthritic; classification performance was evaluated using the area under the receiver-operating characteristic (ROC) curve (AUC). Our results show that the classification performance achieved by 9-D SIM-derived geometric feature sets (AUC: 0.96 ± 0.02) can be maintained with 2-D representations computed from both dimension reduction and feature selection (AUC values as high as 0.97 ± 0.02). Thus, such feature reduction techniques can offer a high degree of compaction to large feature sets extracted from PCI-CT images while maintaining their ability to characterize the underlying chondrocyte patterns. PMID:25710875

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.

Special object extraction from medieval books using superpixels and bag-of-features

NASA Astrophysics Data System (ADS)

Yang, Ying; Rushmeier, Holly

2017-01-01

We propose a method to extract special objects in images of medieval books, which generally represent, for example, figures and capital letters. Instead of working on the single-pixel level, we consider superpixels as the basic classification units for improved time efficiency. More specifically, we classify superpixels into different categories/objects by using a bag-of-features approach, where a superpixel category classifier is trained with the local features of the superpixels of the training images. With the trained classifier, we are able to assign the category labels to the superpixels of a historical document image under test. Finally, special objects can easily be identified and extracted after analyzing the categorization results. Experimental results demonstrate that, as compared to the state-of-the-art algorithms, our method provides comparable performance for some historical books but greatly outperforms them in terms of generality and computational time.

ECG based Myocardial Infarction detection using Hybrid Firefly Algorithm.

PubMed

Kora, Padmavathi

2017-12-01

Myocardial Infarction (MI) is one of the most frequent diseases, and can also cause demise, disability and monetary loss in patients who suffer from cardiovascular disorder. Diagnostic methods of this ailment by physicians are typically invasive, even though they do not fulfill the required detection accuracy. Recent feature extraction methods, for example, Auto Regressive (AR) modelling; Magnitude Squared Coherence (MSC); Wavelet Coherence (WTC) using Physionet database, yielded a collection of huge feature set. A large number of these features may be inconsequential containing some excess and non-discriminative components that present excess burden in computation and loss of execution performance. So Hybrid Firefly and Particle Swarm Optimization (FFPSO) is directly used to optimise the raw ECG signal instead of extracting features using the above feature extraction techniques. Provided results in this paper show that, for the detection of MI class, the FFPSO algorithm with ANN gives 99.3% accuracy, sensitivity of 99.97%, and specificity of 98.7% on MIT-BIH database by including NSR database also. The proposed approach has shown that methods that are based on the feature optimization of the ECG signals are the perfect to diagnosis the condition of the heart patients. Copyright © 2017 Elsevier B.V. All rights reserved.

A new feature extraction method and classification of early stage Parkinsonian rats with and without DBS treatment.

PubMed

Iravani, B; Towhidkhah, F; Roghani, M

2014-12-01

Parkinson Disease (PD) is one of the most common neural disorders worldwide. Different treatments such as medication and deep brain stimulation (DBS) have been proposed to minimize and control Parkinson's symptoms. DBS has been recognized as an effective approach to decrease most movement disorders of PD. In this study, a new method is proposed for feature extraction and separation of treated and untreated Parkinsonan rats. For this purpose, unilateral intrastriatal 6-hydroxydopamine (6-OHDA, 12.5 μg/5 μl of saline-ascorbate)-lesioned rats were treated with DBS. We performed a behavioral experiment and video tracked traveled trajectories of rats. Then, we investigated the effect of deep brain stimulation of subthalamus nucleus on their behavioral movements. Time, frequency and chaotic features of traveled trajectories were extracted. These features provide the ability to quantify the behavioral movements of Parkinsonian rats. The results showed that the traveled trajectories of untreated were more convoluted with the different time/frequency response. Compared to the traditional features used before to quantify the animals' behavior, the new features improved classification accuracy up to 80 % for untreated and treated rats.

Intelligent services for discovery of complex geospatial features from remote sensing imagery

NASA Astrophysics Data System (ADS)

Yue, Peng; Di, Liping; Wei, Yaxing; Han, Weiguo

2013-09-01

Remote sensing imagery has been commonly used by intelligence analysts to discover geospatial features, including complex ones. The overwhelming volume of routine image acquisition requires automated methods or systems for feature discovery instead of manual image interpretation. The methods of extraction of elementary ground features such as buildings and roads from remote sensing imagery have been studied extensively. The discovery of complex geospatial features, however, is still rather understudied. A complex feature, such as a Weapon of Mass Destruction (WMD) proliferation facility, is spatially composed of elementary features (e.g., buildings for hosting fuel concentration machines, cooling towers, transportation roads, and fences). Such spatial semantics, together with thematic semantics of feature types, can be used to discover complex geospatial features. This paper proposes a workflow-based approach for discovery of complex geospatial features that uses geospatial semantics and services. The elementary features extracted from imagery are archived in distributed Web Feature Services (WFSs) and discoverable from a catalogue service. Using spatial semantics among elementary features and thematic semantics among feature types, workflow-based service chains can be constructed to locate semantically-related complex features in imagery. The workflows are reusable and can provide on-demand discovery of complex features in a distributed environment.

Breast MRI radiogenomics: Current status and research implications.

PubMed

Grimm, Lars J

2016-06-01

Breast magnetic resonance imaging (MRI) radiogenomics is an emerging area of research that has the potential to directly influence clinical practice. Clinical MRI scanners today are capable of providing excellent temporal and spatial resolution, which allows extraction of numerous imaging features via human extraction approaches or complex computer vision algorithms. Meanwhile, advances in breast cancer genetics research has resulted in the identification of promising genes associated with cancer outcomes. In addition, validated genomic signatures have been developed that allow categorization of breast cancers into distinct molecular subtypes as well as predict the risk of cancer recurrence and response to therapy. Current radiogenomics research has been directed towards exploratory analysis of individual genes, understanding tumor biology, and developing imaging surrogates to genetic analysis with the long-term goal of developing a meaningful tool for clinical care. The background of breast MRI radiogenomics research, image feature extraction techniques, approaches to radiogenomics research, and promising areas of investigation are reviewed. J. Magn. Reson. Imaging 2016;43:1269-1278. © 2015 Wiley Periodicals, Inc.

Shadow Areas Robust Matching Among Image Sequence in Planetary Landing

NASA Astrophysics Data System (ADS)

Ruoyan, Wei; Xiaogang, Ruan; Naigong, Yu; Xiaoqing, Zhu; Jia, Lin

2017-01-01

In this paper, an approach for robust matching shadow areas in autonomous visual navigation and planetary landing is proposed. The approach begins with detecting shadow areas, which are extracted by Maximally Stable Extremal Regions (MSER). Then, an affine normalization algorithm is applied to normalize the areas. Thirdly, a descriptor called Multiple Angles-SIFT (MA-SIFT) that coming from SIFT is proposed, the descriptor can extract more features of an area. Finally, for eliminating the influence of outliers, a method of improved RANSAC based on Skinner Operation Condition is proposed to extract inliers. At last, series of experiments are conducted to test the performance of the approach this paper proposed, the results show that the approach can maintain the matching accuracy at a high level even the differences among the images are obvious with no attitude measurements supplied.

Improving the automated detection of refugee/IDP dwellings using the multispectral bands of the WorldView-2 satellite

NASA Astrophysics Data System (ADS)

Kemper, Thomas; Gueguen, Lionel; Soille, Pierre

2012-06-01

The enumeration of the population remains a critical task in the management of refugee/IDP camps. Analysis of very high spatial resolution satellite data proofed to be an efficient and secure approach for the estimation of dwellings and the monitoring of the camp over time. In this paper we propose a new methodology for the automated extraction of features based on differential morphological decomposition segmentation for feature extraction and interactive training sample selection from the max-tree and min-tree structures. This feature extraction methodology is tested on a WorldView-2 scene of an IDP camp in Darfur Sudan. Special emphasis is given to the additional available bands of the WorldView-2 sensor. The results obtained show that the interactive image information tool is performing very well by tuning the feature extraction to the local conditions. The analysis of different spectral subsets shows that it is possible to obtain good results already with an RGB combination, but by increasing the number of spectral bands the detection of dwellings becomes more accurate. Best results were obtained using all eight bands of WorldView-2 satellite.

Face antispoofing based on frame difference and multilevel representation

NASA Astrophysics Data System (ADS)

Benlamoudi, Azeddine; Aiadi, Kamal Eddine; Ouafi, Abdelkrim; Samai, Djamel; Oussalah, Mourad

2017-07-01

Due to advances in technology, today's biometric systems become vulnerable to spoof attacks made by fake faces. These attacks occur when an intruder attempts to fool an established face-based recognition system by presenting a fake face (e.g., print photo or replay attacks) in front of the camera instead of the intruder's genuine face. For this purpose, face antispoofing has become a hot topic in face analysis literature, where several applications with antispoofing task have emerged recently. We propose a solution for distinguishing between real faces and fake ones. Our approach is based on extracting features from the difference between successive frames instead of individual frames. We also used a multilevel representation that divides the frame difference into multiple multiblocks. Different texture descriptors (local binary patterns, local phase quantization, and binarized statistical image features) have then been applied to each block. After the feature extraction step, a Fisher score is applied to sort the features in ascending order according to the associated weights. Finally, a support vector machine is used to differentiate between real and fake faces. We tested our approach on three publicly available databases: CASIA Face Antispoofing database, Replay-Attack database, and MSU Mobile Face Spoofing database. The proposed approach outperforms the other state-of-the-art methods in different media and quality metrics.

Fusion of shallow and deep features for classification of high-resolution remote sensing images

NASA Astrophysics Data System (ADS)

Gao, Lang; Tian, Tian; Sun, Xiao; Li, Hang

2018-02-01

Effective spectral and spatial pixel description plays a significant role for the classification of high resolution remote sensing images. Current approaches of pixel-based feature extraction are of two main kinds: one includes the widelyused principal component analysis (PCA) and gray level co-occurrence matrix (GLCM) as the representative of the shallow spectral and shape features, and the other refers to the deep learning-based methods which employ deep neural networks and have made great promotion on classification accuracy. However, the former traditional features are insufficient to depict complex distribution of high resolution images, while the deep features demand plenty of samples to train the network otherwise over fitting easily occurs if only limited samples are involved in the training. In view of the above, we propose a GLCM-based convolution neural network (CNN) approach to extract features and implement classification for high resolution remote sensing images. The employment of GLCM is able to represent the original images and eliminate redundant information and undesired noises. Meanwhile, taking shallow features as the input of deep network will contribute to a better guidance and interpretability. In consideration of the amount of samples, some strategies such as L2 regularization and dropout methods are used to prevent over-fitting. The fine-tuning strategy is also used in our study to reduce training time and further enhance the generalization performance of the network. Experiments with popular data sets such as PaviaU data validate that our proposed method leads to a performance improvement compared to individual involved approaches.

Deep convolutional neural networks for classifying GPR B-scans

NASA Astrophysics Data System (ADS)

Besaw, Lance E.; Stimac, Philip J.

2015-05-01

Symmetric and asymmetric buried explosive hazards (BEHs) present real, persistent, deadly threats on the modern battlefield. Current approaches to mitigate these threats rely on highly trained operatives to reliably detect BEHs with reasonable false alarm rates using handheld Ground Penetrating Radar (GPR) and metal detectors. As computers become smaller, faster and more efficient, there exists greater potential for automated threat detection based on state-of-the-art machine learning approaches, reducing the burden on the field operatives. Recent advancements in machine learning, specifically deep learning artificial neural networks, have led to significantly improved performance in pattern recognition tasks, such as object classification in digital images. Deep convolutional neural networks (CNNs) are used in this work to extract meaningful signatures from 2-dimensional (2-D) GPR B-scans and classify threats. The CNNs skip the traditional "feature engineering" step often associated with machine learning, and instead learn the feature representations directly from the 2-D data. A multi-antennae, handheld GPR with centimeter-accurate positioning data was used to collect shallow subsurface data over prepared lanes containing a wide range of BEHs. Several heuristics were used to prevent over-training, including cross validation, network weight regularization, and "dropout." Our results show that CNNs can extract meaningful features and accurately classify complex signatures contained in GPR B-scans, complementing existing GPR feature extraction and classification techniques.

Epileptic seizure detection in EEG signal using machine learning techniques.

PubMed

Jaiswal, Abeg Kumar; Banka, Haider

2018-03-01

Epilepsy is a well-known nervous system disorder characterized by seizures. Electroencephalograms (EEGs), which capture brain neural activity, can detect epilepsy. Traditional methods for analyzing an EEG signal for epileptic seizure detection are time-consuming. Recently, several automated seizure detection frameworks using machine learning technique have been proposed to replace these traditional methods. The two basic steps involved in machine learning are feature extraction and classification. Feature extraction reduces the input pattern space by keeping informative features and the classifier assigns the appropriate class label. In this paper, we propose two effective approaches involving subpattern based PCA (SpPCA) and cross-subpattern correlation-based PCA (SubXPCA) with Support Vector Machine (SVM) for automated seizure detection in EEG signals. Feature extraction was performed using SpPCA and SubXPCA. Both techniques explore the subpattern correlation of EEG signals, which helps in decision-making process. SVM is used for classification of seizure and non-seizure EEG signals. The SVM was trained with radial basis kernel. All the experiments have been carried out on the benchmark epilepsy EEG dataset. The entire dataset consists of 500 EEG signals recorded under different scenarios. Seven different experimental cases for classification have been conducted. The classification accuracy was evaluated using tenfold cross validation. The classification results of the proposed approaches have been compared with the results of some of existing techniques proposed in the literature to establish the claim.

Hypotheses generation as supervised link discovery with automated class labeling on large-scale biomedical concept networks

PubMed Central

2012-01-01

Computational approaches to generate hypotheses from biomedical literature have been studied intensively in recent years. Nevertheless, it still remains a challenge to automatically discover novel, cross-silo biomedical hypotheses from large-scale literature repositories. In order to address this challenge, we first model a biomedical literature repository as a comprehensive network of biomedical concepts and formulate hypotheses generation as a process of link discovery on the concept network. We extract the relevant information from the biomedical literature corpus and generate a concept network and concept-author map on a cluster using Map-Reduce frame-work. We extract a set of heterogeneous features such as random walk based features, neighborhood features and common author features. The potential number of links to consider for the possibility of link discovery is large in our concept network and to address the scalability problem, the features from a concept network are extracted using a cluster with Map-Reduce framework. We further model link discovery as a classification problem carried out on a training data set automatically extracted from two network snapshots taken in two consecutive time duration. A set of heterogeneous features, which cover both topological and semantic features derived from the concept network, have been studied with respect to their impacts on the accuracy of the proposed supervised link discovery process. A case study of hypotheses generation based on the proposed method has been presented in the paper. PMID:22759614

A fuzzy-based data transformation for feature extraction to increase classification performance with small medical data sets.

PubMed

Li, Der-Chiang; Liu, Chiao-Wen; Hu, Susan C

2011-05-01

Medical data sets are usually small and have very high dimensionality. Too many attributes will make the analysis less efficient and will not necessarily increase accuracy, while too few data will decrease the modeling stability. Consequently, the main objective of this study is to extract the optimal subset of features to increase analytical performance when the data set is small. This paper proposes a fuzzy-based non-linear transformation method to extend classification related information from the original data attribute values for a small data set. Based on the new transformed data set, this study applies principal component analysis (PCA) to extract the optimal subset of features. Finally, we use the transformed data with these optimal features as the input data for a learning tool, a support vector machine (SVM). Six medical data sets: Pima Indians' diabetes, Wisconsin diagnostic breast cancer, Parkinson disease, echocardiogram, BUPA liver disorders dataset, and bladder cancer cases in Taiwan, are employed to illustrate the approach presented in this paper. This research uses the t-test to evaluate the classification accuracy for a single data set; and uses the Friedman test to show the proposed method is better than other methods over the multiple data sets. The experiment results indicate that the proposed method has better classification performance than either PCA or kernel principal component analysis (KPCA) when the data set is small, and suggest creating new purpose-related information to improve the analysis performance. This paper has shown that feature extraction is important as a function of feature selection for efficient data analysis. When the data set is small, using the fuzzy-based transformation method presented in this work to increase the information available produces better results than the PCA and KPCA approaches. Copyright © 2011 Elsevier B.V. All rights reserved.

Rotation, scale, and translation invariant pattern recognition using feature extraction

NASA Astrophysics Data System (ADS)

Prevost, Donald; Doucet, Michel; Bergeron, Alain; Veilleux, Luc; Chevrette, Paul C.; Gingras, Denis J.

1997-03-01

A rotation, scale and translation invariant pattern recognition technique is proposed.It is based on Fourier- Mellin Descriptors (FMD). Each FMD is taken as an independent feature of the object, and a set of those features forms a signature. FMDs are naturally rotation invariant. Translation invariance is achieved through pre- processing. A proper normalization of the FMDs gives the scale invariance property. This approach offers the double advantage of providing invariant signatures of the objects, and a dramatic reduction of the amount of data to process. The compressed invariant feature signature is next presented to a multi-layered perceptron neural network. This final step provides some robustness to the classification of the signatures, enabling good recognition behavior under anamorphically scaled distortion. We also present an original feature extraction technique, adapted to optical calculation of the FMDs. A prototype optical set-up was built, and experimental results are presented.

On the application of neural networks to the classification of phase modulated waveforms

NASA Astrophysics Data System (ADS)

Buchenroth, Anthony; Yim, Joong Gon; Nowak, Michael; Chakravarthy, Vasu

2017-04-01

Accurate classification of phase modulated radar waveforms is a well-known problem in spectrum sensing. Identification of such waveforms aids situational awareness enabling radar and communications spectrum sharing. While various feature extraction and engineering approaches have sought to address this problem, the use of a machine learning algorithm that best utilizes these features is becomes foremost. In this effort, a comparison of a standard shallow and a deep learning approach are explored. Experiments provide insights into classifier architecture, training procedure, and performance.

Writers Identification Based on Multiple Windows Features Mining

NASA Astrophysics Data System (ADS)

Fadhil, Murad Saadi; Alkawaz, Mohammed Hazim; Rehman, Amjad; Saba, Tanzila

2016-03-01

Now a days, writer identification is at high demand to identify the original writer of the script at high accuracy. The one of the main challenge in writer identification is how to extract the discriminative features of different authors' scripts to classify precisely. In this paper, the adaptive division method on the offline Latin script has been implemented using several variant window sizes. Fragments of binarized text a set of features are extracted and classified into clusters in the form of groups or classes. Finally, the proposed approach in this paper has been tested on various parameters in terms of text division and window sizes. It is observed that selection of the right window size yields a well positioned window division. The proposed approach is tested on IAM standard dataset (IAM, Institut für Informatik und angewandte Mathematik, University of Bern, Bern, Switzerland) that is a constraint free script database. Finally, achieved results are compared with several techniques reported in the literature.

Pavement crack detection combining non-negative feature with fast LoG in complex scene

NASA Astrophysics Data System (ADS)

Wang, Wanli; Zhang, Xiuhua; Hong, Hanyu

2015-12-01

Pavement crack detection is affected by much interference in the realistic situation, such as the shadow, road sign, oil stain, salt and pepper noise etc. Due to these unfavorable factors, the exist crack detection methods are difficult to distinguish the crack from background correctly. How to extract crack information effectively is the key problem to the road crack detection system. To solve this problem, a novel method for pavement crack detection based on combining non-negative feature with fast LoG is proposed. The two key novelties and benefits of this new approach are that 1) using image pixel gray value compensation to acquisit uniform image, and 2) combining non-negative feature with fast LoG to extract crack information. The image preprocessing results demonstrate that the method is indeed able to homogenize the crack image with more accurately compared to existing methods. A large number of experimental results demonstrate the proposed approach can detect the crack regions more correctly compared with traditional methods.

Interpretation of fingerprint image quality features extracted by self-organizing maps

NASA Astrophysics Data System (ADS)

Danov, Ivan; Olsen, Martin A.; Busch, Christoph

2014-05-01

Accurate prediction of fingerprint quality is of significant importance to any fingerprint-based biometric system. Ensuring high quality samples for both probe and reference can substantially improve the system's performance by lowering false non-matches, thus allowing finer adjustment of the decision threshold of the biometric system. Furthermore, the increasing usage of biometrics in mobile contexts demands development of lightweight methods for operational environment. A novel two-tier computationally efficient approach was recently proposed based on modelling block-wise fingerprint image data using Self-Organizing Map (SOM) to extract specific ridge pattern features, which are then used as an input to a Random Forests (RF) classifier trained to predict the quality score of a propagated sample. This paper conducts an investigative comparative analysis on a publicly available dataset for the improvement of the two-tier approach by proposing additionally three feature interpretation methods, based respectively on SOM, Generative Topographic Mapping and RF. The analysis shows that two of the proposed methods produce promising results on the given dataset.

Tensor-driven extraction of developmental features from varying paediatric EEG datasets.

PubMed

Kinney-Lang, Eli; Spyrou, Loukianos; Ebied, Ahmed; Chin, Richard Fm; Escudero, Javier

2018-05-21

Constant changes in developing children's brains can pose a challenge in EEG dependant technologies. Advancing signal processing methods to identify developmental differences in paediatric populations could help improve function and usability of such technologies. Taking advantage of the multi-dimensional structure of EEG data through tensor analysis may offer a framework for extracting relevant developmental features of paediatric datasets. A proof of concept is demonstrated through identifying latent developmental features in resting-state EEG. Approach. Three paediatric datasets (n = 50, 17, 44) were analyzed using a two-step constrained parallel factor (PARAFAC) tensor decomposition. Subject age was used as a proxy measure of development. Classification used support vector machines (SVM) to test if PARAFAC identified features could predict subject age. The results were cross-validated within each dataset. Classification analysis was complemented by visualization of the high-dimensional feature structures using t-distributed Stochastic Neighbour Embedding (t-SNE) maps. Main Results. Development-related features were successfully identified for the developmental conditions of each dataset. SVM classification showed the identified features could accurately predict subject at a significant level above chance for both healthy and impaired populations. t-SNE maps revealed suitable tensor factorization was key in extracting the developmental features. Significance. The described methods are a promising tool for identifying latent developmental features occurring throughout childhood EEG. © 2018 IOP Publishing Ltd.

Automatic exudate detection by fusing multiple active contours and regionwise classification.

PubMed

Harangi, Balazs; Hajdu, Andras

2014-11-01

In this paper, we propose a method for the automatic detection of exudates in digital fundus images. Our approach can be divided into three stages: candidate extraction, precise contour segmentation and the labeling of candidates as true or false exudates. For candidate detection, we borrow a grayscale morphology-based method to identify possible regions containing these bright lesions. Then, to extract the precise boundary of the candidates, we introduce a complex active contour-based method. Namely, to increase the accuracy of segmentation, we extract additional possible contours by taking advantage of the diverse behavior of different pre-processing methods. After selecting an appropriate combination of the extracted contours, a region-wise classifier is applied to remove the false exudate candidates. For this task, we consider several region-based features, and extract an appropriate feature subset to train a Naïve-Bayes classifier optimized further by an adaptive boosting technique. Regarding experimental studies, the method was tested on publicly available databases both to measure the accuracy of the segmentation of exudate regions and to recognize their presence at image-level. In a proper quantitative evaluation on publicly available datasets the proposed approach outperformed several state-of-the-art exudate detector algorithms. Copyright © 2014 Elsevier Ltd. All rights reserved.

Feature extraction and classification algorithms for high dimensional data

NASA Technical Reports Server (NTRS)

Lee, Chulhee; Landgrebe, David

1993-01-01

Feature extraction and classification algorithms for high dimensional data are investigated. Developments with regard to sensors for Earth observation are moving in the direction of providing much higher dimensional multispectral imagery than is now possible. In analyzing such high dimensional data, processing time becomes an important factor. With large increases in dimensionality and the number of classes, processing time will increase significantly. To address this problem, a multistage classification scheme is proposed which reduces the processing time substantially by eliminating unlikely classes from further consideration at each stage. Several truncation criteria are developed and the relationship between thresholds and the error caused by the truncation is investigated. Next an approach to feature extraction for classification is proposed based directly on the decision boundaries. It is shown that all the features needed for classification can be extracted from decision boundaries. A characteristic of the proposed method arises by noting that only a portion of the decision boundary is effective in discriminating between classes, and the concept of the effective decision boundary is introduced. The proposed feature extraction algorithm has several desirable properties: it predicts the minimum number of features necessary to achieve the same classification accuracy as in the original space for a given pattern recognition problem; and it finds the necessary feature vectors. The proposed algorithm does not deteriorate under the circumstances of equal means or equal covariances as some previous algorithms do. In addition, the decision boundary feature extraction algorithm can be used both for parametric and non-parametric classifiers. Finally, some problems encountered in analyzing high dimensional data are studied and possible solutions are proposed. First, the increased importance of the second order statistics in analyzing high dimensional data is recognized. By investigating the characteristics of high dimensional data, the reason why the second order statistics must be taken into account in high dimensional data is suggested. Recognizing the importance of the second order statistics, there is a need to represent the second order statistics. A method to visualize statistics using a color code is proposed. By representing statistics using color coding, one can easily extract and compare the first and the second statistics.

An Active Learning Framework for Hyperspectral Image Classification Using Hierarchical Segmentation

NASA Technical Reports Server (NTRS)

Zhang, Zhou; Pasolli, Edoardo; Crawford, Melba M.; Tilton, James C.

2015-01-01

Augmenting spectral data with spatial information for image classification has recently gained significant attention, as classification accuracy can often be improved by extracting spatial information from neighboring pixels. In this paper, we propose a new framework in which active learning (AL) and hierarchical segmentation (HSeg) are combined for spectral-spatial classification of hyperspectral images. The spatial information is extracted from a best segmentation obtained by pruning the HSeg tree using a new supervised strategy. The best segmentation is updated at each iteration of the AL process, thus taking advantage of informative labeled samples provided by the user. The proposed strategy incorporates spatial information in two ways: 1) concatenating the extracted spatial features and the original spectral features into a stacked vector and 2) extending the training set using a self-learning-based semi-supervised learning (SSL) approach. Finally, the two strategies are combined within an AL framework. The proposed framework is validated with two benchmark hyperspectral datasets. Higher classification accuracies are obtained by the proposed framework with respect to five other state-of-the-art spectral-spatial classification approaches. Moreover, the effectiveness of the proposed pruning strategy is also demonstrated relative to the approaches based on a fixed segmentation.

Kernel-Based Relevance Analysis with Enhanced Interpretability for Detection of Brain Activity Patterns

PubMed Central

Alvarez-Meza, Andres M.; Orozco-Gutierrez, Alvaro; Castellanos-Dominguez, German

2017-01-01

We introduce Enhanced Kernel-based Relevance Analysis (EKRA) that aims to support the automatic identification of brain activity patterns using electroencephalographic recordings. EKRA is a data-driven strategy that incorporates two kernel functions to take advantage of the available joint information, associating neural responses to a given stimulus condition. Regarding this, a Centered Kernel Alignment functional is adjusted to learning the linear projection that best discriminates the input feature set, optimizing the required free parameters automatically. Our approach is carried out in two scenarios: (i) feature selection by computing a relevance vector from extracted neural features to facilitating the physiological interpretation of a given brain activity task, and (ii) enhanced feature selection to perform an additional transformation of relevant features aiming to improve the overall identification accuracy. Accordingly, we provide an alternative feature relevance analysis strategy that allows improving the system performance while favoring the data interpretability. For the validation purpose, EKRA is tested in two well-known tasks of brain activity: motor imagery discrimination and epileptic seizure detection. The obtained results show that the EKRA approach estimates a relevant representation space extracted from the provided supervised information, emphasizing the salient input features. As a result, our proposal outperforms the state-of-the-art methods regarding brain activity discrimination accuracy with the benefit of enhanced physiological interpretation about the task at hand. PMID:29056897

Feature Extraction from Subband Brain Signals and Its Classification

NASA Astrophysics Data System (ADS)

Mukul, Manoj Kumar; Matsuno, Fumitoshi

This paper considers both the non-stationarity as well as independence/uncorrelated criteria along with the asymmetry ratio over the electroencephalogram (EEG) signals and proposes a hybrid approach of the signal preprocessing methods before the feature extraction. A filter bank approach of the discrete wavelet transform (DWT) is used to exploit the non-stationary characteristics of the EEG signals and it decomposes the raw EEG signals into the subbands of different center frequencies called as rhythm. A post processing of the selected subband by the AMUSE algorithm (a second order statistics based ICA/BSS algorithm) provides the separating matrix for each class of the movement imagery. In the subband domain the orthogonality as well as orthonormality criteria over the whitening matrix and separating matrix do not come respectively. The human brain has an asymmetrical structure. It has been observed that the ratio between the norms of the left and right class separating matrices should be different for better discrimination between these two classes. The alpha/beta band asymmetry ratio between the separating matrices of the left and right classes will provide the condition to select an appropriate multiplier. So we modify the estimated separating matrix by an appropriate multiplier in order to get the required asymmetry and extend the AMUSE algorithm in the subband domain. The desired subband is further subjected to the updated separating matrix to extract subband sub-components from each class. The extracted subband sub-components sources are further subjected to the feature extraction (power spectral density) step followed by the linear discriminant analysis (LDA).

Modeling the Pulse Signal by Wave-Shape Function and Analyzing by Synchrosqueezing Transform

PubMed Central

Wang, Chun-Li; Yang, Yueh-Lung; Wu, Wen-Hsiang; Tsai, Tung-Hu; Chang, Hen-Hong

2016-01-01

We apply the recently developed adaptive non-harmonic model based on the wave-shape function, as well as the time-frequency analysis tool called synchrosqueezing transform (SST) to model and analyze oscillatory physiological signals. To demonstrate how the model and algorithm work, we apply them to study the pulse wave signal. By extracting features called the spectral pulse signature, and based on functional regression, we characterize the hemodynamics from the radial pulse wave signals recorded by the sphygmomanometer. Analysis results suggest the potential of the proposed signal processing approach to extract health-related hemodynamics features. PMID:27304979

Modeling the Pulse Signal by Wave-Shape Function and Analyzing by Synchrosqueezing Transform.

PubMed

Wu, Hau-Tieng; Wu, Han-Kuei; Wang, Chun-Li; Yang, Yueh-Lung; Wu, Wen-Hsiang; Tsai, Tung-Hu; Chang, Hen-Hong

2016-01-01

We apply the recently developed adaptive non-harmonic model based on the wave-shape function, as well as the time-frequency analysis tool called synchrosqueezing transform (SST) to model and analyze oscillatory physiological signals. To demonstrate how the model and algorithm work, we apply them to study the pulse wave signal. By extracting features called the spectral pulse signature, and based on functional regression, we characterize the hemodynamics from the radial pulse wave signals recorded by the sphygmomanometer. Analysis results suggest the potential of the proposed signal processing approach to extract health-related hemodynamics features.

A biometric identification system based on eigenpalm and eigenfinger features.

PubMed

Ribaric, Slobodan; Fratric, Ivan

2005-11-01

This paper presents a multimodal biometric identification system based on the features of the human hand. We describe a new biometric approach to personal identification using eigenfinger and eigenpalm features, with fusion applied at the matching-score level. The identification process can be divided into the following phases: capturing the image; preprocessing; extracting and normalizing the palm and strip-like finger subimages; extracting the eigenpalm and eigenfinger features based on the K-L transform; matching and fusion; and, finally, a decision based on the (k, l)-NN classifier and thresholding. The system was tested on a database of 237 people (1,820 hand images). The experimental results showed the effectiveness of the system in terms of the recognition rate (100 percent), the equal error rate (EER = 0.58 percent), and the total error rate (TER = 0.72 percent).

Machine learning based sample extraction for automatic speech recognition using dialectal Assamese speech.

PubMed

Agarwalla, Swapna; Sarma, Kandarpa Kumar

2016-06-01

Automatic Speaker Recognition (ASR) and related issues are continuously evolving as inseparable elements of Human Computer Interaction (HCI). With assimilation of emerging concepts like big data and Internet of Things (IoT) as extended elements of HCI, ASR techniques are found to be passing through a paradigm shift. Oflate, learning based techniques have started to receive greater attention from research communities related to ASR owing to the fact that former possess natural ability to mimic biological behavior and that way aids ASR modeling and processing. The current learning based ASR techniques are found to be evolving further with incorporation of big data, IoT like concepts. Here, in this paper, we report certain approaches based on machine learning (ML) used for extraction of relevant samples from big data space and apply them for ASR using certain soft computing techniques for Assamese speech with dialectal variations. A class of ML techniques comprising of the basic Artificial Neural Network (ANN) in feedforward (FF) and Deep Neural Network (DNN) forms using raw speech, extracted features and frequency domain forms are considered. The Multi Layer Perceptron (MLP) is configured with inputs in several forms to learn class information obtained using clustering and manual labeling. DNNs are also used to extract specific sentence types. Initially, from a large storage, relevant samples are selected and assimilated. Next, a few conventional methods are used for feature extraction of a few selected types. The features comprise of both spectral and prosodic types. These are applied to Recurrent Neural Network (RNN) and Fully Focused Time Delay Neural Network (FFTDNN) structures to evaluate their performance in recognizing mood, dialect, speaker and gender variations in dialectal Assamese speech. The system is tested under several background noise conditions by considering the recognition rates (obtained using confusion matrices and manually) and computation time. It is found that the proposed ML based sentence extraction techniques and the composite feature set used with RNN as classifier outperform all other approaches. By using ANN in FF form as feature extractor, the performance of the system is evaluated and a comparison is made. Experimental results show that the application of big data samples has enhanced the learning of the ASR system. Further, the ANN based sample and feature extraction techniques are found to be efficient enough to enable application of ML techniques in big data aspects as part of ASR systems. Copyright © 2015 Elsevier Ltd. All rights reserved.

HoDOr: histogram of differential orientations for rigid landmark tracking in medical images

NASA Astrophysics Data System (ADS)

Tiwari, Abhishek; Patwardhan, Kedar Anil

2018-03-01

Feature extraction plays a pivotal role in pattern recognition and matching. An ideal feature should be invariant to image transformations such as translation, rotation, scaling, etc. In this work, we present a novel rotation-invariant feature, which is based on Histogram of Oriented Gradients (HOG). We compare performance of the proposed approach with the HOG feature on 2D phantom data, as well as 3D medical imaging data. We have used traditional histogram comparison measures such as Bhattacharyya distance and Normalized Correlation Coefficient (NCC) to assess efficacy of the proposed approach under effects of image rotation. In our experiments, the proposed feature performs 40%, 20%, and 28% better than the HOG feature on phantom (2D), Computed Tomography (CT-3D), and Ultrasound (US-3D) data for image matching, and landmark tracking tasks respectively.

Radial gradient and radial deviation radiomic features from pre-surgical CT scans are associated with survival among lung adenocarcinoma patients.

PubMed

Tunali, Ilke; Stringfield, Olya; Guvenis, Albert; Wang, Hua; Liu, Ying; Balagurunathan, Yoganand; Lambin, Philippe; Gillies, Robert J; Schabath, Matthew B

2017-11-10

The goal of this study was to extract features from radial deviation and radial gradient maps which were derived from thoracic CT scans of patients diagnosed with lung adenocarcinoma and assess whether these features are associated with overall survival. We used two independent cohorts from different institutions for training (n= 61) and test (n= 47) and focused our analyses on features that were non-redundant and highly reproducible. To reduce the number of features and covariates into a single parsimonious model, a backward elimination approach was applied. Out of 48 features that were extracted, 31 were eliminated because they were not reproducible or were redundant. We considered 17 features for statistical analysis and identified a final model containing the two most highly informative features that were associated with lung cancer survival. One of the two features, radial deviation outside-border separation standard deviation, was replicated in a test cohort exhibiting a statistically significant association with lung cancer survival (multivariable hazard ratio = 0.40; 95% confidence interval 0.17-0.97). Additionally, we explored the biological underpinnings of these features and found radial gradient and radial deviation image features were significantly associated with semantic radiological features.

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.

Improving the performance of lesion-based computer-aided detection schemes of breast masses using a case-based adaptive cueing method

NASA Astrophysics Data System (ADS)

Tan, Maxine; Aghaei, Faranak; Wang, Yunzhi; Qian, Wei; Zheng, Bin

2016-03-01

Current commercialized CAD schemes have high false-positive (FP) detection rates and also have high correlations in positive lesion detection with radiologists. Thus, we recently investigated a new approach to improve the efficacy of applying CAD to assist radiologists in reading and interpreting screening mammograms. Namely, we developed a new global feature based CAD approach/scheme that can cue the warning sign on the cases with high risk of being positive. In this study, we investigate the possibility of fusing global feature or case-based scores with the local or lesion-based CAD scores using an adaptive cueing method. We hypothesize that the information from the global feature extraction (features extracted from the whole breast regions) are different from and can provide supplementary information to the locally-extracted features (computed from the segmented lesion regions only). On a large and diverse full-field digital mammography (FFDM) testing dataset with 785 cases (347 negative and 438 cancer cases with masses only), we ran our lesion-based and case-based CAD schemes "as is" on the whole dataset. To assess the supplementary information provided by the global features, we used an adaptive cueing method to adaptively adjust the original CAD-generated detection scores (Sorg) of a detected suspicious mass region based on the computed case-based score (Scase) of the case associated with this detected region. Using the adaptive cueing method, better sensitivity results were obtained at lower FP rates (<= 1 FP per image). Namely, increases of sensitivities (in the FROC curves) of up to 6.7% and 8.2% were obtained for the ROI and Case-based results, respectively.

Convolutional Neural Network Based on Extreme Learning Machine for Maritime Ships Recognition in Infrared Images.

PubMed

Khellal, Atmane; Ma, Hongbin; Fei, Qing

2018-05-09

The success of Deep Learning models, notably convolutional neural networks (CNNs), makes them the favorable solution for object recognition systems in both visible and infrared domains. However, the lack of training data in the case of maritime ships research leads to poor performance due to the problem of overfitting. In addition, the back-propagation algorithm used to train CNN is very slow and requires tuning many hyperparameters. To overcome these weaknesses, we introduce a new approach fully based on Extreme Learning Machine (ELM) to learn useful CNN features and perform a fast and accurate classification, which is suitable for infrared-based recognition systems. The proposed approach combines an ELM based learning algorithm to train CNN for discriminative features extraction and an ELM based ensemble for classification. The experimental results on VAIS dataset, which is the largest dataset of maritime ships, confirm that the proposed approach outperforms the state-of-the-art models in term of generalization performance and training speed. For instance, the proposed model is up to 950 times faster than the traditional back-propagation based training of convolutional neural networks, primarily for low-level features extraction.

Development of Vision Based Multiview Gait Recognition System with MMUGait Database

PubMed Central

Ng, Hu; Tan, Wooi-Haw; Tong, Hau-Lee

2014-01-01

This paper describes the acquisition setup and development of a new gait database, MMUGait. This database consists of 82 subjects walking under normal condition and 19 subjects walking with 11 covariate factors, which were captured under two views. This paper also proposes a multiview model-based gait recognition system with joint detection approach that performs well under different walking trajectories and covariate factors, which include self-occluded or external occluded silhouettes. In the proposed system, the process begins by enhancing the human silhouette to remove the artifacts. Next, the width and height of the body are obtained. Subsequently, the joint angular trajectories are determined once the body joints are automatically detected. Lastly, crotch height and step-size of the walking subject are determined. The extracted features are smoothened by Gaussian filter to eliminate the effect of outliers. The extracted features are normalized with linear scaling, which is followed by feature selection prior to the classification process. The classification experiments carried out on MMUGait database were benchmarked against the SOTON Small DB from University of Southampton. Results showed correct classification rate above 90% for all the databases. The proposed approach is found to outperform other approaches on SOTON Small DB in most cases. PMID:25143972

Image Retrieval using Integrated Features of Binary Wavelet Transform

NASA Astrophysics Data System (ADS)

Agarwal, Megha; Maheshwari, R. P.

2011-12-01

In this paper a new approach for image retrieval is proposed with the application of binary wavelet transform. This new approach facilitates the feature calculation with the integration of histogram and correlogram features extracted from binary wavelet subbands. Experiments are performed to evaluate and compare the performance of proposed method with the published literature. It is verified that average precision and average recall of proposed method (69.19%, 41.78%) is significantly improved compared to optimal quantized wavelet correlogram (OQWC) [6] (64.3%, 38.00%) and Gabor wavelet correlogram (GWC) [10] (64.1%, 40.6%). All the experiments are performed on Corel 1000 natural image database [20].

Multiscale quantification of tissue spiculation and distortion for detection of architectural distortion and spiculated mass in mammography

NASA Astrophysics Data System (ADS)

Lao, Zhiqiang; Zheng, Xin

2011-03-01

This paper proposes a multiscale method to quantify tissue spiculation and distortion in mammography CAD systems that aims at improving the sensitivity in detecting architectural distortion and spiculated mass. This approach addresses the difficulty of predetermining the neighborhood size for feature extraction in characterizing lesions demonstrating spiculated mass/architectural distortion that may appear in different sizes. The quantification is based on the recognition of tissue spiculation and distortion pattern using multiscale first-order phase portrait model in texture orientation field generated by Gabor filter bank. A feature map is generated based on the multiscale quantification for each mammogram and two features are then extracted from the feature map. These two features will be combined with other mass features to provide enhanced discriminate ability in detecting lesions demonstrating spiculated mass and architectural distortion. The efficiency and efficacy of the proposed method are demonstrated with results obtained by applying the method to over 500 cancer cases and over 1000 normal cases.

Automated diagnosis of coronary artery disease (CAD) patients using optimized SVM.

PubMed

Davari Dolatabadi, Azam; Khadem, Siamak Esmael Zadeh; Asl, Babak Mohammadzadeh

2017-01-01

Currently Coronary Artery Disease (CAD) is one of the most prevalent diseases, and also can lead to death, disability and economic loss in patients who suffer from cardiovascular disease. Diagnostic procedures of this disease by medical teams are typically invasive, although they do not satisfy the required accuracy. In this study, we have proposed a methodology for the automatic diagnosis of normal and Coronary Artery Disease conditions using Heart Rate Variability (HRV) signal extracted from electrocardiogram (ECG). The features are extracted from HRV signal in time, frequency and nonlinear domains. The Principal Component Analysis (PCA) is applied to reduce the dimension of the extracted features in order to reduce computational complexity and to reveal the hidden information underlaid in the data. Finally, Support Vector Machine (SVM) classifier has been utilized to classify two classes of data using the extracted distinguishing features. In this paper, parameters of the SVM have been optimized in order to improve the accuracy. Provided reports in this paper indicate that the detection of CAD class from normal class using the proposed algorithm was performed with accuracy of 99.2%, sensitivity of 98.43%, and specificity of 100%. This study has shown that methods which are based on the feature extraction of the biomedical signals are an appropriate approach to predict the health situation of the patients. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

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.

SU-F-R-52: A Comparison of the Performance of Radiomic Features From Free Breathing and 4DCT Scans in Predicting Disease Recurrence in Lung Cancer SBRT Patients

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

Huynh, E; Coroller, T; Narayan, V

Purpose: There is a clinical need to identify patients who are at highest risk of recurrence after being treated with stereotactic body radiation therapy (SBRT). Radiomics offers a non-invasive approach by extracting quantitative features from medical images based on tumor phenotype that is predictive of an outcome. Lung cancer patients treated with SBRT routinely undergo free breathing (FB image) and 4DCT (average intensity projection (AIP) image) scans for treatment planning to account for organ motion. The aim of the current study is to evaluate and compare the prognostic performance of radiomic features extracted from FB and AIP images in lungmore » cancer patients treated with SBRT to identify which image type would generate an optimal predictive model for recurrence. Methods: FB and AIP images of 113 Stage I-II NSCLC patients treated with SBRT were analysed. The prognostic performance of radiomic features for distant metastasis (DM) was evaluated by their concordance index (CI). Radiomic features were compared with conventional imaging metrics (e.g. diameter). All p-values were corrected for multiple testing using the false discovery rate. Results: All patients received SBRT and 20.4% of patients developed DM. From each image type (FB or AIP), nineteen radiomic features were selected based on stability and variance. Both image types had five common and fourteen different radiomic features. One FB (CI=0.70) and five AIP (CI range=0.65–0.68) radiomic features were significantly prognostic for DM (p<0.05). None of the conventional features derived from FB images (range CI=0.60–0.61) were significant but all AIP conventional features were (range CI=0.64–0.66). Conclusion: Features extracted from different types of CT scans have varying prognostic performances. AIP images contain more prognostic radiomic features for DM than FB images. These methods can provide personalized medicine approaches at low cost, as FB and AIP data are readily available within a large number of radiation oncology departments. R.M. had consulting interest with Amgen (ended in 2015).« less

Extraction and Classification of Human Gait Features

NASA Astrophysics Data System (ADS)

Ng, Hu; Tan, Wooi-Haw; Tong, Hau-Lee; Abdullah, Junaidi; Komiya, Ryoichi

In this paper, a new approach is proposed for extracting human gait features from a walking human based on the silhouette images. The approach consists of six stages: clearing the background noise of image by morphological opening; measuring of the width and height of the human silhouette; dividing the enhanced human silhouette into six body segments based on anatomical knowledge; applying morphological skeleton to obtain the body skeleton; applying Hough transform to obtain the joint angles from the body segment skeletons; and measuring the distance between the bottom of right leg and left leg from the body segment skeletons. The angles of joints, step-size together with the height and width of the human silhouette are collected and used for gait analysis. The experimental results have demonstrated that the proposed system is feasible and achieved satisfactory results.

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

Cavanaugh, J.E.; McQuarrie, A.D.; Shumway, R.H.

Conventional methods for discriminating between earthquakes and explosions at regional distances have concentrated on extracting specific features such as amplitude and spectral ratios from the waveforms of the P and S phases. We consider here an optimum nonparametric classification procedure derived from the classical approach to discriminating between two Gaussian processes with unequal spectra. Two robust variations based on the minimum discrimination information statistic and Renyi's entropy are also considered. We compare the optimum classification procedure with various amplitude and spectral ratio discriminants and show that its performance is superior when applied to a small population of 8 land-based earthquakesmore » and 8 mining explosions recorded in Scandinavia. Several parametric characterizations of the notion of complexity based on modeling earthquakes and explosions as autoregressive or modulated autoregressive processes are also proposed and their performance compared with the nonparametric and feature extraction approaches.« less

Palmprint and Face Multi-Modal Biometric Recognition Based on SDA-GSVD and Its Kernelization

PubMed Central

Jing, Xiao-Yuan; Li, Sheng; Li, Wen-Qian; Yao, Yong-Fang; Lan, Chao; Lu, Jia-Sen; Yang, Jing-Yu

2012-01-01

When extracting discriminative features from multimodal data, current methods rarely concern themselves with the data distribution. In this paper, we present an assumption that is consistent with the viewpoint of discrimination, that is, a person's overall biometric data should be regarded as one class in the input space, and his different biometric data can form different Gaussians distributions, i.e., different subclasses. Hence, we propose a novel multimodal feature extraction and recognition approach based on subclass discriminant analysis (SDA). Specifically, one person's different bio-data are treated as different subclasses of one class, and a transformed space is calculated, where the difference among subclasses belonging to different persons is maximized, and the difference within each subclass is minimized. Then, the obtained multimodal features are used for classification. Two solutions are presented to overcome the singularity problem encountered in calculation, which are using PCA preprocessing, and employing the generalized singular value decomposition (GSVD) technique, respectively. Further, we provide nonlinear extensions of SDA based multimodal feature extraction, that is, the feature fusion based on KPCA-SDA and KSDA-GSVD. In KPCA-SDA, we first apply Kernel PCA on each single modal before performing SDA. While in KSDA-GSVD, we directly perform Kernel SDA to fuse multimodal data by applying GSVD to avoid the singular problem. For simplicity two typical types of biometric data are considered in this paper, i.e., palmprint data and face data. Compared with several representative multimodal biometrics recognition methods, experimental results show that our approaches outperform related multimodal recognition methods and KSDA-GSVD achieves the best recognition performance. PMID:22778600

Palmprint and face multi-modal biometric recognition based on SDA-GSVD and its kernelization.

PubMed

Jing, Xiao-Yuan; Li, Sheng; Li, Wen-Qian; Yao, Yong-Fang; Lan, Chao; Lu, Jia-Sen; Yang, Jing-Yu

2012-01-01

When extracting discriminative features from multimodal data, current methods rarely concern themselves with the data distribution. In this paper, we present an assumption that is consistent with the viewpoint of discrimination, that is, a person's overall biometric data should be regarded as one class in the input space, and his different biometric data can form different Gaussians distributions, i.e., different subclasses. Hence, we propose a novel multimodal feature extraction and recognition approach based on subclass discriminant analysis (SDA). Specifically, one person's different bio-data are treated as different subclasses of one class, and a transformed space is calculated, where the difference among subclasses belonging to different persons is maximized, and the difference within each subclass is minimized. Then, the obtained multimodal features are used for classification. Two solutions are presented to overcome the singularity problem encountered in calculation, which are using PCA preprocessing, and employing the generalized singular value decomposition (GSVD) technique, respectively. Further, we provide nonlinear extensions of SDA based multimodal feature extraction, that is, the feature fusion based on KPCA-SDA and KSDA-GSVD. In KPCA-SDA, we first apply Kernel PCA on each single modal before performing SDA. While in KSDA-GSVD, we directly perform Kernel SDA to fuse multimodal data by applying GSVD to avoid the singular problem. For simplicity two typical types of biometric data are considered in this paper, i.e., palmprint data and face data. Compared with several representative multimodal biometrics recognition methods, experimental results show that our approaches outperform related multimodal recognition methods and KSDA-GSVD achieves the best recognition performance.

Age and gender estimation using Region-SIFT and multi-layered SVM

NASA Astrophysics Data System (ADS)

Kim, Hyunduk; Lee, Sang-Heon; Sohn, Myoung-Kyu; Hwang, Byunghun

2018-04-01

In this paper, we propose an age and gender estimation framework using the region-SIFT feature and multi-layered SVM classifier. The suggested framework entails three processes. The first step is landmark based face alignment. The second step is the feature extraction step. In this step, we introduce the region-SIFT feature extraction method based on facial landmarks. First, we define sub-regions of the face. We then extract SIFT features from each sub-region. In order to reduce the dimensions of features we employ a Principal Component Analysis (PCA) and a Linear Discriminant Analysis (LDA). Finally, we classify age and gender using a multi-layered Support Vector Machines (SVM) for efficient classification. Rather than performing gender estimation and age estimation independently, the use of the multi-layered SVM can improve the classification rate by constructing a classifier that estimate the age according to gender. Moreover, we collect a dataset of face images, called by DGIST_C, from the internet. A performance evaluation of proposed method was performed with the FERET database, CACD database, and DGIST_C database. The experimental results demonstrate that the proposed approach classifies age and performs gender estimation very efficiently and accurately.

Feature extraction of micro-motion frequency and the maximum wobble angle in a small range of missile warhead based on micro-Doppler effect

NASA Astrophysics Data System (ADS)

Li, M.; Jiang, Y. S.

2014-11-01

Micro-Doppler effect is induced by the micro-motion dynamics of the radar target itself or any structure on the target. In this paper, a simplified cone-shaped model for ballistic missile warhead with micro-nutation is established, followed by the theoretical formula of micro-nutation is derived. It is confirmed that the theoretical results are identical to simulation results by using short-time Fourier transform. Then we propose a new method for nutation period extraction via signature maximum energy fitting based on empirical mode decomposition and short-time Fourier transform. The maximum wobble angle is also extracted by distance approximate approach in a small range of wobble angle, which is combined with the maximum likelihood estimation. By the simulation studies, it is shown that these two feature extraction methods are both valid even with low signal-to-noise ratio.

Configurational coupled cluster approach with applications to magnetic model systems

NASA Astrophysics Data System (ADS)

Wu, Siyuan; Nooijen, Marcel

2018-05-01

A general exponential, coupled cluster like, approach is discussed to extract an effective Hamiltonian in configurational space, as a sum of 1-body, 2-body up to n-body operators. The simplest two-body approach is illustrated by calculations on simple magnetic model systems. A key feature of the approach is that equations up to a certain rank do not depend on higher body cluster operators.

Tree species classification using within crown localization of waveform LiDAR attributes

NASA Astrophysics Data System (ADS)

Blomley, Rosmarie; Hovi, Aarne; Weinmann, Martin; Hinz, Stefan; Korpela, Ilkka; Jutzi, Boris

2017-11-01

Since forest planning is increasingly taking an ecological, diversity-oriented perspective into account, remote sensing technologies are becoming ever more important in assessing existing resources with reduced manual effort. While the light detection and ranging (LiDAR) technology provides a good basis for predictions of tree height and biomass, tree species identification based on this type of data is particularly challenging in structurally heterogeneous forests. In this paper, we analyse existing approaches with respect to the geometrical scale of feature extraction (whole tree, within crown partitions or within laser footprint) and conclude that currently features are always extracted separately from the different scales. Since multi-scale approaches however have proven successful in other applications, we aim to utilize the within-tree-crown distribution of within-footprint signal characteristics as additional features. To do so, a spin image algorithm, originally devised for the extraction of 3D surface features in object recognition, is adapted. This algorithm relies on spinning an image plane around a defined axis, e.g. the tree stem, collecting the number of LiDAR returns or mean values of returns attributes per pixel as respective values. Based on this representation, spin image features are extracted that comprise only those components of highest variability among a given set of library trees. The relative performance and the combined improvement of these spin image features with respect to non-spatial statistical metrics of the waveform (WF) attributes are evaluated for the tree species classification of Scots pine (Pinus sylvestris L.), Norway spruce (Picea abies (L.) Karst.) and Silver/Downy birch (Betula pendula Roth/Betula pubescens Ehrh.) in a boreal forest environment. This evaluation is performed for two WF LiDAR datasets that differ in footprint size, pulse density at ground, laser wavelength and pulse width. Furthermore, we evaluate the robustness of the proposed method with respect to internal parameters and tree size. The results reveal, that the consideration of the crown-internal distribution of within-footprint signal characteristics captured in spin image features improves the classification results in nearly all test cases.

Detecting modification of biomedical events using a deep parsing approach.

PubMed

Mackinlay, Andrew; Martinez, David; Baldwin, Timothy

2012-04-30

This work describes a system for identifying event mentions in bio-molecular research abstracts that are either speculative (e.g. analysis of IkappaBalpha phosphorylation, where it is not specified whether phosphorylation did or did not occur) or negated (e.g. inhibition of IkappaBalpha phosphorylation, where phosphorylation did not occur). The data comes from a standard dataset created for the BioNLP 2009 Shared Task. The system uses a machine-learning approach, where the features used for classification are a combination of shallow features derived from the words of the sentences and more complex features based on the semantic outputs produced by a deep parser. To detect event modification, we use a Maximum Entropy learner with features extracted from the data relative to the trigger words of the events. The shallow features are bag-of-words features based on a small sliding context window of 3-4 tokens on either side of the trigger word. The deep parser features are derived from parses produced by the English Resource Grammar and the RASP parser. The outputs of these parsers are converted into the Minimal Recursion Semantics formalism, and from this, we extract features motivated by linguistics and the data itself. All of these features are combined to create training or test data for the machine learning algorithm. Over the test data, our methods produce approximately a 4% absolute increase in F-score for detection of event modification compared to a baseline based only on the shallow bag-of-words features. Our results indicate that grammar-based techniques can enhance the accuracy of methods for detecting event modification.

Effects of band selection on endmember extraction for forestry applications

NASA Astrophysics Data System (ADS)

Karathanassi, Vassilia; Andreou, Charoula; Andronis, Vassilis; Kolokoussis, Polychronis

2014-10-01

In spectral unmixing theory, data reduction techniques play an important role as hyperspectral imagery contains an immense amount of data, posing many challenging problems such as data storage, computational efficiency, and the so called "curse of dimensionality". Feature extraction and feature selection are the two main approaches for dimensionality reduction. Feature extraction techniques are used for reducing the dimensionality of the hyperspectral data by applying transforms on hyperspectral data. Feature selection techniques retain the physical meaning of the data by selecting a set of bands from the input hyperspectral dataset, which mainly contain the information needed for spectral unmixing. Although feature selection techniques are well-known for their dimensionality reduction potentials they are rarely used in the unmixing process. The majority of the existing state-of-the-art dimensionality reduction methods set criteria to the spectral information, which is derived by the whole wavelength, in order to define the optimum spectral subspace. These criteria are not associated with any particular application but with the data statistics, such as correlation and entropy values. However, each application is associated with specific land c over materials, whose spectral characteristics present variations in specific wavelengths. In forestry for example, many applications focus on tree leaves, in which specific pigments such as chlorophyll, xanthophyll, etc. determine the wavelengths where tree species, diseases, etc., can be detected. For such applications, when the unmixing process is applied, the tree species, diseases, etc., are considered as the endmembers of interest. This paper focuses on investigating the effects of band selection on the endmember extraction by exploiting the information of the vegetation absorbance spectral zones. More precisely, it is explored whether endmember extraction can be optimized when specific sets of initial bands related to leaf spectral characteristics are selected. Experiments comprise application of well-known signal subspace estimation and endmember extraction methods on a hyperspectral imagery that presents a forest area. Evaluation of the extracted endmembers showed that more forest species can be extracted as endmembers using selected bands.

Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram.

PubMed

Truong, Nhan Duy; Nguyen, Anh Duy; Kuhlmann, Levin; Bonyadi, Mohammad Reza; Yang, Jiawei; Ippolito, Samuel; Kavehei, Omid

2018-05-07

Seizure prediction has attracted growing attention as one of the most challenging predictive data analysis efforts to improve the life of patients with drug-resistant epilepsy and tonic seizures. Many outstanding studies have reported great results in providing sensible indirect (warning systems) or direct (interactive neural stimulation) control over refractory seizures, some of which achieved high performance. However, to achieve high sensitivity and a low false prediction rate, many of these studies relied on handcraft feature extraction and/or tailored feature extraction, which is performed for each patient independently. This approach, however, is not generalizable, and requires significant modifications for each new patient within a new dataset. In this article, we apply convolutional neural networks to different intracranial and scalp electroencephalogram (EEG) datasets and propose a generalized retrospective and patient-specific seizure prediction method. We use the short-time Fourier transform on 30-s EEG windows to extract information in both the frequency domain and the time domain. The algorithm automatically generates optimized features for each patient to best classify preictal and interictal segments. The method can be applied to any other patient from any dataset without the need for manual feature extraction. The proposed approach achieves sensitivity of 81.4%, 81.2%, and 75% and a false prediction rate of 0.06/h, 0.16/h, and 0.21/h on the Freiburg Hospital intracranial EEG dataset, the Boston Children's Hospital-MIT scalp EEG dataset, and the American Epilepsy Society Seizure Prediction Challenge dataset, respectively. Our prediction method is also statistically better than an unspecific random predictor for most of the patients in all three datasets. Copyright © 2018 Elsevier Ltd. All rights reserved.

Bayesian decoding using unsorted spikes in the rat hippocampus

PubMed Central

Layton, Stuart P.; Chen, Zhe; Wilson, Matthew A.

2013-01-01

A fundamental task in neuroscience is to understand how neural ensembles represent information. Population decoding is a useful tool to extract information from neuronal populations based on the ensemble spiking activity. We propose a novel Bayesian decoding paradigm to decode unsorted spikes in the rat hippocampus. Our approach uses a direct mapping between spike waveform features and covariates of interest and avoids accumulation of spike sorting errors. Our decoding paradigm is nonparametric, encoding model-free for representing stimuli, and extracts information from all available spikes and their waveform features. We apply the proposed Bayesian decoding algorithm to a position reconstruction task for freely behaving rats based on tetrode recordings of rat hippocampal neuronal activity. Our detailed decoding analyses demonstrate that our approach is efficient and better utilizes the available information in the nonsortable hash than the standard sorting-based decoding algorithm. Our approach can be adapted to an online encoding/decoding framework for applications that require real-time decoding, such as brain-machine interfaces. PMID:24089403

Ranking support vector machine for multiple kernels output combination in protein-protein interaction extraction from biomedical literature.

PubMed

Yang, Zhihao; Lin, Yuan; Wu, Jiajin; Tang, Nan; Lin, Hongfei; Li, Yanpeng

2011-10-01

Knowledge about protein-protein interactions (PPIs) unveils the molecular mechanisms of biological processes. However, the volume and content of published biomedical literature on protein interactions is expanding rapidly, making it increasingly difficult for interaction database curators to detect and curate protein interaction information manually. We present a multiple kernel learning-based approach for automatic PPI extraction from biomedical literature. The approach combines the following kernels: feature-based, tree, and graph and combines their output with Ranking support vector machine (SVM). Experimental evaluations show that the features in individual kernels are complementary and the kernel combined with Ranking SVM achieves better performance than those of the individual kernels, equal weight combination and optimal weight combination. Our approach can achieve state-of-the-art performance with respect to the comparable evaluations, with 64.88% F-score and 88.02% AUC on the AImed corpus. Copyright © 2011 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Reinforcement Learning with Autonomous Small Unmanned Aerial Vehicles in Cluttered Environments

NASA Technical Reports Server (NTRS)

Tran, Loc; Cross, Charles; Montague, Gilbert; Motter, Mark; Neilan, James; Qualls, Garry; Rothhaar, Paul; Trujillo, Anna; Allen, B. Danette

2015-01-01

We present ongoing work in the Autonomy Incubator at NASA Langley Research Center (LaRC) exploring the efficacy of a data set aggregation approach to reinforcement learning for small unmanned aerial vehicle (sUAV) flight in dense and cluttered environments with reactive obstacle avoidance. The goal is to learn an autonomous flight model using training experiences from a human piloting a sUAV around static obstacles. The training approach uses video data from a forward-facing camera that records the human pilot's flight. Various computer vision based features are extracted from the video relating to edge and gradient information. The recorded human-controlled inputs are used to train an autonomous control model that correlates the extracted feature vector to a yaw command. As part of the reinforcement learning approach, the autonomous control model is iteratively updated with feedback from a human agent who corrects undesired model output. This data driven approach to autonomous obstacle avoidance is explored for simulated forest environments furthering autonomous flight under the tree canopy research. This enables flight in previously inaccessible environments which are of interest to NASA researchers in Earth and Atmospheric sciences.

HOTS: A Hierarchy of Event-Based Time-Surfaces for Pattern Recognition.

PubMed

Lagorce, Xavier; Orchard, Garrick; Galluppi, Francesco; Shi, Bertram E; Benosman, Ryad B

2017-07-01

This paper describes novel event-based spatio-temporal features called time-surfaces and how they can be used to create a hierarchical event-based pattern recognition architecture. Unlike existing hierarchical architectures for pattern recognition, the presented model relies on a time oriented approach to extract spatio-temporal features from the asynchronously acquired dynamics of a visual scene. These dynamics are acquired using biologically inspired frameless asynchronous event-driven vision sensors. Similarly to cortical structures, subsequent layers in our hierarchy extract increasingly abstract features using increasingly large spatio-temporal windows. The central concept is to use the rich temporal information provided by events to create contexts in the form of time-surfaces which represent the recent temporal activity within a local spatial neighborhood. We demonstrate that this concept can robustly be used at all stages of an event-based hierarchical model. First layer feature units operate on groups of pixels, while subsequent layer feature units operate on the output of lower level feature units. We report results on a previously published 36 class character recognition task and a four class canonical dynamic card pip task, achieving near 100 percent accuracy on each. We introduce a new seven class moving face recognition task, achieving 79 percent accuracy.This paper describes novel event-based spatio-temporal features called time-surfaces and how they can be used to create a hierarchical event-based pattern recognition architecture. Unlike existing hierarchical architectures for pattern recognition, the presented model relies on a time oriented approach to extract spatio-temporal features from the asynchronously acquired dynamics of a visual scene. These dynamics are acquired using biologically inspired frameless asynchronous event-driven vision sensors. Similarly to cortical structures, subsequent layers in our hierarchy extract increasingly abstract features using increasingly large spatio-temporal windows. The central concept is to use the rich temporal information provided by events to create contexts in the form of time-surfaces which represent the recent temporal activity within a local spatial neighborhood. We demonstrate that this concept can robustly be used at all stages of an event-based hierarchical model. First layer feature units operate on groups of pixels, while subsequent layer feature units operate on the output of lower level feature units. We report results on a previously published 36 class character recognition task and a four class canonical dynamic card pip task, achieving near 100 percent accuracy on each. We introduce a new seven class moving face recognition task, achieving 79 percent accuracy.

Machine vision extracted plant movement for early detection of plant water stress.

PubMed

Kacira, M; Ling, P P; Short, T H

2002-01-01

A methodology was established for early, non-contact, and quantitative detection of plant water stress with machine vision extracted plant features. Top-projected canopy area (TPCA) of the plants was extracted from plant images using image-processing techniques. Water stress induced plant movement was decoupled from plant diurnal movement and plant growth using coefficient of relative variation of TPCA (CRV[TPCA)] and was found to be an effective marker for water stress detection. Threshold value of CRV(TPCA) as an indicator of water stress was determined by a parametric approach. The effectiveness of the sensing technique was evaluated against the timing of stress detection by an operator. Results of this study suggested that plant water stress detection using projected canopy area based features of the plants was feasible.

Machine-assisted verification of latent fingerprints: first results for nondestructive contact-less optical acquisition techniques with a CWL sensor

NASA Astrophysics Data System (ADS)

Hildebrandt, Mario; Kiltz, Stefan; Krapyvskyy, Dmytro; Dittmann, Jana; Vielhauer, Claus; Leich, Marcus

2011-11-01

A machine-assisted analysis of traces from crime scenes might be possible with the advent of new high-resolution non-destructive contact-less acquisition techniques for latent fingerprints. This requires reliable techniques for the automatic extraction of fingerprint features from latent and exemplar fingerprints for matching purposes using pattern recognition approaches. Therefore, we evaluate the NIST Biometric Image Software for the feature extraction and verification of contact-lessly acquired latent fingerprints to determine potential error rates. Our exemplary test setup includes 30 latent fingerprints from 5 people in two test sets that are acquired from different surfaces using a chromatic white light sensor. The first test set includes 20 fingerprints on two different surfaces. It is used to determine the feature extraction performance. The second test set includes one latent fingerprint on 10 different surfaces and an exemplar fingerprint to determine the verification performance. This utilized sensing technique does not require a physical or chemical visibility enhancement of the fingerprint residue, thus the original trace remains unaltered for further investigations. No particular feature extraction and verification techniques have been applied to such data, yet. Hence, we see the need for appropriate algorithms that are suitable to support forensic investigations.

Spectral feature extraction of EEG signals and pattern recognition during mental tasks of 2-D cursor movements for BCI using SVM and ANN.

PubMed

Bascil, M Serdar; Tesneli, Ahmet Y; Temurtas, Feyzullah

2016-09-01

Brain computer interface (BCI) is a new communication way between man and machine. It identifies mental task patterns stored in electroencephalogram (EEG). So, it extracts brain electrical activities recorded by EEG and transforms them machine control commands. The main goal of BCI is to make available assistive environmental devices for paralyzed people such as computers and makes their life easier. This study deals with feature extraction and mental task pattern recognition on 2-D cursor control from EEG as offline analysis approach. The hemispherical power density changes are computed and compared on alpha-beta frequency bands with only mental imagination of cursor movements. First of all, power spectral density (PSD) features of EEG signals are extracted and high dimensional data reduced by principle component analysis (PCA) and independent component analysis (ICA) which are statistical algorithms. In the last stage, all features are classified with two types of support vector machine (SVM) which are linear and least squares (LS-SVM) and three different artificial neural network (ANN) structures which are learning vector quantization (LVQ), multilayer neural network (MLNN) and probabilistic neural network (PNN) and mental task patterns are successfully identified via k-fold cross validation technique.

Driving profile modeling and recognition based on soft computing approach.

PubMed

Wahab, Abdul; Quek, Chai; Tan, Chin Keong; Takeda, Kazuya

2009-04-01

Advancements in biometrics-based authentication have led to its increasing prominence and are being incorporated into everyday tasks. Existing vehicle security systems rely only on alarms or smart card as forms of protection. A biometric driver recognition system utilizing driving behaviors is a highly novel and personalized approach and could be incorporated into existing vehicle security system to form a multimodal identification system and offer a greater degree of multilevel protection. In this paper, detailed studies have been conducted to model individual driving behavior in order to identify features that may be efficiently and effectively used to profile each driver. Feature extraction techniques based on Gaussian mixture models (GMMs) are proposed and implemented. Features extracted from the accelerator and brake pedal pressure were then used as inputs to a fuzzy neural network (FNN) system to ascertain the identity of the driver. Two fuzzy neural networks, namely, the evolving fuzzy neural network (EFuNN) and the adaptive network-based fuzzy inference system (ANFIS), are used to demonstrate the viability of the two proposed feature extraction techniques. The performances were compared against an artificial neural network (NN) implementation using the multilayer perceptron (MLP) network and a statistical method based on the GMM. Extensive testing was conducted and the results show great potential in the use of the FNN for real-time driver identification and verification. In addition, the profiling of driver behaviors has numerous other potential applications for use by law enforcement and companies dealing with buses and truck drivers.

Objective definition of rosette shape variation using a combined computer vision and data mining approach.

PubMed

Camargo, Anyela; Papadopoulou, Dimitra; Spyropoulou, Zoi; Vlachonasios, Konstantinos; Doonan, John H; Gay, Alan P

2014-01-01

Computer-vision based measurements of phenotypic variation have implications for crop improvement and food security because they are intrinsically objective. It should be possible therefore to use such approaches to select robust genotypes. However, plants are morphologically complex and identification of meaningful traits from automatically acquired image data is not straightforward. Bespoke algorithms can be designed to capture and/or quantitate specific features but this approach is inflexible and is not generally applicable to a wide range of traits. In this paper, we have used industry-standard computer vision techniques to extract a wide range of features from images of genetically diverse Arabidopsis rosettes growing under non-stimulated conditions, and then used statistical analysis to identify those features that provide good discrimination between ecotypes. This analysis indicates that almost all the observed shape variation can be described by 5 principal components. We describe an easily implemented pipeline including image segmentation, feature extraction and statistical analysis. This pipeline provides a cost-effective and inherently scalable method to parameterise and analyse variation in rosette shape. The acquisition of images does not require any specialised equipment and the computer routines for image processing and data analysis have been implemented using open source software. Source code for data analysis is written using the R package. The equations to calculate image descriptors have been also provided.

Digital auscultation analysis for heart murmur detection.

PubMed

Delgado-Trejos, Edilson; Quiceno-Manrique, A F; Godino-Llorente, J I; Blanco-Velasco, M; Castellanos-Dominguez, G

2009-02-01

This work presents a comparison of different approaches for the detection of murmurs from phonocardiographic signals. Taking into account the variability of the phonocardiographic signals induced by valve disorders, three families of features were analyzed: (a) time-varying & time-frequency features; (b) perceptual; and (c) fractal features. With the aim of improving the performance of the system, the accuracy of the system was tested using several combinations of the aforementioned families of parameters. In the second stage, the main components extracted from each family were combined together with the goal of improving the accuracy of the system. The contribution of each family of features extracted was evaluated by means of a simple k-nearest neighbors classifier, showing that fractal features provide the best accuracy (97.17%), followed by time-varying & time-frequency (95.28%), and perceptual features (88.7%). However, an accuracy around 94% can be reached just by using the two main features of the fractal family; therefore, considering the difficulties related to the automatic intrabeat segmentation needed for spectral and perceptual features, this scheme becomes an interesting alternative. The conclusion is that fractal type features were the most robust family of parameters (in the sense of accuracy vs. computational load) for the automatic detection of murmurs. This work was carried out using a database that contains 164 phonocardiographic recordings (81 normal and 83 records with murmurs). The database was segmented to extract 360 representative individual beats (180 per class).

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.

Dependency-based long short term memory network for drug-drug interaction extraction.

PubMed

Wang, Wei; Yang, Xi; Yang, Canqun; Guo, Xiaowei; Zhang, Xiang; Wu, Chengkun

2017-12-28

Drug-drug interaction extraction (DDI) needs assistance from automated methods to address the explosively increasing biomedical texts. In recent years, deep neural network based models have been developed to address such needs and they have made significant progress in relation identification. We propose a dependency-based deep neural network model for DDI extraction. By introducing the dependency-based technique to a bi-directional long short term memory network (Bi-LSTM), we build three channels, namely, Linear channel, DFS channel and BFS channel. All of these channels are constructed with three network layers, including embedding layer, LSTM layer and max pooling layer from bottom up. In the embedding layer, we extract two types of features, one is distance-based feature and another is dependency-based feature. In the LSTM layer, a Bi-LSTM is instituted in each channel to better capture relation information. Then max pooling is used to get optimal features from the entire encoding sequential data. At last, we concatenate the outputs of all channels and then link it to the softmax layer for relation identification. To the best of our knowledge, our model achieves new state-of-the-art performance with the F-score of 72.0% on the DDIExtraction 2013 corpus. Moreover, our approach obtains much higher Recall value compared to the existing methods. The dependency-based Bi-LSTM model can learn effective relation information with less feature engineering in the task of DDI extraction. Besides, the experimental results show that our model excels at balancing the Precision and Recall values.

Singular value decomposition based feature extraction technique for physiological signal analysis.

PubMed

Chang, Cheng-Ding; Wang, Chien-Chih; Jiang, Bernard C

2012-06-01

Multiscale entropy (MSE) is one of the popular techniques to calculate and describe the complexity of the physiological signal. Many studies use this approach to detect changes in the physiological conditions in the human body. However, MSE results are easily affected by noise and trends, leading to incorrect estimation of MSE values. In this paper, singular value decomposition (SVD) is adopted to replace MSE to extract the features of physiological signals, and adopt the support vector machine (SVM) to classify the different physiological states. A test data set based on the PhysioNet website was used, and the classification results showed that using SVD to extract features of the physiological signal could attain a classification accuracy rate of 89.157%, which is higher than that using the MSE value (71.084%). The results show the proposed analysis procedure is effective and appropriate for distinguishing different physiological states. This promising result could be used as a reference for doctors in diagnosis of congestive heart failure (CHF) disease.

Wavelet images and Chou's pseudo amino acid composition for protein classification.

PubMed

Nanni, Loris; Brahnam, Sheryl; Lumini, Alessandra

2012-08-01

The last decade has seen an explosion in the collection of protein data. To actualize the potential offered by this wealth of data, it is important to develop machine systems capable of classifying and extracting features from proteins. Reliable machine systems for protein classification offer many benefits, including the promise of finding novel drugs and vaccines. In developing our system, we analyze and compare several feature extraction methods used in protein classification that are based on the calculation of texture descriptors starting from a wavelet representation of the protein. We then feed these texture-based representations of the protein into an Adaboost ensemble of neural network or a support vector machine classifier. In addition, we perform experiments that combine our feature extraction methods with a standard method that is based on the Chou's pseudo amino acid composition. Using several datasets, we show that our best approach outperforms standard methods. The Matlab code of the proposed protein descriptors is available at http://bias.csr.unibo.it/nanni/wave.rar .

Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach.

PubMed

Liu, Li; Shao, Ling; Li, Xuelong; Lu, Ke

2016-01-01

Extracting discriminative and robust features from video sequences is the first and most critical step in human action recognition. In this paper, instead of using handcrafted features, we automatically learn spatio-temporal motion features for action recognition. This is achieved via an evolutionary method, i.e., genetic programming (GP), which evolves the motion feature descriptor on a population of primitive 3D operators (e.g., 3D-Gabor and wavelet). In this way, the scale and shift invariant features can be effectively extracted from both color and optical flow sequences. We intend to learn data adaptive descriptors for different datasets with multiple layers, which makes fully use of the knowledge to mimic the physical structure of the human visual cortex for action recognition and simultaneously reduce the GP searching space to effectively accelerate the convergence of optimal solutions. In our evolutionary architecture, the average cross-validation classification error, which is calculated by an support-vector-machine classifier on the training set, is adopted as the evaluation criterion for the GP fitness function. After the entire evolution procedure finishes, the best-so-far solution selected by GP is regarded as the (near-)optimal action descriptor obtained. The GP-evolving feature extraction method is evaluated on four popular action datasets, namely KTH, HMDB51, UCF YouTube, and Hollywood2. Experimental results show that our method significantly outperforms other types of features, either hand-designed or machine-learned.

Emotion Recognition from Chinese Speech for Smart Affective Services Using a Combination of SVM and DBN

PubMed Central

Zhu, Lianzhang; Chen, Leiming; Zhao, Dehai

2017-01-01

Accurate emotion recognition from speech is important for applications like smart health care, smart entertainment, and other smart services. High accuracy emotion recognition from Chinese speech is challenging due to the complexities of the Chinese language. In this paper, we explore how to improve the accuracy of speech emotion recognition, including speech signal feature extraction and emotion classification methods. Five types of features are extracted from a speech sample: mel frequency cepstrum coefficient (MFCC), pitch, formant, short-term zero-crossing rate and short-term energy. By comparing statistical features with deep features extracted by a Deep Belief Network (DBN), we attempt to find the best features to identify the emotion status for speech. We propose a novel classification method that combines DBN and SVM (support vector machine) instead of using only one of them. In addition, a conjugate gradient method is applied to train DBN in order to speed up the training process. Gender-dependent experiments are conducted using an emotional speech database created by the Chinese Academy of Sciences. The results show that DBN features can reflect emotion status better than artificial features, and our new classification approach achieves an accuracy of 95.8%, which is higher than using either DBN or SVM separately. Results also show that DBN can work very well for small training databases if it is properly designed. PMID:28737705

Identifying well-formed biomedical phrases in MEDLINE® text.

PubMed

Kim, Won; Yeganova, Lana; Comeau, Donald C; Wilbur, W John

2012-12-01

In the modern world people frequently interact with retrieval systems to satisfy their information needs. Humanly understandable well-formed phrases represent a crucial interface between humans and the web, and the ability to index and search with such phrases is beneficial for human-web interactions. In this paper we consider the problem of identifying humanly understandable, well formed, and high quality biomedical phrases in MEDLINE documents. The main approaches used previously for detecting such phrases are syntactic, statistical, and a hybrid approach combining these two. In this paper we propose a supervised learning approach for identifying high quality phrases. First we obtain a set of known well-formed useful phrases from an existing source and label these phrases as positive. We then extract from MEDLINE a large set of multiword strings that do not contain stop words or punctuation. We believe this unlabeled set contains many well-formed phrases. Our goal is to identify these additional high quality phrases. We examine various feature combinations and several machine learning strategies designed to solve this problem. A proper choice of machine learning methods and features identifies in the large collection strings that are likely to be high quality phrases. We evaluate our approach by making human judgments on multiword strings extracted from MEDLINE using our methods. We find that over 85% of such extracted phrase candidates are humanly judged to be of high quality. Published by Elsevier Inc.

Securing palmprint authentication systems using spoof detection approach

NASA Astrophysics Data System (ADS)

Kanhangad, Vivek; Kumar, Abhishek

2013-12-01

Automated human authentication using features extracted from palmprint images has been studied extensively in the literature. Primary focus of the studies thus far has been the improvement of matching performance. As more biometric systems get deployed for wide range of applications, the threat of impostor attacks on these systems is on the rise. The most common among various types of attacks is the sensor level spoof attack using fake hands created using different materials. This paper investigates an approach for securing palmprint based biometric systems against spoof attacks that use photographs of the human hand for circumventing the system. The approach is based on the analysis of local texture patterns of acquired palmprint images for extracting discriminatory features. A trained binary classifier utilizes the discriminating information to determine if the input image is of real hand or a fake one. Experimental results, using 611 palmprint images corresponding to 100 subjects in the publicly available IITD palmprint image database, show that 1) palmprint authentication systems are highly vulnerable to spoof attacks and 2) the proposed spoof detection approach is effective for discriminating between real and fake image samples. In particular, the proposed approach achieves the best classification accuracy of 97.35%.

Texture Feature Extraction and Classification for Iris Diagnosis

NASA Astrophysics Data System (ADS)

Ma, Lin; Li, Naimin

Appling computer aided techniques in iris image processing, and combining occidental iridology with the traditional Chinese medicine is a challenging research area in digital image processing and artificial intelligence. This paper proposes an iridology model that consists the iris image pre-processing, texture feature analysis and disease classification. To the pre-processing, a 2-step iris localization approach is proposed; a 2-D Gabor filter based texture analysis and a texture fractal dimension estimation method are proposed for pathological feature extraction; and at last support vector machines are constructed to recognize 2 typical diseases such as the alimentary canal disease and the nerve system disease. Experimental results show that the proposed iridology diagnosis model is quite effective and promising for medical diagnosis and health surveillance for both hospital and public use.

Modeling for Visual Feature Extraction Using Spiking Neural Networks

NASA Astrophysics Data System (ADS)

Kimura, Ichiro; Kuroe, Yasuaki; Kotera, Hiromichi; Murata, Tomoya

This paper develops models for “visual feature extraction” in biological systems by using “spiking neural network (SNN)”. The SNN is promising for developing the models because the information is encoded and processed by spike trains similar to biological neural networks. Two architectures of SNN are proposed for modeling the directionally selective and the motion parallax cell in neuro-sensory systems and they are trained so as to possess actual biological responses of each cell. To validate the developed models, their representation ability is investigated and their visual feature extraction mechanisms are discussed from the neurophysiological viewpoint. It is expected that this study can be the first step to developing a sensor system similar to the biological systems and also a complementary approach to investigating the function of the brain.

Earth resources data analysis program, phase 3

NASA Technical Reports Server (NTRS)

1975-01-01

Tasks were performed in two areas: (1) systems analysis and (2) algorithmic development. The major effort in the systems analysis task was the development of a recommended approach to the monitoring of resource utilization data for the Large Area Crop Inventory Experiment (LACIE). Other efforts included participation in various studies concerning the LACIE Project Plan, the utility of the GE Image 100, and the specifications for a special purpose processor to be used in the LACIE. In the second task, the major effort was the development of improved algorithms for estimating proportions of unclassified remotely sensed data. Also, work was performed on optimal feature extraction and optimal feature extraction for proportion estimation.

General methodology for simultaneous representation and discrimination of multiple object classes

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.

1998-03-01

We address a new general method for linear and nonlinear feature extraction for simultaneous representation and classification. We call this approach the maximum representation and discrimination feature (MRDF) method. We develop a novel nonlinear eigenfeature extraction technique to represent data with closed-form solutions and use it to derive a nonlinear MRDF algorithm. Results of the MRDF method on synthetic databases are shown and compared with results from standard Fukunaga-Koontz transform and Fisher discriminant function methods. The method is also applied to an automated product inspection problem and for classification and pose estimation of two similar objects under 3D aspect angle variations.

Urinary bladder cancer T-staging from T2-weighted MR images using an optimal biomarker approach

NASA Astrophysics Data System (ADS)

Wang, Chuang; Udupa, Jayaram K.; Tong, Yubing; Chen, Jerry; Venigalla, Sriram; Odhner, Dewey; Guzzo, Thomas J.; Christodouleas, John; Torigian, Drew A.

2018-02-01

Magnetic resonance imaging (MRI) is often used in clinical practice to stage patients with bladder cancer to help plan treatment. However, qualitative assessment of MR images is prone to inaccuracies, adversely affecting patient outcomes. In this paper, T2-weighted MR image-based quantitative features were extracted from the bladder wall in 65 patients with bladder cancer to classify them into two primary tumor (T) stage groups: group 1 - T stage < T2, with primary tumor locally confined to the bladder, and group 2 - T stage < T2, with primary tumor locally extending beyond the bladder. The bladder was divided into 8 sectors in the axial plane, where each sector has a corresponding reference standard T stage that is based on expert radiology qualitative MR image review and histopathologic results. The performance of the classification for correct assignment of T stage grouping was then evaluated at both the patient level and the sector level. Each bladder sector was divided into 3 shells (inner, middle, and outer), and 15,834 features including intensity features and texture features from local binary pattern and gray-level co-occurrence matrix were extracted from the 3 shells of each sector. An optimal feature set was selected from all features using an optimal biomarker approach. Nine optimal biomarker features were derived based on texture properties from the middle shell, with an area under the ROC curve of AUC value at the sector and patient level of 0.813 and 0.806, respectively.

A flower image retrieval method based on ROI feature.

PubMed

Hong, An-Xiang; Chen, Gang; Li, Jun-Li; Chi, Zhe-Ru; Zhang, Dan

2004-07-01

Flower image retrieval is a very important step for computer-aided plant species recognition. In this paper, we propose an efficient segmentation method based on color clustering and domain knowledge to extract flower regions from flower images. For flower retrieval, we use the color histogram of a flower region to characterize the color features of flower and two shape-based features sets, Centroid-Contour Distance (CCD) and Angle Code Histogram (ACH), to characterize the shape features of a flower contour. Experimental results showed that our flower region extraction method based on color clustering and domain knowledge can produce accurate flower regions. Flower retrieval results on a database of 885 flower images collected from 14 plant species showed that our Region-of-Interest (ROI) based retrieval approach using both color and shape features can perform better than a method based on the global color histogram proposed by Swain and Ballard (1991) and a method based on domain knowledge-driven segmentation and color names proposed by Das et al.(1999).

An integrated condition-monitoring method for a milling process using reduced decomposition features

NASA Astrophysics Data System (ADS)

Liu, Jie; Wu, Bo; Wang, Yan; Hu, Youmin

2017-08-01

Complex and non-stationary cutting chatter affects productivity and quality in the milling process. Developing an effective condition-monitoring approach is critical to accurately identify cutting chatter. In this paper, an integrated condition-monitoring method is proposed, where reduced features are used to efficiently recognize and classify machine states in the milling process. In the proposed method, vibration signals are decomposed into multiple modes with variational mode decomposition, and Shannon power spectral entropy is calculated to extract features from the decomposed signals. Principal component analysis is adopted to reduce feature size and computational cost. With the extracted feature information, the probabilistic neural network model is used to recognize and classify the machine states, including stable, transition, and chatter states. Experimental studies are conducted, and results show that the proposed method can effectively detect cutting chatter during different milling operation conditions. This monitoring method is also efficient enough to satisfy fast machine state recognition and classification.

A Novel Modulation Classification Approach Using Gabor Filter Network

PubMed Central

Ghauri, Sajjad Ahmed; Qureshi, Ijaz Mansoor; Cheema, Tanveer Ahmed; Malik, Aqdas Naveed

2014-01-01

A Gabor filter network based approach is used for feature extraction and classification of digital modulated signals by adaptively tuning the parameters of Gabor filter network. Modulation classification of digitally modulated signals is done under the influence of additive white Gaussian noise (AWGN). The modulations considered for the classification purpose are PSK 2 to 64, FSK 2 to 64, and QAM 4 to 64. The Gabor filter network uses the network structure of two layers; the first layer which is input layer constitutes the adaptive feature extraction part and the second layer constitutes the signal classification part. The Gabor atom parameters are tuned using Delta rule and updating of weights of Gabor filter using least mean square (LMS) algorithm. The simulation results show that proposed novel modulation classification algorithm has high classification accuracy at low signal to noise ratio (SNR) on AWGN channel. PMID:25126603

Efficient Spatio-Temporal Local Binary Patterns for Spontaneous Facial Micro-Expression Recognition

PubMed Central

Wang, Yandan; See, John; Phan, Raphael C.-W.; Oh, Yee-Hui

2015-01-01

Micro-expression recognition is still in the preliminary stage, owing much to the numerous difficulties faced in the development of datasets. Since micro-expression is an important affective clue for clinical diagnosis and deceit analysis, much effort has gone into the creation of these datasets for research purposes. There are currently two publicly available spontaneous micro-expression datasets—SMIC and CASME II, both with baseline results released using the widely used dynamic texture descriptor LBP-TOP for feature extraction. Although LBP-TOP is popular and widely used, it is still not compact enough. In this paper, we draw further inspiration from the concept of LBP-TOP that considers three orthogonal planes by proposing two efficient approaches for feature extraction. The compact robust form described by the proposed LBP-Six Intersection Points (SIP) and a super-compact LBP-Three Mean Orthogonal Planes (MOP) not only preserves the essential patterns, but also reduces the redundancy that affects the discriminality of the encoded features. Through a comprehensive set of experiments, we demonstrate the strengths of our approaches in terms of recognition accuracy and efficiency. PMID:25993498

Radial gradient and radial deviation radiomic features from pre-surgical CT scans are associated with survival among lung adenocarcinoma patients

PubMed Central

Tunali, Ilke; Stringfield, Olya; Guvenis, Albert; Wang, Hua; Liu, Ying; Balagurunathan, Yoganand; Lambin, Philippe; Gillies, Robert J.; Schabath, Matthew B.

2017-01-01

The goal of this study was to extract features from radial deviation and radial gradient maps which were derived from thoracic CT scans of patients diagnosed with lung adenocarcinoma and assess whether these features are associated with overall survival. We used two independent cohorts from different institutions for training (n= 61) and test (n= 47) and focused our analyses on features that were non-redundant and highly reproducible. To reduce the number of features and covariates into a single parsimonious model, a backward elimination approach was applied. Out of 48 features that were extracted, 31 were eliminated because they were not reproducible or were redundant. We considered 17 features for statistical analysis and identified a final model containing the two most highly informative features that were associated with lung cancer survival. One of the two features, radial deviation outside-border separation standard deviation, was replicated in a test cohort exhibiting a statistically significant association with lung cancer survival (multivariable hazard ratio = 0.40; 95% confidence interval 0.17-0.97). Additionally, we explored the biological underpinnings of these features and found radial gradient and radial deviation image features were significantly associated with semantic radiological features. PMID:29221183

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.

Approaches for Language Identification in Mismatched Environments

DTIC Science & Technology

2016-09-08

different i-vector systems are considered, which differ in their feature extraction mechanism. The first, which we refer to as the standard i-vector, or...both conversational telephone speech and narrowband broadcast speech. Multiple experiments are conducted to assess the performance of the system in...bottleneck features using i-vectors. The proposed system results in a 30% improvement over the baseline result. Index Terms: language identification

QSPR models for half-wave reduction potential of steroids: a comparative study between feature selection and feature extraction from subsets of or entire set of descriptors.

PubMed

Hemmateenejad, Bahram; Yazdani, Mahdieh

2009-02-16

Steroids are widely distributed in nature and are found in plants, animals, and fungi in abundance. A data set consists of a diverse set of steroids have been used to develop quantitative structure-electrochemistry relationship (QSER) models for their half-wave reduction potential. Modeling was established by means of multiple linear regression (MLR) and principle component regression (PCR) analyses. In MLR analysis, the QSPR models were constructed by first grouping descriptors and then stepwise selection of variables from each group (MLR1) and stepwise selection of predictor variables from the pool of all calculated descriptors (MLR2). Similar procedure was used in PCR analysis so that the principal components (or features) were extracted from different group of descriptors (PCR1) and from entire set of descriptors (PCR2). The resulted models were evaluated using cross-validation, chance correlation, application to prediction reduction potential of some test samples and accessing applicability domain. Both MLR approaches represented accurate results however the QSPR model found by MLR1 was statistically more significant. PCR1 approach produced a model as accurate as MLR approaches whereas less accurate results were obtained by PCR2 approach. In overall, the correlation coefficients of cross-validation and prediction of the QSPR models resulted from MLR1, MLR2 and PCR1 approaches were higher than 90%, which show the high ability of the models to predict reduction potential of the studied steroids.

Intelligent keyframe extraction for video printing

NASA Astrophysics Data System (ADS)

Zhang, Tong

2004-10-01

Nowadays most digital cameras have the functionality of taking short video clips, with the length of video ranging from several seconds to a couple of minutes. The purpose of this research is to develop an algorithm which extracts an optimal set of keyframes from each short video clip so that the user could obtain proper video frames to print out. In current video printing systems, keyframes are normally obtained by evenly sampling the video clip over time. Such an approach, however, may not reflect highlights or regions of interest in the video. Keyframes derived in this way may also be improper for video printing in terms of either content or image quality. In this paper, we present an intelligent keyframe extraction approach to derive an improved keyframe set by performing semantic analysis of the video content. For a video clip, a number of video and audio features are analyzed to first generate a candidate keyframe set. These features include accumulative color histogram and color layout differences, camera motion estimation, moving object tracking, face detection and audio event detection. Then, the candidate keyframes are clustered and evaluated to obtain a final keyframe set. The objective is to automatically generate a limited number of keyframes to show different views of the scene; to show different people and their actions in the scene; and to tell the story in the video shot. Moreover, frame extraction for video printing, which is a rather subjective problem, is considered in this work for the first time, and a semi-automatic approach is proposed.

Bag-of-features approach for improvement of lung tissue classification in diffuse lung disease

NASA Astrophysics Data System (ADS)

Kato, Noriji; Fukui, Motofumi; Isozaki, Takashi

2009-02-01

Many automated techniques have been proposed to classify diffuse lung disease patterns. Most of the techniques utilize texture analysis approaches with second and higher order statistics, and show successful classification result among various lung tissue patterns. However, the approaches do not work well for the patterns with inhomogeneous texture distribution within a region of interest (ROI), such as reticular and honeycombing patterns, because the statistics can only capture averaged feature over the ROI. In this work, we have introduced the bag-of-features approach to overcome this difficulty. In the approach, texture images are represented as histograms or distributions of a few basic primitives, which are obtained by clustering local image features. The intensity descriptor and the Scale Invariant Feature Transformation (SIFT) descriptor are utilized to extract the local features, which have significant discriminatory power due to their specificity to a particular image class. In contrast, the drawback of the local features is lack of invariance under translation and rotation. We improved the invariance by sampling many local regions so that the distribution of the local features is unchanged. We evaluated the performance of our system in the classification task with 5 image classes (ground glass, reticular, honeycombing, emphysema, and normal) using 1109 ROIs from 211 patients. Our system achieved high classification accuracy of 92.8%, which is superior to that of the conventional system with the gray level co-occurrence matrix (GLCM) feature especially for inhomogeneous texture patterns.

Detecting modification of biomedical events using a deep parsing approach

PubMed Central

2012-01-01

Background This work describes a system for identifying event mentions in bio-molecular research abstracts that are either speculative (e.g. analysis of IkappaBalpha phosphorylation, where it is not specified whether phosphorylation did or did not occur) or negated (e.g. inhibition of IkappaBalpha phosphorylation, where phosphorylation did not occur). The data comes from a standard dataset created for the BioNLP 2009 Shared Task. The system uses a machine-learning approach, where the features used for classification are a combination of shallow features derived from the words of the sentences and more complex features based on the semantic outputs produced by a deep parser. Method To detect event modification, we use a Maximum Entropy learner with features extracted from the data relative to the trigger words of the events. The shallow features are bag-of-words features based on a small sliding context window of 3-4 tokens on either side of the trigger word. The deep parser features are derived from parses produced by the English Resource Grammar and the RASP parser. The outputs of these parsers are converted into the Minimal Recursion Semantics formalism, and from this, we extract features motivated by linguistics and the data itself. All of these features are combined to create training or test data for the machine learning algorithm. Results Over the test data, our methods produce approximately a 4% absolute increase in F-score for detection of event modification compared to a baseline based only on the shallow bag-of-words features. Conclusions Our results indicate that grammar-based techniques can enhance the accuracy of methods for detecting event modification. PMID:22595089

Prediction of cause of death from forensic autopsy reports using text classification techniques: A comparative study.

PubMed

Mujtaba, Ghulam; Shuib, Liyana; Raj, Ram Gopal; Rajandram, Retnagowri; Shaikh, Khairunisa

2018-07-01

Automatic text classification techniques are useful for classifying plaintext medical documents. This study aims to automatically predict the cause of death from free text forensic autopsy reports by comparing various schemes for feature extraction, term weighing or feature value representation, text classification, and feature reduction. For experiments, the autopsy reports belonging to eight different causes of death were collected, preprocessed and converted into 43 master feature vectors using various schemes for feature extraction, representation, and reduction. The six different text classification techniques were applied on these 43 master feature vectors to construct a classification model that can predict the cause of death. Finally, classification model performance was evaluated using four performance measures i.e. overall accuracy, macro precision, macro-F-measure, and macro recall. From experiments, it was found that that unigram features obtained the highest performance compared to bigram, trigram, and hybrid-gram features. Furthermore, in feature representation schemes, term frequency, and term frequency with inverse document frequency obtained similar and better results when compared with binary frequency, and normalized term frequency with inverse document frequency. Furthermore, the chi-square feature reduction approach outperformed Pearson correlation, and information gain approaches. Finally, in text classification algorithms, support vector machine classifier outperforms random forest, Naive Bayes, k-nearest neighbor, decision tree, and ensemble-voted classifier. Our results and comparisons hold practical importance and serve as references for future works. Moreover, the comparison outputs will act as state-of-art techniques to compare future proposals with existing automated text classification techniques. Copyright © 2017 Elsevier Ltd and Faculty of Forensic and Legal Medicine. All rights reserved.

Diagnosis of combined faults in Rotary Machinery by Non-Naive Bayesian approach

NASA Astrophysics Data System (ADS)

Asr, Mahsa Yazdanian; Ettefagh, Mir Mohammad; Hassannejad, Reza; Razavi, Seyed Naser

2017-02-01

When combined faults happen in different parts of the rotating machines, their features are profoundly dependent. Experts are completely familiar with individuals faults characteristics and enough data are available from single faults but the problem arises, when the faults combined and the separation of characteristics becomes complex. Therefore, the experts cannot declare exact information about the symptoms of combined fault and its quality. In this paper to overcome this drawback, a novel method is proposed. The core idea of the method is about declaring combined fault without using combined fault features as training data set and just individual fault features are applied in training step. For this purpose, after data acquisition and resampling the obtained vibration signals, Empirical Mode Decomposition (EMD) is utilized to decompose multi component signals to Intrinsic Mode Functions (IMFs). With the use of correlation coefficient, proper IMFs for feature extraction are selected. In feature extraction step, Shannon energy entropy of IMFs was extracted as well as statistical features. It is obvious that most of extracted features are strongly dependent. To consider this matter, Non-Naive Bayesian Classifier (NNBC) is appointed, which release the fundamental assumption of Naive Bayesian, i.e., the independence among features. To demonstrate the superiority of NNBC, other counterpart methods, include Normal Naive Bayesian classifier, Kernel Naive Bayesian classifier and Back Propagation Neural Networks were applied and the classification results are compared. An experimental vibration signals, collected from automobile gearbox, were used to verify the effectiveness of the proposed method. During the classification process, only the features, related individually to healthy state, bearing failure and gear failures, were assigned for training the classifier. But, combined fault features (combined gear and bearing failures) were examined as test data. The achieved probabilities for the test data show that the combined fault can be identified with high success rate.

Automatic Feature Detection, Description and Matching from Mobile Laser Scanning Data and Aerial Imagery

NASA Astrophysics Data System (ADS)

Hussnain, Zille; Oude Elberink, Sander; Vosselman, George

2016-06-01

In mobile laser scanning systems, the platform's position is measured by GNSS and IMU, which is often not reliable in urban areas. Consequently, derived Mobile Laser Scanning Point Cloud (MLSPC) lacks expected positioning reliability and accuracy. Many of the current solutions are either semi-automatic or unable to achieve pixel level accuracy. We propose an automatic feature extraction method which involves utilizing corresponding aerial images as a reference data set. The proposed method comprise three steps; image feature detection, description and matching between corresponding patches of nadir aerial and MLSPC ortho images. In the data pre-processing step the MLSPC is patch-wise cropped and converted to ortho images. Furthermore, each aerial image patch covering the area of the corresponding MLSPC patch is also cropped from the aerial image. For feature detection, we implemented an adaptive variant of Harris-operator to automatically detect corner feature points on the vertices of road markings. In feature description phase, we used the LATCH binary descriptor, which is robust to data from different sensors. For descriptor matching, we developed an outlier filtering technique, which exploits the arrangements of relative Euclidean-distances and angles between corresponding sets of feature points. We found that the positioning accuracy of the computed correspondence has achieved the pixel level accuracy, where the image resolution is 12cm. Furthermore, the developed approach is reliable when enough road markings are available in the data sets. We conclude that, in urban areas, the developed approach can reliably extract features necessary to improve the MLSPC accuracy to pixel level.

An improved strategy for skin lesion detection and classification using uniform segmentation and feature selection based approach.

PubMed

Nasir, Muhammad; Attique Khan, Muhammad; Sharif, Muhammad; Lali, Ikram Ullah; Saba, Tanzila; Iqbal, Tassawar

2018-02-21

Melanoma is the deadliest type of skin cancer with highest mortality rate. However, the annihilation in early stage implies a high survival rate therefore, it demands early diagnosis. The accustomed diagnosis methods are costly and cumbersome due to the involvement of experienced experts as well as the requirements for highly equipped environment. The recent advancements in computerized solutions for these diagnoses are highly promising with improved accuracy and efficiency. In this article, we proposed a method for the classification of melanoma and benign skin lesions. Our approach integrates preprocessing, lesion segmentation, features extraction, features selection, and classification. Preprocessing is executed in the context of hair removal by DullRazor, whereas lesion texture and color information are utilized to enhance the lesion contrast. In lesion segmentation, a hybrid technique has been implemented and results are fused using additive law of probability. Serial based method is applied subsequently that extracts and fuses the traits such as color, texture, and HOG (shape). The fused features are selected afterwards by implementing a novel Boltzman Entropy method. Finally, the selected features are classified by Support Vector Machine. The proposed method is evaluated on publically available data set PH2. Our approach has provided promising results of sensitivity 97.7%, specificity 96.7%, accuracy 97.5%, and F-score 97.5%, which are significantly better than the results of existing methods available on the same data set. The proposed method detects and classifies melanoma significantly good as compared to existing methods. © 2018 Wiley Periodicals, Inc.

Classification of vegetation types in military region

NASA Astrophysics Data System (ADS)

Gonçalves, Miguel; Silva, Jose Silvestre; Bioucas-Dias, Jose

2015-10-01

In decision-making process regarding planning and execution of military operations, the terrain is a determining factor. Aerial photographs are a source of vital information for the success of an operation in hostile region, namely when the cartographic information behind enemy lines is scarce or non-existent. The objective of present work is the development of a tool capable of processing aerial photos. The methodology implemented starts with feature extraction, followed by the application of an automatic selector of features. The next step, using the k-fold cross validation technique, estimates the input parameters for the following classifiers: Sparse Multinomial Logist Regression (SMLR), K Nearest Neighbor (KNN), Linear Classifier using Principal Component Expansion on the Joint Data (PCLDC) and Multi-Class Support Vector Machine (MSVM). These classifiers were used in two different studies with distinct objectives: discrimination of vegetation's density and identification of vegetation's main components. It was found that the best classifier on the first approach is the Sparse Logistic Multinomial Regression (SMLR). On the second approach, the implemented methodology applied to high resolution images showed that the better performance was achieved by KNN classifier and PCLDC. Comparing the two approaches there is a multiscale issue, in which for different resolutions, the best solution to the problem requires different classifiers and the extraction of different features.

A Hybrid Generalized Hidden Markov Model-Based Condition Monitoring Approach for Rolling Bearings

PubMed Central

Liu, Jie; Hu, Youmin; Wu, Bo; Wang, Yan; Xie, Fengyun

2017-01-01

The operating condition of rolling bearings affects productivity and quality in the rotating machine process. Developing an effective rolling bearing condition monitoring approach is critical to accurately identify the operating condition. In this paper, a hybrid generalized hidden Markov model-based condition monitoring approach for rolling bearings is proposed, where interval valued features are used to efficiently recognize and classify machine states in the machine process. In the proposed method, vibration signals are decomposed into multiple modes with variational mode decomposition (VMD). Parameters of the VMD, in the form of generalized intervals, provide a concise representation for aleatory and epistemic uncertainty and improve the robustness of identification. The multi-scale permutation entropy method is applied to extract state features from the decomposed signals in different operating conditions. Traditional principal component analysis is adopted to reduce feature size and computational cost. With the extracted features’ information, the generalized hidden Markov model, based on generalized interval probability, is used to recognize and classify the fault types and fault severity levels. Finally, the experiment results show that the proposed method is effective at recognizing and classifying the fault types and fault severity levels of rolling bearings. This monitoring method is also efficient enough to quantify the two uncertainty components. PMID:28524088

Discriminative Ocular Artifact Correction for Feature Learning in EEG Analysis.

PubMed

Xinyang Li; Cuntai Guan; Haihong Zhang; Kai Keng Ang

2017-08-01

Electrooculogram (EOG) artifact contamination is a common critical issue in general electroencephalogram (EEG) studies as well as in brain-computer interface (BCI) research. It is especially challenging when dedicated EOG channels are unavailable or when there are very few EEG channels available for independent component analysis based ocular artifact removal. It is even more challenging to avoid loss of the signal of interest during the artifact correction process, where the signal of interest can be multiple magnitudes weaker than the artifact. To address these issues, we propose a novel discriminative ocular artifact correction approach for feature learning in EEG analysis. Without extra ocular movement measurements, the artifact is extracted from raw EEG data, which is totally automatic and requires no visual inspection of artifacts. Then, artifact correction is optimized jointly with feature extraction by maximizing oscillatory correlations between trials from the same class and minimizing them between trials from different classes. We evaluate this approach on a real-world EEG dataset comprising 68 subjects performing cognitive tasks. The results showed that the approach is capable of not only suppressing the artifact components but also improving the discriminative power of a classifier with statistical significance. We also demonstrate that the proposed method addresses the confounding issues induced by ocular movements in cognitive EEG study.

Classification of SD-OCT volumes for DME detection: an anomaly detection approach

NASA Astrophysics Data System (ADS)

Sankar, S.; Sidibé, D.; Cheung, Y.; Wong, T. Y.; Lamoureux, E.; Milea, D.; Meriaudeau, F.

2016-03-01

Diabetic Macular Edema (DME) is the leading cause of blindness amongst diabetic patients worldwide. It is characterized by accumulation of water molecules in the macula leading to swelling. Early detection of the disease helps prevent further loss of vision. Naturally, automated detection of DME from Optical Coherence Tomography (OCT) volumes plays a key role. To this end, a pipeline for detecting DME diseases in OCT volumes is proposed in this paper. The method is based on anomaly detection using Gaussian Mixture Model (GMM). It starts with pre-processing the B-scans by resizing, flattening, filtering and extracting features from them. Both intensity and Local Binary Pattern (LBP) features are considered. The dimensionality of the extracted features is reduced using PCA. As the last stage, a GMM is fitted with features from normal volumes. During testing, features extracted from the test volume are evaluated with the fitted model for anomaly and classification is made based on the number of B-scans detected as outliers. The proposed method is tested on two OCT datasets achieving a sensitivity and a specificity of 80% and 93% on the first dataset, and 100% and 80% on the second one. Moreover, experiments show that the proposed method achieves better classification performances than other recently published works.

A flexible data-driven comorbidity feature extraction framework.

PubMed

Sideris, Costas; Pourhomayoun, Mohammad; Kalantarian, Haik; Sarrafzadeh, Majid

2016-06-01

Disease and symptom diagnostic codes are a valuable resource for classifying and predicting patient outcomes. In this paper, we propose a novel methodology for utilizing disease diagnostic information in a predictive machine learning framework. Our methodology relies on a novel, clustering-based feature extraction framework using disease diagnostic information. To reduce the data dimensionality, we identify disease clusters using co-occurrence statistics. We optimize the number of generated clusters in the training set and then utilize these clusters as features to predict patient severity of condition and patient readmission risk. We build our clustering and feature extraction algorithm using the 2012 National Inpatient Sample (NIS), Healthcare Cost and Utilization Project (HCUP) which contains 7 million hospital discharge records and ICD-9-CM codes. The proposed framework is tested on Ronald Reagan UCLA Medical Center Electronic Health Records (EHR) from 3041 Congestive Heart Failure (CHF) patients and the UCI 130-US diabetes dataset that includes admissions from 69,980 diabetic patients. We compare our cluster-based feature set with the commonly used comorbidity frameworks including Charlson's index, Elixhauser's comorbidities and their variations. The proposed approach was shown to have significant gains between 10.7-22.1% in predictive accuracy for CHF severity of condition prediction and 4.65-5.75% in diabetes readmission prediction. Copyright © 2016 Elsevier Ltd. All rights reserved.

Maximum entropy methods for extracting the learned features of deep neural networks.

PubMed

Finnegan, Alex; Song, Jun S

2017-10-01

New architectures of multilayer artificial neural networks and new methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the maximum entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the maximum entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.

Exploring convolutional neural networks for drug–drug interaction extraction

PubMed Central

Segura-Bedmar, Isabel; Martínez, Paloma

2017-01-01

Abstract Drug–drug interaction (DDI), which is a specific type of adverse drug reaction, occurs when a drug influences the level or activity of another drug. Natural language processing techniques can provide health-care professionals with a novel way of reducing the time spent reviewing the literature for potential DDIs. The current state-of-the-art for the extraction of DDIs is based on feature-engineering algorithms (such as support vector machines), which usually require considerable time and effort. One possible alternative to these approaches includes deep learning. This technique aims to automatically learn the best feature representation from the input data for a given task. The purpose of this paper is to examine whether a convolutional neural network (CNN), which only uses word embeddings as input features, can be applied successfully to classify DDIs from biomedical texts. Proposed herein, is a CNN architecture with only one hidden layer, thus making the model more computationally efficient, and we perform detailed experiments in order to determine the best settings of the model. The goal is to determine the best parameter of this basic CNN that should be considered for future research. The experimental results show that the proposed approach is promising because it attained the second position in the 2013 rankings of the DDI extraction challenge. However, it obtained worse results than previous works using neural networks with more complex architectures. PMID:28605776

Multi-Scale Voxel Segmentation for Terrestrial Lidar Data within Marshes

NASA Astrophysics Data System (ADS)

Nguyen, C. T.; Starek, M. J.; Tissot, P.; Gibeaut, J. C.

2016-12-01

The resilience of marshes to a rising sea is dependent on their elevation response. Terrestrial laser scanning (TLS) is a detailed topographic approach for accurate, dense surface measurement with high potential for monitoring of marsh surface elevation response. The dense point cloud provides a 3D representation of the surface, which includes both terrain and non-terrain objects. Extraction of topographic information requires filtering of the data into like-groups or classes, therefore, methods must be incorporated to identify structure in the data prior to creation of an end product. A voxel representation of three-dimensional space provides quantitative visualization and analysis for pattern recognition. The objectives of this study are threefold: 1) apply a multi-scale voxel approach to effectively extract geometric features from the TLS point cloud data, 2) investigate the utility of K-means and Self Organizing Map (SOM) clustering algorithms for segmentation, and 3) utilize a variety of validity indices to measure the quality of the result. TLS data were collected at a marsh site along the central Texas Gulf Coast using a Riegl VZ 400 TLS. The site consists of both exposed and vegetated surface regions. To characterize structure of the point cloud, octree segmentation is applied to create a tree data structure of voxels containing the points. The flexibility of voxels in size and point density makes this algorithm a promising candidate to locally extract statistical and geometric features of the terrain including surface normal and curvature. The characteristics of the voxel itself such as the volume and point density are also computed and assigned to each point as are laser pulse characteristics. The features extracted from the voxelization are then used as input for clustering of the points using the K-means and SOM clustering algorithms. Optimal number of clusters are then determined based on evaluation of cluster separability criterions. Results for different combinations of the feature space vector and differences between K-means and SOM clustering will be presented. The developed method provides a novel approach for compressing TLS scene complexity in marshes, such as for vegetation biomass studies or erosion monitoring.

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.

Towards real-time detection and tracking of spatio-temporal features: Blob-filaments in fusion plasma

DOE PAGES

Wu, Lingfei; Wu, Kesheng; Sim, Alex; ...

2016-06-01

A novel algorithm and implementation of real-time identification and tracking of blob-filaments in fusion reactor data is presented. Similar spatio-temporal features are important in many other applications, for example, ignition kernels in combustion and tumor cells in a medical image. This work presents an approach for extracting these features by dividing the overall task into three steps: local identification of feature cells, grouping feature cells into extended feature, and tracking movement of feature through overlapping in space. Through our extensive work in parallelization, we demonstrate that this approach can effectively make use of a large number of compute nodes tomore » detect and track blob-filaments in real time in fusion plasma. Here, on a set of 30GB fusion simulation data, we observed linear speedup on 1024 processes and completed blob detection in less than three milliseconds using Edison, a Cray XC30 system at NERSC.« less

Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics

PubMed Central

Belo, David; Gamboa, Hugo

2017-01-01

The paper presents results of machine learning approach accuracy applied analysis of cardiac activity. The study evaluates the diagnostics possibilities of the arterial hypertension by means of the short-term heart rate variability signals. Two groups were studied: 30 relatively healthy volunteers and 40 patients suffering from the arterial hypertension of II-III degree. The following machine learning approaches were studied: linear and quadratic discriminant analysis, k-nearest neighbors, support vector machine with radial basis, decision trees, and naive Bayes classifier. Moreover, in the study, different methods of feature extraction are analyzed: statistical, spectral, wavelet, and multifractal. All in all, 53 features were investigated. Investigation results show that discriminant analysis achieves the highest classification accuracy. The suggested approach of noncorrelated feature set search achieved higher results than data set based on the principal components. PMID:28831239

Comparison of hand-craft feature based SVM and CNN based deep learning framework for automatic polyp classification.

PubMed

Younghak Shin; Balasingham, Ilangko

2017-07-01

Colonoscopy is a standard method for screening polyps by highly trained physicians. Miss-detected polyps in colonoscopy are potential risk factor for colorectal cancer. In this study, we investigate an automatic polyp classification framework. We aim to compare two different approaches named hand-craft feature method and convolutional neural network (CNN) based deep learning method. Combined shape and color features are used for hand craft feature extraction and support vector machine (SVM) method is adopted for classification. For CNN approach, three convolution and pooling based deep learning framework is used for classification purpose. The proposed framework is evaluated using three public polyp databases. From the experimental results, we have shown that the CNN based deep learning framework shows better classification performance than the hand-craft feature based methods. It achieves over 90% of classification accuracy, sensitivity, specificity and precision.

Feature construction can improve diagnostic criteria for high-dimensional metabolic data in newborn screening for medium-chain acyl-CoA dehydrogenase deficiency.

PubMed

Ho, Sirikit; Lukacs, Zoltan; Hoffmann, Georg F; Lindner, Martin; Wetter, Thomas

2007-07-01

In newborn screening with tandem mass spectrometry, multiple intermediary metabolites are quantified in a single analytical run for the diagnosis of fatty-acid oxidation disorders, organic acidurias, and aminoacidurias. Published diagnostic criteria for these disorders normally incorporate a primary metabolic marker combined with secondary markers, often analyte ratios, for which the markers have been chosen to reflect metabolic pathway deviations. We applied a procedure to extract new markers and diagnostic criteria for newborn screening to the data of newborns with confirmed medium-chain acyl-CoA dehydrogenase deficiency (MCADD) and a control group from the newborn screening program, Heidelberg, Germany. We validated the results with external data of the screening center in Hamburg, Germany. We extracted new markers by performing a systematic search for analyte combinations (features) with high discriminatory performance for MCADD. To select feature thresholds, we applied automated procedures to separate controls and cases on the basis of the feature values. Finally, we built classifiers from these new markers to serve as diagnostic criteria in screening for MCADD. On the basis of chi(2) scores, we identified approximately 800 of >628,000 new analyte combinations with superior discriminatory performance compared with the best published combinations. Classifiers built with the new features achieved diagnostic sensitivities and specificities approaching 100%. Feature construction methods provide ways to disclose information hidden in the set of measured analytes. Other diagnostic tasks based on high-dimensional metabolic data might also profit from this approach.

Fast correspondences search in anatomical trees

NASA Astrophysics Data System (ADS)

dos Santos, Thiago R.; Gergel, Ingmar; Meinzer, Hans-Peter; Maier-Hein, Lena

2010-03-01

Registration of multiple medical images commonly comprises the steps feature extraction, correspondences search and transformation computation. In this paper, we present a new method for a fast and pose independent search of correspondences using as features anatomical trees such as the bronchial system in the lungs or the vessel system in the liver. Our approach scores the similarities between the trees' nodes (bifurcations) taking into account both, topological properties extracted from their graph representations and anatomical properties extracted from the trees themselves. The node assignment maximizes the global similarity (sum of the scores of each pair of assigned nodes), assuring that the matches are distributed throughout the trees. Furthermore, the proposed method is able to deal with distortions in the data, such as noise, motion, artifacts, and problems associated with the extraction method, such as missing or false branches. According to an evaluation on swine lung data sets, the method requires less than one second on average to compute the matching and yields a high rate of correct matches compared to state of the art work.

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.

Robo-Psychophysics: Extracting Behaviorally Relevant Features from the Output of Sensors on a Prosthetic Finger.

PubMed

Delhaye, Benoit P; Schluter, Erik W; Bensmaia, Sliman J

2016-01-01

Efforts are underway to restore sensorimotor function in amputees and tetraplegic patients using anthropomorphic robotic hands. For this approach to be clinically viable, sensory signals from the hand must be relayed back to the patient. To convey tactile feedback necessary for object manipulation, behaviorally relevant information must be extracted in real time from the output of sensors on the prosthesis. In the present study, we recorded the sensor output from a state-of-the-art bionic finger during the presentation of different tactile stimuli, including punctate indentations and scanned textures. Furthermore, the parameters of stimulus delivery (location, speed, direction, indentation depth, and surface texture) were systematically varied. We developed simple decoders to extract behaviorally relevant variables from the sensor output and assessed the degree to which these algorithms could reliably extract these different types of sensory information across different conditions of stimulus delivery. We then compared the performance of the decoders to that of humans in analogous psychophysical experiments. We show that straightforward decoders can extract behaviorally relevant features accurately from the sensor output and most of them outperform humans.

Photometric Supernova Classification with Machine Learning

NASA Astrophysics Data System (ADS)

Lochner, Michelle; McEwen, Jason D.; Peiris, Hiranya V.; Lahav, Ofer; Winter, Max K.

2016-08-01

Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope, given that spectroscopic confirmation of type for all supernovae discovered will be impossible. Here, we develop a multi-faceted classification pipeline, combining existing and new approaches. Our pipeline consists of two stages: extracting descriptive features from the light curves and classification using a machine learning algorithm. Our feature extraction methods vary from model-dependent techniques, namely SALT2 fits, to more independent techniques that fit parametric models to curves, to a completely model-independent wavelet approach. We cover a range of representative machine learning algorithms, including naive Bayes, k-nearest neighbors, support vector machines, artificial neural networks, and boosted decision trees (BDTs). We test the pipeline on simulated multi-band DES light curves from the Supernova Photometric Classification Challenge. Using the commonly used area under the curve (AUC) of the Receiver Operating Characteristic as a metric, we find that the SALT2 fits and the wavelet approach, with the BDTs algorithm, each achieve an AUC of 0.98, where 1 represents perfect classification. We find that a representative training set is essential for good classification, whatever the feature set or algorithm, with implications for spectroscopic follow-up. Importantly, we find that by using either the SALT2 or the wavelet feature sets with a BDT algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.

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.

A Radio-genomics Approach for Identifying High Risk Estrogen Receptor-positive Breast Cancers on DCE-MRI: Preliminary Results in Predicting OncotypeDX Risk Scores

PubMed Central

Wan, Tao; Bloch, B. Nicolas; Plecha, Donna; Thompson, CheryI L.; Gilmore, Hannah; Jaffe, Carl; Harris, Lyndsay; Madabhushi, Anant

2016-01-01

To identify computer extracted imaging features for estrogen receptor (ER)-positive breast cancers on dynamic contrast en-hanced (DCE)-MRI that are correlated with the low and high OncotypeDX risk categories. We collected 96 ER-positivebreast lesions with low (<18, N = 55) and high (>30, N = 41) OncotypeDX recurrence scores. Each lesion was quantitatively charac-terize via 6 shape features, 3 pharmacokinetics, 4 enhancement kinetics, 4 intensity kinetics, 148 textural kinetics, 5 dynamic histogram of oriented gradient (DHoG), and 6 dynamic local binary pattern (DLBP) features. The extracted features were evaluated by a linear discriminant analysis (LDA) classifier in terms of their ability to distinguish low and high OncotypeDX risk categories. Classification performance was evaluated by area under the receiver operator characteristic curve (Az). The DHoG and DLBP achieved Az values of 0.84 and 0.80, respectively. The 6 top features identified via feature selection were subsequently combined with the LDA classifier to yield an Az of 0.87. The correlation analysis showed that DHoG (ρ = 0.85, P < 0.001) and DLBP (ρ = 0.83, P < 0.01) were significantly associated with the low and high risk classifications from the OncotypeDX assay. Our results indicated that computer extracted texture features of DCE-MRI were highly correlated with the high and low OncotypeDX risk categories for ER-positive cancers. PMID:26887643

EEG classification for motor imagery and resting state in BCI applications using multi-class Adaboost extreme learning machine

NASA Astrophysics Data System (ADS)

Gao, Lin; Cheng, Wei; Zhang, Jinhua; Wang, Jue

2016-08-01

Brain-computer interface (BCI) systems provide an alternative communication and control approach for people with limited motor function. Therefore, the feature extraction and classification approach should differentiate the relative unusual state of motion intention from a common resting state. In this paper, we sought a novel approach for multi-class classification in BCI applications. We collected electroencephalographic (EEG) signals registered by electrodes placed over the scalp during left hand motor imagery, right hand motor imagery, and resting state for ten healthy human subjects. We proposed using the Kolmogorov complexity (Kc) for feature extraction and a multi-class Adaboost classifier with extreme learning machine as base classifier for classification, in order to classify the three-class EEG samples. An average classification accuracy of 79.5% was obtained for ten subjects, which greatly outperformed commonly used approaches. Thus, it is concluded that the proposed method could improve the performance for classification of motor imagery tasks for multi-class samples. It could be applied in further studies to generate the control commands to initiate the movement of a robotic exoskeleton or orthosis, which finally facilitates the rehabilitation of disabled people.

Application of Fourier analysis to multispectral/spatial recognition

NASA Technical Reports Server (NTRS)

Hornung, R. J.; Smith, J. A.

1973-01-01

One approach for investigating spectral response from materials is to consider spatial features of the response. This might be accomplished by considering the Fourier spectrum of the spatial response. The Fourier Transform may be used in a one-dimensional to multidimensional analysis of more than one channel of data. The two-dimensional transform represents the Fraunhofer diffraction pattern of the image in optics and has certain invariant features. Physically the diffraction pattern contains spatial features which are possibly unique to a given configuration or classification type. Different sampling strategies may be used to either enhance geometrical differences or extract additional features.

Signal recognition and parameter estimation of BPSK-LFM combined modulation

NASA Astrophysics Data System (ADS)

Long, Chao; Zhang, Lin; Liu, Yu

2015-07-01

Intra-pulse analysis plays an important role in electronic warfare. Intra-pulse feature abstraction focuses on primary parameters such as instantaneous frequency, modulation, and symbol rate. In this paper, automatic modulation recognition and feature extraction for combined BPSK-LFM modulation signals based on decision theoretic approach is studied. The simulation results show good recognition effect and high estimation precision, and the system is easy to be realized.

Nonlinear, non-stationary image processing technique for eddy current NDE

NASA Astrophysics Data System (ADS)

Yang, Guang; Dib, Gerges; Kim, Jaejoon; Zhang, Lu; Xin, Junjun; Udpa, Lalita

2012-05-01

Automatic analysis of eddy current (EC) data has facilitated the analysis of large volumes of data generated in the inspection of steam generator tubes in nuclear power plants. The traditional procedure for analysis of EC data includes data calibration, pre-processing, region of interest (ROI) detection, feature extraction and classification. Accurate ROI detection has been enhanced by pre-processing, which involves reducing noise and other undesirable components as well as enhancing defect indications in the raw measurement. This paper presents the Hilbert-Huang Transform (HHT) for feature extraction and support vector machine (SVM) for classification. The performance is shown to significantly better than the existing rule based classification approach used in industry.

Multiple degree of freedom optical pattern recognition

NASA Technical Reports Server (NTRS)

Casasent, D.

1987-01-01

Three general optical approaches to multiple degree of freedom object pattern recognition (where no stable object rest position exists) are advanced. These techniques include: feature extraction, correlation, and artificial intelligence. The details of the various processors are advanced together with initial results.

Statistical Approach To Extraction Of Texture In SAR

NASA Technical Reports Server (NTRS)

Rignot, Eric J.; Kwok, Ronald

1992-01-01

Improved statistical method of extraction of textural features in synthetic-aperture-radar (SAR) images takes account of effects of scheme used to sample raw SAR data, system noise, resolution of radar equipment, and speckle. Treatment of speckle incorporated into overall statistical treatment of speckle, system noise, and natural variations in texture. One computes speckle auto-correlation function from system transfer function that expresses effect of radar aperature and incorporates range and azimuth resolutions.

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.

Modelling and representation issues in automated feature extraction from aerial and satellite images

NASA Astrophysics Data System (ADS)

Sowmya, Arcot; Trinder, John

New digital systems for the processing of photogrammetric and remote sensing images have led to new approaches to information extraction for mapping and Geographic Information System (GIS) applications, with the expectation that data can become more readily available at a lower cost and with greater currency. Demands for mapping and GIS data are increasing as well for environmental assessment and monitoring. Hence, researchers from the fields of photogrammetry and remote sensing, as well as computer vision and artificial intelligence, are bringing together their particular skills for automating these tasks of information extraction. The paper will review some of the approaches used in knowledge representation and modelling for machine vision, and give examples of their applications in research for image understanding of aerial and satellite imagery.

Hierarchical graph-based segmentation for extracting road networks from high-resolution satellite images

NASA Astrophysics Data System (ADS)

Alshehhi, Rasha; Marpu, Prashanth Reddy

2017-04-01

Extraction of road networks in urban areas from remotely sensed imagery plays an important role in many urban applications (e.g. road navigation, geometric correction of urban remote sensing images, updating geographic information systems, etc.). It is normally difficult to accurately differentiate road from its background due to the complex geometry of the buildings and the acquisition geometry of the sensor. In this paper, we present a new method for extracting roads from high-resolution imagery based on hierarchical graph-based image segmentation. The proposed method consists of: 1. Extracting features (e.g., using Gabor and morphological filtering) to enhance the contrast between road and non-road pixels, 2. Graph-based segmentation consisting of (i) Constructing a graph representation of the image based on initial segmentation and (ii) Hierarchical merging and splitting of image segments based on color and shape features, and 3. Post-processing to remove irregularities in the extracted road segments. Experiments are conducted on three challenging datasets of high-resolution images to demonstrate the proposed method and compare with other similar approaches. The results demonstrate the validity and superior performance of the proposed method for road extraction in urban areas.

Feature detection on 3D images of dental imprints

NASA Astrophysics Data System (ADS)

Mokhtari, Marielle; Laurendeau, Denis

1994-09-01

A computer vision approach for the extraction of feature points on 3D images of dental imprints is presented. The position of feature points are needed for the measurement of a set of parameters for automatic diagnosis of malocclusion problems in orthodontics. The system for the acquisition of the 3D profile of the imprint, the procedure for the detection of the interstices between teeth, and the approach for the identification of the type of tooth are described, as well as the algorithm for the reconstruction of the surface of each type of tooth. A new approach for the detection of feature points, called the watershed algorithm, is described in detail. The algorithm is a two-stage procedure which tracks the position of local minima at four different scales and produces a final map of the position of the minima. Experimental results of the application of the watershed algorithm on actual 3D images of dental imprints are presented for molars, premolars and canines. The segmentation approach for the analysis of the shape of incisors is also described in detail.

Malay sentiment analysis based on combined classification approaches and Senti-lexicon algorithm.

PubMed

Al-Saffar, Ahmed; Awang, Suryanti; Tao, Hai; Omar, Nazlia; Al-Saiagh, Wafaa; Al-Bared, Mohammed

2018-01-01

Sentiment analysis techniques are increasingly exploited to categorize the opinion text to one or more predefined sentiment classes for the creation and automated maintenance of review-aggregation websites. In this paper, a Malay sentiment analysis classification model is proposed to improve classification performances based on the semantic orientation and machine learning approaches. First, a total of 2,478 Malay sentiment-lexicon phrases and words are assigned with a synonym and stored with the help of more than one Malay native speaker, and the polarity is manually allotted with a score. In addition, the supervised machine learning approaches and lexicon knowledge method are combined for Malay sentiment classification with evaluating thirteen features. Finally, three individual classifiers and a combined classifier are used to evaluate the classification accuracy. In experimental results, a wide-range of comparative experiments is conducted on a Malay Reviews Corpus (MRC), and it demonstrates that the feature extraction improves the performance of Malay sentiment analysis based on the combined classification. However, the results depend on three factors, the features, the number of features and the classification approach.

Malay sentiment analysis based on combined classification approaches and Senti-lexicon algorithm

PubMed Central

Awang, Suryanti; Tao, Hai; Omar, Nazlia; Al-Saiagh, Wafaa; Al-bared, Mohammed

2018-01-01

Sentiment analysis techniques are increasingly exploited to categorize the opinion text to one or more predefined sentiment classes for the creation and automated maintenance of review-aggregation websites. In this paper, a Malay sentiment analysis classification model is proposed to improve classification performances based on the semantic orientation and machine learning approaches. First, a total of 2,478 Malay sentiment-lexicon phrases and words are assigned with a synonym and stored with the help of more than one Malay native speaker, and the polarity is manually allotted with a score. In addition, the supervised machine learning approaches and lexicon knowledge method are combined for Malay sentiment classification with evaluating thirteen features. Finally, three individual classifiers and a combined classifier are used to evaluate the classification accuracy. In experimental results, a wide-range of comparative experiments is conducted on a Malay Reviews Corpus (MRC), and it demonstrates that the feature extraction improves the performance of Malay sentiment analysis based on the combined classification. However, the results depend on three factors, the features, the number of features and the classification approach. PMID:29684036

Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors

PubMed Central

Li, Frédéric; Nisar, Muhammad Adeel; Köping, Lukas; Grzegorzek, Marcin

2018-01-01

Getting a good feature representation of data is paramount for Human Activity Recognition (HAR) using wearable sensors. An increasing number of feature learning approaches—in particular deep-learning based—have been proposed to extract an effective feature representation by analyzing large amounts of data. However, getting an objective interpretation of their performances faces two problems: the lack of a baseline evaluation setup, which makes a strict comparison between them impossible, and the insufficiency of implementation details, which can hinder their use. In this paper, we attempt to address both issues: we firstly propose an evaluation framework allowing a rigorous comparison of features extracted by different methods, and use it to carry out extensive experiments with state-of-the-art feature learning approaches. We then provide all the codes and implementation details to make both the reproduction of the results reported in this paper and the re-use of our framework easier for other researchers. Our studies carried out on the OPPORTUNITY and UniMiB-SHAR datasets highlight the effectiveness of hybrid deep-learning architectures involving convolutional and Long-Short-Term-Memory (LSTM) to obtain features characterising both short- and long-term time dependencies in the data. PMID:29495310

Image processing based automatic diagnosis of glaucoma using wavelet features of segmented optic disc from fundus image.

PubMed

Singh, Anushikha; Dutta, Malay Kishore; ParthaSarathi, M; Uher, Vaclav; Burget, Radim

2016-02-01

Glaucoma is a disease of the retina which is one of the most common causes of permanent blindness worldwide. This paper presents an automatic image processing based method for glaucoma diagnosis from the digital fundus image. In this paper wavelet feature extraction has been followed by optimized genetic feature selection combined with several learning algorithms and various parameter settings. Unlike the existing research works where the features are considered from the complete fundus or a sub image of the fundus, this work is based on feature extraction from the segmented and blood vessel removed optic disc to improve the accuracy of identification. The experimental results presented in this paper indicate that the wavelet features of the segmented optic disc image are clinically more significant in comparison to features of the whole or sub fundus image in the detection of glaucoma from fundus image. Accuracy of glaucoma identification achieved in this work is 94.7% and a comparison with existing methods of glaucoma detection from fundus image indicates that the proposed approach has improved accuracy of classification. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

A Modeling Approach for Burn Scar Assessment Using Natural Features and Elastic Property

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

Tsap, L V; Zhang, Y; Goldgof, D B

2004-04-02

A modeling approach is presented for quantitative burn scar assessment. Emphases are given to: (1) constructing a finite element model from natural image features with an adaptive mesh, and (2) quantifying the Young's modulus of scars using the finite element model and the regularization method. A set of natural point features is extracted from the images of burn patients. A Delaunay triangle mesh is then generated that adapts to the point features. A 3D finite element model is built on top of the mesh with the aid of range images providing the depth information. The Young's modulus of scars ismore » quantified with a simplified regularization functional, assuming that the knowledge of scar's geometry is available. The consistency between the Relative Elasticity Index and the physician's rating based on the Vancouver Scale (a relative scale used to rate burn scars) indicates that the proposed modeling approach has high potentials for image-based quantitative burn scar assessment.« less

Effective Moment Feature Vectors for Protein Domain Structures

PubMed Central

Shi, Jian-Yu; Yiu, Siu-Ming; Zhang, Yan-Ning; Chin, Francis Yuk-Lun

2013-01-01

Imaging processing techniques have been shown to be useful in studying protein domain structures. The idea is to represent the pairwise distances of any two residues of the structure in a 2D distance matrix (DM). Features and/or submatrices are extracted from this DM to represent a domain. Existing approaches, however, may involve a large number of features (100–400) or complicated mathematical operations. Finding fewer but more effective features is always desirable. In this paper, based on some key observations on DMs, we are able to decompose a DM image into four basic binary images, each representing the structural characteristics of a fundamental secondary structure element (SSE) or a motif in the domain. Using the concept of moments in image processing, we further derive 45 structural features based on the four binary images. Together with 4 features extracted from the basic images, we represent the structure of a domain using 49 features. We show that our feature vectors can represent domain structures effectively in terms of the following. (1) We show a higher accuracy for domain classification. (2) We show a clear and consistent distribution of domains using our proposed structural vector space. (3) We are able to cluster the domains according to our moment features and demonstrate a relationship between structural variation and functional diversity. PMID:24391828

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.

Comparison of Single and Multi-Scale Method for Leaf and Wood Points Classification from Terrestrial Laser Scanning Data

NASA Astrophysics Data System (ADS)

Wei, Hongqiang; Zhou, Guiyun; Zhou, Junjie

2018-04-01

The classification of leaf and wood points is an essential preprocessing step for extracting inventory measurements and canopy characterization of trees from the terrestrial laser scanning (TLS) data. The geometry-based approach is one of the widely used classification method. In the geometry-based method, it is common practice to extract salient features at one single scale before the features are used for classification. It remains unclear how different scale(s) used affect the classification accuracy and efficiency. To assess the scale effect on the classification accuracy and efficiency, we extracted the single-scale and multi-scale salient features from the point clouds of two oak trees of different sizes and conducted the classification on leaf and wood. Our experimental results show that the balanced accuracy of the multi-scale method is higher than the average balanced accuracy of the single-scale method by about 10 % for both trees. The average speed-up ratio of single scale classifiers over multi-scale classifier for each tree is higher than 30.

Thyroid Nodule Classification in Ultrasound Images by Fine-Tuning Deep Convolutional Neural Network.

PubMed

Chi, Jianning; Walia, Ekta; Babyn, Paul; Wang, Jimmy; Groot, Gary; Eramian, Mark

2017-08-01

With many thyroid nodules being incidentally detected, it is important to identify as many malignant nodules as possible while excluding those that are highly likely to be benign from fine needle aspiration (FNA) biopsies or surgeries. This paper presents a computer-aided diagnosis (CAD) system for classifying thyroid nodules in ultrasound images. We use deep learning approach to extract features from thyroid ultrasound images. Ultrasound images are pre-processed to calibrate their scale and remove the artifacts. A pre-trained GoogLeNet model is then fine-tuned using the pre-processed image samples which leads to superior feature extraction. The extracted features of the thyroid ultrasound images are sent to a Cost-sensitive Random Forest classifier to classify the images into "malignant" and "benign" cases. The experimental results show the proposed fine-tuned GoogLeNet model achieves excellent classification performance, attaining 98.29% classification accuracy, 99.10% sensitivity and 93.90% specificity for the images in an open access database (Pedraza et al. 16), while 96.34% classification accuracy, 86% sensitivity and 99% specificity for the images in our local health region database.

Dynamic adaptive learning for decision-making supporting systems

NASA Astrophysics Data System (ADS)

He, Haibo; Cao, Yuan; Chen, Sheng; Desai, Sachi; Hohil, Myron E.

2008-03-01

This paper proposes a novel adaptive learning method for data mining in support of decision-making systems. Due to the inherent characteristics of information ambiguity/uncertainty, high dimensionality and noisy in many homeland security and defense applications, such as surveillances, monitoring, net-centric battlefield, and others, it is critical to develop autonomous learning methods to efficiently learn useful information from raw data to help the decision making process. The proposed method is based on a dynamic learning principle in the feature spaces. Generally speaking, conventional approaches of learning from high dimensional data sets include various feature extraction (principal component analysis, wavelet transform, and others) and feature selection (embedded approach, wrapper approach, filter approach, and others) methods. However, very limited understandings of adaptive learning from different feature spaces have been achieved. We propose an integrative approach that takes advantages of feature selection and hypothesis ensemble techniques to achieve our goal. Based on the training data distributions, a feature score function is used to provide a measurement of the importance of different features for learning purpose. Then multiple hypotheses are iteratively developed in different feature spaces according to their learning capabilities. Unlike the pre-set iteration steps in many of the existing ensemble learning approaches, such as adaptive boosting (AdaBoost) method, the iterative learning process will automatically stop when the intelligent system can not provide a better understanding than a random guess in that particular subset of feature spaces. Finally, a voting algorithm is used to combine all the decisions from different hypotheses to provide the final prediction results. Simulation analyses of the proposed method on classification of different US military aircraft databases show the effectiveness of this method.

An Overview of Biomolecular Event Extraction from Scientific Documents

PubMed Central

Vanegas, Jorge A.; Matos, Sérgio; González, Fabio; Oliveira, José L.

2015-01-01

This paper presents a review of state-of-the-art approaches to automatic extraction of biomolecular events from scientific texts. Events involving biomolecules such as genes, transcription factors, or enzymes, for example, have a central role in biological processes and functions and provide valuable information for describing physiological and pathogenesis mechanisms. Event extraction from biomedical literature has a broad range of applications, including support for information retrieval, knowledge summarization, and information extraction and discovery. However, automatic event extraction is a challenging task due to the ambiguity and diversity of natural language and higher-level linguistic phenomena, such as speculations and negations, which occur in biological texts and can lead to misunderstanding or incorrect interpretation. Many strategies have been proposed in the last decade, originating from different research areas such as natural language processing, machine learning, and statistics. This review summarizes the most representative approaches in biomolecular event extraction and presents an analysis of the current state of the art and of commonly used methods, features, and tools. Finally, current research trends and future perspectives are also discussed. PMID:26587051

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.

Tweaked residual convolutional network for face alignment

NASA Astrophysics Data System (ADS)

Du, Wenchao; Li, Ke; Zhao, Qijun; Zhang, Yi; Chen, Hu

2017-08-01

We propose a novel Tweaked Residual Convolutional Network approach for face alignment with two-level convolutional networks architecture. Specifically, the first-level Tweaked Convolutional Network (TCN) module predicts the landmark quickly but accurately enough as a preliminary, by taking low-resolution version of the detected face holistically as the input. The following Residual Convolutional Networks (RCN) module progressively refines the landmark by taking as input the local patch extracted around the predicted landmark, particularly, which allows the Convolutional Neural Network (CNN) to extract local shape-indexed features to fine tune landmark position. Extensive evaluations show that the proposed Tweaked Residual Convolutional Network approach outperforms existing methods.

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.

Using Fractal and Local Binary Pattern Features for Classification of ECOG Motor Imagery Tasks Obtained from the Right Brain Hemisphere.

PubMed

Xu, Fangzhou; Zhou, Weidong; Zhen, Yilin; Yuan, Qi; Wu, Qi

2016-09-01

The feature extraction and classification of brain signal is very significant in brain-computer interface (BCI). In this study, we describe an algorithm for motor imagery (MI) classification of electrocorticogram (ECoG)-based BCI. The proposed approach employs multi-resolution fractal measures and local binary pattern (LBP) operators to form a combined feature for characterizing an ECoG epoch recording from the right hemisphere of the brain. A classifier is trained by using the gradient boosting in conjunction with ordinary least squares (OLS) method. The fractal intercept, lacunarity and LBP features are extracted to classify imagined movements of either the left small finger or the tongue. Experimental results on dataset I of BCI competition III demonstrate the superior performance of our method. The cross-validation accuracy and accuracy is 90.6% and 95%, respectively. Furthermore, the low computational burden of this method makes it a promising candidate for real-time BCI systems.

Pedestrian Detection and Tracking from Low-Resolution Unmanned Aerial Vehicle Thermal Imagery

PubMed Central

Ma, Yalong; Wu, Xinkai; Yu, Guizhen; Xu, Yongzheng; Wang, Yunpeng

2016-01-01

Driven by the prominent thermal signature of humans and following the growing availability of unmanned aerial vehicles (UAVs), more and more research efforts have been focusing on the detection and tracking of pedestrians using thermal infrared images recorded from UAVs. However, pedestrian detection and tracking from the thermal images obtained from UAVs pose many challenges due to the low-resolution of imagery, platform motion, image instability and the relatively small size of the objects. This research tackles these challenges by proposing a pedestrian detection and tracking system. A two-stage blob-based approach is first developed for pedestrian detection. This approach first extracts pedestrian blobs using the regional gradient feature and geometric constraints filtering and then classifies the detected blobs by using a linear Support Vector Machine (SVM) with a hybrid descriptor, which sophisticatedly combines Histogram of Oriented Gradient (HOG) and Discrete Cosine Transform (DCT) features in order to achieve accurate detection. This research further proposes an approach for pedestrian tracking. This approach employs the feature tracker with the update of detected pedestrian location to track pedestrian objects from the registered videos and extracts the motion trajectory data. The proposed detection and tracking approaches have been evaluated by multiple different datasets, and the results illustrate the effectiveness of the proposed methods. This research is expected to significantly benefit many transportation applications, such as the multimodal traffic performance measure, pedestrian behavior study and pedestrian-vehicle crash analysis. Future work will focus on using fused thermal and visual images to further improve the detection efficiency and effectiveness. PMID:27023564

Pedestrian Detection and Tracking from Low-Resolution Unmanned Aerial Vehicle Thermal Imagery.

PubMed

Ma, Yalong; Wu, Xinkai; Yu, Guizhen; Xu, Yongzheng; Wang, Yunpeng

2016-03-26

Driven by the prominent thermal signature of humans and following the growing availability of unmanned aerial vehicles (UAVs), more and more research efforts have been focusing on the detection and tracking of pedestrians using thermal infrared images recorded from UAVs. However, pedestrian detection and tracking from the thermal images obtained from UAVs pose many challenges due to the low-resolution of imagery, platform motion, image instability and the relatively small size of the objects. This research tackles these challenges by proposing a pedestrian detection and tracking system. A two-stage blob-based approach is first developed for pedestrian detection. This approach first extracts pedestrian blobs using the regional gradient feature and geometric constraints filtering and then classifies the detected blobs by using a linear Support Vector Machine (SVM) with a hybrid descriptor, which sophisticatedly combines Histogram of Oriented Gradient (HOG) and Discrete Cosine Transform (DCT) features in order to achieve accurate detection. This research further proposes an approach for pedestrian tracking. This approach employs the feature tracker with the update of detected pedestrian location to track pedestrian objects from the registered videos and extracts the motion trajectory data. The proposed detection and tracking approaches have been evaluated by multiple different datasets, and the results illustrate the effectiveness of the proposed methods. This research is expected to significantly benefit many transportation applications, such as the multimodal traffic performance measure, pedestrian behavior study and pedestrian-vehicle crash analysis. Future work will focus on using fused thermal and visual images to further improve the detection efficiency and effectiveness.

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.

Can Laws Be a Potential PET Image Texture Analysis Approach for Evaluation of Tumor Heterogeneity and Histopathological Characteristics in NSCLC?

PubMed

Karacavus, Seyhan; Yılmaz, Bülent; Tasdemir, Arzu; Kayaaltı, Ömer; Kaya, Eser; İçer, Semra; Ayyıldız, Oguzhan

2018-04-01

We investigated the association between the textural features obtained from 18 F-FDG images, metabolic parameters (SUVmax , SUVmean, MTV, TLG), and tumor histopathological characteristics (stage and Ki-67 proliferation index) in non-small cell lung cancer (NSCLC). The FDG-PET images of 67 patients with NSCLC were evaluated. MATLAB technical computing language was employed in the extraction of 137 features by using first order statistics (FOS), gray-level co-occurrence matrix (GLCM), gray-level run length matrix (GLRLM), and Laws' texture filters. Textural features and metabolic parameters were statistically analyzed in terms of good discrimination power between tumor stages, and selected features/parameters were used in the automatic classification by k-nearest neighbors (k-NN) and support vector machines (SVM). We showed that one textural feature (gray-level nonuniformity, GLN) obtained using GLRLM approach and nine textural features using Laws' approach were successful in discriminating all tumor stages, unlike metabolic parameters. There were significant correlations between Ki-67 index and some of the textural features computed using Laws' method (r = 0.6, p = 0.013). In terms of automatic classification of tumor stage, the accuracy was approximately 84% with k-NN classifier (k = 3) and SVM, using selected five features. Texture analysis of FDG-PET images has a potential to be an objective tool to assess tumor histopathological characteristics. The textural features obtained using Laws' approach could be useful in the discrimination of tumor stage.

Hydro-geomorphic connectivity and landslide features extraction to identifying potential threats and hazardous areas

NASA Astrophysics Data System (ADS)

Tarolli, Paolo; Fuller, Ian C.; Basso, Federica; Cavalli, Marco; Sofia, Giulia

2017-04-01

Hydro-geomorphic connectivity has significantly emerged as a new concept to understand the transfer of surface water and sediment through landscapes. A further scientific challenge is determining how the concept can be used to enable sustainable land and water management. This research proposes an interesting approach to integrating remote sensing techniques, connectivity theory, and geomorphometry based on high-resolution digital terrain model (HR-DTMs) to automatically extract landslides crowns and gully erosion, to determine the different rate of connectivity among the main extracted features and the river network, and thus determine a possible categorization of hazardous areas. The study takes place in two mountainous regions in the Wellington Region (New Zealand). The methodology is a three step approach. Firstly, we performed an automatic detection of the likely landslides crowns through the use of thresholds obtained by the statistical analysis of the variability of landform curvature. After that, the research considered the Connectivity Index to analyse how a complex and rugged topography induces large variations in erosion and sediment delivery in the two catchments. Lastly, the two methods have been integrated to create a unique procedure able to classify the different rate of connectivity among the main features and the river network and thus identifying potential threats and hazardous areas. The methodology is fast, and it can produce a detailed and updated inventory map that could be a key tool for erosional and sediment delivery hazard mitigation. This fast and simple method can be a useful tool to manage emergencies giving priorities to more failure-prone zones. Furthermore, it could be considered to do a preliminary interpretations of geomorphological phenomena and more in general, it could be the base to develop inventory maps. References Cavalli M, Trevisani S, Comiti F, Marchi L. 2013. Geomorphometric assessment of spatial sediment connectivity in small Alpine catchments. Geomorphology 188: 31-41 DOI: 10.1016/j.geomorph.2012.05.007 Sofia G, Dalla Fontana G, Tarolli P. 2014. High-resolution topography and anthropogenic feature extraction: testing geomorphometric parameters in floodplains. Hydrological Processes 28 (4): 2046-2061 DOI: 10.1002/hyp.9727 Tarolli P, Sofia G, Dalla Fontana G. 2012. Geomorphic features extraction from high-resolution topography: landslide crowns and bank erosion. Natural Hazards 61 (1): 65-83 DOI: 10.1007/s11069-010-9695-2

Learning representative features for facial images based on a modified principal component analysis

NASA Astrophysics Data System (ADS)

Averkin, Anton; Potapov, Alexey

2013-05-01

The paper is devoted to facial image analysis and particularly deals with the problem of automatic evaluation of the attractiveness of human faces. We propose a new approach for automatic construction of feature space based on a modified principal component analysis. Input data sets for the algorithm are the learning data sets of facial images, which are rated by one person. The proposed approach allows one to extract features of the individual subjective face beauty perception and to predict attractiveness values for new facial images, which were not included into a learning data set. The Pearson correlation coefficient between values predicted by our method for new facial images and personal attractiveness estimation values equals to 0.89. This means that the new approach proposed is promising and can be used for predicting subjective face attractiveness values in real systems of the facial images analysis.

Hidden discriminative features extraction for supervised high-order time series modeling.

PubMed

Nguyen, Ngoc Anh Thi; Yang, Hyung-Jeong; Kim, Sunhee

2016-11-01

In this paper, an orthogonal Tucker-decomposition-based extraction of high-order discriminative subspaces from a tensor-based time series data structure is presented, named as Tensor Discriminative Feature Extraction (TDFE). TDFE relies on the employment of category information for the maximization of the between-class scatter and the minimization of the within-class scatter to extract optimal hidden discriminative feature subspaces that are simultaneously spanned by every modality for supervised tensor modeling. In this context, the proposed tensor-decomposition method provides the following benefits: i) reduces dimensionality while robustly mining the underlying discriminative features, ii) results in effective interpretable features that lead to an improved classification and visualization, and iii) reduces the processing time during the training stage and the filtering of the projection by solving the generalized eigenvalue issue at each alternation step. Two real third-order tensor-structures of time series datasets (an epilepsy electroencephalogram (EEG) that is modeled as channel×frequency bin×time frame and a microarray data that is modeled as gene×sample×time) were used for the evaluation of the TDFE. The experiment results corroborate the advantages of the proposed method with averages of 98.26% and 89.63% for the classification accuracies of the epilepsy dataset and the microarray dataset, respectively. These performance averages represent an improvement on those of the matrix-based algorithms and recent tensor-based, discriminant-decomposition approaches; this is especially the case considering the small number of samples that are used in practice. Copyright © 2016 Elsevier Ltd. All rights reserved.

Computer extracted texture features on T2w MRI to predict biochemical recurrence following radiation therapy for prostate cancer

NASA Astrophysics Data System (ADS)

Ginsburg, Shoshana B.; Rusu, Mirabela; Kurhanewicz, John; Madabhushi, Anant

2014-03-01

In this study we explore the ability of a novel machine learning approach, in conjunction with computer-extracted features describing prostate cancer morphology on pre-treatment MRI, to predict whether a patient will develop biochemical recurrence within ten years of radiation therapy. Biochemical recurrence, which is characterized by a rise in serum prostate-specific antigen (PSA) of at least 2 ng/mL above the nadir PSA, is associated with increased risk of metastasis and prostate cancer-related mortality. Currently, risk of biochemical recurrence is predicted by the Kattan nomogram, which incorporates several clinical factors to predict the probability of recurrence-free survival following radiation therapy (but has limited prediction accuracy). Semantic attributes on T2w MRI, such as the presence of extracapsular extension and seminal vesicle invasion and surrogate measure- ments of tumor size, have also been shown to be predictive of biochemical recurrence risk. While the correlation between biochemical recurrence and factors like tumor stage, Gleason grade, and extracapsular spread are well- documented, it is less clear how to predict biochemical recurrence in the absence of extracapsular spread and for small tumors fully contained in the capsule. Computer{extracted texture features, which quantitatively de- scribe tumor micro-architecture and morphology on MRI, have been shown to provide clues about a tumor's aggressiveness. However, while computer{extracted features have been employed for predicting cancer presence and grade, they have not been evaluated in the context of predicting risk of biochemical recurrence. This work seeks to evaluate the role of computer-extracted texture features in predicting risk of biochemical recurrence on a cohort of sixteen patients who underwent pre{treatment 1.5 Tesla (T) T2w MRI. We extract a combination of first-order statistical, gradient, co-occurrence, and Gabor wavelet features from T2w MRI. To identify which of these T2w MRI texture features are potential independent prognostic markers of PSA failure, we implement a partial least squares (PLS) method to embed the data in a low{dimensional space and then use the variable importance in projections (VIP) method to quantify the contributions of individual features to classification on the PLS embedding. In spite of the poor resolution of the 1.5 T MRI data, we are able to identify three Gabor wavelet features that, in conjunction with a logistic regression classifier, yield an area under the receiver operating characteristic curve of 0.83 for predicting the probability of biochemical recurrence following radiation therapy. In comparison to both the Kattan nomogram and semantic MRI attributes, the ability of these three computer-extracted features to predict biochemical recurrence risk is demonstrated.

Text feature extraction based on deep learning: a review.

PubMed

Liang, Hong; Sun, Xiao; Sun, Yunlei; Gao, Yuan

2017-01-01

Selection of text feature item is a basic and important matter for text mining and information retrieval. Traditional methods of feature extraction require handcrafted features. To hand-design, an effective feature is a lengthy process, but aiming at new applications, deep learning enables to acquire new effective feature representation from training data. As a new feature extraction method, deep learning has made achievements in text mining. The major difference between deep learning and conventional methods is that deep learning automatically learns features from big data, instead of adopting handcrafted features, which mainly depends on priori knowledge of designers and is highly impossible to take the advantage of big data. Deep learning can automatically learn feature representation from big data, including millions of parameters. This thesis outlines the common methods used in text feature extraction first, and then expands frequently used deep learning methods in text feature extraction and its applications, and forecasts the application of deep learning in feature extraction.

Adaptive Local Spatiotemporal Features from RGB-D Data for One-Shot Learning Gesture Recognition

PubMed Central

Lin, Jia; Ruan, Xiaogang; Yu, Naigong; Yang, Yee-Hong

2016-01-01

Noise and constant empirical motion constraints affect the extraction of distinctive spatiotemporal features from one or a few samples per gesture class. To tackle these problems, an adaptive local spatiotemporal feature (ALSTF) using fused RGB-D data is proposed. First, motion regions of interest (MRoIs) are adaptively extracted using grayscale and depth velocity variance information to greatly reduce the impact of noise. Then, corners are used as keypoints if their depth, and velocities of grayscale and of depth meet several adaptive local constraints in each MRoI. With further filtering of noise, an accurate and sufficient number of keypoints is obtained within the desired moving body parts (MBPs). Finally, four kinds of multiple descriptors are calculated and combined in extended gradient and motion spaces to represent the appearance and motion features of gestures. The experimental results on the ChaLearn gesture, CAD-60 and MSRDailyActivity3D datasets demonstrate that the proposed feature achieves higher performance compared with published state-of-the-art approaches under the one-shot learning setting and comparable accuracy under the leave-one-out cross validation. PMID:27999337

Adaptive Local Spatiotemporal Features from RGB-D Data for One-Shot Learning Gesture Recognition.

PubMed

Lin, Jia; Ruan, Xiaogang; Yu, Naigong; Yang, Yee-Hong

2016-12-17

Noise and constant empirical motion constraints affect the extraction of distinctive spatiotemporal features from one or a few samples per gesture class. To tackle these problems, an adaptive local spatiotemporal feature (ALSTF) using fused RGB-D data is proposed. First, motion regions of interest (MRoIs) are adaptively extracted using grayscale and depth velocity variance information to greatly reduce the impact of noise. Then, corners are used as keypoints if their depth, and velocities of grayscale and of depth meet several adaptive local constraints in each MRoI. With further filtering of noise, an accurate and sufficient number of keypoints is obtained within the desired moving body parts (MBPs). Finally, four kinds of multiple descriptors are calculated and combined in extended gradient and motion spaces to represent the appearance and motion features of gestures. The experimental results on the ChaLearn gesture, CAD-60 and MSRDailyActivity3D datasets demonstrate that the proposed feature achieves higher performance compared with published state-of-the-art approaches under the one-shot learning setting and comparable accuracy under the leave-one-out cross validation.

A multistage approach to improve performance of computer-aided detection of pulmonary embolisms depicted on CT images: preliminary investigation.

PubMed

Park, Sang Cheol; Chapman, Brian E; Zheng, Bin

2011-06-01

This study developed a computer-aided detection (CAD) scheme for pulmonary embolism (PE) detection and investigated several approaches to improve CAD performance. In the study, 20 computed tomography examinations with various lung diseases were selected, which include 44 verified PE lesions. The proposed CAD scheme consists of five basic steps: 1) lung segmentation; 2) PE candidate extraction using an intensity mask and tobogganing region growing; 3) PE candidate feature extraction; 4) false-positive (FP) reduction using an artificial neural network (ANN); and 5) a multifeature-based k-nearest neighbor for positive/negative classification. In this study, we also investigated the following additional methods to improve CAD performance: 1) grouping 2-D detected features into a single 3-D object; 2) selecting features with a genetic algorithm (GA); and 3) limiting the number of allowed suspicious lesions to be cued in one examination. The results showed that 1) CAD scheme using tobogganing, an ANN, and grouping method achieved the maximum detection sensitivity of 79.2%; 2) the maximum scoring method achieved the superior performance over other scoring fusion methods; 3) GA was able to delete "redundant" features and further improve CAD performance; and 4) limiting the maximum number of cued lesions in an examination reduced FP rate by 5.3 times. Combining these approaches, CAD scheme achieved 63.2% detection sensitivity with 18.4 FP lesions per examination. The study suggested that performance of CAD schemes for PE detection depends on many factors that include 1) optimizing the 2-D region grouping and scoring methods; 2) selecting the optimal feature set; and 3) limiting the number of allowed cueing lesions per examination.

Fault Diagnosis for Rotating Machinery Using Vibration Measurement Deep Statistical Feature Learning.

PubMed

Li, Chuan; Sánchez, René-Vinicio; Zurita, Grover; Cerrada, Mariela; Cabrera, Diego

2016-06-17

Fault diagnosis is important for the maintenance of rotating machinery. The detection of faults and fault patterns is a challenging part of machinery fault diagnosis. To tackle this problem, a model for deep statistical feature learning from vibration measurements of rotating machinery is presented in this paper. Vibration sensor signals collected from rotating mechanical systems are represented in the time, frequency, and time-frequency domains, each of which is then used to produce a statistical feature set. For learning statistical features, real-value Gaussian-Bernoulli restricted Boltzmann machines (GRBMs) are stacked to develop a Gaussian-Bernoulli deep Boltzmann machine (GDBM). The suggested approach is applied as a deep statistical feature learning tool for both gearbox and bearing systems. The fault classification performances in experiments using this approach are 95.17% for the gearbox, and 91.75% for the bearing system. The proposed approach is compared to such standard methods as a support vector machine, GRBM and a combination model. In experiments, the best fault classification rate was detected using the proposed model. The results show that deep learning with statistical feature extraction has an essential improvement potential for diagnosing rotating machinery faults.

Fault Diagnosis for Rotating Machinery Using Vibration Measurement Deep Statistical Feature Learning

PubMed Central

Li, Chuan; Sánchez, René-Vinicio; Zurita, Grover; Cerrada, Mariela; Cabrera, Diego

2016-01-01

Fault diagnosis is important for the maintenance of rotating machinery. The detection of faults and fault patterns is a challenging part of machinery fault diagnosis. To tackle this problem, a model for deep statistical feature learning from vibration measurements of rotating machinery is presented in this paper. Vibration sensor signals collected from rotating mechanical systems are represented in the time, frequency, and time-frequency domains, each of which is then used to produce a statistical feature set. For learning statistical features, real-value Gaussian-Bernoulli restricted Boltzmann machines (GRBMs) are stacked to develop a Gaussian-Bernoulli deep Boltzmann machine (GDBM). The suggested approach is applied as a deep statistical feature learning tool for both gearbox and bearing systems. The fault classification performances in experiments using this approach are 95.17% for the gearbox, and 91.75% for the bearing system. The proposed approach is compared to such standard methods as a support vector machine, GRBM and a combination model. In experiments, the best fault classification rate was detected using the proposed model. The results show that deep learning with statistical feature extraction has an essential improvement potential for diagnosing rotating machinery faults. PMID:27322273

Human brain distinctiveness based on EEG spectral coherence connectivity.

PubMed

Rocca, D La; Campisi, P; Vegso, B; Cserti, P; Kozmann, G; Babiloni, F; Fallani, F De Vico

2014-09-01

The use of EEG biometrics, for the purpose of automatic people recognition, has received increasing attention in the recent years. Most of the current analyses rely on the extraction of features characterizing the activity of single brain regions, like power spectrum estimation, thus neglecting possible temporal dependencies between the generated EEG signals. However, important physiological information can be extracted from the way different brain regions are functionally coupled. In this study, we propose a novel approach that fuses spectral coherence-based connectivity between different brain regions as a possibly viable biometric feature. The proposed approach is tested on a large dataset of subjects (N = 108) during eyes-closed (EC) and eyes-open (EO) resting state conditions. The obtained recognition performance shows that using brain connectivity leads to higher distinctiveness with respect to power-spectrum measurements, in both the experimental conditions. Notably, a 100% recognition accuracy is obtained in EC and EO when integrating functional connectivity between regions in the frontal lobe, while a lower 97.5% is obtained in EC (96.26% in EO) when fusing power spectrum information from parieto-occipital (centro-parietal in EO) regions. Taken together, these results suggest that the functional connectivity patterns represent effective features for improving EEG-based biometric systems.

A novel approach for detection and classification of mammographic microcalcifications using wavelet analysis and extreme learning machine.

PubMed

Malar, E; Kandaswamy, A; Chakravarthy, D; Giri Dharan, A

2012-09-01

The objective of this paper is to reveal the effectiveness of wavelet based tissue texture analysis for microcalcification detection in digitized mammograms using Extreme Learning Machine (ELM). Microcalcifications are tiny deposits of calcium in the breast tissue which are potential indicators for early detection of breast cancer. The dense nature of the breast tissue and the poor contrast of the mammogram image prohibit the effectiveness in identifying microcalcifications. Hence, a new approach to discriminate the microcalcifications from the normal tissue is done using wavelet features and is compared with different feature vectors extracted using Gray Level Spatial Dependence Matrix (GLSDM) and Gabor filter based techniques. A total of 120 Region of Interests (ROIs) extracted from 55 mammogram images of mini-Mias database, including normal and microcalcification images are used in the current research. The network is trained with the above mentioned features and the results denote that ELM produces relatively better classification accuracy (94%) with a significant reduction in training time than the other artificial neural networks like Bayesnet classifier, Naivebayes classifier, and Support Vector Machine. ELM also avoids problems like local minima, improper learning rate, and over fitting. Copyright © 2012 Elsevier Ltd. All rights reserved.

Knowledge-based approach to video content classification

NASA Astrophysics Data System (ADS)

Chen, Yu; Wong, Edward K.

2001-01-01

A framework for video content classification using a knowledge-based approach is herein proposed. This approach is motivated by the fact that videos are rich in semantic contents, which can best be interpreted and analyzed by human experts. We demonstrate the concept by implementing a prototype video classification system using the rule-based programming language CLIPS 6.05. Knowledge for video classification is encoded as a set of rules in the rule base. The left-hand-sides of rules contain high level and low level features, while the right-hand-sides of rules contain intermediate results or conclusions. Our current implementation includes features computed from motion, color, and text extracted from video frames. Our current rule set allows us to classify input video into one of five classes: news, weather, reporting, commercial, basketball and football. We use MYCIN's inexact reasoning method for combining evidences, and to handle the uncertainties in the features and in the classification results. We obtained good results in a preliminary experiment, and it demonstrated the validity of the proposed approach.

Knowledge-based approach to video content classification

NASA Astrophysics Data System (ADS)

Chen, Yu; Wong, Edward K.

2000-12-01

A framework for video content classification using a knowledge-based approach is herein proposed. This approach is motivated by the fact that videos are rich in semantic contents, which can best be interpreted and analyzed by human experts. We demonstrate the concept by implementing a prototype video classification system using the rule-based programming language CLIPS 6.05. Knowledge for video classification is encoded as a set of rules in the rule base. The left-hand-sides of rules contain high level and low level features, while the right-hand-sides of rules contain intermediate results or conclusions. Our current implementation includes features computed from motion, color, and text extracted from video frames. Our current rule set allows us to classify input video into one of five classes: news, weather, reporting, commercial, basketball and football. We use MYCIN's inexact reasoning method for combining evidences, and to handle the uncertainties in the features and in the classification results. We obtained good results in a preliminary experiment, and it demonstrated the validity of the proposed approach.

Characterization of Adrenal Lesions on Unenhanced MRI Using Texture Analysis: A Machine-Learning Approach.

PubMed

Romeo, Valeria; Maurea, Simone; Cuocolo, Renato; Petretta, Mario; Mainenti, Pier Paolo; Verde, Francesco; Coppola, Milena; Dell'Aversana, Serena; Brunetti, Arturo

2018-01-17

Adrenal adenomas (AA) are the most common benign adrenal lesions, often characterized based on intralesional fat content as either lipid-rich (LRA) or lipid-poor (LPA). The differentiation of AA, particularly LPA, from nonadenoma adrenal lesions (NAL) may be challenging. Texture analysis (TA) can extract quantitative parameters from MR images. Machine learning is a technique for recognizing patterns that can be applied to medical images by identifying the best combination of TA features to create a predictive model for the diagnosis of interest. To assess the diagnostic efficacy of TA-derived parameters extracted from MR images in characterizing LRA, LPA, and NAL using a machine-learning approach. Retrospective, observational study. Sixty MR examinations, including 20 LRA, 20 LPA, and 20 NAL. Unenhanced T 1 -weighted in-phase (IP) and out-of-phase (OP) as well as T 2 -weighted (T 2 -w) MR images acquired at 3T. Adrenal lesions were manually segmented, placing a spherical volume of interest on IP, OP, and T 2 -w images. Different selection methods were trained and tested using the J48 machine-learning classifiers. The feature selection method that obtained the highest diagnostic performance using the J48 classifier was identified; the diagnostic performance was also compared with that of a senior radiologist by means of McNemar's test. A total of 138 TA-derived features were extracted; among these, four features were selected, extracted from the IP (Short_Run_High_Gray_Level_Emphasis), OP (Mean_Intensity and Maximum_3D_Diameter), and T 2 -w (Standard_Deviation) images; the J48 classifier obtained a diagnostic accuracy of 80%. The expert radiologist obtained a diagnostic accuracy of 73%. McNemar's test did not show significant differences in terms of diagnostic performance between the J48 classifier and the expert radiologist. Machine learning conducted on MR TA-derived features is a potential tool to characterize adrenal lesions. 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018. © 2018 International Society for Magnetic Resonance in Medicine.

IMU-Based Gait Recognition Using Convolutional Neural Networks and Multi-Sensor Fusion.

PubMed

Dehzangi, Omid; Taherisadr, Mojtaba; ChangalVala, Raghvendar

2017-11-27

The wide spread usage of wearable sensors such as in smart watches has provided continuous access to valuable user generated data such as human motion that could be used to identify an individual based on his/her motion patterns such as, gait. Several methods have been suggested to extract various heuristic and high-level features from gait motion data to identify discriminative gait signatures and distinguish the target individual from others. However, the manual and hand crafted feature extraction is error prone and subjective. Furthermore, the motion data collected from inertial sensors have complex structure and the detachment between manual feature extraction module and the predictive learning models might limit the generalization capabilities. In this paper, we propose a novel approach for human gait identification using time-frequency (TF) expansion of human gait cycles in order to capture joint 2 dimensional (2D) spectral and temporal patterns of gait cycles. Then, we design a deep convolutional neural network (DCNN) learning to extract discriminative features from the 2D expanded gait cycles and jointly optimize the identification model and the spectro-temporal features in a discriminative fashion. We collect raw motion data from five inertial sensors placed at the chest, lower-back, right hand wrist, right knee, and right ankle of each human subject synchronously in order to investigate the impact of sensor location on the gait identification performance. We then present two methods for early (input level) and late (decision score level) multi-sensor fusion to improve the gait identification generalization performance. We specifically propose the minimum error score fusion (MESF) method that discriminatively learns the linear fusion weights of individual DCNN scores at the decision level by minimizing the error rate on the training data in an iterative manner. 10 subjects participated in this study and hence, the problem is a 10-class identification task. Based on our experimental results, 91% subject identification accuracy was achieved using the best individual IMU and 2DTF-DCNN. We then investigated our proposed early and late sensor fusion approaches, which improved the gait identification accuracy of the system to 93.36% and 97.06%, respectively.

Simultaneous Spectral-Spatial Feature Selection and Extraction for Hyperspectral Images.

PubMed

Zhang, Lefei; Zhang, Qian; Du, Bo; Huang, Xin; Tang, Yuan Yan; Tao, Dacheng

2018-01-01

In hyperspectral remote sensing data mining, it is important to take into account of both spectral and spatial information, such as the spectral signature, texture feature, and morphological property, to improve the performances, e.g., the image classification accuracy. In a feature representation point of view, a nature approach to handle this situation is to concatenate the spectral and spatial features into a single but high dimensional vector and then apply a certain dimension reduction technique directly on that concatenated vector before feed it into the subsequent classifier. However, multiple features from various domains definitely have different physical meanings and statistical properties, and thus such concatenation has not efficiently explore the complementary properties among different features, which should benefit for boost the feature discriminability. Furthermore, it is also difficult to interpret the transformed results of the concatenated vector. Consequently, finding a physically meaningful consensus low dimensional feature representation of original multiple features is still a challenging task. In order to address these issues, we propose a novel feature learning framework, i.e., the simultaneous spectral-spatial feature selection and extraction algorithm, for hyperspectral images spectral-spatial feature representation and classification. Specifically, the proposed method learns a latent low dimensional subspace by projecting the spectral-spatial feature into a common feature space, where the complementary information has been effectively exploited, and simultaneously, only the most significant original features have been transformed. Encouraging experimental results on three public available hyperspectral remote sensing datasets confirm that our proposed method is effective and efficient.

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%

PEM-PCA: a parallel expectation-maximization PCA face recognition architecture.

PubMed

Rujirakul, Kanokmon; So-In, Chakchai; Arnonkijpanich, Banchar

2014-01-01

Principal component analysis or PCA has been traditionally used as one of the feature extraction techniques in face recognition systems yielding high accuracy when requiring a small number of features. However, the covariance matrix and eigenvalue decomposition stages cause high computational complexity, especially for a large database. Thus, this research presents an alternative approach utilizing an Expectation-Maximization algorithm to reduce the determinant matrix manipulation resulting in the reduction of the stages' complexity. To improve the computational time, a novel parallel architecture was employed to utilize the benefits of parallelization of matrix computation during feature extraction and classification stages including parallel preprocessing, and their combinations, so-called a Parallel Expectation-Maximization PCA architecture. Comparing to a traditional PCA and its derivatives, the results indicate lower complexity with an insignificant difference in recognition precision leading to high speed face recognition systems, that is, the speed-up over nine and three times over PCA and Parallel PCA.

Texture segmentation by genetic programming.

PubMed

Song, Andy; Ciesielski, Vic

2008-01-01

This paper describes a texture segmentation method using genetic programming (GP), which is one of the most powerful evolutionary computation algorithms. By choosing an appropriate representation texture, classifiers can be evolved without computing texture features. Due to the absence of time-consuming feature extraction, the evolved classifiers enable the development of the proposed texture segmentation algorithm. This GP based method can achieve a segmentation speed that is significantly higher than that of conventional methods. This method does not require a human expert to manually construct models for texture feature extraction. In an analysis of the evolved classifiers, it can be seen that these GP classifiers are not arbitrary. Certain textural regularities are captured by these classifiers to discriminate different textures. GP has been shown in this study as a feasible and a powerful approach for texture classification and segmentation, which are generally considered as complex vision tasks.

Fault Diagnosis for Rotating Machinery: A Method based on Image Processing

PubMed Central

Lu, Chen; Wang, Yang; Ragulskis, Minvydas; Cheng, Yujie

2016-01-01

Rotating machinery is one of the most typical types of mechanical equipment and plays a significant role in industrial applications. Condition monitoring and fault diagnosis of rotating machinery has gained wide attention for its significance in preventing catastrophic accident and guaranteeing sufficient maintenance. With the development of science and technology, fault diagnosis methods based on multi-disciplines are becoming the focus in the field of fault diagnosis of rotating machinery. This paper presents a multi-discipline method based on image-processing for fault diagnosis of rotating machinery. Different from traditional analysis method in one-dimensional space, this study employs computing method in the field of image processing to realize automatic feature extraction and fault diagnosis in a two-dimensional space. The proposed method mainly includes the following steps. First, the vibration signal is transformed into a bi-spectrum contour map utilizing bi-spectrum technology, which provides a basis for the following image-based feature extraction. Then, an emerging approach in the field of image processing for feature extraction, speeded-up robust features, is employed to automatically exact fault features from the transformed bi-spectrum contour map and finally form a high-dimensional feature vector. To reduce the dimensionality of the feature vector, thus highlighting main fault features and reducing subsequent computing resources, t-Distributed Stochastic Neighbor Embedding is adopt to reduce the dimensionality of the feature vector. At last, probabilistic neural network is introduced for fault identification. Two typical rotating machinery, axial piston hydraulic pump and self-priming centrifugal pumps, are selected to demonstrate the effectiveness of the proposed method. Results show that the proposed method based on image-processing achieves a high accuracy, thus providing a highly effective means to fault diagnosis for rotating machinery. PMID:27711246

Fault Diagnosis for Rotating Machinery: A Method based on Image Processing.

PubMed

Lu, Chen; Wang, Yang; Ragulskis, Minvydas; Cheng, Yujie

2016-01-01

Rotating machinery is one of the most typical types of mechanical equipment and plays a significant role in industrial applications. Condition monitoring and fault diagnosis of rotating machinery has gained wide attention for its significance in preventing catastrophic accident and guaranteeing sufficient maintenance. With the development of science and technology, fault diagnosis methods based on multi-disciplines are becoming the focus in the field of fault diagnosis of rotating machinery. This paper presents a multi-discipline method based on image-processing for fault diagnosis of rotating machinery. Different from traditional analysis method in one-dimensional space, this study employs computing method in the field of image processing to realize automatic feature extraction and fault diagnosis in a two-dimensional space. The proposed method mainly includes the following steps. First, the vibration signal is transformed into a bi-spectrum contour map utilizing bi-spectrum technology, which provides a basis for the following image-based feature extraction. Then, an emerging approach in the field of image processing for feature extraction, speeded-up robust features, is employed to automatically exact fault features from the transformed bi-spectrum contour map and finally form a high-dimensional feature vector. To reduce the dimensionality of the feature vector, thus highlighting main fault features and reducing subsequent computing resources, t-Distributed Stochastic Neighbor Embedding is adopt to reduce the dimensionality of the feature vector. At last, probabilistic neural network is introduced for fault identification. Two typical rotating machinery, axial piston hydraulic pump and self-priming centrifugal pumps, are selected to demonstrate the effectiveness of the proposed method. Results show that the proposed method based on image-processing achieves a high accuracy, thus providing a highly effective means to fault diagnosis for rotating machinery.

Computer-aided classification of breast microcalcification clusters: merging of features from image processing and radiologists

NASA Astrophysics Data System (ADS)

Lo, Joseph Y.; Gavrielides, Marios A.; Markey, Mia K.; Jesneck, Jonathan L.

2003-05-01

We developed an ensemble classifier for the task of computer-aided diagnosis of breast microcalcification clusters,which are very challenging to characterize for radiologists and computer models alike. The purpose of this study is to help radiologists identify whether suspicious calcification clusters are benign vs. malignant, such that they may potentially recommend fewer unnecessary biopsies for actually benign lesions. The data consists of mammographic features extracted by automated image processing algorithms as well as manually interpreted by radiologists according to a standardized lexicon. We used 292 cases from a publicly available mammography database. From each cases, we extracted 22 image processing features pertaining to lesion morphology, 5 radiologist features also pertaining to morphology, and the patient age. Linear discriminant analysis (LDA) models were designed using each of the three data types. Each local model performed poorly; the best was one based upon image processing features which yielded ROC area index AZ of 0.59 +/- 0.03 and partial AZ above 90% sensitivity of 0.08 +/- 0.03. We then developed ensemble models using different combinations of those data types, and these models all improved performance compared to the local models. The final ensemble model was based upon 5 features selected by stepwise LDA from all 28 available features. This ensemble performed with AZ of 0.69 +/- 0.03 and partial AZ of 0.21 +/- 0.04, which was statistically significantly better than the model based on the image processing features alone (p<0.001 and p=0.01 for full and partial AZ respectively). This demonstrated the value of the radiologist-extracted features as a source of information for this task. It also suggested there is potential for improved performance using this ensemble classifier approach to combine different sources of currently available data.

TEES 2.2: Biomedical Event Extraction for Diverse Corpora

PubMed Central

2015-01-01

Background The Turku Event Extraction System (TEES) is a text mining program developed for the extraction of events, complex biomedical relationships, from scientific literature. Based on a graph-generation approach, the system detects events with the use of a rich feature set built via dependency parsing. The TEES system has achieved record performance in several of the shared tasks of its domain, and continues to be used in a variety of biomedical text mining tasks. Results The TEES system was quickly adapted to the BioNLP'13 Shared Task in order to provide a public baseline for derived systems. An automated approach was developed for learning the underlying annotation rules of event type, allowing immediate adaptation to the various subtasks, and leading to a first place in four out of eight tasks. The system for the automated learning of annotation rules is further enhanced in this paper to the point of requiring no manual adaptation to any of the BioNLP'13 tasks. Further, the scikit-learn machine learning library is integrated into the system, bringing a wide variety of machine learning methods usable with TEES in addition to the default SVM. A scikit-learn ensemble method is also used to analyze the importances of the features in the TEES feature sets. Conclusions The TEES system was introduced for the BioNLP'09 Shared Task and has since then demonstrated good performance in several other shared tasks. By applying the current TEES 2.2 system to multiple corpora from these past shared tasks an overarching analysis of the most promising methods and possible pitfalls in the evolving field of biomedical event extraction are presented. PMID:26551925

TEES 2.2: Biomedical Event Extraction for Diverse Corpora.

PubMed

Björne, Jari; Salakoski, Tapio

2015-01-01

The Turku Event Extraction System (TEES) is a text mining program developed for the extraction of events, complex biomedical relationships, from scientific literature. Based on a graph-generation approach, the system detects events with the use of a rich feature set built via dependency parsing. The TEES system has achieved record performance in several of the shared tasks of its domain, and continues to be used in a variety of biomedical text mining tasks. The TEES system was quickly adapted to the BioNLP'13 Shared Task in order to provide a public baseline for derived systems. An automated approach was developed for learning the underlying annotation rules of event type, allowing immediate adaptation to the various subtasks, and leading to a first place in four out of eight tasks. The system for the automated learning of annotation rules is further enhanced in this paper to the point of requiring no manual adaptation to any of the BioNLP'13 tasks. Further, the scikit-learn machine learning library is integrated into the system, bringing a wide variety of machine learning methods usable with TEES in addition to the default SVM. A scikit-learn ensemble method is also used to analyze the importances of the features in the TEES feature sets. The TEES system was introduced for the BioNLP'09 Shared Task and has since then demonstrated good performance in several other shared tasks. By applying the current TEES 2.2 system to multiple corpora from these past shared tasks an overarching analysis of the most promising methods and possible pitfalls in the evolving field of biomedical event extraction are presented.

Dynamic Features for Iris Recognition.

PubMed

da Costa, R M; Gonzaga, A

2012-08-01

The human eye is sensitive to visible light. Increasing illumination on the eye causes the pupil of the eye to contract, while decreasing illumination causes the pupil to dilate. Visible light causes specular reflections inside the iris ring. On the other hand, the human retina is less sensitive to near infra-red (NIR) radiation in the wavelength range from 800 nm to 1400 nm, but iris detail can still be imaged with NIR illumination. In order to measure the dynamic movement of the human pupil and iris while keeping the light-induced reflexes from affecting the quality of the digitalized image, this paper describes a device based on the consensual reflex. This biological phenomenon contracts and dilates the two pupils synchronously when illuminating one of the eyes by visible light. In this paper, we propose to capture images of the pupil of one eye using NIR illumination while illuminating the other eye using a visible-light pulse. This new approach extracts iris features called "dynamic features (DFs)." This innovative methodology proposes the extraction of information about the way the human eye reacts to light, and to use such information for biometric recognition purposes. The results demonstrate that these features are discriminating features, and, even using the Euclidean distance measure, an average accuracy of recognition of 99.1% was obtained. The proposed methodology has the potential to be "fraud-proof," because these DFs can only be extracted from living irises.

Feature extraction for document text using Latent Dirichlet Allocation

NASA Astrophysics Data System (ADS)

Prihatini, P. M.; Suryawan, I. K.; Mandia, IN

2018-01-01

Feature extraction is one of stages in the information retrieval system that used to extract the unique feature values of a text document. The process of feature extraction can be done by several methods, one of which is Latent Dirichlet Allocation. However, researches related to text feature extraction using Latent Dirichlet Allocation method are rarely found for Indonesian text. Therefore, through this research, a text feature extraction will be implemented for Indonesian text. The research method consists of data acquisition, text pre-processing, initialization, topic sampling and evaluation. The evaluation is done by comparing Precision, Recall and F-Measure value between Latent Dirichlet Allocation and Term Frequency Inverse Document Frequency KMeans which commonly used for feature extraction. The evaluation results show that Precision, Recall and F-Measure value of Latent Dirichlet Allocation method is higher than Term Frequency Inverse Document Frequency KMeans method. This shows that Latent Dirichlet Allocation method is able to extract features and cluster Indonesian text better than Term Frequency Inverse Document Frequency KMeans method.

Method for Face-Emotion Retrieval Using A Cartoon Emotional Expression Approach

NASA Astrophysics Data System (ADS)

Kostov, Vlaho; Yanagisawa, Hideyoshi; Johansson, Martin; Fukuda, Shuichi

A simple method for extracting emotion from a human face, as a form of non-verbal communication, was developed to cope with and optimize mobile communication in a globalized and diversified society. A cartoon face based model was developed and used to evaluate emotional content of real faces. After a pilot survey, basic rules were defined and student subjects were asked to express emotion using the cartoon face. Their face samples were then analyzed using principal component analysis and the Mahalanobis distance method. Feature parameters considered as having relations with emotions were extracted and new cartoon faces (based on these parameters) were generated. The subjects evaluated emotion of these cartoon faces again and we confirmed these parameters were suitable. To confirm how these parameters could be applied to real faces, we asked subjects to express the same emotions which were then captured electronically. Simple image processing techniques were also developed to extract these features from real faces and we then compared them with the cartoon face parameters. It is demonstrated via the cartoon face that we are able to express the emotions from very small amounts of information. As a result, real and cartoon faces correspond to each other. It is also shown that emotion could be extracted from still and dynamic real face images using these cartoon-based features.

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.

Application of the wavelet transform for speech processing

NASA Technical Reports Server (NTRS)

Maes, Stephane

1994-01-01

Speaker identification and word spotting will shortly play a key role in space applications. An approach based on the wavelet transform is presented that, in the context of the 'modulation model,' enables extraction of speech features which are used as input for the classification process.

Optimized Periocular Template Selection for Human Recognition

PubMed Central

Sa, Pankaj K.; Majhi, Banshidhar

2013-01-01

A novel approach for selecting a rectangular template around periocular region optimally potential for human recognition is proposed. A comparatively larger template of periocular image than the optimal one can be slightly more potent for recognition, but the larger template heavily slows down the biometric system by making feature extraction computationally intensive and increasing the database size. A smaller template, on the contrary, cannot yield desirable recognition though the smaller template performs faster due to low computation for feature extraction. These two contradictory objectives (namely, (a) to minimize the size of periocular template and (b) to maximize the recognition through the template) are aimed to be optimized through the proposed research. This paper proposes four different approaches for dynamic optimal template selection from periocular region. The proposed methods are tested on publicly available unconstrained UBIRISv2 and FERET databases and satisfactory results have been achieved. Thus obtained template can be used for recognition of individuals in an organization and can be generalized to recognize every citizen of a nation. PMID:23984370

3D fluid-structure modelling and vibration analysis for fault diagnosis of Francis turbine using multiple ANN and multiple ANFIS

NASA Astrophysics Data System (ADS)

Saeed, R. A.; Galybin, A. N.; Popov, V.

2013-01-01

This paper discusses condition monitoring and fault diagnosis in Francis turbine based on integration of numerical modelling with several different artificial intelligence (AI) techniques. In this study, a numerical approach for fluid-structure (turbine runner) analysis is presented. The results of numerical analysis provide frequency response functions (FRFs) data sets along x-, y- and z-directions under different operating load and different position and size of faults in the structure. To extract features and reduce the dimensionality of the obtained FRF data, the principal component analysis (PCA) has been applied. Subsequently, the extracted features are formulated and fed into multiple artificial neural networks (ANN) and multiple adaptive neuro-fuzzy inference systems (ANFIS) in order to identify the size and position of the damage in the runner and estimate the turbine operating conditions. The results demonstrated the effectiveness of this approach and provide satisfactory accuracy even when the input data are corrupted with certain level of noise.

Integrated feature extraction and selection for neuroimage classification

NASA Astrophysics Data System (ADS)

Fan, Yong; Shen, Dinggang

2009-02-01

Feature extraction and selection are of great importance in neuroimage classification for identifying informative features and reducing feature dimensionality, which are generally implemented as two separate steps. This paper presents an integrated feature extraction and selection algorithm with two iterative steps: constrained subspace learning based feature extraction and support vector machine (SVM) based feature selection. The subspace learning based feature extraction focuses on the brain regions with higher possibility of being affected by the disease under study, while the possibility of brain regions being affected by disease is estimated by the SVM based feature selection, in conjunction with SVM classification. This algorithm can not only take into account the inter-correlation among different brain regions, but also overcome the limitation of traditional subspace learning based feature extraction methods. To achieve robust performance and optimal selection of parameters involved in feature extraction, selection, and classification, a bootstrapping strategy is used to generate multiple versions of training and testing sets for parameter optimization, according to the classification performance measured by the area under the ROC (receiver operating characteristic) curve. The integrated feature extraction and selection method is applied to a structural MR image based Alzheimer's disease (AD) study with 98 non-demented and 100 demented subjects. Cross-validation results indicate that the proposed algorithm can improve performance of the traditional subspace learning based classification.

Accurate facade feature extraction method for buildings from three-dimensional point cloud data considering structural information

NASA Astrophysics Data System (ADS)

Wang, Yongzhi; Ma, Yuqing; Zhu, A.-xing; Zhao, Hui; Liao, Lixia

2018-05-01

Facade features represent segmentations of building surfaces and can serve as a building framework. Extracting facade features from three-dimensional (3D) point cloud data (3D PCD) is an efficient method for 3D building modeling. By combining the advantages of 3D PCD and two-dimensional optical images, this study describes the creation of a highly accurate building facade feature extraction method from 3D PCD with a focus on structural information. The new extraction method involves three major steps: image feature extraction, exploration of the mapping method between the image features and 3D PCD, and optimization of the initial 3D PCD facade features considering structural information. Results show that the new method can extract the 3D PCD facade features of buildings more accurately and continuously. The new method is validated using a case study. In addition, the effectiveness of the new method is demonstrated by comparing it with the range image-extraction method and the optical image-extraction method in the absence of structural information. The 3D PCD facade features extracted by the new method can be applied in many fields, such as 3D building modeling and building information modeling.

Structure constrained semi-nonnegative matrix factorization for EEG-based motor imagery classification.

PubMed

Lu, Na; Li, Tengfei; Pan, Jinjin; Ren, Xiaodong; Feng, Zuren; Miao, Hongyu

2015-05-01

Electroencephalogram (EEG) provides a non-invasive approach to measure the electrical activities of brain neurons and has long been employed for the development of brain-computer interface (BCI). For this purpose, various patterns/features of EEG data need to be extracted and associated with specific events like cue-paced motor imagery. However, this is a challenging task since EEG data are usually non-stationary time series with a low signal-to-noise ratio. In this study, we propose a novel method, called structure constrained semi-nonnegative matrix factorization (SCS-NMF), to extract the key patterns of EEG data in time domain by imposing the mean envelopes of event-related potentials (ERPs) as constraints on the semi-NMF procedure. The proposed method is applicable to general EEG time series, and the extracted temporal features by SCS-NMF can also be combined with other features in frequency domain to improve the performance of motor imagery classification. Real data experiments have been performed using the SCS-NMF approach for motor imagery classification, and the results clearly suggest the superiority of the proposed method. Comparison experiments have also been conducted. The compared methods include ICA, PCA, Semi-NMF, Wavelets, EMD and CSP, which further verified the effectivity of SCS-NMF. The SCS-NMF method could obtain better or competitive performance over the state of the art methods, which provides a novel solution for brain pattern analysis from the perspective of structure constraint. Copyright © 2015 Elsevier Ltd. All rights reserved.

A Multi-Modal Face Recognition Method Using Complete Local Derivative Patterns and Depth Maps

PubMed Central

Yin, Shouyi; Dai, Xu; Ouyang, Peng; Liu, Leibo; Wei, Shaojun

2014-01-01

In this paper, we propose a multi-modal 2D + 3D face recognition method for a smart city application based on a Wireless Sensor Network (WSN) and various kinds of sensors. Depth maps are exploited for the 3D face representation. As for feature extraction, we propose a new feature called Complete Local Derivative Pattern (CLDP). It adopts the idea of layering and has four layers. In the whole system, we apply CLDP separately on Gabor features extracted from a 2D image and depth map. Then, we obtain two features: CLDP-Gabor and CLDP-Depth. The two features weighted by the corresponding coefficients are combined together in the decision level to compute the total classification distance. At last, the probe face is assigned the identity with the smallest classification distance. Extensive experiments are conducted on three different databases. The results demonstrate the robustness and superiority of the new approach. The experimental results also prove that the proposed multi-modal 2D + 3D method is superior to other multi-modal ones and CLDP performs better than other Local Binary Pattern (LBP) based features. PMID:25333290

A data driven approach for condition monitoring of wind turbine blade using vibration signals through best-first tree algorithm and functional trees algorithm: A comparative study.

PubMed

Joshuva, A; Sugumaran, V

2017-03-01

Wind energy is one of the important renewable energy resources available in nature. It is one of the major resources for production of energy because of its dependability due to the development of the technology and relatively low cost. Wind energy is converted into electrical energy using rotating blades. Due to environmental conditions and large structure, the blades are subjected to various vibration forces that may cause damage to the blades. This leads to a liability in energy production and turbine shutdown. The downtime can be reduced when the blades are diagnosed continuously using structural health condition monitoring. These are considered as a pattern recognition problem which consists of three phases namely, feature extraction, feature selection, and feature classification. In this study, statistical features were extracted from vibration signals, feature selection was carried out using a J48 decision tree algorithm and feature classification was performed using best-first tree algorithm and functional trees algorithm. The better algorithm is suggested for fault diagnosis of wind turbine blade. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.

Mammographic mass classification based on possibility theory

NASA Astrophysics Data System (ADS)

Hmida, Marwa; Hamrouni, Kamel; Solaiman, Basel; Boussetta, Sana

2017-03-01

Shape and margin features are very important for differentiating between benign and malignant masses in mammographic images. In fact, benign masses are usually round and oval and have smooth contours. However, malignant tumors have generally irregular shape and appear lobulated or speculated in margins. This knowledge suffers from imprecision and ambiguity. Therefore, this paper deals with the problem of mass classification by using shape and margin features while taking into account the uncertainty linked to the degree of truth of the available information and the imprecision related to its content. Thus, in this work, we proposed a novel mass classification approach which provides a possibility based representation of the extracted shape features and builds a possibility knowledge basis in order to evaluate the possibility degree of malignancy and benignity for each mass. For experimentation, the MIAS database was used and the classification results show the great performance of our approach in spite of using simple features.

Spatial variation analyses of Thematic Mapper data for the identification of linear features in agricultural landscapes

NASA Technical Reports Server (NTRS)

Pelletier, R. E.

1984-01-01

A need exists for digitized information pertaining to linear features such as roads, streams, water bodies and agricultural field boundaries as component parts of a data base. For many areas where this data may not yet exist or is in need of updating, these features may be extracted from remotely sensed digital data. This paper examines two approaches for identifying linear features, one utilizing raw data and the other classified data. Each approach uses a series of data enhancement procedures including derivation of standard deviation values, principal component analysis and filtering procedures using a high-pass window matrix. Just as certain bands better classify different land covers, so too do these bands exhibit high spectral contrast by which boundaries between land covers can be delineated. A few applications for this kind of data are briefly discussed, including its potential in a Universal Soil Loss Equation Model.

End-to-End Multimodal Emotion Recognition Using Deep Neural Networks

NASA Astrophysics Data System (ADS)

Tzirakis, Panagiotis; Trigeorgis, George; Nicolaou, Mihalis A.; Schuller, Bjorn W.; Zafeiriou, Stefanos

2017-12-01

Automatic affect recognition is a challenging task due to the various modalities emotions can be expressed with. Applications can be found in many domains including multimedia retrieval and human computer interaction. In recent years, deep neural networks have been used with great success in determining emotional states. Inspired by this success, we propose an emotion recognition system using auditory and visual modalities. To capture the emotional content for various styles of speaking, robust features need to be extracted. To this purpose, we utilize a Convolutional Neural Network (CNN) to extract features from the speech, while for the visual modality a deep residual network (ResNet) of 50 layers. In addition to the importance of feature extraction, a machine learning algorithm needs also to be insensitive to outliers while being able to model the context. To tackle this problem, Long Short-Term Memory (LSTM) networks are utilized. The system is then trained in an end-to-end fashion where - by also taking advantage of the correlations of the each of the streams - we manage to significantly outperform the traditional approaches based on auditory and visual handcrafted features for the prediction of spontaneous and natural emotions on the RECOLA database of the AVEC 2016 research challenge on emotion recognition.

Integration of adaptive guided filtering, deep feature learning, and edge-detection techniques for hyperspectral image classification

NASA Astrophysics Data System (ADS)

Wan, Xiaoqing; Zhao, Chunhui; Gao, Bing

2017-11-01

The integration of an edge-preserving filtering technique in the classification of a hyperspectral image (HSI) has been proven effective in enhancing classification performance. This paper proposes an ensemble strategy for HSI classification using an edge-preserving filter along with a deep learning model and edge detection. First, an adaptive guided filter is applied to the original HSI to reduce the noise in degraded images and to extract powerful spectral-spatial features. Second, the extracted features are fed as input to a stacked sparse autoencoder to adaptively exploit more invariant and deep feature representations; then, a random forest classifier is applied to fine-tune the entire pretrained network and determine the classification output. Third, a Prewitt compass operator is further performed on the HSI to extract the edges of the first principal component after dimension reduction. Moreover, the regional growth rule is applied to the resulting edge logical image to determine the local region for each unlabeled pixel. Finally, the categories of the corresponding neighborhood samples are determined in the original classification map; then, the major voting mechanism is implemented to generate the final output. Extensive experiments proved that the proposed method achieves competitive performance compared with several traditional approaches.

Two-dimensional wavelet analysis based classification of gas chromatogram differential mobility spectrometry signals.

PubMed

Zhao, Weixiang; Sankaran, Shankar; Ibáñez, Ana M; Dandekar, Abhaya M; Davis, Cristina E

2009-08-04

This study introduces two-dimensional (2-D) wavelet analysis to the classification of gas chromatogram differential mobility spectrometry (GC/DMS) data which are composed of retention time, compensation voltage, and corresponding intensities. One reported method to process such large data sets is to convert 2-D signals to 1-D signals by summing intensities either across retention time or compensation voltage, but it can lose important signal information in one data dimension. A 2-D wavelet analysis approach keeps the 2-D structure of original signals, while significantly reducing data size. We applied this feature extraction method to 2-D GC/DMS signals measured from control and disordered fruit and then employed two typical classification algorithms to testify the effects of the resultant features on chemical pattern recognition. Yielding a 93.3% accuracy of separating data from control and disordered fruit samples, 2-D wavelet analysis not only proves its feasibility to extract feature from original 2-D signals but also shows its superiority over the conventional feature extraction methods including converting 2-D to 1-D and selecting distinguishable pixels from training set. Furthermore, this process does not require coupling with specific pattern recognition methods, which may help ensure wide applications of this method to 2-D spectrometry data.

3D Face Modeling Using the Multi-Deformable Method

PubMed Central

Hwang, Jinkyu; Yu, Sunjin; Kim, Joongrock; Lee, Sangyoun

2012-01-01

In this paper, we focus on the problem of the accuracy performance of 3D face modeling techniques using corresponding features in multiple views, which is quite sensitive to feature extraction errors. To solve the problem, we adopt a statistical model-based 3D face modeling approach in a mirror system consisting of two mirrors and a camera. The overall procedure of our 3D facial modeling method has two primary steps: 3D facial shape estimation using a multiple 3D face deformable model and texture mapping using seamless cloning that is a type of gradient-domain blending. To evaluate our method's performance, we generate 3D faces of 30 individuals and then carry out two tests: accuracy test and robustness test. Our method shows not only highly accurate 3D face shape results when compared with the ground truth, but also robustness to feature extraction errors. Moreover, 3D face rendering results intuitively show that our method is more robust to feature extraction errors than other 3D face modeling methods. An additional contribution of our method is that a wide range of face textures can be acquired by the mirror system. By using this texture map, we generate realistic 3D face for individuals at the end of the paper. PMID:23201976

Automatic classification of written descriptions by healthy adults: An overview of the application of natural language processing and machine learning techniques to clinical discourse analysis.

PubMed

Toledo, Cíntia Matsuda; Cunha, Andre; Scarton, Carolina; Aluísio, Sandra

2014-01-01

Discourse production is an important aspect in the evaluation of brain-injured individuals. We believe that studies comparing the performance of brain-injured subjects with that of healthy controls must use groups with compatible education. A pioneering application of machine learning methods using Brazilian Portuguese for clinical purposes is described, highlighting education as an important variable in the Brazilian scenario. The aims were to describe how to:(i) develop machine learning classifiers using features generated by natural language processing tools to distinguish descriptions produced by healthy individuals into classes based on their years of education; and(ii) automatically identify the features that best distinguish the groups. The approach proposed here extracts linguistic features automatically from the written descriptions with the aid of two Natural Language Processing tools: Coh-Metrix-Port and AIC. It also includes nine task-specific features (three new ones, two extracted manually, besides description time; type of scene described - simple or complex; presentation order - which type of picture was described first; and age). In this study, the descriptions by 144 of the subjects studied in Toledo 18 were used,which included 200 healthy Brazilians of both genders. A Support Vector Machine (SVM) with a radial basis function (RBF) kernel is the most recommended approach for the binary classification of our data, classifying three of the four initial classes. CfsSubsetEval (CFS) is a strong candidate to replace manual feature selection methods.

Biometric identification based on feature fusion with PCA and SVM

NASA Astrophysics Data System (ADS)

Lefkovits, László; Lefkovits, Szidónia; Emerich, Simina

2018-04-01

Biometric identification is gaining ground compared to traditional identification methods. Many biometric measurements may be used for secure human identification. The most reliable among them is the iris pattern because of its uniqueness, stability, unforgeability and inalterability over time. The approach presented in this paper is a fusion of different feature descriptor methods such as HOG, LIOP, LBP, used for extracting iris texture information. The classifiers obtained through the SVM and PCA methods demonstrate the effectiveness of our system applied to one and both irises. The performances measured are highly accurate and foreshadow a fusion system with a rate of identification approaching 100% on the UPOL database.

Assessing Footwear Effects from Principal Features of Plantar Loading during Running.

PubMed

Trudeau, Matthieu B; von Tscharner, Vinzenz; Vienneau, Jordyn; Hoerzer, Stefan; Nigg, Benno M

2015-09-01

The effects of footwear on the musculoskeletal system are commonly assessed by interpreting the resultant force at the foot during the stance phase of running. However, this approach overlooks loading patterns across the entire foot. An alternative technique for assessing foot loading across different footwear conditions is possible using comprehensive analysis tools that extract different foot loading features, thus enhancing the functional interpretation of the differences across different interventions. The purpose of this article was to use pattern recognition techniques to develop and use a novel comprehensive method for assessing the effects of different footwear interventions on plantar loading. A principal component analysis was used to extract different loading features from the stance phase of running, and a support vector machine (SVM) was used to determine whether and how these loading features were different across three shoe conditions. The results revealed distinct loading features at the foot during the stance phase of running. The loading features determined from the principal component analysis allowed successful classification of all three shoe conditions using the SVM. Several differences were found in the location and timing of the loading across each pairwise shoe comparison using the output from the SVM. The analysis approach proposed can successfully be used to compare different loading patterns with a much greater resolution than has been reported previously. This study has several important applications. One such application is that it would not be relevant for a user to select a shoe or for a manufacturer to alter a shoe's construction if the classification across shoe conditions would not have been significant.

Feature Relevance Assessment of Multispectral Airborne LIDAR Data for Tree Species Classification

NASA Astrophysics Data System (ADS)

Amiri, N.; Heurich, M.; Krzystek, P.; Skidmore, A. K.

2018-04-01

The presented experiment investigates the potential of Multispectral Laser Scanning (MLS) point clouds for single tree species classification. The basic idea is to simulate a MLS sensor by combining two different Lidar sensors providing three different wavelngthes. The available data were acquired in the summer 2016 at the same date in a leaf-on condition with an average point density of 37 points/m2. For the purpose of classification, we segmented the combined 3D point clouds consisiting of three different spectral channels into 3D clusters using Normalized Cut segmentation approach. Then, we extracted four group of features from the 3D point cloud space. Once a varity of features has been extracted, we applied forward stepwise feature selection in order to reduce the number of irrelevant or redundant features. For the classification, we used multinomial logestic regression with L1 regularization. Our study is conducted using 586 ground measured single trees from 20 sample plots in the Bavarian Forest National Park, in Germany. Due to lack of reference data for some rare species, we focused on four classes of species. The results show an improvement between 4-10 pp for the tree species classification by using MLS data in comparison to a single wavelength based approach. A cross validated (15-fold) accuracy of 0.75 can be achieved when all feature sets from three different spectral channels are used. Our results cleary indicates that the use of MLS point clouds has great potential to improve detailed forest species mapping.

A framework for feature extraction from hospital medical data with applications in risk prediction.

PubMed

Tran, Truyen; Luo, Wei; Phung, Dinh; Gupta, Sunil; Rana, Santu; Kennedy, Richard Lee; Larkins, Ann; Venkatesh, Svetha

2014-12-30

Feature engineering is a time consuming component of predictive modeling. We propose a versatile platform to automatically extract features for risk prediction, based on a pre-defined and extensible entity schema. The extraction is independent of disease type or risk prediction task. We contrast auto-extracted features to baselines generated from the Elixhauser comorbidities. Hospital medical records was transformed to event sequences, to which filters were applied to extract feature sets capturing diversity in temporal scales and data types. The features were evaluated on a readmission prediction task, comparing with baseline feature sets generated from the Elixhauser comorbidities. The prediction model was through logistic regression with elastic net regularization. Predictions horizons of 1, 2, 3, 6, 12 months were considered for four diverse diseases: diabetes, COPD, mental disorders and pneumonia, with derivation and validation cohorts defined on non-overlapping data-collection periods. For unplanned readmissions, auto-extracted feature set using socio-demographic information and medical records, outperformed baselines derived from the socio-demographic information and Elixhauser comorbidities, over 20 settings (5 prediction horizons over 4 diseases). In particular over 30-day prediction, the AUCs are: COPD-baseline: 0.60 (95% CI: 0.57, 0.63), auto-extracted: 0.67 (0.64, 0.70); diabetes-baseline: 0.60 (0.58, 0.63), auto-extracted: 0.67 (0.64, 0.69); mental disorders-baseline: 0.57 (0.54, 0.60), auto-extracted: 0.69 (0.64,0.70); pneumonia-baseline: 0.61 (0.59, 0.63), auto-extracted: 0.70 (0.67, 0.72). The advantages of auto-extracted standard features from complex medical records, in a disease and task agnostic manner were demonstrated. Auto-extracted features have good predictive power over multiple time horizons. Such feature sets have potential to form the foundation of complex automated analytic tasks.

Comparative analysis of feature extraction methods in satellite imagery

NASA Astrophysics Data System (ADS)

Karim, Shahid; Zhang, Ye; Asif, Muhammad Rizwan; Ali, Saad

2017-10-01

Feature extraction techniques are extensively being used in satellite imagery and getting impressive attention for remote sensing applications. The state-of-the-art feature extraction methods are appropriate according to the categories and structures of the objects to be detected. Based on distinctive computations of each feature extraction method, different types of images are selected to evaluate the performance of the methods, such as binary robust invariant scalable keypoints (BRISK), scale-invariant feature transform, speeded-up robust features (SURF), features from accelerated segment test (FAST), histogram of oriented gradients, and local binary patterns. Total computational time is calculated to evaluate the speed of each feature extraction method. The extracted features are counted under shadow regions and preprocessed shadow regions to compare the functioning of each method. We have studied the combination of SURF with FAST and BRISK individually and found very promising results with an increased number of features and less computational time. Finally, feature matching is conferred for all methods.

Face recognition via sparse representation of SIFT feature on hexagonal-sampling image

NASA Astrophysics Data System (ADS)

Zhang, Daming; Zhang, Xueyong; Li, Lu; Liu, Huayong

2018-04-01

This paper investigates a face recognition approach based on Scale Invariant Feature Transform (SIFT) feature and sparse representation. The approach takes advantage of SIFT which is local feature other than holistic feature in classical Sparse Representation based Classification (SRC) algorithm and possesses strong robustness to expression, pose and illumination variations. Since hexagonal image has more inherit merits than square image to make recognition process more efficient, we extract SIFT keypoint in hexagonal-sampling image. Instead of matching SIFT feature, firstly the sparse representation of each SIFT keypoint is given according the constructed dictionary; secondly these sparse vectors are quantized according dictionary; finally each face image is represented by a histogram and these so-called Bag-of-Words vectors are classified by SVM. Due to use of local feature, the proposed method achieves better result even when the number of training sample is small. In the experiments, the proposed method gave higher face recognition rather than other methods in ORL and Yale B face databases; also, the effectiveness of the hexagonal-sampling in the proposed method is verified.

PHOTOMETRIC SUPERNOVA CLASSIFICATION WITH MACHINE LEARNING

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

Lochner, Michelle; Peiris, Hiranya V.; Lahav, Ofer

Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope, given that spectroscopic confirmation of type for all supernovae discovered will be impossible. Here, we develop a multi-faceted classification pipeline, combining existing and new approaches. Our pipeline consists of two stages: extracting descriptive features from the light curves and classification using a machine learning algorithm. Our feature extraction methods vary from model-dependent techniques, namely SALT2 fits, to more independent techniques that fit parametric models tomore » curves, to a completely model-independent wavelet approach. We cover a range of representative machine learning algorithms, including naive Bayes, k -nearest neighbors, support vector machines, artificial neural networks, and boosted decision trees (BDTs). We test the pipeline on simulated multi-band DES light curves from the Supernova Photometric Classification Challenge. Using the commonly used area under the curve (AUC) of the Receiver Operating Characteristic as a metric, we find that the SALT2 fits and the wavelet approach, with the BDTs algorithm, each achieve an AUC of 0.98, where 1 represents perfect classification. We find that a representative training set is essential for good classification, whatever the feature set or algorithm, with implications for spectroscopic follow-up. Importantly, we find that by using either the SALT2 or the wavelet feature sets with a BDT algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.« less

Feasibility of approaches combining sensor and source features in brain-computer interface.

PubMed

Ahn, Minkyu; Hong, Jun Hee; Jun, Sung Chan

2012-02-15

Brain-computer interface (BCI) provides a new channel for communication between brain and computers through brain signals. Cost-effective EEG provides good temporal resolution, but its spatial resolution is poor and sensor information is blurred by inherent noise. To overcome these issues, spatial filtering and feature extraction techniques have been developed. Source imaging, transformation of sensor signals into the source space through source localizer, has gained attention as a new approach for BCI. It has been reported that the source imaging yields some improvement of BCI performance. However, there exists no thorough investigation on how source imaging information overlaps with, and is complementary to, sensor information. Information (visible information) from the source space may overlap as well as be exclusive to information from the sensor space is hypothesized. Therefore, we can extract more information from the sensor and source spaces if our hypothesis is true, thereby contributing to more accurate BCI systems. In this work, features from each space (sensor or source), and two strategies combining sensor and source features are assessed. The information distribution among the sensor, source, and combined spaces is discussed through a Venn diagram for 18 motor imagery datasets. Additional 5 motor imagery datasets from the BCI Competition III site were examined. The results showed that the addition of source information yielded about 3.8% classification improvement for 18 motor imagery datasets and showed an average accuracy of 75.56% for BCI Competition data. Our proposed approach is promising, and improved performance may be possible with better head model. Copyright © 2011 Elsevier B.V. All rights reserved.

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.

Automated concept-level information extraction to reduce the need for custom software and rules development.

PubMed

D'Avolio, Leonard W; Nguyen, Thien M; Goryachev, Sergey; Fiore, Louis D

2011-01-01

Despite at least 40 years of promising empirical performance, very few clinical natural language processing (NLP) or information extraction systems currently contribute to medical science or care. The authors address this gap by reducing the need for custom software and rules development with a graphical user interface-driven, highly generalizable approach to concept-level retrieval. A 'learn by example' approach combines features derived from open-source NLP pipelines with open-source machine learning classifiers to automatically and iteratively evaluate top-performing configurations. The Fourth i2b2/VA Shared Task Challenge's concept extraction task provided the data sets and metrics used to evaluate performance. Top F-measure scores for each of the tasks were medical problems (0.83), treatments (0.82), and tests (0.83). Recall lagged precision in all experiments. Precision was near or above 0.90 in all tasks. Discussion With no customization for the tasks and less than 5 min of end-user time to configure and launch each experiment, the average F-measure was 0.83, one point behind the mean F-measure of the 22 entrants in the competition. Strong precision scores indicate the potential of applying the approach for more specific clinical information extraction tasks. There was not one best configuration, supporting an iterative approach to model creation. Acceptable levels of performance can be achieved using fully automated and generalizable approaches to concept-level information extraction. The described implementation and related documentation is available for download.

Characterization of coronary plaque regions in intravascular ultrasound images using a hybrid ensemble classifier.

PubMed

Hwang, Yoo Na; Lee, Ju Hwan; Kim, Ga Young; Shin, Eun Seok; Kim, Sung Min

2018-01-01

The purpose of this study was to propose a hybrid ensemble classifier to characterize coronary plaque regions in intravascular ultrasound (IVUS) images. Pixels were allocated to one of four tissues (fibrous tissue (FT), fibro-fatty tissue (FFT), necrotic core (NC), and dense calcium (DC)) through processes of border segmentation, feature extraction, feature selection, and classification. Grayscale IVUS images and their corresponding virtual histology images were acquired from 11 patients with known or suspected coronary artery disease using 20 MHz catheter. A total of 102 hybrid textural features including first order statistics (FOS), gray level co-occurrence matrix (GLCM), extended gray level run-length matrix (GLRLM), Laws, local binary pattern (LBP), intensity, and discrete wavelet features (DWF) were extracted from IVUS images. To select optimal feature sets, genetic algorithm was implemented. A hybrid ensemble classifier based on histogram and texture information was then used for plaque characterization in this study. The optimal feature set was used as input of this ensemble classifier. After tissue characterization, parameters including sensitivity, specificity, and accuracy were calculated to validate the proposed approach. A ten-fold cross validation approach was used to determine the statistical significance of the proposed method. Our experimental results showed that the proposed method had reliable performance for tissue characterization in IVUS images. The hybrid ensemble classification method outperformed other existing methods by achieving characterization accuracy of 81% for FFT and 75% for NC. In addition, this study showed that Laws features (SSV and SAV) were key indicators for coronary tissue characterization. The proposed method had high clinical applicability for image-based tissue characterization. Copyright © 2017 Elsevier B.V. All rights reserved.

Sieve-based relation extraction of gene regulatory networks from biological literature

PubMed Central

2015-01-01

Background Relation extraction is an essential procedure in literature mining. It focuses on extracting semantic relations between parts of text, called mentions. Biomedical literature includes an enormous amount of textual descriptions of biological entities, their interactions and results of related experiments. To extract them in an explicit, computer readable format, these relations were at first extracted manually from databases. Manual curation was later replaced with automatic or semi-automatic tools with natural language processing capabilities. The current challenge is the development of information extraction procedures that can directly infer more complex relational structures, such as gene regulatory networks. Results We develop a computational approach for extraction of gene regulatory networks from textual data. Our method is designed as a sieve-based system and uses linear-chain conditional random fields and rules for relation extraction. With this method we successfully extracted the sporulation gene regulation network in the bacterium Bacillus subtilis for the information extraction challenge at the BioNLP 2013 conference. To enable extraction of distant relations using first-order models, we transform the data into skip-mention sequences. We infer multiple models, each of which is able to extract different relationship types. Following the shared task, we conducted additional analysis using different system settings that resulted in reducing the reconstruction error of bacterial sporulation network from 0.73 to 0.68, measured as the slot error rate between the predicted and the reference network. We observe that all relation extraction sieves contribute to the predictive performance of the proposed approach. Also, features constructed by considering mention words and their prefixes and suffixes are the most important features for higher accuracy of extraction. Analysis of distances between different mention types in the text shows that our choice of transforming data into skip-mention sequences is appropriate for detecting relations between distant mentions. Conclusions Linear-chain conditional random fields, along with appropriate data transformations, can be efficiently used to extract relations. The sieve-based architecture simplifies the system as new sieves can be easily added or removed and each sieve can utilize the results of previous ones. Furthermore, sieves with conditional random fields can be trained on arbitrary text data and hence are applicable to broad range of relation extraction tasks and data domains. PMID:26551454

Sieve-based relation extraction of gene regulatory networks from biological literature.

PubMed

Žitnik, Slavko; Žitnik, Marinka; Zupan, Blaž; Bajec, Marko

2015-01-01

Relation extraction is an essential procedure in literature mining. It focuses on extracting semantic relations between parts of text, called mentions. Biomedical literature includes an enormous amount of textual descriptions of biological entities, their interactions and results of related experiments. To extract them in an explicit, computer readable format, these relations were at first extracted manually from databases. Manual curation was later replaced with automatic or semi-automatic tools with natural language processing capabilities. The current challenge is the development of information extraction procedures that can directly infer more complex relational structures, such as gene regulatory networks. We develop a computational approach for extraction of gene regulatory networks from textual data. Our method is designed as a sieve-based system and uses linear-chain conditional random fields and rules for relation extraction. With this method we successfully extracted the sporulation gene regulation network in the bacterium Bacillus subtilis for the information extraction challenge at the BioNLP 2013 conference. To enable extraction of distant relations using first-order models, we transform the data into skip-mention sequences. We infer multiple models, each of which is able to extract different relationship types. Following the shared task, we conducted additional analysis using different system settings that resulted in reducing the reconstruction error of bacterial sporulation network from 0.73 to 0.68, measured as the slot error rate between the predicted and the reference network. We observe that all relation extraction sieves contribute to the predictive performance of the proposed approach. Also, features constructed by considering mention words and their prefixes and suffixes are the most important features for higher accuracy of extraction. Analysis of distances between different mention types in the text shows that our choice of transforming data into skip-mention sequences is appropriate for detecting relations between distant mentions. Linear-chain conditional random fields, along with appropriate data transformations, can be efficiently used to extract relations. The sieve-based architecture simplifies the system as new sieves can be easily added or removed and each sieve can utilize the results of previous ones. Furthermore, sieves with conditional random fields can be trained on arbitrary text data and hence are applicable to broad range of relation extraction tasks and data domains.

A study of machine-learning-based approaches to extract clinical entities and their assertions from discharge summaries.

PubMed

Jiang, Min; Chen, Yukun; Liu, Mei; Rosenbloom, S Trent; Mani, Subramani; Denny, Joshua C; Xu, Hua

2011-01-01

The authors' goal was to develop and evaluate machine-learning-based approaches to extracting clinical entities-including medical problems, tests, and treatments, as well as their asserted status-from hospital discharge summaries written using natural language. This project was part of the 2010 Center of Informatics for Integrating Biology and the Bedside/Veterans Affairs (VA) natural-language-processing challenge. The authors implemented a machine-learning-based named entity recognition system for clinical text and systematically evaluated the contributions of different types of features and ML algorithms, using a training corpus of 349 annotated notes. Based on the results from training data, the authors developed a novel hybrid clinical entity extraction system, which integrated heuristic rule-based modules with the ML-base named entity recognition module. The authors applied the hybrid system to the concept extraction and assertion classification tasks in the challenge and evaluated its performance using a test data set with 477 annotated notes. Standard measures including precision, recall, and F-measure were calculated using the evaluation script provided by the Center of Informatics for Integrating Biology and the Bedside/VA challenge organizers. The overall performance for all three types of clinical entities and all six types of assertions across 477 annotated notes were considered as the primary metric in the challenge. Systematic evaluation on the training set showed that Conditional Random Fields outperformed Support Vector Machines, and semantic information from existing natural-language-processing systems largely improved performance, although contributions from different types of features varied. The authors' hybrid entity extraction system achieved a maximum overall F-score of 0.8391 for concept extraction (ranked second) and 0.9313 for assertion classification (ranked fourth, but not statistically different than the first three systems) on the test data set in the challenge.

Parenchymal texture analysis in digital mammography: A fully automated pipeline for breast cancer risk assessment.

PubMed

Zheng, Yuanjie; Keller, Brad M; Ray, Shonket; Wang, Yan; Conant, Emily F; Gee, James C; Kontos, Despina

2015-07-01

Mammographic percent density (PD%) is known to be a strong risk factor for breast cancer. Recent studies also suggest that parenchymal texture features, which are more granular descriptors of the parenchymal pattern, can provide additional information about breast cancer risk. To date, most studies have measured mammographic texture within selected regions of interest (ROIs) in the breast, which cannot adequately capture the complexity of the parenchymal pattern throughout the whole breast. To better characterize patterns of the parenchymal tissue, the authors have developed a fully automated software pipeline based on a novel lattice-based strategy to extract a range of parenchymal texture features from the entire breast region. Digital mammograms from 106 cases with 318 age-matched controls were retrospectively analyzed. The lattice-based approach is based on a regular grid virtually overlaid on each mammographic image. Texture features are computed from the intersection (i.e., lattice) points of the grid lines within the breast, using a local window centered at each lattice point. Using this strategy, a range of statistical (gray-level histogram, co-occurrence, and run-length) and structural (edge-enhancing, local binary pattern, and fractal dimension) features are extracted. To cover the entire breast, the size of the local window for feature extraction is set equal to the lattice grid spacing and optimized experimentally by evaluating different windows sizes. The association between their lattice-based texture features and breast cancer was evaluated using logistic regression with leave-one-out cross validation and further compared to that of breast PD% and commonly used single-ROI texture features extracted from the retroareolar or the central breast region. Classification performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC). DeLong's test was used to compare the different ROCs in terms of AUC performance. The average univariate performance of the lattice-based features is higher when extracted from smaller than larger window sizes. While not every individual texture feature is superior to breast PD% (AUC: 0.59, STD: 0.03), their combination in multivariate analysis has significantly better performance (AUC: 0.85, STD: 0.02, p < 0.001). The lattice-based texture features also outperform the single-ROI texture features when extracted from the retroareolar or the central breast region (AUC: 0.60-0.74, STD: 0.03). Adding breast PD% does not make a significant performance improvement to the lattice-based texture features or the single-ROI features (p > 0.05). The proposed lattice-based strategy for mammographic texture analysis enables to characterize the parenchymal pattern over the entire breast. As such, these features provide richer information compared to currently used descriptors and may ultimately improve breast cancer risk assessment. Larger studies are warranted to validate these findings and also compare to standard demographic and reproductive risk factors.

Automatic extraction of planetary image features

NASA Technical Reports Server (NTRS)

LeMoigne-Stewart, Jacqueline J. (Inventor); Troglio, Giulia (Inventor); Benediktsson, Jon A. (Inventor); Serpico, Sebastiano B. (Inventor); Moser, Gabriele (Inventor)

2013-01-01

A method for the extraction of Lunar data and/or planetary features is provided. The feature extraction method can include one or more image processing techniques, including, but not limited to, a watershed segmentation and/or the generalized Hough Transform. According to some embodiments, the feature extraction method can include extracting features, such as, small rocks. According to some embodiments, small rocks can be extracted by applying a watershed segmentation algorithm to the Canny gradient. According to some embodiments, applying a watershed segmentation algorithm to the Canny gradient can allow regions that appear as close contours in the gradient to be segmented.

Classification of vocal aging using parameters extracted from the glottal signal.

PubMed

Forero Mendoza, Leonardo A; Cataldo, Edson; Vellasco, Marley M B R; Silva, Marco A; Apolinário, José A

2014-09-01

This article proposes and evaluates a method to classify vocal aging using artificial neural network (ANN) and support vector machine (SVM), using the parameters extracted from the speech signal as inputs. For each recorded speech, from a corpus of male and female speakers of different ages, the corresponding glottal signal is obtained using an inverse filtering algorithm. The Mel Frequency Cepstrum Coefficients (MFCC) also extracted from the voice signal and the features extracted from the glottal signal are supplied to an ANN and an SVM with a previous selection. The selection is performed by a wrapper approach of the most relevant parameters. Three groups are considered for the aging-voice classification: young (aged 15-30 years), adult (aged 31-60 years), and senior (aged 61-90 years). The results are compared using different possibilities: with only the parameters extracted from the glottal signal, with only the MFCC, and with a combination of both. The results demonstrate that the best classification rate is obtained using the glottal signal features, which is a novel result and the main contribution of this article. Copyright © 2014 The Voice Foundation. Published by Elsevier Inc. All rights reserved.

Some fundamental concepts in remote sensing

NASA Technical Reports Server (NTRS)

1982-01-01

The term remote sensing is defined as well as ideas such as class, pattern, feature, pattern recognition, feature extraction, and theme. The electromagnetic spectrum is examined especially those wavelength regions available to remote sensing. Relevant energy and wave propagation laws are discussed and the characteristics of emitted and reflected radiation and their detection are investigated. The identification of classes by their spectral signatures, the multispectral approach, and the principal types of sensors and platforms used in remote sensing are also considered.

DEKF system for crowding estimation by a multiple-model approach

NASA Astrophysics Data System (ADS)

Cravino, F.; Dellucca, M.; Tesei, A.

1994-03-01

A distributed extended Kalman filter (DEKF) network devoted to real-time crowding estimation for surveillance in complex scenes is presented. Estimation is carried out by extracting a set of significant features from sequences of images. Feature values are associated by virtual sensors with the estimated number of people using nonlinear models obtained in an off-line training phase. Different models are used, depending on the positions and dimensions of the crowded subareas detected in each image.

Beyond HRV: attractor reconstruction using the entire cardiovascular waveform data for novel feature extraction

PubMed Central

Aston, Philip J; Christie, Mark I; Huang, Ying H; Nandi, Manasi

2018-01-01

Abstract Advances in monitoring technology allow blood pressure waveforms to be collected at sampling frequencies of 250–1000 Hz for long time periods. However, much of the raw data are under-analysed. Heart rate variability (HRV) methods, in which beat-to-beat interval lengths are extracted and analysed, have been extensively studied. However, this approach discards the majority of the raw data. Objective: Our aim is to detect changes in the shape of the waveform in long streams of blood pressure data. Approach: Our approach involves extracting key features from large complex data sets by generating a reconstructed attractor in a three-dimensional phase space using delay coordinates from a window of the entire raw waveform data. The naturally occurring baseline variation is removed by projecting the attractor onto a plane from which new quantitative measures are obtained. The time window is moved through the data to give a collection of signals which relate to various aspects of the waveform shape. Main results: This approach enables visualisation and quantification of changes in the waveform shape and has been applied to blood pressure data collected from conscious unrestrained mice and to human blood pressure data. The interpretation of the attractor measures is aided by the analysis of simple artificial waveforms. Significance: We have developed and analysed a new method for analysing blood pressure data that uses all of the waveform data and hence can detect changes in the waveform shape that HRV methods cannot, which is confirmed with an example, and hence our method goes ‘beyond HRV’. PMID:29350622

Flight State Identification of a Self-Sensing Wing via an Improved Feature Selection Method and Machine Learning Approaches.

PubMed

Chen, Xi; Kopsaftopoulos, Fotis; Wu, Qi; Ren, He; Chang, Fu-Kuo

2018-04-29

In this work, a data-driven approach for identifying the flight state of a self-sensing wing structure with an embedded multi-functional sensing network is proposed. The flight state is characterized by the structural vibration signals recorded from a series of wind tunnel experiments under varying angles of attack and airspeeds. A large feature pool is created by extracting potential features from the signals covering the time domain, the frequency domain as well as the information domain. Special emphasis is given to feature selection in which a novel filter method is developed based on the combination of a modified distance evaluation algorithm and a variance inflation factor. Machine learning algorithms are then employed to establish the mapping relationship from the feature space to the practical state space. Results from two case studies demonstrate the high identification accuracy and the effectiveness of the model complexity reduction via the proposed method, thus providing new perspectives of self-awareness towards the next generation of intelligent air vehicles.

Feature selection gait-based gender classification under different circumstances

NASA Astrophysics Data System (ADS)

Sabir, Azhin; Al-Jawad, Naseer; Jassim, Sabah

2014-05-01

This paper proposes a gender classification based on human gait features and investigates the problem of two variations: clothing (wearing coats) and carrying bag condition as addition to the normal gait sequence. The feature vectors in the proposed system are constructed after applying wavelet transform. Three different sets of feature are proposed in this method. First, Spatio-temporal distance that is dealing with the distance of different parts of the human body (like feet, knees, hand, Human Height and shoulder) during one gait cycle. The second and third feature sets are constructed from approximation and non-approximation coefficient of human body respectively. To extract these two sets of feature we divided the human body into two parts, upper and lower body part, based on the golden ratio proportion. In this paper, we have adopted a statistical method for constructing the feature vector from the above sets. The dimension of the constructed feature vector is reduced based on the Fisher score as a feature selection method to optimize their discriminating significance. Finally k-Nearest Neighbor is applied as a classification method. Experimental results demonstrate that our approach is providing more realistic scenario and relatively better performance compared with the existing approaches.

Physiological sensor signals classification for healthcare using sensor data fusion and case-based reasoning.

PubMed

Begum, Shahina; Barua, Shaibal; Ahmed, Mobyen Uddin

2014-07-03

Today, clinicians often do diagnosis and classification of diseases based on information collected from several physiological sensor signals. However, sensor signal could easily be vulnerable to uncertain noises or interferences and due to large individual variations sensitivity to different physiological sensors could also vary. Therefore, multiple sensor signal fusion is valuable to provide more robust and reliable decision. This paper demonstrates a physiological sensor signal classification approach using sensor signal fusion and case-based reasoning. The proposed approach has been evaluated to classify Stressed or Relaxed individuals using sensor data fusion. Physiological sensor signals i.e., Heart Rate (HR), Finger Temperature (FT), Respiration Rate (RR), Carbon dioxide (CO2) and Oxygen Saturation (SpO2) are collected during the data collection phase. Here, sensor fusion has been done in two different ways: (i) decision-level fusion using features extracted through traditional approaches; and (ii) data-level fusion using features extracted by means of Multivariate Multiscale Entropy (MMSE). Case-Based Reasoning (CBR) is applied for the classification of the signals. The experimental result shows that the proposed system could classify Stressed or Relaxed individual 87.5% accurately compare to an expert in the domain. So, it shows promising result in the psychophysiological domain and could be possible to adapt this approach to other relevant healthcare systems.

Wearable Device-Based Gait Recognition Using Angle Embedded Gait Dynamic Images and a Convolutional Neural Network.

PubMed

Zhao, Yongjia; Zhou, Suiping

2017-02-28

The widespread installation of inertial sensors in smartphones and other wearable devices provides a valuable opportunity to identify people by analyzing their gait patterns, for either cooperative or non-cooperative circumstances. However, it is still a challenging task to reliably extract discriminative features for gait recognition with noisy and complex data sequences collected from casually worn wearable devices like smartphones. To cope with this problem, we propose a novel image-based gait recognition approach using the Convolutional Neural Network (CNN) without the need to manually extract discriminative features. The CNN's input image, which is encoded straightforwardly from the inertial sensor data sequences, is called Angle Embedded Gait Dynamic Image (AE-GDI). AE-GDI is a new two-dimensional representation of gait dynamics, which is invariant to rotation and translation. The performance of the proposed approach in gait authentication and gait labeling is evaluated using two datasets: (1) the McGill University dataset, which is collected under realistic conditions; and (2) the Osaka University dataset with the largest number of subjects. Experimental results show that the proposed approach achieves competitive recognition accuracy over existing approaches and provides an effective parametric solution for identification among a large number of subjects by gait patterns.

Wearable Device-Based Gait Recognition Using Angle Embedded Gait Dynamic Images and a Convolutional Neural Network

PubMed Central

Zhao, Yongjia; Zhou, Suiping

2017-01-01

The widespread installation of inertial sensors in smartphones and other wearable devices provides a valuable opportunity to identify people by analyzing their gait patterns, for either cooperative or non-cooperative circumstances. However, it is still a challenging task to reliably extract discriminative features for gait recognition with noisy and complex data sequences collected from casually worn wearable devices like smartphones. To cope with this problem, we propose a novel image-based gait recognition approach using the Convolutional Neural Network (CNN) without the need to manually extract discriminative features. The CNN’s input image, which is encoded straightforwardly from the inertial sensor data sequences, is called Angle Embedded Gait Dynamic Image (AE-GDI). AE-GDI is a new two-dimensional representation of gait dynamics, which is invariant to rotation and translation. The performance of the proposed approach in gait authentication and gait labeling is evaluated using two datasets: (1) the McGill University dataset, which is collected under realistic conditions; and (2) the Osaka University dataset with the largest number of subjects. Experimental results show that the proposed approach achieves competitive recognition accuracy over existing approaches and provides an effective parametric solution for identification among a large number of subjects by gait patterns. PMID:28264503

Machine learning and computer vision approaches for phenotypic profiling.

PubMed

Grys, Ben T; Lo, Dara S; Sahin, Nil; Kraus, Oren Z; Morris, Quaid; Boone, Charles; Andrews, Brenda J

2017-01-02

With recent advances in high-throughput, automated microscopy, there has been an increased demand for effective computational strategies to analyze large-scale, image-based data. To this end, computer vision approaches have been applied to cell segmentation and feature extraction, whereas machine-learning approaches have been developed to aid in phenotypic classification and clustering of data acquired from biological images. Here, we provide an overview of the commonly used computer vision and machine-learning methods for generating and categorizing phenotypic profiles, highlighting the general biological utility of each approach. © 2017 Grys et al.

Machine learning and computer vision approaches for phenotypic profiling

PubMed Central

Morris, Quaid

2017-01-01

With recent advances in high-throughput, automated microscopy, there has been an increased demand for effective computational strategies to analyze large-scale, image-based data. To this end, computer vision approaches have been applied to cell segmentation and feature extraction, whereas machine-learning approaches have been developed to aid in phenotypic classification and clustering of data acquired from biological images. Here, we provide an overview of the commonly used computer vision and machine-learning methods for generating and categorizing phenotypic profiles, highlighting the general biological utility of each approach. PMID:27940887

Towards an intelligent framework for multimodal affective data analysis.

PubMed

Poria, Soujanya; Cambria, Erik; Hussain, Amir; Huang, Guang-Bin

2015-03-01

An increasingly large amount of multimodal content is posted on social media websites such as YouTube and Facebook everyday. In order to cope with the growth of such so much multimodal data, there is an urgent need to develop an intelligent multi-modal analysis framework that can effectively extract information from multiple modalities. In this paper, we propose a novel multimodal information extraction agent, which infers and aggregates the semantic and affective information associated with user-generated multimodal data in contexts such as e-learning, e-health, automatic video content tagging and human-computer interaction. In particular, the developed intelligent agent adopts an ensemble feature extraction approach by exploiting the joint use of tri-modal (text, audio and video) features to enhance the multimodal information extraction process. In preliminary experiments using the eNTERFACE dataset, our proposed multi-modal system is shown to achieve an accuracy of 87.95%, outperforming the best state-of-the-art system by more than 10%, or in relative terms, a 56% reduction in error rate. Copyright © 2014 Elsevier Ltd. All rights reserved.

Automatic extraction of relations between medical concepts in clinical texts

PubMed Central

Harabagiu, Sanda; Roberts, Kirk

2011-01-01

Objective A supervised machine learning approach to discover relations between medical problems, treatments, and tests mentioned in electronic medical records. Materials and methods A single support vector machine classifier was used to identify relations between concepts and to assign their semantic type. Several resources such as Wikipedia, WordNet, General Inquirer, and a relation similarity metric inform the classifier. Results The techniques reported in this paper were evaluated in the 2010 i2b2 Challenge and obtained the highest F1 score for the relation extraction task. When gold standard data for concepts and assertions were available, F1 was 73.7, precision was 72.0, and recall was 75.3. F1 is defined as 2*Precision*Recall/(Precision+Recall). Alternatively, when concepts and assertions were discovered automatically, F1 was 48.4, precision was 57.6, and recall was 41.7. Discussion Although a rich set of features was developed for the classifiers presented in this paper, little knowledge mining was performed from medical ontologies such as those found in UMLS. Future studies should incorporate features extracted from such knowledge sources, which we expect to further improve the results. Moreover, each relation discovery was treated independently. Joint classification of relations may further improve the quality of results. Also, joint learning of the discovery of concepts, assertions, and relations may also improve the results of automatic relation extraction. Conclusion Lexical and contextual features proved to be very important in relation extraction from medical texts. When they are not available to the classifier, the F1 score decreases by 3.7%. In addition, features based on similarity contribute to a decrease of 1.1% when they are not available. PMID:21846787

Integrated Computational System for Aerodynamic Steering and Visualization

NASA Technical Reports Server (NTRS)

Hesselink, Lambertus

1999-01-01

In February of 1994, an effort from the Fluid Dynamics and Information Sciences Divisions at NASA Ames Research Center with McDonnel Douglas Aerospace Company and Stanford University was initiated to develop, demonstrate, validate and disseminate automated software for numerical aerodynamic simulation. The goal of the initiative was to develop a tri-discipline approach encompassing CFD, Intelligent Systems, and Automated Flow Feature Recognition to improve the utility of CFD in the design cycle. This approach would then be represented through an intelligent computational system which could accept an engineer's definition of a problem and construct an optimal and reliable CFD solution. Stanford University's role focused on developing technologies that advance visualization capabilities for analysis of CFD data, extract specific flow features useful for the design process, and compare CFD data with experimental data. During the years 1995-1997, Stanford University focused on developing techniques in the area of tensor visualization and flow feature extraction. Software libraries were created enabling feature extraction and exploration of tensor fields. As a proof of concept, a prototype system called the Integrated Computational System (ICS) was developed to demonstrate CFD design cycle. The current research effort focuses on finding a quantitative comparison of general vector fields based on topological features. Since the method relies on topological information, grid matching and vector alignment is not needed in the comparison. This is often a problem with many data comparison techniques. In addition, since only topology based information is stored and compared for each field, there is a significant compression of information that enables large databases to be quickly searched. This report will (1) briefly review the technologies developed during 1995-1997 (2) describe current technologies in the area of comparison techniques, (4) describe the theory of our new method researched during the grant year (5) summarize a few of the results and finally (6) discuss work within the last 6 months that are direct extensions from the grant.

Prostate cancer detection: Fusion of cytological and textural features.

PubMed

Nguyen, Kien; Jain, Anil K; Sabata, Bikash

2011-01-01

A computer-assisted system for histological prostate cancer diagnosis can assist pathologists in two stages: (i) to locate cancer regions in a large digitized tissue biopsy, and (ii) to assign Gleason grades to the regions detected in stage 1. Most previous studies on this topic have primarily addressed the second stage by classifying the preselected tissue regions. In this paper, we address the first stage by presenting a cancer detection approach for the whole slide tissue image. We propose a novel method to extract a cytological feature, namely the presence of cancer nuclei (nuclei with prominent nucleoli) in the tissue, and apply this feature to detect the cancer regions. Additionally, conventional image texture features which have been widely used in the literature are also considered. The performance comparison among the proposed cytological textural feature combination method, the texture-based method and the cytological feature-based method demonstrates the robustness of the extracted cytological feature. At a false positive rate of 6%, the proposed method is able to achieve a sensitivity of 78% on a dataset including six training images (each of which has approximately 4,000×7,000 pixels) and 1 1 whole-slide test images (each of which has approximately 5,000×23,000 pixels). All images are at 20X magnification.

Prostate cancer detection: Fusion of cytological and textural features

PubMed Central

Nguyen, Kien; Jain, Anil K.; Sabata, Bikash

2011-01-01

A computer-assisted system for histological prostate cancer diagnosis can assist pathologists in two stages: (i) to locate cancer regions in a large digitized tissue biopsy, and (ii) to assign Gleason grades to the regions detected in stage 1. Most previous studies on this topic have primarily addressed the second stage by classifying the preselected tissue regions. In this paper, we address the first stage by presenting a cancer detection approach for the whole slide tissue image. We propose a novel method to extract a cytological feature, namely the presence of cancer nuclei (nuclei with prominent nucleoli) in the tissue, and apply this feature to detect the cancer regions. Additionally, conventional image texture features which have been widely used in the literature are also considered. The performance comparison among the proposed cytological textural feature combination method, the texture-based method and the cytological feature-based method demonstrates the robustness of the extracted cytological feature. At a false positive rate of 6%, the proposed method is able to achieve a sensitivity of 78% on a dataset including six training images (each of which has approximately 4,000×7,000 pixels) and 1 1 whole-slide test images (each of which has approximately 5,000×23,000 pixels). All images are at 20X magnification. PMID:22811959

Machine-learning-based diagnosis of schizophrenia using combined sensor-level and source-level EEG features.

PubMed

Shim, Miseon; Hwang, Han-Jeong; Kim, Do-Won; Lee, Seung-Hwan; Im, Chang-Hwan

2016-10-01

Recently, an increasing number of researchers have endeavored to develop practical tools for diagnosing patients with schizophrenia using machine learning techniques applied to EEG biomarkers. Although a number of studies showed that source-level EEG features can potentially be applied to the differential diagnosis of schizophrenia, most studies have used only sensor-level EEG features such as ERP peak amplitude and power spectrum for machine learning-based diagnosis of schizophrenia. In this study, we used both sensor-level and source-level features extracted from EEG signals recorded during an auditory oddball task for the classification of patients with schizophrenia and healthy controls. EEG signals were recorded from 34 patients with schizophrenia and 34 healthy controls while each subject was asked to attend to oddball tones. Our results demonstrated higher classification accuracy when source-level features were used together with sensor-level features, compared to when only sensor-level features were used. In addition, the selected sensor-level features were mostly found in the frontal area, and the selected source-level features were mostly extracted from the temporal area, which coincide well with the well-known pathological region of cognitive processing in patients with schizophrenia. Our results suggest that our approach would be a promising tool for the computer-aided diagnosis of schizophrenia. Copyright © 2016 Elsevier B.V. All rights reserved.

Pharmacokinetic Tumor Heterogeneity as a Prognostic Biomarker for Classifying Breast Cancer Recurrence Risk.

PubMed

Mahrooghy, Majid; Ashraf, Ahmed B; Daye, Dania; McDonald, Elizabeth S; Rosen, Mark; Mies, Carolyn; Feldman, Michael; Kontos, Despina

2015-06-01

Heterogeneity in cancer can affect response to therapy and patient prognosis. Histologic measures have classically been used to measure heterogeneity, although a reliable noninvasive measurement is needed both to establish baseline risk of recurrence and monitor response to treatment. Here, we propose using spatiotemporal wavelet kinetic features from dynamic contrast-enhanced magnetic resonance imaging to quantify intratumor heterogeneity in breast cancer. Tumor pixels are first partitioned into homogeneous subregions using pharmacokinetic measures. Heterogeneity wavelet kinetic (HetWave) features are then extracted from these partitions to obtain spatiotemporal patterns of the wavelet coefficients and the contrast agent uptake. The HetWave features are evaluated in terms of their prognostic value using a logistic regression classifier with genetic algorithm wrapper-based feature selection to classify breast cancer recurrence risk as determined by a validated gene expression assay. Receiver operating characteristic analysis and area under the curve (AUC) are computed to assess classifier performance using leave-one-out cross validation. The HetWave features outperform other commonly used features (AUC = 0.88 HetWave versus 0.70 standard features). The combination of HetWave and standard features further increases classifier performance (AUCs 0.94). The rate of the spatial frequency pattern over the pharmacokinetic partitions can provide valuable prognostic information. HetWave could be a powerful feature extraction approach for characterizing tumor heterogeneity, providing valuable prognostic information.

CARES: Completely Automated Robust Edge Snapper for carotid ultrasound IMT measurement on a multi-institutional database of 300 images: a two stage system combining an intensity-based feature approach with first order absolute moments

NASA Astrophysics Data System (ADS)

Molinari, Filippo; Acharya, Rajendra; Zeng, Guang; Suri, Jasjit S.

2011-03-01

The carotid intima-media thickness (IMT) is the most used marker for the progression of atherosclerosis and onset of the cardiovascular diseases. Computer-aided measurements improve accuracy, but usually require user interaction. In this paper we characterized a new and completely automated technique for carotid segmentation and IMT measurement based on the merits of two previously developed techniques. We used an integrated approach of intelligent image feature extraction and line fitting for automatically locating the carotid artery in the image frame, followed by wall interfaces extraction based on Gaussian edge operator. We called our system - CARES. We validated the CARES on a multi-institutional database of 300 carotid ultrasound images. IMT measurement bias was 0.032 +/- 0.141 mm, better than other automated techniques and comparable to that of user-driven methodologies. Our novel approach of CARES processed 96% of the images leading to the figure of merit to be 95.7%. CARES ensured complete automation and high accuracy in IMT measurement; hence it could be a suitable clinical tool for processing of large datasets in multicenter studies involving atherosclerosis.pre-

Classification of Sporting Activities Using Smartphone Accelerometers

PubMed Central

Mitchell, Edmond; Monaghan, David; O'Connor, Noel E.

2013-01-01

In this paper we present a framework that allows for the automatic identification of sporting activities using commonly available smartphones. We extract discriminative informational features from smartphone accelerometers using the Discrete Wavelet Transform (DWT). Despite the poor quality of their accelerometers, smartphones were used as capture devices due to their prevalence in today's society. Successful classification on this basis potentially makes the technology accessible to both elite and non-elite athletes. Extracted features are used to train different categories of classifiers. No one classifier family has a reportable direct advantage in activity classification problems to date; thus we examine classifiers from each of the most widely used classifier families. We investigate three classification approaches; a commonly used SVM-based approach, an optimized classification model and a fusion of classifiers. We also investigate the effect of changing several of the DWT input parameters, including mother wavelets, window lengths and DWT decomposition levels. During the course of this work we created a challenging sports activity analysis dataset, comprised of soccer and field-hockey activities. The average maximum F-measure accuracy of 87% was achieved using a fusion of classifiers, which was 6% better than a single classifier model and 23% better than a standard SVM approach. PMID:23604031

Automatic Detection of Galaxy Type From Datasets of Galaxies Image Based on Image Retrieval Approach.

PubMed

Abd El Aziz, Mohamed; Selim, I M; Xiong, Shengwu

2017-06-30

This paper presents a new approach for the automatic detection of galaxy morphology from datasets based on an image-retrieval approach. Currently, there are several classification methods proposed to detect galaxy types within an image. However, in some situations, the aim is not only to determine the type of galaxy within the queried image, but also to determine the most similar images for query image. Therefore, this paper proposes an image-retrieval method to detect the type of galaxies within an image and return with the most similar image. The proposed method consists of two stages, in the first stage, a set of features is extracted based on shape, color and texture descriptors, then a binary sine cosine algorithm selects the most relevant features. In the second stage, the similarity between the features of the queried galaxy image and the features of other galaxy images is computed. Our experiments were performed using the EFIGI catalogue, which contains about 5000 galaxies images with different types (edge-on spiral, spiral, elliptical and irregular). We demonstrate that our proposed approach has better performance compared with the particle swarm optimization (PSO) and genetic algorithm (GA) methods.

Extraction of 3D Femur Neck Trabecular Bone Architecture from Clinical CT Images in Osteoporotic Evaluation: a Novel Framework.

PubMed

Sapthagirivasan, V; Anburajan, M; Janarthanam, S

2015-08-01

The early detection of osteoporosis risk enhances the lifespan and quality of life of an individual. A reasonable in-vivo assessment of trabecular bone strength at the proximal femur helps to evaluate the fracture risk and henceforth, to understand the associated structural dynamics on occurrence of osteoporosis. The main aim of our study was to develop a framework to automatically determine the trabecular bone strength from clinical femur CT images and thereby to estimate its correlation with BMD. All the 50 studied south Indian female subjects aged 30 to 80 years underwent CT and DXA measurements at right femur region. Initially, the original CT slices were intensified and active contour model was utilised for the extraction of the neck region. After processing through a novel process called trabecular enrichment approach (TEA), the three dimensional (3D) trabecular features were extracted. The extracted 3D trabecular features, such as volume fraction (VF), solidity of delta points (SDP) and boundness, demonstrated a significant correlation with femoral neck bone mineral density (r = 0.551, r = 0.432, r = 0.552 respectively) at p < 0.001. The higher area under the curve values of the extracted features (VF: 85.3 %; 95CI: 68.2-100 %, SDP: 82.1 %; 95CI: 65.1-98.9 % and boundness: 90.4 %; 95CI: 78.7-100 %) were observed. The findings suggest that the proposed framework with TEA method would be useful for spotting women vulnerable to osteoporotic risk.

A novel deep learning approach for classification of EEG motor imagery signals.

PubMed

Tabar, Yousef Rezaei; Halici, Ugur

2017-02-01

Signal classification is an important issue in brain computer interface (BCI) systems. Deep learning approaches have been used successfully in many recent studies to learn features and classify different types of data. However, the number of studies that employ these approaches on BCI applications is very limited. In this study we aim to use deep learning methods to improve classification performance of EEG motor imagery signals. In this study we investigate convolutional neural networks (CNN) and stacked autoencoders (SAE) to classify EEG Motor Imagery signals. A new form of input is introduced to combine time, frequency and location information extracted from EEG signal and it is used in CNN having one 1D convolutional and one max-pooling layers. We also proposed a new deep network by combining CNN and SAE. In this network, the features that are extracted in CNN are classified through the deep network SAE. The classification performance obtained by the proposed method on BCI competition IV dataset 2b in terms of kappa value is 0.547. Our approach yields 9% improvement over the winner algorithm of the competition. Our results show that deep learning methods provide better classification performance compared to other state of art approaches. These methods can be applied successfully to BCI systems where the amount of data is large due to daily recording.

A data fusion approach for track monitoring from multiple in-service trains

NASA Astrophysics Data System (ADS)

Lederman, George; Chen, Siheng; Garrett, James H.; Kovačević, Jelena; Noh, Hae Young; Bielak, Jacobo

2017-10-01

We present a data fusion approach for enabling data-driven rail-infrastructure monitoring from multiple in-service trains. A number of researchers have proposed using vibration data collected from in-service trains as a low-cost method to monitor track geometry. The majority of this work has focused on developing novel features to extract information about the tracks from data produced by individual sensors on individual trains. We extend this work by presenting a technique to combine extracted features from multiple passes over the tracks from multiple sensors aboard multiple vehicles. There are a number of challenges in combining multiple data sources, like different relative position coordinates depending on the location of the sensor within the train. Furthermore, as the number of sensors increases, the likelihood that some will malfunction also increases. We use a two-step approach that first minimizes position offset errors through data alignment, then fuses the data with a novel adaptive Kalman filter that weights data according to its estimated reliability. We show the efficacy of this approach both through simulations and on a data-set collected from two instrumented trains operating over a one-year period. Combining data from numerous in-service trains allows for more continuous and more reliable data-driven monitoring than analyzing data from any one train alone; as the number of instrumented trains increases, the proposed fusion approach could facilitate track monitoring of entire rail-networks.

Optical implementation of neocognitron and its applications to radar signature discrimination

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin; Stoner, William W.

1991-01-01

A feature-extraction-based optoelectronic neural network is introduced. The system implementation approach applies the principle of the neocognitron paradigm first introduced by Fukushima et al. (1983). A multichannel correlator is used as a building block of a generic single layer of the neocognitron for shift-invariant feature correlation. Multilayer processing is achieved by iteratively feeding back the output of the feature correlator to the input spatial light modulator. Successful pattern recognition with intraclass fault tolerance and interclass discrimination is achieved using this optoelectronic neocognitron. Detailed system analysis is described. Experimental demonstration of radar signature processing is also provided.

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.

Cuff-less PPG based continuous blood pressure monitoring: a smartphone based approach.

PubMed

Gaurav, Aman; Maheedhar, Maram; Tiwari, Vijay N; Narayanan, Rangavittal

2016-08-01

Cuff-less estimation of systolic (SBP) and diastolic (DBP) blood pressure is an efficient approach for non-invasive and continuous monitoring of an individual's vitals. Although pulse transit time (PTT) based approaches have been successful in estimating the systolic and diastolic blood pressures to a reasonable degree of accuracy, there is still scope for improvement in terms of accuracies. Moreover, PTT approach requires data from sensors placed at two different locations along with individual calibration of physiological parameters for deriving correct estimation of systolic and diastolic blood pressure (BP) and hence is not suitable for smartphone deployment. Heart Rate Variability is one of the extensively used non-invasive parameters to assess cardiovascular autonomic nervous system and is known to be associated with SBP and DBP indirectly. In this work, we propose a novel method to extract a comprehensive set of features by combining PPG signal based and Heart Rate Variability (HRV) related features using a single PPG sensor. Further, these features are fed into a DBP feedback based combinatorial neural network model to arrive at a common weighted average output of DBP and subsequently SBP. Our results show that using this current approach, an accuracy of ±6.8 mmHg for SBP and ±4.7 mmHg for DBP is achievable on 1,750,000 pulses extracted from a public database (comprising 3000 people). Since most of the smartphones are now equipped with PPG sensor, a mobile based cuff-less BP estimation will enable the user to monitor their BP as a vital parameter on demand. This will open new avenues towards development of pervasive and continuous BP monitoring systems leading to an early detection and prevention of cardiovascular diseases.

Combining high-speed SVM learning with CNN feature encoding for real-time target recognition in high-definition video for ISR missions

NASA Astrophysics Data System (ADS)

Kroll, Christine; von der Werth, Monika; Leuck, Holger; Stahl, Christoph; Schertler, Klaus

2017-05-01

For Intelligence, Surveillance, Reconnaissance (ISR) missions of manned and unmanned air systems typical electrooptical payloads provide high-definition video data which has to be exploited with respect to relevant ground targets in real-time by automatic/assisted target recognition software. Airbus Defence and Space is developing required technologies for real-time sensor exploitation since years and has combined the latest advances of Deep Convolutional Neural Networks (CNN) with a proprietary high-speed Support Vector Machine (SVM) learning method into a powerful object recognition system with impressive results on relevant high-definition video scenes compared to conventional target recognition approaches. This paper describes the principal requirements for real-time target recognition in high-definition video for ISR missions and the Airbus approach of combining an invariant feature extraction using pre-trained CNNs and the high-speed training and classification ability of a novel frequency-domain SVM training method. The frequency-domain approach allows for a highly optimized implementation for General Purpose Computation on a Graphics Processing Unit (GPGPU) and also an efficient training of large training samples. The selected CNN which is pre-trained only once on domain-extrinsic data reveals a highly invariant feature extraction. This allows for a significantly reduced adaptation and training of the target recognition method for new target classes and mission scenarios. A comprehensive training and test dataset was defined and prepared using relevant high-definition airborne video sequences. The assessment concept is explained and performance results are given using the established precision-recall diagrams, average precision and runtime figures on representative test data. A comparison to legacy target recognition approaches shows the impressive performance increase by the proposed CNN+SVM machine-learning approach and the capability of real-time high-definition video exploitation.

Classifying patents based on their semantic content.

PubMed

Bergeaud, Antonin; Potiron, Yoann; Raimbault, Juste

2017-01-01

In this paper, we extend some usual techniques of classification resulting from a large-scale data-mining and network approach. This new technology, which in particular is designed to be suitable to big data, is used to construct an open consolidated database from raw data on 4 million patents taken from the US patent office from 1976 onward. To build the pattern network, not only do we look at each patent title, but we also examine their full abstract and extract the relevant keywords accordingly. We refer to this classification as semantic approach in contrast with the more common technological approach which consists in taking the topology when considering US Patent office technological classes. Moreover, we document that both approaches have highly different topological measures and strong statistical evidence that they feature a different model. This suggests that our method is a useful tool to extract endogenous information.

Structure Elucidation of Unknown Metabolites in Metabolomics by Combined NMR and MS/MS Prediction

DOE PAGES

Boiteau, Rene M.; Hoyt, David W.; Nicora, Carrie D.; ...

2018-01-17

Here, we introduce a cheminformatics approach that combines highly selective and orthogonal structure elucidation parameters; accurate mass, MS/MS (MS 2), and NMR in a single analysis platform to accurately identify unknown metabolites in untargeted studies. The approach starts with an unknown LC-MS feature, and then combines the experimental MS/MS and NMR information of the unknown to effectively filter the false positive candidate structures based on their predicted MS/MS and NMR spectra. We demonstrate the approach on a model mixture and then we identify an uncatalogued secondary metabolite in Arabidopsis thaliana. The NMR/MS 2 approach is well suited for discovery ofmore » new metabolites in plant extracts, microbes, soils, dissolved organic matter, food extracts, biofuels, and biomedical samples, facilitating the identification of metabolites that are not present in experimental NMR and MS metabolomics databases.« less

Structure Elucidation of Unknown Metabolites in Metabolomics by Combined NMR and MS/MS Prediction

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

Boiteau, Rene M.; Hoyt, David W.; Nicora, Carrie D.

Here, we introduce a cheminformatics approach that combines highly selective and orthogonal structure elucidation parameters; accurate mass, MS/MS (MS 2), and NMR in a single analysis platform to accurately identify unknown metabolites in untargeted studies. The approach starts with an unknown LC-MS feature, and then combines the experimental MS/MS and NMR information of the unknown to effectively filter the false positive candidate structures based on their predicted MS/MS and NMR spectra. We demonstrate the approach on a model mixture and then we identify an uncatalogued secondary metabolite in Arabidopsis thaliana. The NMR/MS 2 approach is well suited for discovery ofmore » new metabolites in plant extracts, microbes, soils, dissolved organic matter, food extracts, biofuels, and biomedical samples, facilitating the identification of metabolites that are not present in experimental NMR and MS metabolomics databases.« less

Structure Elucidation of Unknown Metabolites in Metabolomics by Combined NMR and MS/MS Prediction

PubMed Central

Hoyt, David W.; Nicora, Carrie D.; Kinmonth-Schultz, Hannah A.; Ward, Joy K.

2018-01-01

We introduce a cheminformatics approach that combines highly selective and orthogonal structure elucidation parameters; accurate mass, MS/MS (MS2), and NMR into a single analysis platform to accurately identify unknown metabolites in untargeted studies. The approach starts with an unknown LC-MS feature, and then combines the experimental MS/MS and NMR information of the unknown to effectively filter out the false positive candidate structures based on their predicted MS/MS and NMR spectra. We demonstrate the approach on a model mixture, and then we identify an uncatalogued secondary metabolite in Arabidopsis thaliana. The NMR/MS2 approach is well suited to the discovery of new metabolites in plant extracts, microbes, soils, dissolved organic matter, food extracts, biofuels, and biomedical samples, facilitating the identification of metabolites that are not present in experimental NMR and MS metabolomics databases. PMID:29342073

Classifying patents based on their semantic content

PubMed Central

2017-01-01

In this paper, we extend some usual techniques of classification resulting from a large-scale data-mining and network approach. This new technology, which in particular is designed to be suitable to big data, is used to construct an open consolidated database from raw data on 4 million patents taken from the US patent office from 1976 onward. To build the pattern network, not only do we look at each patent title, but we also examine their full abstract and extract the relevant keywords accordingly. We refer to this classification as semantic approach in contrast with the more common technological approach which consists in taking the topology when considering US Patent office technological classes. Moreover, we document that both approaches have highly different topological measures and strong statistical evidence that they feature a different model. This suggests that our method is a useful tool to extract endogenous information. PMID:28445550

Improved classification accuracy of powdery mildew infection levels of wine grapes by spatial-spectral analysis of hyperspectral images.

PubMed

Knauer, Uwe; Matros, Andrea; Petrovic, Tijana; Zanker, Timothy; Scott, Eileen S; Seiffert, Udo

2017-01-01

Hyperspectral imaging is an emerging means of assessing plant vitality, stress parameters, nutrition status, and diseases. Extraction of target values from the high-dimensional datasets either relies on pixel-wise processing of the full spectral information, appropriate selection of individual bands, or calculation of spectral indices. Limitations of such approaches are reduced classification accuracy, reduced robustness due to spatial variation of the spectral information across the surface of the objects measured as well as a loss of information intrinsic to band selection and use of spectral indices. In this paper we present an improved spatial-spectral segmentation approach for the analysis of hyperspectral imaging data and its application for the prediction of powdery mildew infection levels (disease severity) of intact Chardonnay grape bunches shortly before veraison. Instead of calculating texture features (spatial features) for the huge number of spectral bands independently, dimensionality reduction by means of Linear Discriminant Analysis (LDA) was applied first to derive a few descriptive image bands. Subsequent classification was based on modified Random Forest classifiers and selective extraction of texture parameters from the integral image representation of the image bands generated. Dimensionality reduction, integral images, and the selective feature extraction led to improved classification accuracies of up to [Formula: see text] for detached berries used as a reference sample (training dataset). Our approach was validated by predicting infection levels for a sample of 30 intact bunches. Classification accuracy improved with the number of decision trees of the Random Forest classifier. These results corresponded with qPCR results. An accuracy of 0.87 was achieved in classification of healthy, infected, and severely diseased bunches. However, discrimination between visually healthy and infected bunches proved to be challenging for a few samples, perhaps due to colonized berries or sparse mycelia hidden within the bunch or airborne conidia on the berries that were detected by qPCR. An advanced approach to hyperspectral image classification based on combined spatial and spectral image features, potentially applicable to many available hyperspectral sensor technologies, has been developed and validated to improve the detection of powdery mildew infection levels of Chardonnay grape bunches. The spatial-spectral approach improved especially the detection of light infection levels compared with pixel-wise spectral data analysis. This approach is expected to improve the speed and accuracy of disease detection once the thresholds for fungal biomass detected by hyperspectral imaging are established; it can also facilitate monitoring in plant phenotyping of grapevine and additional crops.

Contextual descriptors and neural networks for scene analysis in VHR SAR images

NASA Astrophysics Data System (ADS)

Del Frate, Fabio; Picchiani, Matteo; Falasco, Alessia; Schiavon, Giovanni

2016-10-01

The development of SAR technology during the last decade has made it possible to collect a huge amount of data over many regions of the world. In particular, the availability of SAR images from different sensors, with metric or sub-metric spatial resolution, offers novel opportunities in different fields as land cover, urban monitoring, soil consumption etc. On the other hand, automatic approaches become crucial for the exploitation of such a huge amount of information. In such a scenario, especially if single polarization images are considered, the main issue is to select appropriate contextual descriptors, since the backscattering coefficient of a single pixel may not be sufficient to classify an object on the scene. In this paper a comparison among three different approaches for contextual features definition is presented so as to design optimum procedures for VHR SAR scene understanding. The first approach is based on Gray Level Co- Occurrence Matrix since it is widely accepted and several studies have used it for land cover classification with SAR data. The second approach is based on the Fourier spectra and it has been already proposed with positive results for this kind of problems, the third one is based on Auto-associative Neural Networks which have been already proven effective for features extraction from polarimetric SAR images. The three methods are evaluated in terms of the accuracy of the classified scene when the features extracted using each method are considered as input to a neural network classificator and applied on different Cosmo-SkyMed spotlight products.

ECG Identification System Using Neural Network with Global and Local Features

ERIC Educational Resources Information Center

Tseng, Kuo-Kun; Lee, Dachao; Chen, Charles

2016-01-01

This paper proposes a human identification system via extracted electrocardiogram (ECG) signals. Two hierarchical classification structures based on global shape feature and local statistical feature is used to extract ECG signals. Global shape feature represents the outline information of ECG signals and local statistical feature extracts the…

ADAGE signature analysis: differential expression analysis with data-defined gene sets.

PubMed

Tan, Jie; Huyck, Matthew; Hu, Dongbo; Zelaya, René A; Hogan, Deborah A; Greene, Casey S

2017-11-22

Gene set enrichment analysis and overrepresentation analyses are commonly used methods to determine the biological processes affected by a differential expression experiment. This approach requires biologically relevant gene sets, which are currently curated manually, limiting their availability and accuracy in many organisms without extensively curated resources. New feature learning approaches can now be paired with existing data collections to directly extract functional gene sets from big data. Here we introduce a method to identify perturbed processes. In contrast with methods that use curated gene sets, this approach uses signatures extracted from public expression data. We first extract expression signatures from public data using ADAGE, a neural network-based feature extraction approach. We next identify signatures that are differentially active under a given treatment. Our results demonstrate that these signatures represent biological processes that are perturbed by the experiment. Because these signatures are directly learned from data without supervision, they can identify uncurated or novel biological processes. We implemented ADAGE signature analysis for the bacterial pathogen Pseudomonas aeruginosa. For the convenience of different user groups, we implemented both an R package (ADAGEpath) and a web server ( http://adage.greenelab.com ) to run these analyses. Both are open-source to allow easy expansion to other organisms or signature generation methods. We applied ADAGE signature analysis to an example dataset in which wild-type and ∆anr mutant cells were grown as biofilms on the Cystic Fibrosis genotype bronchial epithelial cells. We mapped active signatures in the dataset to KEGG pathways and compared with pathways identified using GSEA. The two approaches generally return consistent results; however, ADAGE signature analysis also identified a signature that revealed the molecularly supported link between the MexT regulon and Anr. We designed ADAGE signature analysis to perform gene set analysis using data-defined functional gene signatures. This approach addresses an important gap for biologists studying non-traditional model organisms and those without extensive curated resources available. We built both an R package and web server to provide ADAGE signature analysis to the community.

Towards Text Copyright Detection Using Metadata in Web Applications

ERIC Educational Resources Information Center

Poulos, Marios; Korfiatis, Nikolaos; Bokos, George

2011-01-01

Purpose: This paper aims to present the semantic content identifier (SCI), a permanent identifier, computed through a linear-time onion-peeling algorithm that enables the extraction of semantic features from a text, and the integration of this information within the permanent identifier. Design/methodology/approach: The authors employ SCI to…

Variable Selection for Road Segmentation in Aerial Images

NASA Astrophysics Data System (ADS)

Warnke, S.; Bulatov, D.

2017-05-01

For extraction of road pixels from combined image and elevation data, Wegner et al. (2015) proposed classification of superpixels into road and non-road, after which a refinement of the classification results using minimum cost paths and non-local optimization methods took place. We believed that the variable set used for classification was to a certain extent suboptimal, because many variables were redundant while several features known as useful in Photogrammetry and Remote Sensing are missed. This motivated us to implement a variable selection approach which builds a model for classification using portions of training data and subsets of features, evaluates this model, updates the feature set, and terminates when a stopping criterion is satisfied. The choice of classifier is flexible; however, we tested the approach with Logistic Regression and Random Forests, and taylored the evaluation module to the chosen classifier. To guarantee a fair comparison, we kept the segment-based approach and most of the variables from the related work, but we extended them by additional, mostly higher-level features. Applying these superior features, removing the redundant ones, as well as using more accurately acquired 3D data allowed to keep stable or even to reduce the misclassification error in a challenging dataset.

New Fault Recognition Method for Rotary Machinery Based on Information Entropy and a Probabilistic Neural Network.

PubMed

Jiang, Quansheng; Shen, Yehu; Li, Hua; Xu, Fengyu

2018-01-24

Feature recognition and fault diagnosis plays an important role in equipment safety and stable operation of rotating machinery. In order to cope with the complexity problem of the vibration signal of rotating machinery, a feature fusion model based on information entropy and probabilistic neural network is proposed in this paper. The new method first uses information entropy theory to extract three kinds of characteristics entropy in vibration signals, namely, singular spectrum entropy, power spectrum entropy, and approximate entropy. Then the feature fusion model is constructed to classify and diagnose the fault signals. The proposed approach can combine comprehensive information from different aspects and is more sensitive to the fault features. The experimental results on simulated fault signals verified better performances of our proposed approach. In real two-span rotor data, the fault detection accuracy of the new method is more than 10% higher compared with the methods using three kinds of information entropy separately. The new approach is proved to be an effective fault recognition method for rotating machinery.

Automated Feature Extraction of Foredune Morphology from Terrestrial Lidar Data

NASA Astrophysics Data System (ADS)

Spore, N.; Brodie, K. L.; Swann, C.

2014-12-01

Foredune morphology is often described in storm impact prediction models using the elevation of the dune crest and dune toe and compared with maximum runup elevations to categorize the storm impact and predicted responses. However, these parameters do not account for other foredune features that may make them more or less erodible, such as alongshore variations in morphology, vegetation coverage, or compaction. The goal of this work is to identify other descriptive features that can be extracted from terrestrial lidar data that may affect the rate of dune erosion under wave attack. Daily, mobile-terrestrial lidar surveys were conducted during a 6-day nor'easter (Hs = 4 m in 6 m water depth) along 20km of coastline near Duck, North Carolina which encompassed a variety of foredune forms in close proximity to each other. This abstract will focus on the tools developed for the automated extraction of the morphological features from terrestrial lidar data, while the response of the dune will be presented by Brodie and Spore as an accompanying abstract. Raw point cloud data can be dense and is often under-utilized due to time and personnel constraints required for analysis, since many algorithms are not fully automated. In our approach, the point cloud is first projected into a local coordinate system aligned with the coastline, and then bare earth points are interpolated onto a rectilinear 0.5 m grid creating a high resolution digital elevation model. The surface is analyzed by identifying features along each cross-shore transect. Surface curvature is used to identify the position of the dune toe, and then beach and berm morphology is extracted shoreward of the dune toe, and foredune morphology is extracted landward of the dune toe. Changes in, and magnitudes of, cross-shore slope, curvature, and surface roughness are used to describe the foredune face and each cross-shore transect is then classified using its pre-storm morphology for storm-response analysis.

Adaptive weighted local textural features for illumination, expression, and occlusion invariant face recognition

NASA Astrophysics Data System (ADS)

Cui, Chen; Asari, Vijayan K.

2014-03-01

Biometric features such as fingerprints, iris patterns, and face features help to identify people and restrict access to secure areas by performing advanced pattern analysis and matching. Face recognition is one of the most promising biometric methodologies for human identification in a non-cooperative security environment. However, the recognition results obtained by face recognition systems are a affected by several variations that may happen to the patterns in an unrestricted environment. As a result, several algorithms have been developed for extracting different facial features for face recognition. Due to the various possible challenges of data captured at different lighting conditions, viewing angles, facial expressions, and partial occlusions in natural environmental conditions, automatic facial recognition still remains as a difficult issue that needs to be resolved. In this paper, we propose a novel approach to tackling some of these issues by analyzing the local textural descriptions for facial feature representation. The textural information is extracted by an enhanced local binary pattern (ELBP) description of all the local regions of the face. The relationship of each pixel with respect to its neighborhood is extracted and employed to calculate the new representation. ELBP reconstructs a much better textural feature extraction vector from an original gray level image in different lighting conditions. The dimensionality of the texture image is reduced by principal component analysis performed on each local face region. Each low dimensional vector representing a local region is now weighted based on the significance of the sub-region. The weight of each sub-region is determined by employing the local variance estimate of the respective region, which represents the significance of the region. The final facial textural feature vector is obtained by concatenating the reduced dimensional weight sets of all the modules (sub-regions) of the face image. Experiments conducted on various popular face databases show promising performance of the proposed algorithm in varying lighting, expression, and partial occlusion conditions. Four databases were used for testing the performance of the proposed system: Yale Face database, Extended Yale Face database B, Japanese Female Facial Expression database, and CMU AMP Facial Expression database. The experimental results in all four databases show the effectiveness of the proposed system. Also, the computation cost is lower because of the simplified calculation steps. Research work is progressing to investigate the effectiveness of the proposed face recognition method on pose-varying conditions as well. It is envisaged that a multilane approach of trained frameworks at different pose bins and an appropriate voting strategy would lead to a good recognition rate in such situation.

Discovery of Predicate-Oriented Relations among Named Entities Extracted from Thai Texts

NASA Astrophysics Data System (ADS)

Tongtep, Nattapong; Theeramunkong, Thanaruk

Extracting named entities (NEs) and their relations is more difficult in Thai than in other languages due to several Thai specific characteristics, including no explicit boundaries for words, phrases and sentences; few case markers and modifier clues; high ambiguity in compound words and serial verbs; and flexible word orders. Unlike most previous works which focused on NE relations of specific actions, such as work_for, live_in, located_in, and kill, this paper proposes more general types of NE relations, called predicate-oriented relation (PoR), where an extracted action part (verb) is used as a core component to associate related named entities extracted from Thai Texts. Lacking a practical parser for the Thai language, we present three types of surface features, i.e. punctuation marks (such as token spaces), entity types and the number of entities and then apply five alternative commonly used learning schemes to investigate their performance on predicate-oriented relation extraction. The experimental results show that our approach achieves the F-measure of 97.76%, 99.19%, 95.00% and 93.50% on four different types of predicate-oriented relation (action-location, location-action, action-person and person-action) in crime-related news documents using a data set of 1,736 entity pairs. The effects of NE extraction techniques, feature sets and class unbalance on the performance of relation extraction are explored.

Fuzzy Nonlinear Proximal Support Vector Machine for Land Extraction Based on Remote Sensing Image

PubMed Central

Zhong, Xiaomei; Li, Jianping; Dou, Huacheng; Deng, Shijun; Wang, Guofei; Jiang, Yu; Wang, Yongjie; Zhou, Zebing; Wang, Li; Yan, Fei

2013-01-01

Currently, remote sensing technologies were widely employed in the dynamic monitoring of the land. This paper presented an algorithm named fuzzy nonlinear proximal support vector machine (FNPSVM) by basing on ETM+ remote sensing image. This algorithm is applied to extract various types of lands of the city Da’an in northern China. Two multi-category strategies, namely “one-against-one” and “one-against-rest” for this algorithm were described in detail and then compared. A fuzzy membership function was presented to reduce the effects of noises or outliers on the data samples. The approaches of feature extraction, feature selection, and several key parameter settings were also given. Numerous experiments were carried out to evaluate its performances including various accuracies (overall accuracies and kappa coefficient), stability, training speed, and classification speed. The FNPSVM classifier was compared to the other three classifiers including the maximum likelihood classifier (MLC), back propagation neural network (BPN), and the proximal support vector machine (PSVM) under different training conditions. The impacts of the selection of training samples, testing samples and features on the four classifiers were also evaluated in these experiments. PMID:23936016

Classifying Physical Morphology of Cocoa Beans Digital Images using Multiclass Ensemble Least-Squares Support Vector Machine

NASA Astrophysics Data System (ADS)

Lawi, Armin; Adhitya, Yudhi

2018-03-01

The objective of this research is to determine the quality of cocoa beans through morphology of their digital images. Samples of cocoa beans were scattered on a bright white paper under a controlled lighting condition. A compact digital camera was used to capture the images. The images were then processed to extract their morphological parameters. Classification process begins with an analysis of cocoa beans image based on morphological feature extraction. Parameters for extraction of morphological or physical feature parameters, i.e., Area, Perimeter, Major Axis Length, Minor Axis Length, Aspect Ratio, Circularity, Roundness, Ferret Diameter. The cocoa beans are classified into 4 groups, i.e.: Normal Beans, Broken Beans, Fractured Beans, and Skin Damaged Beans. The model of classification used in this paper is the Multiclass Ensemble Least-Squares Support Vector Machine (MELS-SVM), a proposed improvement model of SVM using ensemble method in which the separate hyperplanes are obtained by least square approach and the multiclass procedure uses One-Against- All method. The result of our proposed model showed that the classification with morphological feature input parameters were accurately as 99.705% for the four classes, respectively.

Improving iris recognition performance using segmentation, quality enhancement, match score fusion, and indexing.

PubMed

Vatsa, Mayank; Singh, Richa; Noore, Afzel

2008-08-01

This paper proposes algorithms for iris segmentation, quality enhancement, match score fusion, and indexing to improve both the accuracy and the speed of iris recognition. A curve evolution approach is proposed to effectively segment a nonideal iris image using the modified Mumford-Shah functional. Different enhancement algorithms are concurrently applied on the segmented iris image to produce multiple enhanced versions of the iris image. A support-vector-machine-based learning algorithm selects locally enhanced regions from each globally enhanced image and combines these good-quality regions to create a single high-quality iris image. Two distinct features are extracted from the high-quality iris image. The global textural feature is extracted using the 1-D log polar Gabor transform, and the local topological feature is extracted using Euler numbers. An intelligent fusion algorithm combines the textural and topological matching scores to further improve the iris recognition performance and reduce the false rejection rate, whereas an indexing algorithm enables fast and accurate iris identification. The verification and identification performance of the proposed algorithms is validated and compared with other algorithms using the CASIA Version 3, ICE 2005, and UBIRIS iris databases.

Intelligent Diagnosis Method for Rotating Machinery Using Dictionary Learning and Singular Value Decomposition.

PubMed

Han, Te; Jiang, Dongxiang; Zhang, Xiaochen; Sun, Yankui

2017-03-27

Rotating machinery is widely used in industrial applications. With the trend towards more precise and more critical operating conditions, mechanical failures may easily occur. Condition monitoring and fault diagnosis (CMFD) technology is an effective tool to enhance the reliability and security of rotating machinery. In this paper, an intelligent fault diagnosis method based on dictionary learning and singular value decomposition (SVD) is proposed. First, the dictionary learning scheme is capable of generating an adaptive dictionary whose atoms reveal the underlying structure of raw signals. Essentially, dictionary learning is employed as an adaptive feature extraction method regardless of any prior knowledge. Second, the singular value sequence of learned dictionary matrix is served to extract feature vector. Generally, since the vector is of high dimensionality, a simple and practical principal component analysis (PCA) is applied to reduce dimensionality. Finally, the K -nearest neighbor (KNN) algorithm is adopted for identification and classification of fault patterns automatically. Two experimental case studies are investigated to corroborate the effectiveness of the proposed method in intelligent diagnosis of rotating machinery faults. The comparison analysis validates that the dictionary learning-based matrix construction approach outperforms the mode decomposition-based methods in terms of capacity and adaptability for feature extraction.

Segmentation of human face using gradient-based approach

NASA Astrophysics Data System (ADS)

Baskan, Selin; Bulut, M. Mete; Atalay, Volkan

2001-04-01

This paper describes a method for automatic segmentation of facial features such as eyebrows, eyes, nose, mouth and ears in color images. This work is an initial step for wide range of applications based on feature-based approaches, such as face recognition, lip-reading, gender estimation, facial expression analysis, etc. Human face can be characterized by its skin color and nearly elliptical shape. For this purpose, face detection is performed using color and shape information. Uniform illumination is assumed. No restrictions on glasses, make-up, beard, etc. are imposed. Facial features are extracted using the vertically and horizontally oriented gradient projections. The gradient of a minimum with respect to its neighbor maxima gives the boundaries of a facial feature. Each facial feature has a different horizontal characteristic. These characteristics are derived by extensive experimentation with many face images. Using fuzzy set theory, the similarity between the candidate and the feature characteristic under consideration is calculated. Gradient-based method is accompanied by the anthropometrical information, for robustness. Ear detection is performed using contour-based shape descriptors. This method detects the facial features and circumscribes each facial feature with the smallest rectangle possible. AR database is used for testing. The developed method is also suitable for real-time systems.

Image processing based detection of lung cancer on CT scan images

NASA Astrophysics Data System (ADS)

Abdillah, Bariqi; Bustamam, Alhadi; Sarwinda, Devvi

2017-10-01

In this paper, we implement and analyze the image processing method for detection of lung cancer. Image processing techniques are widely used in several medical problems for picture enhancement in the detection phase to support the early medical treatment. In this research we proposed a detection method of lung cancer based on image segmentation. Image segmentation is one of intermediate level in image processing. Marker control watershed and region growing approach are used to segment of CT scan image. Detection phases are followed by image enhancement using Gabor filter, image segmentation, and features extraction. From the experimental results, we found the effectiveness of our approach. The results show that the best approach for main features detection is watershed with masking method which has high accuracy and robust.

A structural SVM approach for reference parsing.

PubMed

Zhang, Xiaoli; Zou, Jie; Le, Daniel X; Thoma, George R

2011-06-09

Automated extraction of bibliographic data, such as article titles, author names, abstracts, and references is essential to the affordable creation of large citation databases. References, typically appearing at the end of journal articles, can also provide valuable information for extracting other bibliographic data. Therefore, parsing individual reference to extract author, title, journal, year, etc. is sometimes a necessary preprocessing step in building citation-indexing systems. The regular structure in references enables us to consider reference parsing a sequence learning problem and to study structural Support Vector Machine (structural SVM), a newly developed structured learning algorithm on parsing references. In this study, we implemented structural SVM and used two types of contextual features to compare structural SVM with conventional SVM. Both methods achieve above 98% token classification accuracy and above 95% overall chunk-level accuracy for reference parsing. We also compared SVM and structural SVM to Conditional Random Field (CRF). The experimental results show that structural SVM and CRF achieve similar accuracies at token- and chunk-levels. When only basic observation features are used for each token, structural SVM achieves higher performance compared to SVM since it utilizes the contextual label features. However, when the contextual observation features from neighboring tokens are combined, SVM performance improves greatly, and is close to that of structural SVM after adding the second order contextual observation features. The comparison of these two methods with CRF using the same set of binary features show that both structural SVM and CRF perform better than SVM, indicating their stronger sequence learning ability in reference parsing.

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.

Speech Emotion Feature Selection Method Based on Contribution Analysis Algorithm of Neural Network

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

Wang Xiaojia; Mao Qirong; Zhan Yongzhao

There are many emotion features. If all these features are employed to recognize emotions, redundant features may be existed. Furthermore, recognition result is unsatisfying and the cost of feature extraction is high. In this paper, a method to select speech emotion features based on contribution analysis algorithm of NN is presented. The emotion features are selected by using contribution analysis algorithm of NN from the 95 extracted features. Cluster analysis is applied to analyze the effectiveness for the features selected, and the time of feature extraction is evaluated. Finally, 24 emotion features selected are used to recognize six speech emotions.more » The experiments show that this method can improve the recognition rate and the time of feature extraction.« less

The effects of variations in parameters and algorithm choices on calculated radiomics feature values: initial investigations and comparisons to feature variability across CT image acquisition conditions

NASA Astrophysics Data System (ADS)

Emaminejad, Nastaran; Wahi-Anwar, Muhammad; Hoffman, John; Kim, Grace H.; Brown, Matthew S.; McNitt-Gray, Michael

2018-02-01

Translation of radiomics into clinical practice requires confidence in its interpretations. This may be obtained via understanding and overcoming the limitations in current radiomic approaches. Currently there is a lack of standardization in radiomic feature extraction. In this study we examined a few factors that are potential sources of inconsistency in characterizing lung nodules, such as 1)different choices of parameters and algorithms in feature calculation, 2)two CT image dose levels, 3)different CT reconstruction algorithms (WFBP, denoised WFBP, and Iterative). We investigated the effect of variation of these factors on entropy textural feature of lung nodules. CT images of 19 lung nodules identified from our lung cancer screening program were identified by a CAD tool and contours provided. The radiomics features were extracted by calculating 36 GLCM based and 4 histogram based entropy features in addition to 2 intensity based features. A robustness index was calculated across different image acquisition parameters to illustrate the reproducibility of features. Most GLCM based and all histogram based entropy features were robust across two CT image dose levels. Denoising of images slightly improved robustness of some entropy features at WFBP. Iterative reconstruction resulted in improvement of robustness in a fewer times and caused more variation in entropy feature values and their robustness. Within different choices of parameters and algorithms texture features showed a wide range of variation, as much as 75% for individual nodules. Results indicate the need for harmonization of feature calculations and identification of optimum parameters and algorithms in a radiomics study.

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

Applications of artificial intelligence to digital photogrammetry

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

Kretsch, J.L.

1988-01-01

The aim of this research was to explore the application of expert systems to digital photogrammetry, specifically to photogrammetric triangulation, feature extraction, and photogrammetric problem solving. In 1987, prototype expert systems were developed for doing system startup, interior orientation, and relative orientation in the mensuration stage. The system explored means of performing diagnostics during the process. In the area of feature extraction, the relationship of metric uncertainty to symbolic uncertainty was the topic of research. Error propagation through the Dempster-Shafer formalism for representing evidence was performed in order to find the variance in the calculated belief values due to errorsmore » in measurements made together the initial evidence needed to being labeling of observed image features with features in an object model. In photogrammetric problem solving, an expert system is under continuous development which seeks to solve photogrammetric problems using mathematical reasoning. The key to the approach used is the representation of knowledge directly in the form of equations, rather than in the form of if-then rules. Then each variable in the equations is treated as a goal to be solved.« less

Unconstrained and contactless hand geometry biometrics.

PubMed

de-Santos-Sierra, Alberto; Sánchez-Ávila, Carmen; Del Pozo, Gonzalo Bailador; Guerra-Casanova, Javier

2011-01-01

This paper presents a hand biometric system for contact-less, platform-free scenarios, proposing innovative methods in feature extraction, template creation and template matching. The evaluation of the proposed method considers both the use of three contact-less publicly available hand databases, and the comparison of the performance to two competitive pattern recognition techniques existing in literature: namely support vector machines (SVM) and k-nearest neighbour (k-NN). Results highlight the fact that the proposed method outcomes existing approaches in literature in terms of computational cost, accuracy in human identification, number of extracted features and number of samples for template creation. The proposed method is a suitable solution for human identification in contact-less scenarios based on hand biometrics, providing a feasible solution to devices with limited hardware requirements like mobile devices.

Unconstrained and Contactless Hand Geometry Biometrics

PubMed Central

de-Santos-Sierra, Alberto; Sánchez-Ávila, Carmen; del Pozo, Gonzalo Bailador; Guerra-Casanova, Javier

2011-01-01

This paper presents a hand biometric system for contact-less, platform-free scenarios, proposing innovative methods in feature extraction, template creation and template matching. The evaluation of the proposed method considers both the use of three contact-less publicly available hand databases, and the comparison of the performance to two competitive pattern recognition techniques existing in literature: namely Support Vector Machines (SVM) and k-Nearest Neighbour (k-NN). Results highlight the fact that the proposed method outcomes existing approaches in literature in terms of computational cost, accuracy in human identification, number of extracted features and number of samples for template creation. The proposed method is a suitable solution for human identification in contact-less scenarios based on hand biometrics, providing a feasible solution to devices with limited hardware requirements like mobile devices. PMID:22346634

Distribution and Features of the Six Classes of Peroxiredoxins

PubMed Central

Poole, Leslie B.; Nelson, Kimberly J.

2016-01-01

Peroxiredoxins are cysteine-dependent peroxide reductases that group into 6 different, structurally discernable classes. In 2011, our research team reported the application of a bioinformatic approach called active site profiling to extract active site-proximal sequence segments from the 29 distinct, structurally-characterized peroxiredoxins available at the time. These extracted sequences were then used to create unique profiles for the six groups which were subsequently used to search GenBank(nr), allowing identification of ∼3500 peroxiredoxin sequences and their respective subgroups. Summarized in this minireview are the features and phylogenetic distributions of each of these peroxiredoxin subgroups; an example is also provided illustrating the use of the web accessible, searchable database known as PREX to identify subfamily-specific peroxiredoxin sequences for the organism Vitis vinifera (grape). PMID:26810075

Radiomic analysis in prediction of Human Papilloma Virus status.

PubMed

Yu, Kaixian; Zhang, Youyi; Yu, Yang; Huang, Chao; Liu, Rongjie; Li, Tengfei; Yang, Liuqing; Morris, Jeffrey S; Baladandayuthapani, Veerabhadran; Zhu, Hongtu

2017-12-01

Human Papilloma Virus (HPV) has been associated with oropharyngeal cancer prognosis. Traditionally the HPV status is tested through invasive lab test. Recently, the rapid development of statistical image analysis techniques has enabled precise quantitative analysis of medical images. The quantitative analysis of Computed Tomography (CT) provides a non-invasive way to assess HPV status for oropharynx cancer patients. We designed a statistical radiomics approach analyzing CT images to predict HPV status. Various radiomics features were extracted from CT scans, and analyzed using statistical feature selection and prediction methods. Our approach ranked the highest in the 2016 Medical Image Computing and Computer Assisted Intervention (MICCAI) grand challenge: Oropharynx Cancer (OPC) Radiomics Challenge, Human Papilloma Virus (HPV) Status Prediction. Further analysis on the most relevant radiomic features distinguishing HPV positive and negative subjects suggested that HPV positive patients usually have smaller and simpler tumors.

Multi Texture Analysis of Colorectal Cancer Continuum Using Multispectral Imagery

PubMed Central

Chaddad, Ahmad; Desrosiers, Christian; Bouridane, Ahmed; Toews, Matthew; Hassan, Lama; Tanougast, Camel

2016-01-01

Purpose This paper proposes to characterize the continuum of colorectal cancer (CRC) using multiple texture features extracted from multispectral optical microscopy images. Three types of pathological tissues (PT) are considered: benign hyperplasia, intraepithelial neoplasia and carcinoma. Materials and Methods In the proposed approach, the region of interest containing PT is first extracted from multispectral images using active contour segmentation. This region is then encoded using texture features based on the Laplacian-of-Gaussian (LoG) filter, discrete wavelets (DW) and gray level co-occurrence matrices (GLCM). To assess the significance of textural differences between PT types, a statistical analysis based on the Kruskal-Wallis test is performed. The usefulness of texture features is then evaluated quantitatively in terms of their ability to predict PT types using various classifier models. Results Preliminary results show significant texture differences between PT types, for all texture features (p-value < 0.01). Individually, GLCM texture features outperform LoG and DW features in terms of PT type prediction. However, a higher performance can be achieved by combining all texture features, resulting in a mean classification accuracy of 98.92%, sensitivity of 98.12%, and specificity of 99.67%. Conclusions These results demonstrate the efficiency and effectiveness of combining multiple texture features for characterizing the continuum of CRC and discriminating between pathological tissues in multispectral images. PMID:26901134

Robust Object Tracking with a Hierarchical Ensemble Framework

DTIC Science & Technology

2016-10-09

layer; 4 -update the top layer; 5-re-extract the sub-patches and update their weights in the middle layer; 6-update the parameters of weak classifiers...approaches [ 4 ], [5], which represent the target with a limited number of non-overlapping or regular local regions. So they may not cope well with the large...significant- ly reduce the feature dimensions so that our approach can handle colorful images without suffering from exponential memory explosion; 4

Extracting features of Gaussian self-similar stochastic processes via the Bandt-Pompe approach.

PubMed

Rosso, O A; Zunino, L; Pérez, D G; Figliola, A; Larrondo, H A; Garavaglia, M; Martín, M T; Plastino, A

2007-12-01

By recourse to appropriate information theory quantifiers (normalized Shannon entropy and Martín-Plastino-Rosso intensive statistical complexity measure), we revisit the characterization of Gaussian self-similar stochastic processes from a Bandt-Pompe viewpoint. We show that the ensuing approach exhibits considerable advantages with respect to other treatments. In particular, clear quantifiers gaps are found in the transition between the continuous processes and their associated noises.

Automatic detection of multi-level acetowhite regions in RGB color images of the uterine cervix

NASA Astrophysics Data System (ADS)

Lange, Holger

2005-04-01

Uterine cervical cancer is the second most common cancer among women worldwide. Colposcopy is a diagnostic method used to detect cancer precursors and cancer of the uterine cervix, whereby a physician (colposcopist) visually inspects the metaplastic epithelium on the cervix for certain distinctly abnormal morphologic features. A contrast agent, a 3-5% acetic acid solution, is used, causing abnormal and metaplastic epithelia to turn white. The colposcopist considers diagnostic features such as the acetowhite, blood vessel structure, and lesion margin to derive a clinical diagnosis. STI Medical Systems is developing a Computer-Aided-Diagnosis (CAD) system for colposcopy -- ColpoCAD, a complex image analysis system that at its core assesses the same visual features as used by colposcopists. The acetowhite feature has been identified as one of the most important individual predictors of lesion severity. Here, we present the details and preliminary results of a multi-level acetowhite region detection algorithm for RGB color images of the cervix, including the detection of the anatomic features: cervix, os and columnar region, which are used for the acetowhite region detection. The RGB images are assumed to be glare free, either obtained by cross-polarized image acquisition or glare removal pre-processing. The basic approach of the algorithm is to extract a feature image from the RGB image that provides a good acetowhite to cervix background ratio, to segment the feature image using novel pixel grouping and multi-stage region-growing algorithms that provide region segmentations with different levels of detail, to extract the acetowhite regions from the region segmentations using a novel region selection algorithm, and then finally to extract the multi-levels from the acetowhite regions using multiple thresholds. The performance of the algorithm is demonstrated using human subject data.

Differential evolution-based multi-objective optimization for the definition of a health indicator for fault diagnostics and prognostics

NASA Astrophysics Data System (ADS)

Baraldi, P.; Bonfanti, G.; Zio, E.

2018-03-01

The identification of the current degradation state of an industrial component and the prediction of its future evolution is a fundamental step for the development of condition-based and predictive maintenance approaches. The objective of the present work is to propose a general method for extracting a health indicator to measure the amount of component degradation from a set of signals measured during operation. The proposed method is based on the combined use of feature extraction techniques, such as Empirical Mode Decomposition and Auto-Associative Kernel Regression, and a multi-objective Binary Differential Evolution (BDE) algorithm for selecting the subset of features optimal for the definition of the health indicator. The objectives of the optimization are desired characteristics of the health indicator, such as monotonicity, trendability and prognosability. A case study is considered, concerning the prediction of the remaining useful life of turbofan engines. The obtained results confirm that the method is capable of extracting health indicators suitable for accurate prognostics.

Image segmentation-based robust feature extraction for color image watermarking

NASA Astrophysics Data System (ADS)

Li, Mianjie; Deng, Zeyu; Yuan, Xiaochen

2018-04-01

This paper proposes a local digital image watermarking method based on Robust Feature Extraction. The segmentation is achieved by Simple Linear Iterative Clustering (SLIC) based on which an Image Segmentation-based Robust Feature Extraction (ISRFE) method is proposed for feature extraction. Our method can adaptively extract feature regions from the blocks segmented by SLIC. This novel method can extract the most robust feature region in every segmented image. Each feature region is decomposed into low-frequency domain and high-frequency domain by Discrete Cosine Transform (DCT). Watermark images are then embedded into the coefficients in the low-frequency domain. The Distortion-Compensated Dither Modulation (DC-DM) algorithm is chosen as the quantization method for embedding. The experimental results indicate that the method has good performance under various attacks. Furthermore, the proposed method can obtain a trade-off between high robustness and good image quality.

An approach for traffic prohibition sign detection

NASA Astrophysics Data System (ADS)

Li, Qingquan; Xu, Dihong; Li, Bijun; Zeng, Zhe

2006-10-01

This paper presents an off-line traffic prohibition sign detection approach, whose core is based on combination with the color feature of traffic prohibition signs, shape feature and degree of circularity. Matlab-Image-processing toolbox is used for this purpose. In order to reduce the computational cost, a pre-processing of the image is applied before the core. Then, we employ the obvious redness attribute of prohibition signs to coarsely eliminate the non-redness image in the input data. Again, a edge-detection operator, Canny edge detector, is applied to extract the potential edge. Finally, Degree of circularity is used to verdict the traffic prohibition sign. Experimental results show that our systems offer satisfactory performance.

Performance estimation for threat detection in CT systems

NASA Astrophysics Data System (ADS)

Montgomery, Trent; Karl, W. Clem; Castañón, David A.

2017-05-01

Detecting the presence of hazardous materials in suitcases and carry-on luggage is an important problem in aviation security. As the set of threats is expanding, there is a corresponding need to increase the capabilities of explosive detection systems to address these threats. However, there is a lack of principled tools for predicting the performance of alternative designs for detection systems. In this paper, we describe an approach for computing bounds on the achievable classification performance of material discrimination systems based on empirical statistics that estimate the f-divergence of the underlying features. Our approach can be used to examine alternative physical observation modalities and measurement configurations, as well as variations in reconstruction and feature extraction algorithms.

Applying the LANL Statistical Pattern Recognition Paradigm for Structural Health Monitoring to Data from a Surface-Effect Fast Patrol Boat

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

Hoon Sohn; Charles Farrar; Norman Hunter

2001-01-01

This report summarizes the analysis of fiber-optic strain gauge data obtained from a surface-effect fast patrol boat being studied by the staff at the Norwegian Defense Research Establishment (NDRE) in Norway and the Naval Research Laboratory (NRL) in Washington D.C. Data from two different structural conditions were provided to the staff at Los Alamos National Laboratory. The problem was then approached from a statistical pattern recognition paradigm. This paradigm can be described as a four-part process: (1) operational evaluation, (2) data acquisition & cleansing, (3) feature extraction and data reduction, and (4) statistical model development for feature discrimination. Given thatmore » the first two portions of this paradigm were mostly completed by the NDRE and NRL staff, this study focused on data normalization, feature extraction, and statistical modeling for feature discrimination. The feature extraction process began by looking at relatively simple statistics of the signals and progressed to using the residual errors from auto-regressive (AR) models fit to the measured data as the damage-sensitive features. Data normalization proved to be the most challenging portion of this investigation. A novel approach to data normalization, where the residual errors in the AR model are considered to be an unmeasured input and an auto-regressive model with exogenous inputs (ARX) is then fit to portions of the data exhibiting similar waveforms, was successfully applied to this problem. With this normalization procedure, a clear distinction between the two different structural conditions was obtained. A false-positive study was also run, and the procedure developed herein did not yield any false-positive indications of damage. Finally, the results must be qualified by the fact that this procedure has only been applied to very limited data samples. A more complete analysis of additional data taken under various operational and environmental conditions as well as other structural conditions is necessary before one can definitively state that the procedure is robust enough to be used in practice.« less