An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network.

PubMed

Shen, Xiaolei; Zhang, Jiachi; Yan, Chenjun; Zhou, Hong

2018-04-11

In this paper, we present a new automatic diagnosis method for facial acne vulgaris which is based on convolutional neural networks (CNNs). To overcome the shortcomings of previous methods which were the inability to classify enough types of acne vulgaris. The core of our method is to extract features of images based on CNNs and achieve classification by classifier. A binary-classifier of skin-and-non-skin is used to detect skin area and a seven-classifier is used to achieve the classification task of facial acne vulgaris and healthy skin. In the experiments, we compare the effectiveness of our CNN and the VGG16 neural network which is pre-trained on the ImageNet data set. We use a ROC curve to evaluate the performance of binary-classifier and use a normalized confusion matrix to evaluate the performance of seven-classifier. The results of our experiments show that the pre-trained VGG16 neural network is effective in extracting features from facial acne vulgaris images. And the features are very useful for the follow-up classifiers. Finally, we try applying the classifiers both based on the pre-trained VGG16 neural network to assist doctors in facial acne vulgaris diagnosis.

An Application Development Platform for Neuromorphic Computing

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

Dean, Mark; Chan, Jason; Daffron, Christopher

2016-01-01

Dynamic Adaptive Neural Network Arrays (DANNAs) are neuromorphic computing systems developed as a hardware based approach to the implementation of neural networks. They feature highly adaptive and programmable structural elements, which model arti cial neural networks with spiking behavior. We design them to solve problems using evolutionary optimization. In this paper, we highlight the current hardware and software implementations of DANNA, including their features, functionalities and performance. We then describe the development of an Application Development Platform (ADP) to support efficient application implementation and testing of DANNA based solutions. We conclude with future directions.

Invariant-feature-based adaptive automatic target recognition in obscured 3D point clouds

NASA Astrophysics Data System (ADS)

Khuon, Timothy; Kershner, Charles; Mattei, Enrico; Alverio, Arnel; Rand, Robert

2014-06-01

Target recognition and classification in a 3D point cloud is a non-trivial process due to the nature of the data collected from a sensor system. The signal can be corrupted by noise from the environment, electronic system, A/D converter, etc. Therefore, an adaptive system with a desired tolerance is required to perform classification and recognition optimally. The feature-based pattern recognition algorithm architecture as described below is particularly devised for solving a single-sensor classification non-parametrically. Feature set is extracted from an input point cloud, normalized, and classifier a neural network classifier. For instance, automatic target recognition in an urban area would require different feature sets from one in a dense foliage area. The figure above (see manuscript) illustrates the architecture of the feature based adaptive signature extraction of 3D point cloud including LIDAR, RADAR, and electro-optical data. This network takes a 3D cluster and classifies it into a specific class. The algorithm is a supervised and adaptive classifier with two modes: the training mode and the performing mode. For the training mode, a number of novel patterns are selected from actual or artificial data. A particular 3D cluster is input to the network as shown above for the decision class output. The network consists of three sequential functional modules. The first module is for feature extraction that extracts the input cluster into a set of singular value features or feature vector. Then the feature vector is input into the feature normalization module to normalize and balance it before being fed to the neural net classifier for the classification. The neural net can be trained by actual or artificial novel data until each trained output reaches the declared output within the defined tolerance. In case new novel data is added after the neural net has been learned, the training is then resumed until the neural net has incrementally learned with the new novel data. The associative memory capability of the neural net enables the incremental learning. The back propagation algorithm or support vector machine can be utilized for the classification and recognition.

Hadoop neural network for parallel and distributed feature selection.

PubMed

Hodge, Victoria J; O'Keefe, Simon; Austin, Jim

2016-06-01

In this paper, we introduce a theoretical basis for a Hadoop-based neural network for parallel and distributed feature selection in Big Data sets. It is underpinned by an associative memory (binary) neural network which is highly amenable to parallel and distributed processing and fits with the Hadoop paradigm. There are many feature selectors described in the literature which all have various strengths and weaknesses. We present the implementation details of five feature selection algorithms constructed using our artificial neural network framework embedded in Hadoop YARN. Hadoop allows parallel and distributed processing. Each feature selector can be divided into subtasks and the subtasks can then be processed in parallel. Multiple feature selectors can also be processed simultaneously (in parallel) allowing multiple feature selectors to be compared. We identify commonalities among the five features selectors. All can be processed in the framework using a single representation and the overall processing can also be greatly reduced by only processing the common aspects of the feature selectors once and propagating these aspects across all five feature selectors as necessary. This allows the best feature selector and the actual features to select to be identified for large and high dimensional data sets through exploiting the efficiency and flexibility of embedding the binary associative-memory neural network in Hadoop. Copyright © 2015 The Authors. Published by Elsevier Ltd.. All rights reserved.

A neural network ActiveX based integrated image processing environment.

PubMed

Ciuca, I; Jitaru, E; Alaicescu, M; Moisil, I

2000-01-01

The paper outlines an integrated image processing environment that uses neural networks ActiveX technology for object recognition and classification. The image processing environment which is Windows based, encapsulates a Multiple-Document Interface (MDI) and is menu driven. Object (shape) parameter extraction is focused on features that are invariant in terms of translation, rotation and scale transformations. The neural network models that can be incorporated as ActiveX components into the environment allow both clustering and classification of objects from the analysed image. Mapping neural networks perform an input sensitivity analysis on the extracted feature measurements and thus facilitate the removal of irrelevant features and improvements in the degree of generalisation. The program has been used to evaluate the dimensions of the hydrocephalus in a study for calculating the Evans index and the angle of the frontal horns of the ventricular system modifications.

Automatic sleep stage classification of single-channel EEG by using complex-valued convolutional neural network.

PubMed

Zhang, Junming; Wu, Yan

2018-03-28

Many systems are developed for automatic sleep stage classification. However, nearly all models are based on handcrafted features. Because of the large feature space, there are so many features that feature selection should be used. Meanwhile, designing handcrafted features is a difficult and time-consuming task because the feature designing needs domain knowledge of experienced experts. Results vary when different sets of features are chosen to identify sleep stages. Additionally, many features that we may be unaware of exist. However, these features may be important for sleep stage classification. Therefore, a new sleep stage classification system, which is based on the complex-valued convolutional neural network (CCNN), is proposed in this study. Unlike the existing sleep stage methods, our method can automatically extract features from raw electroencephalography data and then classify sleep stage based on the learned features. Additionally, we also prove that the decision boundaries for the real and imaginary parts of a complex-valued convolutional neuron intersect orthogonally. The classification performances of handcrafted features are compared with those of learned features via CCNN. Experimental results show that the proposed method is comparable to the existing methods. CCNN obtains a better classification performance and considerably faster convergence speed than convolutional neural network. Experimental results also show that the proposed method is a useful decision-support tool for automatic sleep stage classification.

Neural network-based feature point descriptors for registration of optical and SAR images

NASA Astrophysics Data System (ADS)

Abulkhanov, Dmitry; Konovalenko, Ivan; Nikolaev, Dmitry; Savchik, Alexey; Shvets, Evgeny; Sidorchuk, Dmitry

2018-04-01

Registration of images of different nature is an important technique used in image fusion, change detection, efficient information representation and other problems of computer vision. Solving this task using feature-based approaches is usually more complex than registration of several optical images because traditional feature descriptors (SIFT, SURF, etc.) perform poorly when images have different nature. In this paper we consider the problem of registration of SAR and optical images. We train neural network to build feature point descriptors and use RANSAC algorithm to align found matches. Experimental results are presented that confirm the method's effectiveness.

Feature selection for neural network based defect classification of ceramic components using high frequency ultrasound.

PubMed

Kesharaju, Manasa; Nagarajah, Romesh

2015-09-01

The motivation for this research stems from a need for providing a non-destructive testing method capable of detecting and locating any defects and microstructural variations within armour ceramic components before issuing them to the soldiers who rely on them for their survival. The development of an automated ultrasonic inspection based classification system would make possible the checking of each ceramic component and immediately alert the operator about the presence of defects. Generally, in many classification problems a choice of features or dimensionality reduction is significant and simultaneously very difficult, as a substantial computational effort is required to evaluate possible feature subsets. In this research, a combination of artificial neural networks and genetic algorithms are used to optimize the feature subset used in classification of various defects in reaction-sintered silicon carbide ceramic components. Initially wavelet based feature extraction is implemented from the region of interest. An Artificial Neural Network classifier is employed to evaluate the performance of these features. Genetic Algorithm based feature selection is performed. Principal Component Analysis is a popular technique used for feature selection and is compared with the genetic algorithm based technique in terms of classification accuracy and selection of optimal number of features. The experimental results confirm that features identified by Principal Component Analysis lead to improved performance in terms of classification percentage with 96% than Genetic algorithm with 94%. Copyright © 2015 Elsevier B.V. All rights reserved.

Resting State EEG-based biometrics for individual identification using convolutional neural networks.

PubMed

Lan Ma; Minett, James W; Blu, Thierry; Wang, William S-Y

2015-08-01

Biometrics is a growing field, which permits identification of individuals by means of unique physical features. Electroencephalography (EEG)-based biometrics utilizes the small intra-personal differences and large inter-personal differences between individuals' brainwave patterns. In the past, such methods have used features derived from manually-designed procedures for this purpose. Another possibility is to use convolutional neural networks (CNN) to automatically extract an individual's best and most unique neural features and conduct classification, using EEG data derived from both Resting State with Open Eyes (REO) and Resting State with Closed Eyes (REC). Results indicate that this CNN-based joint-optimized EEG-based Biometric System yields a high degree of accuracy of identification (88%) for 10-class classification. Furthermore, rich inter-personal difference can be found using a very low frequency band (0-2Hz). Additionally, results suggest that the temporal portions over which subjects can be individualized is less than 200 ms.

A P2P Botnet detection scheme based on decision tree and adaptive multilayer neural networks.

PubMed

Alauthaman, Mohammad; Aslam, Nauman; Zhang, Li; Alasem, Rafe; Hossain, M A

2018-01-01

In recent years, Botnets have been adopted as a popular method to carry and spread many malicious codes on the Internet. These malicious codes pave the way to execute many fraudulent activities including spam mail, distributed denial-of-service attacks and click fraud. While many Botnets are set up using centralized communication architecture, the peer-to-peer (P2P) Botnets can adopt a decentralized architecture using an overlay network for exchanging command and control data making their detection even more difficult. This work presents a method of P2P Bot detection based on an adaptive multilayer feed-forward neural network in cooperation with decision trees. A classification and regression tree is applied as a feature selection technique to select relevant features. With these features, a multilayer feed-forward neural network training model is created using a resilient back-propagation learning algorithm. A comparison of feature set selection based on the decision tree, principal component analysis and the ReliefF algorithm indicated that the neural network model with features selection based on decision tree has a better identification accuracy along with lower rates of false positives. The usefulness of the proposed approach is demonstrated by conducting experiments on real network traffic datasets. In these experiments, an average detection rate of 99.08 % with false positive rate of 0.75 % was observed.

Feature-Selective Attention Adaptively Shifts Noise Correlations in Primary Auditory Cortex.

PubMed

Downer, Joshua D; Rapone, Brittany; Verhein, Jessica; O'Connor, Kevin N; Sutter, Mitchell L

2017-05-24

Sensory environments often contain an overwhelming amount of information, with both relevant and irrelevant information competing for neural resources. Feature attention mediates this competition by selecting the sensory features needed to form a coherent percept. How attention affects the activity of populations of neurons to support this process is poorly understood because population coding is typically studied through simulations in which one sensory feature is encoded without competition. Therefore, to study the effects of feature attention on population-based neural coding, investigations must be extended to include stimuli with both relevant and irrelevant features. We measured noise correlations ( r noise ) within small neural populations in primary auditory cortex while rhesus macaques performed a novel feature-selective attention task. We found that the effect of feature-selective attention on r noise depended not only on the population tuning to the attended feature, but also on the tuning to the distractor feature. To attempt to explain how these observed effects might support enhanced perceptual performance, we propose an extension of a simple and influential model in which shifts in r noise can simultaneously enhance the representation of the attended feature while suppressing the distractor. These findings present a novel mechanism by which attention modulates neural populations to support sensory processing in cluttered environments. SIGNIFICANCE STATEMENT Although feature-selective attention constitutes one of the building blocks of listening in natural environments, its neural bases remain obscure. To address this, we developed a novel auditory feature-selective attention task and measured noise correlations ( r noise ) in rhesus macaque A1 during task performance. Unlike previous studies showing that the effect of attention on r noise depends on population tuning to the attended feature, we show that the effect of attention depends on the tuning to the distractor feature as well. We suggest that these effects represent an efficient process by which sensory cortex simultaneously enhances relevant information and suppresses irrelevant information. Copyright © 2017 the authors 0270-6474/17/375378-15$15.00/0.

Feature-Selective Attention Adaptively Shifts Noise Correlations in Primary Auditory Cortex

PubMed Central

2017-01-01

Sensory environments often contain an overwhelming amount of information, with both relevant and irrelevant information competing for neural resources. Feature attention mediates this competition by selecting the sensory features needed to form a coherent percept. How attention affects the activity of populations of neurons to support this process is poorly understood because population coding is typically studied through simulations in which one sensory feature is encoded without competition. Therefore, to study the effects of feature attention on population-based neural coding, investigations must be extended to include stimuli with both relevant and irrelevant features. We measured noise correlations (rnoise) within small neural populations in primary auditory cortex while rhesus macaques performed a novel feature-selective attention task. We found that the effect of feature-selective attention on rnoise depended not only on the population tuning to the attended feature, but also on the tuning to the distractor feature. To attempt to explain how these observed effects might support enhanced perceptual performance, we propose an extension of a simple and influential model in which shifts in rnoise can simultaneously enhance the representation of the attended feature while suppressing the distractor. These findings present a novel mechanism by which attention modulates neural populations to support sensory processing in cluttered environments. SIGNIFICANCE STATEMENT Although feature-selective attention constitutes one of the building blocks of listening in natural environments, its neural bases remain obscure. To address this, we developed a novel auditory feature-selective attention task and measured noise correlations (rnoise) in rhesus macaque A1 during task performance. Unlike previous studies showing that the effect of attention on rnoise depends on population tuning to the attended feature, we show that the effect of attention depends on the tuning to the distractor feature as well. We suggest that these effects represent an efficient process by which sensory cortex simultaneously enhances relevant information and suppresses irrelevant information. PMID:28432139

Segmentation of retinal blood vessels using artificial neural networks for early detection of diabetic retinopathy

NASA Astrophysics Data System (ADS)

Mann, Kulwinder S.; Kaur, Sukhpreet

2017-06-01

There are various eye diseases in the patients suffering from the diabetes which includes Diabetic Retinopathy, Glaucoma, Hypertension etc. These all are the most common sight threatening eye diseases due to the changes in the blood vessel structure. The proposed method using supervised methods concluded that the segmentation of the retinal blood vessels can be performed accurately using neural networks training. It uses features which include Gray level features; Moment Invariant based features, Gabor filtering, Intensity feature, Vesselness feature for feature vector computation. Then the feature vector is calculated using only the prominent features.

Keypoint Density-Based Region Proposal for Fine-Grained Object Detection and Classification Using Regions with Convolutional Neural Network Features

DTIC Science & Technology

2015-12-15

Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network ... Convolutional Neural Networks (CNNs) enable them to outperform conventional techniques on standard object detection and classification tasks, their...detection accuracy and speed on the fine-grained Caltech UCSD bird dataset (Wah et al., 2011). Recently, Convolutional Neural Networks (CNNs), a deep

Diagnostic methodology for incipient system disturbance based on a neural wavelet approach

NASA Astrophysics Data System (ADS)

Won, In-Ho

Since incipient system disturbances are easily mixed up with other events or noise sources, the signal from the system disturbance can be neglected or identified as noise. Thus, as available knowledge and information is obtained incompletely or inexactly from the measurements; an exploration into the use of artificial intelligence (AI) tools to overcome these uncertainties and limitations was done. A methodology integrating the feature extraction efficiency of the wavelet transform with the classification capabilities of neural networks is developed for signal classification in the context of detecting incipient system disturbances. The synergistic effects of wavelets and neural networks present more strength and less weakness than either technique taken alone. A wavelet feature extractor is developed to form concise feature vectors for neural network inputs. The feature vectors are calculated from wavelet coefficients to reduce redundancy and computational expense. During this procedure, the statistical features based on the fractal concept to the wavelet coefficients play a role as crucial key in the wavelet feature extractor. To verify the proposed methodology, two applications are investigated and successfully tested. The first involves pump cavitation detection using dynamic pressure sensor. The second pertains to incipient pump cavitation detection using signals obtained from a current sensor. Also, through comparisons between three proposed feature vectors and with statistical techniques, it is shown that the variance feature extractor provides a better approach in the performed applications.

Collision detection in complex dynamic scenes using an LGMD-based visual neural network with feature enhancement.

PubMed

Yue, Shigang; Rind, F Claire

2006-05-01

The lobula giant movement detector (LGMD) is an identified neuron in the locust brain that responds most strongly to the images of an approaching object such as a predator. Its computational model can cope with unpredictable environments without using specific object recognition algorithms. In this paper, an LGMD-based neural network is proposed with a new feature enhancement mechanism to enhance the expanded edges of colliding objects via grouped excitation for collision detection with complex backgrounds. The isolated excitation caused by background detail will be filtered out by the new mechanism. Offline tests demonstrated the advantages of the presented LGMD-based neural network in complex backgrounds. Real time robotics experiments using the LGMD-based neural network as the only sensory system showed that the system worked reliably in a wide range of conditions; in particular, the robot was able to navigate in arenas with structured surrounds and complex backgrounds.

Automated method for the systematic interpretation of resonance peaks in spectrum data

DOEpatents

Damiano, B.; Wood, R.T.

1997-04-22

A method is described for spectral signature interpretation. The method includes the creation of a mathematical model of a system or process. A neural network training set is then developed based upon the mathematical model. The neural network training set is developed by using the mathematical model to generate measurable phenomena of the system or process based upon model input parameter that correspond to the physical condition of the system or process. The neural network training set is then used to adjust internal parameters of a neural network. The physical condition of an actual system or process represented by the mathematical model is then monitored by extracting spectral features from measured spectra of the actual process or system. The spectral features are then input into said neural network to determine the physical condition of the system or process represented by the mathematical model. More specifically, the neural network correlates the spectral features (i.e. measurable phenomena) of the actual process or system with the corresponding model input parameters. The model input parameters relate to specific components of the system or process, and, consequently, correspond to the physical condition of the process or system. 1 fig.

Automated method for the systematic interpretation of resonance peaks in spectrum data

DOEpatents

Damiano, Brian; Wood, Richard T.

1997-01-01

A method for spectral signature interpretation. The method includes the creation of a mathematical model of a system or process. A neural network training set is then developed based upon the mathematical model. The neural network training set is developed by using the mathematical model to generate measurable phenomena of the system or process based upon model input parameter that correspond to the physical condition of the system or process. The neural network training set is then used to adjust internal parameters of a neural network. The physical condition of an actual system or process represented by the mathematical model is then monitored by extracting spectral features from measured spectra of the actual process or system. The spectral features are then input into said neural network to determine the physical condition of the system or process represented by the mathematical. More specifically, the neural network correlates the spectral features (i.e. measurable phenomena) of the actual process or system with the corresponding model input parameters. The model input parameters relate to specific components of the system or process, and, consequently, correspond to the physical condition of the process or system.

Center for Neural Engineering: applications of pulse-coupled neural networks

NASA Astrophysics Data System (ADS)

Malkani, Mohan; Bodruzzaman, Mohammad; Johnson, John L.; Davis, Joel

1999-03-01

Pulsed-Coupled Neural Network (PCNN) is an oscillatory model neural network where grouping of cells and grouping among the groups that form the output time series (number of cells that fires in each input presentation also called `icon'). This is based on the synchronicity of oscillations. Recent work by Johnson and others demonstrated the functional capabilities of networks containing such elements for invariant feature extraction using intensity maps. PCNN thus presents itself as a more biologically plausible model with solid functional potential. This paper will present the summary of several projects and their results where we successfully applied PCNN. In project one, the PCNN was applied for object recognition and classification through a robotic vision system. The features (icons) generated by the PCNN were then fed into a feedforward neural network for classification. In project two, we developed techniques for sensory data fusion. The PCNN algorithm was implemented and tested on a B14 mobile robot. The PCNN-based features were extracted from the images taken from the robot vision system and used in conjunction with the map generated by data fusion of the sonar and wheel encoder data for the navigation of the mobile robot. In our third project, we applied the PCNN for speaker recognition. The spectrogram image of speech signals are fed into the PCNN to produce invariant feature icons which are then fed into a feedforward neural network for speaker identification.

Deep Convolutional Neural Networks for Classifying Body Constitution Based on Face Image.

PubMed

Huan, Er-Yang; Wen, Gui-Hua; Zhang, Shi-Jun; Li, Dan-Yang; Hu, Yang; Chang, Tian-Yuan; Wang, Qing; Huang, Bing-Lin

2017-01-01

Body constitution classification is the basis and core content of traditional Chinese medicine constitution research. It is to extract the relevant laws from the complex constitution phenomenon and finally build the constitution classification system. Traditional identification methods have the disadvantages of inefficiency and low accuracy, for instance, questionnaires. This paper proposed a body constitution recognition algorithm based on deep convolutional neural network, which can classify individual constitution types according to face images. The proposed model first uses the convolutional neural network to extract the features of face image and then combines the extracted features with the color features. Finally, the fusion features are input to the Softmax classifier to get the classification result. Different comparison experiments show that the algorithm proposed in this paper can achieve the accuracy of 65.29% about the constitution classification. And its performance was accepted by Chinese medicine practitioners.

Convolutional neural network for high-accuracy functional near-infrared spectroscopy in a brain-computer interface: three-class classification of rest, right-, and left-hand motor execution.

PubMed

Trakoolwilaiwan, Thanawin; Behboodi, Bahareh; Lee, Jaeseok; Kim, Kyungsoo; Choi, Ji-Woong

2018-01-01

The aim of this work is to develop an effective brain-computer interface (BCI) method based on functional near-infrared spectroscopy (fNIRS). In order to improve the performance of the BCI system in terms of accuracy, the ability to discriminate features from input signals and proper classification are desired. Previous studies have mainly extracted features from the signal manually, but proper features need to be selected carefully. To avoid performance degradation caused by manual feature selection, we applied convolutional neural networks (CNNs) as the automatic feature extractor and classifier for fNIRS-based BCI. In this study, the hemodynamic responses evoked by performing rest, right-, and left-hand motor execution tasks were measured on eight healthy subjects to compare performances. Our CNN-based method provided improvements in classification accuracy over conventional methods employing the most commonly used features of mean, peak, slope, variance, kurtosis, and skewness, classified by support vector machine (SVM) and artificial neural network (ANN). Specifically, up to 6.49% and 3.33% improvement in classification accuracy was achieved by CNN compared with SVM and ANN, respectively.

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.

Feature-based and object-based attention orientation during short-term memory maintenance.

PubMed

Ku, Yixuan

2015-12-01

Top-down attention biases the short-term memory (STM) processing at multiple stages. Orienting attention during the maintenance period of STM by a retrospective cue (retro-cue) strengthens the representation of the cued item and improves the subsequent STM performance. In a recent article, Backer et al. (Backer KC, Binns MA, Alain C. J Neurosci 35: 1307-1318, 2015) extended these findings from the visual to the auditory domain and combined electroencephalography to dissociate neural mechanisms underlying feature-based and object-based attention orientation. Both event-related potentials and neural oscillations explained the behavioral benefits of retro-cues and favored the theory that feature-based and object-based attention orientation were independent. Copyright © 2015 the American Physiological Society.

A neural joint model for entity and relation extraction from biomedical text.

PubMed

Li, Fei; Zhang, Meishan; Fu, Guohong; Ji, Donghong

2017-03-31

Extracting biomedical entities and their relations from text has important applications on biomedical research. Previous work primarily utilized feature-based pipeline models to process this task. Many efforts need to be made on feature engineering when feature-based models are employed. Moreover, pipeline models may suffer error propagation and are not able to utilize the interactions between subtasks. Therefore, we propose a neural joint model to extract biomedical entities as well as their relations simultaneously, and it can alleviate the problems above. Our model was evaluated on two tasks, i.e., the task of extracting adverse drug events between drug and disease entities, and the task of extracting resident relations between bacteria and location entities. Compared with the state-of-the-art systems in these tasks, our model improved the F1 scores of the first task by 5.1% in entity recognition and 8.0% in relation extraction, and that of the second task by 9.2% in relation extraction. The proposed model achieves competitive performances with less work on feature engineering. We demonstrate that the model based on neural networks is effective for biomedical entity and relation extraction. In addition, parameter sharing is an alternative method for neural models to jointly process this task. Our work can facilitate the research on biomedical text mining.

Low-dimensional recurrent neural network-based Kalman filter for speech enhancement.

PubMed

Xia, Youshen; Wang, Jun

2015-07-01

This paper proposes a new recurrent neural network-based Kalman filter for speech enhancement, based on a noise-constrained least squares estimate. The parameters of speech signal modeled as autoregressive process are first estimated by using the proposed recurrent neural network and the speech signal is then recovered from Kalman filtering. The proposed recurrent neural network is globally asymptomatically stable to the noise-constrained estimate. Because the noise-constrained estimate has a robust performance against non-Gaussian noise, the proposed recurrent neural network-based speech enhancement algorithm can minimize the estimation error of Kalman filter parameters in non-Gaussian noise. Furthermore, having a low-dimensional model feature, the proposed neural network-based speech enhancement algorithm has a much faster speed than two existing recurrent neural networks-based speech enhancement algorithms. Simulation results show that the proposed recurrent neural network-based speech enhancement algorithm can produce a good performance with fast computation and noise reduction. Copyright © 2015 Elsevier Ltd. All rights reserved.

Content-based retrieval using MPEG-7 visual descriptor and hippocampal neural network

NASA Astrophysics Data System (ADS)

Kim, Young Ho; Joung, Lyang-Jae; Kang, Dae-Seong

2005-12-01

As development of digital technology, many kinds of multimedia data are used variously and requirements for effective use by user are increasing. In order to transfer information fast and precisely what user wants, effective retrieval method is required. As existing multimedia data are impossible to apply the MPEG-1, MPEG-2 and MPEG-4 technologies which are aimed at compression, store and transmission. So MPEG-7 is introduced as a new technology for effective management and retrieval for multimedia data. In this paper, we extract content-based features using color descriptor among the MPEG-7 standardization visual descriptor, and reduce feature data applying PCA(Principal Components Analysis) technique. We remodel the cerebral cortex and hippocampal neural networks as a principle of a human's brain and it can label the features of the image-data which are inputted according to the order of hippocampal neuron structure to reaction-pattern according to the adjustment of a good impression in Dentate gyrus region and remove the noise through the auto-associate- memory step in the CA3 region. In the CA1 region receiving the information of the CA3, it can make long-term or short-term memory learned by neuron. Hippocampal neural network makes neuron of the neural network separate and combine dynamically, expand the neuron attaching additional information using the synapse and add new features according to the situation by user's demand. When user is querying, it compares feature value stored in long-term memory first and it learns feature vector fast and construct optimized feature. So the speed of index and retrieval is fast. Also, it uses MPEG-7 standard visual descriptors as content-based feature value, it improves retrieval efficiency.

Deep Constrained Siamese Hash Coding Network and Load-Balanced Locality-Sensitive Hashing for Near Duplicate Image Detection.

PubMed

Hu, Weiming; Fan, Yabo; Xing, Junliang; Sun, Liang; Cai, Zhaoquan; Maybank, Stephen

2018-09-01

We construct a new efficient near duplicate image detection method using a hierarchical hash code learning neural network and load-balanced locality-sensitive hashing (LSH) indexing. We propose a deep constrained siamese hash coding neural network combined with deep feature learning. Our neural network is able to extract effective features for near duplicate image detection. The extracted features are used to construct a LSH-based index. We propose a load-balanced LSH method to produce load-balanced buckets in the hashing process. The load-balanced LSH significantly reduces the query time. Based on the proposed load-balanced LSH, we design an effective and feasible algorithm for near duplicate image detection. Extensive experiments on three benchmark data sets demonstrate the effectiveness of our deep siamese hash encoding network and load-balanced LSH.

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.

Statistical process control using optimized neural networks: a case study.

PubMed

Addeh, Jalil; Ebrahimzadeh, Ata; Azarbad, Milad; Ranaee, Vahid

2014-09-01

The most common statistical process control (SPC) tools employed for monitoring process changes are control charts. A control chart demonstrates that the process has altered by generating an out-of-control signal. This study investigates the design of an accurate system for the control chart patterns (CCPs) recognition in two aspects. First, an efficient system is introduced that includes two main modules: feature extraction module and classifier module. In the feature extraction module, a proper set of shape features and statistical feature are proposed as the efficient characteristics of the patterns. In the classifier module, several neural networks, such as multilayer perceptron, probabilistic neural network and radial basis function are investigated. Based on an experimental study, the best classifier is chosen in order to recognize the CCPs. Second, a hybrid heuristic recognition system is introduced based on cuckoo optimization algorithm (COA) algorithm to improve the generalization performance of the classifier. The simulation results show that the proposed algorithm has high recognition accuracy. Copyright © 2013 ISA. Published by Elsevier Ltd. All rights reserved.

Feature reconstruction of LFP signals based on PLSR in the neural information decoding study.

PubMed

Yonghui Dong; Zhigang Shang; Mengmeng Li; Xinyu Liu; Hong Wan

2017-07-01

To solve the problems of Signal-to-Noise Ratio (SNR) and multicollinearity when the Local Field Potential (LFP) signals is used for the decoding of animal motion intention, a feature reconstruction of LFP signals based on partial least squares regression (PLSR) in the neural information decoding study is proposed in this paper. Firstly, the feature information of LFP coding band is extracted based on wavelet transform. Then the PLSR model is constructed by the extracted LFP coding features. According to the multicollinearity characteristics among the coding features, several latent variables which contribute greatly to the steering behavior are obtained, and the new LFP coding features are reconstructed. Finally, the K-Nearest Neighbor (KNN) method is used to classify the reconstructed coding features to verify the decoding performance. The results show that the proposed method can achieve the highest accuracy compared to the other three methods and the decoding effect of the proposed method is robust.

Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction

PubMed Central

Nguyen, Dat Tien; Kim, Ki Wan; Hong, Hyung Gil; Koo, Ja Hyung; Kim, Min Cheol; Park, Kang Ryoung

2017-01-01

Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT), speed-up robust feature (SURF), local binary patterns (LBP), histogram of oriented gradients (HOG), and weighted HOG. Recently, the convolutional neural network (CNN) method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images. PMID:28335510

Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction.

PubMed

Nguyen, Dat Tien; Kim, Ki Wan; Hong, Hyung Gil; Koo, Ja Hyung; Kim, Min Cheol; Park, Kang Ryoung

2017-03-20

Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT), speed-up robust feature (SURF), local binary patterns (LBP), histogram of oriented gradients (HOG), and weighted HOG. Recently, the convolutional neural network (CNN) method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images.

Classification of polycystic ovary based on ultrasound images using competitive neural network

NASA Astrophysics Data System (ADS)

Dewi, R. M.; Adiwijaya; Wisesty, U. N.; Jondri

2018-03-01

Infertility in the women reproduction system due to inhibition of follicles maturation process causing the number of follicles which is called polycystic ovaries (PCO). PCO detection is still operated manually by a gynecologist by counting the number and size of follicles in the ovaries, so it takes a long time and needs high accuracy. In general, PCO can be detected by calculating stereology or feature extraction and classification. In this paper, we designed a system to classify PCO by using the feature extraction (Gabor Wavelet method) and Competitive Neural Network (CNN). CNN was selected because this method is the combination between Hemming Net and The Max Net so that the data classification can be performed based on the specific characteristics of ultrasound data. Based on the result of system testing, Competitive Neural Network obtained the highest accuracy is 80.84% and the time process is 60.64 seconds (when using 32 feature vectors as well as weight and bias values respectively of 0.03 and 0.002).

Neural Determinants of Task Performance during Feature-Based Attention in Human Cortex

PubMed Central

Gong, Mengyuan

2018-01-01

Abstract Studies of feature-based attention have associated activity in a dorsal frontoparietal network with putative attentional priority signals. Yet, how this neural activity mediates attentional selection and whether it guides behavior are fundamental questions that require investigation. We reasoned that endogenous fluctuations in the quality of attentional priority should influence task performance. Human subjects detected a speed increment while viewing clockwise (CW) or counterclockwise (CCW) motion (baseline task) or while attending to either direction amid distracters (attention task). In an fMRI experiment, direction-specific neural pattern similarity between the baseline task and the attention task revealed a higher level of similarity for correct than incorrect trials in frontoparietal regions. Using transcranial magnetic stimulation (TMS), we disrupted posterior parietal cortex (PPC) and found a selective deficit in the attention task, but not in the baseline task, demonstrating the necessity of this cortical area during feature-based attention. These results reveal that frontoparietal areas maintain attentional priority that facilitates successful behavioral selection. PMID:29497703

Generating description with multi-feature fusion and saliency maps of image

NASA Astrophysics Data System (ADS)

Liu, Lisha; Ding, Yuxuan; Tian, Chunna; Yuan, Bo

2018-04-01

Generating description for an image can be regard as visual understanding. It is across artificial intelligence, machine learning, natural language processing and many other areas. In this paper, we present a model that generates description for images based on RNN (recurrent neural network) with object attention and multi-feature of images. The deep recurrent neural networks have excellent performance in machine translation, so we use it to generate natural sentence description for images. The proposed method uses single CNN (convolution neural network) that is trained on ImageNet to extract image features. But we think it can not adequately contain the content in images, it may only focus on the object area of image. So we add scene information to image feature using CNN which is trained on Places205. Experiments show that model with multi-feature extracted by two CNNs perform better than which with a single feature. In addition, we make saliency weights on images to emphasize the salient objects in images. We evaluate our model on MSCOCO based on public metrics, and the results show that our model performs better than several state-of-the-art methods.

Neural Networks for the Beginner.

ERIC Educational Resources Information Center

Snyder, Robin M.

Motivated by the brain, neural networks are a right-brained approach to artificial intelligence that is used to recognize patterns based on previous training. In practice, one would not program an expert system to recognize a pattern and one would not train a neural network to make decisions from rules; but one could combine the best features of…

Iris double recognition based on modified evolutionary neural network

NASA Astrophysics Data System (ADS)

Liu, Shuai; Liu, Yuan-Ning; Zhu, Xiao-Dong; Huo, Guang; Liu, Wen-Tao; Feng, Jia-Kai

2017-11-01

Aiming at multicategory iris recognition under illumination and noise interference, this paper proposes a method of iris double recognition based on a modified evolutionary neural network. An equalization histogram and Laplace of Gaussian operator are used to process the iris to suppress illumination and noise interference and Haar wavelet to convert the iris feature to binary feature encoding. Calculate the Hamming distance for the test iris and template iris , and compare with classification threshold, determine the type of iris. If the iris cannot be identified as a different type, there needs to be a secondary recognition. The connection weights in back-propagation (BP) neural network use modified evolutionary neural network to adaptively train. The modified neural network is composed of particle swarm optimization with mutation operator and BP neural network. According to different iris libraries in different circumstances of experimental results, under illumination and noise interference, the correct recognition rate of this algorithm is higher, the ROC curve is closer to the coordinate axis, the training and recognition time is shorter, and the stability and the robustness are better.

A novel method for extraction of neural response from single channel cochlear implant auditory evoked potentials.

PubMed

Sinkiewicz, Daniel; Friesen, Lendra; Ghoraani, Behnaz

2017-02-01

Cortical auditory evoked potentials (CAEP) are used to evaluate cochlear implant (CI) patient auditory pathways, but the CI device produces an electrical artifact, which obscures the relevant information in the neural response. Currently there are multiple methods, which attempt to recover the neural response from the contaminated CAEP, but there is no gold standard, which can quantitatively confirm the effectiveness of these methods. To address this crucial shortcoming, we develop a wavelet-based method to quantify the amount of artifact energy in the neural response. In addition, a novel technique for extracting the neural response from single channel CAEPs is proposed. The new method uses matching pursuit (MP) based feature extraction to represent the contaminated CAEP in a feature space, and support vector machines (SVM) to classify the components as normal hearing (NH) or artifact. The NH components are combined to recover the neural response without artifact energy, as verified using the evaluation tool. Although it needs some further evaluation, this approach is a promising method of electrical artifact removal from CAEPs. Copyright © 2016 IPEM. Published by Elsevier Ltd. All rights reserved.

Neural signal processing and closed-loop control algorithm design for an implanted neural recording and stimulation system.

PubMed

Hamilton, Lei; McConley, Marc; Angermueller, Kai; Goldberg, David; Corba, Massimiliano; Kim, Louis; Moran, James; Parks, Philip D; Sang Chin; Widge, Alik S; Dougherty, Darin D; Eskandar, Emad N

2015-08-01

A fully autonomous intracranial device is built to continually record neural activities in different parts of the brain, process these sampled signals, decode features that correlate to behaviors and neuropsychiatric states, and use these features to deliver brain stimulation in a closed-loop fashion. In this paper, we describe the sampling and stimulation aspects of such a device. We first describe the signal processing algorithms of two unsupervised spike sorting methods. Next, we describe the LFP time-frequency analysis and feature derivation from the two spike sorting methods. Spike sorting includes a novel approach to constructing a dictionary learning algorithm in a Compressed Sensing (CS) framework. We present a joint prediction scheme to determine the class of neural spikes in the dictionary learning framework; and, the second approach is a modified OSort algorithm which is implemented in a distributed system optimized for power efficiency. Furthermore, sorted spikes and time-frequency analysis of LFP signals can be used to generate derived features (including cross-frequency coupling, spike-field coupling). We then show how these derived features can be used in the design and development of novel decode and closed-loop control algorithms that are optimized to apply deep brain stimulation based on a patient's neuropsychiatric state. For the control algorithm, we define the state vector as representative of a patient's impulsivity, avoidance, inhibition, etc. Controller parameters are optimized to apply stimulation based on the state vector's current state as well as its historical values. The overall algorithm and software design for our implantable neural recording and stimulation system uses an innovative, adaptable, and reprogrammable architecture that enables advancement of the state-of-the-art in closed-loop neural control while also meeting the challenges of system power constraints and concurrent development with ongoing scientific research designed to define brain network connectivity and neural network dynamics that vary at the individual patient level and vary over time.

Effectiveness of feature and classifier algorithms in character recognition systems

NASA Astrophysics Data System (ADS)

Wilson, Charles L.

1993-04-01

At the first Census Optical Character Recognition Systems Conference, NIST generated accuracy data for more than character recognition systems. Most systems were tested on the recognition of isolated digits and upper and lower case alphabetic characters. The recognition experiments were performed on sample sizes of 58,000 digits, and 12,000 upper and lower case alphabetic characters. The algorithms used by the 26 conference participants included rule-based methods, image-based methods, statistical methods, and neural networks. The neural network methods included Multi-Layer Perceptron's, Learned Vector Quantitization, Neocognitrons, and cascaded neural networks. In this paper 11 different systems are compared using correlations between the answers of different systems, comparing the decrease in error rate as a function of confidence of recognition, and comparing the writer dependence of recognition. This comparison shows that methods that used different algorithms for feature extraction and recognition performed with very high levels of correlation. This is true for neural network systems, hybrid systems, and statistically based systems, and leads to the conclusion that neural networks have not yet demonstrated a clear superiority to more conventional statistical methods. Comparison of these results with the models of Vapnick (for estimation problems), MacKay (for Bayesian statistical models), Moody (for effective parameterization), and Boltzmann models (for information content) demonstrate that as the limits of training data variance are approached, all classifier systems have similar statistical properties. The limiting condition can only be approached for sufficiently rich feature sets because the accuracy limit is controlled by the available information content of the training set, which must pass through the feature extraction process prior to classification.

The Energy Coding of a Structural Neural Network Based on the Hodgkin-Huxley Model.

PubMed

Zhu, Zhenyu; Wang, Rubin; Zhu, Fengyun

2018-01-01

Based on the Hodgkin-Huxley model, the present study established a fully connected structural neural network to simulate the neural activity and energy consumption of the network by neural energy coding theory. The numerical simulation result showed that the periodicity of the network energy distribution was positively correlated to the number of neurons and coupling strength, but negatively correlated to signal transmitting delay. Moreover, a relationship was established between the energy distribution feature and the synchronous oscillation of the neural network, which showed that when the proportion of negative energy in power consumption curve was high, the synchronous oscillation of the neural network was apparent. In addition, comparison with the simulation result of structural neural network based on the Wang-Zhang biophysical model of neurons showed that both models were essentially consistent.

Chinese Sentence Classification Based on Convolutional Neural Network

NASA Astrophysics Data System (ADS)

Gu, Chengwei; Wu, Ming; Zhang, Chuang

2017-10-01

Sentence classification is one of the significant issues in Natural Language Processing (NLP). Feature extraction is often regarded as the key point for natural language processing. Traditional ways based on machine learning can not take high level features into consideration, such as Naive Bayesian Model. The neural network for sentence classification can make use of contextual information to achieve greater results in sentence classification tasks. In this paper, we focus on classifying Chinese sentences. And the most important is that we post a novel architecture of Convolutional Neural Network (CNN) to apply on Chinese sentence classification. In particular, most of the previous methods often use softmax classifier for prediction, we embed a linear support vector machine to substitute softmax in the deep neural network model, minimizing a margin-based loss to get a better result. And we use tanh as an activation function, instead of ReLU. The CNN model improve the result of Chinese sentence classification tasks. Experimental results on the Chinese news title database validate the effectiveness of our model.

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.

Event Recognition Based on Deep Learning in Chinese Texts

PubMed Central

Zhang, Yajun; Liu, Zongtian; Zhou, Wen

2016-01-01

Event recognition is the most fundamental and critical task in event-based natural language processing systems. Existing event recognition methods based on rules and shallow neural networks have certain limitations. For example, extracting features using methods based on rules is difficult; methods based on shallow neural networks converge too quickly to a local minimum, resulting in low recognition precision. To address these problems, we propose the Chinese emergency event recognition model based on deep learning (CEERM). Firstly, we use a word segmentation system to segment sentences. According to event elements labeled in the CEC 2.0 corpus, we classify words into five categories: trigger words, participants, objects, time and location. Each word is vectorized according to the following six feature layers: part of speech, dependency grammar, length, location, distance between trigger word and core word and trigger word frequency. We obtain deep semantic features of words by training a feature vector set using a deep belief network (DBN), then analyze those features in order to identify trigger words by means of a back propagation neural network. Extensive testing shows that the CEERM achieves excellent recognition performance, with a maximum F-measure value of 85.17%. Moreover, we propose the dynamic-supervised DBN, which adds supervised fine-tuning to a restricted Boltzmann machine layer by monitoring its training performance. Test analysis reveals that the new DBN improves recognition performance and effectively controls the training time. Although the F-measure increases to 88.11%, the training time increases by only 25.35%. PMID:27501231

Event Recognition Based on Deep Learning in Chinese Texts.

PubMed

Zhang, Yajun; Liu, Zongtian; Zhou, Wen

2016-01-01

Event recognition is the most fundamental and critical task in event-based natural language processing systems. Existing event recognition methods based on rules and shallow neural networks have certain limitations. For example, extracting features using methods based on rules is difficult; methods based on shallow neural networks converge too quickly to a local minimum, resulting in low recognition precision. To address these problems, we propose the Chinese emergency event recognition model based on deep learning (CEERM). Firstly, we use a word segmentation system to segment sentences. According to event elements labeled in the CEC 2.0 corpus, we classify words into five categories: trigger words, participants, objects, time and location. Each word is vectorized according to the following six feature layers: part of speech, dependency grammar, length, location, distance between trigger word and core word and trigger word frequency. We obtain deep semantic features of words by training a feature vector set using a deep belief network (DBN), then analyze those features in order to identify trigger words by means of a back propagation neural network. Extensive testing shows that the CEERM achieves excellent recognition performance, with a maximum F-measure value of 85.17%. Moreover, we propose the dynamic-supervised DBN, which adds supervised fine-tuning to a restricted Boltzmann machine layer by monitoring its training performance. Test analysis reveals that the new DBN improves recognition performance and effectively controls the training time. Although the F-measure increases to 88.11%, the training time increases by only 25.35%.

Genetic algorithm for the optimization of features and neural networks in ECG signals classification

NASA Astrophysics Data System (ADS)

Li, Hongqiang; Yuan, Danyang; Ma, Xiangdong; Cui, Dianyin; Cao, Lu

2017-01-01

Feature extraction and classification of electrocardiogram (ECG) signals are necessary for the automatic diagnosis of cardiac diseases. In this study, a novel method based on genetic algorithm-back propagation neural network (GA-BPNN) for classifying ECG signals with feature extraction using wavelet packet decomposition (WPD) is proposed. WPD combined with the statistical method is utilized to extract the effective features of ECG signals. The statistical features of the wavelet packet coefficients are calculated as the feature sets. GA is employed to decrease the dimensions of the feature sets and to optimize the weights and biases of the back propagation neural network (BPNN). Thereafter, the optimized BPNN classifier is applied to classify six types of ECG signals. In addition, an experimental platform is constructed for ECG signal acquisition to supply the ECG data for verifying the effectiveness of the proposed method. The GA-BPNN method with the MIT-BIH arrhythmia database achieved a dimension reduction of nearly 50% and produced good classification results with an accuracy of 97.78%. The experimental results based on the established acquisition platform indicated that the GA-BPNN method achieved a high classification accuracy of 99.33% and could be efficiently applied in the automatic identification of cardiac arrhythmias.

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.

Improving deep convolutional neural networks with mixed maxout units.

PubMed

Zhao, Hui-Zhen; Liu, Fu-Xian; Li, Long-Yue

2017-01-01

Motivated by insights from the maxout-units-based deep Convolutional Neural Network (CNN) that "non-maximal features are unable to deliver" and "feature mapping subspace pooling is insufficient," we present a novel mixed variant of the recently introduced maxout unit called a mixout unit. Specifically, we do so by calculating the exponential probabilities of feature mappings gained by applying different convolutional transformations over the same input and then calculating the expected values according to their exponential probabilities. Moreover, we introduce the Bernoulli distribution to balance the maximum values with the expected values of the feature mappings subspace. Finally, we design a simple model to verify the pooling ability of mixout units and a Mixout-units-based Network-in-Network (NiN) model to analyze the feature learning ability of the mixout models. We argue that our proposed units improve the pooling ability and that mixout models can achieve better feature learning and classification performance.

A new feature constituting approach to detection of vocal fold pathology

NASA Astrophysics Data System (ADS)

Hariharan, M.; Polat, Kemal; Yaacob, Sazali

2014-08-01

In the last two decades, non-invasive methods through acoustic analysis of voice signal have been proved to be excellent and reliable tool to diagnose vocal fold pathologies. This paper proposes a new feature vector based on the wavelet packet transform and singular value decomposition for the detection of vocal fold pathology. k-means clustering based feature weighting is proposed to increase the distinguishing performance of the proposed features. In this work, two databases Massachusetts Eye and Ear Infirmary (MEEI) voice disorders database and MAPACI speech pathology database are used. Four different supervised classifiers such as k-nearest neighbour (k-NN), least-square support vector machine, probabilistic neural network and general regression neural network are employed for testing the proposed features. The experimental results uncover that the proposed features give very promising classification accuracy of 100% for both MEEI database and MAPACI speech pathology database.

Human activity recognition based on feature selection in smart home using back-propagation algorithm.

PubMed

Fang, Hongqing; He, Lei; Si, Hao; Liu, Peng; Xie, Xiaolei

2014-09-01

In this paper, Back-propagation(BP) algorithm has been used to train the feed forward neural network for human activity recognition in smart home environments, and inter-class distance method for feature selection of observed motion sensor events is discussed and tested. And then, the human activity recognition performances of neural network using BP algorithm have been evaluated and compared with other probabilistic algorithms: Naïve Bayes(NB) classifier and Hidden Markov Model(HMM). The results show that different feature datasets yield different activity recognition accuracy. The selection of unsuitable feature datasets increases the computational complexity and degrades the activity recognition accuracy. Furthermore, neural network using BP algorithm has relatively better human activity recognition performances than NB classifier and HMM. Copyright © 2014 ISA. Published by Elsevier Ltd. All rights reserved.

A recurrent neural model for proto-object based contour integration and figure-ground segregation.

PubMed

Hu, Brian; Niebur, Ernst

2017-12-01

Visual processing of objects makes use of both feedforward and feedback streams of information. However, the nature of feedback signals is largely unknown, as is the identity of the neuronal populations in lower visual areas that receive them. Here, we develop a recurrent neural model to address these questions in the context of contour integration and figure-ground segregation. A key feature of our model is the use of grouping neurons whose activity represents tentative objects ("proto-objects") based on the integration of local feature information. Grouping neurons receive input from an organized set of local feature neurons, and project modulatory feedback to those same neurons. Additionally, inhibition at both the local feature level and the object representation level biases the interpretation of the visual scene in agreement with principles from Gestalt psychology. Our model explains several sets of neurophysiological results (Zhou et al. Journal of Neuroscience, 20(17), 6594-6611 2000; Qiu et al. Nature Neuroscience, 10(11), 1492-1499 2007; Chen et al. Neuron, 82(3), 682-694 2014), and makes testable predictions about the influence of neuronal feedback and attentional selection on neural responses across different visual areas. Our model also provides a framework for understanding how object-based attention is able to select both objects and the features associated with them.

Development and Validation of a Deep Neural Network Model for Prediction of Postoperative In-hospital Mortality.

PubMed

Lee, Christine K; Hofer, Ira; Gabel, Eilon; Baldi, Pierre; Cannesson, Maxime

2018-04-17

The authors tested the hypothesis that deep neural networks trained on intraoperative features can predict postoperative in-hospital mortality. The data used to train and validate the algorithm consists of 59,985 patients with 87 features extracted at the end of surgery. Feed-forward networks with a logistic output were trained using stochastic gradient descent with momentum. The deep neural networks were trained on 80% of the data, with 20% reserved for testing. The authors assessed improvement of the deep neural network by adding American Society of Anesthesiologists (ASA) Physical Status Classification and robustness of the deep neural network to a reduced feature set. The networks were then compared to ASA Physical Status, logistic regression, and other published clinical scores including the Surgical Apgar, Preoperative Score to Predict Postoperative Mortality, Risk Quantification Index, and the Risk Stratification Index. In-hospital mortality in the training and test sets were 0.81% and 0.73%. The deep neural network with a reduced feature set and ASA Physical Status classification had the highest area under the receiver operating characteristics curve, 0.91 (95% CI, 0.88 to 0.93). The highest logistic regression area under the curve was found with a reduced feature set and ASA Physical Status (0.90, 95% CI, 0.87 to 0.93). The Risk Stratification Index had the highest area under the receiver operating characteristics curve, at 0.97 (95% CI, 0.94 to 0.99). Deep neural networks can predict in-hospital mortality based on automatically extractable intraoperative data, but are not (yet) superior to existing methods.

A Multiobjective Sparse Feature Learning Model for Deep Neural Networks.

PubMed

Gong, Maoguo; Liu, Jia; Li, Hao; Cai, Qing; Su, Linzhi

2015-12-01

Hierarchical deep neural networks are currently popular learning models for imitating the hierarchical architecture of human brain. Single-layer feature extractors are the bricks to build deep networks. Sparse feature learning models are popular models that can learn useful representations. But most of those models need a user-defined constant to control the sparsity of representations. In this paper, we propose a multiobjective sparse feature learning model based on the autoencoder. The parameters of the model are learnt by optimizing two objectives, reconstruction error and the sparsity of hidden units simultaneously to find a reasonable compromise between them automatically. We design a multiobjective induced learning procedure for this model based on a multiobjective evolutionary algorithm. In the experiments, we demonstrate that the learning procedure is effective, and the proposed multiobjective model can learn useful sparse features.

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…

The Basis of Hyperspecificity in Autism: A Preliminary Suggestion Based on Properties of Neural Nets.

ERIC Educational Resources Information Center

McClelland, James L.

2000-01-01

This article discusses representation of information in neural networks and the apparent hyperspecificity that is often seen in the application of previously acquired information by children with autism. Hyperspecificity is seen as reflecting a possible feature of the neural codes used to represent concepts in the autistic brain. (Contains 12…

Off-lexicon online Arabic handwriting recognition using neural network

NASA Astrophysics Data System (ADS)

Yahia, Hamdi; Chaabouni, Aymen; Boubaker, Houcine; Alimi, Adel M.

2017-03-01

This paper highlights a new method for online Arabic handwriting recognition based on graphemes segmentation. The main contribution of our work is to explore the utility of Beta-elliptic model in segmentation and features extraction for online handwriting recognition. Indeed, our method consists in decomposing the input signal into continuous part called graphemes based on Beta-Elliptical model, and classify them according to their position in the pseudo-word. The segmented graphemes are then described by the combination of geometric features and trajectory shape modeling. The efficiency of the considered features has been evaluated using feed forward neural network classifier. Experimental results using the benchmarking ADAB Database show the performance of the proposed method.

A fast button surface defects detection method based on convolutional neural network

NASA Astrophysics Data System (ADS)

Liu, Lizhe; Cao, Danhua; Wu, Songlin; Wu, Yubin; Wei, Taoran

2018-01-01

Considering the complexity of the button surface texture and the variety of buttons and defects, we propose a fast visual method for button surface defect detection, based on convolutional neural network (CNN). CNN has the ability to extract the essential features by training, avoiding designing complex feature operators adapted to different kinds of buttons, textures and defects. Firstly, we obtain the normalized button region and then use HOG-SVM method to identify the front and back side of the button. Finally, a convolutional neural network is developed to recognize the defects. Aiming at detecting the subtle defects, we propose a network structure with multiple feature channels input. To deal with the defects of different scales, we take a strategy of multi-scale image block detection. The experimental results show that our method is valid for a variety of buttons and able to recognize all kinds of defects that have occurred, including dent, crack, stain, hole, wrong paint and uneven. The detection rate exceeds 96%, which is much better than traditional methods based on SVM and methods based on template match. Our method can reach the speed of 5 fps on DSP based smart camera with 600 MHz frequency.

Cellular neural network-based hybrid approach toward automatic image registration

NASA Astrophysics Data System (ADS)

Arun, Pattathal VijayaKumar; Katiyar, Sunil Kumar

2013-01-01

Image registration is a key component of various image processing operations that involve the analysis of different image data sets. Automatic image registration domains have witnessed the application of many intelligent methodologies over the past decade; however, inability to properly model object shape as well as contextual information has limited the attainable accuracy. A framework for accurate feature shape modeling and adaptive resampling using advanced techniques such as vector machines, cellular neural network (CNN), scale invariant feature transform (SIFT), coreset, and cellular automata is proposed. CNN has been found to be effective in improving feature matching as well as resampling stages of registration and complexity of the approach has been considerably reduced using coreset optimization. The salient features of this work are cellular neural network approach-based SIFT feature point optimization, adaptive resampling, and intelligent object modelling. Developed methodology has been compared with contemporary methods using different statistical measures. Investigations over various satellite images revealed that considerable success was achieved with the approach. This system has dynamically used spectral and spatial information for representing contextual knowledge using CNN-prolog approach. This methodology is also illustrated to be effective in providing intelligent interpretation and adaptive resampling.

Some new classification methods for hyperspectral remote sensing

NASA Astrophysics Data System (ADS)

Du, Pei-jun; Chen, Yun-hao; Jones, Simon; Ferwerda, Jelle G.; Chen, Zhi-jun; Zhang, Hua-peng; Tan, Kun; Yin, Zuo-xia

2006-10-01

Hyperspectral Remote Sensing (HRS) is one of the most significant recent achievements of Earth Observation Technology. Classification is the most commonly employed processing methodology. In this paper three new hyperspectral RS image classification methods are analyzed. These methods are: Object-oriented FIRS image classification, HRS image classification based on information fusion and HSRS image classification by Back Propagation Neural Network (BPNN). OMIS FIRS image is used as the example data. Object-oriented techniques have gained popularity for RS image classification in recent years. In such method, image segmentation is used to extract the regions from the pixel information based on homogeneity criteria at first, and spectral parameters like mean vector, texture, NDVI and spatial/shape parameters like aspect ratio, convexity, solidity, roundness and orientation for each region are calculated, finally classification of the image using the region feature vectors and also using suitable classifiers such as artificial neural network (ANN). It proves that object-oriented methods can improve classification accuracy since they utilize information and features both from the point and the neighborhood, and the processing unit is a polygon (in which all pixels are homogeneous and belong to the class). HRS image classification based on information fusion, divides all bands of the image into different groups initially, and extracts features from every group according to the properties of each group. Three levels of information fusion: data level fusion, feature level fusion and decision level fusion are used to HRS image classification. Artificial Neural Network (ANN) can perform well in RS image classification. In order to promote the advances of ANN used for HIRS image classification, Back Propagation Neural Network (BPNN), the most commonly used neural network, is used to HRS image classification.

Distorted Character Recognition Via An Associative Neural Network

NASA Astrophysics Data System (ADS)

Messner, Richard A.; Szu, Harold H.

1987-03-01

The purpose of this paper is two-fold. First, it is intended to provide some preliminary results of a character recognition scheme which has foundations in on-going neural network architecture modeling, and secondly, to apply some of the neural network results in a real application area where thirty years of effort has had little effect on providing the machine an ability to recognize distorted objects within the same object class. It is the author's belief that the time is ripe to start applying in ernest the results of over twenty years of effort in neural modeling to some of the more difficult problems which seem so hard to solve by conventional means. The character recognition scheme proposed utilizes a preprocessing stage which performs a 2-dimensional Walsh transform of an input cartesian image field, then sequency filters this spectrum into three feature bands. Various features are then extracted and organized into three sets of feature vectors. These vector patterns that are stored and recalled associatively. Two possible associative neural memory models are proposed for further investigation. The first being an outer-product linear matrix associative memory with a threshold function controlling the strength of the output pattern (similar to Kohonen's crosscorrelation approach [1]). The second approach is based upon a modified version of Grossberg's neural architecture [2] which provides better self-organizing properties due to its adaptive nature. Preliminary results of the sequency filtering and feature extraction preprocessing stage and discussion about the use of the proposed neural architectures is included.

A hybrid model based on neural networks for biomedical relation extraction.

PubMed

Zhang, Yijia; Lin, Hongfei; Yang, Zhihao; Wang, Jian; Zhang, Shaowu; Sun, Yuanyuan; Yang, Liang

2018-05-01

Biomedical relation extraction can automatically extract high-quality biomedical relations from biomedical texts, which is a vital step for the mining of biomedical knowledge hidden in the literature. Recurrent neural networks (RNNs) and convolutional neural networks (CNNs) are two major neural network models for biomedical relation extraction. Neural network-based methods for biomedical relation extraction typically focus on the sentence sequence and employ RNNs or CNNs to learn the latent features from sentence sequences separately. However, RNNs and CNNs have their own advantages for biomedical relation extraction. Combining RNNs and CNNs may improve biomedical relation extraction. In this paper, we present a hybrid model for the extraction of biomedical relations that combines RNNs and CNNs. First, the shortest dependency path (SDP) is generated based on the dependency graph of the candidate sentence. To make full use of the SDP, we divide the SDP into a dependency word sequence and a relation sequence. Then, RNNs and CNNs are employed to automatically learn the features from the sentence sequence and the dependency sequences, respectively. Finally, the output features of the RNNs and CNNs are combined to detect and extract biomedical relations. We evaluate our hybrid model using five public (protein-protein interaction) PPI corpora and a (drug-drug interaction) DDI corpus. The experimental results suggest that the advantages of RNNs and CNNs in biomedical relation extraction are complementary. Combining RNNs and CNNs can effectively boost biomedical relation extraction performance. Copyright © 2018 Elsevier Inc. All rights reserved.

A spiking neural network model of 3D perception for event-based neuromorphic stereo vision systems

PubMed Central

Osswald, Marc; Ieng, Sio-Hoi; Benosman, Ryad; Indiveri, Giacomo

2017-01-01

Stereo vision is an important feature that enables machine vision systems to perceive their environment in 3D. While machine vision has spawned a variety of software algorithms to solve the stereo-correspondence problem, their implementation and integration in small, fast, and efficient hardware vision systems remains a difficult challenge. Recent advances made in neuromorphic engineering offer a possible solution to this problem, with the use of a new class of event-based vision sensors and neural processing devices inspired by the organizing principles of the brain. Here we propose a radically novel model that solves the stereo-correspondence problem with a spiking neural network that can be directly implemented with massively parallel, compact, low-latency and low-power neuromorphic engineering devices. We validate the model with experimental results, highlighting features that are in agreement with both computational neuroscience stereo vision theories and experimental findings. We demonstrate its features with a prototype neuromorphic hardware system and provide testable predictions on the role of spike-based representations and temporal dynamics in biological stereo vision processing systems. PMID:28079187

A spiking neural network model of 3D perception for event-based neuromorphic stereo vision systems.

PubMed

Osswald, Marc; Ieng, Sio-Hoi; Benosman, Ryad; Indiveri, Giacomo

2017-01-12

Stereo vision is an important feature that enables machine vision systems to perceive their environment in 3D. While machine vision has spawned a variety of software algorithms to solve the stereo-correspondence problem, their implementation and integration in small, fast, and efficient hardware vision systems remains a difficult challenge. Recent advances made in neuromorphic engineering offer a possible solution to this problem, with the use of a new class of event-based vision sensors and neural processing devices inspired by the organizing principles of the brain. Here we propose a radically novel model that solves the stereo-correspondence problem with a spiking neural network that can be directly implemented with massively parallel, compact, low-latency and low-power neuromorphic engineering devices. We validate the model with experimental results, highlighting features that are in agreement with both computational neuroscience stereo vision theories and experimental findings. We demonstrate its features with a prototype neuromorphic hardware system and provide testable predictions on the role of spike-based representations and temporal dynamics in biological stereo vision processing systems.

A spiking neural network model of 3D perception for event-based neuromorphic stereo vision systems

NASA Astrophysics Data System (ADS)

Osswald, Marc; Ieng, Sio-Hoi; Benosman, Ryad; Indiveri, Giacomo

2017-01-01

Stereo vision is an important feature that enables machine vision systems to perceive their environment in 3D. While machine vision has spawned a variety of software algorithms to solve the stereo-correspondence problem, their implementation and integration in small, fast, and efficient hardware vision systems remains a difficult challenge. Recent advances made in neuromorphic engineering offer a possible solution to this problem, with the use of a new class of event-based vision sensors and neural processing devices inspired by the organizing principles of the brain. Here we propose a radically novel model that solves the stereo-correspondence problem with a spiking neural network that can be directly implemented with massively parallel, compact, low-latency and low-power neuromorphic engineering devices. We validate the model with experimental results, highlighting features that are in agreement with both computational neuroscience stereo vision theories and experimental findings. We demonstrate its features with a prototype neuromorphic hardware system and provide testable predictions on the role of spike-based representations and temporal dynamics in biological stereo vision processing systems.

Pattern learning with deep neural networks in EMG-based speech recognition.

PubMed

Wand, Michael; Schultz, Tanja

2014-01-01

We report on classification of phones and phonetic features from facial electromyographic (EMG) data, within the context of our EMG-based Silent Speech interface. In this paper we show that a Deep Neural Network can be used to perform this classification task, yielding a significant improvement over conventional Gaussian Mixture models. Our central contribution is the visualization of patterns which are learned by the neural network. With increasing network depth, these patterns represent more and more intricate electromyographic activity.

The challenges of neural mind-reading paradigms.

PubMed

Vilarroya, Oscar

2013-01-01

Neural mind-reading studies, based on multivariate pattern analysis (MVPA) methods, are providing exciting new studies. Some of the results obtained with these paradigms have raised high expectations, such as the possibility of creating brain reading devices. However, such hopes are based on the assumptions that: (a) the BOLD signal is a marker of neural activity; (b) the BOLD pattern identified by a MVPA is a neurally sound pattern; (c) the MVPA's feature space is a good mapping of the neural representation of a stimulus, and (d) the pattern identified by a MVPA corresponds to a representation. I examine here the challenges that still have to be met before fully accepting such assumptions.

On-line Tool Wear Detection on DCMT070204 Carbide Tool Tip Based on Noise Cutting Audio Signal using Artificial Neural Network

NASA Astrophysics Data System (ADS)

Prasetyo, T.; Amar, S.; Arendra, A.; Zam Zami, M. K.

2018-01-01

This study develops an on-line detection system to predict the wear of DCMT070204 tool tip during the cutting process of the workpiece. The machine used in this research is CNC ProTurn 9000 to cut ST42 steel cylinder. The audio signal has been captured using the microphone placed in the tool post and recorded in Matlab. The signal is recorded at the sampling rate of 44.1 kHz, and the sampling size of 1024. The recorded signal is 110 data derived from the audio signal while cutting using a normal chisel and a worn chisel. And then perform signal feature extraction in the frequency domain using Fast Fourier Transform. Feature selection is done based on correlation analysis. And tool wear classification was performed using artificial neural networks with 33 input features selected. This artificial neural network is trained with back propagation method. Classification performance testing yields an accuracy of 74%.

An Interval Type-2 Neural Fuzzy System for Online System Identification and Feature Elimination.

PubMed

Lin, Chin-Teng; Pal, Nikhil R; Wu, Shang-Lin; Liu, Yu-Ting; Lin, Yang-Yin

2015-07-01

We propose an integrated mechanism for discarding derogatory features and extraction of fuzzy rules based on an interval type-2 neural fuzzy system (NFS)-in fact, it is a more general scheme that can discard bad features, irrelevant antecedent clauses, and even irrelevant rules. High-dimensional input variable and a large number of rules not only enhance the computational complexity of NFSs but also reduce their interpretability. Therefore, a mechanism for simultaneous extraction of fuzzy rules and reducing the impact of (or eliminating) the inferior features is necessary. The proposed approach, namely an interval type-2 Neural Fuzzy System for online System Identification and Feature Elimination (IT2NFS-SIFE), uses type-2 fuzzy sets to model uncertainties associated with information and data in designing the knowledge base. The consequent part of the IT2NFS-SIFE is of Takagi-Sugeno-Kang type with interval weights. The IT2NFS-SIFE possesses a self-evolving property that can automatically generate fuzzy rules. The poor features can be discarded through the concept of a membership modulator. The antecedent and modulator weights are learned using a gradient descent algorithm. The consequent part weights are tuned via the rule-ordered Kalman filter algorithm to enhance learning effectiveness. Simulation results show that IT2NFS-SIFE not only simplifies the system architecture by eliminating derogatory/irrelevant antecedent clauses, rules, and features but also maintains excellent performance.

Implantable neurotechnologies: a review of integrated circuit neural amplifiers.

PubMed

Ng, Kian Ann; Greenwald, Elliot; Xu, Yong Ping; Thakor, Nitish V

2016-01-01

Neural signal recording is critical in modern day neuroscience research and emerging neural prosthesis programs. Neural recording requires the use of precise, low-noise amplifier systems to acquire and condition the weak neural signals that are transduced through electrode interfaces. Neural amplifiers and amplifier-based systems are available commercially or can be designed in-house and fabricated using integrated circuit (IC) technologies, resulting in very large-scale integration or application-specific integrated circuit solutions. IC-based neural amplifiers are now used to acquire untethered/portable neural recordings, as they meet the requirements of a miniaturized form factor, light weight and low power consumption. Furthermore, such miniaturized and low-power IC neural amplifiers are now being used in emerging implantable neural prosthesis technologies. This review focuses on neural amplifier-based devices and is presented in two interrelated parts. First, neural signal recording is reviewed, and practical challenges are highlighted. Current amplifier designs with increased functionality and performance and without penalties in chip size and power are featured. Second, applications of IC-based neural amplifiers in basic science experiments (e.g., cortical studies using animal models), neural prostheses (e.g., brain/nerve machine interfaces) and treatment of neuronal diseases (e.g., DBS for treatment of epilepsy) are highlighted. The review concludes with future outlooks of this technology and important challenges with regard to neural signal amplification.

Implantable neurotechnologies: a review of integrated circuit neural amplifiers

PubMed Central

Greenwald, Elliot; Xu, Yong Ping; Thakor, Nitish V.

2016-01-01

Neural signal recording is critical in modern day neuroscience research and emerging neural prosthesis programs. Neural recording requires the use of precise, low-noise amplifier systems to acquire and condition the weak neural signals that are transduced through electrode interfaces. Neural amplifiers and amplifier-based systems are available commercially or can be designed in-house and fabricated using integrated circuit (IC) technologies, resulting in very large-scale integration or application-specific integrated circuit solutions. IC-based neural amplifiers are now used to acquire untethered/portable neural recordings, as they meet the requirements of a miniaturized form factor, light weight and low power consumption. Furthermore, such miniaturized and low-power IC neural amplifiers are now being used in emerging implantable neural prosthesis technologies. This review focuses on neural amplifier-based devices and is presented in two interrelated parts. First, neural signal recording is reviewed, and practical challenges are highlighted. Current amplifier designs with increased functionality and performance and without penalties in chip size and power are featured. Second, applications of IC-based neural amplifiers in basic science experiments (e.g., cortical studies using animal models), neural prostheses (e.g., brain/nerve machine interfaces) and treatment of neuronal diseases (e.g., DBS for treatment of epilepsy) are highlighted. The review concludes with future outlooks of this technology and important challenges with regard to neural signal amplification. PMID:26798055

Spatial features of synaptic adaptation affecting learning performance.

PubMed

Berger, Damian L; de Arcangelis, Lucilla; Herrmann, Hans J

2017-09-08

Recent studies have proposed that the diffusion of messenger molecules, such as monoamines, can mediate the plastic adaptation of synapses in supervised learning of neural networks. Based on these findings we developed a model for neural learning, where the signal for plastic adaptation is assumed to propagate through the extracellular space. We investigate the conditions allowing learning of Boolean rules in a neural network. Even fully excitatory networks show very good learning performances. Moreover, the investigation of the plastic adaptation features optimizing the performance suggests that learning is very sensitive to the extent of the plastic adaptation and the spatial range of synaptic connections.

Analysis of the Growth Process of Neural Cells in Culture Environment Using Image Processing Techniques

NASA Astrophysics Data System (ADS)

Mirsafianf, Atefeh S.; Isfahani, Shirin N.; Kasaei, Shohreh; Mobasheri, Hamid

Here we present an approach for processing neural cells images to analyze their growth process in culture environment. We have applied several image processing techniques for: 1- Environmental noise reduction, 2- Neural cells segmentation, 3- Neural cells classification based on their dendrites' growth conditions, and 4- neurons' features Extraction and measurement (e.g., like cell body area, number of dendrites, axon's length, and so on). Due to the large amount of noise in the images, we have used feed forward artificial neural networks to detect edges more precisely.

Neural Architecture for Feature Binding in Visual Working Memory.

PubMed

Schneegans, Sebastian; Bays, Paul M

2017-04-05

Binding refers to the operation that groups different features together into objects. We propose a neural architecture for feature binding in visual working memory that employs populations of neurons with conjunction responses. We tested this model using cued recall tasks, in which subjects had to memorize object arrays composed of simple visual features (color, orientation, and location). After a brief delay, one feature of one item was given as a cue, and the observer had to report, on a continuous scale, one or two other features of the cued item. Binding failure in this task is associated with swap errors, in which observers report an item other than the one indicated by the cue. We observed that the probability of swapping two items strongly correlated with the items' similarity in the cue feature dimension, and found a strong correlation between swap errors occurring in spatial and nonspatial report. The neural model explains both swap errors and response variability as results of decoding noisy neural activity, and can account for the behavioral results in quantitative detail. We then used the model to compare alternative mechanisms for binding nonspatial features. We found the behavioral results fully consistent with a model in which nonspatial features are bound exclusively via their shared location, with no indication of direct binding between color and orientation. These results provide evidence for a special role of location in feature binding, and the model explains how this special role could be realized in the neural system. SIGNIFICANCE STATEMENT The problem of feature binding is of central importance in understanding the mechanisms of working memory. How do we remember not only that we saw a red and a round object, but that these features belong together to a single object rather than to different objects in our environment? Here we present evidence for a neural mechanism for feature binding in working memory, based on encoding of visual information by neurons that respond to the conjunction of features. We find clear evidence that nonspatial features are bound via space: we memorize directly where a color or an orientation appeared, but we memorize which color belonged with which orientation only indirectly by virtue of their shared location. Copyright © 2017 Schneegans and Bays.

The 3-D image recognition based on fuzzy neural network technology

NASA Technical Reports Server (NTRS)

Hirota, Kaoru; Yamauchi, Kenichi; Murakami, Jun; Tanaka, Kei

1993-01-01

Three dimensional stereoscopic image recognition system based on fuzzy-neural network technology was developed. The system consists of three parts; preprocessing part, feature extraction part, and matching part. Two CCD color camera image are fed to the preprocessing part, where several operations including RGB-HSV transformation are done. A multi-layer perception is used for the line detection in the feature extraction part. Then fuzzy matching technique is introduced in the matching part. The system is realized on SUN spark station and special image input hardware system. An experimental result on bottle images is also presented.

Improving Feature Representation Based on a Neural Network for Author Profiling in Social Media Texts

PubMed Central

2016-01-01

We introduce a lexical resource for preprocessing social media data. We show that a neural network-based feature representation is enhanced by using this resource. We conducted experiments on the PAN 2015 and PAN 2016 author profiling corpora and obtained better results when performing the data preprocessing using the developed lexical resource. The resource includes dictionaries of slang words, contractions, abbreviations, and emoticons commonly used in social media. Each of the dictionaries was built for the English, Spanish, Dutch, and Italian languages. The resource is freely available. PMID:27795703

Electroencephalogram-based decoding cognitive states using convolutional neural network and likelihood ratio based score fusion.

PubMed

Zafar, Raheel; Dass, Sarat C; Malik, Aamir Saeed

2017-01-01

Electroencephalogram (EEG)-based decoding human brain activity is challenging, owing to the low spatial resolution of EEG. However, EEG is an important technique, especially for brain-computer interface applications. In this study, a novel algorithm is proposed to decode brain activity associated with different types of images. In this hybrid algorithm, convolutional neural network is modified for the extraction of features, a t-test is used for the selection of significant features and likelihood ratio-based score fusion is used for the prediction of brain activity. The proposed algorithm takes input data from multichannel EEG time-series, which is also known as multivariate pattern analysis. Comprehensive analysis was conducted using data from 30 participants. The results from the proposed method are compared with current recognized feature extraction and classification/prediction techniques. The wavelet transform-support vector machine method is the most popular currently used feature extraction and prediction method. This method showed an accuracy of 65.7%. However, the proposed method predicts the novel data with improved accuracy of 79.9%. In conclusion, the proposed algorithm outperformed the current feature extraction and prediction method.

A model of proto-object based saliency

PubMed Central

Russell, Alexander F.; Mihalaş, Stefan; von der Heydt, Rudiger; Niebur, Ernst; Etienne-Cummings, Ralph

2013-01-01

Organisms use the process of selective attention to optimally allocate their computational resources to the instantaneously most relevant subsets of a visual scene, ensuring that they can parse the scene in real time. Many models of bottom-up attentional selection assume that elementary image features, like intensity, color and orientation, attract attention. Gestalt psychologists, how-ever, argue that humans perceive whole objects before they analyze individual features. This is supported by recent psychophysical studies that show that objects predict eye-fixations better than features. In this report we present a neurally inspired algorithm of object based, bottom-up attention. The model rivals the performance of state of the art non-biologically plausible feature based algorithms (and outperforms biologically plausible feature based algorithms) in its ability to predict perceptual saliency (eye fixations and subjective interest points) in natural scenes. The model achieves this by computing saliency as a function of proto-objects that establish the perceptual organization of the scene. All computational mechanisms of the algorithm have direct neural correlates, and our results provide evidence for the interface theory of attention. PMID:24184601

Feature Selection Methods for Zero-Shot Learning of Neural Activity.

PubMed

Caceres, Carlos A; Roos, Matthew J; Rupp, Kyle M; Milsap, Griffin; Crone, Nathan E; Wolmetz, Michael E; Ratto, Christopher R

2017-01-01

Dimensionality poses a serious challenge when making predictions from human neuroimaging data. Across imaging modalities, large pools of potential neural features (e.g., responses from particular voxels, electrodes, and temporal windows) have to be related to typically limited sets of stimuli and samples. In recent years, zero-shot prediction models have been introduced for mapping between neural signals and semantic attributes, which allows for classification of stimulus classes not explicitly included in the training set. While choices about feature selection can have a substantial impact when closed-set accuracy, open-set robustness, and runtime are competing design objectives, no systematic study of feature selection for these models has been reported. Instead, a relatively straightforward feature stability approach has been adopted and successfully applied across models and imaging modalities. To characterize the tradeoffs in feature selection for zero-shot learning, we compared correlation-based stability to several other feature selection techniques on comparable data sets from two distinct imaging modalities: functional Magnetic Resonance Imaging and Electrocorticography. While most of the feature selection methods resulted in similar zero-shot prediction accuracies and spatial/spectral patterns of selected features, there was one exception; A novel feature/attribute correlation approach was able to achieve those accuracies with far fewer features, suggesting the potential for simpler prediction models that yield high zero-shot classification accuracy.

A Deep Neural Network Model for Rainfall Estimation UsingPolarimetric WSR-88DP Radar Observations

NASA Astrophysics Data System (ADS)

Tan, H.; Chandra, C. V.; Chen, H.

2016-12-01

Rainfall estimation based on radar measurements has been an important topic for a few decades. Generally, radar rainfall estimation is conducted through parametric algorisms such as reflectivity-rainfall relation (i.e., Z-R relation). On the other hand, neural networks are developed for ground rainfall estimation based on radar measurements. This nonparametric method, which takes into account of both radar observations and rainfall measurements from ground rain gauges, has been demonstrated successfully for rainfall rate estimation. However, the neural network-based rainfall estimation is limited in practice due to the model complexity and structure, data quality, as well as different rainfall microphysics. Recently, the deep learning approach has been introduced in pattern recognition and machine learning areas. Compared to traditional neural networks, the deep learning based methodologies have larger number of hidden layers and more complex structure for data representation. Through a hierarchical learning process, the high level structured information and knowledge can be extracted automatically from low level features of the data. In this paper, we introduce a novel deep neural network model for rainfall estimation based on ground polarimetric radar measurements .The model is designed to capture the complex abstractions of radar measurements at different levels using multiple layers feature identification and extraction. The abstractions at different levels can be used independently or fused with other data resource such as satellite-based rainfall products and/or topographic data to represent the rain characteristics at certain location. In particular, the WSR-88DP radar and rain gauge data collected in Dallas - Fort Worth Metroplex and Florida are used extensively to train the model, and for demonstration purposes. Quantitative evaluation of the deep neural network based rainfall products will also be presented, which is based on an independent rain gauge network.

Influence of quality of images recorded in far infrared on pattern recognition based on neural networks and Eigenfaces algorithm

NASA Astrophysics Data System (ADS)

Jelen, Lukasz; Kobel, Joanna; Podbielska, Halina

2003-11-01

This paper discusses the possibility of exploiting of the tennovision registration and artificial neural networks for facial recognition systems. A biometric system that is able to identify people from thermograms is presented. To identify a person we used the Eigenfaces algorithm. For the face detection in the picture the backpropagation neural network was designed. For this purpose thermograms of 10 people in various external conditions were studies. The Eigenfaces algorithm calculated an average face and then the set of characteristic features for each studied person was produced. The neural network has to detect the face in the image before it actually can be identified. We used five hidden layers for that purpose. It was shown that the errors in recognition depend on the feature extraction, for low quality pictures the error was so high as 30%. However, for pictures with a good feature extraction the results of proper identification higher then 90%, were obtained.

An Adaptive Multi-Sensor Data Fusion Method Based on Deep Convolutional Neural Networks for Fault Diagnosis of Planetary Gearbox

PubMed Central

Jing, Luyang; Wang, Taiyong; Zhao, Ming; Wang, Peng

2017-01-01

A fault diagnosis approach based on multi-sensor data fusion is a promising tool to deal with complicated damage detection problems of mechanical systems. Nevertheless, this approach suffers from two challenges, which are (1) the feature extraction from various types of sensory data and (2) the selection of a suitable fusion level. It is usually difficult to choose an optimal feature or fusion level for a specific fault diagnosis task, and extensive domain expertise and human labor are also highly required during these selections. To address these two challenges, we propose an adaptive multi-sensor data fusion method based on deep convolutional neural networks (DCNN) for fault diagnosis. The proposed method can learn features from raw data and optimize a combination of different fusion levels adaptively to satisfy the requirements of any fault diagnosis task. The proposed method is tested through a planetary gearbox test rig. Handcraft features, manual-selected fusion levels, single sensory data, and two traditional intelligent models, back-propagation neural networks (BPNN) and a support vector machine (SVM), are used as comparisons in the experiment. The results demonstrate that the proposed method is able to detect the conditions of the planetary gearbox effectively with the best diagnosis accuracy among all comparative methods in the experiment. PMID:28230767

Improving deep convolutional neural networks with mixed maxout units

PubMed Central

Liu, Fu-xian; Li, Long-yue

2017-01-01

Motivated by insights from the maxout-units-based deep Convolutional Neural Network (CNN) that “non-maximal features are unable to deliver” and “feature mapping subspace pooling is insufficient,” we present a novel mixed variant of the recently introduced maxout unit called a mixout unit. Specifically, we do so by calculating the exponential probabilities of feature mappings gained by applying different convolutional transformations over the same input and then calculating the expected values according to their exponential probabilities. Moreover, we introduce the Bernoulli distribution to balance the maximum values with the expected values of the feature mappings subspace. Finally, we design a simple model to verify the pooling ability of mixout units and a Mixout-units-based Network-in-Network (NiN) model to analyze the feature learning ability of the mixout models. We argue that our proposed units improve the pooling ability and that mixout models can achieve better feature learning and classification performance. PMID:28727737

Digital mammographic tumor classification using transfer learning from deep convolutional neural networks.

PubMed

Huynh, Benjamin Q; Li, Hui; Giger, Maryellen L

2016-07-01

Convolutional neural networks (CNNs) show potential for computer-aided diagnosis (CADx) by learning features directly from the image data instead of using analytically extracted features. However, CNNs are difficult to train from scratch for medical images due to small sample sizes and variations in tumor presentations. Instead, transfer learning can be used to extract tumor information from medical images via CNNs originally pretrained for nonmedical tasks, alleviating the need for large datasets. Our database includes 219 breast lesions (607 full-field digital mammographic images). We compared support vector machine classifiers based on the CNN-extracted image features and our prior computer-extracted tumor features in the task of distinguishing between benign and malignant breast lesions. Five-fold cross validation (by lesion) was conducted with the area under the receiver operating characteristic (ROC) curve as the performance metric. Results show that classifiers based on CNN-extracted features (with transfer learning) perform comparably to those using analytically extracted features [area under the ROC curve [Formula: see text

Detection of braking intention in diverse situations during simulated driving based on EEG feature combination.

PubMed

Kim, Il-Hwa; Kim, Jeong-Woo; Haufe, Stefan; Lee, Seong-Whan

2015-02-01

We developed a simulated driving environment for studying neural correlates of emergency braking in diversified driving situations. We further investigated to what extent these neural correlates can be used to detect a participant's braking intention prior to the behavioral response. We measured electroencephalographic (EEG) and electromyographic signals during simulated driving. Fifteen participants drove a virtual vehicle and were exposed to several kinds of traffic situations in a simulator system, while EEG signals were measured. After that, we extracted characteristic features to categorize whether the driver intended to brake or not. Our system shows excellent detection performance in a broad range of possible emergency situations. In particular, we were able to distinguish three different kinds of emergency situations (sudden stop of a preceding vehicle, sudden cutting-in of a vehicle from the side and unexpected appearance of a pedestrian) from non-emergency (soft) braking situations, as well as from situations in which no braking was required, but the sensory stimulation was similar to stimulations inducing an emergency situation (e.g., the sudden stop of a vehicle on a neighboring lane). We proposed a novel feature combination comprising movement-related potentials such as the readiness potential, event-related desynchronization features besides the event-related potentials (ERP) features used in a previous study. The performance of predicting braking intention based on our proposed feature combination was superior compared to using only ERP features. Our study suggests that emergency situations are characterized by specific neural patterns of sensory perception and processing, as well as motor preparation and execution, which can be utilized by neurotechnology based braking assistance systems.

AFM feature definition for neural cells on nanofibrillar tissue scaffolds.

PubMed

Tiryaki, Volkan M; Khan, Adeel A; Ayres, Virginia M

2012-01-01

A diagnostic approach is developed and implemented that provides clear feature definition in atomic force microscopy (AFM) images of neural cells on nanofibrillar tissue scaffolds. Because the cellular edges and processes are on the same order as the background nanofibers, this imaging situation presents a feature definition problem. The diagnostic approach is based on analysis of discrete Fourier transforms of standard AFM section measurements. The diagnostic conclusion that the combination of dynamic range enhancement with low-frequency component suppression enhances feature definition is shown to be correct and to lead to clear-featured images that could change previously held assumptions about the cell-cell interactions present. Clear feature definition of cells on scaffolds extends the usefulness of AFM imaging for use in regenerative medicine. © Wiley Periodicals, Inc.

Automated Depression Analysis Using Convolutional Neural Networks from Speech.

PubMed

He, Lang; Cao, Cui

2018-05-28

To help clinicians to efficiently diagnose the severity of a person's depression, the affective computing community and the artificial intelligence field have shown a growing interest in designing automated systems. The speech features have useful information for the diagnosis of depression. However, manually designing and domain knowledge are still important for the selection of the feature, which makes the process labor consuming and subjective. In recent years, deep-learned features based on neural networks have shown superior performance to hand-crafted features in various areas. In this paper, to overcome the difficulties mentioned above, we propose a combination of hand-crafted and deep-learned features which can effectively measure the severity of depression from speech. In the proposed method, Deep Convolutional Neural Networks (DCNN) are firstly built to learn deep-learned features from spectrograms and raw speech waveforms. Then we manually extract the state-of-the-art texture descriptors named median robust extended local binary patterns (MRELBP) from spectrograms. To capture the complementary information within the hand-crafted features and deep-learned features, we propose joint fine-tuning layers to combine the raw and spectrogram DCNN to boost the depression recognition performance. Moreover, to address the problems with small samples, a data augmentation method was proposed. Experiments conducted on AVEC2013 and AVEC2014 depression databases show that our approach is robust and effective for the diagnosis of depression when compared to state-of-the-art audio-based methods. Copyright © 2018. Published by Elsevier Inc.

Learning representations for the early detection of sepsis with deep neural networks.

PubMed

Kam, Hye Jin; Kim, Ha Young

2017-10-01

Sepsis is one of the leading causes of death in intensive care unit patients. Early detection of sepsis is vital because mortality increases as the sepsis stage worsens. This study aimed to develop detection models for the early stage of sepsis using deep learning methodologies, and to compare the feasibility and performance of the new deep learning methodology with those of the regression method with conventional temporal feature extraction. Study group selection adhered to the InSight model. The results of the deep learning-based models and the InSight model were compared. With deep feedforward networks, the area under the ROC curve (AUC) of the models were 0.887 and 0.915 for the InSight and the new feature sets, respectively. For the model with the combined feature set, the AUC was the same as that of the basic feature set (0.915). For the long short-term memory model, only the basic feature set was applied and the AUC improved to 0.929 compared with the existing 0.887 of the InSight model. The contributions of this paper can be summarized in three ways: (i) improved performance without feature extraction using domain knowledge, (ii) verification of feature extraction capability of deep neural networks through comparison with reference features, and (iii) improved performance with feedforward neural networks using long short-term memory, a neural network architecture that can learn sequential patterns. Copyright © 2017 Elsevier Ltd. All rights reserved.

Image object recognition based on the Zernike moment and neural networks

NASA Astrophysics Data System (ADS)

Wan, Jianwei; Wang, Ling; Huang, Fukan; Zhou, Liangzhu

1998-03-01

This paper first give a comprehensive discussion about the concept of artificial neural network its research methods and the relations with information processing. On the basis of such a discussion, we expound the mathematical similarity of artificial neural network and information processing. Then, the paper presents a new method of image recognition based on invariant features and neural network by using image Zernike transform. The method not only has the invariant properties for rotation, shift and scale of image object, but also has good fault tolerance and robustness. Meanwhile, it is also compared with statistical classifier and invariant moments recognition method.

Deep Convolutional Neural Network-Based Early Automated Detection of Diabetic Retinopathy Using Fundus Image.

PubMed

Xu, Kele; Feng, Dawei; Mi, Haibo

2017-11-23

The automatic detection of diabetic retinopathy is of vital importance, as it is the main cause of irreversible vision loss in the working-age population in the developed world. The early detection of diabetic retinopathy occurrence can be very helpful for clinical treatment; although several different feature extraction approaches have been proposed, the classification task for retinal images is still tedious even for those trained clinicians. Recently, deep convolutional neural networks have manifested superior performance in image classification compared to previous handcrafted feature-based image classification methods. Thus, in this paper, we explored the use of deep convolutional neural network methodology for the automatic classification of diabetic retinopathy using color fundus image, and obtained an accuracy of 94.5% on our dataset, outperforming the results obtained by using classical approaches.

Real-time simulation of large-scale neural architectures for visual features computation based on GPU.

PubMed

Chessa, Manuela; Bianchi, Valentina; Zampetti, Massimo; Sabatini, Silvio P; Solari, Fabio

2012-01-01

The intrinsic parallelism of visual neural architectures based on distributed hierarchical layers is well suited to be implemented on the multi-core architectures of modern graphics cards. The design strategies that allow us to optimally take advantage of such parallelism, in order to efficiently map on GPU the hierarchy of layers and the canonical neural computations, are proposed. Specifically, the advantages of a cortical map-like representation of the data are exploited. Moreover, a GPU implementation of a novel neural architecture for the computation of binocular disparity from stereo image pairs, based on populations of binocular energy neurons, is presented. The implemented neural model achieves good performances in terms of reliability of the disparity estimates and a near real-time execution speed, thus demonstrating the effectiveness of the devised design strategies. The proposed approach is valid in general, since the neural building blocks we implemented are a common basis for the modeling of visual neural functionalities.

Automatic brain MR image denoising based on texture feature-based artificial neural networks.

PubMed

Chang, Yu-Ning; Chang, Herng-Hua

2015-01-01

Noise is one of the main sources of quality deterioration not only for visual inspection but also in computerized processing in brain magnetic resonance (MR) image analysis such as tissue classification, segmentation and registration. Accordingly, noise removal in brain MR images is important for a wide variety of subsequent processing applications. However, most existing denoising algorithms require laborious tuning of parameters that are often sensitive to specific image features and textures. Automation of these parameters through artificial intelligence techniques will be highly beneficial. In the present study, an artificial neural network associated with image texture feature analysis is proposed to establish a predictable parameter model and automate the denoising procedure. In the proposed approach, a total of 83 image attributes were extracted based on four categories: 1) Basic image statistics. 2) Gray-level co-occurrence matrix (GLCM). 3) Gray-level run-length matrix (GLRLM) and 4) Tamura texture features. To obtain the ranking of discrimination in these texture features, a paired-samples t-test was applied to each individual image feature computed in every image. Subsequently, the sequential forward selection (SFS) method was used to select the best texture features according to the ranking of discrimination. The selected optimal features were further incorporated into a back propagation neural network to establish a predictable parameter model. A wide variety of MR images with various scenarios were adopted to evaluate the performance of the proposed framework. Experimental results indicated that this new automation system accurately predicted the bilateral filtering parameters and effectively removed the noise in a number of MR images. Comparing to the manually tuned filtering process, our approach not only produced better denoised results but also saved significant processing time.

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition.

PubMed

Ordóñez, Francisco Javier; Roggen, Daniel

2016-01-18

Human activity recognition (HAR) tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which: (i) is suitable for multimodal wearable sensors; (ii) can perform sensor fusion naturally; (iii) does not require expert knowledge in designing features; and (iv) explicitly models the temporal dynamics of feature activations. We evaluate our framework on two datasets, one of which has been used in a public activity recognition challenge. Our results show that our framework outperforms competing deep non-recurrent networks on the challenge dataset by 4% on average; outperforming some of the previous reported results by up to 9%. Our results show that the framework can be applied to homogeneous sensor modalities, but can also fuse multimodal sensors to improve performance. We characterise key architectural hyperparameters' influence on performance to provide insights about their optimisation.

Deinterlacing using modular neural network

NASA Astrophysics Data System (ADS)

Woo, Dong H.; Eom, Il K.; Kim, Yoo S.

2004-05-01

Deinterlacing is the conversion process from the interlaced scan to progressive one. While many previous algorithms that are based on weighted-sum cause blurring in edge region, deinterlacing using neural network can reduce the blurring through recovering of high frequency component by learning process, and is found robust to noise. In proposed algorithm, input image is divided into edge and smooth region, and then, to each region, one neural network is assigned. Through this process, each neural network learns only patterns that are similar, therefore it makes learning more effective and estimation more accurate. But even within each region, there are various patterns such as long edge and texture in edge region. To solve this problem, modular neural network is proposed. In proposed modular neural network, two modules are combined in output node. One is for low frequency feature of local area of input image, and the other is for high frequency feature. With this structure, each modular neural network can learn different patterns with compensating for drawback of counterpart. Therefore it can adapt to various patterns within each region effectively. In simulation, the proposed algorithm shows better performance compared with conventional deinterlacing methods and single neural network method.

Morphological and wavelet features towards sonographic thyroid nodules evaluation.

PubMed

Tsantis, Stavros; Dimitropoulos, Nikos; Cavouras, Dionisis; Nikiforidis, George

2009-03-01

This paper presents a computer-based classification scheme that utilized various morphological and novel wavelet-based features towards malignancy risk evaluation of thyroid nodules in ultrasonography. The study comprised 85 ultrasound images-patients that were cytological confirmed (54 low-risk and 31 high-risk). A set of 20 features (12 based on nodules boundary shape and 8 based on wavelet local maxima located within each nodule) has been generated. Two powerful pattern recognition algorithms (support vector machines and probabilistic neural networks) have been designed and developed in order to quantify the power of differentiation of the introduced features. A comparative study has also been held, in order to estimate the impact speckle had onto the classification procedure. The diagnostic sensitivity and specificity of both classifiers was made by means of receiver operating characteristics (ROC) analysis. In the speckle-free feature set, the area under the ROC curve was 0.96 for the support vector machines classifier whereas for the probabilistic neural networks was 0.91. In the feature set with speckle, the corresponding areas under the ROC curves were 0.88 and 0.86 respectively for the two classifiers. The proposed features can increase the classification accuracy and decrease the rate of missing and misdiagnosis in thyroid cancer control.

Deep neural networks for texture classification-A theoretical analysis.

PubMed

Basu, Saikat; Mukhopadhyay, Supratik; Karki, Manohar; DiBiano, Robert; Ganguly, Sangram; Nemani, Ramakrishna; Gayaka, Shreekant

2018-01-01

We investigate the use of Deep Neural Networks for the classification of image datasets where texture features are important for generating class-conditional discriminative representations. To this end, we first derive the size of the feature space for some standard textural features extracted from the input dataset and then use the theory of Vapnik-Chervonenkis dimension to show that hand-crafted feature extraction creates low-dimensional representations which help in reducing the overall excess error rate. As a corollary to this analysis, we derive for the first time upper bounds on the VC dimension of Convolutional Neural Network as well as Dropout and Dropconnect networks and the relation between excess error rate of Dropout and Dropconnect networks. The concept of intrinsic dimension is used to validate the intuition that texture-based datasets are inherently higher dimensional as compared to handwritten digits or other object recognition datasets and hence more difficult to be shattered by neural networks. We then derive the mean distance from the centroid to the nearest and farthest sampling points in an n-dimensional manifold and show that the Relative Contrast of the sample data vanishes as dimensionality of the underlying vector space tends to infinity. Copyright © 2017 Elsevier Ltd. All rights reserved.

Neural networks: Application to medical imaging

NASA Technical Reports Server (NTRS)

Clarke, Laurence P.

1994-01-01

The research mission is the development of computer assisted diagnostic (CAD) methods for improved diagnosis of medical images including digital x-ray sensors and tomographic imaging modalities. The CAD algorithms include advanced methods for adaptive nonlinear filters for image noise suppression, hybrid wavelet methods for feature segmentation and enhancement, and high convergence neural networks for feature detection and VLSI implementation of neural networks for real time analysis. Other missions include (1) implementation of CAD methods on hospital based picture archiving computer systems (PACS) and information networks for central and remote diagnosis and (2) collaboration with defense and medical industry, NASA, and federal laboratories in the area of dual use technology conversion from defense or aerospace to medicine.

Neural Mechanisms of Conceptual Relations

ERIC Educational Resources Information Center

Lewis, Gwyneth A.

2017-01-01

An over-arching goal in neurolinguistic research is to characterize the neural bases of semantic representation. A particularly relevant goal concerns whether we represent features and events (a) together in a generalized semantic hub or (b) separately in distinct but complementary systems. While the left anterior temporal lobe (ATL) is strongly…

Predictive information processing in music cognition. A critical review.

PubMed

Rohrmeier, Martin A; Koelsch, Stefan

2012-02-01

Expectation and prediction constitute central mechanisms in the perception and cognition of music, which have been explored in theoretical and empirical accounts. We review the scope and limits of theoretical accounts of musical prediction with respect to feature-based and temporal prediction. While the concept of prediction is unproblematic for basic single-stream features such as melody, it is not straight-forward for polyphonic structures or higher-order features such as formal predictions. Behavioural results based on explicit and implicit (priming) paradigms provide evidence of priming in various domains that may reflect predictive behaviour. Computational learning models, including symbolic (fragment-based), probabilistic/graphical, or connectionist approaches, provide well-specified predictive models of specific features and feature combinations. While models match some experimental results, full-fledged music prediction cannot yet be modelled. Neuroscientific results regarding the early right-anterior negativity (ERAN) and mismatch negativity (MMN) reflect expectancy violations on different levels of processing complexity, and provide some neural evidence for different predictive mechanisms. At present, the combinations of neural and computational modelling methodologies are at early stages and require further research. Copyright © 2012 Elsevier B.V. All rights reserved.

3D High Resolution Mesh Deformation Based on Multi Library Wavelet Neural Network Architecture

NASA Astrophysics Data System (ADS)

Dhibi, Naziha; Elkefi, Akram; Bellil, Wajdi; Amar, Chokri Ben

2016-12-01

This paper deals with the features of a novel technique for large Laplacian boundary deformations using estimated rotations. The proposed method is based on a Multi Library Wavelet Neural Network structure founded on several mother wavelet families (MLWNN). The objective is to align features of mesh and minimize distortion with a fixed feature that minimizes the sum of the distances between all corresponding vertices. New mesh deformation method worked in the domain of Region of Interest (ROI). Our approach computes deformed ROI, updates and optimizes it to align features of mesh based on MLWNN and spherical parameterization configuration. This structure has the advantage of constructing the network by several mother wavelets to solve high dimensions problem using the best wavelet mother that models the signal better. The simulation test achieved the robustness and speed considerations when developing deformation methodologies. The Mean-Square Error and the ratio of deformation are low compared to other works from the state of the art. Our approach minimizes distortions with fixed features to have a well reconstructed object.

A link prediction method for heterogeneous networks based on BP neural network

NASA Astrophysics Data System (ADS)

Li, Ji-chao; Zhao, Dan-ling; Ge, Bing-Feng; Yang, Ke-Wei; Chen, Ying-Wu

2018-04-01

Most real-world systems, composed of different types of objects connected via many interconnections, can be abstracted as various complex heterogeneous networks. Link prediction for heterogeneous networks is of great significance for mining missing links and reconfiguring networks according to observed information, with considerable applications in, for example, friend and location recommendations and disease-gene candidate detection. In this paper, we put forward a novel integrated framework, called MPBP (Meta-Path feature-based BP neural network model), to predict multiple types of links for heterogeneous networks. More specifically, the concept of meta-path is introduced, followed by the extraction of meta-path features for heterogeneous networks. Next, based on the extracted meta-path features, a supervised link prediction model is built with a three-layer BP neural network. Then, the solution algorithm of the proposed link prediction model is put forward to obtain predicted results by iteratively training the network. Last, numerical experiments on the dataset of examples of a gene-disease network and a combat network are conducted to verify the effectiveness and feasibility of the proposed MPBP. It shows that the MPBP with very good performance is superior to the baseline methods.

Neural dynamics based on the recognition of neural fingerprints

PubMed Central

Carrillo-Medina, José Luis; Latorre, Roberto

2015-01-01

Experimental evidence has revealed the existence of characteristic spiking features in different neural signals, e.g., individual neural signatures identifying the emitter or functional signatures characterizing specific tasks. These neural fingerprints may play a critical role in neural information processing, since they allow receptors to discriminate or contextualize incoming stimuli. This could be a powerful strategy for neural systems that greatly enhances the encoding and processing capacity of these networks. Nevertheless, the study of information processing based on the identification of specific neural fingerprints has attracted little attention. In this work, we study (i) the emerging collective dynamics of a network of neurons that communicate with each other by exchange of neural fingerprints and (ii) the influence of the network topology on the self-organizing properties within the network. Complex collective dynamics emerge in the network in the presence of stimuli. Predefined inputs, i.e., specific neural fingerprints, are detected and encoded into coexisting patterns of activity that propagate throughout the network with different spatial organization. The patterns evoked by a stimulus can survive after the stimulation is over, which provides memory mechanisms to the network. The results presented in this paper suggest that neural information processing based on neural fingerprints can be a plausible, flexible, and powerful strategy. PMID:25852531

Feature Selection Methods for Zero-Shot Learning of Neural Activity

PubMed Central

Caceres, Carlos A.; Roos, Matthew J.; Rupp, Kyle M.; Milsap, Griffin; Crone, Nathan E.; Wolmetz, Michael E.; Ratto, Christopher R.

2017-01-01

Dimensionality poses a serious challenge when making predictions from human neuroimaging data. Across imaging modalities, large pools of potential neural features (e.g., responses from particular voxels, electrodes, and temporal windows) have to be related to typically limited sets of stimuli and samples. In recent years, zero-shot prediction models have been introduced for mapping between neural signals and semantic attributes, which allows for classification of stimulus classes not explicitly included in the training set. While choices about feature selection can have a substantial impact when closed-set accuracy, open-set robustness, and runtime are competing design objectives, no systematic study of feature selection for these models has been reported. Instead, a relatively straightforward feature stability approach has been adopted and successfully applied across models and imaging modalities. To characterize the tradeoffs in feature selection for zero-shot learning, we compared correlation-based stability to several other feature selection techniques on comparable data sets from two distinct imaging modalities: functional Magnetic Resonance Imaging and Electrocorticography. While most of the feature selection methods resulted in similar zero-shot prediction accuracies and spatial/spectral patterns of selected features, there was one exception; A novel feature/attribute correlation approach was able to achieve those accuracies with far fewer features, suggesting the potential for simpler prediction models that yield high zero-shot classification accuracy. PMID:28690513

Regional shape-based feature space for segmenting biomedical images using neural networks

NASA Astrophysics Data System (ADS)

Sundaramoorthy, Gopal; Hoford, John D.; Hoffman, Eric A.

1993-07-01

In biomedical images, structure of interest, particularly the soft tissue structures, such as the heart, airways, bronchial and arterial trees often have grey-scale and textural characteristics similar to other structures in the image, making it difficult to segment them using only gray- scale and texture information. However, these objects can be visually recognized by their unique shapes and sizes. In this paper we discuss, what we believe to be, a novel, simple scheme for extracting features based on regional shapes. To test the effectiveness of these features for image segmentation (classification), we use an artificial neural network and a statistical cluster analysis technique. The proposed shape-based feature extraction algorithm computes regional shape vectors (RSVs) for all pixels that meet a certain threshold criteria. The distance from each such pixel to a boundary is computed in 8 directions (or in 26 directions for a 3-D image). Together, these 8 (or 26) values represent the pixel's (or voxel's) RSV. All RSVs from an image are used to train a multi-layered perceptron neural network which uses these features to 'learn' a suitable classification strategy. To clearly distinguish the desired object from other objects within an image, several examples from inside and outside the desired object are used for training. Several examples are presented to illustrate the strengths and weaknesses of our algorithm. Both synthetic and actual biomedical images are considered. Future extensions to this algorithm are also discussed.

Robust Vehicle Detection in Aerial Images Based on Cascaded Convolutional Neural Networks.

PubMed

Zhong, Jiandan; Lei, Tao; Yao, Guangle

2017-11-24

Vehicle detection in aerial images is an important and challenging task. Traditionally, many target detection models based on sliding-window fashion were developed and achieved acceptable performance, but these models are time-consuming in the detection phase. Recently, with the great success of convolutional neural networks (CNNs) in computer vision, many state-of-the-art detectors have been designed based on deep CNNs. However, these CNN-based detectors are inefficient when applied in aerial image data due to the fact that the existing CNN-based models struggle with small-size object detection and precise localization. To improve the detection accuracy without decreasing speed, we propose a CNN-based detection model combining two independent convolutional neural networks, where the first network is applied to generate a set of vehicle-like regions from multi-feature maps of different hierarchies and scales. Because the multi-feature maps combine the advantage of the deep and shallow convolutional layer, the first network performs well on locating the small targets in aerial image data. Then, the generated candidate regions are fed into the second network for feature extraction and decision making. Comprehensive experiments are conducted on the Vehicle Detection in Aerial Imagery (VEDAI) dataset and Munich vehicle dataset. The proposed cascaded detection model yields high performance, not only in detection accuracy but also in detection speed.

Robust Vehicle Detection in Aerial Images Based on Cascaded Convolutional Neural Networks

PubMed Central

Zhong, Jiandan; Lei, Tao; Yao, Guangle

2017-01-01

Vehicle detection in aerial images is an important and challenging task. Traditionally, many target detection models based on sliding-window fashion were developed and achieved acceptable performance, but these models are time-consuming in the detection phase. Recently, with the great success of convolutional neural networks (CNNs) in computer vision, many state-of-the-art detectors have been designed based on deep CNNs. However, these CNN-based detectors are inefficient when applied in aerial image data due to the fact that the existing CNN-based models struggle with small-size object detection and precise localization. To improve the detection accuracy without decreasing speed, we propose a CNN-based detection model combining two independent convolutional neural networks, where the first network is applied to generate a set of vehicle-like regions from multi-feature maps of different hierarchies and scales. Because the multi-feature maps combine the advantage of the deep and shallow convolutional layer, the first network performs well on locating the small targets in aerial image data. Then, the generated candidate regions are fed into the second network for feature extraction and decision making. Comprehensive experiments are conducted on the Vehicle Detection in Aerial Imagery (VEDAI) dataset and Munich vehicle dataset. The proposed cascaded detection model yields high performance, not only in detection accuracy but also in detection speed. PMID:29186756

Convolutional neural network features based change detection in satellite images

NASA Astrophysics Data System (ADS)

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

2016-07-01

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

Tool Wear Prediction in Ti-6Al-4V Machining through Multiple Sensor Monitoring and PCA Features Pattern Recognition.

PubMed

Caggiano, Alessandra

2018-03-09

Machining of titanium alloys is characterised by extremely rapid tool wear due to the high cutting temperature and the strong adhesion at the tool-chip and tool-workpiece interface, caused by the low thermal conductivity and high chemical reactivity of Ti alloys. With the aim to monitor the tool conditions during dry turning of Ti-6Al-4V alloy, a machine learning procedure based on the acquisition and processing of cutting force, acoustic emission and vibration sensor signals during turning is implemented. A number of sensorial features are extracted from the acquired sensor signals in order to feed machine learning paradigms based on artificial neural networks. To reduce the large dimensionality of the sensorial features, an advanced feature extraction methodology based on Principal Component Analysis (PCA) is proposed. PCA allowed to identify a smaller number of features ( k = 2 features), the principal component scores, obtained through linear projection of the original d features into a new space with reduced dimensionality k = 2, sufficient to describe the variance of the data. By feeding artificial neural networks with the PCA features, an accurate diagnosis of tool flank wear ( VB max ) was achieved, with predicted values very close to the measured tool wear values.

Tool Wear Prediction in Ti-6Al-4V Machining through Multiple Sensor Monitoring and PCA Features Pattern Recognition

PubMed Central

2018-01-01

Machining of titanium alloys is characterised by extremely rapid tool wear due to the high cutting temperature and the strong adhesion at the tool-chip and tool-workpiece interface, caused by the low thermal conductivity and high chemical reactivity of Ti alloys. With the aim to monitor the tool conditions during dry turning of Ti-6Al-4V alloy, a machine learning procedure based on the acquisition and processing of cutting force, acoustic emission and vibration sensor signals during turning is implemented. A number of sensorial features are extracted from the acquired sensor signals in order to feed machine learning paradigms based on artificial neural networks. To reduce the large dimensionality of the sensorial features, an advanced feature extraction methodology based on Principal Component Analysis (PCA) is proposed. PCA allowed to identify a smaller number of features (k = 2 features), the principal component scores, obtained through linear projection of the original d features into a new space with reduced dimensionality k = 2, sufficient to describe the variance of the data. By feeding artificial neural networks with the PCA features, an accurate diagnosis of tool flank wear (VBmax) was achieved, with predicted values very close to the measured tool wear values. PMID:29522443

Visual Saliency Detection Based on Multiscale Deep CNN Features.

PubMed

Guanbin Li; Yizhou Yu

2016-11-01

Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using deep convolutional neural networks (CNNs), which have had many successes in visual recognition tasks. For learning such saliency models, we introduce a neural network architecture, which has fully connected layers on top of CNNs responsible for feature extraction at three different scales. The penultimate layer of our neural network has been confirmed to be a discriminative high-level feature vector for saliency detection, which we call deep contrast feature. To generate a more robust feature, we integrate handcrafted low-level features with our deep contrast feature. To promote further research and evaluation of visual saliency models, we also construct a new large database of 4447 challenging images and their pixelwise saliency annotations. Experimental results demonstrate that our proposed method is capable of achieving the state-of-the-art performance on all public benchmarks, improving the F-measure by 6.12% and 10%, respectively, on the DUT-OMRON data set and our new data set (HKU-IS), and lowering the mean absolute error by 9% and 35.3%, respectively, on these two data sets.

Detection of braking intention in diverse situations during simulated driving based on EEG feature combination

NASA Astrophysics Data System (ADS)

Kim, Il-Hwa; Kim, Jeong-Woo; Haufe, Stefan; Lee, Seong-Whan

2015-02-01

Objective. We developed a simulated driving environment for studying neural correlates of emergency braking in diversified driving situations. We further investigated to what extent these neural correlates can be used to detect a participant's braking intention prior to the behavioral response. Approach. We measured electroencephalographic (EEG) and electromyographic signals during simulated driving. Fifteen participants drove a virtual vehicle and were exposed to several kinds of traffic situations in a simulator system, while EEG signals were measured. After that, we extracted characteristic features to categorize whether the driver intended to brake or not. Main results. Our system shows excellent detection performance in a broad range of possible emergency situations. In particular, we were able to distinguish three different kinds of emergency situations (sudden stop of a preceding vehicle, sudden cutting-in of a vehicle from the side and unexpected appearance of a pedestrian) from non-emergency (soft) braking situations, as well as from situations in which no braking was required, but the sensory stimulation was similar to stimulations inducing an emergency situation (e.g., the sudden stop of a vehicle on a neighboring lane). Significance. We proposed a novel feature combination comprising movement-related potentials such as the readiness potential, event-related desynchronization features besides the event-related potentials (ERP) features used in a previous study. The performance of predicting braking intention based on our proposed feature combination was superior compared to using only ERP features. Our study suggests that emergency situations are characterized by specific neural patterns of sensory perception and processing, as well as motor preparation and execution, which can be utilized by neurotechnology based braking assistance systems.

An Ensemble Deep Convolutional Neural Network Model with Improved D-S Evidence Fusion for Bearing Fault Diagnosis.

PubMed

Li, Shaobo; Liu, Guokai; Tang, Xianghong; Lu, Jianguang; Hu, Jianjun

2017-07-28

Intelligent machine health monitoring and fault diagnosis are becoming increasingly important for modern manufacturing industries. Current fault diagnosis approaches mostly depend on expert-designed features for building prediction models. In this paper, we proposed IDSCNN, a novel bearing fault diagnosis algorithm based on ensemble deep convolutional neural networks and an improved Dempster-Shafer theory based evidence fusion. The convolutional neural networks take the root mean square (RMS) maps from the FFT (Fast Fourier Transformation) features of the vibration signals from two sensors as inputs. The improved D-S evidence theory is implemented via distance matrix from evidences and modified Gini Index. Extensive evaluations of the IDSCNN on the Case Western Reserve Dataset showed that our IDSCNN algorithm can achieve better fault diagnosis performance than existing machine learning methods by fusing complementary or conflicting evidences from different models and sensors and adapting to different load conditions.

An Ensemble Deep Convolutional Neural Network Model with Improved D-S Evidence Fusion for Bearing Fault Diagnosis

PubMed Central

Li, Shaobo; Liu, Guokai; Tang, Xianghong; Lu, Jianguang

2017-01-01

Intelligent machine health monitoring and fault diagnosis are becoming increasingly important for modern manufacturing industries. Current fault diagnosis approaches mostly depend on expert-designed features for building prediction models. In this paper, we proposed IDSCNN, a novel bearing fault diagnosis algorithm based on ensemble deep convolutional neural networks and an improved Dempster–Shafer theory based evidence fusion. The convolutional neural networks take the root mean square (RMS) maps from the FFT (Fast Fourier Transformation) features of the vibration signals from two sensors as inputs. The improved D-S evidence theory is implemented via distance matrix from evidences and modified Gini Index. Extensive evaluations of the IDSCNN on the Case Western Reserve Dataset showed that our IDSCNN algorithm can achieve better fault diagnosis performance than existing machine learning methods by fusing complementary or conflicting evidences from different models and sensors and adapting to different load conditions. PMID:28788099

Intelligent multi-spectral IR image segmentation

NASA Astrophysics Data System (ADS)

Lu, Thomas; Luong, Andrew; Heim, Stephen; Patel, Maharshi; Chen, Kang; Chao, Tien-Hsin; Chow, Edward; Torres, Gilbert

2017-05-01

This article presents a neural network based multi-spectral image segmentation method. A neural network is trained on the selected features of both the objects and background in the longwave (LW) Infrared (IR) images. Multiple iterations of training are performed until the accuracy of the segmentation reaches satisfactory level. The segmentation boundary of the LW image is used to segment the midwave (MW) and shortwave (SW) IR images. A second neural network detects the local discontinuities and refines the accuracy of the local boundaries. This article compares the neural network based segmentation method to the Wavelet-threshold and Grab-Cut methods. Test results have shown increased accuracy and robustness of this segmentation scheme for multi-spectral IR images.

An Application to the Prediction of LOD Change Based on General Regression Neural Network

NASA Astrophysics Data System (ADS)

Zhang, X. H.; Wang, Q. J.; Zhu, J. J.; Zhang, H.

2011-07-01

Traditional prediction of the LOD (length of day) change was based on linear models, such as the least square model and the autoregressive technique, etc. Due to the complex non-linear features of the LOD variation, the performances of the linear model predictors are not fully satisfactory. This paper applies a non-linear neural network - general regression neural network (GRNN) model to forecast the LOD change, and the results are analyzed and compared with those obtained with the back propagation neural network and other models. The comparison shows that the performance of the GRNN model in the prediction of the LOD change is efficient and feasible.

Electroencephalogram-based decoding cognitive states using convolutional neural network and likelihood ratio based score fusion

PubMed Central

2017-01-01

Electroencephalogram (EEG)-based decoding human brain activity is challenging, owing to the low spatial resolution of EEG. However, EEG is an important technique, especially for brain–computer interface applications. In this study, a novel algorithm is proposed to decode brain activity associated with different types of images. In this hybrid algorithm, convolutional neural network is modified for the extraction of features, a t-test is used for the selection of significant features and likelihood ratio-based score fusion is used for the prediction of brain activity. The proposed algorithm takes input data from multichannel EEG time-series, which is also known as multivariate pattern analysis. Comprehensive analysis was conducted using data from 30 participants. The results from the proposed method are compared with current recognized feature extraction and classification/prediction techniques. The wavelet transform-support vector machine method is the most popular currently used feature extraction and prediction method. This method showed an accuracy of 65.7%. However, the proposed method predicts the novel data with improved accuracy of 79.9%. In conclusion, the proposed algorithm outperformed the current feature extraction and prediction method. PMID:28558002

Multispectral embedding-based deep neural network for three-dimensional human pose recovery

NASA Astrophysics Data System (ADS)

Yu, Jialin; Sun, Jifeng

2018-01-01

Monocular image-based three-dimensional (3-D) human pose recovery aims to retrieve 3-D poses using the corresponding two-dimensional image features. Therefore, the pose recovery performance highly depends on the image representations. We propose a multispectral embedding-based deep neural network (MSEDNN) to automatically obtain the most discriminative features from multiple deep convolutional neural networks and then embed their penultimate fully connected layers into a low-dimensional manifold. This compact manifold can explore not only the optimum output from multiple deep networks but also the complementary properties of them. Furthermore, the distribution of each hierarchy discriminative manifold is sufficiently smooth so that the training process of our MSEDNN can be effectively implemented only using few labeled data. Our proposed network contains a body joint detector and a human pose regressor that are jointly trained. Extensive experiments conducted on four databases show that our proposed MSEDNN can achieve the best recovery performance compared with the state-of-the-art methods.

Pattern Recognition of Momentary Mental Workload Based on Multi-Channel Electrophysiological Data and Ensemble Convolutional Neural Networks.

PubMed

Zhang, Jianhua; Li, Sunan; Wang, Rubin

2017-01-01

In this paper, we deal with the Mental Workload (MWL) classification problem based on the measured physiological data. First we discussed the optimal depth (i.e., the number of hidden layers) and parameter optimization algorithms for the Convolutional Neural Networks (CNN). The base CNNs designed were tested according to five classification performance indices, namely Accuracy, Precision, F-measure, G-mean, and required training time. Then we developed an Ensemble Convolutional Neural Network (ECNN) to enhance the accuracy and robustness of the individual CNN model. For the ECNN design, three model aggregation approaches (weighted averaging, majority voting and stacking) were examined and a resampling strategy was used to enhance the diversity of individual CNN models. The results of MWL classification performance comparison indicated that the proposed ECNN framework can effectively improve MWL classification performance and is featured by entirely automatic feature extraction and MWL classification, when compared with traditional machine learning methods.

Fabric defect detection based on visual saliency using deep feature and low-rank recovery

NASA Astrophysics Data System (ADS)

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

2018-04-01

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

Extraction of texture features with a multiresolution neural network

NASA Astrophysics Data System (ADS)

Lepage, Richard; Laurendeau, Denis; Gagnon, Roger A.

1992-09-01

Texture is an important surface characteristic. Many industrial materials such as wood, textile, or paper are best characterized by their texture. Detection of defaults occurring on such materials or classification for quality control anD matching can be carried out through careful texture analysis. A system for the classification of pieces of wood used in the furniture industry is proposed. This paper is concerned with a neural network implementation of the features extraction and classification components of the proposed system. Texture appears differently depending at which spatial scale it is observed. A complete description of a texture thus implies an analysis at several spatial scales. We propose a compact pyramidal representation of the input image for multiresolution analysis. The feature extraction system is implemented on a multilayer artificial neural network. Each level of the pyramid, which is a representation of the input image at a given spatial resolution scale, is mapped into a layer of the neural network. A full resolution texture image is input at the base of the pyramid and a representation of the texture image at multiple resolutions is generated by the feedforward pyramid structure of the neural network. The receptive field of each neuron at a given pyramid level is preprogrammed as a discrete Gaussian low-pass filter. Meaningful characteristics of the textured image must be extracted if a good resolving power of the classifier must be achieved. Local dominant orientation is the principal feature which is extracted from the textured image. Local edge orientation is computed with a Sobel mask at four orientation angles (multiple of (pi) /4). The resulting intrinsic image, that is, the local dominant orientation image, is fed to the texture classification neural network. The classification network is a three-layer feedforward back-propagation neural network.

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.

Optical computing and neural networks; Proceedings of the Meeting, National Chiao Tung Univ., Hsinchu, Taiwan, Dec. 16, 17, 1992

NASA Technical Reports Server (NTRS)

Hsu, Ken-Yuh (Editor); Liu, Hua-Kuang (Editor)

1992-01-01

The present conference discusses optical neural networks, photorefractive nonlinear optics, optical pattern recognition, digital and analog processors, and holography and its applications. Attention is given to bifurcating optical information processing, neural structures in digital halftoning, an exemplar-based optical neural net classifier for color pattern recognition, volume storage in photorefractive disks, and microlaser-based compact optical neuroprocessors. Also treated are the optical implementation of a feature-enhanced optical interpattern-associative neural network model and its optical implementation, an optical pattern binary dual-rail logic gate module, a theoretical analysis for holographic associative memories, joint transform correlators, image addition and subtraction via the Talbot effect, and optical wavelet-matched filters. (No individual items are abstracted in this volume)

Optical computing and neural networks; Proceedings of the Meeting, National Chiao Tung Univ., Hsinchu, Taiwan, Dec. 16, 17, 1992

NASA Astrophysics Data System (ADS)

Hsu, Ken-Yuh; Liu, Hua-Kuang

The present conference discusses optical neural networks, photorefractive nonlinear optics, optical pattern recognition, digital and analog processors, and holography and its applications. Attention is given to bifurcating optical information processing, neural structures in digital halftoning, an exemplar-based optical neural net classifier for color pattern recognition, volume storage in photorefractive disks, and microlaser-based compact optical neuroprocessors. Also treated are the optical implementation of a feature-enhanced optical interpattern-associative neural network model and its optical implementation, an optical pattern binary dual-rail logic gate module, a theoretical analysis for holographic associative memories, joint transform correlators, image addition and subtraction via the Talbot effect, and optical wavelet-matched filters. (No individual items are abstracted in this volume)

Optimization of a Multi-Stage ATR System for Small Target Identification

NASA Technical Reports Server (NTRS)

Lin, Tsung-Han; Lu, Thomas; Braun, Henry; Edens, Western; Zhang, Yuhan; Chao, Tien- Hsin; Assad, Christopher; Huntsberger, Terrance

2010-01-01

An Automated Target Recognition system (ATR) was developed to locate and target small object in images and videos. The data is preprocessed and sent to a grayscale optical correlator (GOC) filter to identify possible regionsof- interest (ROIs). Next, features are extracted from ROIs based on Principal Component Analysis (PCA) and sent to neural network (NN) to be classified. The features are analyzed by the NN classifier indicating if each ROI contains the desired target or not. The ATR system was found useful in identifying small boats in open sea. However, due to "noisy background," such as weather conditions, background buildings, or water wakes, some false targets are mis-classified. Feedforward backpropagation and Radial Basis neural networks are optimized for generalization of representative features to reduce false-alarm rate. The neural networks are compared for their performance in classification accuracy, classifying time, and training time.

A novel end-to-end classifier using domain transferred deep convolutional neural networks for biomedical images.

PubMed

Pang, Shuchao; Yu, Zhezhou; Orgun, Mehmet A

2017-03-01

Highly accurate classification of biomedical images is an essential task in the clinical diagnosis of numerous medical diseases identified from those images. Traditional image classification methods combined with hand-crafted image feature descriptors and various classifiers are not able to effectively improve the accuracy rate and meet the high requirements of classification of biomedical images. The same also holds true for artificial neural network models directly trained with limited biomedical images used as training data or directly used as a black box to extract the deep features based on another distant dataset. In this study, we propose a highly reliable and accurate end-to-end classifier for all kinds of biomedical images via deep learning and transfer learning. We first apply domain transferred deep convolutional neural network for building a deep model; and then develop an overall deep learning architecture based on the raw pixels of original biomedical images using supervised training. In our model, we do not need the manual design of the feature space, seek an effective feature vector classifier or segment specific detection object and image patches, which are the main technological difficulties in the adoption of traditional image classification methods. Moreover, we do not need to be concerned with whether there are large training sets of annotated biomedical images, affordable parallel computing resources featuring GPUs or long times to wait for training a perfect deep model, which are the main problems to train deep neural networks for biomedical image classification as observed in recent works. With the utilization of a simple data augmentation method and fast convergence speed, our algorithm can achieve the best accuracy rate and outstanding classification ability for biomedical images. We have evaluated our classifier on several well-known public biomedical datasets and compared it with several state-of-the-art approaches. We propose a robust automated end-to-end classifier for biomedical images based on a domain transferred deep convolutional neural network model that shows a highly reliable and accurate performance which has been confirmed on several public biomedical image datasets. Copyright © 2017 Elsevier Ireland Ltd. All rights reserved.

THE CHOICE OF OPTIMAL STRUCTURE OF ARTIFICIAL NEURAL NETWORK CLASSIFIER INTENDED FOR CLASSIFICATION OF WELDING FLAWS

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

Sikora, R.; Chady, T.; Baniukiewicz, P.

2010-02-22

Nondestructive testing and evaluation are under continuous development. Currently researches are concentrated on three main topics: advancement of existing methods, introduction of novel methods and development of artificial intelligent systems for automatic defect recognition (ADR). Automatic defect classification algorithm comprises of two main tasks: creating a defect database and preparing a defect classifier. Here, the database was built using defect features that describe all geometrical and texture properties of the defect. Almost twenty carefully selected features calculated for flaws extracted from real radiograms were used. The radiograms were obtained from shipbuilding industry and they were verified by qualified operator. Twomore » weld defect's classifiers based on artificial neural networks were proposed and compared. First model consisted of one neural network model, where each output neuron corresponded to different defect group. The second model contained five neural networks. Each neural network had one neuron on output and was responsible for detection of defects from one group. In order to evaluate the effectiveness of the neural networks classifiers, the mean square errors were calculated for test radiograms and compared.« less

The Choice of Optimal Structure of Artificial Neural Network Classifier Intended for Classification of Welding Flaws

NASA Astrophysics Data System (ADS)

Sikora, R.; Chady, T.; Baniukiewicz, P.; Caryk, M.; Piekarczyk, B.

2010-02-01

Nondestructive testing and evaluation are under continuous development. Currently researches are concentrated on three main topics: advancement of existing methods, introduction of novel methods and development of artificial intelligent systems for automatic defect recognition (ADR). Automatic defect classification algorithm comprises of two main tasks: creating a defect database and preparing a defect classifier. Here, the database was built using defect features that describe all geometrical and texture properties of the defect. Almost twenty carefully selected features calculated for flaws extracted from real radiograms were used. The radiograms were obtained from shipbuilding industry and they were verified by qualified operator. Two weld defect's classifiers based on artificial neural networks were proposed and compared. First model consisted of one neural network model, where each output neuron corresponded to different defect group. The second model contained five neural networks. Each neural network had one neuron on output and was responsible for detection of defects from one group. In order to evaluate the effectiveness of the neural networks classifiers, the mean square errors were calculated for test radiograms and compared.

Prediction of residue-residue contact matrix for protein-protein interaction with Fisher score features and deep learning.

PubMed

Du, Tianchuan; Liao, Li; Wu, Cathy H; Sun, Bilin

2016-11-01

Protein-protein interactions play essential roles in many biological processes. Acquiring knowledge of the residue-residue contact information of two interacting proteins is not only helpful in annotating functions for proteins, but also critical for structure-based drug design. The prediction of the protein residue-residue contact matrix of the interfacial regions is challenging. In this work, we introduced deep learning techniques (specifically, stacked autoencoders) to build deep neural network models to tackled the residue-residue contact prediction problem. In tandem with interaction profile Hidden Markov Models, which was used first to extract Fisher score features from protein sequences, stacked autoencoders were deployed to extract and learn hidden abstract features. The deep learning model showed significant improvement over the traditional machine learning model, Support Vector Machines (SVM), with the overall accuracy increased by 15% from 65.40% to 80.82%. We showed that the stacked autoencoders could extract novel features, which can be utilized by deep neural networks and other classifiers to enhance learning, out of the Fisher score features. It is further shown that deep neural networks have significant advantages over SVM in making use of the newly extracted features. Copyright © 2016. Published by Elsevier Inc.

Artificial Neural Network Application in the Diagnosis of Disease Conditions with Liver Ultrasound Images

PubMed Central

Lele, Ramachandra Dattatraya; Joshi, Mukund; Chowdhary, Abhay

2014-01-01

The preliminary study presented within this paper shows a comparative study of various texture features extracted from liver ultrasonic images by employing Multilayer Perceptron (MLP), a type of artificial neural network, to study the presence of disease conditions. An ultrasound (US) image shows echo-texture patterns, which defines the organ characteristics. Ultrasound images of liver disease conditions such as “fatty liver,” “cirrhosis,” and “hepatomegaly” produce distinctive echo patterns. However, various ultrasound imaging artifacts and speckle noise make these echo-texture patterns difficult to identify and often hard to distinguish visually. Here, based on the extracted features from the ultrasonic images, we employed an artificial neural network for the diagnosis of disease conditions in liver and finding of the best classifier that distinguishes between abnormal and normal conditions of the liver. Comparison of the overall performance of all the feature classifiers concluded that “mixed feature set” is the best feature set. It showed an excellent rate of accuracy for the training data set. The gray level run length matrix (GLRLM) feature shows better results when the network was tested against unknown data. PMID:25332717

Method of gear fault diagnosis based on EEMD and improved Elman neural network

NASA Astrophysics Data System (ADS)

Zhang, Qi; Zhao, Wei; Xiao, Shungen; Song, Mengmeng

2017-05-01

Aiming at crack and wear and so on of gears Fault information is difficult to diagnose usually due to its weak, a gear fault diagnosis method that is based on EEMD and improved Elman neural network fusion is proposed. A number of IMF components are obtained by decomposing denoised all kinds of fault signals with EEMD, and the pseudo IMF components is eliminated by using the correlation coefficient method to obtain the effective IMF component. The energy characteristic value of each effective component is calculated as the input feature quantity of Elman neural network, and the improved Elman neural network is based on standard network by adding a feedback factor. The fault data of normal gear, broken teeth, cracked gear and attrited gear were collected by field collecting. The results were analyzed by the diagnostic method proposed in this paper. The results show that compared with the standard Elman neural network, Improved Elman neural network has the advantages of high diagnostic efficiency.

Tracking neural coding of perceptual and semantic features of concrete nouns

PubMed Central

Sudre, Gustavo; Pomerleau, Dean; Palatucci, Mark; Wehbe, Leila; Fyshe, Alona; Salmelin, Riitta; Mitchell, Tom

2015-01-01

We present a methodological approach employing magnetoencephalography (MEG) and machine learning techniques to investigate the flow of perceptual and semantic information decodable from neural activity in the half second during which the brain comprehends the meaning of a concrete noun. Important information about the cortical location of neural activity related to the representation of nouns in the human brain has been revealed by past studies using fMRI. However, the temporal sequence of processing from sensory input to concept comprehension remains unclear, in part because of the poor time resolution provided by fMRI. In this study, subjects answered 20 questions (e.g. is it alive?) about the properties of 60 different nouns prompted by simultaneous presentation of a pictured item and its written name. Our results show that the neural activity observed with MEG encodes a variety of perceptual and semantic features of stimuli at different times relative to stimulus onset, and in different cortical locations. By decoding these features, our MEG-based classifier was able to reliably distinguish between two different concrete nouns that it had never seen before. The results demonstrate that there are clear differences between the time course of the magnitude of MEG activity and that of decodable semantic information. Perceptual features were decoded from MEG activity earlier in time than semantic features, and features related to animacy, size, and manipulability were decoded consistently across subjects. We also observed that regions commonly associated with semantic processing in the fMRI literature may not show high decoding results in MEG. We believe that this type of approach and the accompanying machine learning methods can form the basis for further modeling of the flow of neural information during language processing and a variety of other cognitive processes. PMID:22565201

Research on artificial neural network intrusion detection photochemistry based on the improved wavelet analysis and transformation

NASA Astrophysics Data System (ADS)

Li, Hong; Ding, Xue

2017-03-01

This paper combines wavelet analysis and wavelet transform theory with artificial neural network, through the pretreatment on point feature attributes before in intrusion detection, to make them suitable for improvement of wavelet neural network. The whole intrusion classification model gets the better adaptability, self-learning ability, greatly enhances the wavelet neural network for solving the problem of field detection invasion, reduces storage space, contributes to improve the performance of the constructed neural network, and reduces the training time. Finally the results of the KDDCup99 data set simulation experiment shows that, this method reduces the complexity of constructing wavelet neural network, but also ensures the accuracy of the intrusion classification.

Stochastic architecture for Hopfield neural nets

NASA Technical Reports Server (NTRS)

Pavel, Sandy

1992-01-01

An expandable stochastic digital architecture for recurrent (Hopfield like) neural networks is proposed. The main features and basic principles of stochastic processing are presented. The stochastic digital architecture is based on a chip with n full interconnected neurons with a pipeline, bit processing structure. For large applications, a flexible way to interconnect many such chips is provided.

A comparative study between nonlinear regression and artificial neural network approaches for modelling wild oat (Avena fatua) field emergence

USDA-ARS?s Scientific Manuscript database

Non-linear regression techniques are used widely to fit weed field emergence patterns to soil microclimatic indices using S-type functions. Artificial neural networks present interesting and alternative features for such modeling purposes. In this work, a univariate hydrothermal-time based Weibull m...

Clinical Assistant Diagnosis for Electronic Medical Record Based on Convolutional Neural Network.

PubMed

Yang, Zhongliang; Huang, Yongfeng; Jiang, Yiran; Sun, Yuxi; Zhang, Yu-Jin; Luo, Pengcheng

2018-04-20

Automatically extracting useful information from electronic medical records along with conducting disease diagnoses is a promising task for both clinical decision support(CDS) and neural language processing(NLP). Most of the existing systems are based on artificially constructed knowledge bases, and then auxiliary diagnosis is done by rule matching. In this study, we present a clinical intelligent decision approach based on Convolutional Neural Networks(CNN), which can automatically extract high-level semantic information of electronic medical records and then perform automatic diagnosis without artificial construction of rules or knowledge bases. We use collected 18,590 copies of the real-world clinical electronic medical records to train and test the proposed model. Experimental results show that the proposed model can achieve 98.67% accuracy and 96.02% recall, which strongly supports that using convolutional neural network to automatically learn high-level semantic features of electronic medical records and then conduct assist diagnosis is feasible and effective.

Color image definition evaluation method based on deep learning method

NASA Astrophysics Data System (ADS)

Liu, Di; Li, YingChun

2018-01-01

In order to evaluate different blurring levels of color image and improve the method of image definition evaluation, this paper proposed a method based on the depth learning framework and BP neural network classification model, and presents a non-reference color image clarity evaluation method. Firstly, using VGG16 net as the feature extractor to extract 4,096 dimensions features of the images, then the extracted features and labeled images are employed in BP neural network to train. And finally achieve the color image definition evaluation. The method in this paper are experimented by using images from the CSIQ database. The images are blurred at different levels. There are 4,000 images after the processing. Dividing the 4,000 images into three categories, each category represents a blur level. 300 out of 400 high-dimensional features are trained in VGG16 net and BP neural network, and the rest of 100 samples are tested. The experimental results show that the method can take full advantage of the learning and characterization capability of deep learning. Referring to the current shortcomings of the major existing image clarity evaluation methods, which manually design and extract features. The method in this paper can extract the images features automatically, and has got excellent image quality classification accuracy for the test data set. The accuracy rate is 96%. Moreover, the predicted quality levels of original color images are similar to the perception of the human visual system.

A Hypergraph and Arithmetic Residue-based Probabilistic Neural Network for classification in Intrusion Detection Systems.

PubMed

Raman, M R Gauthama; Somu, Nivethitha; Kirthivasan, Kannan; Sriram, V S Shankar

2017-08-01

Over the past few decades, the design of an intelligent Intrusion Detection System (IDS) remains an open challenge to the research community. Continuous efforts by the researchers have resulted in the development of several learning models based on Artificial Neural Network (ANN) to improve the performance of the IDSs. However, there exists a tradeoff with respect to the stability of ANN architecture and the detection rate for less frequent attacks. This paper presents a novel approach based on Helly property of Hypergraph and Arithmetic Residue-based Probabilistic Neural Network (HG AR-PNN) to address the classification problem in IDS. The Helly property of Hypergraph was exploited for the identification of the optimal feature subset and the arithmetic residue of the optimal feature subset was used to train the PNN. The performance of HG AR-PNN was evaluated using KDD CUP 1999 intrusion dataset. Experimental results prove the dominance of HG AR-PNN classifier over the existing classifiers with respect to the stability and improved detection rate for less frequent attacks. Copyright © 2017 Elsevier Ltd. All rights reserved.

Development of the disable software reporting system on the basis of the neural network

NASA Astrophysics Data System (ADS)

Gavrylenko, S.; Babenko, O.; Ignatova, E.

2018-04-01

The PE structure of malicious and secure software is analyzed, features are highlighted, binary sign vectors are obtained and used as inputs for training the neural network. A software model for detecting malware based on the ART-1 neural network was developed, optimal similarity coefficients were found, and testing was performed. The obtained research results showed the possibility of using the developed system of identifying malicious software in computer systems protection systems

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

PubMed Central

Ordóñez, Francisco Javier; Roggen, Daniel

2016-01-01

Human activity recognition (HAR) tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which: (i) is suitable for multimodal wearable sensors; (ii) can perform sensor fusion naturally; (iii) does not require expert knowledge in designing features; and (iv) explicitly models the temporal dynamics of feature activations. We evaluate our framework on two datasets, one of which has been used in a public activity recognition challenge. Our results show that our framework outperforms competing deep non-recurrent networks on the challenge dataset by 4% on average; outperforming some of the previous reported results by up to 9%. Our results show that the framework can be applied to homogeneous sensor modalities, but can also fuse multimodal sensors to improve performance. We characterise key architectural hyperparameters’ influence on performance to provide insights about their optimisation. PMID:26797612

A neural network model of semantic memory linking feature-based object representation and words.

PubMed

Cuppini, C; Magosso, E; Ursino, M

2009-06-01

Recent theories in cognitive neuroscience suggest that semantic memory is a distributed process, which involves many cortical areas and is based on a multimodal representation of objects. The aim of this work is to extend a previous model of object representation to realize a semantic memory, in which sensory-motor representations of objects are linked with words. The model assumes that each object is described as a collection of features, coded in different cortical areas via a topological organization. Features in different objects are segmented via gamma-band synchronization of neural oscillators. The feature areas are further connected with a lexical area, devoted to the representation of words. Synapses among the feature areas, and among the lexical area and the feature areas are trained via a time-dependent Hebbian rule, during a period in which individual objects are presented together with the corresponding words. Simulation results demonstrate that, during the retrieval phase, the network can deal with the simultaneous presence of objects (from sensory-motor inputs) and words (from acoustic inputs), can correctly associate objects with words and segment objects even in the presence of incomplete information. Moreover, the network can realize some semantic links among words representing objects with shared features. These results support the idea that semantic memory can be described as an integrated process, whose content is retrieved by the co-activation of different multimodal regions. In perspective, extended versions of this model may be used to test conceptual theories, and to provide a quantitative assessment of existing data (for instance concerning patients with neural deficits).

Smart Sensing and Recognition Based on Models of Neural Networks

DTIC Science & Technology

1990-11-15

9P-o ,yY𔄃-’. AD-A230 701 University of Pensylvania Philadelphia, PA 19104-6390 SMART SENSING AND RECOGNITION BASED ON MODELS OF NEURAL NETWORKS ... networks , photonic 1 implementations, nonlinear dynamical signal processing 9 ABSTRACT (Continue on reverse if necessary and identify by block number...not develop in isolation but in synergism with sensory organs and their feature forming networks . This means that development of artificial pattern

Rapid Processing of a Global Feature in the ON Visual Pathways of Behaving Monkeys.

PubMed

Huang, Jun; Yang, Yan; Zhou, Ke; Zhao, Xudong; Zhou, Quan; Zhu, Hong; Yang, Yingshan; Zhang, Chunming; Zhou, Yifeng; Zhou, Wu

2017-01-01

Visual objects are recognized by their features. Whereas, some features are based on simple components (i.e., local features, such as orientation of line segments), some features are based on the whole object (i.e., global features, such as an object having a hole in it). Over the past five decades, behavioral, physiological, anatomical, and computational studies have established a general model of vision, which starts from extracting local features in the lower visual pathways followed by a feature integration process that extracts global features in the higher visual pathways. This local-to-global model is successful in providing a unified account for a vast sets of perception experiments, but it fails to account for a set of experiments showing human visual systems' superior sensitivity to global features. Understanding the neural mechanisms underlying the "global-first" process will offer critical insights into new models of vision. The goal of the present study was to establish a non-human primate model of rapid processing of global features for elucidating the neural mechanisms underlying differential processing of global and local features. Monkeys were trained to make a saccade to a target in the black background, which was different from the distractors (white circle) in color (e.g., red circle target), local features (e.g., white square target), a global feature (e.g., white ring with a hole target) or their combinations (e.g., red square target). Contrary to the predictions of the prevailing local-to-global model, we found that (1) detecting a distinction or a change in the global feature was faster than detecting a distinction or a change in color or local features; (2) detecting a distinction in color was facilitated by a distinction in the global feature, but not in the local features; and (3) detecting the hole was interfered by the local features of the hole (e.g., white ring with a squared hole). These results suggest that monkey ON visual systems have a subsystem that is more sensitive to distinctions in the global feature than local features. They also provide the behavioral constraints for identifying the underlying neural substrates.

Comparing visual representations across human fMRI and computational vision

PubMed Central

Leeds, Daniel D.; Seibert, Darren A.; Pyles, John A.; Tarr, Michael J.

2013-01-01

Feedforward visual object perception recruits a cortical network that is assumed to be hierarchical, progressing from basic visual features to complete object representations. However, the nature of the intermediate features related to this transformation remains poorly understood. Here, we explore how well different computer vision recognition models account for neural object encoding across the human cortical visual pathway as measured using fMRI. These neural data, collected during the viewing of 60 images of real-world objects, were analyzed with a searchlight procedure as in Kriegeskorte, Goebel, and Bandettini (2006): Within each searchlight sphere, the obtained patterns of neural activity for all 60 objects were compared to model responses for each computer recognition algorithm using representational dissimilarity analysis (Kriegeskorte et al., 2008). Although each of the computer vision methods significantly accounted for some of the neural data, among the different models, the scale invariant feature transform (Lowe, 2004), encoding local visual properties gathered from “interest points,” was best able to accurately and consistently account for stimulus representations within the ventral pathway. More generally, when present, significance was observed in regions of the ventral-temporal cortex associated with intermediate-level object perception. Differences in model effectiveness and the neural location of significant matches may be attributable to the fact that each model implements a different featural basis for representing objects (e.g., more holistic or more parts-based). Overall, we conclude that well-known computer vision recognition systems may serve as viable proxies for theories of intermediate visual object representation. PMID:24273227

Stochastic modeling for neural spiking events based on fractional superstatistical Poisson process

NASA Astrophysics Data System (ADS)

Konno, Hidetoshi; Tamura, Yoshiyasu

2018-01-01

In neural spike counting experiments, it is known that there are two main features: (i) the counting number has a fractional power-law growth with time and (ii) the waiting time (i.e., the inter-spike-interval) distribution has a heavy tail. The method of superstatistical Poisson processes (SSPPs) is examined whether these main features are properly modeled. Although various mixed/compound Poisson processes are generated with selecting a suitable distribution of the birth-rate of spiking neurons, only the second feature (ii) can be modeled by the method of SSPPs. Namely, the first one (i) associated with the effect of long-memory cannot be modeled properly. Then, it is shown that the two main features can be modeled successfully by a class of fractional SSPP (FSSPP).

Based on BP Neural Network Stock Prediction

ERIC Educational Resources Information Center

Liu, Xiangwei; Ma, Xin

2012-01-01

The stock market has a high profit and high risk features, on the stock market analysis and prediction research has been paid attention to by people. Stock price trend is a complex nonlinear function, so the price has certain predictability. This article mainly with improved BP neural network (BPNN) to set up the stock market prediction model, and…

Feature-based RNN target recognition

NASA Astrophysics Data System (ADS)

Bakircioglu, Hakan; Gelenbe, Erol

1998-09-01

Detection and recognition of target signatures in sensory data obtained by synthetic aperture radar (SAR), forward- looking infrared, or laser radar, have received considerable attention in the literature. In this paper, we propose a feature based target classification methodology to detect and classify targets in cluttered SAR images, that makes use of selective signature data from sensory data, together with a neural network technique which uses a set of trained networks based on the Random Neural Network (RNN) model (Gelenbe 89, 90, 91, 93) which is trained to act as a matched filter. We propose and investigate radial features of target shapes that are invariant to rotation, translation, and scale, to characterize target and clutter signatures. These features are then used to train a set of learning RNNs which can be used to detect targets within clutter with high accuracy, and to classify the targets or man-made objects from natural clutter. Experimental data from SAR imagery is used to illustrate and validate the proposed method, and to calculate Receiver Operating Characteristics which illustrate the performance of the proposed algorithm.

Blur identification by multilayer neural network based on multivalued neurons.

PubMed

Aizenberg, Igor; Paliy, Dmitriy V; Zurada, Jacek M; Astola, Jaakko T

2008-05-01

A multilayer neural network based on multivalued neurons (MLMVN) is a neural network with a traditional feedforward architecture. At the same time, this network has a number of specific different features. Its backpropagation learning algorithm is derivative-free. The functionality of MLMVN is superior to that of the traditional feedforward neural networks and of a variety kernel-based networks. Its higher flexibility and faster adaptation to the target mapping enables to model complex problems using simpler networks. In this paper, the MLMVN is used to identify both type and parameters of the point spread function, whose precise identification is of crucial importance for the image deblurring. The simulation results show the high efficiency of the proposed approach. It is confirmed that the MLMVN is a powerful tool for solving classification problems, especially multiclass ones.

An analysis of the influence of deep neural network (DNN) topology in bottleneck feature based language recognition.

PubMed

Lozano-Diez, Alicia; Zazo, Ruben; Toledano, Doroteo T; Gonzalez-Rodriguez, Joaquin

2017-01-01

Language recognition systems based on bottleneck features have recently become the state-of-the-art in this research field, showing its success in the last Language Recognition Evaluation (LRE 2015) organized by NIST (U.S. National Institute of Standards and Technology). This type of system is based on a deep neural network (DNN) trained to discriminate between phonetic units, i.e. trained for the task of automatic speech recognition (ASR). This DNN aims to compress information in one of its layers, known as bottleneck (BN) layer, which is used to obtain a new frame representation of the audio signal. This representation has been proven to be useful for the task of language identification (LID). Thus, bottleneck features are used as input to the language recognition system, instead of a classical parameterization of the signal based on cepstral feature vectors such as MFCCs (Mel Frequency Cepstral Coefficients). Despite the success of this approach in language recognition, there is a lack of studies analyzing in a systematic way how the topology of the DNN influences the performance of bottleneck feature-based language recognition systems. In this work, we try to fill-in this gap, analyzing language recognition results with different topologies for the DNN used to extract the bottleneck features, comparing them and against a reference system based on a more classical cepstral representation of the input signal with a total variability model. This way, we obtain useful knowledge about how the DNN configuration influences bottleneck feature-based language recognition systems performance.

Structure and weights optimisation of a modified Elman network emotion classifier using hybrid computational intelligence algorithms: a comparative study

NASA Astrophysics Data System (ADS)

Sheikhan, Mansour; Abbasnezhad Arabi, Mahdi; Gharavian, Davood

2015-10-01

Artificial neural networks are efficient models in pattern recognition applications, but their performance is dependent on employing suitable structure and connection weights. This study used a hybrid method for obtaining the optimal weight set and architecture of a recurrent neural emotion classifier based on gravitational search algorithm (GSA) and its binary version (BGSA), respectively. By considering the features of speech signal that were related to prosody, voice quality, and spectrum, a rich feature set was constructed. To select more efficient features, a fast feature selection method was employed. The performance of the proposed hybrid GSA-BGSA method was compared with similar hybrid methods based on particle swarm optimisation (PSO) algorithm and its binary version, PSO and discrete firefly algorithm, and hybrid of error back-propagation and genetic algorithm that were used for optimisation. Experimental tests on Berlin emotional database demonstrated the superior performance of the proposed method using a lighter network structure.

Permutation coding technique for image recognition systems.

PubMed

Kussul, Ernst M; Baidyk, Tatiana N; Wunsch, Donald C; Makeyev, Oleksandr; Martín, Anabel

2006-11-01

A feature extractor and neural classifier for image recognition systems are proposed. The proposed feature extractor is based on the concept of random local descriptors (RLDs). It is followed by the encoder that is based on the permutation coding technique that allows to take into account not only detected features but also the position of each feature on the image and to make the recognition process invariant to small displacements. The combination of RLDs and permutation coding permits us to obtain a sufficiently general description of the image to be recognized. The code generated by the encoder is used as an input data for the neural classifier. Different types of images were used to test the proposed image recognition system. It was tested in the handwritten digit recognition problem, the face recognition problem, and the microobject shape recognition problem. The results of testing are very promising. The error rate for the Modified National Institute of Standards and Technology (MNIST) database is 0.44% and for the Olivetti Research Laboratory (ORL) database it is 0.1%.

CNNdel: Calling Structural Variations on Low Coverage Data Based on Convolutional Neural Networks

PubMed Central

2017-01-01

Many structural variations (SVs) detection methods have been proposed due to the popularization of next-generation sequencing (NGS). These SV calling methods use different SV-property-dependent features; however, they all suffer from poor accuracy when running on low coverage sequences. The union of results from these tools achieves fairly high sensitivity but still produces low accuracy on low coverage sequence data. That is, these methods contain many false positives. In this paper, we present CNNdel, an approach for calling deletions from paired-end reads. CNNdel gathers SV candidates reported by multiple tools and then extracts features from aligned BAM files at the positions of candidates. With labeled feature-expressed candidates as a training set, CNNdel trains convolutional neural networks (CNNs) to distinguish true unlabeled candidates from false ones. Results show that CNNdel works well with NGS reads from 26 low coverage genomes of the 1000 Genomes Project. The paper demonstrates that convolutional neural networks can automatically assign the priority of SV features and reduce the false positives efficaciously. PMID:28630866

Gait Recognition Based on Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Sokolova, A.; Konushin, A.

2017-05-01

In this work we investigate the problem of people recognition by their gait. For this task, we implement deep learning approach using the optical flow as the main source of motion information and combine neural feature extraction with the additional embedding of descriptors for representation improvement. In order to find the best heuristics, we compare several deep neural network architectures, learning and classification strategies. The experiments were made on two popular datasets for gait recognition, so we investigate their advantages and disadvantages and the transferability of considered methods.

Word embeddings and recurrent neural networks based on Long-Short Term Memory nodes in supervised biomedical word sense disambiguation.

PubMed

Jimeno Yepes, Antonio

2017-09-01

Word sense disambiguation helps identifying the proper sense of ambiguous words in text. With large terminologies such as the UMLS Metathesaurus ambiguities appear and highly effective disambiguation methods are required. Supervised learning algorithm methods are used as one of the approaches to perform disambiguation. Features extracted from the context of an ambiguous word are used to identify the proper sense of such a word. The type of features have an impact on machine learning methods, thus affect disambiguation performance. In this work, we have evaluated several types of features derived from the context of the ambiguous word and we have explored as well more global features derived from MEDLINE using word embeddings. Results show that word embeddings improve the performance of more traditional features and allow as well using recurrent neural network classifiers based on Long-Short Term Memory (LSTM) nodes. The combination of unigrams and word embeddings with an SVM sets a new state of the art performance with a macro accuracy of 95.97 in the MSH WSD data set. Copyright © 2017 Elsevier Inc. All rights reserved.

Yarn-dyed fabric defect classification based on convolutional neural network

NASA Astrophysics Data System (ADS)

Jing, Junfeng; Dong, Amei; Li, Pengfei

2017-07-01

Considering that the manual inspection of the yarn-dyed fabric can be time consuming and less efficient, a convolutional neural network (CNN) solution based on the modified AlexNet structure for the classification of the yarn-dyed fabric defect is proposed. CNN has powerful ability of feature extraction and feature fusion which can simulate the learning mechanism of the human brain. In order to enhance computational efficiency and detection accuracy, the local response normalization (LRN) layers in AlexNet are replaced by the batch normalization (BN) layers. In the process of the network training, through several convolution operations, the characteristics of the image are extracted step by step, and the essential features of the image can be obtained from the edge features. And the max pooling layers, the dropout layers, the fully connected layers are also employed in the classification model to reduce the computation cost and acquire more precise features of fabric defect. Finally, the results of the defect classification are predicted by the softmax function. The experimental results show the capability of defect classification via the modified Alexnet model and indicate its robustness.

CNN-BLPred: a Convolutional neural network based predictor for β-Lactamases (BL) and their classes.

PubMed

White, Clarence; Ismail, Hamid D; Saigo, Hiroto; Kc, Dukka B

2017-12-28

The β-Lactamase (BL) enzyme family is an important class of enzymes that plays a key role in bacterial resistance to antibiotics. As the newly identified number of BL enzymes is increasing daily, it is imperative to develop a computational tool to classify the newly identified BL enzymes into one of its classes. There are two types of classification of BL enzymes: Molecular Classification and Functional Classification. Existing computational methods only address Molecular Classification and the performance of these existing methods is unsatisfactory. We addressed the unsatisfactory performance of the existing methods by implementing a Deep Learning approach called Convolutional Neural Network (CNN). We developed CNN-BLPred, an approach for the classification of BL proteins. The CNN-BLPred uses Gradient Boosted Feature Selection (GBFS) in order to select the ideal feature set for each BL classification. Based on the rigorous benchmarking of CCN-BLPred using both leave-one-out cross-validation and independent test sets, CCN-BLPred performed better than the other existing algorithms. Compared with other architectures of CNN, Recurrent Neural Network, and Random Forest, the simple CNN architecture with only one convolutional layer performs the best. After feature extraction, we were able to remove ~95% of the 10,912 features using Gradient Boosted Trees. During 10-fold cross validation, we increased the accuracy of the classic BL predictions by 7%. We also increased the accuracy of Class A, Class B, Class C, and Class D performance by an average of 25.64%. The independent test results followed a similar trend. We implemented a deep learning algorithm known as Convolutional Neural Network (CNN) to develop a classifier for BL classification. Combined with feature selection on an exhaustive feature set and using balancing method such as Random Oversampling (ROS), Random Undersampling (RUS) and Synthetic Minority Oversampling Technique (SMOTE), CNN-BLPred performs significantly better than existing algorithms for BL classification.

Clinical application of modified bag-of-features coupled with hybrid neural-based classifier in dengue fever classification using gene expression data.

PubMed

Chatterjee, Sankhadeep; Dey, Nilanjan; Shi, Fuqian; Ashour, Amira S; Fong, Simon James; Sen, Soumya

2018-04-01

Dengue fever detection and classification have a vital role due to the recent outbreaks of different kinds of dengue fever. Recently, the advancement in the microarray technology can be employed for such classification process. Several studies have established that the gene selection phase takes a significant role in the classifier performance. Subsequently, the current study focused on detecting two different variations, namely, dengue fever (DF) and dengue hemorrhagic fever (DHF). A modified bag-of-features method has been proposed to select the most promising genes in the classification process. Afterward, a modified cuckoo search optimization algorithm has been engaged to support the artificial neural (ANN-MCS) to classify the unknown subjects into three different classes namely, DF, DHF, and another class containing convalescent and normal cases. The proposed method has been compared with other three well-known classifiers, namely, multilayer perceptron feed-forward network (MLP-FFN), artificial neural network (ANN) trained with cuckoo search (ANN-CS), and ANN trained with PSO (ANN-PSO). Experiments have been carried out with different number of clusters for the initial bag-of-features-based feature selection phase. After obtaining the reduced dataset, the hybrid ANN-MCS model has been employed for the classification process. The results have been compared in terms of the confusion matrix-based performance measuring metrics. The experimental results indicated a highly statistically significant improvement with the proposed classifier over the traditional ANN-CS model.

Detection of Road Surface States from Tire Noise Using Neural Network Analysis

NASA Astrophysics Data System (ADS)

Kongrattanaprasert, Wuttiwat; Nomura, Hideyuki; Kamakura, Tomoo; Ueda, Koji

This report proposes a new processing method for automatically detecting the states of road surfaces from tire noises of passing vehicles. In addition to multiple indicators of the signal features in the frequency domain, we propose a few feature indicators in the time domain to successfully classify the road states into four categories: snowy, slushy, wet, and dry states. The method is based on artificial neural networks. The proposed classification is carried out in multiple neural networks using learning vector quantization. The outcomes of the networks are then integrated by the voting decision-making scheme. Experimental results obtained from recorded signals for ten days in the snowy season demonstrated that an accuracy of approximately 90% can be attained for predicting road surface states using only tire noise data.

Hybrid ANN optimized artificial fish swarm algorithm based classifier for classification of suspicious lesions in breast DCE-MRI

NASA Astrophysics Data System (ADS)

Janaki Sathya, D.; Geetha, K.

2017-12-01

Automatic mass or lesion classification systems are developed to aid in distinguishing between malignant and benign lesions present in the breast DCE-MR images, the systems need to improve both the sensitivity and specificity of DCE-MR image interpretation in order to be successful for clinical use. A new classifier (a set of features together with a classification method) based on artificial neural networks trained using artificial fish swarm optimization (AFSO) algorithm is proposed in this paper. The basic idea behind the proposed classifier is to use AFSO algorithm for searching the best combination of synaptic weights for the neural network. An optimal set of features based on the statistical textural features is presented. The investigational outcomes of the proposed suspicious lesion classifier algorithm therefore confirm that the resulting classifier performs better than other such classifiers reported in the literature. Therefore this classifier demonstrates that the improvement in both the sensitivity and specificity are possible through automated image analysis.

Differentiating malignant from benign breast tumors on acoustic radiation force impulse imaging using fuzzy-based neural networks with principle component analysis

NASA Astrophysics Data System (ADS)

Liu, Hsiao-Chuan; Chou, Yi-Hong; Tiu, Chui-Mei; Hsieh, Chi-Wen; Liu, Brent; Shung, K. Kirk

2017-03-01

Many modalities have been developed as screening tools for breast cancer. A new screening method called acoustic radiation force impulse (ARFI) imaging was created for distinguishing breast lesions based on localized tissue displacement. This displacement was quantitated by virtual touch tissue imaging (VTI). However, VTIs sometimes express reverse results to intensity information in clinical observation. In the study, a fuzzy-based neural network with principle component analysis (PCA) was proposed to differentiate texture patterns of malignant breast from benign tumors. Eighty VTIs were randomly retrospected. Thirty four patients were determined as BI-RADS category 2 or 3, and the rest of them were determined as BI-RADS category 4 or 5 by two leading radiologists. Morphological method and Boolean algebra were performed as the image preprocessing to acquire region of interests (ROIs) on VTIs. Twenty four quantitative parameters deriving from first-order statistics (FOS), fractal dimension and gray level co-occurrence matrix (GLCM) were utilized to analyze the texture pattern of breast tumors on VTIs. PCA was employed to reduce the dimension of features. Fuzzy-based neural network as a classifier to differentiate malignant from benign breast tumors. Independent samples test was used to examine the significance of the difference between benign and malignant breast tumors. The area Az under the receiver operator characteristic (ROC) curve, sensitivity, specificity and accuracy were calculated to evaluate the performance of the system. Most all of texture parameters present significant difference between malignant and benign tumors with p-value of less than 0.05 except the average of fractal dimension. For all features classified by fuzzy-based neural network, the sensitivity, specificity, accuracy and Az were 95.7%, 97.1%, 95% and 0.964, respectively. However, the sensitivity, specificity, accuracy and Az can be increased to 100%, 97.1%, 98.8% and 0.985, respectively if PCA was performed to reduce the dimension of features. Patterns of breast tumors on VTIs can effectively be recognized by quantitative texture parameters, and differentiated malignant from benign lesions by fuzzy-based neural network with PCA.

Feature to prototype transition in neural networks

NASA Astrophysics Data System (ADS)

Krotov, Dmitry; Hopfield, John

Models of associative memory with higher order (higher than quadratic) interactions, and their relationship to neural networks used in deep learning are discussed. Associative memory is conventionally described by recurrent neural networks with dynamical convergence to stable points. Deep learning typically uses feedforward neural nets without dynamics. However, a simple duality relates these two different views when applied to problems of pattern classification. From the perspective of associative memory such models deserve attention because they make it possible to store a much larger number of memories, compared to the quadratic case. In the dual description, these models correspond to feedforward neural networks with one hidden layer and unusual activation functions transmitting the activities of the visible neurons to the hidden layer. These activation functions are rectified polynomials of a higher degree rather than the rectified linear functions used in deep learning. The network learns representations of the data in terms of features for rectified linear functions, but as the power in the activation function is increased there is a gradual shift to a prototype-based representation, the two extreme regimes of pattern recognition known in cognitive psychology. Simons Center for Systems Biology.

Neural representations of emotion are organized around abstract event features.

PubMed

Skerry, Amy E; Saxe, Rebecca

2015-08-03

Research on emotion attribution has tended to focus on the perception of overt expressions of at most five or six basic emotions. However, our ability to identify others' emotional states is not limited to perception of these canonical expressions. Instead, we make fine-grained inferences about what others feel based on the situations they encounter, relying on knowledge of the eliciting conditions for different emotions. In the present research, we provide convergent behavioral and neural evidence concerning the representations underlying these concepts. First, we find that patterns of activity in mentalizing regions contain information about subtle emotional distinctions conveyed through verbal descriptions of eliciting situations. Second, we identify a space of abstract situation features that well captures the emotion discriminations subjects make behaviorally and show that this feature space outperforms competing models in capturing the similarity space of neural patterns in these regions. Together, the data suggest that our knowledge of others' emotions is abstract and high dimensional, that brain regions selective for mental state reasoning support relatively subtle distinctions between emotion concepts, and that the neural representations in these regions are not reducible to more primitive affective dimensions such as valence and arousal. Copyright © 2015 Elsevier Ltd. All rights reserved.

Neural Representations of Emotion Are Organized around Abstract Event Features

PubMed Central

Skerry, Amy E.; Saxe, Rebecca

2016-01-01

Summary Research on emotion attribution has tended to focus on the perception of overt expressions of at most five or six basic emotions. However, our ability to identify others' emotional states is not limited to perception of these canonical expressions. Instead, we make fine-grained inferences about what others feel based on the situations they encounter, relying on knowledge of the eliciting conditions for different emotions. In the present research, we provide convergent behavioral and neural evidence concerning the representations underlying these concepts. First, we find that patterns of activity in mentalizing regions contain information about subtle emotional distinctions conveyed through verbal descriptions of eliciting situations. Second, we identify a space of abstract situation features that well captures the emotion discriminations subjects make behaviorally and show that this feature space outperforms competing models in capturing the similarity space of neural patterns in these regions. Together, the data suggest that our knowledge of others' emotions is abstract and high dimensional, that brain regions selective for mental state reasoning support relatively subtle distinctions between emotion concepts, and that the neural representations in these regions are not reducible to more primitive affective dimensions such as valence and arousal. PMID:26212878

Analyzing multicomponent receptive fields from neural responses to natural stimuli

PubMed Central

Rowekamp, Ryan; Sharpee, Tatyana O

2011-01-01

The challenge of building increasingly better models of neural responses to natural stimuli is to accurately estimate the multiple stimulus features that may jointly affect the neural spike probability. The selectivity for combinations of features is thought to be crucial for achieving classical properties of neural responses such as contrast invariance. The joint search for these multiple stimulus features is difficult because estimating spike probability as a multidimensional function of stimulus projections onto candidate relevant dimensions is subject to the curse of dimensionality. An attractive alternative is to search for relevant dimensions sequentially, as in projection pursuit regression. Here we demonstrate using analytic arguments and simulations of model cells that different types of sequential search strategies exhibit systematic biases when used with natural stimuli. Simulations show that joint optimization is feasible for up to three dimensions with current algorithms. When applied to the responses of V1 neurons to natural scenes, models based on three jointly optimized dimensions had better predictive power in a majority of cases compared to dimensions optimized sequentially, with different sequential methods yielding comparable results. Thus, although the curse of dimensionality remains, at least several relevant dimensions can be estimated by joint information maximization. PMID:21780916

Classification of spontaneous EEG signals in migraine

NASA Astrophysics Data System (ADS)

Bellotti, R.; De Carlo, F.; de Tommaso, M.; Lucente, M.

2007-08-01

We set up a classification system able to detect patients affected by migraine without aura, through the analysis of their spontaneous EEG patterns. First, the signals are characterized by means of wavelet-based features, than a supervised neural network is used to classify the multichannel data. For the feature extraction, scale-dependent and scale-independent methods are considered with a variety of wavelet functions. Both the approaches provide very high and almost comparable classification performances. A complete separation of the two groups is obtained when the data are plotted in the plane spanned by two suitable neural outputs.

Diagnostic analysis of liver B ultrasonic texture features based on LM neural network

NASA Astrophysics Data System (ADS)

Chi, Qingyun; Hua, Hu; Liu, Menglin; Jiang, Xiuying

2017-03-01

In this study, B ultrasound images of 124 benign and malignant patients were randomly selected as the study objects. The B ultrasound images of the liver were treated by enhanced de-noising. By constructing the gray level co-occurrence matrix which reflects the information of each angle, Principal Component Analysis of 22 texture features were extracted and combined with LM neural network for diagnosis and classification. Experimental results show that this method is a rapid and effective diagnostic method for liver imaging, which provides a quantitative basis for clinical diagnosis of liver diseases.

Crowd counting via region based multi-channel convolution neural network

NASA Astrophysics Data System (ADS)

Cao, Xiaoguang; Gao, Siqi; Bai, Xiangzhi

2017-11-01

This paper proposed a novel region based multi-channel convolution neural network architecture for crowd counting. In order to effectively solve the perspective distortion in crowd datasets with a great diversity of scales, this work combines the main channel and three branch channels. These channels extract both the global and region features. And the results are used to estimate density map. Moreover, kernels with ladder-shaped sizes are designed across all the branch channels, which generate adaptive region features. Also, branch channels use relatively deep and shallow network to achieve more accurate detector. By using these strategies, the proposed architecture achieves state-of-the-art performance on ShanghaiTech datasets and competitive performance on UCF_CC_50 datasets.

Predictive Ensemble Decoding of Acoustical Features Explains Context-Dependent Receptive Fields.

PubMed

Yildiz, Izzet B; Mesgarani, Nima; Deneve, Sophie

2016-12-07

A primary goal of auditory neuroscience is to identify the sound features extracted and represented by auditory neurons. Linear encoding models, which describe neural responses as a function of the stimulus, have been primarily used for this purpose. Here, we provide theoretical arguments and experimental evidence in support of an alternative approach, based on decoding the stimulus from the neural response. We used a Bayesian normative approach to predict the responses of neurons detecting relevant auditory features, despite ambiguities and noise. We compared the model predictions to recordings from the primary auditory cortex of ferrets and found that: (1) the decoding filters of auditory neurons resemble the filters learned from the statistics of speech sounds; (2) the decoding model captures the dynamics of responses better than a linear encoding model of similar complexity; and (3) the decoding model accounts for the accuracy with which the stimulus is represented in neural activity, whereas linear encoding model performs very poorly. Most importantly, our model predicts that neuronal responses are fundamentally shaped by "explaining away," a divisive competition between alternative interpretations of the auditory scene. Neural responses in the auditory cortex are dynamic, nonlinear, and hard to predict. Traditionally, encoding models have been used to describe neural responses as a function of the stimulus. However, in addition to external stimulation, neural activity is strongly modulated by the responses of other neurons in the network. We hypothesized that auditory neurons aim to collectively decode their stimulus. In particular, a stimulus feature that is decoded (or explained away) by one neuron is not explained by another. We demonstrated that this novel Bayesian decoding model is better at capturing the dynamic responses of cortical neurons in ferrets. Whereas the linear encoding model poorly reflects selectivity of neurons, the decoding model can account for the strong nonlinearities observed in neural data. Copyright © 2016 Yildiz et al.

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.

Real-time camera-based face detection using a modified LAMSTAR neural network system

NASA Astrophysics Data System (ADS)

Girado, Javier I.; Sandin, Daniel J.; DeFanti, Thomas A.; Wolf, Laura K.

2003-03-01

This paper describes a cost-effective, real-time (640x480 at 30Hz) upright frontal face detector as part of an ongoing project to develop a video-based, tetherless 3D head position and orientation tracking system. The work is specifically targeted for auto-stereoscopic displays and projection-based virtual reality systems. The proposed face detector is based on a modified LAMSTAR neural network system. At the input stage, after achieving image normalization and equalization, a sub-window analyzes facial features using a neural network. The sub-window is segmented, and each part is fed to a neural network layer consisting of a Kohonen Self-Organizing Map (SOM). The output of the SOM neural networks are interconnected and related by correlation-links, and can hence determine the presence of a face with enough redundancy to provide a high detection rate. To avoid tracking multiple faces simultaneously, the system is initially trained to track only the face centered in a box superimposed on the display. The system is also rotationally and size invariant to a certain degree.

Stimulus information contaminates summation tests of independent neural representations of features

NASA Technical Reports Server (NTRS)

Shimozaki, Steven S.; Eckstein, Miguel P.; Abbey, Craig K.

2002-01-01

Many models of visual processing assume that visual information is analyzed into separable and independent neural codes, or features. A common psychophysical test of independent features is known as a summation study, which measures performance in a detection, discrimination, or visual search task as the number of proposed features increases. Improvement in human performance with increasing number of available features is typically attributed to the summation, or combination, of information across independent neural coding of the features. In many instances, however, increasing the number of available features also increases the stimulus information in the task, as assessed by an optimal observer that does not include the independent neural codes. In a visual search task with spatial frequency and orientation as the component features, a particular set of stimuli were chosen so that all searches had equivalent stimulus information, regardless of the number of features. In this case, human performance did not improve with increasing number of features, implying that the improvement observed with additional features may be due to stimulus information and not the combination across independent features.

Video-based convolutional neural networks for activity recognition from robot-centric videos

NASA Astrophysics Data System (ADS)

Ryoo, M. S.; Matthies, Larry

2016-05-01

In this evaluation paper, we discuss convolutional neural network (CNN)-based approaches for human activity recognition. In particular, we investigate CNN architectures designed to capture temporal information in videos and their applications to the human activity recognition problem. There have been multiple previous works to use CNN-features for videos. These include CNNs using 3-D XYT convolutional filters, CNNs using pooling operations on top of per-frame image-based CNN descriptors, and recurrent neural networks to learn temporal changes in per-frame CNN descriptors. We experimentally compare some of these different representatives CNNs while using first-person human activity videos. We especially focus on videos from a robots viewpoint, captured during its operations and human-robot interactions.

Knowledge synthesis with maps of neural connectivity.

PubMed

Tallis, Marcelo; Thompson, Richard; Russ, Thomas A; Burns, Gully A P C

2011-01-01

This paper describes software for neuroanatomical knowledge synthesis based on neural connectivity data. This software supports a mature methodology developed since the early 1990s. Over this time, the Swanson laboratory at USC has generated an account of the neural connectivity of the sub-structures of the hypothalamus, amygdala, septum, hippocampus, and bed nucleus of the stria terminalis. This is based on neuroanatomical data maps drawn into a standard brain atlas by experts. In earlier work, we presented an application for visualizing and comparing anatomical macro connections using the Swanson third edition atlas as a framework for accurate registration. Here we describe major improvements to the NeuARt application based on the incorporation of a knowledge representation of experimental design. We also present improvements in the interface and features of the data mapping components within a unified web-application. As a step toward developing an accurate sub-regional account of neural connectivity, we provide navigational access between the data maps and a semantic representation of area-to-area connections that they support. We do so based on an approach called "Knowledge Engineering from Experimental Design" (KEfED) model that is based on experimental variables. We have extended the underlying KEfED representation of tract-tracing experiments by incorporating the definition of a neuronanatomical data map as a measurement variable in the study design. This paper describes the software design of a web-application that allows anatomical data sets to be described within a standard experimental context and thus indexed by non-spatial experimental design features.

Neural networks distinguish between taste qualities based on receptor cell population responses.

PubMed

Varkevisser, B; Peterson, D; Ogura, T; Kinnamon, S C

2001-06-01

Response features of taste receptor cell action potentials were examined using an artificial neural network to determine whether they contain information about taste quality. Using the loose patch technique to record from hamster taste buds in vivo we recorded population responses of single fungiform papillae to NaCl (100 mM), sucrose (200 mM) and the synthetic sweetener NC-00274-01 (NC-01) (200 microM). Features of each response describing both burst and inter-burst characteristics were then presented to an artificial neural network for pairwise classification of taste stimuli. Responses to NaCl could be distinguished from those to both NC-01 and sucrose with accuracies of up to 86%. In contrast, pairwise comparisons between sucrose and NC-01 were not successful, scoring at chance (50%). Also, comparisons between two different concentrations of NaCl, 0.01 and 0.005 M, scored at chance. Pairwise comparisons using only those features that relate to the inter-burst behavior of the response (i.e. bursting rate) did not hinder the performance of the neural network as both sweeteners versus NaCl received scores of 75--85%. Comparisons using features corresponding to each individual burst scored poorly, receiving scores only slightly above chance. We then compared the sweeteners with varying concentrations of NaCl (0.1, 0.01, 0.005 and 0.001 M) using only those features corresponding to bursting rate within a 1 s time window. The neural network was capable of distinguishing between NaCl and NC-01 at all concentrations tested; while comparisons between NaCl and sucrose received high scores at all concentrations except 0.001 M. These results show that two different taste qualities can be distinguished from each other based solely on the bursting rates of action potentials in single taste buds and that this distinction is independent of stimulation intensity down to 0.001 M NaCl. These data suggest that action potentials in taste receptor cells may play a role in taste quality coding.

Manifold decoding for neural representations of face viewpoint and gaze direction using magnetoencephalographic data.

PubMed

Kuo, Po-Chih; Chen, Yong-Sheng; Chen, Li-Fen

2018-05-01

The main challenge in decoding neural representations lies in linking neural activity to representational content or abstract concepts. The transformation from a neural-based to a low-dimensional representation may hold the key to encoding perceptual processes in the human brain. In this study, we developed a novel model by which to represent two changeable features of faces: face viewpoint and gaze direction. These features are embedded in spatiotemporal brain activity derived from magnetoencephalographic data. Our decoding results demonstrate that face viewpoint and gaze direction can be represented by manifold structures constructed from brain responses in the bilateral occipital face area and right superior temporal sulcus, respectively. Our results also show that the superposition of brain activity in the manifold space reveals the viewpoints of faces as well as directions of gazes as perceived by the subject. The proposed manifold representation model provides a novel opportunity to gain further insight into the processing of information in the human brain. © 2018 Wiley Periodicals, Inc.

Using input feature information to improve ultraviolet retrieval in neural networks

NASA Astrophysics Data System (ADS)

Sun, Zhibin; Chang, Ni-Bin; Gao, Wei; Chen, Maosi; Zempila, Melina

2017-09-01

In neural networks, the training/predicting accuracy and algorithm efficiency can be improved significantly via accurate input feature extraction. In this study, some spatial features of several important factors in retrieving surface ultraviolet (UV) are extracted. An extreme learning machine (ELM) is used to retrieve the surface UV of 2014 in the continental United States, using the extracted features. The results conclude that more input weights can improve the learning capacities of neural networks.

Progressively expanded neural network for automatic material identification in hyperspectral imagery

NASA Astrophysics Data System (ADS)

Paheding, Sidike

The science of hyperspectral remote sensing focuses on the exploitation of the spectral signatures of various materials to enhance capabilities including object detection, recognition, and material characterization. Hyperspectral imagery (HSI) has been extensively used for object detection and identification applications since it provides plenty of spectral information to uniquely identify materials by their reflectance spectra. HSI-based object detection algorithms can be generally classified into stochastic and deterministic approaches. Deterministic approaches are comparatively simple to apply since it is usually based on direct spectral similarity such as spectral angles or spectral correlation. In contrast, stochastic algorithms require statistical modeling and estimation for target class and non-target class. Over the decades, many single class object detection methods have been proposed in the literature, however, deterministic multiclass object detection in HSI has not been explored. In this work, we propose a deterministic multiclass object detection scheme, named class-associative spectral fringe-adjusted joint transform correlation. Human brain is capable of simultaneously processing high volumes of multi-modal data received every second of the day. In contrast, a machine sees input data simply as random binary numbers. Although machines are computationally efficient, they are inferior when comes to data abstraction and interpretation. Thus, mimicking the learning strength of human brain has been current trend in artificial intelligence. In this work, we present a biological inspired neural network, named progressively expanded neural network (PEN Net), based on nonlinear transformation of input neurons to a feature space for better pattern differentiation. In PEN Net, discrete fixed excitations are disassembled and scattered in the feature space as a nonlinear line. Each disassembled element on the line corresponds to a pattern with similar features. Unlike the conventional neural network where hidden neurons need to be iteratively adjusted to achieve better accuracy, our proposed PEN Net does not require hidden neurons tuning which achieves better computational efficiency, and it has also shown superior performance in HSI classification tasks compared to the state-of-the-arts. Spectral-spatial features based HSI classification framework has shown stronger strength compared to spectral-only based methods. In our lastly proposed technique, PEN Net is incorporated with multiscale spatial features (i.e., multiscale complete local binary pattern) to perform a spectral-spatial classification of HSI. Several experiments demonstrate excellent performance of our proposed technique compared to the more recent developed approaches.

Discriminating Induced-Microearthquakes Using New Seismic Features

NASA Astrophysics Data System (ADS)

Mousavi, S. M.; Horton, S.

2016-12-01

We studied characteristics of induced-microearthquakes on the basis of the waveforms recorded on a limited number of surface receivers using machine-learning techniques. Forty features in the time, frequency, and time-frequency domains were measured on each waveform, and several techniques such as correlation-based feature selection, Artificial Neural Networks (ANNs), Logistic Regression (LR) and X-mean were used as research tools to explore the relationship between these seismic features and source parameters. The results show that spectral features have the highest correlation to source depth. Two new measurements developed as seismic features for this study, spectral centroids and 2D cross-correlations in the time-frequency domain, performed better than the common seismic measurements. These features can be used by machine learning techniques for efficient automatic classification of low energy signals recorded at one or more seismic stations. We applied the technique to 440 microearthquakes-1.7Reference: Mousavi, S.M., S.P. Horton, C. A. Langston, B. Samei, (2016) Seismic features and automatic discrimination of deep and shallow induced-microearthquakes using neural network and logistic regression, Geophys. J. Int. doi: 10.1093/gji/ggw258.

Classification and recognition of texture collagen obtaining by multiphoton microscope with neural network analysis

NASA Astrophysics Data System (ADS)

Wu, Shulian; Peng, Yuanyuan; Hu, Liangjun; Zhang, Xiaoman; Li, Hui

2016-01-01

Second harmonic generation microscopy (SHGM) was used to monitor the process of chronological aging skin in vivo. The collagen structures of mice model with different ages were obtained using SHGM. Then, texture feature with contrast, correlation and entropy were extracted and analysed using the grey level co-occurrence matrix. At last, the neural network tool of Matlab was applied to train the texture of collagen in different statues during the aging process. And the simulation of mice collagen texture was carried out. The results indicated that the classification accuracy reach 85%. Results demonstrated that the proposed approach effectively detected the target object in the collagen texture image during the chronological aging process and the analysis tool based on neural network applied the skin of classification and feature extraction method is feasible.

Neural Differentiation of Incorrectly Predicted Memories.

PubMed

Kim, Ghootae; Norman, Kenneth A; Turk-Browne, Nicholas B

2017-02-22

When an item is predicted in a particular context but the prediction is violated, memory for that item is weakened (Kim et al., 2014). Here, we explore what happens when such previously mispredicted items are later reencountered. According to prior neural network simulations, this sequence of events-misprediction and subsequent restudy-should lead to differentiation of the item's neural representation from the previous context (on which the misprediction was based). Specifically, misprediction weakens connections in the representation to features shared with the previous context and restudy allows new features to be incorporated into the representation that are not shared with the previous context. This cycle of misprediction and restudy should have the net effect of moving the item's neural representation away from the neural representation of the previous context. We tested this hypothesis using human fMRI by tracking changes in item-specific BOLD activity patterns in the hippocampus, a key structure for representing memories and generating predictions. In left CA2/3/DG, we found greater neural differentiation for items that were repeatedly mispredicted and restudied compared with items from a control condition that was identical except without misprediction. We also measured prediction strength in a trial-by-trial fashion and found that greater misprediction for an item led to more differentiation, further supporting our hypothesis. Therefore, the consequences of prediction error go beyond memory weakening. If the mispredicted item is restudied, the brain adaptively differentiates its memory representation to improve the accuracy of subsequent predictions and to shield it from further weakening. SIGNIFICANCE STATEMENT Competition between overlapping memories leads to weakening of nontarget memories over time, making it easier to access target memories. However, a nontarget memory in one context might become a target memory in another context. How do such memories get restrengthened without increasing competition again? Computational models suggest that the brain handles this by reducing neural connections to the previous context and adding connections to new features that were not part of the previous context. The result is neural differentiation away from the previous context. Here, we provide support for this theory, using fMRI to track neural representations of individual memories in the hippocampus and how they change based on learning. Copyright © 2017 the authors 0270-6474/17/372022-10$15.00/0.

An Optimization-Based Method for Feature Ranking in Nonlinear Regression Problems.

PubMed

Bravi, Luca; Piccialli, Veronica; Sciandrone, Marco

2017-04-01

In this paper, we consider the feature ranking problem, where, given a set of training instances, the task is to associate a score with the features in order to assess their relevance. Feature ranking is a very important tool for decision support systems, and may be used as an auxiliary step of feature selection to reduce the high dimensionality of real-world data. We focus on regression problems by assuming that the process underlying the generated data can be approximated by a continuous function (for instance, a feedforward neural network). We formally state the notion of relevance of a feature by introducing a minimum zero-norm inversion problem of a neural network, which is a nonsmooth, constrained optimization problem. We employ a concave approximation of the zero-norm function, and we define a smooth, global optimization problem to be solved in order to assess the relevance of the features. We present the new feature ranking method based on the solution of instances of the global optimization problem depending on the available training data. Computational experiments on both artificial and real data sets are performed, and point out that the proposed feature ranking method is a valid alternative to existing methods in terms of effectiveness. The obtained results also show that the method is costly in terms of CPU time, and this may be a limitation in the solution of large-dimensional problems.

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.

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

Reward-based training of recurrent neural networks for cognitive and value-based tasks

PubMed Central

Song, H Francis; Yang, Guangyu R; Wang, Xiao-Jing

2017-01-01

Trained neural network models, which exhibit features of neural activity recorded from behaving animals, may provide insights into the circuit mechanisms of cognitive functions through systematic analysis of network activity and connectivity. However, in contrast to the graded error signals commonly used to train networks through supervised learning, animals learn from reward feedback on definite actions through reinforcement learning. Reward maximization is particularly relevant when optimal behavior depends on an animal’s internal judgment of confidence or subjective preferences. Here, we implement reward-based training of recurrent neural networks in which a value network guides learning by using the activity of the decision network to predict future reward. We show that such models capture behavioral and electrophysiological findings from well-known experimental paradigms. Our work provides a unified framework for investigating diverse cognitive and value-based computations, and predicts a role for value representation that is essential for learning, but not executing, a task. DOI: http://dx.doi.org/10.7554/eLife.21492.001 PMID:28084991

Recurrent neural networks for breast lesion classification based on DCE-MRIs

NASA Astrophysics Data System (ADS)

Antropova, Natasha; Huynh, Benjamin; Giger, Maryellen

2018-02-01

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a significant role in breast cancer screening, cancer staging, and monitoring response to therapy. Recently, deep learning methods are being rapidly incorporated in image-based breast cancer diagnosis and prognosis. However, most of the current deep learning methods make clinical decisions based on 2-dimentional (2D) or 3D images and are not well suited for temporal image data. In this study, we develop a deep learning methodology that enables integration of clinically valuable temporal components of DCE-MRIs into deep learning-based lesion classification. Our work is performed on a database of 703 DCE-MRI cases for the task of distinguishing benign and malignant lesions, and uses the area under the ROC curve (AUC) as the performance metric in conducting that task. We train a recurrent neural network, specifically a long short-term memory network (LSTM), on sequences of image features extracted from the dynamic MRI sequences. These features are extracted with VGGNet, a convolutional neural network pre-trained on a large dataset of natural images ImageNet. The features are obtained from various levels of the network, to capture low-, mid-, and high-level information about the lesion. Compared to a classification method that takes as input only images at a single time-point (yielding an AUC = 0.81 (se = 0.04)), our LSTM method improves lesion classification with an AUC of 0.85 (se = 0.03).

Online particle detection with Neural Networks based on topological calorimetry information

NASA Astrophysics Data System (ADS)

Ciodaro, T.; Deva, D.; de Seixas, J. M.; Damazio, D.

2012-06-01

This paper presents the latest results from the Ringer algorithm, which is based on artificial neural networks for the electron identification at the online filtering system of the ATLAS particle detector, in the context of the LHC experiment at CERN. The algorithm performs topological feature extraction using the ATLAS calorimetry information (energy measurements). The extracted information is presented to a neural network classifier. Studies showed that the Ringer algorithm achieves high detection efficiency, while keeping the false alarm rate low. Optimizations, guided by detailed analysis, reduced the algorithm execution time by 59%. Also, the total memory necessary to store the Ringer algorithm information represents less than 6.2 percent of the total filtering system amount.

Neural net target-tracking system using structured laser patterns

NASA Astrophysics Data System (ADS)

Cho, Jae-Wan; Lee, Yong-Bum; Lee, Nam-Ho; Park, Soon-Yong; Lee, Jongmin; Choi, Gapchu; Baek, Sunghyun; Park, Dong-Sun

1996-06-01

In this paper, we describe a robot endeffector tracking system using sensory information from recently-announced structured pattern laser diodes, which can generate images with several different types of structured pattern. The neural network approach is employed to recognize the robot endeffector covering the situation of three types of motion: translation, scaling and rotation. Features for the neural network to detect the position of the endeffector are extracted from the preprocessed images. Artificial neural networks are used to store models and to match with unknown input features recognizing the position of the robot endeffector. Since a minimal number of samples are used for different directions of the robot endeffector in the system, an artificial neural network with the generalization capability can be utilized for unknown input features. A feedforward neural network with the generalization capability can be utilized for unknown input features. A feedforward neural network trained with the back propagation learning is used to detect the position of the robot endeffector. Another feedforward neural network module is used to estimate the motion from a sequence of images and to control movements of the robot endeffector. COmbining the tow neural networks for recognizing the robot endeffector and estimating the motion with the preprocessing stage, the whole system keeps tracking of the robot endeffector effectively.

Automatic detection and recognition of traffic signs in stereo images based on features and probabilistic neural networks

NASA Astrophysics Data System (ADS)

Sheng, Yehua; Zhang, Ka; Ye, Chun; Liang, Cheng; Li, Jian

2008-04-01

Considering the problem of automatic traffic sign detection and recognition in stereo images captured under motion conditions, a new algorithm for traffic sign detection and recognition based on features and probabilistic neural networks (PNN) is proposed in this paper. Firstly, global statistical color features of left image are computed based on statistics theory. Then for red, yellow and blue traffic signs, left image is segmented to three binary images by self-adaptive color segmentation method. Secondly, gray-value projection and shape analysis are used to confirm traffic sign regions in left image. Then stereo image matching is used to locate the homonymy traffic signs in right image. Thirdly, self-adaptive image segmentation is used to extract binary inner core shapes of detected traffic signs. One-dimensional feature vectors of inner core shapes are computed by central projection transformation. Fourthly, these vectors are input to the trained probabilistic neural networks for traffic sign recognition. Lastly, recognition results in left image are compared with recognition results in right image. If results in stereo images are identical, these results are confirmed as final recognition results. The new algorithm is applied to 220 real images of natural scenes taken by the vehicle-borne mobile photogrammetry system in Nanjing at different time. Experimental results show a detection and recognition rate of over 92%. So the algorithm is not only simple, but also reliable and high-speed on real traffic sign detection and recognition. Furthermore, it can obtain geometrical information of traffic signs at the same time of recognizing their types.

Spike Timing Matters in Novel Neuronal Code Involved in Vibrotactile Frequency Perception.

PubMed

Birznieks, Ingvars; Vickery, Richard M

2017-05-22

Skin vibrations sensed by tactile receptors contribute significantly to the perception of object properties during tactile exploration [1-4] and to sensorimotor control during object manipulation [5]. Sustained low-frequency skin vibration (<60 Hz) evokes a distinct tactile sensation referred to as flutter whose frequency can be clearly perceived [6]. How afferent spiking activity translates into the perception of frequency is still unknown. Measures based on mean spike rates of neurons in the primary somatosensory cortex are sufficient to explain performance in some frequency discrimination tasks [7-11]; however, there is emerging evidence that stimuli can be distinguished based also on temporal features of neural activity [12, 13]. Our study's advance is to demonstrate that temporal features are fundamental for vibrotactile frequency perception. Pulsatile mechanical stimuli were used to elicit specified temporal spike train patterns in tactile afferents, and subsequently psychophysical methods were employed to characterize human frequency perception. Remarkably, the most salient temporal feature determining vibrotactile frequency was not the underlying periodicity but, rather, the duration of the silent gap between successive bursts of neural activity. This burst gap code for frequency represents a previously unknown form of neural coding in the tactile sensory system, which parallels auditory pitch perception mechanisms based on purely temporal information where longer inter-pulse intervals receive higher perceptual weights than short intervals [14]. Our study also demonstrates that human perception of stimuli can be determined exclusively by temporal features of spike trains independent of the mean spike rate and without contribution from population response factors. Copyright © 2017 Elsevier Ltd. All rights reserved.

Supervised neural network classification of pre-sliced cooked pork ham images using quaternionic singular values.

PubMed

Valous, Nektarios A; Mendoza, Fernando; Sun, Da-Wen; Allen, Paul

2010-03-01

The quaternionic singular value decomposition is a technique to decompose a quaternion matrix (representation of a colour image) into quaternion singular vector and singular value component matrices exposing useful properties. The objective of this study was to use a small portion of uncorrelated singular values, as robust features for the classification of sliced pork ham images, using a supervised artificial neural network classifier. Images were acquired from four qualities of sliced cooked pork ham typically consumed in Ireland (90 slices per quality), having similar appearances. Mahalanobis distances and Pearson product moment correlations were used for feature selection. Six highly discriminating features were used as input to train the neural network. An adaptive feedforward multilayer perceptron classifier was employed to obtain a suitable mapping from the input dataset. The overall correct classification performance for the training, validation and test set were 90.3%, 94.4%, and 86.1%, respectively. The results confirm that the classification performance was satisfactory. Extracting the most informative features led to the recognition of a set of different but visually quite similar textural patterns based on quaternionic singular values. Copyright 2009 Elsevier Ltd. All rights reserved.

Deep learning-based features of breast MRI for prediction of occult invasive disease following a diagnosis of ductal carcinoma in situ: preliminary data

NASA Astrophysics Data System (ADS)

Zhu, Zhe; Harowicz, Michael; Zhang, Jun; Saha, Ashirbani; Grimm, Lars J.; Hwang, Shelley; Mazurowski, Maciej A.

2018-02-01

Approximately 25% of patients with ductal carcinoma in situ (DCIS) diagnosed from core needle biopsy are subsequently upstaged to invasive cancer at surgical excision. Identifying patients with occult invasive disease is important as it changes treatment and precludes enrollment in active surveillance for DCIS. In this study, we investigated upstaging of DCIS to invasive disease using deep features. While deep neural networks require large amounts of training data, the available data to predict DCIS upstaging is sparse and thus directly training a neural network is unlikely to be successful. In this work, a pre-trained neural network is used as a feature extractor and a support vector machine (SVM) is trained on the extracted features. We used the dynamic contrast-enhanced (DCE) MRIs of patients at our institution from January 1, 2000, through March 23, 2014 who underwent MRI following a diagnosis of DCIS. Among the 131 DCIS patients, there were 35 patients who were upstaged to invasive cancer. Area under the ROC curve within the 10-fold cross-validation scheme was used for validation of our predictive model. The use of deep features was able to achieve an AUC of 0.68 (95% CI: 0.56-0.78) to predict occult invasive disease. This preliminary work demonstrates the promise of deep features to predict surgical upstaging following a diagnosis of DCIS.

Using Graph Components Derived from an Associative Concept Dictionary to Predict fMRI Neural Activation Patterns that Represent the Meaning of Nouns.

PubMed

Akama, Hiroyuki; Miyake, Maki; Jung, Jaeyoung; Murphy, Brian

2015-01-01

In this study, we introduce an original distance definition for graphs, called the Markov-inverse-F measure (MiF). This measure enables the integration of classical graph theory indices with new knowledge pertaining to structural feature extraction from semantic networks. MiF improves the conventional Jaccard and/or Simpson indices, and reconciles both the geodesic information (random walk) and co-occurrence adjustment (degree balance and distribution). We measure the effectiveness of graph-based coefficients through the application of linguistic graph information for a neural activity recorded during conceptual processing in the human brain. Specifically, the MiF distance is computed between each of the nouns used in a previous neural experiment and each of the in-between words in a subgraph derived from the Edinburgh Word Association Thesaurus of English. From the MiF-based information matrix, a machine learning model can accurately obtain a scalar parameter that specifies the degree to which each voxel in (the MRI image of) the brain is activated by each word or each principal component of the intermediate semantic features. Furthermore, correlating the voxel information with the MiF-based principal components, a new computational neurolinguistics model with a network connectivity paradigm is created. This allows two dimensions of context space to be incorporated with both semantic and neural distributional representations.

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.

A novel prosodic-information synthesizer based on recurrent fuzzy neural network for the Chinese TTS system.

PubMed

Lin, Chin-Teng; Wu, Rui-Cheng; Chang, Jyh-Yeong; Liang, Sheng-Fu

2004-02-01

In this paper, a new technique for the Chinese text-to-speech (TTS) system is proposed. Our major effort focuses on the prosodic information generation. New methodologies for constructing fuzzy rules in a prosodic model simulating human's pronouncing rules are developed. The proposed Recurrent Fuzzy Neural Network (RFNN) is a multilayer recurrent neural network (RNN) which integrates a Self-cOnstructing Neural Fuzzy Inference Network (SONFIN) into a recurrent connectionist structure. The RFNN can be functionally divided into two parts. The first part adopts the SONFIN as a prosodic model to explore the relationship between high-level linguistic features and prosodic information based on fuzzy inference rules. As compared to conventional neural networks, the SONFIN can always construct itself with an economic network size in high learning speed. The second part employs a five-layer network to generate all prosodic parameters by directly using the prosodic fuzzy rules inferred from the first part as well as other important features of syllables. The TTS system combined with the proposed method can behave not only sandhi rules but also the other prosodic phenomena existing in the traditional TTS systems. Moreover, the proposed scheme can even find out some new rules about prosodic phrase structure. The performance of the proposed RFNN-based prosodic model is verified by imbedding it into a Chinese TTS system with a Chinese monosyllable database based on the time-domain pitch synchronous overlap add (TD-PSOLA) method. Our experimental results show that the proposed RFNN can generate proper prosodic parameters including pitch means, pitch shapes, maximum energy levels, syllable duration, and pause duration. Some synthetic sounds are online available for demonstration.

Seismic signal auto-detecing from different features by using Convolutional Neural Network

NASA Astrophysics Data System (ADS)

Huang, Y.; Zhou, Y.; Yue, H.; Zhou, S.

2017-12-01

We try Convolutional Neural Network to detect some features of seismic data and compare their efficience. The features include whether a signal is seismic signal or noise and the arrival time of P and S phase and each feature correspond to a Convolutional Neural Network. We first use traditional STA/LTA to recongnize some events and then use templete matching to find more events as training set for the Neural Network. To make the training set more various, we add some noise to the seismic data and make some synthetic seismic data and noise. The 3-component raw signal and time-frequancy ananlyze are used as the input data for our neural network. Our Training is performed on GPUs to achieve efficient convergence. Our method improved the precision in comparison with STA/LTA and template matching. We will move to recurrent neural network to see if this kind network is better in detect P and S phase.

Combining Feature Selection and Integration—A Neural Model for MT Motion Selectivity

PubMed Central

Beck, Cornelia; Neumann, Heiko

2011-01-01

Background The computation of pattern motion in visual area MT based on motion input from area V1 has been investigated in many experiments and models attempting to replicate the main mechanisms. Two different core conceptual approaches were developed to explain the findings. In integrationist models the key mechanism to achieve pattern selectivity is the nonlinear integration of V1 motion activity. In contrast, selectionist models focus on the motion computation at positions with 2D features. Methodology/Principal Findings Recent experiments revealed that neither of the two concepts alone is sufficient to explain all experimental data and that most of the existing models cannot account for the complex behaviour found. MT pattern selectivity changes over time for stimuli like type II plaids from vector average to the direction computed with an intersection of constraint rule or by feature tracking. Also, the spatial arrangement of the stimulus within the receptive field of a MT cell plays a crucial role. We propose a recurrent neural model showing how feature integration and selection can be combined into one common architecture to explain these findings. The key features of the model are the computation of 1D and 2D motion in model area V1 subpopulations that are integrated in model MT cells using feedforward and feedback processing. Our results are also in line with findings concerning the solution of the aperture problem. Conclusions/Significance We propose a new neural model for MT pattern computation and motion disambiguation that is based on a combination of feature selection and integration. The model can explain a range of recent neurophysiological findings including temporally dynamic behaviour. PMID:21814543

Task-induced frequency modulation features for brain-computer interfacing.

PubMed

Jayaram, Vinay; Hohmann, Matthias; Just, Jennifer; Schölkopf, Bernhard; Grosse-Wentrup, Moritz

2017-10-01

Task-induced amplitude modulation of neural oscillations is routinely used in brain-computer interfaces (BCIs) for decoding subjects' intents, and underlies some of the most robust and common methods in the field, such as common spatial patterns and Riemannian geometry. While there has been some interest in phase-related features for classification, both techniques usually presuppose that the frequencies of neural oscillations remain stable across various tasks. We investigate here whether features based on task-induced modulation of the frequency of neural oscillations enable decoding of subjects' intents with an accuracy comparable to task-induced amplitude modulation. We compare cross-validated classification accuracies using the amplitude and frequency modulated features, as well as a joint feature space, across subjects in various paradigms and pre-processing conditions. We show results with a motor imagery task, a cognitive task, and also preliminary results in patients with amyotrophic lateral sclerosis (ALS), as well as using common spatial patterns and Laplacian filtering. The frequency features alone do not significantly out-perform traditional amplitude modulation features, and in some cases perform significantly worse. However, across both tasks and pre-processing in healthy subjects the joint space significantly out-performs either the frequency or amplitude features alone. This result only does not hold for ALS patients, for whom the dataset is of insufficient size to draw any statistically significant conclusions. Task-induced frequency modulation is robust and straight forward to compute, and increases performance when added to standard amplitude modulation features across paradigms. This allows more information to be extracted from the EEG signal cheaply and can be used throughout the field of BCIs.

Identification of input variables for feature based artificial neural networks-saccade detection in EOG recordings.

PubMed

Tigges, P; Kathmann, N; Engel, R R

1997-07-01

Though artificial neural networks (ANN) are excellent tools for pattern recognition problems when signal to noise ratio is low, the identification of decision relevant features for ANN input data is still a crucial issue. The experience of the ANN designer and the existing knowledge and understanding of the problem seem to be the only links for a specific construction. In the present study a backpropagation ANN based on modified raw data inputs showed encouraging results. Investigating the specific influences of prototypical input patterns on a specially designed ANN led to a new sparse and efficient input data presentation. This data coding obtained by a semiautomatic procedure combining existing expert knowledge and the internal representation structures of the raw data based ANN yielded a list of feature vectors, each representing the relevant information for saccade identification. The feature based ANN produced a reduction of the error rate of nearly 40% compared with the raw data ANN. An overall correct classification of 92% of so far unknown data was realized. The proposed method of extracting internal ANN knowledge for the production of a better input data representation is not restricted to EOG recordings, and could be used in various fields of signal analysis.

Identification of hand motion using background subtraction method and extraction of image binary with backpropagation neural network on skeleton model

NASA Astrophysics Data System (ADS)

Fauziah; Wibowo, E. P.; Madenda, S.; Hustinawati

2018-03-01

Capturing and recording motion in human is mostly done with the aim for sports, health, animation films, criminality, and robotic applications. In this study combined background subtraction and back propagation neural network. This purpose to produce, find similarity movement. The acquisition process using 8 MP resolution camera MP4 format, duration 48 seconds, 30frame/rate. video extracted produced 1444 pieces and results hand motion identification process. Phase of image processing performed is segmentation process, feature extraction, identification. Segmentation using bakground subtraction, extracted feature basically used to distinguish between one object to another object. Feature extraction performed by using motion based morfology analysis based on 7 invariant moment producing four different classes motion: no object, hand down, hand-to-side and hands-up. Identification process used to recognize of hand movement using seven inputs. Testing and training with a variety of parameters tested, it appears that architecture provides the highest accuracy in one hundred hidden neural network. The architecture is used propagate the input value of the system implementation process into the user interface. The result of the identification of the type of the human movement has been clone to produce the highest acuracy of 98.5447%. The training process is done to get the best results.

Tongue Images Classification Based on Constrained High Dispersal Network.

PubMed

Meng, Dan; Cao, Guitao; Duan, Ye; Zhu, Minghua; Tu, Liping; Xu, Dong; Xu, Jiatuo

2017-01-01

Computer aided tongue diagnosis has a great potential to play important roles in traditional Chinese medicine (TCM). However, the majority of the existing tongue image analyses and classification methods are based on the low-level features, which may not provide a holistic view of the tongue. Inspired by deep convolutional neural network (CNN), we propose a novel feature extraction framework called constrained high dispersal neural networks (CHDNet) to extract unbiased features and reduce human labor for tongue diagnosis in TCM. Previous CNN models have mostly focused on learning convolutional filters and adapting weights between them, but these models have two major issues: redundancy and insufficient capability in handling unbalanced sample distribution. We introduce high dispersal and local response normalization operation to address the issue of redundancy. We also add multiscale feature analysis to avoid the problem of sensitivity to deformation. Our proposed CHDNet learns high-level features and provides more classification information during training time, which may result in higher accuracy when predicting testing samples. We tested the proposed method on a set of 267 gastritis patients and a control group of 48 healthy volunteers. Test results show that CHDNet is a promising method in tongue image classification for the TCM study.

Feature Extraction of Event-Related Potentials Using Wavelets: An Application to Human Performance Monitoring

NASA Technical Reports Server (NTRS)

Trejo, Leonard J.; Shensa, Mark J.; Remington, Roger W. (Technical Monitor)

1998-01-01

This report describes the development and evaluation of mathematical models for predicting human performance from discrete wavelet transforms (DWT) of event-related potentials (ERP) elicited by task-relevant stimuli. The DWT was compared to principal components analysis (PCA) for representation of ERPs in linear regression and neural network models developed to predict a composite measure of human signal detection performance. Linear regression models based on coefficients of the decimated DWT predicted signal detection performance with half as many f ree parameters as comparable models based on PCA scores. In addition, the DWT-based models were more resistant to model degradation due to over-fitting than PCA-based models. Feed-forward neural networks were trained using the backpropagation,-, algorithm to predict signal detection performance based on raw ERPs, PCA scores, or high-power coefficients of the DWT. Neural networks based on high-power DWT coefficients trained with fewer iterations, generalized to new data better, and were more resistant to overfitting than networks based on raw ERPs. Networks based on PCA scores did not generalize to new data as well as either the DWT network or the raw ERP network. The results show that wavelet expansions represent the ERP efficiently and extract behaviorally important features for use in linear regression or neural network models of human performance. The efficiency of the DWT is discussed in terms of its decorrelation and energy compaction properties. In addition, the DWT models provided evidence that a pattern of low-frequency activity (1 to 3.5 Hz) occurring at specific times and scalp locations is a reliable correlate of human signal detection performance.

Feature extraction of event-related potentials using wavelets: an application to human performance monitoring

NASA Technical Reports Server (NTRS)

Trejo, L. J.; Shensa, M. J.

1999-01-01

This report describes the development and evaluation of mathematical models for predicting human performance from discrete wavelet transforms (DWT) of event-related potentials (ERP) elicited by task-relevant stimuli. The DWT was compared to principal components analysis (PCA) for representation of ERPs in linear regression and neural network models developed to predict a composite measure of human signal detection performance. Linear regression models based on coefficients of the decimated DWT predicted signal detection performance with half as many free parameters as comparable models based on PCA scores. In addition, the DWT-based models were more resistant to model degradation due to over-fitting than PCA-based models. Feed-forward neural networks were trained using the backpropagation algorithm to predict signal detection performance based on raw ERPs, PCA scores, or high-power coefficients of the DWT. Neural networks based on high-power DWT coefficients trained with fewer iterations, generalized to new data better, and were more resistant to overfitting than networks based on raw ERPs. Networks based on PCA scores did not generalize to new data as well as either the DWT network or the raw ERP network. The results show that wavelet expansions represent the ERP efficiently and extract behaviorally important features for use in linear regression or neural network models of human performance. The efficiency of the DWT is discussed in terms of its decorrelation and energy compaction properties. In addition, the DWT models provided evidence that a pattern of low-frequency activity (1 to 3.5 Hz) occurring at specific times and scalp locations is a reliable correlate of human signal detection performance. Copyright 1999 Academic Press.

Comparison of breast DCE-MRI contrast time points for predicting response to neoadjuvant chemotherapy using deep convolutional neural network features with transfer learning

NASA Astrophysics Data System (ADS)

Huynh, Benjamin Q.; Antropova, Natasha; Giger, Maryellen L.

2017-03-01

DCE-MRI datasets have a temporal aspect to them, resulting in multiple regions of interest (ROIs) per subject, based on contrast time points. It is unclear how the different contrast time points vary in terms of usefulness for computer-aided diagnosis tasks in conjunction with deep learning methods. We thus sought to compare the different DCE-MRI contrast time points with regard to how well their extracted features predict response to neoadjuvant chemotherapy within a deep convolutional neural network. Our dataset consisted of 561 ROIs from 64 subjects. Each subject was categorized as a non-responder or responder, determined by recurrence-free survival. First, features were extracted from each ROI using a convolutional neural network (CNN) pre-trained on non-medical images. Linear discriminant analysis classifiers were then trained on varying subsets of these features, based on their contrast time points of origin. Leave-one-out cross validation (by subject) was used to assess performance in the task of estimating probability of response to therapy, with area under the ROC curve (AUC) as the metric. The classifier trained on features from strictly the pre-contrast time point performed the best, with an AUC of 0.85 (SD = 0.033). The remaining classifiers resulted in AUCs ranging from 0.71 (SD = 0.028) to 0.82 (SD = 0.027). Overall, we found the pre-contrast time point to be the most effective at predicting response to therapy and that including additional contrast time points moderately reduces variance.

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.

Neonatal Seizure Detection Using Deep Convolutional Neural Networks.

PubMed

Ansari, Amir H; Cherian, Perumpillichira J; Caicedo, Alexander; Naulaers, Gunnar; De Vos, Maarten; Van Huffel, Sabine

2018-04-02

Identifying a core set of features is one of the most important steps in the development of an automated seizure detector. In most of the published studies describing features and seizure classifiers, the features were hand-engineered, which may not be optimal. The main goal of the present paper is using deep convolutional neural networks (CNNs) and random forest to automatically optimize feature selection and classification. The input of the proposed classifier is raw multi-channel EEG and the output is the class label: seizure/nonseizure. By training this network, the required features are optimized, while fitting a nonlinear classifier on the features. After training the network with EEG recordings of 26 neonates, five end layers performing the classification were replaced with a random forest classifier in order to improve the performance. This resulted in a false alarm rate of 0.9 per hour and seizure detection rate of 77% using a test set of EEG recordings of 22 neonates that also included dubious seizures. The newly proposed CNN classifier outperformed three data-driven feature-based approaches and performed similar to a previously developed heuristic method.

Mission scheduling

NASA Technical Reports Server (NTRS)

Gaspin, Christine

1989-01-01

How a neural network can work, compared to a hybrid system based on an operations research and artificial intelligence approach, is investigated through a mission scheduling problem. The characteristic features of each system are discussed.

Semantic image segmentation with fused CNN features

NASA Astrophysics Data System (ADS)

Geng, Hui-qiang; Zhang, Hua; Xue, Yan-bing; Zhou, Mian; Xu, Guang-ping; Gao, Zan

2017-09-01

Semantic image segmentation is a task to predict a category label for every image pixel. The key challenge of it is to design a strong feature representation. In this paper, we fuse the hierarchical convolutional neural network (CNN) features and the region-based features as the feature representation. The hierarchical features contain more global information, while the region-based features contain more local information. The combination of these two kinds of features significantly enhances the feature representation. Then the fused features are used to train a softmax classifier to produce per-pixel label assignment probability. And a fully connected conditional random field (CRF) is used as a post-processing method to improve the labeling consistency. We conduct experiments on SIFT flow dataset. The pixel accuracy and class accuracy are 84.4% and 34.86%, respectively.

Sentiment analysis: a comparison of deep learning neural network algorithm with SVM and naϊve Bayes for Indonesian text

NASA Astrophysics Data System (ADS)

Calvin Frans Mariel, Wahyu; Mariyah, Siti; Pramana, Setia

2018-03-01

Deep learning is a new era of machine learning techniques that essentially imitate the structure and function of the human brain. It is a development of deeper Artificial Neural Network (ANN) that uses more than one hidden layer. Deep Learning Neural Network has a great ability on recognizing patterns from various data types such as picture, audio, text, and many more. In this paper, the authors tries to measure that algorithm’s ability by applying it into the text classification. The classification task herein is done by considering the content of sentiment in a text which is also called as sentiment analysis. By using several combinations of text preprocessing and feature extraction techniques, we aim to compare the precise modelling results of Deep Learning Neural Network with the other two commonly used algorithms, the Naϊve Bayes and Support Vector Machine (SVM). This algorithm comparison uses Indonesian text data with balanced and unbalanced sentiment composition. Based on the experimental simulation, Deep Learning Neural Network clearly outperforms the Naϊve Bayes and SVM and offers a better F-1 Score while for the best feature extraction technique which improves that modelling result is Bigram.

Convolutional Neural Network-Based Finger-Vein Recognition Using NIR Image Sensors

PubMed Central

Hong, Hyung Gil; Lee, Min Beom; Park, Kang Ryoung

2017-01-01

Conventional finger-vein recognition systems perform recognition based on the finger-vein lines extracted from the input images or image enhancement, and texture feature extraction from the finger-vein images. In these cases, however, the inaccurate detection of finger-vein lines lowers the recognition accuracy. In the case of texture feature extraction, the developer must experimentally decide on a form of the optimal filter for extraction considering the characteristics of the image database. To address this problem, this research proposes a finger-vein recognition method that is robust to various database types and environmental changes based on the convolutional neural network (CNN). In the experiments using the two finger-vein databases constructed in this research and the SDUMLA-HMT finger-vein database, which is an open database, the method proposed in this research showed a better performance compared to the conventional methods. PMID:28587269

Convolutional Neural Network-Based Finger-Vein Recognition Using NIR Image Sensors.

PubMed

Hong, Hyung Gil; Lee, Min Beom; Park, Kang Ryoung

2017-06-06

Conventional finger-vein recognition systems perform recognition based on the finger-vein lines extracted from the input images or image enhancement, and texture feature extraction from the finger-vein images. In these cases, however, the inaccurate detection of finger-vein lines lowers the recognition accuracy. In the case of texture feature extraction, the developer must experimentally decide on a form of the optimal filter for extraction considering the characteristics of the image database. To address this problem, this research proposes a finger-vein recognition method that is robust to various database types and environmental changes based on the convolutional neural network (CNN). In the experiments using the two finger-vein databases constructed in this research and the SDUMLA-HMT finger-vein database, which is an open database, the method proposed in this research showed a better performance compared to the conventional methods.

TRPM7 maintains progenitor-like features of neuroblastoma cells: implications for metastasis formation

PubMed Central

Middelbeek, Jeroen; Kamermans, Alwin; Kuipers, Arthur J.; Hoogerbrugge, Peter M.; Jalink, Kees; van Leeuwen, Frank N.

2015-01-01

Neuroblastoma is an embryonal tumor derived from poorly differentiated neural crest cells. Current research is aimed at identifying the molecular mechanisms that maintain the progenitor state of neuroblastoma cells and to develop novel therapeutic strategies that induce neuroblastoma cell differentiation. Mechanisms controlling neural crest development are typically dysregulated during neuroblastoma progression, and provide an appealing starting point for drug target discovery. Transcriptional programs involved in neural crest development act as a context dependent gene regulatory network. In addition to BMP, Wnt and Notch signaling, activation of developmental gene expression programs depends on the physical characteristics of the tissue microenvironment. TRPM7, a mechanically regulated TRP channel with kinase activity, was previously found essential for embryogenesis and the maintenance of undifferentiated neural crest progenitors. Hence, we hypothesized that TRPM7 may preserve progenitor-like, metastatic features of neuroblastoma cells. Using multiple neuroblastoma cell models, we demonstrate that TRPM7 expression closely associates with the migratory and metastatic properties of neuroblastoma cells in vitro and in vivo. Moreover, microarray-based expression profiling on control and TRPM7 shRNA transduced neuroblastoma cells indicates that TRPM7 controls a developmental transcriptional program involving the transcription factor SNAI2. Overall, our data indicate that TRPM7 contributes to neuroblastoma progression by maintaining progenitor-like features. PMID:25797249

A neutron spectrum unfolding computer code based on artificial neural networks

NASA Astrophysics Data System (ADS)

Ortiz-Rodríguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Cervantes Viramontes, J. M.; Vega-Carrillo, H. R.

2014-02-01

The Bonner Spheres Spectrometer consists of a thermal neutron sensor placed at the center of a number of moderating polyethylene spheres of different diameters. From the measured readings, information can be derived about the spectrum of the neutron field where measurements were made. Disadvantages of the Bonner system are the weight associated with each sphere and the need to sequentially irradiate the spheres, requiring long exposure periods. Provided a well-established response matrix and adequate irradiation conditions, the most delicate part of neutron spectrometry, is the unfolding process. The derivation of the spectral information is not simple because the unknown is not given directly as a result of the measurements. The drawbacks associated with traditional unfolding procedures have motivated the need of complementary approaches. Novel methods based on Artificial Intelligence, mainly Artificial Neural Networks, have been widely investigated. In this work, a neutron spectrum unfolding code based on neural nets technology is presented. This code is called Neutron Spectrometry and Dosimetry with Artificial Neural networks unfolding code that was designed in a graphical interface. The core of the code is an embedded neural network architecture previously optimized using the robust design of artificial neural networks methodology. The main features of the code are: easy to use, friendly and intuitive to the user. This code was designed for a Bonner Sphere System based on a 6LiI(Eu) neutron detector and a response matrix expressed in 60 energy bins taken from an International Atomic Energy Agency compilation. The main feature of the code is that as entrance data, for unfolding the neutron spectrum, only seven rate counts measured with seven Bonner spheres are required; simultaneously the code calculates 15 dosimetric quantities as well as the total flux for radiation protection purposes. This code generates a full report with all information of the unfolding in the HTML format. NSDann unfolding code is freely available, upon request to the authors.

Residual neural processing of musical sound features in adult cochlear implant users.

PubMed

Timm, Lydia; Vuust, Peter; Brattico, Elvira; Agrawal, Deepashri; Debener, Stefan; Büchner, Andreas; Dengler, Reinhard; Wittfoth, Matthias

2014-01-01

Auditory processing in general and music perception in particular are hampered in adult cochlear implant (CI) users. To examine the residual music perception skills and their underlying neural correlates in CI users implanted in adolescence or adulthood, we conducted an electrophysiological and behavioral study comparing adult CI users with normal-hearing age-matched controls (NH controls). We used a newly developed musical multi-feature paradigm, which makes it possible to test automatic auditory discrimination of six different types of sound feature changes inserted within a musical enriched setting lasting only 20 min. The presentation of stimuli did not require the participants' attention, allowing the study of the early automatic stage of feature processing in the auditory cortex. For the CI users, we obtained mismatch negativity (MMN) brain responses to five feature changes but not to changes of rhythm, whereas we obtained MMNs for all the feature changes in the NH controls. Furthermore, the MMNs to deviants of pitch of CI users were reduced in amplitude and later than those of NH controls for changes of pitch and guitar timber. No other group differences in MMN parameters were found to changes in intensity and saxophone timber. Furthermore, the MMNs in CI users reflected the behavioral scores from a respective discrimination task and were correlated with patients' age and speech intelligibility. Our results suggest that even though CI users are not performing at the same level as NH controls in neural discrimination of pitch-based features, they do possess potential neural abilities for music processing. However, CI users showed a disrupted ability to automatically discriminate rhythmic changes compared with controls. The current behavioral and MMN findings highlight the residual neural skills for music processing even in CI users who have been implanted in adolescence or adulthood. -Automatic brain responses to musical feature changes reflect the limitations of central auditory processing in adult Cochlear Implant users.-The brains of adult CI users automatically process sound features changes even when inserted in a musical context.-CI users show disrupted automatic discriminatory abilities for rhythm in the brain.-Our fast paradigm demonstrate residual musical abilities in the brains of adult CI users giving hope for their future rehabilitation.

Residual Neural Processing of Musical Sound Features in Adult Cochlear Implant Users

PubMed Central

Timm, Lydia; Vuust, Peter; Brattico, Elvira; Agrawal, Deepashri; Debener, Stefan; Büchner, Andreas; Dengler, Reinhard; Wittfoth, Matthias

2014-01-01

Auditory processing in general and music perception in particular are hampered in adult cochlear implant (CI) users. To examine the residual music perception skills and their underlying neural correlates in CI users implanted in adolescence or adulthood, we conducted an electrophysiological and behavioral study comparing adult CI users with normal-hearing age-matched controls (NH controls). We used a newly developed musical multi-feature paradigm, which makes it possible to test automatic auditory discrimination of six different types of sound feature changes inserted within a musical enriched setting lasting only 20 min. The presentation of stimuli did not require the participants’ attention, allowing the study of the early automatic stage of feature processing in the auditory cortex. For the CI users, we obtained mismatch negativity (MMN) brain responses to five feature changes but not to changes of rhythm, whereas we obtained MMNs for all the feature changes in the NH controls. Furthermore, the MMNs to deviants of pitch of CI users were reduced in amplitude and later than those of NH controls for changes of pitch and guitar timber. No other group differences in MMN parameters were found to changes in intensity and saxophone timber. Furthermore, the MMNs in CI users reflected the behavioral scores from a respective discrimination task and were correlated with patients’ age and speech intelligibility. Our results suggest that even though CI users are not performing at the same level as NH controls in neural discrimination of pitch-based features, they do possess potential neural abilities for music processing. However, CI users showed a disrupted ability to automatically discriminate rhythmic changes compared with controls. The current behavioral and MMN findings highlight the residual neural skills for music processing even in CI users who have been implanted in adolescence or adulthood. Highlights: -Automatic brain responses to musical feature changes reflect the limitations of central auditory processing in adult Cochlear Implant users.-The brains of adult CI users automatically process sound features changes even when inserted in a musical context.-CI users show disrupted automatic discriminatory abilities for rhythm in the brain.-Our fast paradigm demonstrate residual musical abilities in the brains of adult CI users giving hope for their future rehabilitation. PMID:24772074

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.

Spatial and Time Domain Feature of ERP Speller System Extracted via Convolutional Neural Network.

PubMed

Yoon, Jaehong; Lee, Jungnyun; Whang, Mincheol

2018-01-01

Feature of event-related potential (ERP) has not been completely understood and illiteracy problem remains unsolved. To this end, P300 peak has been used as the feature of ERP in most brain-computer interface applications, but subjects who do not show such peak are common. Recent development of convolutional neural network provides a way to analyze spatial and temporal features of ERP. Here, we train the convolutional neural network with 2 convolutional layers whose feature maps represented spatial and temporal features of event-related potential. We have found that nonilliterate subjects' ERP show high correlation between occipital lobe and parietal lobe, whereas illiterate subjects only show correlation between neural activities from frontal lobe and central lobe. The nonilliterates showed peaks in P300, P500, and P700, whereas illiterates mostly showed peaks in around P700. P700 was strong in both subjects. We found that P700 peak may be the key feature of ERP as it appears in both illiterate and nonilliterate subjects.

Spatial and Time Domain Feature of ERP Speller System Extracted via Convolutional Neural Network

PubMed Central

2018-01-01

Feature of event-related potential (ERP) has not been completely understood and illiteracy problem remains unsolved. To this end, P300 peak has been used as the feature of ERP in most brain–computer interface applications, but subjects who do not show such peak are common. Recent development of convolutional neural network provides a way to analyze spatial and temporal features of ERP. Here, we train the convolutional neural network with 2 convolutional layers whose feature maps represented spatial and temporal features of event-related potential. We have found that nonilliterate subjects' ERP show high correlation between occipital lobe and parietal lobe, whereas illiterate subjects only show correlation between neural activities from frontal lobe and central lobe. The nonilliterates showed peaks in P300, P500, and P700, whereas illiterates mostly showed peaks in around P700. P700 was strong in both subjects. We found that P700 peak may be the key feature of ERP as it appears in both illiterate and nonilliterate subjects.

Style-based classification of Chinese ink and wash paintings

NASA Astrophysics Data System (ADS)

Sheng, Jiachuan; Jiang, Jianmin

2013-09-01

Following the fact that a large collection of ink and wash paintings (IWP) is being digitized and made available on the Internet, their automated content description, analysis, and management are attracting attention across research communities. While existing research in relevant areas is primarily focused on image processing approaches, a style-based algorithm is proposed to classify IWPs automatically by their authors. As IWPs do not have colors or even tones, the proposed algorithm applies edge detection to locate the local region and detect painting strokes to enable histogram-based feature extraction and capture of important cues to reflect the styles of different artists. Such features are then applied to drive a number of neural networks in parallel to complete the classification, and an information entropy balanced fusion is proposed to make an integrated decision for the multiple neural network classification results in which the entropy is used as a pointer to combine the global and local features. Evaluations via experiments support that the proposed algorithm achieves good performances, providing excellent potential for computerized analysis and management of IWPs.

Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network.

PubMed

Prasoon, Adhish; Petersen, Kersten; Igel, Christian; Lauze, François; Dam, Erik; Nielsen, Mads

2013-01-01

Segmentation of anatomical structures in medical images is often based on a voxel/pixel classification approach. Deep learning systems, such as convolutional neural networks (CNNs), can infer a hierarchical representation of images that fosters categorization. We propose a novel system for voxel classification integrating three 2D CNNs, which have a one-to-one association with the xy, yz and zx planes of 3D image, respectively. We applied our method to the segmentation of tibial cartilage in low field knee MRI scans and tested it on 114 unseen scans. Although our method uses only 2D features at a single scale, it performs better than a state-of-the-art method using 3D multi-scale features. In the latter approach, the features and the classifier have been carefully adapted to the problem at hand. That we were able to get better results by a deep learning architecture that autonomously learns the features from the images is the main insight of this study.

Identification and interpretation of patterns in rocket engine data: Artificial intelligence and neural network approaches

NASA Technical Reports Server (NTRS)

Ali, Moonis; Whitehead, Bruce; Gupta, Uday K.; Ferber, Harry

1989-01-01

This paper describes an expert system which is designed to perform automatic data analysis, identify anomalous events, and determine the characteristic features of these events. We have employed both artificial intelligence and neural net approaches in the design of this expert system. The artificial intelligence approach is useful because it provides (1) the use of human experts' knowledge of sensor behavior and faulty engine conditions in interpreting data; (2) the use of engine design knowledge and physical sensor locations in establishing relationships among the events of multiple sensors; (3) the use of stored analysis of past data of faulty engine conditions; and (4) the use of knowledge-based reasoning in distinguishing sensor failure from actual faults. The neural network approach appears promising because neural nets (1) can be trained on extremely noisy data and produce classifications which are more robust under noisy conditions than other classification techniques; (2) avoid the necessity of noise removal by digital filtering and therefore avoid the need to make assumptions about frequency bands or other signal characteristics of anomalous behavior; (3) can, in effect, generate their own feature detectors based on the characteristics of the sensor data used in training; and (4) are inherently parallel and therefore are potentially implementable in special-purpose parallel hardware.

Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images.

PubMed

Rajaraman, Sivaramakrishnan; Antani, Sameer K; Poostchi, Mahdieh; Silamut, Kamolrat; Hossain, Md A; Maude, Richard J; Jaeger, Stefan; Thoma, George R

2018-01-01

Malaria is a blood disease caused by the Plasmodium parasites transmitted through the bite of female Anopheles mosquito. Microscopists commonly examine thick and thin blood smears to diagnose disease and compute parasitemia. However, their accuracy depends on smear quality and expertise in classifying and counting parasitized and uninfected cells. Such an examination could be arduous for large-scale diagnoses resulting in poor quality. State-of-the-art image-analysis based computer-aided diagnosis (CADx) methods using machine learning (ML) techniques, applied to microscopic images of the smears using hand-engineered features demand expertise in analyzing morphological, textural, and positional variations of the region of interest (ROI). In contrast, Convolutional Neural Networks (CNN), a class of deep learning (DL) models promise highly scalable and superior results with end-to-end feature extraction and classification. Automated malaria screening using DL techniques could, therefore, serve as an effective diagnostic aid. In this study, we evaluate the performance of pre-trained CNN based DL models as feature extractors toward classifying parasitized and uninfected cells to aid in improved disease screening. We experimentally determine the optimal model layers for feature extraction from the underlying data. Statistical validation of the results demonstrates the use of pre-trained CNNs as a promising tool for feature extraction for this purpose.

Driver Fatigue Classification With Independent Component by Entropy Rate Bound Minimization Analysis in an EEG-Based System.

PubMed

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

2017-05-01

This paper presents a two-class electroencephal-ography-based classification for classifying of driver fatigue (fatigue state versus alert state) from 43 healthy participants. The system uses independent component by entropy rate bound minimization analysis (ERBM-ICA) for the source separation, autoregressive (AR) modeling for the features extraction, and Bayesian neural network for the classification algorithm. The classification results demonstrate a sensitivity of 89.7%, a specificity of 86.8%, and an accuracy of 88.2%. The combination of ERBM-ICA (source separator), AR (feature extractor), and Bayesian neural network (classifier) provides the best outcome with a p-value < 0.05 with the highest value of area under the receiver operating curve (AUC-ROC = 0.93) against other methods such as power spectral density as feature extractor (AUC-ROC = 0.81). The results of this study suggest the method could be utilized effectively for a countermeasure device for driver fatigue identification and other adverse event applications.

Knowledge Synthesis with Maps of Neural Connectivity

PubMed Central

Tallis, Marcelo; Thompson, Richard; Russ, Thomas A.; Burns, Gully A. P. C.

2011-01-01

This paper describes software for neuroanatomical knowledge synthesis based on neural connectivity data. This software supports a mature methodology developed since the early 1990s. Over this time, the Swanson laboratory at USC has generated an account of the neural connectivity of the sub-structures of the hypothalamus, amygdala, septum, hippocampus, and bed nucleus of the stria terminalis. This is based on neuroanatomical data maps drawn into a standard brain atlas by experts. In earlier work, we presented an application for visualizing and comparing anatomical macro connections using the Swanson third edition atlas as a framework for accurate registration. Here we describe major improvements to the NeuARt application based on the incorporation of a knowledge representation of experimental design. We also present improvements in the interface and features of the data mapping components within a unified web-application. As a step toward developing an accurate sub-regional account of neural connectivity, we provide navigational access between the data maps and a semantic representation of area-to-area connections that they support. We do so based on an approach called “Knowledge Engineering from Experimental Design” (KEfED) model that is based on experimental variables. We have extended the underlying KEfED representation of tract-tracing experiments by incorporating the definition of a neuronanatomical data map as a measurement variable in the study design. This paper describes the software design of a web-application that allows anatomical data sets to be described within a standard experimental context and thus indexed by non-spatial experimental design features. PMID:22053155

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.

Feature Extraction Using an Unsupervised Neural Network

DTIC Science & Technology

1991-05-03

with this neural netowrk is given and its connection to exploratory projection pursuit methods is established. DD I 2 P JA d 73 EDITIONj Of I NOV 6s...IS OBSOLETE $IN 0102- LF- 014- 6601 SECURITY CLASSIFICATION OF THIS PAGE (When Daoes Enlered) Feature Extraction using an Unsupervised Neural Network

View-invariant gait recognition method by three-dimensional convolutional neural network

NASA Astrophysics Data System (ADS)

Xing, Weiwei; Li, Ying; Zhang, Shunli

2018-01-01

Gait as an important biometric feature can identify a human at a long distance. View change is one of the most challenging factors for gait recognition. To address the cross view issues in gait recognition, we propose a view-invariant gait recognition method by three-dimensional (3-D) convolutional neural network. First, 3-D convolutional neural network (3DCNN) is introduced to learn view-invariant feature, which can capture the spatial information and temporal information simultaneously on normalized silhouette sequences. Second, a network training method based on cross-domain transfer learning is proposed to solve the problem of the limited gait training samples. We choose the C3D as the basic model, which is pretrained on the Sports-1M and then fine-tune C3D model to adapt gait recognition. In the recognition stage, we use the fine-tuned model to extract gait features and use Euclidean distance to measure the similarity of gait sequences. Sufficient experiments are carried out on the CASIA-B dataset and the experimental results demonstrate that our method outperforms many other methods.

Predicting Response to Neoadjuvant Chemotherapy with PET Imaging Using Convolutional Neural Networks

PubMed Central

Ypsilantis, Petros-Pavlos; Siddique, Musib; Sohn, Hyon-Mok; Davies, Andrew; Cook, Gary; Goh, Vicky; Montana, Giovanni

2015-01-01

Imaging of cancer with 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) has become a standard component of diagnosis and staging in oncology, and is becoming more important as a quantitative monitor of individual response to therapy. In this article we investigate the challenging problem of predicting a patient’s response to neoadjuvant chemotherapy from a single 18F-FDG PET scan taken prior to treatment. We take a “radiomics” approach whereby a large amount of quantitative features is automatically extracted from pretherapy PET images in order to build a comprehensive quantification of the tumor phenotype. While the dominant methodology relies on hand-crafted texture features, we explore the potential of automatically learning low- to high-level features directly from PET scans. We report on a study that compares the performance of two competing radiomics strategies: an approach based on state-of-the-art statistical classifiers using over 100 quantitative imaging descriptors, including texture features as well as standardized uptake values, and a convolutional neural network, 3S-CNN, trained directly from PET scans by taking sets of adjacent intra-tumor slices. Our experimental results, based on a sample of 107 patients with esophageal cancer, provide initial evidence that convolutional neural networks have the potential to extract PET imaging representations that are highly predictive of response to therapy. On this dataset, 3S-CNN achieves an average 80.7% sensitivity and 81.6% specificity in predicting non-responders, and outperforms other competing predictive models. PMID:26355298

A neuro-fuzzy architecture for real-time applications

NASA Technical Reports Server (NTRS)

Ramamoorthy, P. A.; Huang, Song

1992-01-01

Neural networks and fuzzy expert systems perform the same task of functional mapping using entirely different approaches. Each approach has certain unique features. The ability to learn specific input-output mappings from large input/output data possibly corrupted by noise and the ability to adapt or continue learning are some important features of neural networks. Fuzzy expert systems are known for their ability to deal with fuzzy information and incomplete/imprecise data in a structured, logical way. Since both of these techniques implement the same task (that of functional mapping--we regard 'inferencing' as one specific category under this class), a fusion of the two concepts that retains their unique features while overcoming their individual drawbacks will have excellent applications in the real world. In this paper, we arrive at a new architecture by fusing the two concepts. The architecture has the trainability/adaptibility (based on input/output observations) property of the neural networks and the architectural features that are unique to fuzzy expert systems. It also does not require specific information such as fuzzy rules, defuzzification procedure used, etc., though any such information can be integrated into the architecture. We show that this architecture can provide better performance than is possible from a single two or three layer feedforward neural network. Further, we show that this new architecture can be used as an efficient vehicle for hardware implementation of complex fuzzy expert systems for real-time applications. A numerical example is provided to show the potential of this approach.

PSF estimation for defocus blurred image based on quantum back-propagation neural network

NASA Astrophysics Data System (ADS)

Gao, Kun; Zhang, Yan; Shao, Xiao-guang; Liu, Ying-hui; Ni, Guoqiang

2010-11-01

Images obtained by an aberration-free system are defocused blur due to motion in depth and/or zooming. The precondition of restoring the degraded image is to estimate point spread function (PSF) of the imaging system as precisely as possible. But it is difficult to identify the analytic model of PSF precisely due to the complexity of the degradation process. Inspired by the similarity between the quantum process and imaging process in the probability and statistics fields, one reformed multilayer quantum neural network (QNN) is proposed to estimate PSF of the defocus blurred image. Different from the conventional artificial neural network (ANN), an improved quantum neuron model is used in the hidden layer instead, which introduces a 2-bit controlled NOT quantum gate to control output and adopts 2 texture and edge features as the input vectors. The supervised back-propagation learning rule is adopted to train network based on training sets from the historical images. Test results show that this method owns excellent features of high precision and strong generalization ability.

A neural network approach to lung nodule segmentation

NASA Astrophysics Data System (ADS)

Hu, Yaoxiu; Menon, Prahlad G.

2016-03-01

Computed tomography (CT) imaging is a sensitive and specific lung cancer screening tool for the high-risk population and shown to be promising for detection of lung cancer. This study proposes an automatic methodology for detecting and segmenting lung nodules from CT images. The proposed methods begin with thorax segmentation, lung extraction and reconstruction of the original shape of the parenchyma using morphology operations. Next, a multi-scale hessian-based vesselness filter is applied to extract lung vasculature in lung. The lung vasculature mask is subtracted from the lung region segmentation mask to extract 3D regions representing candidate pulmonary nodules. Finally, the remaining structures are classified as nodules through shape and intensity features which are together used to train an artificial neural network. Up to 75% sensitivity and 98% specificity was achieved for detection of lung nodules in our testing dataset, with an overall accuracy of 97.62%+/-0.72% using 11 selected features as input to the neural network classifier, based on 4-fold cross-validation studies. Receiver operator characteristics for identifying nodules revealed an area under curve of 0.9476.

An implementation of Elman neural network for polycystic ovary classification based on ultrasound images

NASA Astrophysics Data System (ADS)

Thufailah, I. F.; Adiwijaya; Wisesty, U. N.; Jondri

2018-03-01

Polycystic Ovary Syndrome (PCOS) is a reproduction problem that causes irregular menstruation period. Insulin and androgen hormone have big roles for this problem. This syndrome should be detected shortly, since it is able to cause a more serious disease, such as cardiovascular, diabetes, and obesity. The detection of this syndrome is done by analyzing ovary morphology and hormone test. However, the more economical way of test is by identifying the ovary morphology using ultrasonography. To classify whether one ovary is normal or it has polycystic ovary (PCO) follicle, the analysis will be done manually by a gynecologist. This paper will design a system to detect PCO using Gabor Wavelet method for feature extraction and Elman Neural Network is used to classify PCO and non-PCO. Elman Neural Network is chosen because it contains context layer to recall the previous condition. This paper compared the accuracy and process time of each dataset, then also did testing on elman’s parameters, such as layer delay, hidden layer, and training function. Based on tests done in this paper, the most accurate number is 78.1% with 32 features.

Vehicle Detection in Aerial Images Based on Region Convolutional Neural Networks and Hard Negative Example Mining.

PubMed

Tang, Tianyu; Zhou, Shilin; Deng, Zhipeng; Zou, Huanxin; Lei, Lin

2017-02-10

Detecting vehicles in aerial imagery plays an important role in a wide range of applications. The current vehicle detection methods are mostly based on sliding-window search and handcrafted or shallow-learning-based features, having limited description capability and heavy computational costs. Recently, due to the powerful feature representations, region convolutional neural networks (CNN) based detection methods have achieved state-of-the-art performance in computer vision, especially Faster R-CNN. However, directly using it for vehicle detection in aerial images has many limitations: (1) region proposal network (RPN) in Faster R-CNN has poor performance for accurately locating small-sized vehicles, due to the relatively coarse feature maps; and (2) the classifier after RPN cannot distinguish vehicles and complex backgrounds well. In this study, an improved detection method based on Faster R-CNN is proposed in order to accomplish the two challenges mentioned above. Firstly, to improve the recall, we employ a hyper region proposal network (HRPN) to extract vehicle-like targets with a combination of hierarchical feature maps. Then, we replace the classifier after RPN by a cascade of boosted classifiers to verify the candidate regions, aiming at reducing false detection by negative example mining. We evaluate our method on the Munich vehicle dataset and the collected vehicle dataset, with improvements in accuracy and robustness compared to existing methods.

Automated target recognition and tracking using an optical pattern recognition neural network

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin

1991-01-01

The on-going development of an automatic target recognition and tracking system at the Jet Propulsion Laboratory is presented. This system is an optical pattern recognition neural network (OPRNN) that is an integration of an innovative optical parallel processor and a feature extraction based neural net training algorithm. The parallel optical processor provides high speed and vast parallelism as well as full shift invariance. The neural network algorithm enables simultaneous discrimination of multiple noisy targets in spite of their scales, rotations, perspectives, and various deformations. This fully developed OPRNN system can be effectively utilized for the automated spacecraft recognition and tracking that will lead to success in the Automated Rendezvous and Capture (AR&C) of the unmanned Cargo Transfer Vehicle (CTV). One of the most powerful optical parallel processors for automatic target recognition is the multichannel correlator. With the inherent advantages of parallel processing capability and shift invariance, multiple objects can be simultaneously recognized and tracked using this multichannel correlator. This target tracking capability can be greatly enhanced by utilizing a powerful feature extraction based neural network training algorithm such as the neocognitron. The OPRNN, currently under investigation at JPL, is constructed with an optical multichannel correlator where holographic filters have been prepared using the neocognitron training algorithm. The computation speed of the neocognitron-type OPRNN is up to 10(exp 14) analog connections/sec that enabling the OPRNN to outperform its state-of-the-art electronics counterpart by at least two orders of magnitude.

Deep feature representation with stacked sparse auto-encoder and convolutional neural network for hyperspectral imaging-based detection of cucumber defects

USDA-ARS?s Scientific Manuscript database

It is challenging to achieve rapid and accurate processing of large amounts of hyperspectral image data. This research was aimed to develop a novel classification method by employing deep feature representation with the stacked sparse auto-encoder (SSAE) and the SSAE combined with convolutional neur...

A novel wavelet neural network based pathological stage detection technique for an oral precancerous condition

PubMed Central

Paul, R R; Mukherjee, A; Dutta, P K; Banerjee, S; Pal, M; Chatterjee, J; Chaudhuri, K; Mukkerjee, K

2005-01-01

Aim: To describe a novel neural network based oral precancer (oral submucous fibrosis; OSF) stage detection method. Method: The wavelet coefficients of transmission electron microscopy images of collagen fibres from normal oral submucosa and OSF tissues were used to choose the feature vector which, in turn, was used to train the artificial neural network. Results: The trained network was able to classify normal and oral precancer stages (less advanced and advanced) after obtaining the image as an input. Conclusions: The results obtained from this proposed technique were promising and suggest that with further optimisation this method could be used to detect and stage OSF, and could be adapted for other conditions. PMID:16126873

Particle identification with neural networks using a rotational invariant moment representation

NASA Astrophysics Data System (ADS)

Sinkus, R.; Voss, T.

1997-02-01

A feed-forward neural network is used to identify electromagnetic particles based upon their showering properties within a segmented calorimeter. The novel feature is the expansion of the energy distribution in terms of moments of the so-called Zernike functions which are invariant under rotation. The multidimensional input distribution for the neural network is transformed via a principle component analysis and rescaled by its respective variances to ensure input values of the order of one. This results is a better performance in identifying and separating electromagnetic from hadronic particles, especially at low energies.

Neural Systems with Numerically Matched Input-Output Statistic: Isotonic Bivariate Statistical Modeling

PubMed Central

Fiori, Simone

2007-01-01

Bivariate statistical modeling from incomplete data is a useful statistical tool that allows to discover the model underlying two data sets when the data in the two sets do not correspond in size nor in ordering. Such situation may occur when the sizes of the two data sets do not match (i.e., there are “holes” in the data) or when the data sets have been acquired independently. Also, statistical modeling is useful when the amount of available data is enough to show relevant statistical features of the phenomenon underlying the data. We propose to tackle the problem of statistical modeling via a neural (nonlinear) system that is able to match its input-output statistic to the statistic of the available data sets. A key point of the new implementation proposed here is that it is based on look-up-table (LUT) neural systems, which guarantee a computationally advantageous way of implementing neural systems. A number of numerical experiments, performed on both synthetic and real-world data sets, illustrate the features of the proposed modeling procedure. PMID:18566641

Neural-network classifiers for automatic real-world aerial image recognition

NASA Astrophysics Data System (ADS)

Greenberg, Shlomo; Guterman, Hugo

1996-08-01

We describe the application of the multilayer perceptron (MLP) network and a version of the adaptive resonance theory version 2-A (ART 2-A) network to the problem of automatic aerial image recognition (AAIR). The classification of aerial images, independent of their positions and orientations, is required for automatic tracking and target recognition. Invariance is achieved by the use of different invariant feature spaces in combination with supervised and unsupervised neural networks. The performance of neural-network-based classifiers in conjunction with several types of invariant AAIR global features, such as the Fourier-transform space, Zernike moments, central moments, and polar transforms, are examined. The advantages of this approach are discussed. The performance of the MLP network is compared with that of a classical correlator. The MLP neural-network correlator outperformed the binary phase-only filter (BPOF) correlator. It was found that the ART 2-A distinguished itself with its speed and its low number of required training vectors. However, only the MLP classifier was able to deal with a combination of shift and rotation geometric distortions.

Neural-network classifiers for automatic real-world aerial image recognition.

PubMed

Greenberg, S; Guterman, H

1996-08-10

We describe the application of the multilayer perceptron (MLP) network and a version of the adaptive resonance theory version 2-A (ART 2-A) network to the problem of automatic aerial image recognition (AAIR). The classification of aerial images, independent of their positions and orientations, is required for automatic tracking and target recognition. Invariance is achieved by the use of different invariant feature spaces in combination with supervised and unsupervised neural networks. The performance of neural-network-based classifiers in conjunction with several types of invariant AAIR global features, such as the Fourier-transform space, Zernike moments, central moments, and polar transforms, are examined. The advantages of this approach are discussed. The performance of the MLP network is compared with that of a classical correlator. The MLP neural-network correlator outperformed the binary phase-only filter (BPOF) correlator. It was found that the ART 2-A distinguished itself with its speed and its low number of required training vectors. However, only the MLP classifier was able to deal with a combination of shift and rotation geometric distortions.

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

The Role of Competitive Inhibition and Top-Down Feedback in Binding during Object Recognition

PubMed Central

Wyatte, Dean; Herd, Seth; Mingus, Brian; O’Reilly, Randall

2012-01-01

How does the brain bind together visual features that are processed concurrently by different neurons into a unified percept suitable for processes such as object recognition? Here, we describe how simple, commonly accepted principles of neural processing can interact over time to solve the brain’s binding problem. We focus on mechanisms of neural inhibition and top-down feedback. Specifically, we describe how inhibition creates competition among neural populations that code different features, effectively suppressing irrelevant information, and thus minimizing illusory conjunctions. Top-down feedback contributes to binding in a similar manner, but by reinforcing relevant features. Together, inhibition and top-down feedback contribute to a competitive environment that ensures only the most appropriate features are bound together. We demonstrate this overall proposal using a biologically realistic neural model of vision that processes features across a hierarchy of interconnected brain areas. Finally, we argue that temporal synchrony plays only a limited role in binding – it does not simultaneously bind multiple objects, but does aid in creating additional contrast between relevant and irrelevant features. Thus, our overall theory constitutes a solution to the binding problem that relies only on simple neural principles without any binding-specific processes. PMID:22719733

Can responses to basic non-numerical visual features explain neural numerosity responses?

PubMed

Harvey, Ben M; Dumoulin, Serge O

2017-04-01

Humans and many animals can distinguish between stimuli that differ in numerosity, the number of objects in a set. Human and macaque parietal lobes contain neurons that respond to changes in stimulus numerosity. However, basic non-numerical visual features can affect neural responses to and perception of numerosity, and visual features often co-vary with numerosity. Therefore, it is debated whether numerosity or co-varying low-level visual features underlie neural and behavioral responses to numerosity. To test the hypothesis that non-numerical visual features underlie neural numerosity responses in a human parietal numerosity map, we analyze responses to a group of numerosity stimulus configurations that have the same numerosity progression but vary considerably in their non-numerical visual features. Using ultra-high-field (7T) fMRI, we measure responses to these stimulus configurations in an area of posterior parietal cortex whose responses are believed to reflect numerosity-selective activity. We describe an fMRI analysis method to distinguish between alternative models of neural response functions, following a population receptive field (pRF) modeling approach. For each stimulus configuration, we first quantify the relationships between numerosity and several non-numerical visual features that have been proposed to underlie performance in numerosity discrimination tasks. We then determine how well responses to these non-numerical visual features predict the observed fMRI responses, and compare this to the predictions of responses to numerosity. We demonstrate that a numerosity response model predicts observed responses more accurately than models of responses to simple non-numerical visual features. As such, neural responses in cognitive processing need not reflect simpler properties of early sensory inputs. Copyright © 2017 Elsevier Inc. All rights reserved.

Research on improving image recognition robustness by combining multiple features with associative memory

NASA Astrophysics Data System (ADS)

Guo, Dongwei; Wang, Zhe

2018-05-01

Convolutional neural networks (CNN) achieve great success in computer vision, it can learn hierarchical representation from raw pixels and has outstanding performance in various image recognition tasks [1]. However, CNN is easy to be fraudulent in terms of it is possible to produce images totally unrecognizable to human eyes that CNNs believe with near certainty are familiar objects. [2]. In this paper, an associative memory model based on multiple features is proposed. Within this model, feature extraction and classification are carried out by CNN, T-SNE and exponential bidirectional associative memory neural network (EBAM). The geometric features extracted from CNN and the digital features extracted from T-SNE are associated by EBAM. Thus we ensure the recognition of robustness by a comprehensive assessment of the two features. In our model, we can get only 8% error rate with fraudulent data. In systems that require a high safety factor or some key areas, strong robustness is extremely important, if we can ensure the image recognition robustness, network security will be greatly improved and the social production efficiency will be extremely enhanced.

Electroencephalography Based Fusion Two-Dimensional (2D)-Convolution Neural Networks (CNN) Model for Emotion Recognition System.

PubMed

Kwon, Yea-Hoon; Shin, Sae-Byuk; Kim, Shin-Dug

2018-04-30

The purpose of this study is to improve human emotional classification accuracy using a convolution neural networks (CNN) model and to suggest an overall method to classify emotion based on multimodal data. We improved classification performance by combining electroencephalogram (EEG) and galvanic skin response (GSR) signals. GSR signals are preprocessed using by the zero-crossing rate. Sufficient EEG feature extraction can be obtained through CNN. Therefore, we propose a suitable CNN model for feature extraction by tuning hyper parameters in convolution filters. The EEG signal is preprocessed prior to convolution by a wavelet transform while considering time and frequency simultaneously. We use a database for emotion analysis using the physiological signals open dataset to verify the proposed process, achieving 73.4% accuracy, showing significant performance improvement over the current best practice models.

An effective convolutional neural network model for Chinese sentiment analysis

NASA Astrophysics Data System (ADS)

Zhang, Yu; Chen, Mengdong; Liu, Lianzhong; Wang, Yadong

2017-06-01

Nowadays microblog is getting more and more popular. People are increasingly accustomed to expressing their opinions on Twitter, Facebook and Sina Weibo. Sentiment analysis of microblog has received significant attention, both in academia and in industry. So far, Chinese microblog exploration still needs lots of further work. In recent years CNN has also been used to deal with NLP tasks, and already achieved good results. However, these methods ignore the effective use of a large number of existing sentimental resources. For this purpose, we propose a Lexicon-based Sentiment Convolutional Neural Networks (LSCNN) model focus on Weibo's sentiment analysis, which combines two CNNs, trained individually base on sentiment features and word embedding, at the fully connected hidden layer. The experimental results show that our model outperforms the CNN model only with word embedding features on microblog sentiment analysis task.

Neural network and SVM classifiers accurately predict lipid binding proteins, irrespective of sequence homology.

PubMed

Bakhtiarizadeh, Mohammad Reza; Moradi-Shahrbabak, Mohammad; Ebrahimi, Mansour; Ebrahimie, Esmaeil

2014-09-07

Due to the central roles of lipid binding proteins (LBPs) in many biological processes, sequence based identification of LBPs is of great interest. The major challenge is that LBPs are diverse in sequence, structure, and function which results in low accuracy of sequence homology based methods. Therefore, there is a need for developing alternative functional prediction methods irrespective of sequence similarity. To identify LBPs from non-LBPs, the performances of support vector machine (SVM) and neural network were compared in this study. Comprehensive protein features and various techniques were employed to create datasets. Five-fold cross-validation (CV) and independent evaluation (IE) tests were used to assess the validity of the two methods. The results indicated that SVM outperforms neural network. SVM achieved 89.28% (CV) and 89.55% (IE) overall accuracy in identification of LBPs from non-LBPs and 92.06% (CV) and 92.90% (IE) (in average) for classification of different LBPs classes. Increasing the number and the range of extracted protein features as well as optimization of the SVM parameters significantly increased the efficiency of LBPs class prediction in comparison to the only previous report in this field. Altogether, the results showed that the SVM algorithm can be run on broad, computationally calculated protein features and offers a promising tool in detection of LBPs classes. The proposed approach has the potential to integrate and improve the common sequence alignment based methods. Copyright © 2014 Elsevier Ltd. All rights reserved.

Nonsinusoidal Beta Oscillations Reflect Cortical Pathophysiology in Parkinson's Disease.

PubMed

Cole, Scott R; van der Meij, Roemer; Peterson, Erik J; de Hemptinne, Coralie; Starr, Philip A; Voytek, Bradley

2017-05-03

Oscillations in neural activity play a critical role in neural computation and communication. There is intriguing new evidence that the nonsinusoidal features of the oscillatory waveforms may inform underlying physiological and pathophysiological characteristics. Time-domain waveform analysis approaches stand in contrast to traditional Fourier-based methods, which alter or destroy subtle waveform features. Recently, it has been shown that the waveform features of oscillatory beta (13-30 Hz) events, a prominent motor cortical oscillation, may reflect near-synchronous excitatory synaptic inputs onto cortical pyramidal neurons. Here we analyze data from invasive human primary motor cortex (M1) recordings from patients with Parkinson's disease (PD) implanted with a deep brain stimulator (DBS) to test the hypothesis that the beta waveform becomes less sharp with DBS, suggesting that M1 input synchrony may be decreased. We find that, in PD, M1 beta oscillations have sharp, asymmetric, nonsinusoidal features, specifically asymmetries in the ratio between the sharpness of the beta peaks compared with the troughs. This waveform feature is nearly perfectly correlated with beta-high gamma phase-amplitude coupling ( r = 0.94), a neural index previously shown to track PD-related motor deficit. Our results suggest that the pathophysiological beta generator is altered by DBS, smoothing out the beta waveform. This has implications not only for the interpretation of the physiological mechanism by which DBS reduces PD-related motor symptoms, but more broadly for our analytic toolkit in general. That is, the often-overlooked time-domain features of oscillatory waveforms may carry critical physiological information about neural processes and dynamics. SIGNIFICANCE STATEMENT To better understand the neural basis of cognition and disease, we need to understand how groups of neurons interact to communicate with one another. For example, there is evidence that parkinsonian bradykinesia and rigidity may arise from an oversynchronization of afferents to the motor cortex, and that these symptoms are treatable using deep brain stimulation. Here we show that the waveform shape of beta (13-30 Hz) oscillations, which may reflect input synchrony onto the cortex, is altered by deep brain stimulation. This suggests that mechanistic inferences regarding physiological and pathophysiological neural communication may be made from the temporal dynamics of oscillatory waveform shape. Copyright © 2017 the authors 0270-6474/17/374830-11$15.00/0.

Residual Shuffling Convolutional Neural Networks for Deep Semantic Image Segmentation Using Multi-Modal Data

NASA Astrophysics Data System (ADS)

Chen, K.; Weinmann, M.; Gao, X.; Yan, M.; Hinz, S.; Jutzi, B.; Weinmann, M.

2018-05-01

In this paper, we address the deep semantic segmentation of aerial imagery based on multi-modal data. Given multi-modal data composed of true orthophotos and the corresponding Digital Surface Models (DSMs), we extract a variety of hand-crafted radiometric and geometric features which are provided separately and in different combinations as input to a modern deep learning framework. The latter is represented by a Residual Shuffling Convolutional Neural Network (RSCNN) combining the characteristics of a Residual Network with the advantages of atrous convolution and a shuffling operator to achieve a dense semantic labeling. Via performance evaluation on a benchmark dataset, we analyze the value of different feature sets for the semantic segmentation task. The derived results reveal that the use of radiometric features yields better classification results than the use of geometric features for the considered dataset. Furthermore, the consideration of data on both modalities leads to an improvement of the classification results. However, the derived results also indicate that the use of all defined features is less favorable than the use of selected features. Consequently, data representations derived via feature extraction and feature selection techniques still provide a gain if used as the basis for deep semantic segmentation.

Chinese wine classification system based on micrograph using combination of shape and structure features

NASA Astrophysics Data System (ADS)

Wan, Yi

2011-06-01

Chinese wines can be classification or graded by the micrographs. Micrographs of Chinese wines show floccules, stick and granule of variant shape and size. Different wines have variant microstructure and micrographs, we study the classification of Chinese wines based on the micrographs. Shape and structure of wines' particles in microstructure is the most important feature for recognition and classification of wines. So we introduce a feature extraction method which can describe the structure and region shape of micrograph efficiently. First, the micrographs are enhanced using total variation denoising, and segmented using a modified Otsu's method based on the Rayleigh Distribution. Then features are extracted using proposed method in the paper based on area, perimeter and traditional shape feature. Eight kinds total 26 features are selected. Finally, Chinese wine classification system based on micrograph using combination of shape and structure features and BP neural network have been presented. We compare the recognition results for different choices of features (traditional shape features or proposed features). The experimental results show that the better classification rate have been achieved using the combinational features proposed in this paper.

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.

Classification and pose estimation of objects using nonlinear features

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.

1998-03-01

A new nonlinear feature extraction method called the maximum representation and discrimination feature (MRDF) method is presented for extraction of features from input image data. It implements transformations similar to the Sigma-Pi neural network. However, the weights of the MRDF are obtained in closed form, and offer advantages compared to nonlinear neural network implementations. The features extracted are useful for both object discrimination (classification) and object representation (pose estimation). We show its use in estimating the class and pose of images of real objects and rendered solid CAD models of machine parts from single views using a feature-space trajectory (FST) neural network classifier. We show more accurate classification and pose estimation results than are achieved by standard principal component analysis (PCA) and Fukunaga-Koontz (FK) feature extraction methods.

Explaining seeing? Disentangling qualia from perceptual organization.

PubMed

Ibáñez, Agustin; Bekinschtein, Tristan

2010-09-01

Abstract Visual perception and integration seem to play an essential role in our conscious phenomenology. Relatively local neural processing of reentrant nature may explain several visual integration processes (feature binding or figure-ground segregation, object recognition, inference, competition), even without attention or cognitive control. Based on the above statements, should the neural signatures of visual integration (via reentrant process) be non-reportable phenomenological qualia? We argue that qualia are not required to understand this perceptual organization.

Task-induced frequency modulation features for brain-computer interfacing

NASA Astrophysics Data System (ADS)

Jayaram, Vinay; Hohmann, Matthias; Just, Jennifer; Schölkopf, Bernhard; Grosse-Wentrup, Moritz

2017-10-01

Objective. Task-induced amplitude modulation of neural oscillations is routinely used in brain-computer interfaces (BCIs) for decoding subjects’ intents, and underlies some of the most robust and common methods in the field, such as common spatial patterns and Riemannian geometry. While there has been some interest in phase-related features for classification, both techniques usually presuppose that the frequencies of neural oscillations remain stable across various tasks. We investigate here whether features based on task-induced modulation of the frequency of neural oscillations enable decoding of subjects’ intents with an accuracy comparable to task-induced amplitude modulation. Approach. We compare cross-validated classification accuracies using the amplitude and frequency modulated features, as well as a joint feature space, across subjects in various paradigms and pre-processing conditions. We show results with a motor imagery task, a cognitive task, and also preliminary results in patients with amyotrophic lateral sclerosis (ALS), as well as using common spatial patterns and Laplacian filtering. Main results. The frequency features alone do not significantly out-perform traditional amplitude modulation features, and in some cases perform significantly worse. However, across both tasks and pre-processing in healthy subjects the joint space significantly out-performs either the frequency or amplitude features alone. This result only does not hold for ALS patients, for whom the dataset is of insufficient size to draw any statistically significant conclusions. Significance. Task-induced frequency modulation is robust and straight forward to compute, and increases performance when added to standard amplitude modulation features across paradigms. This allows more information to be extracted from the EEG signal cheaply and can be used throughout the field of BCIs.

Firing rate dynamics in recurrent spiking neural networks with intrinsic and network heterogeneity.

PubMed

Ly, Cheng

2015-12-01

Heterogeneity of neural attributes has recently gained a lot of attention and is increasing recognized as a crucial feature in neural processing. Despite its importance, this physiological feature has traditionally been neglected in theoretical studies of cortical neural networks. Thus, there is still a lot unknown about the consequences of cellular and circuit heterogeneity in spiking neural networks. In particular, combining network or synaptic heterogeneity and intrinsic heterogeneity has yet to be considered systematically despite the fact that both are known to exist and likely have significant roles in neural network dynamics. In a canonical recurrent spiking neural network model, we study how these two forms of heterogeneity lead to different distributions of excitatory firing rates. To analytically characterize how these types of heterogeneities affect the network, we employ a dimension reduction method that relies on a combination of Monte Carlo simulations and probability density function equations. We find that the relationship between intrinsic and network heterogeneity has a strong effect on the overall level of heterogeneity of the firing rates. Specifically, this relationship can lead to amplification or attenuation of firing rate heterogeneity, and these effects depend on whether the recurrent network is firing asynchronously or rhythmically firing. These observations are captured with the aforementioned reduction method, and furthermore simpler analytic descriptions based on this dimension reduction method are developed. The final analytic descriptions provide compact and descriptive formulas for how the relationship between intrinsic and network heterogeneity determines the firing rate heterogeneity dynamics in various settings.

Predicting membrane protein types by fusing composite protein sequence features into pseudo amino acid composition.

PubMed

Hayat, Maqsood; Khan, Asifullah

2011-02-21

Membrane proteins are vital type of proteins that serve as channels, receptors, and energy transducers in a cell. Prediction of membrane protein types is an important research area in bioinformatics. Knowledge of membrane protein types provides some valuable information for predicting novel example of the membrane protein types. However, classification of membrane protein types can be both time consuming and susceptible to errors due to the inherent similarity of membrane protein types. In this paper, neural networks based membrane protein type prediction system is proposed. Composite protein sequence representation (CPSR) is used to extract the features of a protein sequence, which includes seven feature sets; amino acid composition, sequence length, 2 gram exchange group frequency, hydrophobic group, electronic group, sum of hydrophobicity, and R-group. Principal component analysis is then employed to reduce the dimensionality of the feature vector. The probabilistic neural network (PNN), generalized regression neural network, and support vector machine (SVM) are used as classifiers. A high success rate of 86.01% is obtained using SVM for the jackknife test. In case of independent dataset test, PNN yields the highest accuracy of 95.73%. These classifiers exhibit improved performance using other performance measures such as sensitivity, specificity, Mathew's correlation coefficient, and F-measure. The experimental results show that the prediction performance of the proposed scheme for classifying membrane protein types is the best reported, so far. This performance improvement may largely be credited to the learning capabilities of neural networks and the composite feature extraction strategy, which exploits seven different properties of protein sequences. The proposed Mem-Predictor can be accessed at http://111.68.99.218/Mem-Predictor. Copyright © 2010 Elsevier Ltd. All rights reserved.

Deep convolutional neural network for mammographic density segmentation

NASA Astrophysics Data System (ADS)

Wei, Jun; Li, Songfeng; Chan, Heang-Ping; Helvie, Mark A.; Roubidoux, Marilyn A.; Lu, Yao; Zhou, Chuan; Hadjiiski, Lubomir; Samala, Ravi K.

2018-02-01

Breast density is one of the most significant factors for cancer risk. In this study, we proposed a supervised deep learning approach for automated estimation of percentage density (PD) on digital mammography (DM). The deep convolutional neural network (DCNN) was trained to estimate a probability map of breast density (PMD). PD was calculated as the ratio of the dense area to the breast area based on the probability of each pixel belonging to dense region or fatty region at a decision threshold of 0.5. The DCNN estimate was compared to a feature-based statistical learning approach, in which gray level, texture and morphological features were extracted from each ROI and the least absolute shrinkage and selection operator (LASSO) was used to select and combine the useful features to generate the PMD. The reference PD of each image was provided by two experienced MQSA radiologists. With IRB approval, we retrospectively collected 347 DMs from patient files at our institution. The 10-fold cross-validation results showed a strong correlation r=0.96 between the DCNN estimation and interactive segmentation by radiologists while that of the feature-based statistical learning approach vs radiologists' segmentation had a correlation r=0.78. The difference between the segmentation by DCNN and by radiologists was significantly smaller than that between the feature-based learning approach and radiologists (p < 0.0001) by two-tailed paired t-test. This study demonstrated that the DCNN approach has the potential to replace radiologists' interactive thresholding in PD estimation on DMs.

Computerized Classification of Pneumoconiosis on Digital Chest Radiography Artificial Neural Network with Three Stages.

PubMed

Okumura, Eiichiro; Kawashita, Ikuo; Ishida, Takayuki

2017-08-01

It is difficult for radiologists to classify pneumoconiosis from category 0 to category 3 on chest radiographs. Therefore, we have developed a computer-aided diagnosis (CAD) system based on a three-stage artificial neural network (ANN) method for classification based on four texture features. The image database consists of 36 chest radiographs classified as category 0 to category 3. Regions of interest (ROIs) with a matrix size of 32 × 32 were selected from chest radiographs. We obtained a gray-level histogram, histogram of gray-level difference, gray-level run-length matrix (GLRLM) feature image, and gray-level co-occurrence matrix (GLCOM) feature image in each ROI. For ROI-based classification, the first ANN was trained with each texture feature. Next, the second ANN was trained with output patterns obtained from the first ANN. Finally, we obtained a case-based classification for distinguishing among four categories with the third ANN method. We determined the performance of the third ANN by receiver operating characteristic (ROC) analysis. The areas under the ROC curve (AUC) of the highest category (severe pneumoconiosis) case and the lowest category (early pneumoconiosis) case were 0.89 ± 0.09 and 0.84 ± 0.12, respectively. The three-stage ANN with four texture features showed the highest performance for classification among the four categories. Our CAD system would be useful for assisting radiologists in classification of pneumoconiosis from category 0 to category 3.

Feature Representations for Neuromorphic Audio Spike Streams.

PubMed

Anumula, Jithendar; Neil, Daniel; Delbruck, Tobi; Liu, Shih-Chii

2018-01-01

Event-driven neuromorphic spiking sensors such as the silicon retina and the silicon cochlea encode the external sensory stimuli as asynchronous streams of spikes across different channels or pixels. Combining state-of-art deep neural networks with the asynchronous outputs of these sensors has produced encouraging results on some datasets but remains challenging. While the lack of effective spiking networks to process the spike streams is one reason, the other reason is that the pre-processing methods required to convert the spike streams to frame-based features needed for the deep networks still require further investigation. This work investigates the effectiveness of synchronous and asynchronous frame-based features generated using spike count and constant event binning in combination with the use of a recurrent neural network for solving a classification task using N-TIDIGITS18 dataset. This spike-based dataset consists of recordings from the Dynamic Audio Sensor, a spiking silicon cochlea sensor, in response to the TIDIGITS audio dataset. We also propose a new pre-processing method which applies an exponential kernel on the output cochlea spikes so that the interspike timing information is better preserved. The results from the N-TIDIGITS18 dataset show that the exponential features perform better than the spike count features, with over 91% accuracy on the digit classification task. This accuracy corresponds to an improvement of at least 2.5% over the use of spike count features, establishing a new state of the art for this dataset.

Feature Representations for Neuromorphic Audio Spike Streams

PubMed Central

Anumula, Jithendar; Neil, Daniel; Delbruck, Tobi; Liu, Shih-Chii

2018-01-01

Event-driven neuromorphic spiking sensors such as the silicon retina and the silicon cochlea encode the external sensory stimuli as asynchronous streams of spikes across different channels or pixels. Combining state-of-art deep neural networks with the asynchronous outputs of these sensors has produced encouraging results on some datasets but remains challenging. While the lack of effective spiking networks to process the spike streams is one reason, the other reason is that the pre-processing methods required to convert the spike streams to frame-based features needed for the deep networks still require further investigation. This work investigates the effectiveness of synchronous and asynchronous frame-based features generated using spike count and constant event binning in combination with the use of a recurrent neural network for solving a classification task using N-TIDIGITS18 dataset. This spike-based dataset consists of recordings from the Dynamic Audio Sensor, a spiking silicon cochlea sensor, in response to the TIDIGITS audio dataset. We also propose a new pre-processing method which applies an exponential kernel on the output cochlea spikes so that the interspike timing information is better preserved. The results from the N-TIDIGITS18 dataset show that the exponential features perform better than the spike count features, with over 91% accuracy on the digit classification task. This accuracy corresponds to an improvement of at least 2.5% over the use of spike count features, establishing a new state of the art for this dataset. PMID:29479300

Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks

NASA Astrophysics Data System (ADS)

Abdeljaber, Osama; Avci, Onur; Kiranyaz, Serkan; Gabbouj, Moncef; Inman, Daniel J.

2017-02-01

Structural health monitoring (SHM) and vibration-based structural damage detection have been a continuous interest for civil, mechanical and aerospace engineers over the decades. Early and meticulous damage detection has always been one of the principal objectives of SHM applications. The performance of a classical damage detection system predominantly depends on the choice of the features and the classifier. While the fixed and hand-crafted features may either be a sub-optimal choice for a particular structure or fail to achieve the same level of performance on another structure, they usually require a large computation power which may hinder their usage for real-time structural damage detection. This paper presents a novel, fast and accurate structural damage detection system using 1D Convolutional Neural Networks (CNNs) that has an inherent adaptive design to fuse both feature extraction and classification blocks into a single and compact learning body. The proposed method performs vibration-based damage detection and localization of the damage in real-time. The advantage of this approach is its ability to extract optimal damage-sensitive features automatically from the raw acceleration signals. Large-scale experiments conducted on a grandstand simulator revealed an outstanding performance and verified the computational efficiency of the proposed real-time damage detection method.

Disease named entity recognition from biomedical literature using a novel convolutional neural network.

PubMed

Zhao, Zhehuan; Yang, Zhihao; Luo, Ling; Wang, Lei; Zhang, Yin; Lin, Hongfei; Wang, Jian

2017-12-28

Automatic disease named entity recognition (DNER) is of utmost importance for development of more sophisticated BioNLP tools. However, most conventional CRF based DNER systems rely on well-designed features whose selection is labor intensive and time-consuming. Though most deep learning methods can solve NER problems with little feature engineering, they employ additional CRF layer to capture the correlation information between labels in neighborhoods which makes them much complicated. In this paper, we propose a novel multiple label convolutional neural network (MCNN) based disease NER approach. In this approach, instead of the CRF layer, a multiple label strategy (MLS) first introduced by us, is employed. First, the character-level embedding, word-level embedding and lexicon feature embedding are concatenated. Then several convolutional layers are stacked over the concatenated embedding. Finally, MLS strategy is applied to the output layer to capture the correlation information between neighboring labels. As shown by the experimental results, MCNN can achieve the state-of-the-art performance on both NCBI and CDR corpora. The proposed MCNN based disease NER method achieves the state-of-the-art performance with little feature engineering. And the experimental results show the MLS strategy's effectiveness of capturing the correlation information between labels in the neighborhood.

A Novel Hybrid Classification Model of Genetic Algorithms, Modified k-Nearest Neighbor and Developed Backpropagation Neural Network

PubMed Central

Salari, Nader; Shohaimi, Shamarina; Najafi, Farid; Nallappan, Meenakshii; Karishnarajah, Isthrinayagy

2014-01-01

Among numerous artificial intelligence approaches, k-Nearest Neighbor algorithms, genetic algorithms, and artificial neural networks are considered as the most common and effective methods in classification problems in numerous studies. In the present study, the results of the implementation of a novel hybrid feature selection-classification model using the above mentioned methods are presented. The purpose is benefitting from the synergies obtained from combining these technologies for the development of classification models. Such a combination creates an opportunity to invest in the strength of each algorithm, and is an approach to make up for their deficiencies. To develop proposed model, with the aim of obtaining the best array of features, first, feature ranking techniques such as the Fisher's discriminant ratio and class separability criteria were used to prioritize features. Second, the obtained results that included arrays of the top-ranked features were used as the initial population of a genetic algorithm to produce optimum arrays of features. Third, using a modified k-Nearest Neighbor method as well as an improved method of backpropagation neural networks, the classification process was advanced based on optimum arrays of the features selected by genetic algorithms. The performance of the proposed model was compared with thirteen well-known classification models based on seven datasets. Furthermore, the statistical analysis was performed using the Friedman test followed by post-hoc tests. The experimental findings indicated that the novel proposed hybrid model resulted in significantly better classification performance compared with all 13 classification methods. Finally, the performance results of the proposed model was benchmarked against the best ones reported as the state-of-the-art classifiers in terms of classification accuracy for the same data sets. The substantial findings of the comprehensive comparative study revealed that performance of the proposed model in terms of classification accuracy is desirable, promising, and competitive to the existing state-of-the-art classification models. PMID:25419659

Alexnet Feature Extraction and Multi-Kernel Learning for Objectoriented Classification

NASA Astrophysics Data System (ADS)

Ding, L.; Li, H.; Hu, C.; Zhang, W.; Wang, S.

2018-04-01

In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation.

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.

Automated embolic signal detection using Deep Convolutional Neural Network.

PubMed

Sombune, Praotasna; Phienphanich, Phongphan; Phuechpanpaisal, Sutanya; Muengtaweepongsa, Sombat; Ruamthanthong, Anuchit; Tantibundhit, Charturong

2017-07-01

This work investigated the potential of Deep Neural Network in detection of cerebral embolic signal (ES) from transcranial Doppler ultrasound (TCD). The resulting system is aimed to couple with TCD devices in diagnosing a risk of stroke in real-time with high accuracy. The Adaptive Gain Control (AGC) approach developed in our previous study is employed to capture suspected ESs in real-time. By using spectrograms of the same TCD signal dataset as that of our previous work as inputs and the same experimental setup, Deep Convolutional Neural Network (CNN), which can learn features while training, was investigated for its ability to bypass the traditional handcrafted feature extraction and selection process. Extracted feature vectors from the suspected ESs are later determined whether they are of an ES, artifact (AF) or normal (NR) interval. The effectiveness of the developed system was evaluated over 19 subjects going under procedures generating emboli. The CNN-based system could achieve in average of 83.0% sensitivity, 80.1% specificity, and 81.4% accuracy, with considerably much less time consumption in development. The certainly growing set of training samples and computational resources will contribute to high performance. Besides having potential use in various clinical ES monitoring settings, continuation of this promising study will benefit developments of wearable applications by leveraging learnable features to serve demographic differentials.

Image quality assessment using deep convolutional networks

NASA Astrophysics Data System (ADS)

Li, Yezhou; Ye, Xiang; Li, Yong

2017-12-01

This paper proposes a method of accurately assessing image quality without a reference image by using a deep convolutional neural network. Existing training based methods usually utilize a compact set of linear filters for learning features of images captured by different sensors to assess their quality. These methods may not be able to learn the semantic features that are intimately related with the features used in human subject assessment. Observing this drawback, this work proposes training a deep convolutional neural network (CNN) with labelled images for image quality assessment. The ReLU in the CNN allows non-linear transformations for extracting high-level image features, providing a more reliable assessment of image quality than linear filters. To enable the neural network to take images of any arbitrary size as input, the spatial pyramid pooling (SPP) is introduced connecting the top convolutional layer and the fully-connected layer. In addition, the SPP makes the CNN robust to object deformations to a certain extent. The proposed method taking an image as input carries out an end-to-end learning process, and outputs the quality of the image. It is tested on public datasets. Experimental results show that it outperforms existing methods by a large margin and can accurately assess the image quality on images taken by different sensors of varying sizes.

Bilinear Convolutional Neural Networks for Fine-grained Visual Recognition.

PubMed

Lin, Tsung-Yu; RoyChowdhury, Aruni; Maji, Subhransu

2017-07-04

We present a simple and effective architecture for fine-grained recognition called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of features derived from two CNNs and capture localized feature interactions in a translationally invariant manner. B-CNNs are related to orderless texture representations built on deep features but can be trained in an end-to-end manner. Our most accurate model obtains 84.1%, 79.4%, 84.5% and 91.3% per-image accuracy on the Caltech-UCSD birds [66], NABirds [63], FGVC aircraft [42], and Stanford cars [33] dataset respectively and runs at 30 frames-per-second on a NVIDIA Titan X GPU. We then present a systematic analysis of these networks and show that (1) the bilinear features are highly redundant and can be reduced by an order of magnitude in size without significant loss in accuracy, (2) are also effective for other image classification tasks such as texture and scene recognition, and (3) can be trained from scratch on the ImageNet dataset offering consistent improvements over the baseline architecture. Finally, we present visualizations of these models on various datasets using top activations of neural units and gradient-based inversion techniques. The source code for the complete system is available at http://vis-www.cs.umass.edu/bcnn.

Collaborative Brain-Computer Interface for Aiding Decision-Making

PubMed Central

Poli, Riccardo; Valeriani, Davide; Cinel, Caterina

2014-01-01

We look at the possibility of integrating the percepts from multiple non-communicating observers as a means of achieving better joint perception and better group decisions. Our approach involves the combination of a brain-computer interface with human behavioural responses. To test ideas in controlled conditions, we asked observers to perform a simple matching task involving the rapid sequential presentation of pairs of visual patterns and the subsequent decision as whether the two patterns in a pair were the same or different. We recorded the response times of observers as well as a neural feature which predicts incorrect decisions and, thus, indirectly indicates the confidence of the decisions made by the observers. We then built a composite neuro-behavioural feature which optimally combines the two measures. For group decisions, we uses a majority rule and three rules which weigh the decisions of each observer based on response times and our neural and neuro-behavioural features. Results indicate that the integration of behavioural responses and neural features can significantly improve accuracy when compared with the majority rule. An analysis of event-related potentials indicates that substantial differences are present in the proximity of the response for correct and incorrect trials, further corroborating the idea of using hybrids of brain-computer interfaces and traditional strategies for improving decision making. PMID:25072739

A fresh look at functional link neural network for motor imagery-based brain-computer interface.

PubMed

Hettiarachchi, Imali T; Babaei, Toktam; Nguyen, Thanh; Lim, Chee P; Nahavandi, Saeid

2018-05-04

Artificial neural networks (ANNs) are one of the widely used classifiers in the brain-computer interface (BCI) systems-based on noninvasive electroencephalography (EEG) signals. Among the different ANN architectures, the most commonly applied for BCI classifiers is the multilayer perceptron (MLP). When appropriately designed with optimal number of neuron layers and number of neurons per layer, the ANN can act as a universal approximator. However, due to the low signal-to-noise ratio of EEG signal data, overtraining problem may become an inherent issue, causing these universal approximators to fail in real-time applications. In this study we introduce a higher order neural network, namely the functional link neural network (FLNN) as a classifier for motor imagery (MI)-based BCI systems, to remedy the drawbacks in MLP. We compare the proposed method with competing classifiers such as linear decomposition analysis, naïve Bayes, k-nearest neighbours, support vector machine and three MLP architectures. Two multi-class benchmark datasets from the BCI competitions are used. Common spatial pattern algorithm is utilized for feature extraction to build classification models. FLNN reports the highest average Kappa value over multiple subjects for both the BCI competition datasets, under similarly preprocessed data and extracted features. Further, statistical comparison results over multiple subjects show that the proposed FLNN classification method yields the best performance among the competing classifiers. Findings from this study imply that the proposed method, which has less computational complexity compared to the MLP, can be implemented effectively in practical MI-based BCI systems. Copyright © 2018 Elsevier B.V. All rights reserved.

Using phone sensors and an artificial neural network to detect gait changes during drinking episodes in the natural environment.

PubMed

Suffoletto, Brian; Gharani, Pedram; Chung, Tammy; Karimi, Hassan

2018-02-01

Phone sensors could be useful in assessing changes in gait that occur with alcohol consumption. This study determined (1) feasibility of collecting gait-related data during drinking occasions in the natural environment, and (2) how gait-related features measured by phone sensors relate to estimated blood alcohol concentration (eBAC). Ten young adult heavy drinkers were prompted to complete a 5-step gait task every hour from 8pm to 12am over four consecutive weekends. We collected 3-axis accelerometer, gyroscope, and magnetometer data from phone sensors, and computed 24 gait-related features using a sliding window technique. eBAC levels were calculated at each time point based on Ecological Momentary Assessment (EMA) of alcohol use. We used an artificial neural network model to analyze associations between sensor features and eBACs in training (70% of the data) and validation and test (30% of the data) datasets. We analyzed 128 data points where both eBAC and gait-related sensor data were captured, either when not drinking (n=60), while eBAC was ascending (n=55) or eBAC was descending (n=13). 21 data points were captured at times when the eBAC was greater than the legal limit (0.08mg/dl). Using a Bayesian regularized neural network, gait-related phone sensor features showed a high correlation with eBAC (Pearson's r>0.9), and >95% of estimated eBAC would fall between -0.012 and +0.012 of actual eBAC. It is feasible to collect gait-related data from smartphone sensors during drinking occasions in the natural environment. Sensor-based features can be used to infer gait changes associated with elevated blood alcohol content. Copyright © 2017 Elsevier B.V. All rights reserved.

Decoding of Human Movements Based on Deep Brain Local Field Potentials Using Ensemble Neural Networks

PubMed Central

2017-01-01

Decoding neural activities related to voluntary and involuntary movements is fundamental to understanding human brain motor circuits and neuromotor disorders and can lead to the development of neuromotor prosthetic devices for neurorehabilitation. This study explores using recorded deep brain local field potentials (LFPs) for robust movement decoding of Parkinson's disease (PD) and Dystonia patients. The LFP data from voluntary movement activities such as left and right hand index finger clicking were recorded from patients who underwent surgeries for implantation of deep brain stimulation electrodes. Movement-related LFP signal features were extracted by computing instantaneous power related to motor response in different neural frequency bands. An innovative neural network ensemble classifier has been proposed and developed for accurate prediction of finger movement and its forthcoming laterality. The ensemble classifier contains three base neural network classifiers, namely, feedforward, radial basis, and probabilistic neural networks. The majority voting rule is used to fuse the decisions of the three base classifiers to generate the final decision of the ensemble classifier. The overall decoding performance reaches a level of agreement (kappa value) at about 0.729 ± 0.16 for decoding movement from the resting state and about 0.671 ± 0.14 for decoding left and right visually cued movements. PMID:29201041

Invariant object recognition based on the generalized discrete radon transform

NASA Astrophysics Data System (ADS)

Easley, Glenn R.; Colonna, Flavia

2004-04-01

We introduce a method for classifying objects based on special cases of the generalized discrete Radon transform. We adjust the transform and the corresponding ridgelet transform by means of circular shifting and a singular value decomposition (SVD) to obtain a translation, rotation and scaling invariant set of feature vectors. We then use a back-propagation neural network to classify the input feature vectors. We conclude with experimental results and compare these with other invariant recognition methods.

Compact VLSI neural computer integrated with active pixel sensor for real-time ATR applications

NASA Astrophysics Data System (ADS)

Fang, Wai-Chi; Udomkesmalee, Gabriel; Alkalai, Leon

1997-04-01

A compact VLSI neural computer integrated with an active pixel sensor has been under development to mimic what is inherent in biological vision systems. This electronic eye- brain computer is targeted for real-time machine vision applications which require both high-bandwidth communication and high-performance computing for data sensing, synergy of multiple types of sensory information, feature extraction, target detection, target recognition, and control functions. The neural computer is based on a composite structure which combines Annealing Cellular Neural Network (ACNN) and Hierarchical Self-Organization Neural Network (HSONN). The ACNN architecture is a programmable and scalable multi- dimensional array of annealing neurons which are locally connected with their local neurons. Meanwhile, the HSONN adopts a hierarchical structure with nonlinear basis functions. The ACNN+HSONN neural computer is effectively designed to perform programmable functions for machine vision processing in all levels with its embedded host processor. It provides a two order-of-magnitude increase in computation power over the state-of-the-art microcomputer and DSP microelectronics. A compact current-mode VLSI design feasibility of the ACNN+HSONN neural computer is demonstrated by a 3D 16X8X9-cube neural processor chip design in a 2-micrometers CMOS technology. Integration of this neural computer as one slice of a 4'X4' multichip module into the 3D MCM based avionics architecture for NASA's New Millennium Program is also described.

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.

Motor Fault Diagnosis Based on Short-time Fourier Transform and Convolutional Neural Network

NASA Astrophysics Data System (ADS)

Wang, Li-Hua; Zhao, Xiao-Ping; Wu, Jia-Xin; Xie, Yang-Yang; Zhang, Yong-Hong

2017-11-01

With the rapid development of mechanical equipment, the mechanical health monitoring field has entered the era of big data. However, the method of manual feature extraction has the disadvantages of low efficiency and poor accuracy, when handling big data. In this study, the research object was the asynchronous motor in the drivetrain diagnostics simulator system. The vibration signals of different fault motors were collected. The raw signal was pretreated using short time Fourier transform (STFT) to obtain the corresponding time-frequency map. Then, the feature of the time-frequency map was adaptively extracted by using a convolutional neural network (CNN). The effects of the pretreatment method, and the hyper parameters of network diagnostic accuracy, were investigated experimentally. The experimental results showed that the influence of the preprocessing method is small, and that the batch-size is the main factor affecting accuracy and training efficiency. By investigating feature visualization, it was shown that, in the case of big data, the extracted CNN features can represent complex mapping relationships between signal and health status, and can also overcome the prior knowledge and engineering experience requirement for feature extraction, which is used by traditional diagnosis methods. This paper proposes a new method, based on STFT and CNN, which can complete motor fault diagnosis tasks more intelligently and accurately.

The Use of Artificial Neural Networks for Forecasting the Electric Demand of Stand-Alone Consumers

NASA Astrophysics Data System (ADS)

Ivanin, O. A.; Direktor, L. B.

2018-05-01

The problem of short-term forecasting of electric power demand of stand-alone consumers (small inhabited localities) situated outside centralized power supply areas is considered. The basic approaches to modeling the electric power demand depending on the forecasting time frame and the problems set, as well as the specific features of such modeling, are described. The advantages and disadvantages of the methods used for the short-term forecast of the electric demand are indicated, and difficulties involved in the solution of the problem are outlined. The basic principles of arranging artificial neural networks are set forth; it is also shown that the proposed method is preferable when the input information necessary for prediction is lacking or incomplete. The selection of the parameters that should be included into the list of the input data for modeling the electric power demand of residential areas using artificial neural networks is validated. The structure of a neural network is proposed for solving the problem of modeling the electric power demand of residential areas. The specific features of generation of the training dataset are outlined. The results of test modeling of daily electric demand curves for some settlements of Kamchatka and Yakutia based on known actual electric demand curves are provided. The reliability of the test modeling has been validated. A high value of the deviation of the modeled curve from the reference curve obtained in one of the four reference calculations is explained. The input data and the predicted power demand curves for the rural settlement of Kuokuiskii Nasleg are provided. The power demand curves were modeled for four characteristic days of the year, and they can be used in the future for designing a power supply system for the settlement. To enhance the accuracy of the method, a series of measures based on specific features of a neural network's functioning are proposed.

Investigating Patterns for Self-Induced Emotion Recognition from EEG Signals.

PubMed

Zhuang, Ning; Zeng, Ying; Yang, Kai; Zhang, Chi; Tong, Li; Yan, Bin

2018-03-12

Most current approaches to emotion recognition are based on neural signals elicited by affective materials such as images, sounds and videos. However, the application of neural patterns in the recognition of self-induced emotions remains uninvestigated. In this study we inferred the patterns and neural signatures of self-induced emotions from electroencephalogram (EEG) signals. The EEG signals of 30 participants were recorded while they watched 18 Chinese movie clips which were intended to elicit six discrete emotions, including joy, neutrality, sadness, disgust, anger and fear. After watching each movie clip the participants were asked to self-induce emotions by recalling a specific scene from each movie. We analyzed the important features, electrode distribution and average neural patterns of different self-induced emotions. Results demonstrated that features related to high-frequency rhythm of EEG signals from electrodes distributed in the bilateral temporal, prefrontal and occipital lobes have outstanding performance in the discrimination of emotions. Moreover, the six discrete categories of self-induced emotion exhibit specific neural patterns and brain topography distributions. We achieved an average accuracy of 87.36% in the discrimination of positive from negative self-induced emotions and 54.52% in the classification of emotions into six discrete categories. Our research will help promote the development of comprehensive endogenous emotion recognition methods.

Investigating Patterns for Self-Induced Emotion Recognition from EEG Signals

PubMed Central

Zeng, Ying; Yang, Kai; Tong, Li; Yan, Bin

2018-01-01

Most current approaches to emotion recognition are based on neural signals elicited by affective materials such as images, sounds and videos. However, the application of neural patterns in the recognition of self-induced emotions remains uninvestigated. In this study we inferred the patterns and neural signatures of self-induced emotions from electroencephalogram (EEG) signals. The EEG signals of 30 participants were recorded while they watched 18 Chinese movie clips which were intended to elicit six discrete emotions, including joy, neutrality, sadness, disgust, anger and fear. After watching each movie clip the participants were asked to self-induce emotions by recalling a specific scene from each movie. We analyzed the important features, electrode distribution and average neural patterns of different self-induced emotions. Results demonstrated that features related to high-frequency rhythm of EEG signals from electrodes distributed in the bilateral temporal, prefrontal and occipital lobes have outstanding performance in the discrimination of emotions. Moreover, the six discrete categories of self-induced emotion exhibit specific neural patterns and brain topography distributions. We achieved an average accuracy of 87.36% in the discrimination of positive from negative self-induced emotions and 54.52% in the classification of emotions into six discrete categories. Our research will help promote the development of comprehensive endogenous emotion recognition methods. PMID:29534515

An Investigation of the Application of Artificial Neural Networks to Adaptive Optics Imaging Systems

DTIC Science & Technology

1991-12-01

neural network and the feedforward neural network studied is the single layer perceptron artificial neural network . The recurrent artificial neural network input...features are the wavefront sensor slope outputs and neighboring actuator feedback commands. The feedforward artificial neural network input

An Artificial Neural Network for Movement Pattern Analysis to Estimate Blood Alcohol Content Level.

PubMed

Gharani, Pedram; Suffoletto, Brian; Chung, Tammy; Karimi, Hassan A

2017-12-13

Impairments in gait occur after alcohol consumption, and, if detected in real-time, could guide the delivery of "just-in-time" injury prevention interventions. We aimed to identify the salient features of gait that could be used for estimating blood alcohol content (BAC) level in a typical drinking environment. We recruited 10 young adults with a history of heavy drinking to test our research app. During four consecutive Fridays and Saturdays, every hour from 8 p.m. to 12 a.m., they were prompted to use the app to report alcohol consumption and complete a 5-step straight-line walking task, during which 3-axis acceleration and angular velocity data was sampled at a frequency of 100 Hz. BAC for each subject was calculated. From sensor signals, 24 features were calculated using a sliding window technique, including energy, mean, and standard deviation. Using an artificial neural network (ANN), we performed regression analysis to define a model determining association between gait features and BACs. Part (70%) of the data was then used as a training dataset, and the results tested and validated using the rest of the samples. We evaluated different training algorithms for the neural network and the result showed that a Bayesian regularization neural network (BRNN) was the most efficient and accurate. Analyses support the use of the tandem gait task paired with our approach to reliably estimate BAC based on gait features. Results from this work could be useful in designing effective prevention interventions to reduce risky behaviors during periods of alcohol consumption.

CNN universal machine as classificaton platform: an art-like clustering algorithm.

PubMed

Bálya, David

2003-12-01

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

Neural network-based brain tissue segmentation in MR images using extracted features from intraframe coding in H.264

NASA Astrophysics Data System (ADS)

Jafari, Mehdi; Kasaei, Shohreh

2012-01-01

Automatic brain tissue segmentation is a crucial task in diagnosis and treatment of medical images. This paper presents a new algorithm to segment different brain tissues, such as white matter (WM), gray matter (GM), cerebral spinal fluid (CSF), background (BKG), and tumor tissues. The proposed technique uses the modified intraframe coding yielded from H.264/(AVC), for feature extraction. Extracted features are then imposed to an artificial back propagation neural network (BPN) classifier to assign each block to its appropriate class. Since the newest coding standard, H.264/AVC, has the highest compression ratio, it decreases the dimension of extracted features and thus yields to a more accurate classifier with low computational complexity. The performance of the BPN classifier is evaluated using the classification accuracy and computational complexity terms. The results show that the proposed technique is more robust and effective with low computational complexity compared to other recent works.

Neural network-based brain tissue segmentation in MR images using extracted features from intraframe coding in H.264

NASA Astrophysics Data System (ADS)

Jafari, Mehdi; Kasaei, Shohreh

2011-12-01

Automatic brain tissue segmentation is a crucial task in diagnosis and treatment of medical images. This paper presents a new algorithm to segment different brain tissues, such as white matter (WM), gray matter (GM), cerebral spinal fluid (CSF), background (BKG), and tumor tissues. The proposed technique uses the modified intraframe coding yielded from H.264/(AVC), for feature extraction. Extracted features are then imposed to an artificial back propagation neural network (BPN) classifier to assign each block to its appropriate class. Since the newest coding standard, H.264/AVC, has the highest compression ratio, it decreases the dimension of extracted features and thus yields to a more accurate classifier with low computational complexity. The performance of the BPN classifier is evaluated using the classification accuracy and computational complexity terms. The results show that the proposed technique is more robust and effective with low computational complexity compared to other recent works.

Unsupervised texture image segmentation by improved neural network ART2

NASA Technical Reports Server (NTRS)

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

1994-01-01

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

A hybrid CNN feature model for pulmonary nodule malignancy risk differentiation.

PubMed

Wang, Huafeng; Zhao, Tingting; Li, Lihong Connie; Pan, Haixia; Liu, Wanquan; Gao, Haoqi; Han, Fangfang; Wang, Yuehai; Qi, Yifan; Liang, Zhengrong

2018-01-01

The malignancy risk differentiation of pulmonary nodule is one of the most challenge tasks of computer-aided diagnosis (CADx). Most recently reported CADx methods or schemes based on texture and shape estimation have shown relatively satisfactory on differentiating the risk level of malignancy among the nodules detected in lung cancer screening. However, the existing CADx schemes tend to detect and analyze characteristics of pulmonary nodules from a statistical perspective according to local features only. Enlightened by the currently prevailing learning ability of convolutional neural network (CNN), which simulates human neural network for target recognition and our previously research on texture features, we present a hybrid model that takes into consideration of both global and local features for pulmonary nodule differentiation using the largest public database founded by the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). By comparing three types of CNN models in which two of them were newly proposed by us, we observed that the multi-channel CNN model yielded the best discrimination in capacity of differentiating malignancy risk of the nodules based on the projection of distributions of extracted features. Moreover, CADx scheme using the new multi-channel CNN model outperformed our previously developed CADx scheme using the 3D texture feature analysis method, which increased the computed area under a receiver operating characteristic curve (AUC) from 0.9441 to 0.9702.

Diagnosis of Diabetes Mellitus by Extraction of Morphological Features of Red Blood Cells Using an Artificial Neural Network.

PubMed

Palanisamy, Vinupritha; Mariamichael, Anburajan

2016-10-01

Background and Aim: Diabetes mellitus is a metabolic disorder characterized by varying hyperglycemias either due to insufficient secretion of insulin by the pancreas or improper utilization of glucose. The study was aimed to investigate the association of morphological features of erythrocytes among normal and diabetic subjects and its gender-based changes and thereby to develop a computer aided tool to diagnose diabetes using features extracted from RBC. Materials and Methods: The study involved 138 normal and 144 diabetic subjects. The blood was drawn from the subjects and the blood smear prepared was digitized using Zeiss fluorescent microscope. The digitized images were pre-processed and texture segmentation was performed to extract the various morphological features. The Pearson correlation test was performed and subsequently, classification of subjects as normal and diabetes was carried out by a neural network classifier based on the features that demonstrated significance at the level of P <0.05. Result: The proposed system demonstrated an overall accuracy, sensitivity, specificity, positive predictive value and negative predictive value of 93.3, 93.71, 92.8, 93.1 and 93.5% respectively. Conclusion: The morphological features exhibited a statistically significant difference (P<0.01) between the normal and diabetic cells, suggesting that it could be helpful in the diagnosis of Diabetes mellitus using a computer aided system. © Georg Thieme Verlag KG Stuttgart · New York.

Speech reconstruction using a deep partially supervised neural network.

PubMed

McLoughlin, Ian; Li, Jingjie; Song, Yan; Sharifzadeh, Hamid R

2017-08-01

Statistical speech reconstruction for larynx-related dysphonia has achieved good performance using Gaussian mixture models and, more recently, restricted Boltzmann machine arrays; however, deep neural network (DNN)-based systems have been hampered by the limited amount of training data available from individual voice-loss patients. The authors propose a novel DNN structure that allows a partially supervised training approach on spectral features from smaller data sets, yielding very good results compared with the current state-of-the-art.

Development and application of deep convolutional neural network in target detection

NASA Astrophysics Data System (ADS)

Jiang, Xiaowei; Wang, Chunping; Fu, Qiang

2018-04-01

With the development of big data and algorithms, deep convolution neural networks with more hidden layers have more powerful feature learning and feature expression ability than traditional machine learning methods, making artificial intelligence surpass human level in many fields. This paper first reviews the development and application of deep convolutional neural networks in the field of object detection in recent years, then briefly summarizes and ponders some existing problems in the current research, and the future development of deep convolutional neural network is prospected.

A novel biomedical image indexing and retrieval system via deep preference learning.

PubMed

Pang, Shuchao; Orgun, Mehmet A; Yu, Zhezhou

2018-05-01

The traditional biomedical image retrieval methods as well as content-based image retrieval (CBIR) methods originally designed for non-biomedical images either only consider using pixel and low-level features to describe an image or use deep features to describe images but still leave a lot of room for improving both accuracy and efficiency. In this work, we propose a new approach, which exploits deep learning technology to extract the high-level and compact features from biomedical images. The deep feature extraction process leverages multiple hidden layers to capture substantial feature structures of high-resolution images and represent them at different levels of abstraction, leading to an improved performance for indexing and retrieval of biomedical images. We exploit the current popular and multi-layered deep neural networks, namely, stacked denoising autoencoders (SDAE) and convolutional neural networks (CNN) to represent the discriminative features of biomedical images by transferring the feature representations and parameters of pre-trained deep neural networks from another domain. Moreover, in order to index all the images for finding the similarly referenced images, we also introduce preference learning technology to train and learn a kind of a preference model for the query image, which can output the similarity ranking list of images from a biomedical image database. To the best of our knowledge, this paper introduces preference learning technology for the first time into biomedical image retrieval. We evaluate the performance of two powerful algorithms based on our proposed system and compare them with those of popular biomedical image indexing approaches and existing regular image retrieval methods with detailed experiments over several well-known public biomedical image databases. Based on different criteria for the evaluation of retrieval performance, experimental results demonstrate that our proposed algorithms outperform the state-of-the-art techniques in indexing biomedical images. We propose a novel and automated indexing system based on deep preference learning to characterize biomedical images for developing computer aided diagnosis (CAD) systems in healthcare. Our proposed system shows an outstanding indexing ability and high efficiency for biomedical image retrieval applications and it can be used to collect and annotate the high-resolution images in a biomedical database for further biomedical image research and applications. Copyright © 2018 Elsevier B.V. All rights reserved.

Video-based face recognition via convolutional neural networks

NASA Astrophysics Data System (ADS)

Bao, Tianlong; Ding, Chunhui; Karmoshi, Saleem; Zhu, Ming

2017-06-01

Face recognition has been widely studied recently while video-based face recognition still remains a challenging task because of the low quality and large intra-class variation of video captured face images. In this paper, we focus on two scenarios of video-based face recognition: 1)Still-to-Video(S2V) face recognition, i.e., querying a still face image against a gallery of video sequences; 2)Video-to-Still(V2S) face recognition, in contrast to S2V scenario. A novel method was proposed in this paper to transfer still and video face images to an Euclidean space by a carefully designed convolutional neural network, then Euclidean metrics are used to measure the distance between still and video images. Identities of still and video images that group as pairs are used as supervision. In the training stage, a joint loss function that measures the Euclidean distance between the predicted features of training pairs and expanding vectors of still images is optimized to minimize the intra-class variation while the inter-class variation is guaranteed due to the large margin of still images. Transferred features are finally learned via the designed convolutional neural network. Experiments are performed on COX face dataset. Experimental results show that our method achieves reliable performance compared with other state-of-the-art methods.

Underwater target classification using wavelet packets and neural networks.

PubMed

Azimi-Sadjadi, M R; Yao, D; Huang, Q; Dobeck, G J

2000-01-01

In this paper, a new subband-based classification scheme is developed for classifying underwater mines and mine-like targets from the acoustic backscattered signals. The system consists of a feature extractor using wavelet packets in conjunction with linear predictive coding (LPC), a feature selection scheme, and a backpropagation neural-network classifier. The data set used for this study consists of the backscattered signals from six different objects: two mine-like targets and four nontargets for several aspect angles. Simulation results on ten different noisy realizations and for signal-to-noise ratio (SNR) of 12 dB are presented. The receiver operating characteristic (ROC) curve of the classifier generated based on these results demonstrated excellent classification performance of the system. The generalization ability of the trained network was demonstrated by computing the error and classification rate statistics on a large data set. A multiaspect fusion scheme was also adopted in order to further improve the classification performance.

Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson's disease identification.

PubMed

Pereira, Clayton R; Pereira, Danilo R; Rosa, Gustavo H; Albuquerque, Victor H C; Weber, Silke A T; Hook, Christian; Papa, João P

2018-05-01

Parkinson's disease (PD) is considered a degenerative disorder that affects the motor system, which may cause tremors, micrography, and the freezing of gait. Although PD is related to the lack of dopamine, the triggering process of its development is not fully understood yet. In this work, we introduce convolutional neural networks to learn features from images produced by handwritten dynamics, which capture different information during the individual's assessment. Additionally, we make available a dataset composed of images and signal-based data to foster the research related to computer-aided PD diagnosis. The proposed approach was compared against raw data and texture-based descriptors, showing suitable results, mainly in the context of early stage detection, with results nearly to 95%. The analysis of handwritten dynamics using deep learning techniques showed to be useful for automatic Parkinson's disease identification, as well as it can outperform handcrafted features. Copyright © 2018 Elsevier B.V. All rights reserved.

Estimation of tool wear during CNC milling using neural network-based sensor fusion

NASA Astrophysics Data System (ADS)

Ghosh, N.; Ravi, Y. B.; Patra, A.; Mukhopadhyay, S.; Paul, S.; Mohanty, A. R.; Chattopadhyay, A. B.

2007-01-01

Cutting tool wear degrades the product quality in manufacturing processes. Monitoring tool wear value online is therefore needed to prevent degradation in machining quality. Unfortunately there is no direct way of measuring the tool wear online. Therefore one has to adopt an indirect method wherein the tool wear is estimated from several sensors measuring related process variables. In this work, a neural network-based sensor fusion model has been developed for tool condition monitoring (TCM). Features extracted from a number of machining zone signals, namely cutting forces, spindle vibration, spindle current, and sound pressure level have been fused to estimate the average flank wear of the main cutting edge. Novel strategies such as, signal level segmentation for temporal registration, feature space filtering, outlier removal, and estimation space filtering have been proposed. The proposed approach has been validated by both laboratory and industrial implementations.

Automated extraction of metadata from remotely sensed satellite imagery

NASA Technical Reports Server (NTRS)

Cromp, Robert F.

1991-01-01

The paper discusses research in the Intelligent Data Management project at the NASA/Goddard Space Flight Center, with emphasis on recent improvements in low-level feature detection algorithms for performing real-time characterization of images. Images, including MSS and TM data, are characterized using neural networks and the interpretation of the neural network output by an expert system for subsequent archiving in an object-oriented data base. The data show the applicability of this approach to different arrangements of low-level remote sensing channels. The technique works well when the neural network is trained on data similar to the data used for testing.

Design and fabrication of a flexible substrate microelectrode array for brain machine interfaces.

PubMed

Patrick, Erin; Ordonez, Matthew; Alba, Nicolas; Sanchez, Justin C; Nishida, Toshikazu

2006-01-01

We report a neural microelectrode array design that leverages the recording properties of conventional microwire electrode arrays with the additional features of precise control of the electrode geometries. Using microfabrication techniques, a neural probe array is fabricated that possesses a flexible polyimide-based cable. The performance of the design was tested with electrochemical impedance spectroscopy and in vivo studies. The gold-plated electrode site has an impedance value of 0.9 M Omega at 1 kHz. Acute neural recording provided high neuronal yields, peak-to-peak amplitudes (as high as 100 microV), and signal-to-noise ratios (27 dB).

Decoding of visual activity patterns from fMRI responses using multivariate pattern analyses and convolutional neural network.

PubMed

Zafar, Raheel; Kamel, Nidal; Naufal, Mohamad; Malik, Aamir Saeed; Dass, Sarat C; Ahmad, Rana Fayyaz; Abdullah, Jafri M; Reza, Faruque

2017-01-01

Decoding of human brain activity has always been a primary goal in neuroscience especially with functional magnetic resonance imaging (fMRI) data. In recent years, Convolutional neural network (CNN) has become a popular method for the extraction of features due to its higher accuracy, however it needs a lot of computation and training data. In this study, an algorithm is developed using Multivariate pattern analysis (MVPA) and modified CNN to decode the behavior of brain for different images with limited data set. Selection of significant features is an important part of fMRI data analysis, since it reduces the computational burden and improves the prediction performance; significant features are selected using t-test. MVPA uses machine learning algorithms to classify different brain states and helps in prediction during the task. General linear model (GLM) is used to find the unknown parameters of every individual voxel and the classification is done using multi-class support vector machine (SVM). MVPA-CNN based proposed algorithm is compared with region of interest (ROI) based method and MVPA based estimated values. The proposed method showed better overall accuracy (68.6%) compared to ROI (61.88%) and estimation values (64.17%).

Deep Spatial-Temporal Joint Feature Representation for Video Object Detection.

PubMed

Zhao, Baojun; Zhao, Boya; Tang, Linbo; Han, Yuqi; Wang, Wenzheng

2018-03-04

With the development of deep neural networks, many object detection frameworks have shown great success in the fields of smart surveillance, self-driving cars, and facial recognition. However, the data sources are usually videos, and the object detection frameworks are mostly established on still images and only use the spatial information, which means that the feature consistency cannot be ensured because the training procedure loses temporal information. To address these problems, we propose a single, fully-convolutional neural network-based object detection framework that involves temporal information by using Siamese networks. In the training procedure, first, the prediction network combines the multiscale feature map to handle objects of various sizes. Second, we introduce a correlation loss by using the Siamese network, which provides neighboring frame features. This correlation loss represents object co-occurrences across time to aid the consistent feature generation. Since the correlation loss should use the information of the track ID and detection label, our video object detection network has been evaluated on the large-scale ImageNet VID dataset where it achieves a 69.5% mean average precision (mAP).

Tehran Air Pollutants Prediction Based on Random Forest Feature Selection Method

NASA Astrophysics Data System (ADS)

Shamsoddini, A.; Aboodi, M. R.; Karami, J.

2017-09-01

Air pollution as one of the most serious forms of environmental pollutions poses huge threat to human life. Air pollution leads to environmental instability, and has harmful and undesirable effects on the environment. Modern prediction methods of the pollutant concentration are able to improve decision making and provide appropriate solutions. This study examines the performance of the Random Forest feature selection in combination with multiple-linear regression and Multilayer Perceptron Artificial Neural Networks methods, in order to achieve an efficient model to estimate carbon monoxide and nitrogen dioxide, sulfur dioxide and PM2.5 contents in the air. The results indicated that Artificial Neural Networks fed by the attributes selected by Random Forest feature selection method performed more accurate than other models for the modeling of all pollutants. The estimation accuracy of sulfur dioxide emissions was lower than the other air contaminants whereas the nitrogen dioxide was predicted more accurate than the other pollutants.

Improved wavelet packet classification algorithm for vibrational intrusions in distributed fiber-optic monitoring systems

NASA Astrophysics Data System (ADS)

Wang, Bingjie; Pi, Shaohua; Sun, Qi; Jia, Bo

2015-05-01

An improved classification algorithm that considers multiscale wavelet packet Shannon entropy is proposed. Decomposition coefficients at all levels are obtained to build the initial Shannon entropy feature vector. After subtracting the Shannon entropy map of the background signal, components of the strongest discriminating power in the initial feature vector are picked out to rebuild the Shannon entropy feature vector, which is transferred to radial basis function (RBF) neural network for classification. Four types of man-made vibrational intrusion signals are recorded based on a modified Sagnac interferometer. The performance of the improved classification algorithm has been evaluated by the classification experiments via RBF neural network under different diffusion coefficients. An 85% classification accuracy rate is achieved, which is higher than the other common algorithms. The classification results show that this improved classification algorithm can be used to classify vibrational intrusion signals in an automatic real-time monitoring system.

Identification and classification of similar looking food grains

NASA Astrophysics Data System (ADS)

Anami, B. S.; Biradar, Sunanda D.; Savakar, D. G.; Kulkarni, P. V.

2013-01-01

This paper describes the comparative study of Artificial Neural Network (ANN) and Support Vector Machine (SVM) classifiers by taking a case study of identification and classification of four pairs of similar looking food grains namely, Finger Millet, Mustard, Soyabean, Pigeon Pea, Aniseed, Cumin-seeds, Split Greengram and Split Blackgram. Algorithms are developed to acquire and process color images of these grains samples. The developed algorithms are used to extract 18 colors-Hue Saturation Value (HSV), and 42 wavelet based texture features. Back Propagation Neural Network (BPNN)-based classifier is designed using three feature sets namely color - HSV, wavelet-texture and their combined model. SVM model for color- HSV model is designed for the same set of samples. The classification accuracies ranging from 93% to 96% for color-HSV, ranging from 78% to 94% for wavelet texture model and from 92% to 97% for combined model are obtained for ANN based models. The classification accuracy ranging from 80% to 90% is obtained for color-HSV based SVM model. Training time required for the SVM based model is substantially lesser than ANN for the same set of images.

A Hybrid Neural Network and Feature Extraction Technique for Target Recognition.

DTIC Science & Technology

target features are extracted, the extracted data being evaluated in an artificial neural network to identify a target at a location within the image scene from which the different viewing angles extend.

Feature extraction using extrema sampling of discrete derivatives for spike sorting in implantable upper-limb neural prostheses.

PubMed

Zamani, Majid; Demosthenous, Andreas

2014-07-01

Next generation neural interfaces for upper-limb (and other) prostheses aim to develop implantable interfaces for one or more nerves, each interface having many neural signal channels that work reliably in the stump without harming the nerves. To achieve real-time multi-channel processing it is important to integrate spike sorting on-chip to overcome limitations in transmission bandwidth. This requires computationally efficient algorithms for feature extraction and clustering suitable for low-power hardware implementation. This paper describes a new feature extraction method for real-time spike sorting based on extrema analysis (namely positive peaks and negative peaks) of spike shapes and their discrete derivatives at different frequency bands. Employing simulation across different datasets, the accuracy and computational complexity of the proposed method are assessed and compared with other methods. The average classification accuracy of the proposed method in conjunction with online sorting (O-Sort) is 91.6%, outperforming all the other methods tested with the O-Sort clustering algorithm. The proposed method offers a better tradeoff between classification error and computational complexity, making it a particularly strong choice for on-chip spike sorting.

Multichannel Convolutional Neural Network for Biological Relation Extraction.

PubMed

Quan, Chanqin; Hua, Lei; Sun, Xiao; Bai, Wenjun

2016-01-01

The plethora of biomedical relations which are embedded in medical logs (records) demands researchers' attention. Previous theoretical and practical focuses were restricted on traditional machine learning techniques. However, these methods are susceptible to the issues of "vocabulary gap" and data sparseness and the unattainable automation process in feature extraction. To address aforementioned issues, in this work, we propose a multichannel convolutional neural network (MCCNN) for automated biomedical relation extraction. The proposed model has the following two contributions: (1) it enables the fusion of multiple (e.g., five) versions in word embeddings; (2) the need for manual feature engineering can be obviated by automated feature learning with convolutional neural network (CNN). We evaluated our model on two biomedical relation extraction tasks: drug-drug interaction (DDI) extraction and protein-protein interaction (PPI) extraction. For DDI task, our system achieved an overall f -score of 70.2% compared to the standard linear SVM based system (e.g., 67.0%) on DDIExtraction 2013 challenge dataset. And for PPI task, we evaluated our system on Aimed and BioInfer PPI corpus; our system exceeded the state-of-art ensemble SVM system by 2.7% and 5.6% on f -scores.

Applying the multivariate time-rescaling theorem to neural population models

PubMed Central

Gerhard, Felipe; Haslinger, Robert; Pipa, Gordon

2011-01-01

Statistical models of neural activity are integral to modern neuroscience. Recently, interest has grown in modeling the spiking activity of populations of simultaneously recorded neurons to study the effects of correlations and functional connectivity on neural information processing. However any statistical model must be validated by an appropriate goodness-of-fit test. Kolmogorov-Smirnov tests based upon the time-rescaling theorem have proven to be useful for evaluating point-process-based statistical models of single-neuron spike trains. Here we discuss the extension of the time-rescaling theorem to the multivariate (neural population) case. We show that even in the presence of strong correlations between spike trains, models which neglect couplings between neurons can be erroneously passed by the univariate time-rescaling test. We present the multivariate version of the time-rescaling theorem, and provide a practical step-by-step procedure for applying it towards testing the sufficiency of neural population models. Using several simple analytically tractable models and also more complex simulated and real data sets, we demonstrate that important features of the population activity can only be detected using the multivariate extension of the test. PMID:21395436

Urban Area Detection in Very High Resolution Remote Sensing Images Using Deep Convolutional Neural Networks.

PubMed

Tian, Tian; Li, Chang; Xu, Jinkang; Ma, Jiayi

2018-03-18

Detecting urban areas from very high resolution (VHR) remote sensing images plays an important role in the field of Earth observation. The recently-developed deep convolutional neural networks (DCNNs), which can extract rich features from training data automatically, have achieved outstanding performance on many image classification databases. Motivated by this fact, we propose a new urban area detection method based on DCNNs in this paper. The proposed method mainly includes three steps: (i) a visual dictionary is obtained based on the deep features extracted by pre-trained DCNNs; (ii) urban words are learned from labeled images; (iii) the urban regions are detected in a new image based on the nearest dictionary word criterion. The qualitative and quantitative experiments on different datasets demonstrate that the proposed method can obtain a remarkable overall accuracy (OA) and kappa coefficient. Moreover, it can also strike a good balance between the true positive rate (TPR) and false positive rate (FPR).

A CNN based neurobiology inspired approach for retinal image quality assessment.

PubMed

Mahapatra, Dwarikanath; Roy, Pallab K; Sedai, Suman; Garnavi, Rahil

2016-08-01

Retinal image quality assessment (IQA) algorithms use different hand crafted features for training classifiers without considering the working of the human visual system (HVS) which plays an important role in IQA. We propose a convolutional neural network (CNN) based approach that determines image quality using the underlying principles behind the working of the HVS. CNNs provide a principled approach to feature learning and hence higher accuracy in decision making. Experimental results demonstrate the superior performance of our proposed algorithm over competing methods.

A neural network detection model of spilled oil based on the texture analysis of SAR image

NASA Astrophysics Data System (ADS)

An, Jubai; Zhu, Lisong

2006-01-01

A Radial Basis Function Neural Network (RBFNN) Model is investigated for the detection of spilled oil based on the texture analysis of SAR imagery. In this paper, to take the advantage of the abundant texture information of SAR imagery, the texture features are extracted by both wavelet transform and the Gray Level Co-occurrence matrix. The RBFNN Model is fed with a vector of these texture features. The RBFNN Model is trained and tested by the sample data set of the feature vectors. Finally, a SAR image is classified by this model. The classification results of a spilled oil SAR image show that the classification accuracy for oil spill is 86.2 by the RBFNN Model using both wavelet texture and gray texture, while the classification accuracy for oil spill is 78.0 by same RBFNN Model using only wavelet texture as the input of this RBFNN model. The model using both wavelet transform and the Gray Level Co-occurrence matrix is more effective than that only using wavelet texture. Furthermore, it keeps the complicated proximity and has a good performance of classification.

Yarn-dyed fabric defect classification based on convolutional neural network

NASA Astrophysics Data System (ADS)

Jing, Junfeng; Dong, Amei; Li, Pengfei; Zhang, Kaibing

2017-09-01

Considering that manual inspection of the yarn-dyed fabric can be time consuming and inefficient, we propose a yarn-dyed fabric defect classification method by using a convolutional neural network (CNN) based on a modified AlexNet. CNN shows powerful ability in performing feature extraction and fusion by simulating the learning mechanism of human brain. The local response normalization layers in AlexNet are replaced by the batch normalization layers, which can enhance both the computational efficiency and classification accuracy. In the training process of the network, the characteristics of the defect are extracted step by step and the essential features of the image can be obtained from the fusion of the edge details with several convolution operations. Then the max-pooling layers, the dropout layers, and the fully connected layers are employed in the classification model to reduce the computation cost and extract more precise features of the defective fabric. Finally, the results of the defect classification are predicted by the softmax function. The experimental results show promising performance with an acceptable average classification rate and strong robustness on yarn-dyed fabric defect classification.

Classifying dysmorphic syndromes by using artificial neural network based hierarchical decision tree.

PubMed

Özdemir, Merve Erkınay; Telatar, Ziya; Eroğul, Osman; Tunca, Yusuf

2018-05-01

Dysmorphic syndromes have different facial malformations. These malformations are significant to an early diagnosis of dysmorphic syndromes and contain distinctive information for face recognition. In this study we define the certain features of each syndrome by considering facial malformations and classify Fragile X, Hurler, Prader Willi, Down, Wolf Hirschhorn syndromes and healthy groups automatically. The reference points are marked on the face images and ratios between the points' distances are taken into consideration as features. We suggest a neural network based hierarchical decision tree structure in order to classify the syndrome types. We also implement k-nearest neighbor (k-NN) and artificial neural network (ANN) classifiers to compare classification accuracy with our hierarchical decision tree. The classification accuracy is 50, 73 and 86.7% with k-NN, ANN and hierarchical decision tree methods, respectively. Then, the same images are shown to a clinical expert who achieve a recognition rate of 46.7%. We develop an efficient system to recognize different syndrome types automatically in a simple, non-invasive imaging data, which is independent from the patient's age, sex and race at high accuracy. The promising results indicate that our method can be used for pre-diagnosis of the dysmorphic syndromes by clinical experts.

Investigating the effect of traditional Persian music on ECG signals in young women using wavelet transform and neural networks.

PubMed

Abedi, Behzad; Abbasi, Ataollah; Goshvarpour, Atefeh

2017-05-01

In the past few decades, several studies have reported the physiological effects of listening to music. The physiological effects of different music types on different people are different. In the present study, we aimed to examine the effects of listening to traditional Persian music on electrocardiogram (ECG) signals in young women. Twenty-two healthy females participated in this study. ECG signals were recorded under two conditions: rest and music. For each ECG signal, 20 morphological and wavelet-based features were selected. Artificial neural network (ANN) and probabilistic neural network (PNN) classifiers were used for the classification of ECG signals during and before listening to music. Collected data were separated into two data sets: train and test. Classification accuracies of 88% and 97% were achieved in train data sets using ANN and PNN, respectively. In addition, the test data set was employed for evaluating the classifiers, and classification rates of 84% and 93% were obtained using ANN and PNN, respectively. The present study investigated the effect of music on ECG signals based on wavelet transform and morphological features. The results obtained here can provide a good understanding on the effects of music on ECG signals to researchers.

Neural correlates of novelty and appropriateness processing in externally induced constraint relaxation.

PubMed

Huang, Furong; Tang, Shuang; Sun, Pei; Luo, Jing

2018-05-15

Novelty and appropriateness are considered the two fundamental features of creative thinking, including insight problem solving, which can be performed through chunk decomposition and constraint relaxation. Based on a previous study that separated the neural bases of novelty and appropriateness in chunk decomposition, in this study, we used event-related functional magnetic resonance imaging (fMRI) to further dissociate these mechanisms in constraint relaxation. Participants were guided to mentally represent the method of problem solving according to the externally provided solutions that were elaborately prepared in advance and systematically varied in their novelty and appropriateness for the given problem situation. The results showed that novelty processing was completed by the temporoparietal junction (TPJ) and regions in the executive system (dorsolateral prefrontal cortex [DLPFC]), whereas appropriateness processing was completed by the TPJ and regions in the episodic memory (hippocampus), emotion (amygdala), and reward systems (orbitofrontal cortex [OFC]). These results likely indicate that appropriateness processing can result in a more memorable and richer experience than novelty processing in constraint relaxation. The shared and distinct neural mechanisms of the features of novelty and appropriateness in constraint relaxation are discussed, enriching the representation of the change theory of insight. Copyright © 2018 Elsevier Inc. All rights reserved.

Integrated built-in-test false and missed alarms reduction based on forward infinite impulse response & recurrent finite impulse response dynamic neural networks

NASA Astrophysics Data System (ADS)

Cui, Yiqian; Shi, Junyou; Wang, Zili

2017-11-01

Built-in tests (BITs) are widely used in mechanical systems to perform state identification, whereas the BIT false and missed alarms cause trouble to the operators or beneficiaries to make correct judgments. Artificial neural networks (ANN) are previously used for false and missed alarms identification, which has the features such as self-organizing and self-study. However, these ANN models generally do not incorporate the temporal effect of the bottom-level threshold comparison outputs and the historical temporal features are not fully considered. To improve the situation, this paper proposes a new integrated BIT design methodology by incorporating a novel type of dynamic neural networks (DNN) model. The new DNN model is termed as Forward IIR & Recurrent FIR DNN (FIRF-DNN), where its component neurons, network structures, and input/output relationships are discussed. The condition monitoring false and missed alarms reduction implementation scheme based on FIRF-DNN model is also illustrated, which is composed of three stages including model training, false and missed alarms detection, and false and missed alarms suppression. Finally, the proposed methodology is demonstrated in the application study and the experimental results are analyzed.

Automated system for characterization and classification of malaria-infected stages using light microscopic images of thin blood smears.

PubMed

Das, D K; Maiti, A K; Chakraborty, C

2015-03-01

In this paper, we propose a comprehensive image characterization cum classification framework for malaria-infected stage detection using microscopic images of thin blood smears. The methodology mainly includes microscopic imaging of Leishman stained blood slides, noise reduction and illumination correction, erythrocyte segmentation, feature selection followed by machine classification. Amongst three-image segmentation algorithms (namely, rule-based, Chan-Vese-based and marker-controlled watershed methods), marker-controlled watershed technique provides better boundary detection of erythrocytes specially in overlapping situations. Microscopic features at intensity, texture and morphology levels are extracted to discriminate infected and noninfected erythrocytes. In order to achieve subgroup of potential features, feature selection techniques, namely, F-statistic and information gain criteria are considered here for ranking. Finally, five different classifiers, namely, Naive Bayes, multilayer perceptron neural network, logistic regression, classification and regression tree (CART), RBF neural network have been trained and tested by 888 erythrocytes (infected and noninfected) for each features' subset. Performance evaluation of the proposed methodology shows that multilayer perceptron network provides higher accuracy for malaria-infected erythrocytes recognition and infected stage classification. Results show that top 90 features ranked by F-statistic (specificity: 98.64%, sensitivity: 100%, PPV: 99.73% and overall accuracy: 96.84%) and top 60 features ranked by information gain provides better results (specificity: 97.29%, sensitivity: 100%, PPV: 99.46% and overall accuracy: 96.73%) for malaria-infected stage classification. © 2014 The Authors Journal of Microscopy © 2014 Royal Microscopical Society.

PrAS: Prediction of amidation sites using multiple feature extraction.

PubMed

Wang, Tong; Zheng, Wei; Wuyun, Qiqige; Wu, Zhenfeng; Ruan, Jishou; Hu, Gang; Gao, Jianzhao

2017-02-01

Amidation plays an important role in a variety of pathological processes and serious diseases like neural dysfunction and hypertension. However, identification of protein amidation sites through traditional experimental methods is time consuming and expensive. In this paper, we proposed a novel predictor for Prediction of Amidation Sites (PrAS), which is the first software package for academic users. The method incorporated four representative feature types, which are position-based features, physicochemical and biochemical properties features, predicted structure-based features and evolutionary information features. A novel feature selection method, positive contribution feature selection was proposed to optimize features. PrAS achieved AUC of 0.96, accuracy of 92.1%, sensitivity of 81.2%, specificity of 94.9% and MCC of 0.76 on the independent test set. PrAS is freely available at https://sourceforge.net/p/praspkg. Copyright © 2016 Elsevier Ltd. All rights reserved.

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.

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.

Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule.

PubMed

Liu, Hui; Song, Yongduan; Xue, Fangzheng; Li, Xiumin

2015-11-01

In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than the SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.

Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule

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

Liu, Hui; Song, Yongduan; Xue, Fangzheng

In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than themore » SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.« less

ANNA: A Convolutional Neural Network Code for Spectroscopic Analysis

NASA Astrophysics Data System (ADS)

Lee-Brown, Donald; Anthony-Twarog, Barbara J.; Twarog, Bruce A.

2018-01-01

We present ANNA, a Python-based convolutional neural network code for the automated analysis of stellar spectra. ANNA provides a flexible framework that allows atmospheric parameters such as temperature and metallicity to be determined with accuracies comparable to those of established but less efficient techniques. ANNA performs its parameterization extremely quickly; typically several thousand spectra can be analyzed in less than a second. Additionally, the code incorporates features which greatly speed up the training process necessary for the neural network to measure spectra accurately, resulting in a tool that can easily be run on a single desktop or laptop computer. Thus, ANNA is useful in an era when spectrographs increasingly have the capability to collect dozens to hundreds of spectra each night. This talk will cover the basic features included in ANNA and demonstrate its performance in two use cases: an open cluster abundance analysis involving several hundred spectra, and a metal-rich field star study. Applicability of the code to large survey datasets will also be discussed.

Detection of broken rotor bar faults in induction motor at low load using neural network.

PubMed

Bessam, B; Menacer, A; Boumehraz, M; Cherif, H

2016-09-01

The knowledge of the broken rotor bars characteristic frequencies and amplitudes has a great importance for all related diagnostic methods. The monitoring of motor faults requires a high resolution spectrum to separate different frequency components. The Discrete Fourier Transform (DFT) has been widely used to achieve these requirements. However, at low slip this technique cannot give good results. As a solution for these problems, this paper proposes an efficient technique based on a neural network approach and Hilbert transform (HT) for broken rotor bar diagnosis in induction machines at low load. The Hilbert transform is used to extract the stator current envelope (SCE). Two features are selected from the (SCE) spectrum (the amplitude and frequency of the harmonic). These features will be used as input for neural network. The results obtained are astonishing and it is capable to detect the correct number of broken rotor bars under different load conditions. Copyright © 2016 ISA. Published by Elsevier Ltd. All rights reserved.

Similarity estimation for reference image retrieval in mammograms using convolutional neural network

NASA Astrophysics Data System (ADS)

Muramatsu, Chisako; Higuchi, Shunichi; Morita, Takako; Oiwa, Mikinao; Fujita, Hiroshi

2018-02-01

Periodic breast cancer screening with mammography is considered effective in decreasing breast cancer mortality. For screening programs to be successful, an intelligent image analytic system may support radiologists' efficient image interpretation. In our previous studies, we have investigated image retrieval schemes for diagnostic references of breast lesions on mammograms and ultrasound images. Using a machine learning method, reliable similarity measures that agree with radiologists' similarity were determined and relevant images could be retrieved. However, our previous method includes a feature extraction step, in which hand crafted features were determined based on manual outlines of the masses. Obtaining the manual outlines of masses is not practical in clinical practice and such data would be operator-dependent. In this study, we investigated a similarity estimation scheme using a convolutional neural network (CNN) to skip such procedure and to determine data-driven similarity scores. By using CNN as feature extractor, in which extracted features were employed in determination of similarity measures with a conventional 3-layered neural network, the determined similarity measures were correlated well with the subjective ratings and the precision of retrieving diagnostically relevant images was comparable with that of the conventional method using handcrafted features. By using CNN for determination of similarity measure directly, the result was also comparable. By optimizing the network parameters, results may be further improved. The proposed method has a potential usefulness in determination of similarity measure without precise lesion outlines for retrieval of similar mass images on mammograms.

A Markovian event-based framework for stochastic spiking neural networks.

PubMed

Touboul, Jonathan D; Faugeras, Olivier D

2011-11-01

In spiking neural networks, the information is conveyed by the spike times, that depend on the intrinsic dynamics of each neuron, the input they receive and on the connections between neurons. In this article we study the Markovian nature of the sequence of spike times in stochastic neural networks, and in particular the ability to deduce from a spike train the next spike time, and therefore produce a description of the network activity only based on the spike times regardless of the membrane potential process. To study this question in a rigorous manner, we introduce and study an event-based description of networks of noisy integrate-and-fire neurons, i.e. that is based on the computation of the spike times. We show that the firing times of the neurons in the networks constitute a Markov chain, whose transition probability is related to the probability distribution of the interspike interval of the neurons in the network. In the cases where the Markovian model can be developed, the transition probability is explicitly derived in such classical cases of neural networks as the linear integrate-and-fire neuron models with excitatory and inhibitory interactions, for different types of synapses, possibly featuring noisy synaptic integration, transmission delays and absolute and relative refractory period. This covers most of the cases that have been investigated in the event-based description of spiking deterministic neural networks.

Optimal Non-Invasive Fault Classification Model for Packaged Ceramic Tile Quality Monitoring Using MMW Imaging

NASA Astrophysics Data System (ADS)

Agarwal, Smriti; Singh, Dharmendra

2016-04-01

Millimeter wave (MMW) frequency has emerged as an efficient tool for different stand-off imaging applications. In this paper, we have dealt with a novel MMW imaging application, i.e., non-invasive packaged goods quality estimation for industrial quality monitoring applications. An active MMW imaging radar operating at 60 GHz has been ingeniously designed for concealed fault estimation. Ceramic tiles covered with commonly used packaging cardboard were used as concealed targets for undercover fault classification. A comparison of computer vision-based state-of-the-art feature extraction techniques, viz, discrete Fourier transform (DFT), wavelet transform (WT), principal component analysis (PCA), gray level co-occurrence texture (GLCM), and histogram of oriented gradient (HOG) has been done with respect to their efficient and differentiable feature vector generation capability for undercover target fault classification. An extensive number of experiments were performed with different ceramic tile fault configurations, viz., vertical crack, horizontal crack, random crack, diagonal crack along with the non-faulty tiles. Further, an independent algorithm validation was done demonstrating classification accuracy: 80, 86.67, 73.33, and 93.33 % for DFT, WT, PCA, GLCM, and HOG feature-based artificial neural network (ANN) classifier models, respectively. Classification results show good capability for HOG feature extraction technique towards non-destructive quality inspection with appreciably low false alarm as compared to other techniques. Thereby, a robust and optimal image feature-based neural network classification model has been proposed for non-invasive, automatic fault monitoring for a financially and commercially competent industrial growth.

Exploring Neural Network Models with Hierarchical Memories and Their Use in Modeling Biological Systems

NASA Astrophysics Data System (ADS)

Pusuluri, Sai Teja

Energy landscapes are often used as metaphors for phenomena in biology, social sciences and finance. Different methods have been implemented in the past for the construction of energy landscapes. Neural network models based on spin glass physics provide an excellent mathematical framework for the construction of energy landscapes. This framework uses a minimal number of parameters and constructs the landscape using data from the actual phenomena. In the past neural network models were used to mimic the storage and retrieval process of memories (patterns) in the brain. With advances in the field now, these models are being used in machine learning, deep learning and modeling of complex phenomena. Most of the past literature focuses on increasing the storage capacity and stability of stored patterns in the network but does not study these models from a modeling perspective or an energy landscape perspective. This dissertation focuses on neural network models both from a modeling perspective and from an energy landscape perspective. I firstly show how the cellular interconversion phenomenon can be modeled as a transition between attractor states on an epigenetic landscape constructed using neural network models. The model allows the identification of a reaction coordinate of cellular interconversion by analyzing experimental and simulation time course data. Monte Carlo simulations of the model show that the initial phase of cellular interconversion is a Poisson process and the later phase of cellular interconversion is a deterministic process. Secondly, I explore the static features of landscapes generated using neural network models, such as sizes of basins of attraction and densities of metastable states. The simulation results show that the static landscape features are strongly dependent on the correlation strength and correlation structure between patterns. Using different hierarchical structures of the correlation between patterns affects the landscape features. These results show how the static landscape features can be controlled by adjusting the correlations between patterns. Finally, I explore the dynamical features of landscapes generated using neural network models such as the stability of minima and the transition rates between minima. The results from this project show that the stability depends on the correlations between patterns. It is also found that the transition rates between minima strongly depend on the type of bias applied and the correlation between patterns. The results from this part of the dissertation can be useful in engineering an energy landscape without even having the complete information about the associated minima of the landscape.

Neural Signatures of Stimulus Features in Visual Working Memory—A Spatiotemporal Approach

PubMed Central

Jackson, Margaret C.; Klein, Christoph; Mohr, Harald; Shapiro, Kimron L.; Linden, David E. J.

2010-01-01

We examined the neural signatures of stimulus features in visual working memory (WM) by integrating functional magnetic resonance imaging (fMRI) and event-related potential data recorded during mental manipulation of colors, rotation angles, and color–angle conjunctions. The N200, negative slow wave, and P3b were modulated by the information content of WM, and an fMRI-constrained source model revealed a progression in neural activity from posterior visual areas to higher order areas in the ventral and dorsal processing streams. Color processing was associated with activity in inferior frontal gyrus during encoding and retrieval, whereas angle processing involved right parietal regions during the delay interval. WM for color–angle conjunctions did not involve any additional neural processes. The finding that different patterns of brain activity underlie WM for color and spatial information is consistent with ideas that the ventral/dorsal “what/where” segregation of perceptual processing influences WM organization. The absence of characteristic signatures of conjunction-related brain activity, which was generally intermediate between the 2 single conditions, suggests that conjunction judgments are based on the coordinated activity of these 2 streams. PMID:19429863

Cortical processing of dynamic sound envelope transitions.

PubMed

Zhou, Yi; Wang, Xiaoqin

2010-12-08

Slow envelope fluctuations in the range of 2-20 Hz provide important segmental cues for processing communication sounds. For a successful segmentation, a neural processor must capture envelope features associated with the rise and fall of signal energy, a process that is often challenged by the interference of background noise. This study investigated the neural representations of slowly varying envelopes in quiet and in background noise in the primary auditory cortex (A1) of awake marmoset monkeys. We characterized envelope features based on the local average and rate of change of sound level in envelope waveforms and identified envelope features to which neurons were selective by reverse correlation. Our results showed that envelope feature selectivity of A1 neurons was correlated with the degree of nonmonotonicity in their static rate-level functions. Nonmonotonic neurons exhibited greater feature selectivity than monotonic neurons in quiet and in background noise. The diverse envelope feature selectivity decreased spike-timing correlation among A1 neurons in response to the same envelope waveforms. As a result, the variability, but not the average, of the ensemble responses of A1 neurons represented more faithfully the dynamic transitions in low-frequency sound envelopes both in quiet and in background noise.

Multi-Level and Multi-Scale Feature Aggregation Using Pretrained Convolutional Neural Networks for Music Auto-Tagging

NASA Astrophysics Data System (ADS)

Lee, Jongpil; Nam, Juhan

2017-08-01

Music auto-tagging is often handled in a similar manner to image classification by regarding the 2D audio spectrogram as image data. However, music auto-tagging is distinguished from image classification in that the tags are highly diverse and have different levels of abstractions. Considering this issue, we propose a convolutional neural networks (CNN)-based architecture that embraces multi-level and multi-scaled features. The architecture is trained in three steps. First, we conduct supervised feature learning to capture local audio features using a set of CNNs with different input sizes. Second, we extract audio features from each layer of the pre-trained convolutional networks separately and aggregate them altogether given a long audio clip. Finally, we put them into fully-connected networks and make final predictions of the tags. Our experiments show that using the combination of multi-level and multi-scale features is highly effective in music auto-tagging and the proposed method outperforms previous state-of-the-arts on the MagnaTagATune dataset and the Million Song Dataset. We further show that the proposed architecture is useful in transfer learning.

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.

Event-driven processing for hardware-efficient neural spike sorting

NASA Astrophysics Data System (ADS)

Liu, Yan; Pereira, João L.; Constandinou, Timothy G.

2018-02-01

Objective. The prospect of real-time and on-node spike sorting provides a genuine opportunity to push the envelope of large-scale integrated neural recording systems. In such systems the hardware resources, power requirements and data bandwidth increase linearly with channel count. Event-based (or data-driven) processing can provide here a new efficient means for hardware implementation that is completely activity dependant. In this work, we investigate using continuous-time level-crossing sampling for efficient data representation and subsequent spike processing. Approach. (1) We first compare signals (synthetic neural datasets) encoded with this technique against conventional sampling. (2) We then show how such a representation can be directly exploited by extracting simple time domain features from the bitstream to perform neural spike sorting. (3) The proposed method is implemented in a low power FPGA platform to demonstrate its hardware viability. Main results. It is observed that considerably lower data rates are achievable when using 7 bits or less to represent the signals, whilst maintaining the signal fidelity. Results obtained using both MATLAB and reconfigurable logic hardware (FPGA) indicate that feature extraction and spike sorting accuracies can be achieved with comparable or better accuracy than reference methods whilst also requiring relatively low hardware resources. Significance. By effectively exploiting continuous-time data representation, neural signal processing can be achieved in a completely event-driven manner, reducing both the required resources (memory, complexity) and computations (operations). This will see future large-scale neural systems integrating on-node processing in real-time hardware.

Neural networks for data compression and invariant image recognition

NASA Technical Reports Server (NTRS)

Gardner, Sheldon

1989-01-01

An approach to invariant image recognition (I2R), based upon a model of biological vision in the mammalian visual system (MVS), is described. The complete I2R model incorporates several biologically inspired features: exponential mapping of retinal images, Gabor spatial filtering, and a neural network associative memory. In the I2R model, exponentially mapped retinal images are filtered by a hierarchical set of Gabor spatial filters (GSF) which provide compression of the information contained within a pixel-based image. A neural network associative memory (AM) is used to process the GSF coded images. We describe a 1-D shape function method for coding of scale and rotationally invariant shape information. This method reduces image shape information to a periodic waveform suitable for coding as an input vector to a neural network AM. The shape function method is suitable for near term applications on conventional computing architectures equipped with VLSI FFT chips to provide a rapid image search capability.

Competition in high dimensional spaces using a sparse approximation of neural fields.

PubMed

Quinton, Jean-Charles; Girau, Bernard; Lefort, Mathieu

2011-01-01

The Continuum Neural Field Theory implements competition within topologically organized neural networks with lateral inhibitory connections. However, due to the polynomial complexity of matrix-based implementations, updating dense representations of the activity becomes computationally intractable when an adaptive resolution or an arbitrary number of input dimensions is required. This paper proposes an alternative to self-organizing maps with a sparse implementation based on Gaussian mixture models, promoting a trade-off in redundancy for higher computational efficiency and alleviating constraints on the underlying substrate.This version reproduces the emergent attentional properties of the original equations, by directly applying them within a continuous approximation of a high dimensional neural field. The model is compatible with preprocessed sensory flows but can also be interfaced with artificial systems. This is particularly important for sensorimotor systems, where decisions and motor actions must be taken and updated in real-time. Preliminary tests are performed on a reactive color tracking application, using spatially distributed color features.

Adaptive Backstepping-Based Neural Tracking Control for MIMO Nonlinear Switched Systems Subject to Input Delays.

PubMed

Niu, Ben; Li, Lu

2018-06-01

This brief proposes a new neural-network (NN)-based adaptive output tracking control scheme for a class of disturbed multiple-input multiple-output uncertain nonlinear switched systems with input delays. By combining the universal approximation ability of radial basis function NNs and adaptive backstepping recursive design with an improved multiple Lyapunov function (MLF) scheme, a novel adaptive neural output tracking controller design method is presented for the switched system. The feature of the developed design is that different coordinate transformations are adopted to overcome the conservativeness caused by adopting a common coordinate transformation for all subsystems. It is shown that all the variables of the resulting closed-loop system are semiglobally uniformly ultimately bounded under a class of switching signals in the presence of MLF and that the system output can follow the desired reference signal. To demonstrate the practicability of the obtained result, an adaptive neural output tracking controller is designed for a mass-spring-damper system.

Identifying Patients with Atrioventricular Septal Defect in Down Syndrome Populations by Using Self-Normalizing Neural Networks and Feature Selection.

PubMed

Pan, Xiaoyong; Hu, Xiaohua; Zhang, Yu Hang; Feng, Kaiyan; Wang, Shao Peng; Chen, Lei; Huang, Tao; Cai, Yu Dong

2018-04-12

Atrioventricular septal defect (AVSD) is a clinically significant subtype of congenital heart disease (CHD) that severely influences the health of babies during birth and is associated with Down syndrome (DS). Thus, exploring the differences in functional genes in DS samples with and without AVSD is a critical way to investigate the complex association between AVSD and DS. In this study, we present a computational method to distinguish DS patients with AVSD from those without AVSD using the newly proposed self-normalizing neural network (SNN). First, each patient was encoded by using the copy number of probes on chromosome 21. The encoded features were ranked by the reliable Monte Carlo feature selection (MCFS) method to obtain a ranked feature list. Based on this feature list, we used a two-stage incremental feature selection to construct two series of feature subsets and applied SNNs to build classifiers to identify optimal features. Results show that 2737 optimal features were obtained, and the corresponding optimal SNN classifier constructed on optimal features yielded a Matthew's correlation coefficient (MCC) value of 0.748. For comparison, random forest was also used to build classifiers and uncover optimal features. This method received an optimal MCC value of 0.582 when top 132 features were utilized. Finally, we analyzed some key features derived from the optimal features in SNNs found in literature support to further reveal their essential roles.

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.

Village Building Identification Based on Ensemble Convolutional Neural Networks

PubMed Central

Guo, Zhiling; Chen, Qi; Xu, Yongwei; Shibasaki, Ryosuke; Shao, Xiaowei

2017-01-01

In this study, we present the Ensemble Convolutional Neural Network (ECNN), an elaborate CNN frame formulated based on ensembling state-of-the-art CNN models, to identify village buildings from open high-resolution remote sensing (HRRS) images. First, to optimize and mine the capability of CNN for village mapping and to ensure compatibility with our classification targets, a few state-of-the-art models were carefully optimized and enhanced based on a series of rigorous analyses and evaluations. Second, rather than directly implementing building identification by using these models, we exploited most of their advantages by ensembling their feature extractor parts into a stronger model called ECNN based on the multiscale feature learning method. Finally, the generated ECNN was applied to a pixel-level classification frame to implement object identification. The proposed method can serve as a viable tool for village building identification with high accuracy and efficiency. The experimental results obtained from the test area in Savannakhet province, Laos, prove that the proposed ECNN model significantly outperforms existing methods, improving overall accuracy from 96.64% to 99.26%, and kappa from 0.57 to 0.86. PMID:29084154

Network-centric decision architecture for financial or 1/f data models

NASA Astrophysics Data System (ADS)

Jaenisch, Holger M.; Handley, James W.; Massey, Stoney; Case, Carl T.; Songy, Claude G.

2002-12-01

This paper presents a decision architecture algorithm for training neural equation based networks to make autonomous multi-goal oriented, multi-class decisions. These architectures make decisions based on their individual goals and draw from the same network centric feature set. Traditionally, these architectures are comprised of neural networks that offer marginal performance due to lack of convergence of the training set. We present an approach for autonomously extracting sample points as I/O exemplars for generation of multi-branch, multi-node decision architectures populated by adaptively derived neural equations. To test the robustness of this architecture, open source data sets in the form of financial time series were used, requiring a three-class decision space analogous to the lethal, non-lethal, and clutter discrimination problem. This algorithm and the results of its application are presented here.

Neural dynamics underlying attentional orienting to auditory representations in short-term memory.

PubMed

Backer, Kristina C; Binns, Malcolm A; Alain, Claude

2015-01-21

Sounds are ephemeral. Thus, coherent auditory perception depends on "hearing" back in time: retrospectively attending that which was lost externally but preserved in short-term memory (STM). Current theories of auditory attention assume that sound features are integrated into a perceptual object, that multiple objects can coexist in STM, and that attention can be deployed to an object in STM. Recording electroencephalography from humans, we tested these assumptions, elucidating feature-general and feature-specific neural correlates of auditory attention to STM. Alpha/beta oscillations and frontal and posterior event-related potentials indexed feature-general top-down attentional control to one of several coexisting auditory representations in STM. Particularly, task performance during attentional orienting was correlated with alpha/low-beta desynchronization (i.e., power suppression). However, attention to one feature could occur without simultaneous processing of the second feature of the representation. Therefore, auditory attention to memory relies on both feature-specific and feature-general neural dynamics. Copyright © 2015 the authors 0270-6474/15/351307-12$15.00/0.

Computer vision-based method for classification of wheat grains using artificial neural network.

PubMed

Sabanci, Kadir; Kayabasi, Ahmet; Toktas, Abdurrahim

2017-06-01

A simplified computer vision-based application using artificial neural network (ANN) depending on multilayer perceptron (MLP) for accurately classifying wheat grains into bread or durum is presented. The images of 100 bread and 100 durum wheat grains are taken via a high-resolution camera and subjected to pre-processing. The main visual features of four dimensions, three colors and five textures are acquired using image-processing techniques (IPTs). A total of 21 visual features are reproduced from the 12 main features to diversify the input population for training and testing the ANN model. The data sets of visual features are considered as input parameters of the ANN model. The ANN with four different input data subsets is modelled to classify the wheat grains into bread or durum. The ANN model is trained with 180 grains and its accuracy tested with 20 grains from a total of 200 wheat grains. Seven input parameters that are most effective on the classifying results are determined using the correlation-based CfsSubsetEval algorithm to simplify the ANN model. The results of the ANN model are compared in terms of accuracy rate. The best result is achieved with a mean absolute error (MAE) of 9.8 × 10 -6 by the simplified ANN model. This shows that the proposed classifier based on computer vision can be successfully exploited to automatically classify a variety of grains. © 2016 Society of Chemical Industry. © 2016 Society of Chemical Industry.

Neural synchronization during face-to-face communication.

PubMed

Jiang, Jing; Dai, Bohan; Peng, Danling; Zhu, Chaozhe; Liu, Li; Lu, Chunming

2012-11-07

Although the human brain may have evolutionarily adapted to face-to-face communication, other modes of communication, e.g., telephone and e-mail, increasingly dominate our modern daily life. This study examined the neural difference between face-to-face communication and other types of communication by simultaneously measuring two brains using a hyperscanning approach. The results showed a significant increase in the neural synchronization in the left inferior frontal cortex during a face-to-face dialog between partners but none during a back-to-back dialog, a face-to-face monologue, or a back-to-back monologue. Moreover, the neural synchronization between partners during the face-to-face dialog resulted primarily from the direct interactions between the partners, including multimodal sensory information integration and turn-taking behavior. The communicating behavior during the face-to-face dialog could be predicted accurately based on the neural synchronization level. These results suggest that face-to-face communication, particularly dialog, has special neural features that other types of communication do not have and that the neural synchronization between partners may underlie successful face-to-face communication.

A three-dimensional image processing program for accurate, rapid, and semi-automated segmentation of neuronal somata with dense neurite outgrowth

PubMed Central

Ross, James D.; Cullen, D. Kacy; Harris, James P.; LaPlaca, Michelle C.; DeWeerth, Stephen P.

2015-01-01

Three-dimensional (3-D) image analysis techniques provide a powerful means to rapidly and accurately assess complex morphological and functional interactions between neural cells. Current software-based identification methods of neural cells generally fall into two applications: (1) segmentation of cell nuclei in high-density constructs or (2) tracing of cell neurites in single cell investigations. We have developed novel methodologies to permit the systematic identification of populations of neuronal somata possessing rich morphological detail and dense neurite arborization throughout thick tissue or 3-D in vitro constructs. The image analysis incorporates several novel automated features for the discrimination of neurites and somata by initially classifying features in 2-D and merging these classifications into 3-D objects; the 3-D reconstructions automatically identify and adjust for over and under segmentation errors. Additionally, the platform provides for software-assisted error corrections to further minimize error. These features attain very accurate cell boundary identifications to handle a wide range of morphological complexities. We validated these tools using confocal z-stacks from thick 3-D neural constructs where neuronal somata had varying degrees of neurite arborization and complexity, achieving an accuracy of ≥95%. We demonstrated the robustness of these algorithms in a more complex arena through the automated segmentation of neural cells in ex vivo brain slices. These novel methods surpass previous techniques by improving the robustness and accuracy by: (1) the ability to process neurites and somata, (2) bidirectional segmentation correction, and (3) validation via software-assisted user input. This 3-D image analysis platform provides valuable tools for the unbiased analysis of neural tissue or tissue surrogates within a 3-D context, appropriate for the study of multi-dimensional cell-cell and cell-extracellular matrix interactions. PMID:26257609

Automated detection of videotaped neonatal seizures of epileptic origin.

PubMed

Karayiannis, Nicolaos B; Xiong, Yaohua; Tao, Guozhi; Frost, James D; Wise, Merrill S; Hrachovy, Richard A; Mizrahi, Eli M

2006-06-01

This study aimed at the development of a seizure-detection system by training neural networks with quantitative motion information extracted from short video segments of neonatal seizures of the myoclonic and focal clonic types and random infant movements. The motion of the infants' body parts was quantified by temporal motion-strength signals extracted from video segments by motion-segmentation methods based on optical flow computation. The area of each frame occupied by the infants' moving body parts was segmented by clustering the motion parameters obtained by fitting an affine model to the pixel velocities. The motion of the infants' body parts also was quantified by temporal motion-trajectory signals extracted from video recordings by robust motion trackers based on block-motion models. These motion trackers were developed to adjust autonomously to illumination and contrast changes that may occur during the video-frame sequence. Video segments were represented by quantitative features obtained by analyzing motion-strength and motion-trajectory signals in both the time and frequency domains. Seizure recognition was performed by conventional feed-forward neural networks, quantum neural networks, and cosine radial basis function neural networks, which were trained to detect neonatal seizures of the myoclonic and focal clonic types and to distinguish them from random infant movements. The computational tools and procedures developed for automated seizure detection were evaluated on a set of 240 video segments of 54 patients exhibiting myoclonic seizures (80 segments), focal clonic seizures (80 segments), and random infant movements (80 segments). Regardless of the decision scheme used for interpreting the responses of the trained neural networks, all the neural network models exhibited sensitivity and specificity>90%. For one of the decision schemes proposed for interpreting the responses of the trained neural networks, the majority of the trained neural-network models exhibited sensitivity>90% and specificity>95%. In particular, cosine radial basis function neural networks achieved the performance targets of this phase of the project (i.e., sensitivity>95% and specificity>95%). The best among the motion segmentation and tracking methods developed in this study produced quantitative features that constitute a reliable basis for detecting neonatal seizures. The performance targets of this phase of the project were achieved by combining the quantitative features obtained by analyzing motion-strength signals with those produced by analyzing motion-trajectory signals. The computational procedures and tools developed in this study to perform off-line analysis of short video segments will be used in the next phase of this project, which involves the integration of these procedures and tools into a system that can process and analyze long video recordings of infants monitored for seizures in real time.

Imbalance aware lithography hotspot detection: a deep learning approach

NASA Astrophysics Data System (ADS)

Yang, Haoyu; Luo, Luyang; Su, Jing; Lin, Chenxi; Yu, Bei

2017-03-01

With the advancement of VLSI technology nodes, light diffraction caused lithographic hotspots have become a serious problem affecting manufacture yield. Lithography hotspot detection at the post-OPC stage is imperative to check potential circuit failures when transferring designed patterns onto silicon wafers. Although conventional lithography hotspot detection methods, such as machine learning, have gained satisfactory performance, with extreme scaling of transistor feature size and more and more complicated layout patterns, conventional methodologies may suffer from performance degradation. For example, manual or ad hoc feature extraction in a machine learning framework may lose important information when predicting potential errors in ultra-large-scale integrated circuit masks. In this paper, we present a deep convolutional neural network (CNN) targeting representative feature learning in lithography hotspot detection. We carefully analyze impact and effectiveness of different CNN hyper-parameters, through which a hotspot-detection-oriented neural network model is established. Because hotspot patterns are always minorities in VLSI mask design, the training data set is highly imbalanced. In this situation, a neural network is no longer reliable, because a trained model with high classification accuracy may still suffer from high false negative results (missing hotspots), which is fatal in hotspot detection problems. To address the imbalance problem, we further apply minority upsampling and random-mirror flipping before training the network. Experimental results show that our proposed neural network model achieves highly comparable or better performance on the ICCAD 2012 contest benchmark compared to state-of-the-art hotspot detectors based on deep or representative machine leaning.

Automatic QRS complex detection using two-level convolutional neural network.

PubMed

Xiang, Yande; Lin, Zhitao; Meng, Jianyi

2018-01-29

The QRS complex is the most noticeable feature in the electrocardiogram (ECG) signal, therefore, its detection is critical for ECG signal analysis. The existing detection methods largely depend on hand-crafted manual features and parameters, which may introduce significant computational complexity, especially in the transform domains. In addition, fixed features and parameters are not suitable for detecting various kinds of QRS complexes under different circumstances. In this study, based on 1-D convolutional neural network (CNN), an accurate method for QRS complex detection is proposed. The CNN consists of object-level and part-level CNNs for extracting different grained ECG morphological features automatically. All the extracted morphological features are used by multi-layer perceptron (MLP) for QRS complex detection. Additionally, a simple ECG signal preprocessing technique which only contains difference operation in temporal domain is adopted. Based on the MIT-BIH arrhythmia (MIT-BIH-AR) database, the proposed detection method achieves overall sensitivity Sen = 99.77%, positive predictivity rate PPR = 99.91%, and detection error rate DER = 0.32%. In addition, the performance variation is performed according to different signal-to-noise ratio (SNR) values. An automatic QRS detection method using two-level 1-D CNN and simple signal preprocessing technique is proposed for QRS complex detection. Compared with the state-of-the-art QRS complex detection approaches, experimental results show that the proposed method acquires comparable accuracy.

Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data

NASA Astrophysics Data System (ADS)

Jia, Feng; Lei, Yaguo; Lin, Jing; Zhou, Xin; Lu, Na

2016-05-01

Aiming to promptly process the massive fault data and automatically provide accurate diagnosis results, numerous studies have been conducted on intelligent fault diagnosis of rotating machinery. Among these studies, the methods based on artificial neural networks (ANNs) are commonly used, which employ signal processing techniques for extracting features and further input the features to ANNs for classifying faults. Though these methods did work in intelligent fault diagnosis of rotating machinery, they still have two deficiencies. (1) The features are manually extracted depending on much prior knowledge about signal processing techniques and diagnostic expertise. In addition, these manual features are extracted according to a specific diagnosis issue and probably unsuitable for other issues. (2) The ANNs adopted in these methods have shallow architectures, which limits the capacity of ANNs to learn the complex non-linear relationships in fault diagnosis issues. As a breakthrough in artificial intelligence, deep learning holds the potential to overcome the aforementioned deficiencies. Through deep learning, deep neural networks (DNNs) with deep architectures, instead of shallow ones, could be established to mine the useful information from raw data and approximate complex non-linear functions. Based on DNNs, a novel intelligent method is proposed in this paper to overcome the deficiencies of the aforementioned intelligent diagnosis methods. The effectiveness of the proposed method is validated using datasets from rolling element bearings and planetary gearboxes. These datasets contain massive measured signals involving different health conditions under various operating conditions. The diagnosis results show that the proposed method is able to not only adaptively mine available fault characteristics from the measured signals, but also obtain superior diagnosis accuracy compared with the existing methods.

Rock images classification by using deep convolution neural network

NASA Astrophysics Data System (ADS)

Cheng, Guojian; Guo, Wenhui

2017-08-01

Granularity analysis is one of the most essential issues in authenticate under microscope. To improve the efficiency and accuracy of traditional manual work, an convolutional neural network based method is proposed for granularity analysis from thin section image, which chooses and extracts features from image samples while build classifier to recognize granularity of input image samples. 4800 samples from Ordos basin are used for experiments under colour spaces of HSV, YCbCr and RGB respectively. On the test dataset, the correct rate in RGB colour space is 98.5%, and it is believable in HSV and YCbCr colour space. The results show that the convolution neural network can classify the rock images with high reliability.

Body size and shape misperception and visual adaptation: An overview of an emerging research paradigm.

PubMed

Challinor, Kirsten L; Mond, Jonathan; Stephen, Ian D; Mitchison, Deborah; Stevenson, Richard J; Hay, Phillipa; Brooks, Kevin R

2017-12-01

Although body size and shape misperception (BSSM) is a common feature of anorexia nervosa, bulimia nervosa and muscle dysmorphia, little is known about its underlying neural mechanisms. Recently, a new approach has emerged, based on the long-established non-invasive technique of perceptual adaptation, which allows for inferences about the structure of the neural apparatus responsible for alterations in visual appearance. Here, we describe several recent experimental examples of BSSM, wherein exposure to "extreme" body stimuli causes visual aftereffects of biased perception. The implications of these studies for our understanding of the neural and cognitive representation of human bodies, along with their implications for clinical practice are discussed.

Two-stage neural-network-based technique for Urdu character two-dimensional shape representation, classification, and recognition

NASA Astrophysics Data System (ADS)

Megherbi, Dalila B.; Lodhi, S. M.; Boulenouar, A. J.

2001-03-01

This work is in the field of automated document processing. This work addresses the problem of representation and recognition of Urdu characters using Fourier representation and a Neural Network architecture. In particular, we show that a two-stage Neural Network scheme is used here to make classification of 36 Urdu characters into seven sub-classes namely subclasses characterized by seven proposed and defined fuzzy features specifically related to Urdu characters. We show that here Fourier Descriptors and Neural Network provide a remarkably simple way to draw definite conclusions from vague, ambiguous, noisy or imprecise information. In particular, we illustrate the concept of interest regions and describe a framing method that provides a way to make the proposed technique for Urdu characters recognition robust and invariant to scaling and translation. We also show that a given character rotation is dealt with by using the Hotelling transform. This transform is based upon the eigenvalue decomposition of the covariance matrix of an image, providing a method of determining the orientation of the major axis of an object within an image. Finally experimental results are presented to show the power and robustness of the proposed two-stage Neural Network based technique for Urdu character recognition, its fault tolerance, and high recognition accuracy.

Information based universal feature extraction

NASA Astrophysics Data System (ADS)

Amiri, Mohammad; Brause, Rüdiger

2015-02-01

In many real world image based pattern recognition tasks, the extraction and usage of task-relevant features are the most crucial part of the diagnosis. In the standard approach, they mostly remain task-specific, although humans who perform such a task always use the same image features, trained in early childhood. It seems that universal feature sets exist, but they are not yet systematically found. In our contribution, we tried to find those universal image feature sets that are valuable for most image related tasks. In our approach, we trained a neural network by natural and non-natural images of objects and background, using a Shannon information-based algorithm and learning constraints. The goal was to extract those features that give the most valuable information for classification of visual objects hand-written digits. This will give a good start and performance increase for all other image learning tasks, implementing a transfer learning approach. As result, in our case we found that we could indeed extract features which are valid in all three kinds of tasks.

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.

How does the 'rest-self overlap' mediate the qualitative and automatic features of self-reference?

PubMed

Northoff, Georg

2016-01-01

The target article points out the qualitative and automatic features of self-reference while leaving open the underlying neural mechanisms. Based on empirical evidence about rest-self overlap and rest-stimulus interaction being special for self-related stimuli, I postulate that the resting state shows self-specific organization. The resting state's self-specific organization may be encoded by activity balances between different networks which in turn predispose the qualitative features of subsequent self-related stimulus-induced activity in, for instance, SAN as well as the automatic features of self-reference effects.

A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification

NASA Astrophysics Data System (ADS)

Cao, Jianfang; Chen, Lichao; Wang, Min; Shi, Hao; Tian, Yun

2016-12-01

Image classification uses computers to simulate human understanding and cognition of images by automatically categorizing images. This study proposes a faster image classification approach that parallelizes the traditional Adaboost-Backpropagation (BP) neural network using the MapReduce parallel programming model. First, we construct a strong classifier by assembling the outputs of 15 BP neural networks (which are individually regarded as weak classifiers) based on the Adaboost algorithm. Second, we design Map and Reduce tasks for both the parallel Adaboost-BP neural network and the feature extraction algorithm. Finally, we establish an automated classification model by building a Hadoop cluster. We use the Pascal VOC2007 and Caltech256 datasets to train and test the classification model. The results are superior to those obtained using traditional Adaboost-BP neural network or parallel BP neural network approaches. Our approach increased the average classification accuracy rate by approximately 14.5% and 26.0% compared to the traditional Adaboost-BP neural network and parallel BP neural network, respectively. Furthermore, the proposed approach requires less computation time and scales very well as evaluated by speedup, sizeup and scaleup. The proposed approach may provide a foundation for automated large-scale image classification and demonstrates practical value.

A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification.

PubMed

Cao, Jianfang; Chen, Lichao; Wang, Min; Shi, Hao; Tian, Yun

2016-12-01

Image classification uses computers to simulate human understanding and cognition of images by automatically categorizing images. This study proposes a faster image classification approach that parallelizes the traditional Adaboost-Backpropagation (BP) neural network using the MapReduce parallel programming model. First, we construct a strong classifier by assembling the outputs of 15 BP neural networks (which are individually regarded as weak classifiers) based on the Adaboost algorithm. Second, we design Map and Reduce tasks for both the parallel Adaboost-BP neural network and the feature extraction algorithm. Finally, we establish an automated classification model by building a Hadoop cluster. We use the Pascal VOC2007 and Caltech256 datasets to train and test the classification model. The results are superior to those obtained using traditional Adaboost-BP neural network or parallel BP neural network approaches. Our approach increased the average classification accuracy rate by approximately 14.5% and 26.0% compared to the traditional Adaboost-BP neural network and parallel BP neural network, respectively. Furthermore, the proposed approach requires less computation time and scales very well as evaluated by speedup, sizeup and scaleup. The proposed approach may provide a foundation for automated large-scale image classification and demonstrates practical value.

A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification

PubMed Central

Cao, Jianfang; Chen, Lichao; Wang, Min; Shi, Hao; Tian, Yun

2016-01-01

Image classification uses computers to simulate human understanding and cognition of images by automatically categorizing images. This study proposes a faster image classification approach that parallelizes the traditional Adaboost-Backpropagation (BP) neural network using the MapReduce parallel programming model. First, we construct a strong classifier by assembling the outputs of 15 BP neural networks (which are individually regarded as weak classifiers) based on the Adaboost algorithm. Second, we design Map and Reduce tasks for both the parallel Adaboost-BP neural network and the feature extraction algorithm. Finally, we establish an automated classification model by building a Hadoop cluster. We use the Pascal VOC2007 and Caltech256 datasets to train and test the classification model. The results are superior to those obtained using traditional Adaboost-BP neural network or parallel BP neural network approaches. Our approach increased the average classification accuracy rate by approximately 14.5% and 26.0% compared to the traditional Adaboost-BP neural network and parallel BP neural network, respectively. Furthermore, the proposed approach requires less computation time and scales very well as evaluated by speedup, sizeup and scaleup. The proposed approach may provide a foundation for automated large-scale image classification and demonstrates practical value. PMID:27905520

Real-time object-to-features vectorisation via Siamese neural networks

NASA Astrophysics Data System (ADS)

Fedorenko, Fedor; Usilin, Sergey

2017-03-01

Object-to-features vectorisation is a hard problem to solve for objects that can be hard to distinguish. Siamese and Triplet neural networks are one of the more recent tools used for such task. However, most networks used are very deep networks that prove to be hard to compute in the Internet of Things setting. In this paper, a computationally efficient neural network is proposed for real-time object-to-features vectorisation into a Euclidean metric space. We use L2 distance to reflect feature vector similarity during both training and testing. In this way, feature vectors we develop can be easily classified using K-Nearest Neighbours classifier. Such approach can be used to train networks to vectorise such "problematic" objects like images of human faces, keypoint image patches, like keypoints on Arctic maps and surrounding marine areas.

Emergent Auditory Feature Tuning in a Real-Time Neuromorphic VLSI System.

PubMed

Sheik, Sadique; Coath, Martin; Indiveri, Giacomo; Denham, Susan L; Wennekers, Thomas; Chicca, Elisabetta

2012-01-01

Many sounds of ecological importance, such as communication calls, are characterized by time-varying spectra. However, most neuromorphic auditory models to date have focused on distinguishing mainly static patterns, under the assumption that dynamic patterns can be learned as sequences of static ones. In contrast, the emergence of dynamic feature sensitivity through exposure to formative stimuli has been recently modeled in a network of spiking neurons based on the thalamo-cortical architecture. The proposed network models the effect of lateral and recurrent connections between cortical layers, distance-dependent axonal transmission delays, and learning in the form of Spike Timing Dependent Plasticity (STDP), which effects stimulus-driven changes in the pattern of network connectivity. In this paper we demonstrate how these principles can be efficiently implemented in neuromorphic hardware. In doing so we address two principle problems in the design of neuromorphic systems: real-time event-based asynchronous communication in multi-chip systems, and the realization in hybrid analog/digital VLSI technology of neural computational principles that we propose underlie plasticity in neural processing of dynamic stimuli. The result is a hardware neural network that learns in real-time and shows preferential responses, after exposure, to stimuli exhibiting particular spectro-temporal patterns. The availability of hardware on which the model can be implemented, makes this a significant step toward the development of adaptive, neurobiologically plausible, spike-based, artificial sensory systems.

Emergent Auditory Feature Tuning in a Real-Time Neuromorphic VLSI System

PubMed Central

Sheik, Sadique; Coath, Martin; Indiveri, Giacomo; Denham, Susan L.; Wennekers, Thomas; Chicca, Elisabetta

2011-01-01

Many sounds of ecological importance, such as communication calls, are characterized by time-varying spectra. However, most neuromorphic auditory models to date have focused on distinguishing mainly static patterns, under the assumption that dynamic patterns can be learned as sequences of static ones. In contrast, the emergence of dynamic feature sensitivity through exposure to formative stimuli has been recently modeled in a network of spiking neurons based on the thalamo-cortical architecture. The proposed network models the effect of lateral and recurrent connections between cortical layers, distance-dependent axonal transmission delays, and learning in the form of Spike Timing Dependent Plasticity (STDP), which effects stimulus-driven changes in the pattern of network connectivity. In this paper we demonstrate how these principles can be efficiently implemented in neuromorphic hardware. In doing so we address two principle problems in the design of neuromorphic systems: real-time event-based asynchronous communication in multi-chip systems, and the realization in hybrid analog/digital VLSI technology of neural computational principles that we propose underlie plasticity in neural processing of dynamic stimuli. The result is a hardware neural network that learns in real-time and shows preferential responses, after exposure, to stimuli exhibiting particular spectro-temporal patterns. The availability of hardware on which the model can be implemented, makes this a significant step toward the development of adaptive, neurobiologically plausible, spike-based, artificial sensory systems. PMID:22347163

Distinct contributions of functional and deep neural network features to representational similarity of scenes in human brain and behavior

PubMed Central

Greene, Michelle R; Baldassano, Christopher; Fei-Fei, Li; Beck, Diane M; Baker, Chris I

2018-01-01

Inherent correlations between visual and semantic features in real-world scenes make it difficult to determine how different scene properties contribute to neural representations. Here, we assessed the contributions of multiple properties to scene representation by partitioning the variance explained in human behavioral and brain measurements by three feature models whose inter-correlations were minimized a priori through stimulus preselection. Behavioral assessments of scene similarity reflected unique contributions from a functional feature model indicating potential actions in scenes as well as high-level visual features from a deep neural network (DNN). In contrast, similarity of cortical responses in scene-selective areas was uniquely explained by mid- and high-level DNN features only, while an object label model did not contribute uniquely to either domain. The striking dissociation between functional and DNN features in their contribution to behavioral and brain representations of scenes indicates that scene-selective cortex represents only a subset of behaviorally relevant scene information. PMID:29513219

Distinct contributions of functional and deep neural network features to representational similarity of scenes in human brain and behavior.

PubMed

Groen, Iris Ia; Greene, Michelle R; Baldassano, Christopher; Fei-Fei, Li; Beck, Diane M; Baker, Chris I

2018-03-07

Inherent correlations between visual and semantic features in real-world scenes make it difficult to determine how different scene properties contribute to neural representations. Here, we assessed the contributions of multiple properties to scene representation by partitioning the variance explained in human behavioral and brain measurements by three feature models whose inter-correlations were minimized a priori through stimulus preselection. Behavioral assessments of scene similarity reflected unique contributions from a functional feature model indicating potential actions in scenes as well as high-level visual features from a deep neural network (DNN). In contrast, similarity of cortical responses in scene-selective areas was uniquely explained by mid- and high-level DNN features only, while an object label model did not contribute uniquely to either domain. The striking dissociation between functional and DNN features in their contribution to behavioral and brain representations of scenes indicates that scene-selective cortex represents only a subset of behaviorally relevant scene information.

Learning high-level features for chord recognition using Autoencoder

NASA Astrophysics Data System (ADS)

Phongthongloa, Vilailukkana; Kamonsantiroj, Suwatchai; Pipanmaekaporn, Luepol

2016-07-01

Chord transcription is valuable to do by itself. It is known that the manual transcription of chords is very tiresome, time-consuming. It requires, moreover, musical knowledge. Automatic chord recognition has recently attracted a number of researches in the Music Information Retrieval field. It has known that a pitch class profile (PCP) is the commonly signal representation of musical harmonic analysis. However, the PCP may contain additional non-harmonic noise such as harmonic overtones and transient noise. The problem of non-harmonic might be generating the sound energy in term of frequency more than the actual notes of the respective chord. Autoencoder neural network may be trained to learn a mapping from low level feature to one or more higher-level representation. These high-level representations can explain dependencies of the inputs and reduce the effect of non-harmonic noise. Then these improve features are fed into neural network classifier. The proposed high-level musical features show 80.90% of accuracy. The experimental results have shown that the proposed approach can achieve better performance in comparison with other based method.

Deep neural network features for horses identity recognition using multiview horses' face pattern

NASA Astrophysics Data System (ADS)

Jarraya, Islem; Ouarda, Wael; Alimi, Adel M.

2017-03-01

To control the state of horses in the born, breeders needs a monitoring system with a surveillance camera that can identify and distinguish between horses. We proposed in [5] a method of horse's identification at a distance using the frontal facial biometric modality. Due to the change of views, the face recognition becomes more difficult. In this paper, the number of images used in our THoDBRL'2015 database (Tunisian Horses DataBase of Regim Lab) is augmented by adding other images of other views. Thus, we used front, right and left profile face's view. Moreover, we suggested an approach for multiview face recognition. First, we proposed to use the Gabor filter for face characterization. Next, due to the augmentation of the number of images, and the large number of Gabor features, we proposed to test the Deep Neural Network with the auto-encoder to obtain the more pertinent features and to reduce the size of features vector. Finally, we performed the proposed approach on our THoDBRL'2015 database and we used the linear SVM for classification.

Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream.

PubMed

Güçlü, Umut; van Gerven, Marcel A J

2015-07-08

Converging evidence suggests that the primate ventral visual pathway encodes increasingly complex stimulus features in downstream areas. We quantitatively show that there indeed exists an explicit gradient for feature complexity in the ventral pathway of the human brain. This was achieved by mapping thousands of stimulus features of increasing complexity across the cortical sheet using a deep neural network. Our approach also revealed a fine-grained functional specialization of downstream areas of the ventral stream. Furthermore, it allowed decoding of representations from human brain activity at an unsurpassed degree of accuracy, confirming the quality of the developed approach. Stimulus features that successfully explained neural responses indicate that population receptive fields were explicitly tuned for object categorization. This provides strong support for the hypothesis that object categorization is a guiding principle in the functional organization of the primate ventral stream. Copyright © 2015 the authors 0270-6474/15/3510005-10$15.00/0.

Ratiometric Decoding of Pheromones for a Biomimetic Infochemical Communication System.

PubMed

Wei, Guangfen; Thomas, Sanju; Cole, Marina; Rácz, Zoltán; Gardner, Julian W

2017-10-30

Biosynthetic infochemical communication is an emerging scientific field employing molecular compounds for information transmission, labelling, and biochemical interfacing; having potential application in diverse areas ranging from pest management to group coordination of swarming robots. Our communication system comprises a chemoemitter module that encodes information by producing volatile pheromone components and a chemoreceiver module that decodes the transmitted ratiometric information via polymer-coated piezoelectric Surface Acoustic Wave Resonator (SAWR) sensors. The inspiration for such a system is based on the pheromone-based communication between insects. Ten features are extracted from the SAWR sensor response and analysed using multi-variate classification techniques, i.e., Linear Discriminant Analysis (LDA), Probabilistic Neural Network (PNN), and Multilayer Perception Neural Network (MLPNN) methods, and an optimal feature subset is identified. A combination of steady state and transient features of the sensor signals showed superior performances with LDA and MLPNN. Although MLPNN gave excellent results reaching 100% recognition rate at 400 s, over all time stations PNN gave the best performance based on an expanded data-set with adjacent neighbours. In this case, 100% of the pheromone mixtures were successfully identified just 200 s after they were first injected into the wind tunnel. We believe that this approach can be used for future chemical communication employing simple mixtures of airborne molecules.

Ratiometric Decoding of Pheromones for a Biomimetic Infochemical Communication System

PubMed Central

Wei, Guangfen; Thomas, Sanju; Cole, Marina; Rácz, Zoltán

2017-01-01

Biosynthetic infochemical communication is an emerging scientific field employing molecular compounds for information transmission, labelling, and biochemical interfacing; having potential application in diverse areas ranging from pest management to group coordination of swarming robots. Our communication system comprises a chemoemitter module that encodes information by producing volatile pheromone components and a chemoreceiver module that decodes the transmitted ratiometric information via polymer-coated piezoelectric Surface Acoustic Wave Resonator (SAWR) sensors. The inspiration for such a system is based on the pheromone-based communication between insects. Ten features are extracted from the SAWR sensor response and analysed using multi-variate classification techniques, i.e., Linear Discriminant Analysis (LDA), Probabilistic Neural Network (PNN), and Multilayer Perception Neural Network (MLPNN) methods, and an optimal feature subset is identified. A combination of steady state and transient features of the sensor signals showed superior performances with LDA and MLPNN. Although MLPNN gave excellent results reaching 100% recognition rate at 400 s, over all time stations PNN gave the best performance based on an expanded data-set with adjacent neighbours. In this case, 100% of the pheromone mixtures were successfully identified just 200 s after they were first injected into the wind tunnel. We believe that this approach can be used for future chemical communication employing simple mixtures of airborne molecules. PMID:29084158

Image fusion algorithm based on energy of Laplacian and PCNN

NASA Astrophysics Data System (ADS)

Li, Meili; Wang, Hongmei; Li, Yanjun; Zhang, Ke

2009-12-01

Owing to the global coupling and pulse synchronization characteristic of pulse coupled neural networks (PCNN), it has been proved to be suitable for image processing and successfully employed in image fusion. However, in almost all the literatures of image processing about PCNN, linking strength of each neuron is assigned the same value which is chosen by experiments. This is not consistent with the human vision system in which the responses to the region with notable features are stronger than that to the region with nonnotable features. It is more reasonable that notable features, rather than the same value, are employed to linking strength of each neuron. As notable feature, energy of Laplacian (EOL) is used to obtain the value of linking strength in PCNN in this paper. Experimental results demonstrate that the proposed algorithm outperforms Laplacian-based, wavelet-based, PCNN -based fusion algorithms.

Adaptive pattern recognition by mini-max neural networks as a part of an intelligent processor

NASA Technical Reports Server (NTRS)

Szu, Harold H.

1990-01-01

In this decade and progressing into 21st Century, NASA will have missions including Space Station and the Earth related Planet Sciences. To support these missions, a high degree of sophistication in machine automation and an increasing amount of data processing throughput rate are necessary. Meeting these challenges requires intelligent machines, designed to support the necessary automations in a remote space and hazardous environment. There are two approaches to designing these intelligent machines. One of these is the knowledge-based expert system approach, namely AI. The other is a non-rule approach based on parallel and distributed computing for adaptive fault-tolerances, namely Neural or Natural Intelligence (NI). The union of AI and NI is the solution to the problem stated above. The NI segment of this unit extracts features automatically by applying Cauchy simulated annealing to a mini-max cost energy function. The feature discovered by NI can then be passed to the AI system for future processing, and vice versa. This passing increases reliability, for AI can follow the NI formulated algorithm exactly, and can provide the context knowledge base as the constraints of neurocomputing. The mini-max cost function that solves the unknown feature can furthermore give us a top-down architectural design of neural networks by means of Taylor series expansion of the cost function. A typical mini-max cost function consists of the sample variance of each class in the numerator, and separation of the center of each class in the denominator. Thus, when the total cost energy is minimized, the conflicting goals of intraclass clustering and interclass segregation are achieved simultaneously.

NSDann2BS, a neutron spectrum unfolding code based on neural networks technology and two bonner spheres

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

Ortiz-Rodriguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.

In this work a neutron spectrum unfolding code, based on artificial intelligence technology is presented. The code called ''Neutron Spectrometry and Dosimetry with Artificial Neural Networks and two Bonner spheres'', (NSDann2BS), was designed in a graphical user interface under the LabVIEW programming environment. The main features of this code are to use an embedded artificial neural network architecture optimized with the ''Robust design of artificial neural networks methodology'' and to use two Bonner spheres as the only piece of information. In order to build the code here presented, once the net topology was optimized and properly trained, knowledge stored atmore » synaptic weights was extracted and using a graphical framework build on the LabVIEW programming environment, the NSDann2BS code was designed. This code is friendly, intuitive and easy to use for the end user. The code is freely available upon request to authors. To demonstrate the use of the neural net embedded in the NSDann2BS code, the rate counts of {sup 252}Cf, {sup 241}AmBe and {sup 239}PuBe neutron sources measured with a Bonner spheres system.« less

Neural network-based preprocessing to estimate the parameters of the X-ray emission of a single-temperature thermal plasma

NASA Astrophysics Data System (ADS)

Ichinohe, Y.; Yamada, S.; Miyazaki, N.; Saito, S.

2018-04-01

We present data preprocessing based on an artificial neural network to estimate the parameters of the X-ray emission spectra of a single-temperature thermal plasma. The method finds appropriate parameters close to the global optimum. The neural network is designed to learn the parameters of the thermal plasma (temperature, abundance, normalization and redshift) of the input spectra. After training using 9000 simulated X-ray spectra, the network has grown to predict all the unknown parameters with uncertainties of about a few per cent. The performance dependence on the network structure has been studied. We applied the neural network to an actual high-resolution spectrum obtained with Hitomi. The predicted plasma parameters agree with the known best-fitting parameters of the Perseus cluster within uncertainties of ≲10 per cent. The result shows that neural networks trained by simulated data might possibly be used to extract a feature built in the data. This would reduce human-intensive preprocessing costs before detailed spectral analysis, and would help us make the best use of the large quantities of spectral data that will be available in the coming decades.

NSDann2BS, a neutron spectrum unfolding code based on neural networks technology and two bonner spheres

NASA Astrophysics Data System (ADS)

Ortiz-Rodríguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Solís Sánches, L. O.; Miranda, R. Castañeda; Cervantes Viramontes, J. M.; Vega-Carrillo, H. R.

2013-07-01

In this work a neutron spectrum unfolding code, based on artificial intelligence technology is presented. The code called "Neutron Spectrometry and Dosimetry with Artificial Neural Networks and two Bonner spheres", (NSDann2BS), was designed in a graphical user interface under the LabVIEW programming environment. The main features of this code are to use an embedded artificial neural network architecture optimized with the "Robust design of artificial neural networks methodology" and to use two Bonner spheres as the only piece of information. In order to build the code here presented, once the net topology was optimized and properly trained, knowledge stored at synaptic weights was extracted and using a graphical framework build on the LabVIEW programming environment, the NSDann2BS code was designed. This code is friendly, intuitive and easy to use for the end user. The code is freely available upon request to authors. To demonstrate the use of the neural net embedded in the NSDann2BS code, the rate counts of 252Cf, 241AmBe and 239PuBe neutron sources measured with a Bonner spheres system.

Model Of Neural Network With Creative Dynamics

NASA Technical Reports Server (NTRS)

Zak, Michail; Barhen, Jacob

1993-01-01

Paper presents analysis of mathematical model of one-neuron/one-synapse neural network featuring coupled activation and learning dynamics and parametrical periodic excitation. Demonstrates self-programming, partly random behavior of suitable designed neural network; believed to be related to spontaneity and creativity of biological neural networks.

Biased Dropout and Crossmap Dropout: Learning towards effective Dropout regularization in convolutional neural network.

PubMed

Poernomo, Alvin; Kang, Dae-Ki

2018-08-01

Training a deep neural network with a large number of parameters often leads to overfitting problem. Recently, Dropout has been introduced as a simple, yet effective regularization approach to combat overfitting in such models. Although Dropout has shown remarkable results on many deep neural network cases, its actual effect on CNN has not been thoroughly explored. Moreover, training a Dropout model will significantly increase the training time as it takes longer time to converge than a non-Dropout model with the same architecture. To deal with these issues, we address Biased Dropout and Crossmap Dropout, two novel approaches of Dropout extension based on the behavior of hidden units in CNN model. Biased Dropout divides the hidden units in a certain layer into two groups based on their magnitude and applies different Dropout rate to each group appropriately. Hidden units with higher activation value, which give more contributions to the network final performance, will be retained by a lower Dropout rate, while units with lower activation value will be exposed to a higher Dropout rate to compensate the previous part. The second approach is Crossmap Dropout, which is an extension of the regular Dropout in convolution layer. Each feature map in a convolution layer has a strong correlation between each other, particularly in every identical pixel location in each feature map. Crossmap Dropout tries to maintain this important correlation yet at the same time break the correlation between each adjacent pixel with respect to all feature maps by applying the same Dropout mask to all feature maps, so that all pixels or units in equivalent positions in each feature map will be either dropped or active during training. Our experiment with various benchmark datasets shows that our approaches provide better generalization than the regular Dropout. Moreover, our Biased Dropout takes faster time to converge during training phase, suggesting that assigning noise appropriately in hidden units can lead to an effective regularization. Copyright © 2018 Elsevier Ltd. All rights reserved.

A Hybrid Neuro-Fuzzy Model For Integrating Large Earth-Science Datasets

NASA Astrophysics Data System (ADS)

Porwal, A.; Carranza, J.; Hale, M.

2004-12-01

A GIS-based hybrid neuro-fuzzy approach to integration of large earth-science datasets for mineral prospectivity mapping is described. It implements a Takagi-Sugeno type fuzzy inference system in the framework of a four-layered feed-forward adaptive neural network. Each unique combination of the datasets is considered a feature vector whose components are derived by knowledge-based ordinal encoding of the constituent datasets. A subset of feature vectors with a known output target vector (i.e., unique conditions known to be associated with either a mineralized or a barren location) is used for the training of an adaptive neuro-fuzzy inference system. Training involves iterative adjustment of parameters of the adaptive neuro-fuzzy inference system using a hybrid learning procedure for mapping each training vector to its output target vector with minimum sum of squared error. The trained adaptive neuro-fuzzy inference system is used to process all feature vectors. The output for each feature vector is a value that indicates the extent to which a feature vector belongs to the mineralized class or the barren class. These values are used to generate a prospectivity map. The procedure is demonstrated by an application to regional-scale base metal prospectivity mapping in a study area located in the Aravalli metallogenic province (western India). A comparison of the hybrid neuro-fuzzy approach with pure knowledge-driven fuzzy and pure data-driven neural network approaches indicates that the former offers a superior method for integrating large earth-science datasets for predictive spatial mathematical modelling.

Early Visual Cortex Dynamics during Top-Down Modulated Shifts of Feature-Selective Attention.

PubMed

Müller, Matthias M; Trautmann, Mireille; Keitel, Christian

2016-04-01

Shifting attention from one color to another color or from color to another feature dimension such as shape or orientation is imperative when searching for a certain object in a cluttered scene. Most attention models that emphasize feature-based selection implicitly assume that all shifts in feature-selective attention underlie identical temporal dynamics. Here, we recorded time courses of behavioral data and steady-state visual evoked potentials (SSVEPs), an objective electrophysiological measure of neural dynamics in early visual cortex to investigate temporal dynamics when participants shifted attention from color or orientation toward color or orientation, respectively. SSVEPs were elicited by four random dot kinematograms that flickered at different frequencies. Each random dot kinematogram was composed of dashes that uniquely combined two features from the dimensions color (red or blue) and orientation (slash or backslash). Participants were cued to attend to one feature (such as color or orientation) and respond to coherent motion targets of the to-be-attended feature. We found that shifts toward color occurred earlier after the shifting cue compared with shifts toward orientation, regardless of the original feature (i.e., color or orientation). This was paralleled in SSVEP amplitude modulations as well as in the time course of behavioral data. Overall, our results suggest different neural dynamics during shifts of attention from color and orientation and the respective shifting destinations, namely, either toward color or toward orientation.

Dynamical principles in neuroscience

NASA Astrophysics Data System (ADS)

Rabinovich, Mikhail I.; Varona, Pablo; Selverston, Allen I.; Abarbanel, Henry D. I.

2006-10-01

Dynamical modeling of neural systems and brain functions has a history of success over the last half century. This includes, for example, the explanation and prediction of some features of neural rhythmic behaviors. Many interesting dynamical models of learning and memory based on physiological experiments have been suggested over the last two decades. Dynamical models even of consciousness now exist. Usually these models and results are based on traditional approaches and paradigms of nonlinear dynamics including dynamical chaos. Neural systems are, however, an unusual subject for nonlinear dynamics for several reasons: (i) Even the simplest neural network, with only a few neurons and synaptic connections, has an enormous number of variables and control parameters. These make neural systems adaptive and flexible, and are critical to their biological function. (ii) In contrast to traditional physical systems described by well-known basic principles, first principles governing the dynamics of neural systems are unknown. (iii) Many different neural systems exhibit similar dynamics despite having different architectures and different levels of complexity. (iv) The network architecture and connection strengths are usually not known in detail and therefore the dynamical analysis must, in some sense, be probabilistic. (v) Since nervous systems are able to organize behavior based on sensory inputs, the dynamical modeling of these systems has to explain the transformation of temporal information into combinatorial or combinatorial-temporal codes, and vice versa, for memory and recognition. In this review these problems are discussed in the context of addressing the stimulating questions: What can neuroscience learn from nonlinear dynamics, and what can nonlinear dynamics learn from neuroscience?

Dynamical principles in neuroscience

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

Rabinovich, Mikhail I.; Varona, Pablo; Selverston, Allen I.

Dynamical modeling of neural systems and brain functions has a history of success over the last half century. This includes, for example, the explanation and prediction of some features of neural rhythmic behaviors. Many interesting dynamical models of learning and memory based on physiological experiments have been suggested over the last two decades. Dynamical models even of consciousness now exist. Usually these models and results are based on traditional approaches and paradigms of nonlinear dynamics including dynamical chaos. Neural systems are, however, an unusual subject for nonlinear dynamics for several reasons: (i) Even the simplest neural network, with only amore » few neurons and synaptic connections, has an enormous number of variables and control parameters. These make neural systems adaptive and flexible, and are critical to their biological function. (ii) In contrast to traditional physical systems described by well-known basic principles, first principles governing the dynamics of neural systems are unknown. (iii) Many different neural systems exhibit similar dynamics despite having different architectures and different levels of complexity. (iv) The network architecture and connection strengths are usually not known in detail and therefore the dynamical analysis must, in some sense, be probabilistic. (v) Since nervous systems are able to organize behavior based on sensory inputs, the dynamical modeling of these systems has to explain the transformation of temporal information into combinatorial or combinatorial-temporal codes, and vice versa, for memory and recognition. In this review these problems are discussed in the context of addressing the stimulating questions: What can neuroscience learn from nonlinear dynamics, and what can nonlinear dynamics learn from neuroscience?.« less

Feature-Based Change Detection Reveals Inconsistent Individual Differences in Visual Working Memory Capacity.

PubMed

Ambrose, Joseph P; Wijeakumar, Sobanawartiny; Buss, Aaron T; Spencer, John P

2016-01-01

Visual working memory (VWM) is a key cognitive system that enables people to hold visual information in mind after a stimulus has been removed and compare past and present to detect changes that have occurred. VWM is severely capacity limited to around 3-4 items, although there are robust individual differences in this limit. Importantly, these individual differences are evident in neural measures of VWM capacity. Here, we capitalized on recent work showing that capacity is lower for more complex stimulus dimension. In particular, we asked whether individual differences in capacity remain consistent if capacity is shifted by a more demanding task, and, further, whether the correspondence between behavioral and neural measures holds across a shift in VWM capacity. Participants completed a change detection (CD) task with simple colors and complex shapes in an fMRI experiment. As expected, capacity was significantly lower for the shape dimension. Moreover, there were robust individual differences in behavioral estimates of VWM capacity across dimensions. Similarly, participants with a stronger BOLD response for color also showed a strong neural response for shape within the lateral occipital cortex, intraparietal sulcus (IPS), and superior IPS. Although there were robust individual differences in the behavioral and neural measures, we found little evidence of systematic brain-behavior correlations across feature dimensions. This suggests that behavioral and neural measures of capacity provide different views onto the processes that underlie VWM and CD. Recent theoretical approaches that attempt to bridge between behavioral and neural measures are well positioned to address these findings in future work.

Object Recognition using Feature- and Color-Based Methods

NASA Technical Reports Server (NTRS)

Duong, Tuan; Duong, Vu; Stubberud, Allen

2008-01-01

An improved adaptive method of processing image data in an artificial neural network has been developed to enable automated, real-time recognition of possibly moving objects under changing (including suddenly changing) conditions of illumination and perspective. The method involves a combination of two prior object-recognition methods one based on adaptive detection of shape features and one based on adaptive color segmentation to enable recognition in situations in which either prior method by itself may be inadequate. The chosen prior feature-based method is known as adaptive principal-component analysis (APCA); the chosen prior color-based method is known as adaptive color segmentation (ACOSE). These methods are made to interact with each other in a closed-loop system to obtain an optimal solution of the object-recognition problem in a dynamic environment. One of the results of the interaction is to increase, beyond what would otherwise be possible, the accuracy of the determination of a region of interest (containing an object that one seeks to recognize) within an image. Another result is to provide a minimized adaptive step that can be used to update the results obtained by the two component methods when changes of color and apparent shape occur. The net effect is to enable the neural network to update its recognition output and improve its recognition capability via an adaptive learning sequence. In principle, the improved method could readily be implemented in integrated circuitry to make a compact, low-power, real-time object-recognition system. It has been proposed to demonstrate the feasibility of such a system by integrating a 256-by-256 active-pixel sensor with APCA, ACOSE, and neural processing circuitry on a single chip. It has been estimated that such a system on a chip would have a volume no larger than a few cubic centimeters, could operate at a rate as high as 1,000 frames per second, and would consume in the order of milliwatts of power.

Image texture segmentation using a neural network

NASA Astrophysics Data System (ADS)

Sayeh, Mohammed R.; Athinarayanan, Ragu; Dhali, Pushpuak

1992-09-01

In this paper we use a neural network called the Lyapunov associative memory (LYAM) system to segment image texture into different categories or clusters. The LYAM system is constructed by a set of ordinary differential equations which are simulated on a digital computer. The clustering can be achieved by using a single tuning parameter in the simplest model. Pattern classes are represented by the stable equilibrium states of the system. Design of the system is based on synthesizing two local energy functions, namely, the learning and recall energy functions. Before the implementation of the segmentation process, a Gauss-Markov random field (GMRF) model is applied to the raw image. This application suitably reduces the image data and prepares the texture information for the neural network process. We give a simple image example illustrating the capability of the technique. The GMRF-generated features are also used for a clustering, based on the Euclidean distance.

Baseline estimation in flame's spectra by using neural networks and robust statistics

NASA Astrophysics Data System (ADS)

Garces, Hugo; Arias, Luis; Rojas, Alejandro

2014-09-01

This work presents a baseline estimation method in flame spectra based on artificial intelligence structure as a neural network, combining robust statistics with multivariate analysis to automatically discriminate measured wavelengths belonging to continuous feature for model adaptation, surpassing restriction of measuring target baseline for training. The main contributions of this paper are: to analyze a flame spectra database computing Jolliffe statistics from Principal Components Analysis detecting wavelengths not correlated with most of the measured data corresponding to baseline; to systematically determine the optimal number of neurons in hidden layers based on Akaike's Final Prediction Error; to estimate baseline in full wavelength range sampling measured spectra; and to train an artificial intelligence structure as a Neural Network which allows to generalize the relation between measured and baseline spectra. The main application of our research is to compute total radiation with baseline information, allowing to diagnose combustion process state for optimization in early stages.

A Spiking Neural Network in sEMG Feature Extraction.

PubMed

Lobov, Sergey; Mironov, Vasiliy; Kastalskiy, Innokentiy; Kazantsev, Victor

2015-11-03

We have developed a novel algorithm for sEMG feature extraction and classification. It is based on a hybrid network composed of spiking and artificial neurons. The spiking neuron layer with mutual inhibition was assigned as feature extractor. We demonstrate that the classification accuracy of the proposed model could reach high values comparable with existing sEMG interface systems. Moreover, the algorithm sensibility for different sEMG collecting systems characteristics was estimated. Results showed rather equal accuracy, despite a significant sampling rate difference. The proposed algorithm was successfully tested for mobile robot control.

Lumen-based detection of prostate cancer via convolutional neural networks

NASA Astrophysics Data System (ADS)

Kwak, Jin Tae; Hewitt, Stephen M.

2017-03-01

We present a deep learning approach for detecting prostate cancers. The approach consists of two steps. In the first step, we perform tissue segmentation that identifies lumens within digitized prostate tissue specimen images. Intensity- and texture-based image features are computed at five different scales, and a multiview boosting method is adopted to cooperatively combine the image features from differing scales and to identify lumens. In the second step, we utilize convolutional neural networks (CNN) to automatically extract high-level image features of lumens and to predict cancers. The segmented lumens are rescaled to reduce computational complexity and data augmentation by scaling, rotating, and flipping the rescaled image is applied to avoid overfitting. We evaluate the proposed method using two tissue microarrays (TMA) - TMA1 includes 162 tissue specimens (73 Benign and 89 Cancer) and TMA2 comprises 185 tissue specimens (70 Benign and 115 Cancer). In cross-validation on TMA1, the proposed method achieved an AUC of 0.95 (CI: 0.93-0.98). Trained on TMA1 and tested on TMA2, CNN obtained an AUC of 0.95 (CI: 0.92-0.98). This demonstrates that the proposed method can potentially improve prostate cancer pathology.

Fully Connected Cascade Artificial Neural Network Architecture for Attention Deficit Hyperactivity Disorder Classification From Functional Magnetic Resonance Imaging Data.

PubMed

Deshpande, Gopikrishna; Wang, Peng; Rangaprakash, D; Wilamowski, Bogdan

2015-12-01

Automated recognition and classification of brain diseases are of tremendous value to society. Attention deficit hyperactivity disorder (ADHD) is a diverse spectrum disorder whose diagnosis is based on behavior and hence will benefit from classification utilizing objective neuroimaging measures. Toward this end, an international competition was conducted for classifying ADHD using functional magnetic resonance imaging data acquired from multiple sites worldwide. Here, we consider the data from this competition as an example to illustrate the utility of fully connected cascade (FCC) artificial neural network (ANN) architecture for performing classification. We employed various directional and nondirectional brain connectivity-based methods to extract discriminative features which gave better classification accuracy compared to raw data. Our accuracy for distinguishing ADHD from healthy subjects was close to 90% and between the ADHD subtypes was close to 95%. Further, we show that, if properly used, FCC ANN performs very well compared to other classifiers such as support vector machines in terms of accuracy, irrespective of the feature used. Finally, the most discriminative connectivity features provided insights about the pathophysiology of ADHD and showed reduced and altered connectivity involving the left orbitofrontal cortex and various cerebellar regions in ADHD.

Scalable learning method for feedforward neural networks using minimal-enclosing-ball approximation.

PubMed

Wang, Jun; Deng, Zhaohong; Luo, Xiaoqing; Jiang, Yizhang; Wang, Shitong

2016-06-01

Training feedforward neural networks (FNNs) is one of the most critical issues in FNNs studies. However, most FNNs training methods cannot be directly applied for very large datasets because they have high computational and space complexity. In order to tackle this problem, the CCMEB (Center-Constrained Minimum Enclosing Ball) problem in hidden feature space of FNN is discussed and a novel learning algorithm called HFSR-GCVM (hidden-feature-space regression using generalized core vector machine) is developed accordingly. In HFSR-GCVM, a novel learning criterion using L2-norm penalty-based ε-insensitive function is formulated and the parameters in the hidden nodes are generated randomly independent of the training sets. Moreover, the learning of parameters in its output layer is proved equivalent to a special CCMEB problem in FNN hidden feature space. As most CCMEB approximation based machine learning algorithms, the proposed HFSR-GCVM training algorithm has the following merits: The maximal training time of the HFSR-GCVM training is linear with the size of training datasets and the maximal space consumption is independent of the size of training datasets. The experiments on regression tasks confirm the above conclusions. Copyright © 2016 Elsevier Ltd. All rights reserved.

Modeling first impressions from highly variable facial images.

PubMed

Vernon, Richard J W; Sutherland, Clare A M; Young, Andrew W; Hartley, Tom

2014-08-12

First impressions of social traits, such as trustworthiness or dominance, are reliably perceived in faces, and despite their questionable validity they can have considerable real-world consequences. We sought to uncover the information driving such judgments, using an attribute-based approach. Attributes (physical facial features) were objectively measured from feature positions and colors in a database of highly variable "ambient" face photographs, and then used as input for a neural network to model factor dimensions (approachability, youthful-attractiveness, and dominance) thought to underlie social attributions. A linear model based on this approach was able to account for 58% of the variance in raters' impressions of previously unseen faces, and factor-attribute correlations could be used to rank attributes by their importance to each factor. Reversing this process, neural networks were then used to predict facial attributes and corresponding image properties from specific combinations of factor scores. In this way, the factors driving social trait impressions could be visualized as a series of computer-generated cartoon face-like images, depicting how attributes change along each dimension. This study shows that despite enormous variation in ambient images of faces, a substantial proportion of the variance in first impressions can be accounted for through linear changes in objectively defined features.

Classifying medical relations in clinical text via convolutional neural networks.

PubMed

He, Bin; Guan, Yi; Dai, Rui

2018-05-16

Deep learning research on relation classification has achieved solid performance in the general domain. This study proposes a convolutional neural network (CNN) architecture with a multi-pooling operation for medical relation classification on clinical records and explores a loss function with a category-level constraint matrix. Experiments using the 2010 i2b2/VA relation corpus demonstrate these models, which do not depend on any external features, outperform previous single-model methods and our best model is competitive with the existing ensemble-based method. Copyright © 2018. Published by Elsevier B.V.

Neural Methods for Imagery, GMTI, and Information Fusion

DTIC Science & Technology

2006-03-15

Dynamic Range Contrast Enhanced Length & Power Normalized JV\\ 0.7 11 2500. No0 00 0.6 :a -30 - i 0.5 1 •4e ,3 ta I. a* 20 4B 60 Be° .0 120 140 160 s e...conditioned profile after length and power normalization. 2 Neural-Based Feature Extraction 2.2 Contrast enhancement and adaptive Rather than directly... power of the signal comprised of HRR range profiles synthesized from the is normalized. This ensures that very weak or very strong MSTAR SAR imagery

Coding of visual object features and feature conjunctions in the human brain.

PubMed

Martinovic, Jasna; Gruber, Thomas; Müller, Matthias M

2008-01-01

Object recognition is achieved through neural mechanisms reliant on the activity of distributed coordinated neural assemblies. In the initial steps of this process, an object's features are thought to be coded very rapidly in distinct neural assemblies. These features play different functional roles in the recognition process--while colour facilitates recognition, additional contours and edges delay it. Here, we selectively varied the amount and role of object features in an entry-level categorization paradigm and related them to the electrical activity of the human brain. We found that early synchronizations (approx. 100 ms) increased quantitatively when more image features had to be coded, without reflecting their qualitative contribution to the recognition process. Later activity (approx. 200-400 ms) was modulated by the representational role of object features. These findings demonstrate that although early synchronizations may be sufficient for relatively crude discrimination of objects in visual scenes, they cannot support entry-level categorization. This was subserved by later processes of object model selection, which utilized the representational value of object features such as colour or edges to select the appropriate model and achieve identification.

Brain-Computer Interfaces Using Sensorimotor Rhythms: Current State and Future Perspectives

PubMed Central

Yuan, Han; He, Bin

2014-01-01

Many studies over the past two decades have shown that people can use brain signals to convey their intent to a computer using brain-computer interfaces (BCIs). BCI systems extract specific features of brain activity and translate them into control signals that drive an output. Recently, a category of BCIs that are built on the rhythmic activity recorded over the sensorimotor cortex, i.e. the sensorimotor rhythm (SMR), has attracted considerable attention among the BCIs that use noninvasive neural recordings, e.g. electroencephalography (EEG), and have demonstrated the capability of multi-dimensional prosthesis control. This article reviews the current state and future perspectives of SMR-based BCI and its clinical applications, in particular focusing on the EEG SMR. The characteristic features of SMR from the human brain are described and their underlying neural sources are discussed. The functional components of SMR-based BCI, together with its current clinical applications are reviewed. Lastly, limitations of SMR-BCIs and future outlooks are also discussed. PMID:24759276

An artificial neural networks approach for assessment treatment response in oncological patients using PET/CT images.

PubMed

Nogueira, Mariana A; Abreu, Pedro H; Martins, Pedro; Machado, Penousal; Duarte, Hugo; Santos, João

2017-02-13

Positron Emission Tomography - Computed Tomography (PET/CT) imaging is the basis for the evaluation of response-to-treatment of several oncological diseases. In practice, such evaluation is manually performed by specialists, which is rather complex and time-consuming. Evaluation measures have been proposed, but with questionable reliability. The usage of before and after-treatment image descriptors of the lesions for treatment response evaluation is still a territory to be explored. In this project, Artificial Neural Network approaches were implemented to automatically assess treatment response of patients suffering from neuroendocrine tumors and Hodgkyn lymphoma, based on image features extracted from PET/CT. The results show that the considered set of features allows for the achievement of very high classification performances, especially when data is properly balanced. After synthetic data generation and PCA-based dimensionality reduction to only two components, LVQNN assured classification accuracies of 100%, 100%, 96.3% and 100% regarding the 4 response-to-treatment classes.

Artificial neural networks in mammography interpretation and diagnostic decision making.

PubMed

Ayer, Turgay; Chen, Qiushi; Burnside, Elizabeth S

2013-01-01

Screening mammography is the most effective means for early detection of breast cancer. Although general rules for discriminating malignant and benign lesions exist, radiologists are unable to perfectly detect and classify all lesions as malignant and benign, for many reasons which include, but are not limited to, overlap of features that distinguish malignancy, difficulty in estimating disease risk, and variability in recommended management. When predictive variables are numerous and interact, ad hoc decision making strategies based on experience and memory may lead to systematic errors and variability in practice. The integration of computer models to help radiologists increase the accuracy of mammography examinations in diagnostic decision making has gained increasing attention in the last two decades. In this study, we provide an overview of one of the most commonly used models, artificial neural networks (ANNs), in mammography interpretation and diagnostic decision making and discuss important features in mammography interpretation. We conclude by discussing several common limitations of existing research on ANN-based detection and diagnostic models and provide possible future research directions.

Multi-Sensor Data Fusion Identification for Shearer Cutting Conditions Based on Parallel Quasi-Newton Neural Networks and the Dempster-Shafer Theory.

PubMed

Si, Lei; Wang, Zhongbin; Liu, Xinhua; Tan, Chao; Xu, Jing; Zheng, Kehong

2015-11-13

In order to efficiently and accurately identify the cutting condition of a shearer, this paper proposed an intelligent multi-sensor data fusion identification method using the parallel quasi-Newton neural network (PQN-NN) and the Dempster-Shafer (DS) theory. The vibration acceleration signals and current signal of six cutting conditions were collected from a self-designed experimental system and some special state features were extracted from the intrinsic mode functions (IMFs) based on the ensemble empirical mode decomposition (EEMD). In the experiment, three classifiers were trained and tested by the selected features of the measured data, and the DS theory was used to combine the identification results of three single classifiers. Furthermore, some comparisons with other methods were carried out. The experimental results indicate that the proposed method performs with higher detection accuracy and credibility than the competing algorithms. Finally, an industrial application example in the fully mechanized coal mining face was demonstrated to specify the effect of the proposed system.

Automotive System for Remote Surface Classification.

PubMed

Bystrov, Aleksandr; Hoare, Edward; Tran, Thuy-Yung; Clarke, Nigel; Gashinova, Marina; Cherniakov, Mikhail

2017-04-01

In this paper we shall discuss a novel approach to road surface recognition, based on the analysis of backscattered microwave and ultrasonic signals. The novelty of our method is sonar and polarimetric radar data fusion, extraction of features for separate swathes of illuminated surface (segmentation), and using of multi-stage artificial neural network for surface classification. The developed system consists of 24 GHz radar and 40 kHz ultrasonic sensor. The features are extracted from backscattered signals and then the procedures of principal component analysis and supervised classification are applied to feature data. The special attention is paid to multi-stage artificial neural network which allows an overall increase in classification accuracy. The proposed technique was tested for recognition of a large number of real surfaces in different weather conditions with the average accuracy of correct classification of 95%. The obtained results thereby demonstrate that the use of proposed system architecture and statistical methods allow for reliable discrimination of various road surfaces in real conditions.

Automotive System for Remote Surface Classification

PubMed Central

Bystrov, Aleksandr; Hoare, Edward; Tran, Thuy-Yung; Clarke, Nigel; Gashinova, Marina; Cherniakov, Mikhail

2017-01-01

In this paper we shall discuss a novel approach to road surface recognition, based on the analysis of backscattered microwave and ultrasonic signals. The novelty of our method is sonar and polarimetric radar data fusion, extraction of features for separate swathes of illuminated surface (segmentation), and using of multi-stage artificial neural network for surface classification. The developed system consists of 24 GHz radar and 40 kHz ultrasonic sensor. The features are extracted from backscattered signals and then the procedures of principal component analysis and supervised classification are applied to feature data. The special attention is paid to multi-stage artificial neural network which allows an overall increase in classification accuracy. The proposed technique was tested for recognition of a large number of real surfaces in different weather conditions with the average accuracy of correct classification of 95%. The obtained results thereby demonstrate that the use of proposed system architecture and statistical methods allow for reliable discrimination of various road surfaces in real conditions. PMID:28368297

White blood cells identification system based on convolutional deep neural learning networks.

PubMed

Shahin, A I; Guo, Yanhui; Amin, K M; Sharawi, Amr A

2017-11-16

White blood cells (WBCs) differential counting yields valued information about human health and disease. The current developed automated cell morphology equipments perform differential count which is based on blood smear image analysis. Previous identification systems for WBCs consist of successive dependent stages; pre-processing, segmentation, feature extraction, feature selection, and classification. There is a real need to employ deep learning methodologies so that the performance of previous WBCs identification systems can be increased. Classifying small limited datasets through deep learning systems is a major challenge and should be investigated. In this paper, we propose a novel identification system for WBCs based on deep convolutional neural networks. Two methodologies based on transfer learning are followed: transfer learning based on deep activation features and fine-tuning of existed deep networks. Deep acrivation featues are extracted from several pre-trained networks and employed in a traditional identification system. Moreover, a novel end-to-end convolutional deep architecture called "WBCsNet" is proposed and built from scratch. Finally, a limited balanced WBCs dataset classification is performed through the WBCsNet as a pre-trained network. During our experiments, three different public WBCs datasets (2551 images) have been used which contain 5 healthy WBCs types. The overall system accuracy achieved by the proposed WBCsNet is (96.1%) which is more than different transfer learning approaches or even the previous traditional identification system. We also present features visualization for the WBCsNet activation which reflects higher response than the pre-trained activated one. a novel WBCs identification system based on deep learning theory is proposed and a high performance WBCsNet can be employed as a pre-trained network. Copyright © 2017. Published by Elsevier B.V.

An EEG-Based Person Authentication System with Open-Set Capability Combining Eye Blinking Signals

PubMed Central

Wu, Qunjian; Zeng, Ying; Zhang, Chi; Tong, Li; Yan, Bin

2018-01-01

The electroencephalogram (EEG) signal represents a subject’s specific brain activity patterns and is considered as an ideal biometric given its superior forgery prevention. However, the accuracy and stability of the current EEG-based person authentication systems are still unsatisfactory in practical application. In this paper, a multi-task EEG-based person authentication system combining eye blinking is proposed, which can achieve high precision and robustness. Firstly, we design a novel EEG-based biometric evoked paradigm using self- or non-self-face rapid serial visual presentation (RSVP). The designed paradigm could obtain a distinct and stable biometric trait from EEG with a lower time cost. Secondly, the event-related potential (ERP) features and morphological features are extracted from EEG signals and eye blinking signals, respectively. Thirdly, convolutional neural network and back propagation neural network are severally designed to gain the score estimation of EEG features and eye blinking features. Finally, a score fusion technology based on least square method is proposed to get the final estimation score. The performance of multi-task authentication system is improved significantly compared to the system using EEG only, with an increasing average accuracy from 92.4% to 97.6%. Moreover, open-set authentication tests for additional imposters and permanence tests for users are conducted to simulate the practical scenarios, which have never been employed in previous EEG-based person authentication systems. A mean false accepted rate (FAR) of 3.90% and a mean false rejected rate (FRR) of 3.87% are accomplished in open-set authentication tests and permanence tests, respectively, which illustrate the open-set authentication and permanence capability of our systems. PMID:29364848

An EEG-Based Person Authentication System with Open-Set Capability Combining Eye Blinking Signals.

PubMed

Wu, Qunjian; Zeng, Ying; Zhang, Chi; Tong, Li; Yan, Bin

2018-01-24

The electroencephalogram (EEG) signal represents a subject's specific brain activity patterns and is considered as an ideal biometric given its superior forgery prevention. However, the accuracy and stability of the current EEG-based person authentication systems are still unsatisfactory in practical application. In this paper, a multi-task EEG-based person authentication system combining eye blinking is proposed, which can achieve high precision and robustness. Firstly, we design a novel EEG-based biometric evoked paradigm using self- or non-self-face rapid serial visual presentation (RSVP). The designed paradigm could obtain a distinct and stable biometric trait from EEG with a lower time cost. Secondly, the event-related potential (ERP) features and morphological features are extracted from EEG signals and eye blinking signals, respectively. Thirdly, convolutional neural network and back propagation neural network are severally designed to gain the score estimation of EEG features and eye blinking features. Finally, a score fusion technology based on least square method is proposed to get the final estimation score. The performance of multi-task authentication system is improved significantly compared to the system using EEG only, with an increasing average accuracy from 92.4% to 97.6%. Moreover, open-set authentication tests for additional imposters and permanence tests for users are conducted to simulate the practical scenarios, which have never been employed in previous EEG-based person authentication systems. A mean false accepted rate (FAR) of 3.90% and a mean false rejected rate (FRR) of 3.87% are accomplished in open-set authentication tests and permanence tests, respectively, which illustrate the open-set authentication and permanence capability of our systems.

A pre-trained convolutional neural network based method for thyroid nodule diagnosis.

PubMed

Ma, Jinlian; Wu, Fa; Zhu, Jiang; Xu, Dong; Kong, Dexing

2017-01-01

In ultrasound images, most thyroid nodules are in heterogeneous appearances with various internal components and also have vague boundaries, so it is difficult for physicians to discriminate malignant thyroid nodules from benign ones. In this study, we propose a hybrid method for thyroid nodule diagnosis, which is a fusion of two pre-trained convolutional neural networks (CNNs) with different convolutional layers and fully-connected layers. Firstly, the two networks pre-trained with ImageNet database are separately trained. Secondly, we fuse feature maps learned by trained convolutional filters, pooling and normalization operations of the two CNNs. Finally, with the fused feature maps, a softmax classifier is used to diagnose thyroid nodules. The proposed method is validated on 15,000 ultrasound images collected from two local hospitals. Experiment results show that the proposed CNN based methods can accurately and effectively diagnose thyroid nodules. In addition, the fusion of the two CNN based models lead to significant performance improvement, with an accuracy of 83.02%±0.72%. These demonstrate the potential clinical applications of this method. Copyright © 2016 Elsevier B.V. All rights reserved.

Two-dimensional shape classification using generalized Fourier representation and neural networks

NASA Astrophysics Data System (ADS)

Chodorowski, Artur; Gustavsson, Tomas; Mattsson, Ulf

2000-04-01

A shape-based classification method is developed based upon the Generalized Fourier Representation (GFR). GFR can be regarded as an extension of traditional polar Fourier descriptors, suitable for description of closed objects, both convex and concave, with or without holes. Explicit relations of GFR coefficients to regular moments, moment invariants and affine moment invariants are given in the paper. The dual linear relation between GFR coefficients and regular moments was used to compare shape features derive from GFR descriptors and Hu's moment invariants. the GFR was then applied to a clinical problem within oral medicine and used to represent the contours of the lesions in the oral cavity. The lesions studied were leukoplakia and different forms of lichenoid reactions. Shape features were extracted from GFR coefficients in order to classify potentially cancerous oral lesions. Alternative classifiers were investigated based on a multilayer perceptron with different architectures and extensions. The overall classification accuracy for recognition of potentially cancerous oral lesions when using neural network classifier was 85%, while the classification between leukoplakia and reticular lichenoid reactions gave 96% (5-fold cross-validated) recognition rate.

Exploration of complex visual feature spaces for object perception

PubMed Central

Leeds, Daniel D.; Pyles, John A.; Tarr, Michael J.

2014-01-01

The mid- and high-level visual properties supporting object perception in the ventral visual pathway are poorly understood. In the absence of well-specified theory, many groups have adopted a data-driven approach in which they progressively interrogate neural units to establish each unit's selectivity. Such methods are challenging in that they require search through a wide space of feature models and stimuli using a limited number of samples. To more rapidly identify higher-level features underlying human cortical object perception, we implemented a novel functional magnetic resonance imaging method in which visual stimuli are selected in real-time based on BOLD responses to recently shown stimuli. This work was inspired by earlier primate physiology work, in which neural selectivity for mid-level features in IT was characterized using a simple parametric approach (Hung et al., 2012). To extend such work to human neuroimaging, we used natural and synthetic object stimuli embedded in feature spaces constructed on the basis of the complex visual properties of the objects themselves. During fMRI scanning, we employed a real-time search method to control continuous stimulus selection within each image space. This search was designed to maximize neural responses across a pre-determined 1 cm3 brain region within ventral cortex. To assess the value of this method for understanding object encoding, we examined both the behavior of the method itself and the complex visual properties the method identified as reliably activating selected brain regions. We observed: (1) Regions selective for both holistic and component object features and for a variety of surface properties; (2) Object stimulus pairs near one another in feature space that produce responses at the opposite extremes of the measured activity range. Together, these results suggest that real-time fMRI methods may yield more widely informative measures of selectivity within the broad classes of visual features associated with cortical object representation. PMID:25309408

Control chart pattern recognition using RBF neural network with new training algorithm and practical features.

PubMed

Addeh, Abdoljalil; Khormali, Aminollah; Golilarz, Noorbakhsh Amiri

2018-05-04

The control chart patterns are the most commonly used statistical process control (SPC) tools to monitor process changes. When a control chart produces an out-of-control signal, this means that the process has been changed. In this study, a new method based on optimized radial basis function neural network (RBFNN) is proposed for control chart patterns (CCPs) recognition. The proposed method consists of four main modules: feature extraction, feature selection, classification and learning algorithm. In the feature extraction module, shape and statistical features are used. Recently, various shape and statistical features have been presented for the CCPs recognition. In the feature selection module, the association rules (AR) method has been employed to select the best set of the shape and statistical features. In the classifier section, RBFNN is used and finally, in RBFNN, learning algorithm has a high impact on the network performance. Therefore, a new learning algorithm based on the bees algorithm has been used in the learning module. Most studies have considered only six patterns: Normal, Cyclic, Increasing Trend, Decreasing Trend, Upward Shift and Downward Shift. Since three patterns namely Normal, Stratification, and Systematic are very similar to each other and distinguishing them is very difficult, in most studies Stratification and Systematic have not been considered. Regarding to the continuous monitoring and control over the production process and the exact type detection of the problem encountered during the production process, eight patterns have been investigated in this study. The proposed method is tested on a dataset containing 1600 samples (200 samples from each pattern) and the results showed that the proposed method has a very good performance. Copyright © 2018 ISA. Published by Elsevier Ltd. All rights reserved.

Neural correlates of processing facial identity based on features versus their spacing.

PubMed

Maurer, D; O'Craven, K M; Le Grand, R; Mondloch, C J; Springer, M V; Lewis, T L; Grady, C L

2007-04-08

Adults' expertise in recognizing facial identity involves encoding subtle differences among faces in the shape of individual facial features (featural processing) and in the spacing among features (a type of configural processing called sensitivity to second-order relations). We used fMRI to investigate the neural mechanisms that differentiate these two types of processing. Participants made same/different judgments about pairs of faces that differed only in the shape of the eyes and mouth, with minimal differences in spacing (featural blocks), or pairs of faces that had identical features but differed in the positions of those features (spacing blocks). From a localizer scan with faces, objects, and houses, we identified regions with comparatively more activity for faces, including the fusiform face area (FFA) in the right fusiform gyrus, other extrastriate regions, and prefrontal cortices. Contrasts between the featural and spacing conditions revealed distributed patterns of activity differentiating the two conditions. A region of the right fusiform gyrus (near but not overlapping the localized FFA) showed greater activity during the spacing task, along with multiple areas of right frontal cortex, whereas left prefrontal activity increased for featural processing. These patterns of activity were not related to differences in performance between the two tasks. The results indicate that the processing of facial features is distinct from the processing of second-order relations in faces, and that these functions are mediated by separate and lateralized networks involving the right fusiform gyrus, although the FFA as defined from a localizer scan is not differentially involved.

Neural network disturbance observer-based distributed finite-time formation tracking control for multiple unmanned helicopters.

PubMed

Wang, Dandan; Zong, Qun; Tian, Bailing; Shao, Shikai; Zhang, Xiuyun; Zhao, Xinyi

2018-02-01

The distributed finite-time formation tracking control problem for multiple unmanned helicopters is investigated in this paper. The control object is to maintain the positions of follower helicopters in formation with external interferences. The helicopter model is divided into a second order outer-loop subsystem and a second order inner-loop subsystem based on multiple-time scale features. Using radial basis function neural network (RBFNN) technique, we first propose a novel finite-time multivariable neural network disturbance observer (FMNNDO) to estimate the external disturbance and model uncertainty, where the neural network (NN) approximation errors can be dynamically compensated by adaptive law. Next, based on FMNNDO, a distributed finite-time formation tracking controller and a finite-time attitude tracking controller are designed using the nonsingular fast terminal sliding mode (NFTSM) method. In order to estimate the second derivative of the virtual desired attitude signal, a novel finite-time sliding mode integral filter is designed. Finally, Lyapunov analysis and multiple-time scale principle ensure the realization of control goal in finite-time. The effectiveness of the proposed FMNNDO and controllers are then verified by numerical simulations. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.

Landslide Susceptibility Index Determination Using Aritificial Neural Network

NASA Astrophysics Data System (ADS)

Kawabata, D.; Bandibas, J.; Urai, M.

2004-12-01

The occurrence of landslide is the result of the interaction of complex and diverse environmental factors. The geomorphic features, rock types and geologic structure are especially important base factors of the landslide occurrence. Generating landslide susceptibility index by defining the relationship between landslide occurrence and that base factors using conventional mathematical and statistical methods is very difficult and inaccurate. This study focuses on generating landslide susceptibility index using artificial neural networks in Southern Japanese Alps. The training data are geomorphic (e.g. altitude, slope and aspect) and geologic parameters (e.g. rock type, distance from geologic boundary and geologic dip-strike angle) and landslides. Artificial neural network structure and training scheme are formulated to generate the index. Data from areas with and without landslide occurrences are used to train the network. The network is trained to output 1 when the input data are from areas with landslides and 0 when no landslide occurred. The trained network generates an output ranging from 0 to 1 reflecting the possibility of landslide occurrence based on the inputted data. Output values nearer to 1 means higher possibility of landslide occurrence. The artificial neural network model is incorporated into the GIS software to generate a landslide susceptibility map.

Assessing the performance of multiple spectral-spatial features of a hyperspectral image for classification of urban land cover classes using support vector machines and artificial neural network

NASA Astrophysics Data System (ADS)

Pullanagari, Reddy; Kereszturi, Gábor; Yule, Ian J.; Ghamisi, Pedram

2017-04-01

Accurate and spatially detailed mapping of complex urban environments is essential for land managers. Classifying high spectral and spatial resolution hyperspectral images is a challenging task because of its data abundance and computational complexity. Approaches with a combination of spectral and spatial information in a single classification framework have attracted special attention because of their potential to improve the classification accuracy. We extracted multiple features from spectral and spatial domains of hyperspectral images and evaluated them with two supervised classification algorithms; support vector machines (SVM) and an artificial neural network. The spatial features considered are produced by a gray level co-occurrence matrix and extended multiattribute profiles. All of these features were stacked, and the most informative features were selected using a genetic algorithm-based SVM. After selecting the most informative features, the classification model was integrated with a segmentation map derived using a hidden Markov random field. We tested the proposed method on a real application of a hyperspectral image acquired from AisaFENIX and on widely used hyperspectral images. From the results, it can be concluded that the proposed framework significantly improves the results with different spectral and spatial resolutions over different instrumentation.

Neural correlates of behavioral amplitude modulation sensitivity in the budgerigar midbrain

PubMed Central

Neilans, Erikson G.; Abrams, Kristina S.; Idrobo, Fabio; Carney, Laurel H.

2016-01-01

Amplitude modulation (AM) is a crucial feature of many communication signals, including speech. Whereas average discharge rates in the auditory midbrain correlate with behavioral AM sensitivity in rabbits, the neural bases of AM sensitivity in species with human-like behavioral acuity are unexplored. Here, we used parallel behavioral and neurophysiological experiments to explore the neural (midbrain) bases of AM perception in an avian speech mimic, the budgerigar (Melopsittacus undulatus). Behavioral AM sensitivity was quantified using operant conditioning procedures. Neural AM sensitivity was studied using chronically implanted microelectrodes in awake, unrestrained birds. Average discharge rates of multiunit recording sites in the budgerigar midbrain were insufficient to explain behavioral sensitivity to modulation frequencies <100 Hz for both tone- and noise-carrier stimuli, even with optimal pooling of information across recording sites. Neural envelope synchrony, in contrast, could explain behavioral performance for both carrier types across the full range of modulation frequencies studied (16–512 Hz). The results suggest that envelope synchrony in the budgerigar midbrain may underlie behavioral sensitivity to AM. Behavioral AM sensitivity based on synchrony in the budgerigar, which contrasts with rate-correlated behavioral performance in rabbits, raises the possibility that envelope synchrony, rather than average discharge rate, might also underlie AM perception in other species with sensitive AM detection abilities, including humans. These results highlight the importance of synchrony coding of envelope structure in the inferior colliculus. Furthermore, they underscore potential benefits of devices (e.g., midbrain implants) that evoke robust neural synchrony. PMID:26843608

Emotional textile image classification based on cross-domain convolutional sparse autoencoders with feature selection

NASA Astrophysics Data System (ADS)

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

2017-01-01

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

Fall Detection Using Smartphone Audio Features.

PubMed

Cheffena, Michael

2016-07-01

An automated fall detection system based on smartphone audio features is developed. The spectrogram, mel frequency cepstral coefficents (MFCCs), linear predictive coding (LPC), and matching pursuit (MP) features of different fall and no-fall sound events are extracted from experimental data. Based on the extracted audio features, four different machine learning classifiers: k-nearest neighbor classifier (k-NN), support vector machine (SVM), least squares method (LSM), and artificial neural network (ANN) are investigated for distinguishing between fall and no-fall events. For each audio feature, the performance of each classifier in terms of sensitivity, specificity, accuracy, and computational complexity is evaluated. The best performance is achieved using spectrogram features with ANN classifier with sensitivity, specificity, and accuracy all above 98%. The classifier also has acceptable computational requirement for training and testing. The system is applicable in home environments where the phone is placed in the vicinity of the user.

No-reference image quality assessment based on statistics of convolution feature maps

NASA Astrophysics Data System (ADS)

Lv, Xiaoxin; Qin, Min; Chen, Xiaohui; Wei, Guo

2018-04-01

We propose a Convolutional Feature Maps (CFM) driven approach to accurately predict image quality. Our motivation bases on the finding that the Nature Scene Statistic (NSS) features on convolution feature maps are significantly sensitive to distortion degree of an image. In our method, a Convolutional Neural Network (CNN) is trained to obtain kernels for generating CFM. We design a forward NSS layer which performs on CFM to better extract NSS features. The quality aware features derived from the output of NSS layer is effective to describe the distortion type and degree an image suffered. Finally, a Support Vector Regression (SVR) is employed in our No-Reference Image Quality Assessment (NR-IQA) model to predict a subjective quality score of a distorted image. Experiments conducted on two public databases demonstrate the promising performance of the proposed method is competitive to state of the art NR-IQA methods.

Complex Environmental Data Modelling Using Adaptive General Regression Neural Networks

NASA Astrophysics Data System (ADS)

Kanevski, Mikhail

2015-04-01

The research deals with an adaptation and application of Adaptive General Regression Neural Networks (GRNN) to high dimensional environmental data. GRNN [1,2,3] are efficient modelling tools both for spatial and temporal data and are based on nonparametric kernel methods closely related to classical Nadaraya-Watson estimator. Adaptive GRNN, using anisotropic kernels, can be also applied for features selection tasks when working with high dimensional data [1,3]. In the present research Adaptive GRNN are used to study geospatial data predictability and relevant feature selection using both simulated and real data case studies. The original raw data were either three dimensional monthly precipitation data or monthly wind speeds embedded into 13 dimensional space constructed by geographical coordinates and geo-features calculated from digital elevation model. GRNN were applied in two different ways: 1) adaptive GRNN with the resulting list of features ordered according to their relevancy; and 2) adaptive GRNN applied to evaluate all possible models N [in case of wind fields N=(2^13 -1)=8191] and rank them according to the cross-validation error. In both cases training were carried out applying leave-one-out procedure. An important result of the study is that the set of the most relevant features depends on the month (strong seasonal effect) and year. The predictabilities of precipitation and wind field patterns, estimated using the cross-validation and testing errors of raw and shuffled data, were studied in detail. The results of both approaches were qualitatively and quantitatively compared. In conclusion, Adaptive GRNN with their ability to select features and efficient modelling of complex high dimensional data can be widely used in automatic/on-line mapping and as an integrated part of environmental decision support systems. 1. Kanevski M., Pozdnoukhov A., Timonin V. Machine Learning for Spatial Environmental Data. Theory, applications and software. EPFL Press. With a CD: data, software, guides. (2009). 2. Kanevski M. Spatial Predictions of Soil Contamination Using General Regression Neural Networks. Systems Research and Information Systems, Volume 8, number 4, 1999. 3. Robert S., Foresti L., Kanevski M. Spatial prediction of monthly wind speeds in complex terrain with adaptive general regression neural networks. International Journal of Climatology, 33 pp. 1793-1804, 2013.

Toward a self-organizing pre-symbolic neural model representing sensorimotor primitives.

PubMed

Zhong, Junpei; Cangelosi, Angelo; Wermter, Stefan

2014-01-01

The acquisition of symbolic and linguistic representations of sensorimotor behavior is a cognitive process performed by an agent when it is executing and/or observing own and others' actions. According to Piaget's theory of cognitive development, these representations develop during the sensorimotor stage and the pre-operational stage. We propose a model that relates the conceptualization of the higher-level information from visual stimuli to the development of ventral/dorsal visual streams. This model employs neural network architecture incorporating a predictive sensory module based on an RNNPB (Recurrent Neural Network with Parametric Biases) and a horizontal product model. We exemplify this model through a robot passively observing an object to learn its features and movements. During the learning process of observing sensorimotor primitives, i.e., observing a set of trajectories of arm movements and its oriented object features, the pre-symbolic representation is self-organized in the parametric units. These representational units act as bifurcation parameters, guiding the robot to recognize and predict various learned sensorimotor primitives. The pre-symbolic representation also accounts for the learning of sensorimotor primitives in a latent learning context.

Toward a self-organizing pre-symbolic neural model representing sensorimotor primitives

PubMed Central

Zhong, Junpei; Cangelosi, Angelo; Wermter, Stefan

2014-01-01

The acquisition of symbolic and linguistic representations of sensorimotor behavior is a cognitive process performed by an agent when it is executing and/or observing own and others' actions. According to Piaget's theory of cognitive development, these representations develop during the sensorimotor stage and the pre-operational stage. We propose a model that relates the conceptualization of the higher-level information from visual stimuli to the development of ventral/dorsal visual streams. This model employs neural network architecture incorporating a predictive sensory module based on an RNNPB (Recurrent Neural Network with Parametric Biases) and a horizontal product model. We exemplify this model through a robot passively observing an object to learn its features and movements. During the learning process of observing sensorimotor primitives, i.e., observing a set of trajectories of arm movements and its oriented object features, the pre-symbolic representation is self-organized in the parametric units. These representational units act as bifurcation parameters, guiding the robot to recognize and predict various learned sensorimotor primitives. The pre-symbolic representation also accounts for the learning of sensorimotor primitives in a latent learning context. PMID:24550798

An Application of Data Mining Techniques for Flood Forecasting: Application in Rivers Daya and Bhargavi, India

NASA Astrophysics Data System (ADS)

Panigrahi, Binay Kumar; Das, Soumya; Nath, Tushar Kumar; Senapati, Manas Ranjan

2018-05-01

In the present study, with a view to speculate the water flow of two rivers in eastern India namely river Daya and river Bhargavi, the focus was on developing Cascaded Functional Link Artificial Neural Network (C-FLANN) model. Parameters of C-FLANN architecture were updated using Harmony Search (HS) and Differential Evolution (DE). As the numbers of samples are very low, there is a risk of over fitting. To avoid this Map reduce based ANOVA technique is used to select important features. These features were used and provided to the architecture which is used to predict the water flow in both the rivers, one day, one week and two weeks ahead. The results of both the techniques were compared with Radial Basis Functional Neural Network (RBFNN) and Multilayer Perceptron (MLP), two widely used artificial neural network for prediction. From the result it was confirmed that C-FLANN trained through HS gives better prediction result than being trained through DE or RBFNN or MLP and can be used for predicting water flow in different rivers.

Detection of Foreign Matter in Transfusion Solution Based on Gaussian Background Modeling and an Optimized BP Neural Network

PubMed Central

Zhou, Fuqiang; Su, Zhen; Chai, Xinghua; Chen, Lipeng

2014-01-01

This paper proposes a new method to detect and identify foreign matter mixed in a plastic bottle filled with transfusion solution. A spin-stop mechanism and mixed illumination style are applied to obtain high contrast images between moving foreign matter and a static transfusion background. The Gaussian mixture model is used to model the complex background of the transfusion image and to extract moving objects. A set of features of moving objects are extracted and selected by the ReliefF algorithm, and optimal feature vectors are fed into the back propagation (BP) neural network to distinguish between foreign matter and bubbles. The mind evolutionary algorithm (MEA) is applied to optimize the connection weights and thresholds of the BP neural network to obtain a higher classification accuracy and faster convergence rate. Experimental results show that the proposed method can effectively detect visible foreign matter in 250-mL transfusion bottles. The misdetection rate and false alarm rate are low, and the detection accuracy and detection speed are satisfactory. PMID:25347581

Comparative evaluation of Chitosan, Cellulose Acetate, and Polyethersulfone Nanofiber Scaffolds for Neural Differentiation

PubMed Central

Du, Jian; Tan, Elaine; Kim, Hyo Jun; Zhang, Allen; Bhattacharya, Rahul; Yarema, Kevin J

2013-01-01

Based on accumulating evidence that the 3D topography and the chemical features of a growth surface influence neuronal differentiation, we combined these two features by evaluating the cytotoxicity, proliferation, and differentiation of the rat PC12 line and human neural stem cells (hNSCs) on chitosan (CS), cellulose acetate (CA), and polyethersulfone (PES)-derived electrospun nanofibers that had similar diameters, centered in the 200 to 500 nm range. None of the nanofibrous materials were cytotoxic compared to 2D (e.g., flat surface) controls; however, proliferation generally was inhibited on the nanofibrous scaffolds although to a lesser extent on the polysaccharide-derived materials compared to PES. In an exception to the trend towards slower growth on the 3D substrates, hNSCs differentiated on the CS nanofibers proliferated faster than the 2D controls and both cell types showed enhanced indication of neuronal differentiation on the CS scaffolds. Together, these results demonstrate beneficial attributes of CS for neural tissue engineering when this polysaccharide is used in the context of the defined 3D topography found in electrospun nanofibers. PMID:24274534

LANGUAGE EXPERIENCE SHAPES PROCESSING OF PITCH RELEVANT INFORMATION IN THE HUMAN BRAINSTEM AND AUDITORY CORTEX: ELECTROPHYSIOLOGICAL EVIDENCE.

PubMed

Krishnan, Ananthanarayan; Gandour, Jackson T

2014-12-01

Pitch is a robust perceptual attribute that plays an important role in speech, language, and music. As such, it provides an analytic window to evaluate how neural activity relevant to pitch undergo transformation from early sensory to later cognitive stages of processing in a well coordinated hierarchical network that is subject to experience-dependent plasticity. We review recent evidence of language experience-dependent effects in pitch processing based on comparisons of native vs. nonnative speakers of a tonal language from electrophysiological recordings in the auditory brainstem and auditory cortex. We present evidence that shows enhanced representation of linguistically-relevant pitch dimensions or features at both the brainstem and cortical levels with a stimulus-dependent preferential activation of the right hemisphere in native speakers of a tone language. We argue that neural representation of pitch-relevant information in the brainstem and early sensory level processing in the auditory cortex is shaped by the perceptual salience of domain-specific features. While both stages of processing are shaped by language experience, neural representations are transformed and fundamentally different at each biological level of abstraction. The representation of pitch relevant information in the brainstem is more fine-grained spectrotemporally as it reflects sustained neural phase-locking to pitch relevant periodicities contained in the stimulus. In contrast, the cortical pitch relevant neural activity reflects primarily a series of transient temporal neural events synchronized to certain temporal attributes of the pitch contour. We argue that experience-dependent enhancement of pitch representation for Chinese listeners most likely reflects an interaction between higher-level cognitive processes and early sensory-level processing to improve representations of behaviorally-relevant features that contribute optimally to perception. It is our view that long-term experience shapes this adaptive process wherein the top-down connections provide selective gating of inputs to both cortical and subcortical structures to enhance neural responses to specific behaviorally-relevant attributes of the stimulus. A theoretical framework for a neural network is proposed involving coordination between local, feedforward, and feedback components that can account for experience-dependent enhancement of pitch representations at multiple levels of the auditory pathway. The ability to record brainstem and cortical pitch relevant responses concurrently may provide a new window to evaluate the online interplay between feedback, feedforward, and local intrinsic components in the hierarchical processing of pitch relevant information.

LANGUAGE EXPERIENCE SHAPES PROCESSING OF PITCH RELEVANT INFORMATION IN THE HUMAN BRAINSTEM AND AUDITORY CORTEX: ELECTROPHYSIOLOGICAL EVIDENCE

PubMed Central

Krishnan, Ananthanarayan; Gandour, Jackson T.

2015-01-01

Pitch is a robust perceptual attribute that plays an important role in speech, language, and music. As such, it provides an analytic window to evaluate how neural activity relevant to pitch undergo transformation from early sensory to later cognitive stages of processing in a well coordinated hierarchical network that is subject to experience-dependent plasticity. We review recent evidence of language experience-dependent effects in pitch processing based on comparisons of native vs. nonnative speakers of a tonal language from electrophysiological recordings in the auditory brainstem and auditory cortex. We present evidence that shows enhanced representation of linguistically-relevant pitch dimensions or features at both the brainstem and cortical levels with a stimulus-dependent preferential activation of the right hemisphere in native speakers of a tone language. We argue that neural representation of pitch-relevant information in the brainstem and early sensory level processing in the auditory cortex is shaped by the perceptual salience of domain-specific features. While both stages of processing are shaped by language experience, neural representations are transformed and fundamentally different at each biological level of abstraction. The representation of pitch relevant information in the brainstem is more fine-grained spectrotemporally as it reflects sustained neural phase-locking to pitch relevant periodicities contained in the stimulus. In contrast, the cortical pitch relevant neural activity reflects primarily a series of transient temporal neural events synchronized to certain temporal attributes of the pitch contour. We argue that experience-dependent enhancement of pitch representation for Chinese listeners most likely reflects an interaction between higher-level cognitive processes and early sensory-level processing to improve representations of behaviorally-relevant features that contribute optimally to perception. It is our view that long-term experience shapes this adaptive process wherein the top-down connections provide selective gating of inputs to both cortical and subcortical structures to enhance neural responses to specific behaviorally-relevant attributes of the stimulus. A theoretical framework for a neural network is proposed involving coordination between local, feedforward, and feedback components that can account for experience-dependent enhancement of pitch representations at multiple levels of the auditory pathway. The ability to record brainstem and cortical pitch relevant responses concurrently may provide a new window to evaluate the online interplay between feedback, feedforward, and local intrinsic components in the hierarchical processing of pitch relevant information. PMID:25838636

Tracking real-time neural activation of conceptual knowledge using single-trial event-related potentials.

PubMed

Amsel, Ben D

2011-04-01

Empirically derived semantic feature norms categorized into different types of knowledge (e.g., visual, functional, auditory) can be summed to create number-of-feature counts per knowledge type. Initial evidence suggests several such knowledge types may be recruited during language comprehension. The present study provides a more detailed understanding of the timecourse and intensity of influence of several such knowledge types on real-time neural activity. A linear mixed-effects model was applied to single trial event-related potentials for 207 visually presented concrete words measured on total number of features (semantic richness), imageability, and number of visual motion, color, visual form, smell, taste, sound, and function features. Significant influences of multiple feature types occurred before 200ms, suggesting parallel neural computation of word form and conceptual knowledge during language comprehension. Function and visual motion features most prominently influenced neural activity, underscoring the importance of action-related knowledge in computing word meaning. The dynamic time courses and topographies of these effects are most consistent with a flexible conceptual system wherein temporally dynamic recruitment of representations in modal and supramodal cortex are a crucial element of the constellation of processes constituting word meaning computation in the brain. Copyright © 2011 Elsevier Ltd. All rights reserved.

Using multiple classifiers for predicting the risk of endovascular aortic aneurysm repair re-intervention through hybrid feature selection.

PubMed

Attallah, Omneya; Karthikesalingam, Alan; Holt, Peter Je; Thompson, Matthew M; Sayers, Rob; Bown, Matthew J; Choke, Eddie C; Ma, Xianghong

2017-11-01

Feature selection is essential in medical area; however, its process becomes complicated with the presence of censoring which is the unique character of survival analysis. Most survival feature selection methods are based on Cox's proportional hazard model, though machine learning classifiers are preferred. They are less employed in survival analysis due to censoring which prevents them from directly being used to survival data. Among the few work that employed machine learning classifiers, partial logistic artificial neural network with auto-relevance determination is a well-known method that deals with censoring and perform feature selection for survival data. However, it depends on data replication to handle censoring which leads to unbalanced and biased prediction results especially in highly censored data. Other methods cannot deal with high censoring. Therefore, in this article, a new hybrid feature selection method is proposed which presents a solution to high level censoring. It combines support vector machine, neural network, and K-nearest neighbor classifiers using simple majority voting and a new weighted majority voting method based on survival metric to construct a multiple classifier system. The new hybrid feature selection process uses multiple classifier system as a wrapper method and merges it with iterated feature ranking filter method to further reduce features. Two endovascular aortic repair datasets containing 91% censored patients collected from two centers were used to construct a multicenter study to evaluate the performance of the proposed approach. The results showed the proposed technique outperformed individual classifiers and variable selection methods based on Cox's model such as Akaike and Bayesian information criterions and least absolute shrinkage and selector operator in p values of the log-rank test, sensitivity, and concordance index. This indicates that the proposed classifier is more powerful in correctly predicting the risk of re-intervention enabling doctor in selecting patients' future follow-up plan.

Hierarchical learning architecture with automatic feature selection for multiclass protein fold classification.

PubMed

Huang, Chuen-Der; Lin, Chin-Teng; Pal, Nikhil Ranjan

2003-12-01

The structure classification of proteins plays a very important role in bioinformatics, since the relationships and characteristics among those known proteins can be exploited to predict the structure of new proteins. The success of a classification system depends heavily on two things: the tools being used and the features considered. For the bioinformatics applications, the role of appropriate features has not been paid adequate importance. In this investigation we use three novel ideas for multiclass protein fold classification. First, we use the gating neural network, where each input node is associated with a gate. This network can select important features in an online manner when the learning goes on. At the beginning of the training, all gates are almost closed, i.e., no feature is allowed to enter the network. Through the training, gates corresponding to good features are completely opened while gates corresponding to bad features are closed more tightly, and some gates may be partially open. The second novel idea is to use a hierarchical learning architecture (HLA). The classifier in the first level of HLA classifies the protein features into four major classes: all alpha, all beta, alpha + beta, and alpha/beta. And in the next level we have another set of classifiers, which further classifies the protein features into 27 folds. The third novel idea is to induce the indirect coding features from the amino-acid composition sequence of proteins based on the N-gram concept. This provides us with more representative and discriminative new local features of protein sequences for multiclass protein fold classification. The proposed HLA with new indirect coding features increases the protein fold classification accuracy by about 12%. Moreover, the gating neural network is found to reduce the number of features drastically. Using only half of the original features selected by the gating neural network can reach comparable test accuracy as that using all the original features. The gating mechanism also helps us to get a better insight into the folding process of proteins. For example, tracking the evolution of different gates we can find which characteristics (features) of the data are more important for the folding process. And, of course, it also reduces the computation time.

Traffic sign recognition by color segmentation and neural network

NASA Astrophysics Data System (ADS)

Surinwarangkoon, Thongchai; Nitsuwat, Supot; Moore, Elvin J.

2011-12-01

An algorithm is proposed for traffic sign detection and identification based on color filtering, color segmentation and neural networks. Traffic signs in Thailand are classified by color into four types: namely, prohibitory signs (red or blue), general warning signs (yellow) and construction area warning signs (amber). A color filtering method is first used to detect traffic signs and classify them by type. Then color segmentation methods adapted for each color type are used to extract inner features, e.g., arrows, bars etc. Finally, neural networks trained to recognize signs in each color type are used to identify any given traffic sign. Experiments show that the algorithm can improve the accuracy of traffic sign detection and recognition for the traffic signs used in Thailand.

Statistical Learning Analysis in Neuroscience: Aiming for Transparency

PubMed Central

Hanke, Michael; Halchenko, Yaroslav O.; Haxby, James V.; Pollmann, Stefan

2009-01-01

Encouraged by a rise of reciprocal interest between the machine learning and neuroscience communities, several recent studies have demonstrated the explanatory power of statistical learning techniques for the analysis of neural data. In order to facilitate a wider adoption of these methods, neuroscientific research needs to ensure a maximum of transparency to allow for comprehensive evaluation of the employed procedures. We argue that such transparency requires “neuroscience-aware” technology for the performance of multivariate pattern analyses of neural data that can be documented in a comprehensive, yet comprehensible way. Recently, we introduced PyMVPA, a specialized Python framework for machine learning based data analysis that addresses this demand. Here, we review its features and applicability to various neural data modalities. PMID:20582270

Audio Spectrogram Representations for Processing with Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Wyse, L.

2017-05-01

One of the decisions that arise when designing a neural network for any application is how the data should be represented in order to be presented to, and possibly generated by, a neural network. For audio, the choice is less obvious than it seems to be for visual images, and a variety of representations have been used for different applications including the raw digitized sample stream, hand-crafted features, machine discovered features, MFCCs and variants that include deltas, and a variety of spectral representations. This paper reviews some of these representations and issues that arise, focusing particularly on spectrograms for generating audio using neural networks for style transfer.

Dynamic security contingency screening and ranking using neural networks.

PubMed

Mansour, Y; Vaahedi, E; El-Sharkawi, M A

1997-01-01

This paper summarizes BC Hydro's experience in applying neural networks to dynamic security contingency screening and ranking. The idea is to use the information on the prevailing operating condition and directly provide contingency screening and ranking using a trained neural network. To train the two neural networks for the large scale systems of BC Hydro and Hydro Quebec, in total 1691 detailed transient stability simulation were conducted, 1158 for BC Hydro system and 533 for the Hydro Quebec system. The simulation program was equipped with the energy margin calculation module (second kick) to measure the energy margin in each run. The first set of results showed poor performance for the neural networks in assessing the dynamic security. However a number of corrective measures improved the results significantly. These corrective measures included: 1) the effectiveness of output; 2) the number of outputs; 3) the type of features (static versus dynamic); 4) the number of features; 5) system partitioning; and 6) the ratio of training samples to features. The final results obtained using the large scale systems of BC Hydro and Hydro Quebec demonstrates a good potential for neural network in dynamic security assessment contingency screening and ranking.

Imbalance aware lithography hotspot detection: a deep learning approach

NASA Astrophysics Data System (ADS)

Yang, Haoyu; Luo, Luyang; Su, Jing; Lin, Chenxi; Yu, Bei

2017-07-01

With the advancement of very large scale integrated circuits (VLSI) technology nodes, lithographic hotspots become a serious problem that affects manufacture yield. Lithography hotspot detection at the post-OPC stage is imperative to check potential circuit failures when transferring designed patterns onto silicon wafers. Although conventional lithography hotspot detection methods, such as machine learning, have gained satisfactory performance, with the extreme scaling of transistor feature size and layout patterns growing in complexity, conventional methodologies may suffer from performance degradation. For example, manual or ad hoc feature extraction in a machine learning framework may lose important information when predicting potential errors in ultra-large-scale integrated circuit masks. We present a deep convolutional neural network (CNN) that targets representative feature learning in lithography hotspot detection. We carefully analyze the impact and effectiveness of different CNN hyperparameters, through which a hotspot-detection-oriented neural network model is established. Because hotspot patterns are always in the minority in VLSI mask design, the training dataset is highly imbalanced. In this situation, a neural network is no longer reliable, because a trained model with high classification accuracy may still suffer from a high number of false negative results (missing hotspots), which is fatal in hotspot detection problems. To address the imbalance problem, we further apply hotspot upsampling and random-mirror flipping before training the network. Experimental results show that our proposed neural network model achieves comparable or better performance on the ICCAD 2012 contest benchmark compared to state-of-the-art hotspot detectors based on deep or representative machine leaning.

Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology.

PubMed

Sharma, Harshita; Zerbe, Norman; Klempert, Iris; Hellwich, Olaf; Hufnagl, Peter

2017-11-01

Deep learning using convolutional neural networks is an actively emerging field in histological image analysis. This study explores deep learning methods for computer-aided classification in H&E stained histopathological whole slide images of gastric carcinoma. An introductory convolutional neural network architecture is proposed for two computerized applications, namely, cancer classification based on immunohistochemical response and necrosis detection based on the existence of tumor necrosis in the tissue. Classification performance of the developed deep learning approach is quantitatively compared with traditional image analysis methods in digital histopathology requiring prior computation of handcrafted features, such as statistical measures using gray level co-occurrence matrix, Gabor filter-bank responses, LBP histograms, gray histograms, HSV histograms and RGB histograms, followed by random forest machine learning. Additionally, the widely known AlexNet deep convolutional framework is comparatively analyzed for the corresponding classification problems. The proposed convolutional neural network architecture reports favorable results, with an overall classification accuracy of 0.6990 for cancer classification and 0.8144 for necrosis detection. Copyright © 2017 Elsevier Ltd. All rights reserved.

Neural network approach to proximity effect corrections in electron-beam lithography

NASA Astrophysics Data System (ADS)

Frye, Robert C.; Cummings, Kevin D.; Rietman, Edward A.

1990-05-01

The proximity effect, caused by electron beam backscattering during resist exposure, is an important concern in writing submicron features. It can be compensated by appropriate local changes in the incident beam dose, but computation of the optimal correction usually requires a prohibitively long time. We present an example of such a computation on a small test pattern, which we performed by an iterative method. We then used this solution as a training set for an adaptive neural network. After training, the network computed the same correction as the iterative method, but in a much shorter time. Correcting the image with a software based neural network resulted in a decrease in the computation time by a factor of 30, and a hardware based network enhanced the computation speed by more than a factor of 1000. Both methods had an acceptably small error of 0.5% compared to the results of the iterative computation. Additionally, we verified that the neural network correctly generalized the solution of the problem to include patterns not contained in its training set.

A Hybrid Spectral Clustering and Deep Neural Network Ensemble Algorithm for Intrusion Detection in Sensor Networks

PubMed Central

Ma, Tao; Wang, Fen; Cheng, Jianjun; Yu, Yang; Chen, Xiaoyun

2016-01-01

The development of intrusion detection systems (IDS) that are adapted to allow routers and network defence systems to detect malicious network traffic disguised as network protocols or normal access is a critical challenge. This paper proposes a novel approach called SCDNN, which combines spectral clustering (SC) and deep neural network (DNN) algorithms. First, the dataset is divided into k subsets based on sample similarity using cluster centres, as in SC. Next, the distance between data points in a testing set and the training set is measured based on similarity features and is fed into the deep neural network algorithm for intrusion detection. Six KDD-Cup99 and NSL-KDD datasets and a sensor network dataset were employed to test the performance of the model. These experimental results indicate that the SCDNN classifier not only performs better than backpropagation neural network (BPNN), support vector machine (SVM), random forest (RF) and Bayes tree models in detection accuracy and the types of abnormal attacks found. It also provides an effective tool of study and analysis of intrusion detection in large networks. PMID:27754380

A Hybrid Spectral Clustering and Deep Neural Network Ensemble Algorithm for Intrusion Detection in Sensor Networks.

PubMed

Ma, Tao; Wang, Fen; Cheng, Jianjun; Yu, Yang; Chen, Xiaoyun

2016-10-13

The development of intrusion detection systems (IDS) that are adapted to allow routers and network defence systems to detect malicious network traffic disguised as network protocols or normal access is a critical challenge. This paper proposes a novel approach called SCDNN, which combines spectral clustering (SC) and deep neural network (DNN) algorithms. First, the dataset is divided into k subsets based on sample similarity using cluster centres, as in SC. Next, the distance between data points in a testing set and the training set is measured based on similarity features and is fed into the deep neural network algorithm for intrusion detection. Six KDD-Cup99 and NSL-KDD datasets and a sensor network dataset were employed to test the performance of the model. These experimental results indicate that the SCDNN classifier not only performs better than backpropagation neural network (BPNN), support vector machine (SVM), random forest (RF) and Bayes tree models in detection accuracy and the types of abnormal attacks found. It also provides an effective tool of study and analysis of intrusion detection in large networks.

Internal representations for face detection: an application of noise-based image classification to BOLD responses.

PubMed

Nestor, Adrian; Vettel, Jean M; Tarr, Michael J

2013-11-01

What basic visual structures underlie human face detection and how can we extract such structures directly from the amplitude of neural responses elicited by face processing? Here, we address these issues by investigating an extension of noise-based image classification to BOLD responses recorded in high-level visual areas. First, we assess the applicability of this classification method to such data and, second, we explore its results in connection with the neural processing of faces. To this end, we construct luminance templates from white noise fields based on the response of face-selective areas in the human ventral cortex. Using behaviorally and neurally-derived classification images, our results reveal a family of simple but robust image structures subserving face representation and detection. Thus, we confirm the role played by classical face selective regions in face detection and we help clarify the representational basis of this perceptual function. From a theory standpoint, our findings support the idea of simple but highly diagnostic neurally-coded features for face detection. At the same time, from a methodological perspective, our work demonstrates the ability of noise-based image classification in conjunction with fMRI to help uncover the structure of high-level perceptual representations. Copyright © 2012 Wiley Periodicals, Inc.

Neural Network based Control of SG based Standalone Generating System with Energy Storage for Power Quality Enhancement

NASA Astrophysics Data System (ADS)

Nayar, Priya; Singh, Bhim; Mishra, Sukumar

2017-08-01

An artificial intelligence based control algorithm is used in solving power quality problems of a diesel engine driven synchronous generator with automatic voltage regulator and governor based standalone system. A voltage source converter integrated with a battery energy storage system is employed to mitigate the power quality problems. An adaptive neural network based signed regressor control algorithm is used for the estimation of the fundamental component of load currents for control of a standalone system with load leveling as an integral feature. The developed model of the system performs accurately under varying load conditions and provides good dynamic response to the step changes in loads. The real time performance is achieved using MATLAB along with simulink/simpower system toolboxes and results adhere to an IEEE-519 standard for power quality enhancement.

Dimensionality-varied convolutional neural network for spectral-spatial classification of hyperspectral data

NASA Astrophysics Data System (ADS)

Liu, Wanjun; Liang, Xuejian; Qu, Haicheng

2017-11-01

Hyperspectral image (HSI) classification is one of the most popular topics in remote sensing community. Traditional and deep learning-based classification methods were proposed constantly in recent years. In order to improve the classification accuracy and robustness, a dimensionality-varied convolutional neural network (DVCNN) was proposed in this paper. DVCNN was a novel deep architecture based on convolutional neural network (CNN). The input of DVCNN was a set of 3D patches selected from HSI which contained spectral-spatial joint information. In the following feature extraction process, each patch was transformed into some different 1D vectors by 3D convolution kernels, which were able to extract features from spectral-spatial data. The rest of DVCNN was about the same as general CNN and processed 2D matrix which was constituted by by all 1D data. So that the DVCNN could not only extract more accurate and rich features than CNN, but also fused spectral-spatial information to improve classification accuracy. Moreover, the robustness of network on water-absorption bands was enhanced in the process of spectral-spatial fusion by 3D convolution, and the calculation was simplified by dimensionality varied convolution. Experiments were performed on both Indian Pines and Pavia University scene datasets, and the results showed that the classification accuracy of DVCNN improved by 32.87% on Indian Pines and 19.63% on Pavia University scene than spectral-only CNN. The maximum accuracy improvement of DVCNN achievement was 13.72% compared with other state-of-the-art HSI classification methods, and the robustness of DVCNN on water-absorption bands noise was demonstrated.

Dynamical information encoding in neural adaptation.

PubMed

Luozheng Li; Wenhao Zhang; Yuanyuan Mi; Dahui Wang; Xiaohan Lin; Si Wu

2016-08-01

Adaptation refers to the general phenomenon that a neural system dynamically adjusts its response property according to the statistics of external inputs. In response to a prolonged constant stimulation, neuronal firing rates always first increase dramatically at the onset of the stimulation; and afterwards, they decrease rapidly to a low level close to background activity. This attenuation of neural activity seems to be contradictory to our experience that we can still sense the stimulus after the neural system is adapted. Thus, it prompts a question: where is the stimulus information encoded during the adaptation? Here, we investigate a computational model in which the neural system employs a dynamical encoding strategy during the neural adaptation: at the early stage of the adaptation, the stimulus information is mainly encoded in the strong independent firings; and as time goes on, the information is shifted into the weak but concerted responses of neurons. We find that short-term plasticity, a general feature of synapses, provides a natural mechanism to achieve this goal. Furthermore, we demonstrate that with balanced excitatory and inhibitory inputs, this correlation-based information can be read out efficiently. The implications of this study on our understanding of neural information encoding are discussed.

Slow cortical potentials and "inner time consciousness" - A neuro-phenomenal hypothesis about the "width of present".

PubMed

Northoff, Georg

2016-05-01

William James postulated a "stream of consciousness" that presupposes temporal continuity. The neuronal mechanisms underlying the construction of such temporal continuity remain unclear, however, in my contribution, I propose a neuro-phenomenal hypothesis that is based on slow cortical potentials and their extension of the present moment as described in the phenomenal term of "width of present". More specifically, I focus on the way the brain's neural activity needs to be encoded in order to make possible the "stream of consciousness." This leads us again to the low-frequency fluctuations of the brain's neural activity and more specifically to slow cortical potentials (SCPs). Due to their long phase duration as low-frequency fluctuations, SCPs can integrate different stimuli and their associated neural activity from different regions in one converging region. Such integration may be central for consciousness to occur, as it was recently postulated by He and Raichle. They leave open, however, the question of the exact neuronal mechanisms, like the encoding strategy, that make possible the association of the otherwise purely neuronal SCP with consciousness and its phenomenal features. I hypothesize that SCPs allow for linking and connecting different discrete points in physical time by encoding their statistically based temporal differences rather than the single discrete time points by themselves. This presupposes difference-based coding rather than stimulus-based coding. The encoding of such statistically based temporal differences makes it possible to "go beyond" the merely physical features of the stimuli; that is, their single discrete time points and their conduction delays (as related to their neural processing in the brain). This, in turn, makes possible the constitution of "local temporal continuity" of neural activity in one particular region. The concept of "local temporal continuity" signifies the linkage and integration of different discrete time points into one neural activity in a particular region. How does such local temporal continuity predispose the experience of time in consciousness? For that, I turn to phenomenological philosopher Edmund Husserl and his description of what he calls "inner time consciousness" (Husserl and Brough, 1990). One hallmark of humans' "inner time consciousness" is that we experience events and objects in succession and duration in our consciousness; according to Husserl, this amounts to what he calls the "width of [the] present." The concept of the width of present describes the extension of the present beyond the single discrete time point, such as, for instance, when we perceive different tones as a melody. I now hypothesize the degree of the width of present to be directly dependent upon and thus predisposed by the degree of the temporal differences between two (or more) discrete time points as they are encoded into neural activity. I therefore conclude that the SCPs and their encoding of neural activity in terms of temporal differences must be regarded a neural predisposition of consciousness (NPC) as distinguished from a neural correlate of consciousness (NCC). Copyright © 2015 Elsevier B.V. All rights reserved.

New wideband radar target classification method based on neural learning and modified Euclidean metric

NASA Astrophysics Data System (ADS)

Jiang, Yicheng; Cheng, Ping; Ou, Yangkui

2001-09-01

A new method for target classification of high-range resolution radar is proposed. It tries to use neural learning to obtain invariant subclass features of training range profiles. A modified Euclidean metric based on the Box-Cox transformation technique is investigated for Nearest Neighbor target classification improvement. The classification experiments using real radar data of three different aircraft have demonstrated that classification error can reduce 8% if this method proposed in this paper is chosen instead of the conventional method. The results of this paper have shown that by choosing an optimized metric, it is indeed possible to reduce the classification error without increasing the number of samples.

Visualization of suspicious lesions in breast MRI based on intelligent neural systems

NASA Astrophysics Data System (ADS)

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

2006-05-01

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

A Structural and Content-Based Analysis for Web Filtering.

ERIC Educational Resources Information Center

Lee, P. Y.; Hui, S. C.; Fong, A. C. M.

2003-01-01

Presents an analysis of the distinguishing features of pornographic Web pages so that effective filtering techniques can be developed. Surveys the existing techniques for Web content filtering and describes the implementation of a Web content filtering system that uses an artificial neural network. (Author/LRW)

Dynamic functional connectivity: Promise, issues, and interpretations

PubMed Central

Hutchison, R. Matthew; Womelsdorf, Thilo; Allen, Elena A.; Bandettini, Peter A.; Calhoun, Vince D.; Corbetta, Maurizio; Penna, Stefania Della; Duyn, Jeff H.; Glover, Gary H.; Gonzalez-Castillo, Javier; Handwerker, Daniel A.; Keilholz, Shella; Kiviniemi, Vesa; Leopold, David A.; de Pasquale, Francesco; Sporns, Olaf; Walter, Martin; Chang, Catie

2013-01-01

The brain must dynamically integrate, coordinate, and respond to internal and external stimuli across multiple time scales. Non-invasive measurements of brain activity with fMRI have greatly advanced our understanding of the large-scale functional organization supporting these fundamental features of brain function. Conclusions from previous resting-state fMRI investigations were based upon static descriptions of functional connectivity (FC), and only recently studies have begun to capitalize on the wealth of information contained within the temporal features of spontaneous BOLD FC. Emerging evidence suggests that dynamic FC metrics may index changes in macroscopic neural activity patterns underlying critical aspects of cognition and behavior, though limitations with regard to analysis and interpretation remain. Here, we review recent findings, methodological considerations, neural and behavioral correlates, and future directions in the emerging field of dynamic FC investigations. PMID:23707587

Tropical Timber Identification using Backpropagation Neural Network

NASA Astrophysics Data System (ADS)

Siregar, B.; Andayani, U.; Fatihah, N.; Hakim, L.; Fahmi, F.

2017-01-01

Each and every type of wood has different characteristics. Identifying the type of wood properly is important, especially for industries that need to know the type of timber specifically. However, it requires expertise in identifying the type of wood and only limited experts available. In addition, the manual identification even by experts is rather inefficient because it requires a lot of time and possibility of human errors. To overcome these problems, a digital image based method to identify the type of timber automatically is needed. In this study, backpropagation neural network is used as artificial intelligence component. Several stages were developed: a microscope image acquisition, pre-processing, feature extraction using gray level co-occurrence matrix and normalization of data extraction using decimal scaling features. The results showed that the proposed method was able to identify the timber with an accuracy of 94%.

Auto-Associative Recurrent Neural Networks and Long Term Dependencies in Novelty Detection for Audio Surveillance Applications

NASA Astrophysics Data System (ADS)

Rossi, A.; Montefoschi, F.; Rizzo, A.; Diligenti, M.; Festucci, C.

2017-10-01

Machine Learning applied to Automatic Audio Surveillance has been attracting increasing attention in recent years. In spite of several investigations based on a large number of different approaches, little attention had been paid to the environmental temporal evolution of the input signal. In this work, we propose an exploration in this direction comparing the temporal correlations extracted at the feature level with the one learned by a representational structure. To this aim we analysed the prediction performances of a Recurrent Neural Network architecture varying the length of the processed input sequence and the size of the time window used in the feature extraction. Results corroborated the hypothesis that sequential models work better when dealing with data characterized by temporal order. However, so far the optimization of the temporal dimension remains an open issue.

Diagnosing Autism Spectrum Disorder from Brain Resting-State Functional Connectivity Patterns Using a Deep Neural Network with a Novel Feature Selection Method.

PubMed

Guo, Xinyu; Dominick, Kelli C; Minai, Ali A; Li, Hailong; Erickson, Craig A; Lu, Long J

2017-01-01

The whole-brain functional connectivity (FC) pattern obtained from resting-state functional magnetic resonance imaging data are commonly applied to study neuropsychiatric conditions such as autism spectrum disorder (ASD) by using different machine learning models. Recent studies indicate that both hyper- and hypo- aberrant ASD-associated FCs were widely distributed throughout the entire brain rather than only in some specific brain regions. Deep neural networks (DNN) with multiple hidden layers have shown the ability to systematically extract lower-to-higher level information from high dimensional data across a series of neural hidden layers, significantly improving classification accuracy for such data. In this study, a DNN with a novel feature selection method (DNN-FS) is developed for the high dimensional whole-brain resting-state FC pattern classification of ASD patients vs. typical development (TD) controls. The feature selection method is able to help the DNN generate low dimensional high-quality representations of the whole-brain FC patterns by selecting features with high discriminating power from multiple trained sparse auto-encoders. For the comparison, a DNN without the feature selection method (DNN-woFS) is developed, and both of them are tested with different architectures (i.e., with different numbers of hidden layers/nodes). Results show that the best classification accuracy of 86.36% is generated by the DNN-FS approach with 3 hidden layers and 150 hidden nodes (3/150). Remarkably, DNN-FS outperforms DNN-woFS for all architectures studied. The most significant accuracy improvement was 9.09% with the 3/150 architecture. The method also outperforms other feature selection methods, e.g., two sample t -test and elastic net. In addition to improving the classification accuracy, a Fisher's score-based biomarker identification method based on the DNN is also developed, and used to identify 32 FCs related to ASD. These FCs come from or cross different pre-defined brain networks including the default-mode, cingulo-opercular, frontal-parietal, and cerebellum. Thirteen of them are statically significant between ASD and TD groups (two sample t -test p < 0.05) while 19 of them are not. The relationship between the statically significant FCs and the corresponding ASD behavior symptoms is discussed based on the literature and clinician's expert knowledge. Meanwhile, the potential reason of obtaining 19 FCs which are not statistically significant is also provided.

Deep-Learning Convolutional Neural Networks Accurately Classify Genetic Mutations in Gliomas.

PubMed

Chang, P; Grinband, J; Weinberg, B D; Bardis, M; Khy, M; Cadena, G; Su, M-Y; Cha, S; Filippi, C G; Bota, D; Baldi, P; Poisson, L M; Jain, R; Chow, D

2018-05-10

The World Health Organization has recently placed new emphasis on the integration of genetic information for gliomas. While tissue sampling remains the criterion standard, noninvasive imaging techniques may provide complimentary insight into clinically relevant genetic mutations. Our aim was to train a convolutional neural network to independently predict underlying molecular genetic mutation status in gliomas with high accuracy and identify the most predictive imaging features for each mutation. MR imaging data and molecular information were retrospectively obtained from The Cancer Imaging Archives for 259 patients with either low- or high-grade gliomas. A convolutional neural network was trained to classify isocitrate dehydrogenase 1 ( IDH1 ) mutation status, 1p/19q codeletion, and O6-methylguanine-DNA methyltransferase ( MGMT ) promotor methylation status. Principal component analysis of the final convolutional neural network layer was used to extract the key imaging features critical for successful classification. Classification had high accuracy: IDH1 mutation status, 94%; 1p/19q codeletion, 92%; and MGMT promotor methylation status, 83%. Each genetic category was also associated with distinctive imaging features such as definition of tumor margins, T1 and FLAIR suppression, extent of edema, extent of necrosis, and textural features. Our results indicate that for The Cancer Imaging Archives dataset, machine-learning approaches allow classification of individual genetic mutations of both low- and high-grade gliomas. We show that relevant MR imaging features acquired from an added dimensionality-reduction technique demonstrate that neural networks are capable of learning key imaging components without prior feature selection or human-directed training. © 2018 by American Journal of Neuroradiology.

Deep features for efficient multi-biometric recognition with face and ear images

NASA Astrophysics Data System (ADS)

Omara, Ibrahim; Xiao, Gang; Amrani, Moussa; Yan, Zifei; Zuo, Wangmeng

2017-07-01

Recently, multimodal biometric systems have received considerable research interest in many applications especially in the fields of security. Multimodal systems can increase the resistance to spoof attacks, provide more details and flexibility, and lead to better performance and lower error rate. In this paper, we present a multimodal biometric system based on face and ear, and propose how to exploit the extracted deep features from Convolutional Neural Networks (CNNs) on the face and ear images to introduce more powerful discriminative features and robust representation ability for them. First, the deep features for face and ear images are extracted based on VGG-M Net. Second, the extracted deep features are fused by using a traditional concatenation and a Discriminant Correlation Analysis (DCA) algorithm. Third, multiclass support vector machine is adopted for matching and classification. The experimental results show that the proposed multimodal system based on deep features is efficient and achieves a promising recognition rate up to 100 % by using face and ear. In addition, the results indicate that the fusion based on DCA is superior to traditional fusion.

Use of sEMG in identification of low level muscle activities: features based on ICA and fractal dimension.

PubMed

Naik, Ganesh R; Kumar, Dinesh K; Arjunan, Sridhar

2009-01-01

This paper has experimentally verified and compared features of sEMG (Surface Electromyogram) such as ICA (Independent Component Analysis) and Fractal Dimension (FD) for identification of low level forearm muscle activities. The fractal dimension was used as a feature as reported in the literature. The normalized feature values were used as training and testing vectors for an Artificial neural network (ANN), in order to reduce inter-experimental variations. The identification accuracy using FD of four channels sEMG was 58%, and increased to 96% when the signals are separated to their independent components using ICA.

Causal involvement of visual area MT in global feature-based enhancement but not contingent attentional capture.

PubMed

Painter, David R; Dux, Paul E; Mattingley, Jason B

2015-09-01

When visual attention is set for a particular target feature, such as color or shape, neural responses to that feature are enhanced across the visual field. This global feature-based enhancement is hypothesized to underlie the contingent attentional capture effect, in which task-irrelevant items with the target feature capture spatial attention. In humans, however, different cortical regions have been implicated in global feature-based enhancement and contingent capture. Here, we applied intermittent theta-burst stimulation (iTBS) to assess the causal roles of two regions of extrastriate cortex - right area MT and the right temporoparietal junction (TPJ) - in both global feature-based enhancement and contingent capture. We recorded cortical activity using EEG while participants monitored centrally for targets defined by color and ignored peripheral checkerboards that matched the distractor or target color. In central vision, targets were preceded by colored cues designed to capture attention. Stimuli flickered at unique frequencies, evoking distinct cortical oscillations. Analyses of these oscillations and behavioral performance revealed contingent capture in central vision and global feature-based enhancement in the periphery. Stimulation of right area MT selectively increased global feature-based enhancement, but did not influence contingent attentional capture. By contrast, stimulation of the right TPJ left both processes unaffected. Our results reveal a causal role for the right area MT in feature-based attention, and suggest that global feature-based enhancement does not underlie the contingent capture effect. Copyright © 2015 Elsevier Inc. All rights reserved.

Expectation and Surprise Determine Neural Population Responses in the Ventral Visual Stream

PubMed Central

Egner, Tobias; Monti, Jim M.; Summerfield, Christopher

2014-01-01

Visual cortex is traditionally viewed as a hierarchy of neural feature detectors, with neural population responses being driven by bottom-up stimulus features. Conversely, “predictive coding” models propose that each stage of the visual hierarchy harbors two computationally distinct classes of processing unit: representational units that encode the conditional probability of a stimulus and provide predictions to the next lower level; and error units that encode the mismatch between predictions and bottom-up evidence, and forward prediction error to the next higher level. Predictive coding therefore suggests that neural population responses in category-selective visual regions, like the fusiform face area (FFA), reflect a summation of activity related to prediction (“face expectation”) and prediction error (“face surprise”), rather than a homogenous feature detection response. We tested the rival hypotheses of the feature detection and predictive coding models by collecting functional magnetic resonance imaging data from the FFA while independently varying both stimulus features (faces vs houses) and subjects’ perceptual expectations regarding those features (low vs medium vs high face expectation). The effects of stimulus and expectation factors interacted, whereby FFA activity elicited by face and house stimuli was indistinguishable under high face expectation and maximally differentiated under low face expectation. Using computational modeling, we show that these data can be explained by predictive coding but not by feature detection models, even when the latter are augmented with attentional mechanisms. Thus, population responses in the ventral visual stream appear to be determined by feature expectation and surprise rather than by stimulus features per se. PMID:21147999

Electronic Neural Networks

NASA Technical Reports Server (NTRS)

Thakoor, Anil

1990-01-01

Viewgraphs on electronic neural networks for space station are presented. Topics covered include: electronic neural networks; electronic implementations; VLSI/thin film hybrid hardware for neurocomputing; computations with analog parallel processing; features of neuroprocessors; applications of neuroprocessors; neural network hardware for terrain trafficability determination; a dedicated processor for path planning; neural network system interface; neural network for robotic control; error backpropagation algorithm for learning; resource allocation matrix; global optimization neuroprocessor; and electrically programmable read only thin-film synaptic array.

Amphioxus and lamprey AP-2 genes: implications for neural crest evolution and migration patterns

NASA Technical Reports Server (NTRS)

Meulemans, Daniel; Bronner-Fraser, Marianne

2002-01-01

The neural crest is a uniquely vertebrate cell type present in the most basal vertebrates, but not in cephalochordates. We have studied differences in regulation of the neural crest marker AP-2 across two evolutionary transitions: invertebrate to vertebrate, and agnathan to gnathostome. Isolation and comparison of amphioxus, lamprey and axolotl AP-2 reveals its extensive expansion in the vertebrate dorsal neural tube and pharyngeal arches, implying co-option of AP-2 genes by neural crest cells early in vertebrate evolution. Expression in non-neural ectoderm is a conserved feature in amphioxus and vertebrates, suggesting an ancient role for AP-2 genes in this tissue. There is also common expression in subsets of ventrolateral neurons in the anterior neural tube, consistent with a primitive role in brain development. Comparison of AP-2 expression in axolotl and lamprey suggests an elaboration of cranial neural crest patterning in gnathostomes. However, migration of AP-2-expressing neural crest cells medial to the pharyngeal arch mesoderm appears to be a primitive feature retained in all vertebrates. Because AP-2 has essential roles in cranial neural crest differentiation and proliferation, the co-option of AP-2 by neural crest cells in the vertebrate lineage was a potentially crucial event in vertebrate evolution.

A Sieving ANN for Emotion-Based Movie Clip Classification

NASA Astrophysics Data System (ADS)

Watanapa, Saowaluk C.; Thipakorn, Bundit; Charoenkitkarn, Nipon

Effective classification and analysis of semantic contents are very important for the content-based indexing and retrieval of video database. Our research attempts to classify movie clips into three groups of commonly elicited emotions, namely excitement, joy and sadness, based on a set of abstract-level semantic features extracted from the film sequence. In particular, these features consist of six visual and audio measures grounded on the artistic film theories. A unique sieving-structured neural network is proposed to be the classifying model due to its robustness. The performance of the proposed model is tested with 101 movie clips excerpted from 24 award-winning and well-known Hollywood feature films. The experimental result of 97.8% correct classification rate, measured against the collected human-judges, indicates the great potential of using abstract-level semantic features as an engineered tool for the application of video-content retrieval/indexing.

Oscillatory neural representations in the sensory thalamus predict neuropathic pain relief by deep brain stimulation.

PubMed

Huang, Yongzhi; Green, Alexander L; Hyam, Jonathan; Fitzgerald, James; Aziz, Tipu Z; Wang, Shouyan

2018-01-01

Understanding the function of sensory thalamic neural activity is essential for developing and improving interventions for neuropathic pain. However, there is a lack of investigation of the relationship between sensory thalamic oscillations and pain relief in patients with neuropathic pain. This study aims to identify the oscillatory neural characteristics correlated with pain relief induced by deep brain stimulation (DBS), and develop a quantitative model to predict pain relief by integrating characteristic measures of the neural oscillations. Measures of sensory thalamic local field potentials (LFPs) in thirteen patients with neuropathic pain were screened in three dimensional feature space according to the rhythm, balancing, and coupling neural behaviours, and correlated with pain relief. An integrated approach based on principal component analysis (PCA) and multiple regression analysis is proposed to integrate the multiple measures and provide a predictive model. This study reveals distinct thalamic rhythms of theta, alpha, high beta and high gamma oscillations correlating with pain relief. The balancing and coupling measures between these neural oscillations were also significantly correlated with pain relief. The study enriches the series research on the function of thalamic neural oscillations in neuropathic pain and relief, and provides a quantitative approach for predicting pain relief by DBS using thalamic neural oscillations. Copyright © 2017 Elsevier Inc. All rights reserved.

Feature extraction for ultrasonic sensor based defect detection in ceramic components

NASA Astrophysics Data System (ADS)

Kesharaju, Manasa; Nagarajah, Romesh

2014-02-01

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

A reverberation-time-aware DNN approach leveraging spatial information for microphone array dereverberation

NASA Astrophysics Data System (ADS)

Wu, Bo; Yang, Minglei; Li, Kehuang; Huang, Zhen; Siniscalchi, Sabato Marco; Wang, Tong; Lee, Chin-Hui

2017-12-01

A reverberation-time-aware deep-neural-network (DNN)-based multi-channel speech dereverberation framework is proposed to handle a wide range of reverberation times (RT60s). There are three key steps in designing a robust system. First, to accomplish simultaneous speech dereverberation and beamforming, we propose a framework, namely DNNSpatial, by selectively concatenating log-power spectral (LPS) input features of reverberant speech from multiple microphones in an array and map them into the expected output LPS features of anechoic reference speech based on a single deep neural network (DNN). Next, the temporal auto-correlation function of received signals at different RT60s is investigated to show that RT60-dependent temporal-spatial contexts in feature selection are needed in the DNNSpatial training stage in order to optimize the system performance in diverse reverberant environments. Finally, the RT60 is estimated to select the proper temporal and spatial contexts before feeding the log-power spectrum features to the trained DNNs for speech dereverberation. The experimental evidence gathered in this study indicates that the proposed framework outperforms the state-of-the-art signal processing dereverberation algorithm weighted prediction error (WPE) and conventional DNNSpatial systems without taking the reverberation time into account, even for extremely weak and severe reverberant conditions. The proposed technique generalizes well to unseen room size, array geometry and loudspeaker position, and is robust to reverberation time estimation error.

The Spotlight of Attention Illuminates Failed Feature-based Expectancies

PubMed Central

Bengson, Jesse J.; Lopez-Calderon, Javier; Mangun, George R.

2012-01-01

A well-replicated finding is that visual stimuli presented at an attended location are afforded a processing benefit in the form of speeded reaction times and increased accuracy (Posner, 1979; Mangun 1995). This effect has been described using a spotlight metaphor, in which all stimuli within the focus of spatial attention receive facilitated processing, irrespective of other stimulus parameters. However, the spotlight metaphor has been brought into question by a series of combined expectancy studies which demonstrated that the behavioral benefits of spatial attention are contingent upon secondary feature-based expectancies (Kingstone, 1992). The present work used an event-related potential (ERP) approach to reveal that the early neural signature of the spotlight of spatial attention is not sensitive to the validity of secondary feature-based expectancies. PMID:22775503

Artificial Neural Networks: A Novel Approach to Analysing the Nutritional Ecology of a Blowfly Species, Chrysomya megacephala

PubMed Central

Bianconi, André; Zuben, Cláudio J. Von; Serapião, Adriane B. de S.; Govone, José S.

2010-01-01

Bionomic features of blowflies may be clarified and detailed by the deployment of appropriate modelling techniques such as artificial neural networks, which are mathematical tools widely applied to the resolution of complex biological problems. The principal aim of this work was to use three well-known neural networks, namely Multi-Layer Perceptron (MLP), Radial Basis Function (RBF), and Adaptive Neural Network-Based Fuzzy Inference System (ANFIS), to ascertain whether these tools would be able to outperform a classical statistical method (multiple linear regression) in the prediction of the number of resultant adults (survivors) of experimental populations of Chrysomya megacephala (F.) (Diptera: Calliphoridae), based on initial larval density (number of larvae), amount of available food, and duration of immature stages. The coefficient of determination (R2) derived from the RBF was the lowest in the testing subset in relation to the other neural networks, even though its R2 in the training subset exhibited virtually a maximum value. The ANFIS model permitted the achievement of the best testing performance. Hence this model was deemed to be more effective in relation to MLP and RBF for predicting the number of survivors. All three networks outperformed the multiple linear regression, indicating that neural models could be taken as feasible techniques for predicting bionomic variables concerning the nutritional dynamics of blowflies. PMID:20569135

Neural Correlates of the Encoding of Multimodal Contextual Features

ERIC Educational Resources Information Center

Gottlieb, Lauren J.; Wong, Jenny; de Chastelaine, Marianne; Rugg, Michael D.

2012-01-01

Functional magnetic resonance imaging (fMRI) was employed to identify neural regions engaged during the encoding of contextual features belonging to different modalities. Subjects studied objects that were presented to the left or right of fixation. Each object was paired with its name, spoken in either a male or a female voice. The test…

Singing-Related Activity in Anterior Forebrain of Male Zebra Finches Reflects Courtship Motivation for Target Females

PubMed Central

Iwasaki, Mai; Poulsen, Thomas M.; Oka, Kotaro; Hessler, Neal A.

2013-01-01

A critical function of singing by male songbirds is to attract a female mate. Previous studies have suggested that the anterior forebrain system is involved in this courtship behavior. Neural activity in this system, including the striatal Area X, is strikingly dependent on the function of male singing. When males sing to attract a female bird rather than while alone, less variable neural activity results in less variable song spectral features, which may be attractive to the female. These characteristics of neural activity and singing thus may reflect a male's motivation for courtship. Here, we compared the variability of neural activity and song features between courtship singing directed to a female with whom a male had previously formed a pair-bond or to other females. Surprisingly, across all units, there was no clear tendency for a difference in variability of neural activity or song features between courtship of paired females, nonpaired females, or dummy females. However, across the population of recordings, there was a significant relationship between the relative variability of syllable frequency and neural activity: when syllable frequency was less variable to paired than nonpaired females, neural activity was also less variable (and vice-versa). These results show that the lower variability of neural activity and syllable frequency during directed singing is not a binary distinction from undirected singing, but can vary in intensity, possibly related to the relative preference of a male for his singing target. PMID:24312344

SiNC: Saliency-injected neural codes for representation and efficient retrieval of medical radiographs

PubMed Central

Sajjad, Muhammad; Mehmood, Irfan; Baik, Sung Wook

2017-01-01

Medical image collections contain a wealth of information which can assist radiologists and medical experts in diagnosis and disease detection for making well-informed decisions. However, this objective can only be realized if efficient access is provided to semantically relevant cases from the ever-growing medical image repositories. In this paper, we present an efficient method for representing medical images by incorporating visual saliency and deep features obtained from a fine-tuned convolutional neural network (CNN) pre-trained on natural images. Saliency detector is employed to automatically identify regions of interest like tumors, fractures, and calcified spots in images prior to feature extraction. Neuronal activation features termed as neural codes from different CNN layers are comprehensively studied to identify most appropriate features for representing radiographs. This study revealed that neural codes from the last fully connected layer of the fine-tuned CNN are found to be the most suitable for representing medical images. The neural codes extracted from the entire image and salient part of the image are fused to obtain the saliency-injected neural codes (SiNC) descriptor which is used for indexing and retrieval. Finally, locality sensitive hashing techniques are applied on the SiNC descriptor to acquire short binary codes for allowing efficient retrieval in large scale image collections. Comprehensive experimental evaluations on the radiology images dataset reveal that the proposed framework achieves high retrieval accuracy and efficiency for scalable image retrieval applications and compares favorably with existing approaches. PMID:28771497

Towards intelligent diagnostic system employing integration of mathematical and engineering model

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

Isa, Nor Ashidi Mat

The development of medical diagnostic system has been one of the main research fields during years. The goal of the medical diagnostic system is to place a nosological system that could ease the diagnostic evaluation normally performed by scientists and doctors. Efficient diagnostic evaluation is essentials and requires broad knowledge in order to improve conventional diagnostic system. Several approaches on developing the medical diagnostic system have been designed and tested since the earliest 60s. Attempts on improving their performance have been made which utilizes the fields of artificial intelligence, statistical analyses, mathematical model and engineering theories. With the availability ofmore » the microcomputer and software development as well as the promising aforementioned fields, medical diagnostic prototypes could be developed. In general, the medical diagnostic system consists of several stages, namely the 1) data acquisition, 2) feature extraction, 3) feature selection, and 4) classifications stages. Data acquisition stage plays an important role in converting the inputs measured from the real world physical conditions to the digital numeric values that can be manipulated by the computer system. One of the common medical inputs could be medical microscopic images, radiographic images, magnetic resonance image (MRI) as well as medical signals such as electrocardiogram (ECG) and electroencephalogram (EEG). Normally, the scientist or doctors have to deal with myriad of data and redundant to be processed. In order to reduce the complexity of the diagnosis process, only the significant features of the raw data such as peak value of the ECG signal or size of lesion in the mammogram images will be extracted and considered in the subsequent stages. Mathematical models and statistical analyses will be performed to select the most significant features to be classified. The statistical analyses such as principal component analysis and discriminant analysis as well as mathematical model of clustering technique have been widely used in developing the medical diagnostic systems. The selected features will be classified using mathematical models that embedded engineering theory such as artificial intelligence, support vector machine, neural network and fuzzy-neuro system. These classifiers will provide the diagnostic results without human intervention. Among many publishable researches, several prototypes have been developed namely NeuralPap, Neural Mammo, and Cervix Kit. The former system (NeuralPap) is an automatic intelligent diagnostic system for classifying and distinguishing between the normal and cervical cancerous cells. Meanwhile, the Cervix Kit is a portable Field-programmable gate array (FPGA)-based cervical diagnostic kit that could automatically diagnose the cancerous cell based on the images obtained during sampling test. Besides the cervical diagnostic system, the Neural Mammo system is developed to specifically aid the diagnosis of breast cancer using a fine needle aspiration image.« less

Towards intelligent diagnostic system employing integration of mathematical and engineering model

NASA Astrophysics Data System (ADS)

Isa, Nor Ashidi Mat

2015-05-01

The development of medical diagnostic system has been one of the main research fields during years. The goal of the medical diagnostic system is to place a nosological system that could ease the diagnostic evaluation normally performed by scientists and doctors. Efficient diagnostic evaluation is essentials and requires broad knowledge in order to improve conventional diagnostic system. Several approaches on developing the medical diagnostic system have been designed and tested since the earliest 60s. Attempts on improving their performance have been made which utilizes the fields of artificial intelligence, statistical analyses, mathematical model and engineering theories. With the availability of the microcomputer and software development as well as the promising aforementioned fields, medical diagnostic prototypes could be developed. In general, the medical diagnostic system consists of several stages, namely the 1) data acquisition, 2) feature extraction, 3) feature selection, and 4) classifications stages. Data acquisition stage plays an important role in converting the inputs measured from the real world physical conditions to the digital numeric values that can be manipulated by the computer system. One of the common medical inputs could be medical microscopic images, radiographic images, magnetic resonance image (MRI) as well as medical signals such as electrocardiogram (ECG) and electroencephalogram (EEG). Normally, the scientist or doctors have to deal with myriad of data and redundant to be processed. In order to reduce the complexity of the diagnosis process, only the significant features of the raw data such as peak value of the ECG signal or size of lesion in the mammogram images will be extracted and considered in the subsequent stages. Mathematical models and statistical analyses will be performed to select the most significant features to be classified. The statistical analyses such as principal component analysis and discriminant analysis as well as mathematical model of clustering technique have been widely used in developing the medical diagnostic systems. The selected features will be classified using mathematical models that embedded engineering theory such as artificial intelligence, support vector machine, neural network and fuzzy-neuro system. These classifiers will provide the diagnostic results without human intervention. Among many publishable researches, several prototypes have been developed namely NeuralPap, Neural Mammo, and Cervix Kit. The former system (NeuralPap) is an automatic intelligent diagnostic system for classifying and distinguishing between the normal and cervical cancerous cells. Meanwhile, the Cervix Kit is a portable Field-programmable gate array (FPGA)-based cervical diagnostic kit that could automatically diagnose the cancerous cell based on the images obtained during sampling test. Besides the cervical diagnostic system, the Neural Mammo system is developed to specifically aid the diagnosis of breast cancer using a fine needle aspiration image.

Attention Determines Contextual Enhancement versus Suppression in Human Primary Visual Cortex.

PubMed

Flevaris, Anastasia V; Murray, Scott O

2015-09-02

Neural responses in primary visual cortex (V1) depend on stimulus context in seemingly complex ways. For example, responses to an oriented stimulus can be suppressed when it is flanked by iso-oriented versus orthogonally oriented stimuli but can also be enhanced when attention is directed to iso-oriented versus orthogonal flanking stimuli. Thus the exact same contextual stimulus arrangement can have completely opposite effects on neural responses-in some cases leading to orientation-tuned suppression and in other cases leading to orientation-tuned enhancement. Here we show that stimulus-based suppression and enhancement of fMRI responses in humans depends on small changes in the focus of attention and can be explained by a model that combines feature-based attention with response normalization. Neurons in the primary visual cortex (V1) respond to stimuli within a restricted portion of the visual field, termed their "receptive field." However, neuronal responses can also be influenced by stimuli that surround a receptive field, although the nature of these contextual interactions and underlying neural mechanisms are debated. Here we show that the response in V1 to a stimulus in the same context can either be suppressed or enhanced depending on the focus of attention. We are able to explain the results using a simple computational model that combines two well established properties of visual cortical responses: response normalization and feature-based enhancement. Copyright © 2015 the authors 0270-6474/15/3512273-08$15.00/0.

Analysis of feature selection with Probabilistic Neural Network (PNN) to classify sources influencing indoor air quality

NASA Astrophysics Data System (ADS)

Saad, S. M.; Shakaff, A. Y. M.; Saad, A. R. M.; Yusof, A. M.; Andrew, A. M.; Zakaria, A.; Adom, A. H.

2017-03-01

There are various sources influencing indoor air quality (IAQ) which could emit dangerous gases such as carbon monoxide (CO), carbon dioxide (CO2), ozone (O3) and particulate matter. These gases are usually safe for us to breathe in if they are emitted in safe quantity but if the amount of these gases exceeded the safe level, they might be hazardous to human being especially children and people with asthmatic problem. Therefore, a smart indoor air quality monitoring system (IAQMS) is needed that able to tell the occupants about which sources that trigger the indoor air pollution. In this project, an IAQMS that able to classify sources influencing IAQ has been developed. This IAQMS applies a classification method based on Probabilistic Neural Network (PNN). It is used to classify the sources of indoor air pollution based on five conditions: ambient air, human activity, presence of chemical products, presence of food and beverage, and presence of fragrance. In order to get good and best classification accuracy, an analysis of several feature selection based on data pre-processing method is done to discriminate among the sources. The output from each data pre-processing method has been used as the input for the neural network. The result shows that PNN analysis with the data pre-processing method give good classification accuracy of 99.89% and able to classify the sources influencing IAQ high classification rate.

Crossmodal integration enhances neural representation of task-relevant features in audiovisual face perception.

PubMed

Li, Yuanqing; Long, Jinyi; Huang, Biao; Yu, Tianyou; Wu, Wei; Liu, Yongjian; Liang, Changhong; Sun, Pei

2015-02-01

Previous studies have shown that audiovisual integration improves identification performance and enhances neural activity in heteromodal brain areas, for example, the posterior superior temporal sulcus/middle temporal gyrus (pSTS/MTG). Furthermore, it has also been demonstrated that attention plays an important role in crossmodal integration. In this study, we considered crossmodal integration in audiovisual facial perception and explored its effect on the neural representation of features. The audiovisual stimuli in the experiment consisted of facial movie clips that could be classified into 2 gender categories (male vs. female) or 2 emotion categories (crying vs. laughing). The visual/auditory-only stimuli were created from these movie clips by removing the auditory/visual contents. The subjects needed to make a judgment about the gender/emotion category for each movie clip in the audiovisual, visual-only, or auditory-only stimulus condition as functional magnetic resonance imaging (fMRI) signals were recorded. The neural representation of the gender/emotion feature was assessed using the decoding accuracy and the brain pattern-related reproducibility indices, obtained by a multivariate pattern analysis method from the fMRI data. In comparison to the visual-only and auditory-only stimulus conditions, we found that audiovisual integration enhanced the neural representation of task-relevant features and that feature-selective attention might play a role of modulation in the audiovisual integration. © The Author 2013. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Predicting the Emplacement of Improvised Explosive Devices: An Innovative Solution

ERIC Educational Resources Information Center

Lerner, Warren D.

2013-01-01

In this quantitative correlational study, simulated data were employed to examine artificial-intelligence techniques or, more specifically, artificial neural networks, as they relate to the location prediction of improvised explosive devices (IEDs). An ANN model was developed to predict IED placement, based upon terrain features and objects…

Developing a multimodal biometric authentication system using soft computing methods.

PubMed

Malcangi, Mario

2015-01-01

Robust personal authentication is becoming ever more important in computer-based applications. Among a variety of methods, biometric offers several advantages, mainly in embedded system applications. Hard and soft multi-biometric, combined with hard and soft computing methods, can be applied to improve the personal authentication process and to generalize the applicability. This chapter describes the embedded implementation of a multi-biometric (voiceprint and fingerprint) multimodal identification system based on hard computing methods (DSP) for feature extraction and matching, an artificial neural network (ANN) for soft feature pattern matching, and a fuzzy logic engine (FLE) for data fusion and decision.

A universal deep learning approach for modeling the flow of patients under different severities.

PubMed

Jiang, Shancheng; Chin, Kwai-Sang; Tsui, Kwok L

2018-02-01

The Accident and Emergency Department (A&ED) is the frontline for providing emergency care in hospitals. Unfortunately, relative A&ED resources have failed to keep up with continuously increasing demand in recent years, which leads to overcrowding in A&ED. Knowing the fluctuation of patient arrival volume in advance is a significant premise to relieve this pressure. Based on this motivation, the objective of this study is to explore an integrated framework with high accuracy for predicting A&ED patient flow under different triage levels, by combining a novel feature selection process with deep neural networks. Administrative data is collected from an actual A&ED and categorized into five groups based on different triage levels. A genetic algorithm (GA)-based feature selection algorithm is improved and implemented as a pre-processing step for this time-series prediction problem, in order to explore key features affecting patient flow. In our improved GA, a fitness-based crossover is proposed to maintain the joint information of multiple features during iterative process, instead of traditional point-based crossover. Deep neural networks (DNN) is employed as the prediction model to utilize their universal adaptability and high flexibility. In the model-training process, the learning algorithm is well-configured based on a parallel stochastic gradient descent algorithm. Two effective regularization strategies are integrated in one DNN framework to avoid overfitting. All introduced hyper-parameters are optimized efficiently by grid-search in one pass. As for feature selection, our improved GA-based feature selection algorithm has outperformed a typical GA and four state-of-the-art feature selection algorithms (mRMR, SAFS, VIFR, and CFR). As for the prediction accuracy of proposed integrated framework, compared with other frequently used statistical models (GLM, seasonal-ARIMA, ARIMAX, and ANN) and modern machine models (SVM-RBF, SVM-linear, RF, and R-LASSO), the proposed integrated "DNN-I-GA" framework achieves higher prediction accuracy on both MAPE and RMSE metrics in pairwise comparisons. The contribution of our study is two-fold. Theoretically, the traditional GA-based feature selection process is improved to have less hyper-parameters and higher efficiency, and the joint information of multiple features is maintained by fitness-based crossover operator. The universal property of DNN is further enhanced by merging different regularization strategies. Practically, features selected by our improved GA can be used to acquire an underlying relationship between patient flows and input features. Predictive values are significant indicators of patients' demand and can be used by A&ED managers to make resource planning and allocation. High accuracy achieved by the present framework in different cases enhances the reliability of downstream decision makings. Copyright © 2017 Elsevier B.V. All rights reserved.

Design of a Closed-Loop, Bidirectional Brain Machine Interface System With Energy Efficient Neural Feature Extraction and PID Control.

PubMed

Liu, Xilin; Zhang, Milin; Richardson, Andrew G; Lucas, Timothy H; Van der Spiegel, Jan

2017-08-01

This paper presents a bidirectional brain machine interface (BMI) microsystem designed for closed-loop neuroscience research, especially experiments in freely behaving animals. The system-on-chip (SoC) consists of 16-channel neural recording front-ends, neural feature extraction units, 16-channel programmable neural stimulator back-ends, in-channel programmable closed-loop controllers, global analog-digital converters (ADC), and peripheral circuits. The proposed neural feature extraction units includes 1) an ultra low-power neural energy extraction unit enabling a 64-step natural logarithmic domain frequency tuning, and 2) a current-mode action potential (AP) detection unit with time-amplitude window discriminator. A programmable proportional-integral-derivative (PID) controller has been integrated in each channel enabling a various of closed-loop operations. The implemented ADCs include a 10-bit voltage-mode successive approximation register (SAR) ADC for the digitization of the neural feature outputs and/or local field potential (LFP) outputs, and an 8-bit current-mode SAR ADC for the digitization of the action potential outputs. The multi-mode stimulator can be programmed to perform monopolar or bipolar, symmetrical or asymmetrical charge balanced stimulation with a maximum current of 4 mA in an arbitrary channel configuration. The chip has been fabricated in 0.18 μ m CMOS technology, occupying a silicon area of 3.7 mm 2 . The chip dissipates 56 μW/ch on average. General purpose low-power microcontroller with Bluetooth module are integrated in the system to provide wireless link and SoC configuration. Methods, circuit techniques and system topology proposed in this work can be used in a wide range of relevant neurophysiology research, especially closed-loop BMI experiments.

Modular, Hierarchical Learning By Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Baldi, Pierre F.; Toomarian, Nikzad

1996-01-01

Modular and hierarchical approach to supervised learning by artificial neural networks leads to neural networks more structured than neural networks in which all neurons fully interconnected. These networks utilize general feedforward flow of information and sparse recurrent connections to achieve dynamical effects. The modular organization, sparsity of modular units and connections, and fact that learning is much more circumscribed are all attractive features for designing neural-network hardware. Learning streamlined by imitating some aspects of biological neural networks.

Chinese License Plates Recognition Method Based on A Robust and Efficient Feature Extraction and BPNN Algorithm

NASA Astrophysics Data System (ADS)

Zhang, Ming; Xie, Fei; Zhao, Jing; Sun, Rui; Zhang, Lei; Zhang, Yue

2018-04-01

The prosperity of license plate recognition technology has made great contribution to the development of Intelligent Transport System (ITS). In this paper, a robust and efficient license plate recognition method is proposed which is based on a combined feature extraction model and BPNN (Back Propagation Neural Network) algorithm. Firstly, the candidate region of the license plate detection and segmentation method is developed. Secondly, a new feature extraction model is designed considering three sets of features combination. Thirdly, the license plates classification and recognition method using the combined feature model and BPNN algorithm is presented. Finally, the experimental results indicate that the license plate segmentation and recognition both can be achieved effectively by the proposed algorithm. Compared with three traditional methods, the recognition accuracy of the proposed method has increased to 95.7% and the consuming time has decreased to 51.4ms.

Prediction of troponin-T degradation using color image texture features in 10d aged beef longissimus steaks.

PubMed

Sun, X; Chen, K J; Berg, E P; Newman, D J; Schwartz, C A; Keller, W L; Maddock Carlin, K R

2014-02-01

The objective was to use digital color image texture features to predict troponin-T degradation in beef. Image texture features, including 88 gray level co-occurrence texture features, 81 two-dimension fast Fourier transformation texture features, and 48 Gabor wavelet filter texture features, were extracted from color images of beef strip steaks (longissimus dorsi, n = 102) aged for 10d obtained using a digital camera and additional lighting. Steaks were designated degraded or not-degraded based on troponin-T degradation determined on d 3 and d 10 postmortem by immunoblotting. Statistical analysis (STEPWISE regression model) and artificial neural network (support vector machine model, SVM) methods were designed to classify protein degradation. The d 3 and d 10 STEPWISE models were 94% and 86% accurate, respectively, while the d 3 and d 10 SVM models were 63% and 71%, respectively, in predicting protein degradation in aged meat. STEPWISE and SVM models based on image texture features show potential to predict troponin-T degradation in meat. © 2013.

Corpus callosum segmentation using deep neural networks with prior information from multi-atlas images

NASA Astrophysics Data System (ADS)

Park, Gilsoon; Hong, Jinwoo; Lee, Jong-Min

2018-03-01

In human brain, Corpus Callosum (CC) is the largest white matter structure, connecting between right and left hemispheres. Structural features such as shape and size of CC in midsagittal plane are of great significance for analyzing various neurological diseases, for example Alzheimer's disease, autism and epilepsy. For quantitative and qualitative studies of CC in brain MR images, robust segmentation of CC is important. In this paper, we present a novel method for CC segmentation. Our approach is based on deep neural networks and the prior information generated from multi-atlas images. Deep neural networks have recently shown good performance in various image processing field. Convolutional neural networks (CNN) have shown outstanding performance for classification and segmentation in medical image fields. We used convolutional neural networks for CC segmentation. Multi-atlas based segmentation model have been widely used in medical image segmentation because atlas has powerful information about the target structure we want to segment, consisting of MR images and corresponding manual segmentation of the target structure. We combined the prior information, such as location and intensity distribution of target structure (i.e. CC), made from multi-atlas images in CNN training process for more improving training. The CNN with prior information showed better segmentation performance than without.

Estimation of effective connectivity via data-driven neural modeling

PubMed Central

Freestone, Dean R.; Karoly, Philippa J.; Nešić, Dragan; Aram, Parham; Cook, Mark J.; Grayden, David B.

2014-01-01

This research introduces a new method for functional brain imaging via a process of model inversion. By estimating parameters of a computational model, we are able to track effective connectivity and mean membrane potential dynamics that cannot be directly measured using electrophysiological measurements alone. The ability to track the hidden aspects of neurophysiology will have a profound impact on the way we understand and treat epilepsy. For example, under the assumption the model captures the key features of the cortical circuits of interest, the framework will provide insights into seizure initiation and termination on a patient-specific basis. It will enable investigation into the effect a particular drug has on specific neural populations and connectivity structures using minimally invasive measurements. The method is based on approximating brain networks using an interconnected neural population model. The neural population model is based on a neural mass model that describes the functional activity of the brain, capturing the mesoscopic biophysics and anatomical structure. The model is made subject-specific by estimating the strength of intra-cortical connections within a region and inter-cortical connections between regions using a novel Kalman filtering method. We demonstrate through simulation how the framework can be used to track the mechanisms involved in seizure initiation and termination. PMID:25506315

Id expression in amphioxus and lamprey highlights the role of gene cooption during neural crest evolution

NASA Technical Reports Server (NTRS)

Meulemans, Daniel; McCauley, David; Bronner-Fraser, Marianne

2003-01-01

Neural crest cells are unique to vertebrates and generate many of the adult structures that differentiate them from their closest invertebrate relatives, the cephalochordates. Id genes are robust markers of neural crest cells at all stages of development. We compared Id gene expression in amphioxus and lamprey to ask if cephalochordates deploy Id genes at the neural plate border and dorsal neural tube in a manner similar to vertebrates. Furthermore, we examined whether Id expression in these cells is a basal vertebrate trait or a derived feature of gnathostomes. We found that while expression of Id genes in the mesoderm and endoderm is conserved between amphioxus and vertebrates, expression in the lateral neural plate border and dorsal neural tube is a vertebrate novelty. Furthermore, expression of lamprey Id implies that recruitment of Id genes to these cells occurred very early in the vertebrate lineage. Based on expression in amphioxus we postulate that Id cooption conferred sensory cell progenitor-like properties upon the lateral neurectoderm, and pharyngeal mesoderm-like properties upon cranial neural crest. Amphioxus Id expression is also consistent with homology between the anterior neurectoderm of amphioxus and the presumptive placodal ectoderm of vertebrates. These observations support the idea that neural crest evolution was driven in large part by cooption of multipurpose transcriptional regulators from other tissues and cell types.

Three-Class Mammogram Classification Based on Descriptive CNN Features

PubMed Central

Zhang, Qianni; Jadoon, Adeel

2017-01-01

In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW) and convolutional neural network-curvelet transform (CNN-CT). An augmented data set is generated by using mammogram patches. To enhance the contrast of mammogram images, the data set is filtered by contrast limited adaptive histogram equalization (CLAHE). In the CNN-DW method, enhanced mammogram images are decomposed as its four subbands by means of two-dimensional discrete wavelet transform (2D-DWT), while in the second method discrete curvelet transform (DCT) is used. In both methods, dense scale invariant feature (DSIFT) for all subbands is extracted. Input data matrix containing these subband features of all the mammogram patches is created that is processed as input to convolutional neural network (CNN). Softmax layer and support vector machine (SVM) layer are used to train CNN for classification. Proposed methods have been compared with existing methods in terms of accuracy rate, error rate, and various validation assessment measures. CNN-DW and CNN-CT have achieved accuracy rate of 81.83% and 83.74%, respectively. Simulation results clearly validate the significance and impact of our proposed model as compared to other well-known existing techniques. PMID:28191461

Three-Class Mammogram Classification Based on Descriptive CNN Features.

PubMed

Jadoon, M Mohsin; Zhang, Qianni; Haq, Ihsan Ul; Butt, Sharjeel; Jadoon, Adeel

2017-01-01

In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW) and convolutional neural network-curvelet transform (CNN-CT). An augmented data set is generated by using mammogram patches. To enhance the contrast of mammogram images, the data set is filtered by contrast limited adaptive histogram equalization (CLAHE). In the CNN-DW method, enhanced mammogram images are decomposed as its four subbands by means of two-dimensional discrete wavelet transform (2D-DWT), while in the second method discrete curvelet transform (DCT) is used. In both methods, dense scale invariant feature (DSIFT) for all subbands is extracted. Input data matrix containing these subband features of all the mammogram patches is created that is processed as input to convolutional neural network (CNN). Softmax layer and support vector machine (SVM) layer are used to train CNN for classification. Proposed methods have been compared with existing methods in terms of accuracy rate, error rate, and various validation assessment measures. CNN-DW and CNN-CT have achieved accuracy rate of 81.83% and 83.74%, respectively. Simulation results clearly validate the significance and impact of our proposed model as compared to other well-known existing techniques.

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

CLIPS: A tool for corn disease diagnostic system and an aid to neural network for automated knowledge acquisition

NASA Technical Reports Server (NTRS)

Wu, Cathy; Taylor, Pam; Whitson, George; Smith, Cathy

1990-01-01

This paper describes the building of a corn disease diagnostic expert system using CLIPS, and the development of a neural expert system using the fact representation method of CLIPS for automated knowledge acquisition. The CLIPS corn expert system diagnoses 21 diseases from 52 symptoms and signs with certainty factors. CLIPS has several unique features. It allows the facts in rules to be broken down to object-attribute-value (OAV) triples, allows rule-grouping, and fires rules based on pattern-matching. These features combined with the chained inference engine result to a natural user query system and speedy execution. In order to develop a method for automated knowledge acquisition, an Artificial Neural Expert System (ANES) is developed by a direct mapping from the CLIPS system. The ANES corn expert system uses the same OAV triples in the CLIPS system for its facts. The LHS and RHS facts of the CLIPS rules are mapped into the input and output layers of the ANES, respectively; and the inference engine of the rules is imbedded in the hidden layer. The fact representation by OAC triples gives a natural grouping of the rules. These features allow the ANES system to automate rule-generation, and make it efficient to execute and easy to expand for a large and complex domain.

Cognitive architecture of perceptual organization: from neurons to gnosons.

PubMed

van der Helm, Peter A

2012-02-01

What, if anything, is cognitive architecture and how is it implemented in neural architecture? Focusing on perceptual organization, this question is addressed by way of a pluralist approach which, supported by metatheoretical considerations, combines complementary insights from representational, connectionist, and dynamic systems approaches to cognition. This pluralist approach starts from a representationally inspired model which implements the intertwined but functionally distinguishable subprocesses of feedforward feature encoding, horizontal feature binding, and recurrent feature selection. As sustained by a review of neuroscientific evidence, these are the subprocesses that are believed to take place in the visual hierarchy in the brain. Furthermore, the model employs a special form of processing, called transparallel processing, whose neural signature is proposed to be gamma-band synchronization in transient horizontal neural assemblies. In neuroscience, such assemblies are believed to mediate binding of similar features. Their formal counterparts in the model are special input-dependent distributed representations, called hyperstrings, which allow many similar features to be processed in a transparallel fashion, that is, simultaneously as if only one feature were concerned. This form of processing does justice to both the high combinatorial capacity and the high speed of the perceptual organization process. A naturally following proposal is that those temporarily synchronized neural assemblies are "gnosons", that is, constituents of flexible self-organizing cognitive architecture in between the relatively rigid level of neurons and the still elusive level of consciousness.

Subauditory Speech Recognition based on EMG/EPG Signals

NASA Technical Reports Server (NTRS)

Jorgensen, Charles; Lee, Diana Dee; Agabon, Shane; Lau, Sonie (Technical Monitor)

2003-01-01

Sub-vocal electromyogram/electro palatogram (EMG/EPG) signal classification is demonstrated as a method for silent speech recognition. Recorded electrode signals from the larynx and sublingual areas below the jaw are noise filtered and transformed into features using complex dual quad tree wavelet transforms. Feature sets for six sub-vocally pronounced words are trained using a trust region scaled conjugate gradient neural network. Real time signals for previously unseen patterns are classified into categories suitable for primitive control of graphic objects. Feature construction, recognition accuracy and an approach for extension of the technique to a variety of real world application areas are presented.

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.

Objects Classification by Learning-Based Visual Saliency Model and Convolutional Neural Network.

PubMed

Li, Na; Zhao, Xinbo; Yang, Yongjia; Zou, Xiaochun

2016-01-01

Humans can easily classify different kinds of objects whereas it is quite difficult for computers. As a hot and difficult problem, objects classification has been receiving extensive interests with broad prospects. Inspired by neuroscience, deep learning concept is proposed. Convolutional neural network (CNN) as one of the methods of deep learning can be used to solve classification problem. But most of deep learning methods, including CNN, all ignore the human visual information processing mechanism when a person is classifying objects. Therefore, in this paper, inspiring the completed processing that humans classify different kinds of objects, we bring forth a new classification method which combines visual attention model and CNN. Firstly, we use the visual attention model to simulate the processing of human visual selection mechanism. Secondly, we use CNN to simulate the processing of how humans select features and extract the local features of those selected areas. Finally, not only does our classification method depend on those local features, but also it adds the human semantic features to classify objects. Our classification method has apparently advantages in biology. Experimental results demonstrated that our method made the efficiency of classification improve significantly.

New development of the image matching algorithm

NASA Astrophysics Data System (ADS)

Zhang, Xiaoqiang; Feng, Zhao

2018-04-01

To study the image matching algorithm, algorithm four elements are described, i.e., similarity measurement, feature space, search space and search strategy. Four common indexes for evaluating the image matching algorithm are described, i.e., matching accuracy, matching efficiency, robustness and universality. Meanwhile, this paper describes the principle of image matching algorithm based on the gray value, image matching algorithm based on the feature, image matching algorithm based on the frequency domain analysis, image matching algorithm based on the neural network and image matching algorithm based on the semantic recognition, and analyzes their characteristics and latest research achievements. Finally, the development trend of image matching algorithm is discussed. This study is significant for the algorithm improvement, new algorithm design and algorithm selection in practice.