Support vector machine-based prediction of local tumor control after stereotactic body radiation therapy for early-stage non-small cell lung cancer.

PubMed

Klement, Rainer J; Allgäuer, Michael; Appold, Steffen; Dieckmann, Karin; Ernst, Iris; Ganswindt, Ute; Holy, Richard; Nestle, Ursula; Nevinny-Stickel, Meinhard; Semrau, Sabine; Sterzing, Florian; Wittig, Andrea; Andratschke, Nicolaus; Guckenberger, Matthias

2014-03-01

Several prognostic factors for local tumor control probability (TCP) after stereotactic body radiation therapy (SBRT) for early stage non-small cell lung cancer (NSCLC) have been described, but no attempts have been undertaken to explore whether a nonlinear combination of potential factors might synergistically improve the prediction of local control. We investigated a support vector machine (SVM) for predicting TCP in a cohort of 399 patients treated at 13 German and Austrian institutions. Among 7 potential input features for the SVM we selected those most important on the basis of forward feature selection, thereby evaluating classifier performance by using 10-fold cross-validation and computing the area under the ROC curve (AUC). The final SVM classifier was built by repeating the feature selection 10 times with different splitting of the data for cross-validation and finally choosing only those features that were selected at least 5 out of 10 times. It was compared with a multivariate logistic model that was built by forward feature selection. Local failure occurred in 12% of patients. Biologically effective dose (BED) at the isocenter (BED(ISO)) was the strongest predictor of TCP in the logistic model and also the most frequently selected input feature for the SVM. A bivariate logistic function of BED(ISO) and the pulmonary function indicator forced expiratory volume in 1 second (FEV1) yielded the best description of the data but resulted in a significantly smaller AUC than the final SVM classifier with the input features BED(ISO), age, baseline Karnofsky index, and FEV1 (0.696 ± 0.040 vs 0.789 ± 0.001, P<.03). The final SVM resulted in sensitivity and specificity of 67.0% ± 0.5% and 78.7% ± 0.3%, respectively. These results confirm that machine learning techniques like SVMs can be successfully applied to predict treatment outcome after SBRT. Improvements over traditional TCP modeling are expected through a nonlinear combination of multiple features, eventually helping in the task of personalized treatment planning. Copyright © 2014 Elsevier Inc. All rights reserved.

Intelligent fault diagnosis of rolling bearings using an improved deep recurrent neural network

NASA Astrophysics Data System (ADS)

Jiang, Hongkai; Li, Xingqiu; Shao, Haidong; Zhao, Ke

2018-06-01

Traditional intelligent fault diagnosis methods for rolling bearings heavily depend on manual feature extraction and feature selection. For this purpose, an intelligent deep learning method, named the improved deep recurrent neural network (DRNN), is proposed in this paper. Firstly, frequency spectrum sequences are used as inputs to reduce the input size and ensure good robustness. Secondly, DRNN is constructed by the stacks of the recurrent hidden layer to automatically extract the features from the input spectrum sequences. Thirdly, an adaptive learning rate is adopted to improve the training performance of the constructed DRNN. The proposed method is verified with experimental rolling bearing data, and the results confirm that the proposed method is more effective than traditional intelligent fault diagnosis methods.

Kernel-based Joint Feature Selection and Max-Margin Classification for Early Diagnosis of Parkinson’s Disease

NASA Astrophysics Data System (ADS)

Adeli, Ehsan; Wu, Guorong; Saghafi, Behrouz; An, Le; Shi, Feng; Shen, Dinggang

2017-01-01

Feature selection methods usually select the most compact and relevant set of features based on their contribution to a linear regression model. Thus, these features might not be the best for a non-linear classifier. This is especially crucial for the tasks, in which the performance is heavily dependent on the feature selection techniques, like the diagnosis of neurodegenerative diseases. Parkinson’s disease (PD) is one of the most common neurodegenerative disorders, which progresses slowly while affects the quality of life dramatically. In this paper, we use the data acquired from multi-modal neuroimaging data to diagnose PD by investigating the brain regions, known to be affected at the early stages. We propose a joint kernel-based feature selection and classification framework. Unlike conventional feature selection techniques that select features based on their performance in the original input feature space, we select features that best benefit the classification scheme in the kernel space. We further propose kernel functions, specifically designed for our non-negative feature types. We use MRI and SPECT data of 538 subjects from the PPMI database, and obtain a diagnosis accuracy of 97.5%, which outperforms all baseline and state-of-the-art methods.

Kernel-based Joint Feature Selection and Max-Margin Classification for Early Diagnosis of Parkinson’s Disease

PubMed Central

Adeli, Ehsan; Wu, Guorong; Saghafi, Behrouz; An, Le; Shi, Feng; Shen, Dinggang

2017-01-01

Feature selection methods usually select the most compact and relevant set of features based on their contribution to a linear regression model. Thus, these features might not be the best for a non-linear classifier. This is especially crucial for the tasks, in which the performance is heavily dependent on the feature selection techniques, like the diagnosis of neurodegenerative diseases. Parkinson’s disease (PD) is one of the most common neurodegenerative disorders, which progresses slowly while affects the quality of life dramatically. In this paper, we use the data acquired from multi-modal neuroimaging data to diagnose PD by investigating the brain regions, known to be affected at the early stages. We propose a joint kernel-based feature selection and classification framework. Unlike conventional feature selection techniques that select features based on their performance in the original input feature space, we select features that best benefit the classification scheme in the kernel space. We further propose kernel functions, specifically designed for our non-negative feature types. We use MRI and SPECT data of 538 subjects from the PPMI database, and obtain a diagnosis accuracy of 97.5%, which outperforms all baseline and state-of-the-art methods. PMID:28120883

A new method of building footprints detection using airborne laser scanning data and multispectral image

NASA Astrophysics Data System (ADS)

Luo, Yiping; Jiang, Ting; Gao, Shengli; Wang, Xin

2010-10-01

It presents a new approach for detecting building footprints in a combination of registered aerial image with multispectral bands and airborne laser scanning data synchronously obtained by Leica-Geosystems ALS40 and Applanix DACS-301 on the same platform. A two-step method for building detection was presented consisting of selecting 'building' candidate points and then classifying candidate points. A digital surface model(DSM) derived from last pulse laser scanning data was first filtered and the laser points were classified into classes 'ground' and 'building or tree' based on mathematic morphological filter. Then, 'ground' points were resample into digital elevation model(DEM), and a Normalized DSM(nDSM) was generated from DEM and DSM. The candidate points were selected from 'building or tree' points by height value and area threshold in nDSM. The candidate points were further classified into building points and tree points by using the support vector machines(SVM) classification method. Two classification tests were carried out using features only from laser scanning data and associated features from two input data sources. The features included height, height finite difference, RGB bands value, and so on. The RGB value of points was acquired by matching laser scanning data and image using collinear equation. The features of training points were presented as input data for SVM classification method, and cross validation was used to select best classification parameters. The determinant function could be constructed by the classification parameters and the class of candidate points was determined by determinant function. The result showed that associated features from two input data sources were superior to features only from laser scanning data. The accuracy of more than 90% was achieved for buildings in first kind of features.

Vibration and acoustic frequency spectra for industrial process modeling using selective fusion multi-condition samples and multi-source features

NASA Astrophysics Data System (ADS)

Tang, Jian; Qiao, Junfei; Wu, ZhiWei; Chai, Tianyou; Zhang, Jian; Yu, Wen

2018-01-01

Frequency spectral data of mechanical vibration and acoustic signals relate to difficult-to-measure production quality and quantity parameters of complex industrial processes. A selective ensemble (SEN) algorithm can be used to build a soft sensor model of these process parameters by fusing valued information selectively from different perspectives. However, a combination of several optimized ensemble sub-models with SEN cannot guarantee the best prediction model. In this study, we use several techniques to construct mechanical vibration and acoustic frequency spectra of a data-driven industrial process parameter model based on selective fusion multi-condition samples and multi-source features. Multi-layer SEN (MLSEN) strategy is used to simulate the domain expert cognitive process. Genetic algorithm and kernel partial least squares are used to construct the inside-layer SEN sub-model based on each mechanical vibration and acoustic frequency spectral feature subset. Branch-and-bound and adaptive weighted fusion algorithms are integrated to select and combine outputs of the inside-layer SEN sub-models. Then, the outside-layer SEN is constructed. Thus, "sub-sampling training examples"-based and "manipulating input features"-based ensemble construction methods are integrated, thereby realizing the selective information fusion process based on multi-condition history samples and multi-source input features. This novel approach is applied to a laboratory-scale ball mill grinding process. A comparison with other methods indicates that the proposed MLSEN approach effectively models mechanical vibration and acoustic signals.

Network and neuronal membrane properties in hybrid networks reciprocally regulate selectivity to rapid thalamocortical inputs.

PubMed

Pesavento, Michael J; Pinto, David J

2012-11-01

Rapidly changing environments require rapid processing from sensory inputs. Varying deflection velocities of a rodent's primary facial vibrissa cause varying temporal neuronal activity profiles within the ventral posteromedial thalamic nucleus. Local neuron populations in a single somatosensory layer 4 barrel transform sparsely coded input into a spike count based on the input's temporal profile. We investigate this transformation by creating a barrel-like hybrid network with whole cell recordings of in vitro neurons from a cortical slice preparation, embedding the biological neuron in the simulated network by presenting virtual synaptic conductances via a conductance clamp. Utilizing the hybrid network, we examine the reciprocal network properties (local excitatory and inhibitory synaptic convergence) and neuronal membrane properties (input resistance) by altering the barrel population response to diverse thalamic input. In the presence of local network input, neurons are more selective to thalamic input timing; this arises from strong feedforward inhibition. Strongly inhibitory (damping) network regimes are more selective to timing and less selective to the magnitude of input but require stronger initial input. Input selectivity relies heavily on the different membrane properties of excitatory and inhibitory neurons. When inhibitory and excitatory neurons had identical membrane properties, the sensitivity of in vitro neurons to temporal vs. magnitude features of input was substantially reduced. Increasing the mean leak conductance of the inhibitory cells decreased the network's temporal sensitivity, whereas increasing excitatory leak conductance enhanced magnitude sensitivity. Local network synapses are essential in shaping thalamic input, and differing membrane properties of functional classes reciprocally modulate this effect.

Relevance popularity: A term event model based feature selection scheme for text classification.

PubMed

Feng, Guozhong; An, Baiguo; Yang, Fengqin; Wang, Han; Zhang, Libiao

2017-01-01

Feature selection is a practical approach for improving the performance of text classification methods by optimizing the feature subsets input to classifiers. In traditional feature selection methods such as information gain and chi-square, the number of documents that contain a particular term (i.e. the document frequency) is often used. However, the frequency of a given term appearing in each document has not been fully investigated, even though it is a promising feature to produce accurate classifications. In this paper, we propose a new feature selection scheme based on a term event Multinomial naive Bayes probabilistic model. According to the model assumptions, the matching score function, which is based on the prediction probability ratio, can be factorized. Finally, we derive a feature selection measurement for each term after replacing inner parameters by their estimators. On a benchmark English text datasets (20 Newsgroups) and a Chinese text dataset (MPH-20), our numerical experiment results obtained from using two widely used text classifiers (naive Bayes and support vector machine) demonstrate that our method outperformed the representative feature selection methods.

Software-hardware complex for the input of telemetric information obtained from rocket studies of the radiation of the earth's upper atmosphere

NASA Astrophysics Data System (ADS)

Bazdrov, I. I.; Bortkevich, V. S.; Khokhlov, V. N.

2004-10-01

This paper describes a software-hardware complex for the input into a personal computer of telemetric information obtained by means of telemetry stations TRAL KR28, RTS-8, and TRAL K2N. Structural and functional diagrams are given of the input device and the hardware complex. Results that characterize the features of the input process and selective data of optical measurements of atmospheric radiation are given. © 2004

Computational Intelligence Modeling of the Macromolecules Release from PLGA Microspheres-Focus on Feature Selection.

PubMed

Zawbaa, Hossam M; Szlȩk, Jakub; Grosan, Crina; Jachowicz, Renata; Mendyk, Aleksander

2016-01-01

Poly-lactide-co-glycolide (PLGA) is a copolymer of lactic and glycolic acid. Drug release from PLGA microspheres depends not only on polymer properties but also on drug type, particle size, morphology of microspheres, release conditions, etc. Selecting a subset of relevant properties for PLGA is a challenging machine learning task as there are over three hundred features to consider. In this work, we formulate the selection of critical attributes for PLGA as a multiobjective optimization problem with the aim of minimizing the error of predicting the dissolution profile while reducing the number of attributes selected. Four bio-inspired optimization algorithms: antlion optimization, binary version of antlion optimization, grey wolf optimization, and social spider optimization are used to select the optimal feature set for predicting the dissolution profile of PLGA. Besides these, LASSO algorithm is also used for comparisons. Selection of crucial variables is performed under the assumption that both predictability and model simplicity are of equal importance to the final result. During the feature selection process, a set of input variables is employed to find minimum generalization error across different predictive models and their settings/architectures. The methodology is evaluated using predictive modeling for which various tools are chosen, such as Cubist, random forests, artificial neural networks (monotonic MLP, deep learning MLP), multivariate adaptive regression splines, classification and regression tree, and hybrid systems of fuzzy logic and evolutionary computations (fugeR). The experimental results are compared with the results reported by Szlȩk. We obtain a normalized root mean square error (NRMSE) of 15.97% versus 15.4%, and the number of selected input features is smaller, nine versus eleven.

Computational Intelligence Modeling of the Macromolecules Release from PLGA Microspheres—Focus on Feature Selection

PubMed Central

Zawbaa, Hossam M.; Szlȩk, Jakub; Grosan, Crina; Jachowicz, Renata; Mendyk, Aleksander

2016-01-01

Poly-lactide-co-glycolide (PLGA) is a copolymer of lactic and glycolic acid. Drug release from PLGA microspheres depends not only on polymer properties but also on drug type, particle size, morphology of microspheres, release conditions, etc. Selecting a subset of relevant properties for PLGA is a challenging machine learning task as there are over three hundred features to consider. In this work, we formulate the selection of critical attributes for PLGA as a multiobjective optimization problem with the aim of minimizing the error of predicting the dissolution profile while reducing the number of attributes selected. Four bio-inspired optimization algorithms: antlion optimization, binary version of antlion optimization, grey wolf optimization, and social spider optimization are used to select the optimal feature set for predicting the dissolution profile of PLGA. Besides these, LASSO algorithm is also used for comparisons. Selection of crucial variables is performed under the assumption that both predictability and model simplicity are of equal importance to the final result. During the feature selection process, a set of input variables is employed to find minimum generalization error across different predictive models and their settings/architectures. The methodology is evaluated using predictive modeling for which various tools are chosen, such as Cubist, random forests, artificial neural networks (monotonic MLP, deep learning MLP), multivariate adaptive regression splines, classification and regression tree, and hybrid systems of fuzzy logic and evolutionary computations (fugeR). The experimental results are compared with the results reported by Szlȩk. We obtain a normalized root mean square error (NRMSE) of 15.97% versus 15.4%, and the number of selected input features is smaller, nine versus eleven. PMID:27315205

Feature selection for elderly faller classification based on wearable sensors.

PubMed

Howcroft, Jennifer; Kofman, Jonathan; Lemaire, Edward D

2017-05-30

Wearable sensors can be used to derive numerous gait pattern features for elderly fall risk and faller classification; however, an appropriate feature set is required to avoid high computational costs and the inclusion of irrelevant features. The objectives of this study were to identify and evaluate smaller feature sets for faller classification from large feature sets derived from wearable accelerometer and pressure-sensing insole gait data. A convenience sample of 100 older adults (75.5 ± 6.7 years; 76 non-fallers, 24 fallers based on 6 month retrospective fall occurrence) walked 7.62 m while wearing pressure-sensing insoles and tri-axial accelerometers at the head, pelvis, left and right shanks. Feature selection was performed using correlation-based feature selection (CFS), fast correlation based filter (FCBF), and Relief-F algorithms. Faller classification was performed using multi-layer perceptron neural network, naïve Bayesian, and support vector machine classifiers, with 75:25 single stratified holdout and repeated random sampling. The best performing model was a support vector machine with 78% accuracy, 26% sensitivity, 95% specificity, 0.36 F1 score, and 0.31 MCC and one posterior pelvis accelerometer input feature (left acceleration standard deviation). The second best model achieved better sensitivity (44%) and used a support vector machine with 74% accuracy, 83% specificity, 0.44 F1 score, and 0.29 MCC. This model had ten input features: maximum, mean and standard deviation posterior acceleration; maximum, mean and standard deviation anterior acceleration; mean superior acceleration; and three impulse features. The best multi-sensor model sensitivity (56%) was achieved using posterior pelvis and both shank accelerometers and a naïve Bayesian classifier. The best single-sensor model sensitivity (41%) was achieved using the posterior pelvis accelerometer and a naïve Bayesian classifier. Feature selection provided models with smaller feature sets and improved faller classification compared to faller classification without feature selection. CFS and FCBF provided the best feature subset (one posterior pelvis accelerometer feature) for faller classification. However, better sensitivity was achieved by the second best model based on a Relief-F feature subset with three pressure-sensing insole features and seven head accelerometer features. Feature selection should be considered as an important step in faller classification using wearable sensors.

Electrosensory Midbrain Neurons Display Feature Invariant Responses to Natural Communication Stimuli.

PubMed

Aumentado-Armstrong, Tristan; Metzen, Michael G; Sproule, Michael K J; Chacron, Maurice J

2015-10-01

Neurons that respond selectively but in an invariant manner to a given feature of natural stimuli have been observed across species and systems. Such responses emerge in higher brain areas, thereby suggesting that they occur by integrating afferent input. However, the mechanisms by which such integration occurs are poorly understood. Here we show that midbrain electrosensory neurons can respond selectively and in an invariant manner to heterogeneity in behaviorally relevant stimulus waveforms. Such invariant responses were not seen in hindbrain electrosensory neurons providing afferent input to these midbrain neurons, suggesting that response invariance results from nonlinear integration of such input. To test this hypothesis, we built a model based on the Hodgkin-Huxley formalism that received realistic afferent input. We found that multiple combinations of parameter values could give rise to invariant responses matching those seen experimentally. Our model thus shows that there are multiple solutions towards achieving invariant responses and reveals how subthreshold membrane conductances help promote robust and invariant firing in response to heterogeneous stimulus waveforms associated with behaviorally relevant stimuli. We discuss the implications of our findings for the electrosensory and other systems.

Feature Selection and Parameters Optimization of SVM Using Particle Swarm Optimization for Fault Classification in Power Distribution Systems.

PubMed

Cho, Ming-Yuan; Hoang, Thi Thom

2017-01-01

Fast and accurate fault classification is essential to power system operations. In this paper, in order to classify electrical faults in radial distribution systems, a particle swarm optimization (PSO) based support vector machine (SVM) classifier has been proposed. The proposed PSO based SVM classifier is able to select appropriate input features and optimize SVM parameters to increase classification accuracy. Further, a time-domain reflectometry (TDR) method with a pseudorandom binary sequence (PRBS) stimulus has been used to generate a dataset for purposes of classification. The proposed technique has been tested on a typical radial distribution network to identify ten different types of faults considering 12 given input features generated by using Simulink software and MATLAB Toolbox. The success rate of the SVM classifier is over 97%, which demonstrates the effectiveness and high efficiency of the developed method.

The Synaptic and Morphological Basis of Orientation Selectivity in a Polyaxonal Amacrine Cell of the Rabbit Retina.

PubMed

Murphy-Baum, Benjamin L; Taylor, W Rowland

2015-09-30

Much of the computational power of the retina derives from the activity of amacrine cells, a large and diverse group of GABAergic and glycinergic inhibitory interneurons. Here, we identify an ON-type orientation-selective, wide-field, polyaxonal amacrine cell (PAC) in the rabbit retina and demonstrate how its orientation selectivity arises from the structure of the dendritic arbor and the pattern of excitatory and inhibitory inputs. Excitation from ON bipolar cells and inhibition arising from the OFF pathway converge to generate a quasi-linear integration of visual signals in the receptive field center. This serves to suppress responses to high spatial frequencies, thereby improving sensitivity to larger objects and enhancing orientation selectivity. Inhibition also regulates the magnitude and time course of excitatory inputs to this PAC through serial inhibitory connections onto the presynaptic terminals of ON bipolar cells. This presynaptic inhibition is driven by graded potentials within local microcircuits, similar in extent to the size of single bipolar cell receptive fields. Additional presynaptic inhibition is generated by spiking amacrine cells on a larger spatial scale covering several hundred microns. The orientation selectivity of this PAC may be a substrate for the inhibition that mediates orientation selectivity in some types of ganglion cells. Significance statement: The retina comprises numerous excitatory and inhibitory circuits that encode specific features in the visual scene, such as orientation, contrast, or motion. Here, we identify a wide-field inhibitory neuron that responds to visual stimuli of a particular orientation, a feature selectivity that is primarily due to the elongated shape of the dendritic arbor. Integration of convergent excitatory and inhibitory inputs from the ON and OFF visual pathways suppress responses to small objects and fine textures, thus enhancing selectivity for larger objects. Feedback inhibition regulates the strength and speed of excitation on both local and wide-field spatial scales. This study demonstrates how different synaptic inputs are regulated to tune a neuron to respond to specific features in the visual scene. Copyright © 2015 the authors 0270-6474/15/3513336-15$15.00/0.

Choice: 36 band feature selection software with applications to multispectral pattern recognition

NASA Technical Reports Server (NTRS)

Jones, W. C.

1973-01-01

Feature selection software was developed at the Earth Resources Laboratory that is capable of inputting up to 36 channels and selecting channel subsets according to several criteria based on divergence. One of the criterion used is compatible with the table look-up classifier requirements. The software indicates which channel subset best separates (based on average divergence) each class from all other classes. The software employs an exhaustive search technique, and computer time is not prohibitive. A typical task to select the best 4 of 22 channels for 12 classes takes 9 minutes on a Univac 1108 computer.

An improved wrapper-based feature selection method for machinery fault diagnosis

PubMed Central

2017-01-01

A major issue of machinery fault diagnosis using vibration signals is that it is over-reliant on personnel knowledge and experience in interpreting the signal. Thus, machine learning has been adapted for machinery fault diagnosis. The quantity and quality of the input features, however, influence the fault classification performance. Feature selection plays a vital role in selecting the most representative feature subset for the machine learning algorithm. In contrast, the trade-off relationship between capability when selecting the best feature subset and computational effort is inevitable in the wrapper-based feature selection (WFS) method. This paper proposes an improved WFS technique before integration with a support vector machine (SVM) model classifier as a complete fault diagnosis system for a rolling element bearing case study. The bearing vibration dataset made available by the Case Western Reserve University Bearing Data Centre was executed using the proposed WFS and its performance has been analysed and discussed. The results reveal that the proposed WFS secures the best feature subset with a lower computational effort by eliminating the redundancy of re-evaluation. The proposed WFS has therefore been found to be capable and efficient to carry out feature selection tasks. PMID:29261689

Neuromorphic VLSI Models of Selective Attention: From Single Chip Vision Sensors to Multi-chip Systems

PubMed Central

Indiveri, Giacomo

2008-01-01

Biological organisms perform complex selective attention operations continuously and effortlessly. These operations allow them to quickly determine the motor actions to take in response to combinations of external stimuli and internal states, and to pay attention to subsets of sensory inputs suppressing non salient ones. Selective attention strategies are extremely effective in both natural and artificial systems which have to cope with large amounts of input data and have limited computational resources. One of the main computational primitives used to perform these selection operations is the Winner-Take-All (WTA) network. These types of networks are formed by arrays of coupled computational nodes that selectively amplify the strongest input signals, and suppress the weaker ones. Neuromorphic circuits are an optimal medium for constructing WTA networks and for implementing efficient hardware models of selective attention systems. In this paper we present an overview of selective attention systems based on neuromorphic WTA circuits ranging from single-chip vision sensors for selecting and tracking the position of salient features, to multi-chip systems implement saliency-map based models of selective attention. PMID:27873818

Neuromorphic VLSI Models of Selective Attention: From Single Chip Vision Sensors to Multi-chip Systems.

PubMed

Indiveri, Giacomo

2008-09-03

Biological organisms perform complex selective attention operations continuously and effortlessly. These operations allow them to quickly determine the motor actions to take in response to combinations of external stimuli and internal states, and to pay attention to subsets of sensory inputs suppressing non salient ones. Selective attention strategies are extremely effective in both natural and artificial systems which have to cope with large amounts of input data and have limited computational resources. One of the main computational primitives used to perform these selection operations is the Winner-Take-All (WTA) network. These types of networks are formed by arrays of coupled computational nodes that selectively amplify the strongest input signals, and suppress the weaker ones. Neuromorphic circuits are an optimal medium for constructing WTA networks and for implementing efficient hardware models of selective attention systems. In this paper we present an overview of selective attention systems based on neuromorphic WTA circuits ranging from single-chip vision sensors for selecting and tracking the position of salient features, to multi-chip systems implement saliency-map based models of selective attention.

[Severity classification of chronic obstructive pulmonary disease based on deep learning].

PubMed

Ying, Jun; Yang, Ceyuan; Li, Quanzheng; Xue, Wanguo; Li, Tanshi; Cao, Wenzhe

2017-12-01

In this paper, a deep learning method has been raised to build an automatic classification algorithm of severity of chronic obstructive pulmonary disease. Large sample clinical data as input feature were analyzed for their weights in classification. Through feature selection, model training, parameter optimization and model testing, a classification prediction model based on deep belief network was built to predict severity classification criteria raised by the Global Initiative for Chronic Obstructive Lung Disease (GOLD). We get accuracy over 90% in prediction for two different standardized versions of severity criteria raised in 2007 and 2011 respectively. Moreover, we also got the contribution ranking of different input features through analyzing the model coefficient matrix and confirmed that there was a certain degree of agreement between the more contributive input features and the clinical diagnostic knowledge. The validity of the deep belief network model was proved by this result. This study provides an effective solution for the application of deep learning method in automatic diagnostic decision making.

Classification of motor imagery tasks for BCI with multiresolution analysis and multiobjective feature selection.

PubMed

Ortega, Julio; Asensio-Cubero, Javier; Gan, John Q; Ortiz, Andrés

2016-07-15

Brain-computer interfacing (BCI) applications based on the classification of electroencephalographic (EEG) signals require solving high-dimensional pattern classification problems with such a relatively small number of training patterns that curse of dimensionality problems usually arise. Multiresolution analysis (MRA) has useful properties for signal analysis in both temporal and spectral analysis, and has been broadly used in the BCI field. However, MRA usually increases the dimensionality of the input data. Therefore, some approaches to feature selection or feature dimensionality reduction should be considered for improving the performance of the MRA based BCI. This paper investigates feature selection in the MRA-based frameworks for BCI. Several wrapper approaches to evolutionary multiobjective feature selection are proposed with different structures of classifiers. They are evaluated by comparing with baseline methods using sparse representation of features or without feature selection. The statistical analysis, by applying the Kolmogorov-Smirnoff and Kruskal-Wallis tests to the means of the Kappa values evaluated by using the test patterns in each approach, has demonstrated some advantages of the proposed approaches. In comparison with the baseline MRA approach used in previous studies, the proposed evolutionary multiobjective feature selection approaches provide similar or even better classification performances, with significant reduction in the number of features that need to be computed.

Optical-Correlator Neural Network Based On Neocognitron

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin; Stoner, William W.

1994-01-01

Multichannel optical correlator implements shift-invariant, high-discrimination pattern-recognizing neural network based on paradigm of neocognitron. Selected as basic building block of this neural network because invariance under shifts is inherent advantage of Fourier optics included in optical correlators in general. Neocognitron is conceptual electronic neural-network model for recognition of visual patterns. Multilayer processing achieved by iteratively feeding back output of feature correlator to input spatial light modulator and updating Fourier filters. Neural network trained by use of characteristic features extracted from target images. Multichannel implementation enables parallel processing of large number of selected features.

There's Waldo! A Normalization Model of Visual Search Predicts Single-Trial Human Fixations in an Object Search Task

PubMed Central

Miconi, Thomas; Groomes, Laura; Kreiman, Gabriel

2016-01-01

When searching for an object in a scene, how does the brain decide where to look next? Visual search theories suggest the existence of a global “priority map” that integrates bottom-up visual information with top-down, target-specific signals. We propose a mechanistic model of visual search that is consistent with recent neurophysiological evidence, can localize targets in cluttered images, and predicts single-trial behavior in a search task. This model posits that a high-level retinotopic area selective for shape features receives global, target-specific modulation and implements local normalization through divisive inhibition. The normalization step is critical to prevent highly salient bottom-up features from monopolizing attention. The resulting activity pattern constitues a priority map that tracks the correlation between local input and target features. The maximum of this priority map is selected as the locus of attention. The visual input is then spatially enhanced around the selected location, allowing object-selective visual areas to determine whether the target is present at this location. This model can localize objects both in array images and when objects are pasted in natural scenes. The model can also predict single-trial human fixations, including those in error and target-absent trials, in a search task involving complex objects. PMID:26092221

Self-supervised ARTMAP.

PubMed

Amis, Gregory P; Carpenter, Gail A

2010-03-01

Computational models of learning typically train on labeled input patterns (supervised learning), unlabeled input patterns (unsupervised learning), or a combination of the two (semi-supervised learning). In each case input patterns have a fixed number of features throughout training and testing. Human and machine learning contexts present additional opportunities for expanding incomplete knowledge from formal training, via self-directed learning that incorporates features not previously experienced. This article defines a new self-supervised learning paradigm to address these richer learning contexts, introducing a neural network called self-supervised ARTMAP. Self-supervised learning integrates knowledge from a teacher (labeled patterns with some features), knowledge from the environment (unlabeled patterns with more features), and knowledge from internal model activation (self-labeled patterns). Self-supervised ARTMAP learns about novel features from unlabeled patterns without destroying partial knowledge previously acquired from labeled patterns. A category selection function bases system predictions on known features, and distributed network activation scales unlabeled learning to prediction confidence. Slow distributed learning on unlabeled patterns focuses on novel features and confident predictions, defining classification boundaries that were ambiguous in the labeled patterns. Self-supervised ARTMAP improves test accuracy on illustrative low-dimensional problems and on high-dimensional benchmarks. Model code and benchmark data are available from: http://techlab.eu.edu/SSART/. Copyright 2009 Elsevier Ltd. All rights reserved.

Sequential sensory and decision processing in posterior parietal cortex

PubMed Central

Ibos, Guilhem; Freedman, David J

2017-01-01

Decisions about the behavioral significance of sensory stimuli often require comparing sensory inference of what we are looking at to internal models of what we are looking for. Here, we test how neuronal selectivity for visual features is transformed into decision-related signals in posterior parietal cortex (area LIP). Monkeys performed a visual matching task that required them to detect target stimuli composed of conjunctions of color and motion-direction. Neuronal recordings from area LIP revealed two main findings. First, the sequential processing of visual features and the selection of target-stimuli suggest that LIP is involved in transforming sensory information into decision-related signals. Second, the patterns of color and motion selectivity and their impact on decision-related encoding suggest that LIP plays a role in detecting target stimuli by comparing bottom-up sensory inputs (what the monkeys were looking at) and top-down cognitive encoding inputs (what the monkeys were looking for). DOI: http://dx.doi.org/10.7554/eLife.23743.001 PMID:28418332

Synaptic Mechanisms Generating Orientation Selectivity in the ON Pathway of the Rabbit Retina

PubMed Central

Venkataramani, Sowmya

2016-01-01

Neurons that signal the orientation of edges within the visual field have been widely studied in primary visual cortex. Much less is known about the mechanisms of orientation selectivity that arise earlier in the visual stream. Here we examine the synaptic and morphological properties of a subtype of orientation-selective ganglion cell in the rabbit retina. The receptive field has an excitatory ON center, flanked by excitatory OFF regions, a structure similar to simple cell receptive fields in primary visual cortex. Examination of the light-evoked postsynaptic currents in these ON-type orientation-selective ganglion cells (ON-OSGCs) reveals that synaptic input is mediated almost exclusively through the ON pathway. Orientation selectivity is generated by larger excitation for preferred relative to orthogonal stimuli, and conversely larger inhibition for orthogonal relative to preferred stimuli. Excitatory orientation selectivity arises in part from the morphology of the dendritic arbors. Blocking GABAA receptors reduces orientation selectivity of the inhibitory synaptic inputs and the spiking responses. Negative contrast stimuli in the flanking regions produce orientation-selective excitation in part by disinhibition of a tonic NMDA receptor-mediated input arising from ON bipolar cells. Comparison with earlier studies of OFF-type OSGCs indicates that diverse synaptic circuits have evolved in the retina to detect the orientation of edges in the visual input. SIGNIFICANCE STATEMENT A core goal for visual neuroscientists is to understand how neural circuits at each stage of the visual system extract and encode features from the visual scene. This study documents a novel type of orientation-selective ganglion cell in the retina and shows that the receptive field structure is remarkably similar to that of simple cells in primary visual cortex. However, the data indicate that, unlike in the cortex, orientation selectivity in the retina depends on the activity of inhibitory interneurons. The results further reveal the physiological basis for feature detection in the visual system, elucidate the synaptic mechanisms that generate orientation selectivity at an early stage of visual processing, and illustrate a novel role for NMDA receptors in retinal processing. PMID:26985041

Synaptic Mechanisms Generating Orientation Selectivity in the ON Pathway of the Rabbit Retina.

PubMed

Venkataramani, Sowmya; Taylor, W Rowland

2016-03-16

Neurons that signal the orientation of edges within the visual field have been widely studied in primary visual cortex. Much less is known about the mechanisms of orientation selectivity that arise earlier in the visual stream. Here we examine the synaptic and morphological properties of a subtype of orientation-selective ganglion cell in the rabbit retina. The receptive field has an excitatory ON center, flanked by excitatory OFF regions, a structure similar to simple cell receptive fields in primary visual cortex. Examination of the light-evoked postsynaptic currents in these ON-type orientation-selective ganglion cells (ON-OSGCs) reveals that synaptic input is mediated almost exclusively through the ON pathway. Orientation selectivity is generated by larger excitation for preferred relative to orthogonal stimuli, and conversely larger inhibition for orthogonal relative to preferred stimuli. Excitatory orientation selectivity arises in part from the morphology of the dendritic arbors. Blocking GABAA receptors reduces orientation selectivity of the inhibitory synaptic inputs and the spiking responses. Negative contrast stimuli in the flanking regions produce orientation-selective excitation in part by disinhibition of a tonic NMDA receptor-mediated input arising from ON bipolar cells. Comparison with earlier studies of OFF-type OSGCs indicates that diverse synaptic circuits have evolved in the retina to detect the orientation of edges in the visual input. A core goal for visual neuroscientists is to understand how neural circuits at each stage of the visual system extract and encode features from the visual scene. This study documents a novel type of orientation-selective ganglion cell in the retina and shows that the receptive field structure is remarkably similar to that of simple cells in primary visual cortex. However, the data indicate that, unlike in the cortex, orientation selectivity in the retina depends on the activity of inhibitory interneurons. The results further reveal the physiological basis for feature detection in the visual system, elucidate the synaptic mechanisms that generate orientation selectivity at an early stage of visual processing, and illustrate a novel role for NMDA receptors in retinal processing. Copyright © 2016 the authors 0270-6474/16/363336-14$15.00/0.

Temporal kinetics of prefrontal modulation of the extrastriate cortex during visual attention.

PubMed

Yago, Elena; Duarte, Audrey; Wong, Ting; Barceló, Francisco; Knight, Robert T

2004-12-01

Single-unit, event-related potential (ERP), and neuroimaging studies have implicated the prefrontal cortex (PFC) in top-down control of attention and working memory. We conducted an experiment in patients with unilateral PFC damage (n = 8) to assess the temporal kinetics of PFC-extrastriate interactions during visual attention. Subjects alternated attention between the left and the right hemifields in successive runs while they detected target stimuli embedded in streams of repetitive task-irrelevant stimuli (standards). The design enabled us to examine tonic (spatial selection) and phasic (feature selection) PFC-extrastriate interactions. PFC damage impaired performance in the visual field contralateral to lesions, as manifested by both larger reaction times and error rates. Assessment of the extrastriate P1 ERP revealed that the PFC exerts a tonic (spatial selection) excitatory input to the ipsilateral extrastriate cortex as early as 100 msec post stimulus delivery. The PFC exerts a second phasic (feature selection) excitatory extrastriate modulation from 180 to 300 msec, as evidenced by reductions in selection negativity after damage. Finally, reductions of the N2 ERP to target stimuli supports the notion that the PFC exerts a third phasic (target selection) signal necessary for successful template matching during postselection analysis of target features. The results provide electrophysiological evidence of three distinct tonic and phasic PFC inputs to the extrastriate cortex in the initial few hundred milliseconds of stimulus processing. Damage to this network appears to underlie the pervasive deficits in attention observed in patients with prefrontal lesions.

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

Informal Names for Features on Pluto Moon Charon

NASA Image and Video Library

2015-07-29

This image contains the initial, informal names being used by NASA's New Horizons team for the features on Pluto's largest moon, Charon. Names were selected based on the input the team received from the Our Pluto naming campaign. Names have not yet been approved by the International Astronomical Union (IAU). For more information on the maps and feature naming, visit http://www.ourpluto.org/maps. http://photojournal.jpl.nasa.gov/catalog/PIA19864

Informal Names for Features on Pluto Sputnik Planum

NASA Image and Video Library

2015-07-29

This image contains the initial, informal names being used by NASA's New Horizons team for the features on Pluto's Sputnik Planum (plain). Names were selected based on the input the team received from the Our Pluto naming campaign. Names have not yet been approved by the International Astronomical Union (IAU). For more information on the maps and feature naming, visit http://www.ourpluto.org/maps. http://photojournal.jpl.nasa.gov/catalog/PIA19865

Informal Names for Features on Pluto

NASA Image and Video Library

2015-07-29

This image contains the initial, informal names being used by NASA's New Horizons team for the features and regions on the surface of Pluto. Names were selected based on the input the team received from the Our Pluto naming campaign. Names have not yet been approved by the International Astronomical Union (IAU). For more information on the maps and feature naming, visit http://www.ourpluto.org/maps. http://photojournal.jpl.nasa.gov/catalog/PIA19863

On the Role of L1 Markedness and L2 Input Robustness in Determining Potentially Fossilizable Language Forms in Iranian EFL Learners' Writing

ERIC Educational Resources Information Center

Nushi, Musa

2016-01-01

Han's (2009, 2013) selective fossilization hypothesis (SFH) claims that L1 markedness and L2 input robustness determine the fossilizability (and learnability) of an L2 feature. To test the validity of the model, a pseudo-longitudinal study was designed in which the errors in the argumentative essays of 52 Iranian EFL learners were identified and…

A comparison of supervised classification methods for the prediction of substrate type using multibeam acoustic and legacy grain-size data.

PubMed

Stephens, David; Diesing, Markus

2014-01-01

Detailed seabed substrate maps are increasingly in demand for effective planning and management of marine ecosystems and resources. It has become common to use remotely sensed multibeam echosounder data in the form of bathymetry and acoustic backscatter in conjunction with ground-truth sampling data to inform the mapping of seabed substrates. Whilst, until recently, such data sets have typically been classified by expert interpretation, it is now obvious that more objective, faster and repeatable methods of seabed classification are required. This study compares the performances of a range of supervised classification techniques for predicting substrate type from multibeam echosounder data. The study area is located in the North Sea, off the north-east coast of England. A total of 258 ground-truth samples were classified into four substrate classes. Multibeam bathymetry and backscatter data, and a range of secondary features derived from these datasets were used in this study. Six supervised classification techniques were tested: Classification Trees, Support Vector Machines, k-Nearest Neighbour, Neural Networks, Random Forest and Naive Bayes. Each classifier was trained multiple times using different input features, including i) the two primary features of bathymetry and backscatter, ii) a subset of the features chosen by a feature selection process and iii) all of the input features. The predictive performances of the models were validated using a separate test set of ground-truth samples. The statistical significance of model performances relative to a simple baseline model (Nearest Neighbour predictions on bathymetry and backscatter) were tested to assess the benefits of using more sophisticated approaches. The best performing models were tree based methods and Naive Bayes which achieved accuracies of around 0.8 and kappa coefficients of up to 0.5 on the test set. The models that used all input features didn't generally perform well, highlighting the need for some means of feature selection.

Intelligent Fault Diagnosis of HVCB with Feature Space Optimization-Based Random Forest

PubMed Central

Ma, Suliang; Wu, Jianwen; Wang, Yuhao; Jia, Bowen; Jiang, Yuan

2018-01-01

Mechanical faults of high-voltage circuit breakers (HVCBs) always happen over long-term operation, so extracting the fault features and identifying the fault type have become a key issue for ensuring the security and reliability of power supply. Based on wavelet packet decomposition technology and random forest algorithm, an effective identification system was developed in this paper. First, compared with the incomplete description of Shannon entropy, the wavelet packet time-frequency energy rate (WTFER) was adopted as the input vector for the classifier model in the feature selection procedure. Then, a random forest classifier was used to diagnose the HVCB fault, assess the importance of the feature variable and optimize the feature space. Finally, the approach was verified based on actual HVCB vibration signals by considering six typical fault classes. The comparative experiment results show that the classification accuracy of the proposed method with the origin feature space reached 93.33% and reached up to 95.56% with optimized input feature vector of classifier. This indicates that feature optimization procedure is successful, and the proposed diagnosis algorithm has higher efficiency and robustness than traditional methods. PMID:29659548

Dimensionality Reduction Through Classifier Ensembles

NASA Technical Reports Server (NTRS)

Oza, Nikunj C.; Tumer, Kagan; Norwig, Peter (Technical Monitor)

1999-01-01

In data mining, one often needs to analyze datasets with a very large number of attributes. Performing machine learning directly on such data sets is often impractical because of extensive run times, excessive complexity of the fitted model (often leading to overfitting), and the well-known "curse of dimensionality." In practice, to avoid such problems, feature selection and/or extraction are often used to reduce data dimensionality prior to the learning step. However, existing feature selection/extraction algorithms either evaluate features by their effectiveness across the entire data set or simply disregard class information altogether (e.g., principal component analysis). Furthermore, feature extraction algorithms such as principal components analysis create new features that are often meaningless to human users. In this article, we present input decimation, a method that provides "feature subsets" that are selected for their ability to discriminate among the classes. These features are subsequently used in ensembles of classifiers, yielding results superior to single classifiers, ensembles that use the full set of features, and ensembles based on principal component analysis on both real and synthetic datasets.

Utilizing Hierarchical Clustering to improve Efficiency of Self-Organizing Feature Map to Identify Hydrological Homogeneous Regions

NASA Astrophysics Data System (ADS)

Farsadnia, Farhad; Ghahreman, Bijan

2016-04-01

Hydrologic homogeneous group identification is considered both fundamental and applied research in hydrology. Clustering methods are among conventional methods to assess the hydrological homogeneous regions. Recently, Self-Organizing feature Map (SOM) method has been applied in some studies. However, the main problem of this method is the interpretation on the output map of this approach. Therefore, SOM is used as input to other clustering algorithms. The aim of this study is to apply a two-level Self-Organizing feature map and Ward hierarchical clustering method to determine the hydrologic homogenous regions in North and Razavi Khorasan provinces. At first by principal component analysis, we reduced SOM input matrix dimension, then the SOM was used to form a two-dimensional features map. To determine homogeneous regions for flood frequency analysis, SOM output nodes were used as input into the Ward method. Generally, the regions identified by the clustering algorithms are not statistically homogeneous. Consequently, they have to be adjusted to improve their homogeneity. After adjustment of the homogeneity regions by L-moment tests, five hydrologic homogeneous regions were identified. Finally, adjusted regions were created by a two-level SOM and then the best regional distribution function and associated parameters were selected by the L-moment approach. The results showed that the combination of self-organizing maps and Ward hierarchical clustering by principal components as input is more effective than the hierarchical method, by principal components or standardized inputs to achieve hydrologic homogeneous regions.

Learning feature representations with a cost-relevant sparse autoencoder.

PubMed

Längkvist, Martin; Loutfi, Amy

2015-02-01

There is an increasing interest in the machine learning community to automatically learn feature representations directly from the (unlabeled) data instead of using hand-designed features. The autoencoder is one method that can be used for this purpose. However, for data sets with a high degree of noise, a large amount of the representational capacity in the autoencoder is used to minimize the reconstruction error for these noisy inputs. This paper proposes a method that improves the feature learning process by focusing on the task relevant information in the data. This selective attention is achieved by weighting the reconstruction error and reducing the influence of noisy inputs during the learning process. The proposed model is trained on a number of publicly available image data sets and the test error rate is compared to a standard sparse autoencoder and other methods, such as the denoising autoencoder and contractive autoencoder.

CBM First-level Event Selector Input Interface Demonstrator

NASA Astrophysics Data System (ADS)

Hutter, Dirk; de Cuveland, Jan; Lindenstruth, Volker

2017-10-01

CBM is a heavy-ion experiment at the future FAIR facility in Darmstadt, Germany. Featuring self-triggered front-end electronics and free-streaming read-out, event selection will exclusively be done by the First Level Event Selector (FLES). Designed as an HPC cluster with several hundred nodes its task is an online analysis and selection of the physics data at a total input data rate exceeding 1 TByte/s. To allow efficient event selection, the FLES performs timeslice building, which combines the data from all given input links to self-contained, potentially overlapping processing intervals and distributes them to compute nodes. Partitioning the input data streams into specialized containers allows performing this task very efficiently. The FLES Input Interface defines the linkage between the FEE and the FLES data transport framework. A custom FPGA PCIe board, the FLES Interface Board (FLIB), is used to receive data via optical links and transfer them via DMA to the host’s memory. The current prototype of the FLIB features a Kintex-7 FPGA and provides up to eight 10 GBit/s optical links. A custom FPGA design has been developed for this board. DMA transfers and data structures are optimized for subsequent timeslice building. Index tables generated by the FPGA enable fast random access to the written data containers. In addition the DMA target buffers can directly serve as InfiniBand RDMA source buffers without copying the data. The usage of POSIX shared memory for these buffers allows data access from multiple processes. An accompanying HDL module has been developed to integrate the FLES link into the front-end FPGA designs. It implements the front-end logic interface as well as the link protocol. Prototypes of all Input Interface components have been implemented and integrated into the FLES test framework. This allows the implementation and evaluation of the foreseen CBM read-out chain.

An improved method of early diagnosis of smoking-induced respiratory changes using machine learning algorithms.

PubMed

Amaral, Jorge L M; Lopes, Agnaldo J; Jansen, José M; Faria, Alvaro C D; Melo, Pedro L

2013-12-01

The purpose of this study was to develop an automatic classifier to increase the accuracy of the forced oscillation technique (FOT) for diagnosing early respiratory abnormalities in smoking patients. The data consisted of FOT parameters obtained from 56 volunteers, 28 healthy and 28 smokers with low tobacco consumption. Many supervised learning techniques were investigated, including logistic linear classifiers, k nearest neighbor (KNN), neural networks and support vector machines (SVM). To evaluate performance, the ROC curve of the most accurate parameter was established as baseline. To determine the best input features and classifier parameters, we used genetic algorithms and a 10-fold cross-validation using the average area under the ROC curve (AUC). In the first experiment, the original FOT parameters were used as input. We observed a significant improvement in accuracy (KNN=0.89 and SVM=0.87) compared with the baseline (0.77). The second experiment performed a feature selection on the original FOT parameters. This selection did not cause any significant improvement in accuracy, but it was useful in identifying more adequate FOT parameters. In the third experiment, we performed a feature selection on the cross products of the FOT parameters. This selection resulted in a further increase in AUC (KNN=SVM=0.91), which allows for high diagnostic accuracy. In conclusion, machine learning classifiers can help identify early smoking-induced respiratory alterations. The use of FOT cross products and the search for the best features and classifier parameters can markedly improve the performance of machine learning classifiers. Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.

Tensor Rank Preserving Discriminant Analysis for Facial Recognition.

PubMed

Tao, Dapeng; Guo, Yanan; Li, Yaotang; Gao, Xinbo

2017-10-12

Facial recognition, one of the basic topics in computer vision and pattern recognition, has received substantial attention in recent years. However, for those traditional facial recognition algorithms, the facial images are reshaped to a long vector, thereby losing part of the original spatial constraints of each pixel. In this paper, a new tensor-based feature extraction algorithm termed tensor rank preserving discriminant analysis (TRPDA) for facial image recognition is proposed; the proposed method involves two stages: in the first stage, the low-dimensional tensor subspace of the original input tensor samples was obtained; in the second stage, discriminative locality alignment was utilized to obtain the ultimate vector feature representation for subsequent facial recognition. On the one hand, the proposed TRPDA algorithm fully utilizes the natural structure of the input samples, and it applies an optimization criterion that can directly handle the tensor spectral analysis problem, thereby decreasing the computation cost compared those traditional tensor-based feature selection algorithms. On the other hand, the proposed TRPDA algorithm extracts feature by finding a tensor subspace that preserves most of the rank order information of the intra-class input samples. Experiments on the three facial databases are performed here to determine the effectiveness of the proposed TRPDA algorithm.

The impact of feature selection on one and two-class classification performance for plant microRNAs.

PubMed

Khalifa, Waleed; Yousef, Malik; Saçar Demirci, Müşerref Duygu; Allmer, Jens

2016-01-01

MicroRNAs (miRNAs) are short nucleotide sequences that form a typical hairpin structure which is recognized by a complex enzyme machinery. It ultimately leads to the incorporation of 18-24 nt long mature miRNAs into RISC where they act as recognition keys to aid in regulation of target mRNAs. It is involved to determine miRNAs experimentally and, therefore, machine learning is used to complement such endeavors. The success of machine learning mostly depends on proper input data and appropriate features for parameterization of the data. Although, in general, two-class classification (TCC) is used in the field; because negative examples are hard to come by, one-class classification (OCC) has been tried for pre-miRNA detection. Since both positive and negative examples are currently somewhat limited, feature selection can prove to be vital for furthering the field of pre-miRNA detection. In this study, we compare the performance of OCC and TCC using eight feature selection methods and seven different plant species providing positive pre-miRNA examples. Feature selection was very successful for OCC where the best feature selection method achieved an average accuracy of 95.6%, thereby being ∼29% better than the worst method which achieved 66.9% accuracy. While the performance is comparable to TCC, which performs up to 3% better than OCC, TCC is much less affected by feature selection and its largest performance gap is ∼13% which only occurs for two of the feature selection methodologies. We conclude that feature selection is crucially important for OCC and that it can perform on par with TCC given the proper set of features.

Dual frequency parametric excitation of a nonlinear, multi degree of freedom mechanical amplifier with electronically modified topology

NASA Astrophysics Data System (ADS)

Dolev, A.; Bucher, I.

2018-04-01

Mechanical or electromechanical amplifiers can exploit the high-Q and low noise features of mechanical resonance, in particular when parametric excitation is employed. Multi-frequency parametric excitation introduces tunability and is able to project weak input signals on a selected resonance. The present paper addresses multi degree of freedom mechanical amplifiers or resonators whose analysis and features require treatment of the spatial as well as temporal behavior. In some cases, virtual electronic coupling can alter the given topology of the resonator to better amplify specific inputs. An analytical development is followed by a numerical and experimental sensitivity and performance verifications, illustrating the advantages and disadvantages of such topologies.

Face recognition via Gabor and convolutional neural network

NASA Astrophysics Data System (ADS)

Lu, Tongwei; Wu, Menglu; Lu, Tao

2018-04-01

In recent years, the powerful feature learning and classification ability of convolutional neural network have attracted widely attention. Compared with the deep learning, the traditional machine learning algorithm has a good explanatory which deep learning does not have. Thus, In this paper, we propose a method to extract the feature of the traditional algorithm as the input of convolution neural network. In order to reduce the complexity of the network, the kernel function of Gabor wavelet is used to extract the feature from different position, frequency and direction of target image. It is sensitive to edge of image which can provide good direction and scale selection. The extraction of the image from eight directions on a scale are as the input of network that we proposed. The network have the advantage of weight sharing and local connection and texture feature of the input image can reduce the influence of facial expression, gesture and illumination. At the same time, we introduced a layer which combined the results of the pooling and convolution can extract deeper features. The training network used the open source caffe framework which is beneficial to feature extraction. The experiment results of the proposed method proved that the network structure effectively overcame the barrier of illumination and had a good robustness as well as more accurate and rapid than the traditional algorithm.

Automated corresponding point candidate selection for image registration using wavelet transformation neurla network with rotation invariant inputs and context information about neighboring candidates

NASA Astrophysics Data System (ADS)

Okumura, Hiroshi; Suezaki, Masashi; Sueyasu, Hideki; Arai, Kohei

2003-03-01

An automated method that can select corresponding point candidates is developed. This method has the following three features: 1) employment of the RIN-net for corresponding point candidate selection; 2) employment of multi resolution analysis with Haar wavelet transformation for improvement of selection accuracy and noise tolerance; 3) employment of context information about corresponding point candidates for screening of selected candidates. Here, the 'RIN-net' means the back-propagation trained feed-forward 3-layer artificial neural network that feeds rotation invariants as input data. In our system, pseudo Zernike moments are employed as the rotation invariants. The RIN-net has N x N pixels field of view (FOV). Some experiments are conducted to evaluate corresponding point candidate selection capability of the proposed method by using various kinds of remotely sensed images. The experimental results show the proposed method achieves fewer training patterns, less training time, and higher selection accuracy than conventional method.

Less is more: Avoiding the LIBS dimensionality curse through judicious feature selection for explosive detection.

PubMed

Kumar Myakalwar, Ashwin; Spegazzini, Nicolas; Zhang, Chi; Kumar Anubham, Siva; Dasari, Ramachandra R; Barman, Ishan; Kumar Gundawar, Manoj

2015-08-19

Despite its intrinsic advantages, translation of laser induced breakdown spectroscopy for material identification has been often impeded by the lack of robustness of developed classification models, often due to the presence of spurious correlations. While a number of classifiers exhibiting high discriminatory power have been reported, efforts in establishing the subset of relevant spectral features that enable a fundamental interpretation of the segmentation capability and avoid the 'curse of dimensionality' have been lacking. Using LIBS data acquired from a set of secondary explosives, we investigate judicious feature selection approaches and architect two different chemometrics classifiers -based on feature selection through prerequisite knowledge of the sample composition and genetic algorithm, respectively. While the full spectral input results in classification rate of ca.92%, selection of only carbon to hydrogen spectral window results in near identical performance. Importantly, the genetic algorithm-derived classifier shows a statistically significant improvement to ca. 94% accuracy for prospective classification, even though the number of features used is an order of magnitude smaller. Our findings demonstrate the impact of rigorous feature selection in LIBS and also hint at the feasibility of using a discrete filter based detector thereby enabling a cheaper and compact system more amenable to field operations.

Less is more: Avoiding the LIBS dimensionality curse through judicious feature selection for explosive detection

PubMed Central

Kumar Myakalwar, Ashwin; Spegazzini, Nicolas; Zhang, Chi; Kumar Anubham, Siva; Dasari, Ramachandra R.; Barman, Ishan; Kumar Gundawar, Manoj

2015-01-01

Despite its intrinsic advantages, translation of laser induced breakdown spectroscopy for material identification has been often impeded by the lack of robustness of developed classification models, often due to the presence of spurious correlations. While a number of classifiers exhibiting high discriminatory power have been reported, efforts in establishing the subset of relevant spectral features that enable a fundamental interpretation of the segmentation capability and avoid the ‘curse of dimensionality’ have been lacking. Using LIBS data acquired from a set of secondary explosives, we investigate judicious feature selection approaches and architect two different chemometrics classifiers –based on feature selection through prerequisite knowledge of the sample composition and genetic algorithm, respectively. While the full spectral input results in classification rate of ca.92%, selection of only carbon to hydrogen spectral window results in near identical performance. Importantly, the genetic algorithm-derived classifier shows a statistically significant improvement to ca. 94% accuracy for prospective classification, even though the number of features used is an order of magnitude smaller. Our findings demonstrate the impact of rigorous feature selection in LIBS and also hint at the feasibility of using a discrete filter based detector thereby enabling a cheaper and compact system more amenable to field operations. PMID:26286630

Automated Feature Identification and Classification Using Automated Feature Weighted Self Organizing Map (FWSOM)

NASA Astrophysics Data System (ADS)

Starkey, Andrew; Usman Ahmad, Aliyu; Hamdoun, Hassan

2017-10-01

This paper investigates the application of a novel method for classification called Feature Weighted Self Organizing Map (FWSOM) that analyses the topology information of a converged standard Self Organizing Map (SOM) to automatically guide the selection of important inputs during training for improved classification of data with redundant inputs, examined against two traditional approaches namely neural networks and Support Vector Machines (SVM) for the classification of EEG data as presented in previous work. In particular, the novel method looks to identify the features that are important for classification automatically, and in this way the important features can be used to improve the diagnostic ability of any of the above methods. The paper presents the results and shows how the automated identification of the important features successfully identified the important features in the dataset and how this results in an improvement of the classification results for all methods apart from linear discriminatory methods which cannot separate the underlying nonlinear relationship in the data. The FWSOM in addition to achieving higher classification accuracy has given insights into what features are important in the classification of each class (left and right-hand movements), and these are corroborated by already published work in this area.

A data mining framework for time series estimation.

PubMed

Hu, Xiao; Xu, Peng; Wu, Shaozhi; Asgari, Shadnaz; Bergsneider, Marvin

2010-04-01

Time series estimation techniques are usually employed in biomedical research to derive variables less accessible from a set of related and more accessible variables. These techniques are traditionally built from systems modeling approaches including simulation, blind decovolution, and state estimation. In this work, we define target time series (TTS) and its related time series (RTS) as the output and input of a time series estimation process, respectively. We then propose a novel data mining framework for time series estimation when TTS and RTS represent different sets of observed variables from the same dynamic system. This is made possible by mining a database of instances of TTS, its simultaneously recorded RTS, and the input/output dynamic models between them. The key mining strategy is to formulate a mapping function for each TTS-RTS pair in the database that translates a feature vector extracted from RTS to the dissimilarity between true TTS and its estimate from the dynamic model associated with the same TTS-RTS pair. At run time, a feature vector is extracted from an inquiry RTS and supplied to the mapping function associated with each TTS-RTS pair to calculate a dissimilarity measure. An optimal TTS-RTS pair is then selected by analyzing these dissimilarity measures. The associated input/output model of the selected TTS-RTS pair is then used to simulate the TTS given the inquiry RTS as an input. An exemplary implementation was built to address a biomedical problem of noninvasive intracranial pressure assessment. The performance of the proposed method was superior to that of a simple training-free approach of finding the optimal TTS-RTS pair by a conventional similarity-based search on RTS features. 2009 Elsevier Inc. All rights reserved.

A support vector machine approach for classification of welding defects from ultrasonic signals

NASA Astrophysics Data System (ADS)

Chen, Yuan; Ma, Hong-Wei; Zhang, Guang-Ming

2014-07-01

Defect classification is an important issue in ultrasonic non-destructive evaluation. A layered multi-class support vector machine (LMSVM) classification system, which combines multiple SVM classifiers through a layered architecture, is proposed in this paper. The proposed LMSVM classification system is applied to the classification of welding defects from ultrasonic test signals. The measured ultrasonic defect echo signals are first decomposed into wavelet coefficients by the wavelet packet transform. The energy of the wavelet coefficients at different frequency channels are used to construct the feature vectors. The bees algorithm (BA) is then used for feature selection and SVM parameter optimisation for the LMSVM classification system. The BA-based feature selection optimises the energy feature vectors. The optimised feature vectors are input to the LMSVM classification system for training and testing. Experimental results of classifying welding defects demonstrate that the proposed technique is highly robust, precise and reliable for ultrasonic defect classification.

GABAergic neurons in ferret visual cortex participate in functionally specific networks

PubMed Central

Wilson, Daniel E.; Smith, Gordon B.; Jacob, Amanda; Walker, Theo; Dimidschstein, Jordane; Fishell, Gord J.; Fitzpatrick, David

2017-01-01

Summary Functional circuits in the visual cortex require the coordinated activity of excitatory and inhibitory neurons. Molecular genetic approaches in the mouse have led to the ‘local nonspecific pooling principle’ of inhibitory connectivity, in which inhibitory neurons are untuned for stimulus features due to the random pooling of local inputs. However, it remains unclear whether this principle generalizes to species with a columnar organization of feature selectivity such as carnivores, primates, and humans. Here we use virally-mediated GABAergic-specific GCaMP6f expression to demonstrate that inhibitory neurons in ferret visual cortex respond robustly and selectively to oriented stimuli. We find that the tuning of inhibitory neurons is inconsistent with the local non-specific pooling of excitatory inputs, and that inhibitory neurons exhibit orientation-specific noise correlations with local and distant excitatory neurons. These findings challenge the generality of the non-specific pooling principle for inhibitory neurons, suggesting different rules for functional excitatory-inhibitory interactions in non-murine species. PMID:28279352

Master/Programmable-Slave Computer

NASA Technical Reports Server (NTRS)

Smaistrla, David; Hall, William A.

1990-01-01

Unique modular computer features compactness, low power, mass storage of data, multiprocessing, and choice of various input/output modes. Master processor communicates with user via usual keyboard and video display terminal. Coordinates operations of as many as 24 slave processors, each dedicated to different experiment. Each slave circuit card includes slave microprocessor and assortment of input/output circuits for communication with external equipment, with master processor, and with other slave processors. Adaptable to industrial process control with selectable degrees of automatic control, automatic and/or manual monitoring, and manual intervention.

Image segmentation via foreground and background semantic descriptors

NASA Astrophysics Data System (ADS)

Yuan, Ding; Qiang, Jingjing; Yin, Jihao

2017-09-01

In the field of image processing, it has been a challenging task to obtain a complete foreground that is not uniform in color or texture. Unlike other methods, which segment the image by only using low-level features, we present a segmentation framework, in which high-level visual features, such as semantic information, are used. First, the initial semantic labels were obtained by using the nonparametric method. Then, a subset of the training images, with a similar foreground to the input image, was selected. Consequently, the semantic labels could be further refined according to the subset. Finally, the input image was segmented by integrating the object affinity and refined semantic labels. State-of-the-art performance was achieved in experiments with the challenging MSRC 21 dataset.

Emergence of binocular functional properties in a monocular neural circuit

PubMed Central

Ramdya, Pavan; Engert, Florian

2010-01-01

Sensory circuits frequently integrate converging inputs while maintaining precise functional relationships between them. For example, in mammals with stereopsis, neurons at the first stages of binocular visual processing show a close alignment of receptive-field properties for each eye. Still, basic questions about the global wiring mechanisms that enable this functional alignment remain unanswered, including whether the addition of a second retinal input to an otherwise monocular neural circuit is sufficient for the emergence of these binocular properties. We addressed this question by inducing a de novo binocular retinal projection to the larval zebrafish optic tectum and examining recipient neuronal populations using in vivo two-photon calcium imaging. Notably, neurons in rewired tecta were predominantly binocular and showed matching direction selectivity for each eye. We found that a model based on local inhibitory circuitry that computes direction selectivity using the topographic structure of both retinal inputs can account for the emergence of this binocular feature. PMID:19160507

On-Line Pattern Analysis and Recognition System. OLPARS VI. Software Reference Manual,

DTIC Science & Technology

1982-06-18

Discriminant Analysis Data Transformation, Feature Extraction, Feature Evaluation Cluster Analysis, Classification Computer Software 20Z. ABSTRACT... cluster /scatter cut-off value, (2) change the one-space bin factor, (3) change from long prompts to short prompts or vice versa, (4) change the...value, a cluster plot is displayed, otherwise a scatter plot is shown. if option 1 is selected, the program requests that a new value be input

Applications of Microcomputers in the Education of the Physically Disabled Child.

ERIC Educational Resources Information Center

Foulds, Richard A.

1982-01-01

Microcomputers can serve as expressive communication tools for severely physically disabled persons. Features such as single input devices, direct selection aids, and speech synthesis capabilities can be extremely useful. The trend toward portable battery-operated computers will make the technology even more accessible. (CL)

Selective Laser Treatment on Cold-Sprayed Titanium Coatings: Numerical Modeling and Experimental Analysis

NASA Astrophysics Data System (ADS)

Carlone, Pierpaolo; Astarita, Antonello; Rubino, Felice; Pasquino, Nicola; Aprea, Paolo

2016-12-01

In this paper, a selective laser post-deposition on pure grade II titanium coatings, cold-sprayed on AA2024-T3 sheets, was experimentally and numerically investigated. Morphological features, microstructure, and chemical composition of the treated zone were assessed by means of optical microscopy, scanning electron microscopy, and energy dispersive X-ray spectrometry. Microhardness measurements were also carried out to evaluate the mechanical properties of the coating. A numerical model of the laser treatment was implemented and solved to simulate the process and discuss the experimental outcomes. Obtained results highlighted the key role played by heat input and dimensional features on the effectiveness of the treatment.

Freezing of Gait Detection in Parkinson's Disease: A Subject-Independent Detector Using Anomaly Scores.

PubMed

Pham, Thuy T; Moore, Steven T; Lewis, Simon John Geoffrey; Nguyen, Diep N; Dutkiewicz, Eryk; Fuglevand, Andrew J; McEwan, Alistair L; Leong, Philip H W

2017-11-01

Freezing of gait (FoG) is common in Parkinsonian gait and strongly relates to falls. Current clinical FoG assessments are patients' self-report diaries and experts' manual video analysis. Both are subjective and yield moderate reliability. Existing detection algorithms have been predominantly designed in subject-dependent settings. In this paper, we aim to develop an automated FoG detector for subject independent. After extracting highly relevant features, we apply anomaly detection techniques to detect FoG events. Specifically, feature selection is performed using correlation and clusterability metrics. From a list of 244 feature candidates, 36 candidates were selected using saliency and robustness criteria. We develop an anomaly score detector with adaptive thresholding to identify FoG events. Then, using accuracy metrics, we reduce the feature list to seven candidates. Our novel multichannel freezing index was the most selective across all window sizes, achieving sensitivity (specificity) of (). On the other hand, freezing index from the vertical axis was the best choice for a single input, achieving sensitivity (specificity) of () for ankle and () for back sensors. Our subject-independent method is not only significantly more accurate than those previously reported, but also uses a much smaller window (e.g., versus ) and/or lower tolerance (e.g., versus ).Freezing of gait (FoG) is common in Parkinsonian gait and strongly relates to falls. Current clinical FoG assessments are patients' self-report diaries and experts' manual video analysis. Both are subjective and yield moderate reliability. Existing detection algorithms have been predominantly designed in subject-dependent settings. In this paper, we aim to develop an automated FoG detector for subject independent. After extracting highly relevant features, we apply anomaly detection techniques to detect FoG events. Specifically, feature selection is performed using correlation and clusterability metrics. From a list of 244 feature candidates, 36 candidates were selected using saliency and robustness criteria. We develop an anomaly score detector with adaptive thresholding to identify FoG events. Then, using accuracy metrics, we reduce the feature list to seven candidates. Our novel multichannel freezing index was the most selective across all window sizes, achieving sensitivity (specificity) of (). On the other hand, freezing index from the vertical axis was the best choice for a single input, achieving sensitivity (specificity) of () for ankle and () for back sensors. Our subject-independent method is not only significantly more accurate than those previously reported, but also uses a much smaller window (e.g., versus ) and/or lower tolerance (e.g., versus ).

PredPPCrys: accurate prediction of sequence cloning, protein production, purification and crystallization propensity from protein sequences using multi-step heterogeneous feature fusion and selection.

PubMed

Wang, Huilin; Wang, Mingjun; Tan, Hao; Li, Yuan; Zhang, Ziding; Song, Jiangning

2014-01-01

X-ray crystallography is the primary approach to solve the three-dimensional structure of a protein. However, a major bottleneck of this method is the failure of multi-step experimental procedures to yield diffraction-quality crystals, including sequence cloning, protein material production, purification, crystallization and ultimately, structural determination. Accordingly, prediction of the propensity of a protein to successfully undergo these experimental procedures based on the protein sequence may help narrow down laborious experimental efforts and facilitate target selection. A number of bioinformatics methods based on protein sequence information have been developed for this purpose. However, our knowledge on the important determinants of propensity for a protein sequence to produce high diffraction-quality crystals remains largely incomplete. In practice, most of the existing methods display poorer performance when evaluated on larger and updated datasets. To address this problem, we constructed an up-to-date dataset as the benchmark, and subsequently developed a new approach termed 'PredPPCrys' using the support vector machine (SVM). Using a comprehensive set of multifaceted sequence-derived features in combination with a novel multi-step feature selection strategy, we identified and characterized the relative importance and contribution of each feature type to the prediction performance of five individual experimental steps required for successful crystallization. The resulting optimal candidate features were used as inputs to build the first-level SVM predictor (PredPPCrys I). Next, prediction outputs of PredPPCrys I were used as the input to build second-level SVM classifiers (PredPPCrys II), which led to significantly enhanced prediction performance. Benchmarking experiments indicated that our PredPPCrys method outperforms most existing procedures on both up-to-date and previous datasets. In addition, the predicted crystallization targets of currently non-crystallizable proteins were provided as compendium data, which are anticipated to facilitate target selection and design for the worldwide structural genomics consortium. PredPPCrys is freely available at http://www.structbioinfor.org/PredPPCrys.

Neural mechanisms of selective attention in the somatosensory system.

PubMed

Gomez-Ramirez, Manuel; Hysaj, Kristjana; Niebur, Ernst

2016-09-01

Selective attention allows organisms to extract behaviorally relevant information while ignoring distracting stimuli that compete for the limited resources of their central nervous systems. Attention is highly flexible, and it can be harnessed to select information based on sensory modality, within-modality feature(s), spatial location, object identity, and/or temporal properties. In this review, we discuss the body of work devoted to understanding mechanisms of selective attention in the somatosensory system. In particular, we describe the effects of attention on tactile behavior and corresponding neural activity in somatosensory cortex. Our focus is on neural mechanisms that select tactile stimuli based on their location on the body (somatotopic-based attention) or their sensory feature (feature-based attention). We highlight parallels between selection mechanisms in touch and other sensory systems and discuss several putative neural coding schemes employed by cortical populations to signal the behavioral relevance of sensory inputs. Specifically, we contrast the advantages and disadvantages of using a gain vs. spike-spike correlation code for representing attended sensory stimuli. We favor a neural network model of tactile attention that is composed of frontal, parietal, and subcortical areas that controls somatosensory cells encoding the relevant stimulus features to enable preferential processing throughout the somatosensory hierarchy. Our review is based on data from noninvasive electrophysiological and imaging data in humans as well as single-unit recordings in nonhuman primates. Copyright © 2016 the American Physiological Society.

Neural mechanisms of selective attention in the somatosensory system

PubMed Central

Hysaj, Kristjana; Niebur, Ernst

2016-01-01

Selective attention allows organisms to extract behaviorally relevant information while ignoring distracting stimuli that compete for the limited resources of their central nervous systems. Attention is highly flexible, and it can be harnessed to select information based on sensory modality, within-modality feature(s), spatial location, object identity, and/or temporal properties. In this review, we discuss the body of work devoted to understanding mechanisms of selective attention in the somatosensory system. In particular, we describe the effects of attention on tactile behavior and corresponding neural activity in somatosensory cortex. Our focus is on neural mechanisms that select tactile stimuli based on their location on the body (somatotopic-based attention) or their sensory feature (feature-based attention). We highlight parallels between selection mechanisms in touch and other sensory systems and discuss several putative neural coding schemes employed by cortical populations to signal the behavioral relevance of sensory inputs. Specifically, we contrast the advantages and disadvantages of using a gain vs. spike-spike correlation code for representing attended sensory stimuli. We favor a neural network model of tactile attention that is composed of frontal, parietal, and subcortical areas that controls somatosensory cells encoding the relevant stimulus features to enable preferential processing throughout the somatosensory hierarchy. Our review is based on data from noninvasive electrophysiological and imaging data in humans as well as single-unit recordings in nonhuman primates. PMID:27334956

78 FR 11609 - Special Conditions: Embraer S.A., Model EMB-550 Airplane; Landing Pitchover Condition

Federal Register 2010, 2011, 2012, 2013, 2014

2013-02-19

... automatic braking system. The applicable airworthiness regulations do not contain adequate or appropriate... with an automatic braking system. This feature is a pilot-selectable function that allows earlier braking at landing without pilot pedal input. When the autobrake system is armed before landing, it...

Target dependence of orientation and direction selectivity of corticocortical projection neurons in the mouse V1

PubMed Central

Matsui, Teppei; Ohki, Kenichi

2013-01-01

Higher order visual areas that receive input from the primary visual cortex (V1) are specialized for the processing of distinct features of visual information. However, it is still incompletely understood how this functional specialization is acquired. Here we used in vivo two photon calcium imaging in the mouse visual cortex to investigate whether this functional distinction exists at as early as the level of projections from V1 to two higher order visual areas, AL and LM. Specifically, we examined whether sharpness of orientation and direction selectivity and optimal spatial and temporal frequency of projection neurons from V1 to higher order visual areas match with that of target areas. We found that the V1 input to higher order visual areas were indeed functionally distinct: AL preferentially received inputs from V1 that were more orientation and direction selective and tuned for lower spatial frequency compared to projection of V1 to LM, consistent with functional differences between AL and LM. The present findings suggest that selective projections from V1 to higher order visual areas initiates parallel processing of sensory information in the visual cortical network. PMID:24068987

Fully automatic time-window selection using machine learning for global adjoint tomography

NASA Astrophysics Data System (ADS)

Chen, Y.; Hill, J.; Lei, W.; Lefebvre, M. P.; Bozdag, E.; Komatitsch, D.; Tromp, J.

2017-12-01

Selecting time windows from seismograms such that the synthetic measurements (from simulations) and measured observations are sufficiently close is indispensable in a global adjoint tomography framework. The increasing amount of seismic data collected everyday around the world demands "intelligent" algorithms for seismic window selection. While the traditional FLEXWIN algorithm can be "automatic" to some extent, it still requires both human input and human knowledge or experience, and thus is not deemed to be fully automatic. The goal of intelligent window selection is to automatically select windows based on a learnt engine that is built upon a huge number of existing windows generated through the adjoint tomography project. We have formulated the automatic window selection problem as a classification problem. All possible misfit calculation windows are classified as either usable or unusable. Given a large number of windows with a known selection mode (select or not select), we train a neural network to predict the selection mode of an arbitrary input window. Currently, the five features we extract from the windows are its cross-correlation value, cross-correlation time lag, amplitude ratio between observed and synthetic data, window length, and minimum STA/LTA value. More features can be included in the future. We use these features to characterize each window for training a multilayer perceptron neural network (MPNN). Training the MPNN is equivalent to solve a non-linear optimization problem. We use backward propagation to derive the gradient of the loss function with respect to the weighting matrices and bias vectors and use the mini-batch stochastic gradient method to iteratively optimize the MPNN. Numerical tests show that with a careful selection of the training data and a sufficient amount of training data, we are able to train a robust neural network that is capable of detecting the waveforms in an arbitrary earthquake data with negligible detection error compared to existing selection methods (e.g. FLEXWIN). We will introduce in detail the mathematical formulation of the window-selection-oriented MPNN and show very encouraging results when applying the new algorithm to real earthquake data.

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.

An adaptable neuromorphic model of orientation selectivity based on floating gate dynamics

PubMed Central

Gupta, Priti; Markan, C. M.

2014-01-01

The biggest challenge that the neuromorphic community faces today is to build systems that can be considered truly cognitive. Adaptation and self-organization are the two basic principles that underlie any cognitive function that the brain performs. If we can replicate this behavior in hardware, we move a step closer to our goal of having cognitive neuromorphic systems. Adaptive feature selectivity is a mechanism by which nature optimizes resources so as to have greater acuity for more abundant features. Developing neuromorphic feature maps can help design generic machines that can emulate this adaptive behavior. Most neuromorphic models that have attempted to build self-organizing systems, follow the approach of modeling abstract theoretical frameworks in hardware. While this is good from a modeling and analysis perspective, it may not lead to the most efficient hardware. On the other hand, exploiting hardware dynamics to build adaptive systems rather than forcing the hardware to behave like mathematical equations, seems to be a more robust methodology when it comes to developing actual hardware for real world applications. In this paper we use a novel time-staggered Winner Take All circuit, that exploits the adaptation dynamics of floating gate transistors, to model an adaptive cortical cell that demonstrates Orientation Selectivity, a well-known biological phenomenon observed in the visual cortex. The cell performs competitive learning, refining its weights in response to input patterns resembling different oriented bars, becoming selective to a particular oriented pattern. Different analysis performed on the cell such as orientation tuning, application of abnormal inputs, response to spatial frequency and periodic patterns reveal close similarity between our cell and its biological counterpart. Embedded in a RC grid, these cells interact diffusively exhibiting cluster formation, making way for adaptively building orientation selective maps in silicon. PMID:24765062

Pattern classification using an olfactory model with PCA feature selection in electronic noses: study and application.

PubMed

Fu, Jun; Huang, Canqin; Xing, Jianguo; Zheng, Junbao

2012-01-01

Biologically-inspired models and algorithms are considered as promising sensor array signal processing methods for electronic noses. Feature selection is one of the most important issues for developing robust pattern recognition models in machine learning. This paper describes an investigation into the classification performance of a bionic olfactory model with the increase of the dimensions of input feature vector (outer factor) as well as its parallel channels (inner factor). The principal component analysis technique was applied for feature selection and dimension reduction. Two data sets of three classes of wine derived from different cultivars and five classes of green tea derived from five different provinces of China were used for experiments. In the former case the results showed that the average correct classification rate increased as more principal components were put in to feature vector. In the latter case the results showed that sufficient parallel channels should be reserved in the model to avoid pattern space crowding. We concluded that 6~8 channels of the model with principal component feature vector values of at least 90% cumulative variance is adequate for a classification task of 3~5 pattern classes considering the trade-off between time consumption and classification rate.

Auditory evoked potentials in patients with major depressive disorder measured by Emotiv system.

PubMed

Wang, Dongcui; Mo, Fongming; Zhang, Yangde; Yang, Chao; Liu, Jun; Chen, Zhencheng; Zhao, Jinfeng

2015-01-01

In a previous study (unpublished), Emotiv headset was validated for capturing event-related potentials (ERPs) from normal subjects. In the present follow-up study, the signal quality of Emotiv headset was tested by the accuracy rate of discriminating Major Depressive Disorder (MDD) patients from the normal subjects. ERPs of 22 MDD patients and 15 normal subjects were induced by an auditory oddball task and the amplitude of N1, N2 and P3 of ERP components were specifically analyzed. The features of ERPs were statistically investigated. It is found that Emotiv headset is capable of discriminating the abnormal N1, N2 and P3 components in MDD patients. Relief-F algorithm was applied to all features for feature selection. The selected features were then input to a linear discriminant analysis (LDA) classifier with leave-one-out cross-validation to characterize the ERP features of MDD. 127 possible combinations out of the selected 7 ERP features were classified using LDA. The best classification accuracy was achieved to be 89.66%. These results suggest that MDD patients are identifiable from normal subjects by ERPs measured by Emotiv headset.

[Prosody, speech input and language acquisition].

PubMed

Jungheim, M; Miller, S; Kühn, D; Ptok, M

2014-04-01

In order to acquire language, children require speech input. The prosody of the speech input plays an important role. In most cultures adults modify their code when communicating with children. Compared to normal speech this code differs especially with regard to prosody. For this review a selective literature search in PubMed and Scopus was performed. Prosodic characteristics are a key feature of spoken language. By analysing prosodic features, children gain knowledge about underlying grammatical structures. Child-directed speech (CDS) is modified in a way that meaningful sequences are highlighted acoustically so that important information can be extracted from the continuous speech flow more easily. CDS is said to enhance the representation of linguistic signs. Taking into consideration what has previously been described in the literature regarding the perception of suprasegmentals, CDS seems to be able to support language acquisition due to the correspondence of prosodic and syntactic units. However, no findings have been reported, stating that the linguistically reduced CDS could hinder first language acquisition.

Computer program for plotting and fairing wind-tunnel data

NASA Technical Reports Server (NTRS)

Morgan, H. L., Jr.

1983-01-01

A detailed description of the Langley computer program PLOTWD which plots and fairs experimental wind-tunnel data is presented. The program was written for use primarily on the Langley CDC computer and CALCOMP plotters. The fundamental operating features of the program are that the input data are read and written to a random-access file for use during program execution, that the data for a selected run can be sorted and edited to delete duplicate points, and that the data can be plotted and faired using tension splines, least-squares polynomial, or least-squares cubic-spline curves. The most noteworthy feature of the program is the simplicity of the user-supplied input requirements. Several subroutines are also included that can be used to draw grid lines, zero lines, axis scale values and lables, and legends. A detailed description of the program operational features and each sub-program are presented. The general application of the program is also discussed together with the input and output for two typical plot types. A listing of the program code, user-guide, and output description are presented in appendices. The program has been in use at Langley for several years and has proven to be both easy to use and versatile.

Some characteristic features of the construction of the amplifying channel for working with semiconductor detectors in the charged particle energy spectrometer. [noise minimization at preamplifier input

NASA Technical Reports Server (NTRS)

Kuzyuta, E. I.

1974-01-01

A transistorized spectrometric amplifier with a shaper is reported that selects the shape of the frequency characteristic of the amplifying channel for which the primary frequency spectrum of the signal will pass, but where the noise spectrum is limited to the maximum. A procedure is presented for selecting the shaping circuits and their inclusion principles.

A Neural-Dynamic Architecture for Concurrent Estimation of Object Pose and Identity

PubMed Central

Lomp, Oliver; Faubel, Christian; Schöner, Gregor

2017-01-01

Handling objects or interacting with a human user about objects on a shared tabletop requires that objects be identified after learning from a small number of views and that object pose be estimated. We present a neurally inspired architecture that learns object instances by storing features extracted from a single view of each object. Input features are color and edge histograms from a localized area that is updated during processing. The system finds the best-matching view for the object in a novel input image while concurrently estimating the object’s pose, aligning the learned view with current input. The system is based on neural dynamics, computationally operating in real time, and can handle dynamic scenes directly off live video input. In a scenario with 30 everyday objects, the system achieves recognition rates of 87.2% from a single training view for each object, while also estimating pose quite precisely. We further demonstrate that the system can track moving objects, and that it can segment the visual array, selecting and recognizing one object while suppressing input from another known object in the immediate vicinity. Evaluation on the COIL-100 dataset, in which objects are depicted from different viewing angles, revealed recognition rates of 91.1% on the first 30 objects, each learned from four training views. PMID:28503145

Feature selection for examining behavior by pathology laboratories.

PubMed

Hawkins, S; Williams, G; Baxter, R

2001-08-01

Australia has a universal health insurance scheme called Medicare, which is managed by Australia's Health Insurance Commission. Medicare payments for pathology services generate voluminous transaction data on patients, doctors and pathology laboratories. The Health Insurance Commission (HIC) currently uses predictive models to monitor compliance with regulatory requirements. The HIC commissioned a project to investigate the generation of new features from the data. Feature generation has not appeared as an important step in the knowledge discovery in databases (KDD) literature. New interesting features for use in predictive modeling are generated. These features were summarized, visualized and used as inputs for clustering and outlier detection methods. Data organization and data transformation methods are described for the efficient access and manipulation of these new features.

A general procedure to generate models for urban environmental-noise pollution using feature selection and machine learning methods.

PubMed

Torija, Antonio J; Ruiz, Diego P

2015-02-01

The prediction of environmental noise in urban environments requires the solution of a complex and non-linear problem, since there are complex relationships among the multitude of variables involved in the characterization and modelling of environmental noise and environmental-noise magnitudes. Moreover, the inclusion of the great spatial heterogeneity characteristic of urban environments seems to be essential in order to achieve an accurate environmental-noise prediction in cities. This problem is addressed in this paper, where a procedure based on feature-selection techniques and machine-learning regression methods is proposed and applied to this environmental problem. Three machine-learning regression methods, which are considered very robust in solving non-linear problems, are used to estimate the energy-equivalent sound-pressure level descriptor (LAeq). These three methods are: (i) multilayer perceptron (MLP), (ii) sequential minimal optimisation (SMO), and (iii) Gaussian processes for regression (GPR). In addition, because of the high number of input variables involved in environmental-noise modelling and estimation in urban environments, which make LAeq prediction models quite complex and costly in terms of time and resources for application to real situations, three different techniques are used to approach feature selection or data reduction. The feature-selection techniques used are: (i) correlation-based feature-subset selection (CFS), (ii) wrapper for feature-subset selection (WFS), and the data reduction technique is principal-component analysis (PCA). The subsequent analysis leads to a proposal of different schemes, depending on the needs regarding data collection and accuracy. The use of WFS as the feature-selection technique with the implementation of SMO or GPR as regression algorithm provides the best LAeq estimation (R(2)=0.94 and mean absolute error (MAE)=1.14-1.16 dB(A)). Copyright © 2014 Elsevier B.V. All rights reserved.

Computational methods in the development of a knowledge-based system for the prediction of solid catalyst performance.

PubMed

Procelewska, Joanna; Galilea, Javier Llamas; Clerc, Frederic; Farrusseng, David; Schüth, Ferdi

2007-01-01

The objective of this work is the construction of a correlation between characteristics of heterogeneous catalysts, encoded in a descriptor vector, and their experimentally measured performances in the propene oxidation reaction. In this paper the key issue in the modeling process, namely the selection of adequate input variables, is explored. Several data-driven feature selection strategies were applied in order to obtain an estimate of the differences in variance and information content of various attributes, furthermore to compare their relative importance. Quantitative property activity relationship techniques using probabilistic neural networks have been used for the creation of various semi-empirical models. Finally, a robust classification model, assigning selected attributes of solid compounds as input to an appropriate performance class in the model reaction was obtained. It has been evident that the mathematical support for the primary attributes set proposed by chemists can be highly desirable.

Sensory noise predicts divisive reshaping of receptive fields

PubMed Central

Deneve, Sophie; Gutkin, Boris

2017-01-01

In order to respond reliably to specific features of their environment, sensory neurons need to integrate multiple incoming noisy signals. Crucially, they also need to compete for the interpretation of those signals with other neurons representing similar features. The form that this competition should take depends critically on the noise corrupting these signals. In this study we show that for the type of noise commonly observed in sensory systems, whose variance scales with the mean signal, sensory neurons should selectively divide their input signals by their predictions, suppressing ambiguous cues while amplifying others. Any change in the stimulus context alters which inputs are suppressed, leading to a deep dynamic reshaping of neural receptive fields going far beyond simple surround suppression. Paradoxically, these highly variable receptive fields go alongside and are in fact required for an invariant representation of external sensory features. In addition to offering a normative account of context-dependent changes in sensory responses, perceptual inference in the presence of signal-dependent noise accounts for ubiquitous features of sensory neurons such as divisive normalization, gain control and contrast dependent temporal dynamics. PMID:28622330

Sensory noise predicts divisive reshaping of receptive fields.

PubMed

Chalk, Matthew; Masset, Paul; Deneve, Sophie; Gutkin, Boris

2017-06-01

In order to respond reliably to specific features of their environment, sensory neurons need to integrate multiple incoming noisy signals. Crucially, they also need to compete for the interpretation of those signals with other neurons representing similar features. The form that this competition should take depends critically on the noise corrupting these signals. In this study we show that for the type of noise commonly observed in sensory systems, whose variance scales with the mean signal, sensory neurons should selectively divide their input signals by their predictions, suppressing ambiguous cues while amplifying others. Any change in the stimulus context alters which inputs are suppressed, leading to a deep dynamic reshaping of neural receptive fields going far beyond simple surround suppression. Paradoxically, these highly variable receptive fields go alongside and are in fact required for an invariant representation of external sensory features. In addition to offering a normative account of context-dependent changes in sensory responses, perceptual inference in the presence of signal-dependent noise accounts for ubiquitous features of sensory neurons such as divisive normalization, gain control and contrast dependent temporal dynamics.

A comprehensive analysis of earthquake damage patterns using high dimensional model representation feature selection

NASA Astrophysics Data System (ADS)

Taşkin Kaya, Gülşen

2013-10-01

Recently, earthquake damage assessment using satellite images has been a very popular ongoing research direction. Especially with the availability of very high resolution (VHR) satellite images, a quite detailed damage map based on building scale has been produced, and various studies have also been conducted in the literature. As the spatial resolution of satellite images increases, distinguishability of damage patterns becomes more cruel especially in case of using only the spectral information during classification. In order to overcome this difficulty, textural information needs to be involved to the classification to improve the visual quality and reliability of damage map. There are many kinds of textural information which can be derived from VHR satellite images depending on the algorithm used. However, extraction of textural information and evaluation of them have been generally a time consuming process especially for the large areas affected from the earthquake due to the size of VHR image. Therefore, in order to provide a quick damage map, the most useful features describing damage patterns needs to be known in advance as well as the redundant features. In this study, a very high resolution satellite image after Iran, Bam earthquake was used to identify the earthquake damage. Not only the spectral information, textural information was also used during the classification. For textural information, second order Haralick features were extracted from the panchromatic image for the area of interest using gray level co-occurrence matrix with different size of windows and directions. In addition to using spatial features in classification, the most useful features representing the damage characteristic were selected with a novel feature selection method based on high dimensional model representation (HDMR) giving sensitivity of each feature during classification. The method called HDMR was recently proposed as an efficient tool to capture the input-output relationships in high-dimensional systems for many problems in science and engineering. The HDMR method is developed to improve the efficiency of the deducing high dimensional behaviors. The method is formed by a particular organization of low dimensional component functions, in which each function is the contribution of one or more input variables to the output variables.

Attention-driven auditory cortex short-term plasticity helps segregate relevant sounds from noise.

PubMed

Ahveninen, Jyrki; Hämäläinen, Matti; Jääskeläinen, Iiro P; Ahlfors, Seppo P; Huang, Samantha; Lin, Fa-Hsuan; Raij, Tommi; Sams, Mikko; Vasios, Christos E; Belliveau, John W

2011-03-08

How can we concentrate on relevant sounds in noisy environments? A "gain model" suggests that auditory attention simply amplifies relevant and suppresses irrelevant afferent inputs. However, it is unclear whether this suffices when attended and ignored features overlap to stimulate the same neuronal receptive fields. A "tuning model" suggests that, in addition to gain, attention modulates feature selectivity of auditory neurons. We recorded magnetoencephalography, EEG, and functional MRI (fMRI) while subjects attended to tones delivered to one ear and ignored opposite-ear inputs. The attended ear was switched every 30 s to quantify how quickly the effects evolve. To produce overlapping inputs, the tones were presented alone vs. during white-noise masking notch-filtered ±1/6 octaves around the tone center frequencies. Amplitude modulation (39 vs. 41 Hz in opposite ears) was applied for "frequency tagging" of attention effects on maskers. Noise masking reduced early (50-150 ms; N1) auditory responses to unattended tones. In support of the tuning model, selective attention canceled out this attenuating effect but did not modulate the gain of 50-150 ms activity to nonmasked tones or steady-state responses to the maskers themselves. These tuning effects originated at nonprimary auditory cortices, purportedly occupied by neurons that, without attention, have wider frequency tuning than ±1/6 octaves. The attentional tuning evolved rapidly, during the first few seconds after attention switching, and correlated with behavioral discrimination performance. In conclusion, a simple gain model alone cannot explain auditory selective attention. In nonprimary auditory cortices, attention-driven short-term plasticity retunes neurons to segregate relevant sounds from noise.

Oral cancer prognosis based on clinicopathologic and genomic markers using a hybrid of feature selection and machine learning methods

PubMed Central

2013-01-01

Background Machine learning techniques are becoming useful as an alternative approach to conventional medical diagnosis or prognosis as they are good for handling noisy and incomplete data, and significant results can be attained despite a small sample size. Traditionally, clinicians make prognostic decisions based on clinicopathologic markers. However, it is not easy for the most skilful clinician to come out with an accurate prognosis by using these markers alone. Thus, there is a need to use genomic markers to improve the accuracy of prognosis. The main aim of this research is to apply a hybrid of feature selection and machine learning methods in oral cancer prognosis based on the parameters of the correlation of clinicopathologic and genomic markers. Results In the first stage of this research, five feature selection methods have been proposed and experimented on the oral cancer prognosis dataset. In the second stage, the model with the features selected from each feature selection methods are tested on the proposed classifiers. Four types of classifiers are chosen; these are namely, ANFIS, artificial neural network, support vector machine and logistic regression. A k-fold cross-validation is implemented on all types of classifiers due to the small sample size. The hybrid model of ReliefF-GA-ANFIS with 3-input features of drink, invasion and p63 achieved the best accuracy (accuracy = 93.81%; AUC = 0.90) for the oral cancer prognosis. Conclusions The results revealed that the prognosis is superior with the presence of both clinicopathologic and genomic markers. The selected features can be investigated further to validate the potential of becoming as significant prognostic signature in the oral cancer studies. PMID:23725313

An SVM-Based Classifier for Estimating the State of Various Rotating Components in Agro-Industrial Machinery with a Vibration Signal Acquired from a Single Point on the Machine Chassis

PubMed Central

Ruiz-Gonzalez, Ruben; Gomez-Gil, Jaime; Gomez-Gil, Francisco Javier; Martínez-Martínez, Víctor

2014-01-01

The goal of this article is to assess the feasibility of estimating the state of various rotating components in agro-industrial machinery by employing just one vibration signal acquired from a single point on the machine chassis. To do so, a Support Vector Machine (SVM)-based system is employed. Experimental tests evaluated this system by acquiring vibration data from a single point of an agricultural harvester, while varying several of its working conditions. The whole process included two major steps. Initially, the vibration data were preprocessed through twelve feature extraction algorithms, after which the Exhaustive Search method selected the most suitable features. Secondly, the SVM-based system accuracy was evaluated by using Leave-One-Out cross-validation, with the selected features as the input data. The results of this study provide evidence that (i) accurate estimation of the status of various rotating components in agro-industrial machinery is possible by processing the vibration signal acquired from a single point on the machine structure; (ii) the vibration signal can be acquired with a uniaxial accelerometer, the orientation of which does not significantly affect the classification accuracy; and, (iii) when using an SVM classifier, an 85% mean cross-validation accuracy can be reached, which only requires a maximum of seven features as its input, and no significant improvements are noted between the use of either nonlinear or linear kernels. PMID:25372618

An SVM-based classifier for estimating the state of various rotating components in agro-industrial machinery with a vibration signal acquired from a single point on the machine chassis.

PubMed

Ruiz-Gonzalez, Ruben; Gomez-Gil, Jaime; Gomez-Gil, Francisco Javier; Martínez-Martínez, Víctor

2014-11-03

The goal of this article is to assess the feasibility of estimating the state of various rotating components in agro-industrial machinery by employing just one vibration signal acquired from a single point on the machine chassis. To do so, a Support Vector Machine (SVM)-based system is employed. Experimental tests evaluated this system by acquiring vibration data from a single point of an agricultural harvester, while varying several of its working conditions. The whole process included two major steps. Initially, the vibration data were preprocessed through twelve feature extraction algorithms, after which the Exhaustive Search method selected the most suitable features. Secondly, the SVM-based system accuracy was evaluated by using Leave-One-Out cross-validation, with the selected features as the input data. The results of this study provide evidence that (i) accurate estimation of the status of various rotating components in agro-industrial machinery is possible by processing the vibration signal acquired from a single point on the machine structure; (ii) the vibration signal can be acquired with a uniaxial accelerometer, the orientation of which does not significantly affect the classification accuracy; and, (iii) when using an SVM classifier, an 85% mean cross-validation accuracy can be reached, which only requires a maximum of seven features as its input, and no significant improvements are noted between the use of either nonlinear or linear kernels.

Estimation of end point foot clearance points from inertial sensor data.

PubMed

Santhiranayagam, Braveena K; Lai, Daniel T H; Begg, Rezaul K; Palaniswami, Marimuthu

2011-01-01

Foot clearance parameters provide useful insight into tripping risks during walking. This paper proposes a technique for the estimate of key foot clearance parameters using inertial sensor (accelerometers and gyroscopes) data. Fifteen features were extracted from raw inertial sensor measurements, and a regression model was used to estimate two key foot clearance parameters: First maximum vertical clearance (m x 1) after toe-off and the Minimum Toe Clearance (MTC) of the swing foot. Comparisons are made against measurements obtained using an optoelectronic motion capture system (Optotrak), at 4 different walking speeds. General Regression Neural Networks (GRNN) were used to estimate the desired parameters from the sensor features. Eight subjects foot clearance data were examined and a Leave-one-subject-out (LOSO) method was used to select the best model. The best average Root Mean Square Errors (RMSE) across all subjects obtained using all sensor features at the maximum speed for m x 1 was 5.32 mm and for MTC was 4.04 mm. Further application of a hill-climbing feature selection technique resulted in 0.54-21.93% improvement in RMSE and required fewer input features. The results demonstrated that using raw inertial sensor data with regression models and feature selection could accurately estimate key foot clearance parameters.

Pattern Classification Using an Olfactory Model with PCA Feature Selection in Electronic Noses: Study and Application

PubMed Central

Fu, Jun; Huang, Canqin; Xing, Jianguo; Zheng, Junbao

2012-01-01

Biologically-inspired models and algorithms are considered as promising sensor array signal processing methods for electronic noses. Feature selection is one of the most important issues for developing robust pattern recognition models in machine learning. This paper describes an investigation into the classification performance of a bionic olfactory model with the increase of the dimensions of input feature vector (outer factor) as well as its parallel channels (inner factor). The principal component analysis technique was applied for feature selection and dimension reduction. Two data sets of three classes of wine derived from different cultivars and five classes of green tea derived from five different provinces of China were used for experiments. In the former case the results showed that the average correct classification rate increased as more principal components were put in to feature vector. In the latter case the results showed that sufficient parallel channels should be reserved in the model to avoid pattern space crowding. We concluded that 6∼8 channels of the model with principal component feature vector values of at least 90% cumulative variance is adequate for a classification task of 3∼5 pattern classes considering the trade-off between time consumption and classification rate. PMID:22736979

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.

Learning to attend: modeling the shaping of selectivity in infero-temporal cortex in a categorization task.

PubMed

Szabo, Miruna; Deco, Gustavo; Fusi, Stefano; Del Giudice, Paolo; Mattia, Maurizio; Stetter, Martin

2006-05-01

Recent experiments on behaving monkeys have shown that learning a visual categorization task makes the neurons in infero-temporal cortex (ITC) more selective to the task-relevant features of the stimuli (Sigala and Logothetis in Nature 415 318-320, 2002). We hypothesize that such a selectivity modulation emerges from the interaction between ITC and other cortical area, presumably the prefrontal cortex (PFC), where the previously learned stimulus categories are encoded. We propose a biologically inspired model of excitatory and inhibitory spiking neurons with plastic synapses, modified according to a reward based Hebbian learning rule, to explain the experimental results and test the validity of our hypothesis. We assume that the ITC neurons, receiving feature selective inputs, form stronger connections with the category specific neurons to which they are consistently associated in rewarded trials. After learning, the top-down influence of PFC neurons enhances the selectivity of the ITC neurons encoding the behaviorally relevant features of the stimuli, as observed in the experiments. We conclude that the perceptual representation in visual areas like ITC can be strongly affected by the interaction with other areas which are devoted to higher cognitive functions.

Construction of In-house Databases in a Corporation

NASA Astrophysics Data System (ADS)

Sano, Hikomaro

This report outlines “Repoir” (Report information retrieval) system of Toyota Central R & D Laboratories, Inc. as an example of in-house information retrieval system. The online system was designed to process in-house technical reports with the aid of a mainframe computer and has been in operation since 1979. Its features are multiple use of the information for technical and managerial purposes and simplicity in indexing and data input. The total number of descriptors, specially selected for the system, was minimized for ease of indexing. The report also describes the input items, processing flow and typical outputs in kanji letters.

Constant-Elasticity-of-Substitution Simulation

NASA Technical Reports Server (NTRS)

Reiter, G.

1986-01-01

Program simulates constant elasticity-of-substitution (CES) production function. CES function used by economic analysts to examine production costs as well as uncertainties in production. User provides such input parameters as price of labor, price of capital, and dispersion levels. CES minimizes expected cost to produce capital-uncertainty pair. By varying capital-value input, one obtains series of capital-uncertainty pairs. Capital-uncertainty pairs then used to generate several cost curves. CES program menu driven and features specific print menu for examining selected output curves. Program written in BASIC for interactive execution and implemented on IBM PC-series computer.

Achromatical Optical Correlator

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin; Liu, Hua-Kuang

1989-01-01

Signal-to-noise ratio exceeds that of monochromatic correlator. Achromatical optical correlator uses multiple-pinhole diffraction of dispersed white light to form superposed multiple correlations of input and reference images in output plane. Set of matched spatial filters made by multiple-exposure holographic process, each exposure using suitably-scaled input image and suitable angle of reference beam. Recording-aperture mask translated to appropriate horizontal position for each exposure. Noncoherent illumination suitable for applications involving recognition of color and determination of scale. When fully developed achromatical correlators will be useful for recognition of patterns; for example, in industrial inspection and search for selected features in aerial photographs.

New bandwidth selection criterion for Kernel PCA: approach to dimensionality reduction and classification problems.

PubMed

Thomas, Minta; De Brabanter, Kris; De Moor, Bart

2014-05-10

DNA microarrays are potentially powerful technology for improving diagnostic classification, treatment selection, and prognostic assessment. The use of this technology to predict cancer outcome has a history of almost a decade. Disease class predictors can be designed for known disease cases and provide diagnostic confirmation or clarify abnormal cases. The main input to this class predictors are high dimensional data with many variables and few observations. Dimensionality reduction of these features set significantly speeds up the prediction task. Feature selection and feature transformation methods are well known preprocessing steps in the field of bioinformatics. Several prediction tools are available based on these techniques. Studies show that a well tuned Kernel PCA (KPCA) is an efficient preprocessing step for dimensionality reduction, but the available bandwidth selection method for KPCA was computationally expensive. In this paper, we propose a new data-driven bandwidth selection criterion for KPCA, which is related to least squares cross-validation for kernel density estimation. We propose a new prediction model with a well tuned KPCA and Least Squares Support Vector Machine (LS-SVM). We estimate the accuracy of the newly proposed model based on 9 case studies. Then, we compare its performances (in terms of test set Area Under the ROC Curve (AUC) and computational time) with other well known techniques such as whole data set + LS-SVM, PCA + LS-SVM, t-test + LS-SVM, Prediction Analysis of Microarrays (PAM) and Least Absolute Shrinkage and Selection Operator (Lasso). Finally, we assess the performance of the proposed strategy with an existing KPCA parameter tuning algorithm by means of two additional case studies. We propose, evaluate, and compare several mathematical/statistical techniques, which apply feature transformation/selection for subsequent classification, and consider its application in medical diagnostics. Both feature selection and feature transformation perform well on classification tasks. Due to the dynamic selection property of feature selection, it is hard to define significant features for the classifier, which predicts classes of future samples. Moreover, the proposed strategy enjoys a distinctive advantage with its relatively lesser time complexity.

PredPPCrys: Accurate Prediction of Sequence Cloning, Protein Production, Purification and Crystallization Propensity from Protein Sequences Using Multi-Step Heterogeneous Feature Fusion and Selection

PubMed Central

Wang, Huilin; Wang, Mingjun; Tan, Hao; Li, Yuan; Zhang, Ziding; Song, Jiangning

2014-01-01

X-ray crystallography is the primary approach to solve the three-dimensional structure of a protein. However, a major bottleneck of this method is the failure of multi-step experimental procedures to yield diffraction-quality crystals, including sequence cloning, protein material production, purification, crystallization and ultimately, structural determination. Accordingly, prediction of the propensity of a protein to successfully undergo these experimental procedures based on the protein sequence may help narrow down laborious experimental efforts and facilitate target selection. A number of bioinformatics methods based on protein sequence information have been developed for this purpose. However, our knowledge on the important determinants of propensity for a protein sequence to produce high diffraction-quality crystals remains largely incomplete. In practice, most of the existing methods display poorer performance when evaluated on larger and updated datasets. To address this problem, we constructed an up-to-date dataset as the benchmark, and subsequently developed a new approach termed ‘PredPPCrys’ using the support vector machine (SVM). Using a comprehensive set of multifaceted sequence-derived features in combination with a novel multi-step feature selection strategy, we identified and characterized the relative importance and contribution of each feature type to the prediction performance of five individual experimental steps required for successful crystallization. The resulting optimal candidate features were used as inputs to build the first-level SVM predictor (PredPPCrys I). Next, prediction outputs of PredPPCrys I were used as the input to build second-level SVM classifiers (PredPPCrys II), which led to significantly enhanced prediction performance. Benchmarking experiments indicated that our PredPPCrys method outperforms most existing procedures on both up-to-date and previous datasets. In addition, the predicted crystallization targets of currently non-crystallizable proteins were provided as compendium data, which are anticipated to facilitate target selection and design for the worldwide structural genomics consortium. PredPPCrys is freely available at http://www.structbioinfor.org/PredPPCrys. PMID:25148528

Impaired visual search in rats reveals cholinergic contributions to feature binding in visuospatial attention.

PubMed

Botly, Leigh C P; De Rosa, Eve

2012-10-01

The visual search task established the feature integration theory of attention in humans and measures visuospatial attentional contributions to feature binding. We recently demonstrated that the neuromodulator acetylcholine (ACh), from the nucleus basalis magnocellularis (NBM), supports the attentional processes required for feature binding using a rat digging-based task. Additional research has demonstrated cholinergic contributions from the NBM to visuospatial attention in rats. Here, we combined these lines of evidence and employed visual search in rats to examine whether cortical cholinergic input supports visuospatial attention specifically for feature binding. We trained 18 male Long-Evans rats to perform visual search using touch screen-equipped operant chambers. Sessions comprised Feature Search (no feature binding required) and Conjunctive Search (feature binding required) trials using multiple stimulus set sizes. Following acquisition of visual search, 8 rats received bilateral NBM lesions using 192 IgG-saporin to selectively reduce cholinergic afferentation of the neocortex, which we hypothesized would selectively disrupt the visuospatial attentional processes needed for efficient conjunctive visual search. As expected, relative to sham-lesioned rats, ACh-NBM-lesioned rats took significantly longer to locate the target stimulus on Conjunctive Search, but not Feature Search trials, thus demonstrating that cholinergic contributions to visuospatial attention are important for feature binding in rats.

Thalamic input to auditory cortex is locally heterogeneous but globally tonotopic

PubMed Central

Vasquez-Lopez, Sebastian A; Weissenberger, Yves; Lohse, Michael; Keating, Peter; King, Andrew J

2017-01-01

Topographic representation of the receptor surface is a fundamental feature of sensory cortical organization. This is imparted by the thalamus, which relays information from the periphery to the cortex. To better understand the rules governing thalamocortical connectivity and the origin of cortical maps, we used in vivo two-photon calcium imaging to characterize the properties of thalamic axons innervating different layers of mouse auditory cortex. Although tonotopically organized at a global level, we found that the frequency selectivity of individual thalamocortical axons is surprisingly heterogeneous, even in layers 3b/4 of the primary cortical areas, where the thalamic input is dominated by the lemniscal projection. We also show that thalamocortical input to layer 1 includes collaterals from axons innervating layers 3b/4 and is largely in register with the main input targeting those layers. Such locally varied thalamocortical projections may be useful in enabling rapid contextual modulation of cortical frequency representations. PMID:28891466

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

Assessment of the relationship between rural non-point source pollution and economic development in the Three Gorges Reservoir Area.

PubMed

Zhang, Tong; Ni, Jiupai; Xie, Deti

2016-04-01

This study investigates the relationship between rural non-point source (NPS) pollution and economic development in the Three Gorges Reservoir Area (TGRA) by using the Environmental Kuznets Curve (EKC) hypothesis for the first time. Five types of pollution indicators, namely, fertilizer input density (FD), pesticide input density (PD), agricultural film input density (AD), grain residues impact (GI), and livestock manure impact (MI), were selected as rural NPS pollutant variables. Rural net income per capita was used as the indicator of economic development. Pollution load was generated by agricultural inputs (consumption of fertilizer, pesticide, and agricultural film) and economic growth with invert U-shaped features. The predicted turning points for FD, PD, and AD were at rural net income per capita levels of 6167.64, 6205.02, and 4955.29 CNY, respectively, which were all surpassed. However, the features between agricultural waste outputs (grain residues and livestock manure) and economic growth were inconsistent with the EKC hypothesis, which reflected the current trends of agricultural economic structure in the TGRA. Given that several other factors aside from economic development level could influence the pollutant generation in rural NPS, a further examination with long-run data support should be performed to understand the relationship between rural NPS pollution and income level.

Attention-driven auditory cortex short-term plasticity helps segregate relevant sounds from noise

PubMed Central

Ahveninen, Jyrki; Hämäläinen, Matti; Jääskeläinen, Iiro P.; Ahlfors, Seppo P.; Huang, Samantha; Raij, Tommi; Sams, Mikko; Vasios, Christos E.; Belliveau, John W.

2011-01-01

How can we concentrate on relevant sounds in noisy environments? A “gain model” suggests that auditory attention simply amplifies relevant and suppresses irrelevant afferent inputs. However, it is unclear whether this suffices when attended and ignored features overlap to stimulate the same neuronal receptive fields. A “tuning model” suggests that, in addition to gain, attention modulates feature selectivity of auditory neurons. We recorded magnetoencephalography, EEG, and functional MRI (fMRI) while subjects attended to tones delivered to one ear and ignored opposite-ear inputs. The attended ear was switched every 30 s to quantify how quickly the effects evolve. To produce overlapping inputs, the tones were presented alone vs. during white-noise masking notch-filtered ±1/6 octaves around the tone center frequencies. Amplitude modulation (39 vs. 41 Hz in opposite ears) was applied for “frequency tagging” of attention effects on maskers. Noise masking reduced early (50–150 ms; N1) auditory responses to unattended tones. In support of the tuning model, selective attention canceled out this attenuating effect but did not modulate the gain of 50–150 ms activity to nonmasked tones or steady-state responses to the maskers themselves. These tuning effects originated at nonprimary auditory cortices, purportedly occupied by neurons that, without attention, have wider frequency tuning than ±1/6 octaves. The attentional tuning evolved rapidly, during the first few seconds after attention switching, and correlated with behavioral discrimination performance. In conclusion, a simple gain model alone cannot explain auditory selective attention. In nonprimary auditory cortices, attention-driven short-term plasticity retunes neurons to segregate relevant sounds from noise. PMID:21368107

Feature Augmentation via Nonparametrics and Selection (FANS) in High-Dimensional Classification.

PubMed

Fan, Jianqing; Feng, Yang; Jiang, Jiancheng; Tong, Xin

We propose a high dimensional classification method that involves nonparametric feature augmentation. Knowing that marginal density ratios are the most powerful univariate classifiers, we use the ratio estimates to transform the original feature measurements. Subsequently, penalized logistic regression is invoked, taking as input the newly transformed or augmented features. This procedure trains models equipped with local complexity and global simplicity, thereby avoiding the curse of dimensionality while creating a flexible nonlinear decision boundary. The resulting method is called Feature Augmentation via Nonparametrics and Selection (FANS). We motivate FANS by generalizing the Naive Bayes model, writing the log ratio of joint densities as a linear combination of those of marginal densities. It is related to generalized additive models, but has better interpretability and computability. Risk bounds are developed for FANS. In numerical analysis, FANS is compared with competing methods, so as to provide a guideline on its best application domain. Real data analysis demonstrates that FANS performs very competitively on benchmark email spam and gene expression data sets. Moreover, FANS is implemented by an extremely fast algorithm through parallel computing.

Feature Augmentation via Nonparametrics and Selection (FANS) in High-Dimensional Classification

PubMed Central

Feng, Yang; Jiang, Jiancheng; Tong, Xin

2015-01-01

We propose a high dimensional classification method that involves nonparametric feature augmentation. Knowing that marginal density ratios are the most powerful univariate classifiers, we use the ratio estimates to transform the original feature measurements. Subsequently, penalized logistic regression is invoked, taking as input the newly transformed or augmented features. This procedure trains models equipped with local complexity and global simplicity, thereby avoiding the curse of dimensionality while creating a flexible nonlinear decision boundary. The resulting method is called Feature Augmentation via Nonparametrics and Selection (FANS). We motivate FANS by generalizing the Naive Bayes model, writing the log ratio of joint densities as a linear combination of those of marginal densities. It is related to generalized additive models, but has better interpretability and computability. Risk bounds are developed for FANS. In numerical analysis, FANS is compared with competing methods, so as to provide a guideline on its best application domain. Real data analysis demonstrates that FANS performs very competitively on benchmark email spam and gene expression data sets. Moreover, FANS is implemented by an extremely fast algorithm through parallel computing. PMID:27185970

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.

Model-based analysis of pattern motion processing in mouse primary visual cortex

PubMed Central

Muir, Dylan R.; Roth, Morgane M.; Helmchen, Fritjof; Kampa, Björn M.

2015-01-01

Neurons in sensory areas of neocortex exhibit responses tuned to specific features of the environment. In visual cortex, information about features such as edges or textures with particular orientations must be integrated to recognize a visual scene or object. Connectivity studies in rodent cortex have revealed that neurons make specific connections within sub-networks sharing common input tuning. In principle, this sub-network architecture enables local cortical circuits to integrate sensory information. However, whether feature integration indeed occurs locally in rodent primary sensory areas has not been examined directly. We studied local integration of sensory features in primary visual cortex (V1) of the mouse by presenting drifting grating and plaid stimuli, while recording the activity of neuronal populations with two-photon calcium imaging. Using a Bayesian model-based analysis framework, we classified single-cell responses as being selective for either individual grating components or for moving plaid patterns. Rather than relying on trial-averaged responses, our model-based framework takes into account single-trial responses and can easily be extended to consider any number of arbitrary predictive models. Our analysis method was able to successfully classify significantly more responses than traditional partial correlation (PC) analysis, and provides a rigorous statistical framework to rank any number of models and reject poorly performing models. We also found a large proportion of cells that respond strongly to only one stimulus class. In addition, a quarter of selectively responding neurons had more complex responses that could not be explained by any simple integration model. Our results show that a broad range of pattern integration processes already take place at the level of V1. This diversity of integration is consistent with processing of visual inputs by local sub-networks within V1 that are tuned to combinations of sensory features. PMID:26300738

Localized direction selective responses in the dendrites of visual interneurons of the fly

PubMed Central

2010-01-01

Background The various tasks of visual systems, including course control, collision avoidance and the detection of small objects, require at the neuronal level the dendritic integration and subsequent processing of many spatially distributed visual motion inputs. While much is known about the pooled output in these systems, as in the medial superior temporal cortex of monkeys or in the lobula plate of the insect visual system, the motion tuning of the elements that provide the input has yet received little attention. In order to visualize the motion tuning of these inputs we examined the dendritic activation patterns of neurons that are selective for the characteristic patterns of wide-field motion, the lobula-plate tangential cells (LPTCs) of the blowfly. These neurons are known to sample direction-selective motion information from large parts of the visual field and combine these signals into axonal and dendro-dendritic outputs. Results Fluorescence imaging of intracellular calcium concentration allowed us to take a direct look at the local dendritic activity and the resulting local preferred directions in LPTC dendrites during activation by wide-field motion in different directions. These 'calcium response fields' resembled a retinotopic dendritic map of local preferred directions in the receptive field, the layout of which is a distinguishing feature of different LPTCs. Conclusions Our study reveals how neurons acquire selectivity for distinct visual motion patterns by dendritic integration of the local inputs with different preferred directions. With their spatial layout of directional responses, the dendrites of the LPTCs we investigated thus served as matched filters for wide-field motion patterns. PMID:20384983

Combined data mining/NIR spectroscopy for purity assessment of lime juice

NASA Astrophysics Data System (ADS)

Shafiee, Sahameh; Minaei, Saeid

2018-06-01

This paper reports the data mining study on the NIR spectrum of lime juice samples to determine their purity (natural or synthetic). NIR spectra for 72 pure and synthetic lime juice samples were recorded in reflectance mode. Sample outliers were removed using PCA analysis. Different data mining techniques for feature selection (Genetic Algorithm (GA)) and classification (including the radial basis function (RBF) network, Support Vector Machine (SVM), and Random Forest (RF) tree) were employed. Based on the results, SVM proved to be the most accurate classifier as it achieved the highest accuracy (97%) using the raw spectrum information. The classifier accuracy dropped to 93% when selected feature vector by GA search method was applied as classifier input. It can be concluded that some relevant features which produce good performance with the SVM classifier are removed by feature selection. Also, reduced spectra using PCA do not show acceptable performance (total accuracy of 66% by RBFNN), which indicates that dimensional reduction methods such as PCA do not always lead to more accurate results. These findings demonstrate the potential of data mining combination with near-infrared spectroscopy for monitoring lime juice quality in terms of natural or synthetic nature.

Multivariable passive RFID vapor sensors: roll-to-roll fabrication on a flexible substrate.

PubMed

Potyrailo, Radislav A; Burns, Andrew; Surman, Cheryl; Lee, D J; McGinniss, Edward

2012-06-21

We demonstrate roll-to-roll (R2R) fabrication of highly selective, battery-free radio frequency identification (RFID) sensors on a flexible polyethylene terephthalate (PET) polymeric substrate. Selectivity of our developed RFID sensors is provided by measurements of their resonance impedance spectra, followed by the multivariate analysis of spectral features, and correlation of these spectral features to the concentrations of vapors of interest. The multivariate analysis of spectral features also provides the ability for the rejection of ambient interferences. As a demonstration of our R2R fabrication process, we employed polyetherurethane (PEUT) as a "classic" sensing material, extruded this sensing material as 25, 75, and 125-μm thick films, and thermally laminated the films onto RFID inlays, rapidly producing approximately 5000 vapor sensors. We further tested these RFID vapor sensors for their response selectivity toward several model vapors such as toluene, acetone, and ethanol as well as water vapor as an abundant interferent. Our RFID sensing concept features 16-bit resolution provided by the sensor reader, granting a highly desired independence from costly proprietary RFID memory chips with a low-resolution analog input. Future steps are being planned for field-testing of these sensors in numerous conditions.

An Automatic Prediction of Epileptic Seizures Using Cloud Computing and Wireless Sensor Networks.

PubMed

Sareen, Sanjay; Sood, Sandeep K; Gupta, Sunil Kumar

2016-11-01

Epilepsy is one of the most common neurological disorders which is characterized by the spontaneous and unforeseeable occurrence of seizures. An automatic prediction of seizure can protect the patients from accidents and save their life. In this article, we proposed a mobile-based framework that automatically predict seizures using the information contained in electroencephalography (EEG) signals. The wireless sensor technology is used to capture the EEG signals of patients. The cloud-based services are used to collect and analyze the EEG data from the patient's mobile phone. The features from the EEG signal are extracted using the fast Walsh-Hadamard transform (FWHT). The Higher Order Spectral Analysis (HOSA) is applied to FWHT coefficients in order to select the features set relevant to normal, preictal and ictal states of seizure. We subsequently exploit the selected features as input to a k-means classifier to detect epileptic seizure states in a reasonable time. The performance of the proposed model is tested on Amazon EC2 cloud and compared in terms of execution time and accuracy. The findings show that with selected HOS based features, we were able to achieve a classification accuracy of 94.6 %.

Evolutionary optimization of radial basis function classifiers for data mining applications.

PubMed

Buchtala, Oliver; Klimek, Manuel; Sick, Bernhard

2005-10-01

In many data mining applications that address classification problems, feature and model selection are considered as key tasks. That is, appropriate input features of the classifier must be selected from a given (and often large) set of possible features and structure parameters of the classifier must be adapted with respect to these features and a given data set. This paper describes an evolutionary algorithm (EA) that performs feature and model selection simultaneously for radial basis function (RBF) classifiers. In order to reduce the optimization effort, various techniques are integrated that accelerate and improve the EA significantly: hybrid training of RBF networks, lazy evaluation, consideration of soft constraints by means of penalty terms, and temperature-based adaptive control of the EA. The feasibility and the benefits of the approach are demonstrated by means of four data mining problems: intrusion detection in computer networks, biometric signature verification, customer acquisition with direct marketing methods, and optimization of chemical production processes. It is shown that, compared to earlier EA-based RBF optimization techniques, the runtime is reduced by up to 99% while error rates are lowered by up to 86%, depending on the application. The algorithm is independent of specific applications so that many ideas and solutions can be transferred to other classifier paradigms.

An evaluation of unsupervised and supervised learning algorithms for clustering landscape types in the United States

USGS Publications Warehouse

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

2016-01-01

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

Self-organizing map classifier for stressed speech recognition

NASA Astrophysics Data System (ADS)

Partila, Pavol; Tovarek, Jaromir; Voznak, Miroslav

2016-05-01

This paper presents a method for detecting speech under stress using Self-Organizing Maps. Most people who are exposed to stressful situations can not adequately respond to stimuli. Army, police, and fire department occupy the largest part of the environment that are typical of an increased number of stressful situations. The role of men in action is controlled by the control center. Control commands should be adapted to the psychological state of a man in action. It is known that the psychological changes of the human body are also reflected physiologically, which consequently means the stress effected speech. Therefore, it is clear that the speech stress recognizing system is required in the security forces. One of the possible classifiers, which are popular for its flexibility, is a self-organizing map. It is one type of the artificial neural networks. Flexibility means independence classifier on the character of the input data. This feature is suitable for speech processing. Human Stress can be seen as a kind of emotional state. Mel-frequency cepstral coefficients, LPC coefficients, and prosody features were selected for input data. These coefficients were selected for their sensitivity to emotional changes. The calculation of the parameters was performed on speech recordings, which can be divided into two classes, namely the stress state recordings and normal state recordings. The benefit of the experiment is a method using SOM classifier for stress speech detection. Results showed the advantage of this method, which is input data flexibility.

Fuzzy support vector machine for microarray imbalanced data classification

NASA Astrophysics Data System (ADS)

Ladayya, Faroh; Purnami, Santi Wulan; Irhamah

2017-11-01

DNA microarrays are data containing gene expression with small sample sizes and high number of features. Furthermore, imbalanced classes is a common problem in microarray data. This occurs when a dataset is dominated by a class which have significantly more instances than the other minority classes. Therefore, it is needed a classification method that solve the problem of high dimensional and imbalanced data. Support Vector Machine (SVM) is one of the classification methods that is capable of handling large or small samples, nonlinear, high dimensional, over learning and local minimum issues. SVM has been widely applied to DNA microarray data classification and it has been shown that SVM provides the best performance among other machine learning methods. However, imbalanced data will be a problem because SVM treats all samples in the same importance thus the results is bias for minority class. To overcome the imbalanced data, Fuzzy SVM (FSVM) is proposed. This method apply a fuzzy membership to each input point and reformulate the SVM such that different input points provide different contributions to the classifier. The minority classes have large fuzzy membership so FSVM can pay more attention to the samples with larger fuzzy membership. Given DNA microarray data is a high dimensional data with a very large number of features, it is necessary to do feature selection first using Fast Correlation based Filter (FCBF). In this study will be analyzed by SVM, FSVM and both methods by applying FCBF and get the classification performance of them. Based on the overall results, FSVM on selected features has the best classification performance compared to SVM.

Contextual modulation and stimulus selectivity in extrastriate cortex.

PubMed

Krause, Matthew R; Pack, Christopher C

2014-11-01

Contextual modulation is observed throughout the visual system, using techniques ranging from single-neuron recordings to behavioral experiments. Its role in generating feature selectivity within the retina and primary visual cortex has been extensively described in the literature. Here, we describe how similar computations can also elaborate feature selectivity in the extrastriate areas of both the dorsal and ventral streams of the primate visual system. We discuss recent work that makes use of normalization models to test specific roles for contextual modulation in visual cortex function. We suggest that contextual modulation renders neuronal populations more selective for naturalistic stimuli. Specifically, we discuss contextual modulation's role in processing optic flow in areas MT and MST and for representing naturally occurring curvature and contours in areas V4 and IT. We also describe how the circuitry that supports contextual modulation is robust to variations in overall input levels. Finally, we describe how this theory relates to other hypothesized roles for contextual modulation. Copyright © 2014 Elsevier Ltd. All rights reserved.

Detrended fluctuation analysis for major depressive disorder.

PubMed

Mumtaz, Wajid; Malik, Aamir Saeed; Ali, Syed Saad Azhar; Yasin, Mohd Azhar Mohd; Amin, Hafeezullah

2015-01-01

Clinical utility of Electroencephalography (EEG) based diagnostic studies is less clear for major depressive disorder (MDD). In this paper, a novel machine learning (ML) scheme was presented to discriminate the MDD patients and healthy controls. The proposed method inherently involved feature extraction, selection, classification and validation. The EEG data acquisition involved eyes closed (EC) and eyes open (EO) conditions. At feature extraction stage, the de-trended fluctuation analysis (DFA) was performed, based on the EEG data, to achieve scaling exponents. The DFA was performed to analyzes the presence or absence of long-range temporal correlations (LRTC) in the recorded EEG data. The scaling exponents were used as input features to our proposed system. At feature selection stage, 3 different techniques were used for comparison purposes. Logistic regression (LR) classifier was employed. The method was validated by a 10-fold cross-validation. As results, we have observed that the effect of 3 different reference montages on the computed features. The proposed method employed 3 different types of feature selection techniques for comparison purposes as well. The results show that the DFA analysis performed better in LE data compared with the IR and AR data. In addition, during Wilcoxon ranking, the AR performed better than LE and IR. Based on the results, it was concluded that the DFA provided useful information to discriminate the MDD patients and with further validation can be employed in clinics for diagnosis of MDD.

Modelling effects on grid cells of sensory input during self‐motion

PubMed Central

Raudies, Florian; Hinman, James R.

2016-01-01

Abstract The neural coding of spatial location for memory function may involve grid cells in the medial entorhinal cortex, but the mechanism of generating the spatial responses of grid cells remains unclear. This review describes some current theories and experimental data concerning the role of sensory input in generating the regular spatial firing patterns of grid cells, and changes in grid cell firing fields with movement of environmental barriers. As described here, the influence of visual features on spatial firing could involve either computations of self‐motion based on optic flow, or computations of absolute position based on the angle and distance of static visual cues. Due to anatomical selectivity of retinotopic processing, the sensory features on the walls of an environment may have a stronger effect on ventral grid cells that have wider spaced firing fields, whereas the sensory features on the ground plane may influence the firing of dorsal grid cells with narrower spacing between firing fields. These sensory influences could contribute to the potential functional role of grid cells in guiding goal‐directed navigation. PMID:27094096

Object-based attentional selection modulates anticipatory alpha oscillations

PubMed Central

Knakker, Balázs; Weiss, Béla; Vidnyánszky, Zoltán

2015-01-01

Visual cortical alpha oscillations are involved in attentional gating of incoming visual information. It has been shown that spatial and feature-based attentional selection result in increased alpha oscillations over the cortical regions representing sensory input originating from the unattended visual field and task-irrelevant visual features, respectively. However, whether attentional gating in the case of object based selection is also associated with alpha oscillations has not been investigated before. Here we measured anticipatory electroencephalography (EEG) alpha oscillations while participants were cued to attend to foveal face or word stimuli, the processing of which is known to have right and left hemispheric lateralization, respectively. The results revealed that in the case of simultaneously displayed, overlapping face and word stimuli, attending to the words led to increased power of parieto-occipital alpha oscillations over the right hemisphere as compared to when faces were attended. This object category-specific modulation of the hemispheric lateralization of anticipatory alpha oscillations was maintained during sustained attentional selection of sequentially presented face and word stimuli. These results imply that in the case of object-based attentional selection—similarly to spatial and feature-based attention—gating of visual information processing might involve visual cortical alpha oscillations. PMID:25628554

Assessment of geostatistical features for object-based image classification of contrasted landscape vegetation cover

NASA Astrophysics Data System (ADS)

de Oliveira Silveira, Eduarda Martiniano; de Menezes, Michele Duarte; Acerbi Júnior, Fausto Weimar; Castro Nunes Santos Terra, Marcela; de Mello, José Márcio

2017-07-01

Accurate mapping and monitoring of savanna and semiarid woodland biomes are needed to support the selection of areas of conservation, to provide sustainable land use, and to improve the understanding of vegetation. The potential of geostatistical features, derived from medium spatial resolution satellite imagery, to characterize contrasted landscape vegetation cover and improve object-based image classification is studied. The study site in Brazil includes cerrado sensu stricto, deciduous forest, and palm swamp vegetation cover. Sentinel 2 and Landsat 8 images were acquired and divided into objects, for each of which a semivariogram was calculated using near-infrared (NIR) and normalized difference vegetation index (NDVI) to extract the set of geostatistical features. The features selected by principal component analysis were used as input data to train a random forest algorithm. Tests were conducted, combining spectral and geostatistical features. Change detection evaluation was performed using a confusion matrix and its accuracies. The semivariogram curves were efficient to characterize spatial heterogeneity, with similar results using NIR and NDVI from Sentinel 2 and Landsat 8. Accuracy was significantly greater when combining geostatistical features with spectral data, suggesting that this method can improve image classification results.

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.

FuzzObserver

NASA Technical Reports Server (NTRS)

Howard, Ayanna; Bayard, David

2006-01-01

Fuzzy Feature Observation Planner for Small Body Proximity Observations (FuzzObserver) is a developmental computer program, to be used along with other software, for autonomous planning of maneuvers of a spacecraft near an asteroid, comet, or other small astronomical body. Selection of terrain features and estimation of the position of the spacecraft relative to these features is an essential part of such planning. FuzzObserver contributes to the selection and estimation by generating recommendations for spacecraft trajectory adjustments to maintain the spacecraft's ability to observe sufficient terrain features for estimating position. The input to FuzzObserver consists of data from terrain images, including sets of data on features acquired during descent toward, or traversal of, a body of interest. The name of this program reflects its use of fuzzy logic to reason about the terrain features represented by the data and extract corresponding trajectory-adjustment rules. Linguistic fuzzy sets and conditional statements enable fuzzy systems to make decisions based on heuristic rule-based knowledge derived by engineering experts. A major advantage of using fuzzy logic is that it involves simple arithmetic calculations that can be performed rapidly enough to be useful for planning within the short times typically available for spacecraft maneuvers.

A no-reference bitstream-based perceptual model for video quality estimation of videos affected by coding artifacts and packet losses

NASA Astrophysics Data System (ADS)

Pandremmenou, K.; Shahid, M.; Kondi, L. P.; Lövström, B.

2015-03-01

In this work, we propose a No-Reference (NR) bitstream-based model for predicting the quality of H.264/AVC video sequences, affected by both compression artifacts and transmission impairments. The proposed model is based on a feature extraction procedure, where a large number of features are calculated from the packet-loss impaired bitstream. Many of the features are firstly proposed in this work, and the specific set of the features as a whole is applied for the first time for making NR video quality predictions. All feature observations are taken as input to the Least Absolute Shrinkage and Selection Operator (LASSO) regression method. LASSO indicates the most important features, and using only them, it is possible to estimate the Mean Opinion Score (MOS) with high accuracy. Indicatively, we point out that only 13 features are able to produce a Pearson Correlation Coefficient of 0.92 with the MOS. Interestingly, the performance statistics we computed in order to assess our method for predicting the Structural Similarity Index and the Video Quality Metric are equally good. Thus, the obtained experimental results verified the suitability of the features selected by LASSO as well as the ability of LASSO in making accurate predictions through sparse modeling.

The Effects of Audiovisual Inputs on Solving the Cocktail Party Problem in the Human Brain: An fMRI Study.

PubMed

Li, Yuanqing; Wang, Fangyi; Chen, Yongbin; Cichocki, Andrzej; Sejnowski, Terrence

2017-09-25

At cocktail parties, our brains often simultaneously receive visual and auditory information. Although the cocktail party problem has been widely investigated under auditory-only settings, the effects of audiovisual inputs have not. This study explored the effects of audiovisual inputs in a simulated cocktail party. In our fMRI experiment, each congruent audiovisual stimulus was a synthesis of 2 facial movie clips, each of which could be classified into 1 of 2 emotion categories (crying and laughing). Visual-only (faces) and auditory-only stimuli (voices) were created by extracting the visual and auditory contents from the synthesized audiovisual stimuli. Subjects were instructed to selectively attend to 1 of the 2 objects contained in each stimulus and to judge its emotion category in the visual-only, auditory-only, and audiovisual conditions. The neural representations of the emotion features were assessed by calculating decoding accuracy and brain pattern-related reproducibility index based on the fMRI data. We compared the audiovisual condition with the visual-only and auditory-only conditions and found that audiovisual inputs enhanced the neural representations of emotion features of the attended objects instead of the unattended objects. This enhancement might partially explain the benefits of audiovisual inputs for the brain to solve the cocktail party problem. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

The Cutplane - A tool for interactive solid modeling

NASA Technical Reports Server (NTRS)

Edwards, Laurence; Kessler, William; Leifer, Larry

1988-01-01

A geometric modeling system which incorporates a new concept for intuitively and unambiguously specifying and manipulating points or features in three dimensional space is presented. The central concept, the Cutplane, consists of a plane that moves through space under control of a mouse or similar input device. The intersection of the plane and any object is highlighted, and only this highlighted section can be selected for manipulation. Selection is accomplished with a crosshair that is constrained to remain within the plane, so that the relationship between the crosshair and the feature of interest is immediately evident. Although the idea of a section view is not new, previously it has been used as a way to reveal hidden structure, not as a means of manipulating objects or indicating spatial position, as is proposed here.

Automated method for measuring the extent of selective logging damage with airborne LiDAR data

NASA Astrophysics Data System (ADS)

Melendy, L.; Hagen, S. C.; Sullivan, F. B.; Pearson, T. R. H.; Walker, S. M.; Ellis, P.; Kustiyo; Sambodo, Ari Katmoko; Roswintiarti, O.; Hanson, M. A.; Klassen, A. W.; Palace, M. W.; Braswell, B. H.; Delgado, G. M.

2018-05-01

Selective logging has an impact on the global carbon cycle, as well as on the forest micro-climate, and longer-term changes in erosion, soil and nutrient cycling, and fire susceptibility. Our ability to quantify these impacts is dependent on methods and tools that accurately identify the extent and features of logging activity. LiDAR-based measurements of these features offers significant promise. Here, we present a set of algorithms for automated detection and mapping of critical features associated with logging - roads/decks, skid trails, and gaps - using commercial airborne LiDAR data as input. The automated algorithm was applied to commercial LiDAR data collected over two logging concessions in Kalimantan, Indonesia in 2014. The algorithm results were compared to measurements of the logging features collected in the field soon after logging was complete. The automated algorithm-mapped road/deck and skid trail features match closely with features measured in the field, with agreement levels ranging from 69% to 99% when adjusting for GPS location error. The algorithm performed most poorly with gaps, which, by their nature, are variable due to the unpredictable impact of tree fall versus the linear and regular features directly created by mechanical means. Overall, the automated algorithm performs well and offers significant promise as a generalizable tool useful to efficiently and accurately capture the effects of selective logging, including the potential to distinguish reduced impact logging from conventional logging.

STAGS Example Problems Manual

NASA Technical Reports Server (NTRS)

Knight, Norman F., Jr.; Rankin, Charles C.

2006-01-01

This document summarizes the STructural Analysis of General Shells (STAGS) development effort, STAGS performance for selected demonstration problems, and STAGS application problems illustrating selected advanced features available in the STAGS Version 5.0. Each problem is discussed including selected background information and reference solutions when available. The modeling and solution approach for each problem is described and illustrated. Numerical results are presented and compared with reference solutions, test data, and/or results obtained from mesh refinement studies. These solutions provide an indication of the overall capabilities of the STAGS nonlinear finite element analysis tool and provide users with representative cases, including input files, to explore these capabilities that may then be tailored to other applications.

Comparing the role of shape and texture on staging hepatic fibrosis from medical imaging

NASA Astrophysics Data System (ADS)

Zhang, Xuejun; Louie, Ryan; Liu, Brent J.; Gao, Xin; Tan, Xiaomin; Qu, Xianghe; Long, Liling

2016-03-01

The purpose of this study is to investigate the role of shape and texture in the classification of hepatic fibrosis by selecting the optimal parameters for a better Computer-aided diagnosis (CAD) system. 10 surface shape features are extracted from a standardized profile of liver; while15 texture features calculated from gray level co-occurrence matrix (GLCM) are extracted within an ROI in liver. Each combination of these input subsets is checked by using support vector machine (SVM) with leave-one-case-out method to differentiate fibrosis into two groups: normal or abnormal. The accurate rate value of all 10/15 types number of features is 66.83% by texture, while 85.74% by shape features, respectively. The irregularity of liver shape can demonstrate fibrotic grade efficiently and texture feature of CT image is not recommended to use with shape feature for interpretation of cirrhosis.

Two multichannel integrated circuits for neural recording and signal processing.

PubMed

Obeid, Iyad; Morizio, James C; Moxon, Karen A; Nicolelis, Miguel A L; Wolf, Patrick D

2003-02-01

We have developed, manufactured, and tested two analog CMOS integrated circuit "neurochips" for recording from arrays of densely packed neural electrodes. Device A is a 16-channel buffer consisting of parallel noninverting amplifiers with a gain of 2 V/V. Device B is a 16-channel two-stage analog signal processor with differential amplification and high-pass filtering. It features selectable gains of 250 and 500 V/V as well as reference channel selection. The resulting amplifiers on Device A had a mean gain of 1.99 V/V with an equivalent input noise of 10 microV(rms). Those on Device B had mean gains of 53.4 and 47.4 dB with a high-pass filter pole at 211 Hz and an equivalent input noise of 4.4 microV(rms). Both devices were tested in vivo with electrode arrays implanted in the somatosensory cortex.

GrouseFlocks: steerable exploration of graph hierarchy space.

PubMed

Archambault, Daniel; Munzner, Tamara; Auber, David

2008-01-01

Several previous systems allow users to interactively explore a large input graph through cuts of a superimposed hierarchy. This hierarchy is often created using clustering algorithms or topological features present in the graph. However, many graphs have domain-specific attributes associated with the nodes and edges, which could be used to create many possible hierarchies providing unique views of the input graph. GrouseFlocks is a system for the exploration of this graph hierarchy space. By allowing users to see several different possible hierarchies on the same graph, the system helps users investigate graph hierarchy space instead of a single fixed hierarchy. GrouseFlocks provides a simple set of operations so that users can create and modify their graph hierarchies based on selections. These selections can be made manually or based on patterns in the attribute data provided with the graph. It provides feedback to the user within seconds, allowing interactive exploration of this space.

Assessing the effects of habitat patches ensuring propagule supply and different costs inclusion in marine spatial planning through multivariate analyses.

PubMed

Appolloni, L; Sandulli, R; Vetrano, G; Russo, G F

2018-05-15

Marine Protected Areas are considered key tools for conservation of coastal ecosystems. However, many reserves are characterized by several problems mainly related to inadequate zonings that often do not protect high biodiversity and propagule supply areas precluding, at the same time, economic important zones for local interests. The Gulf of Naples is here employed as a study area to assess the effects of inclusion of different conservation features and costs in reserve design process. In particular eight scenarios are developed using graph theory to identify propagule source patches and fishing and exploitation activities as costs-in-use for local population. Scenarios elaborated by MARXAN, software commonly used for marine conservation planning, are compared using multivariate analyses (MDS, PERMANOVA and PERMDISP) in order to assess input data having greatest effects on protected areas selection. MARXAN is heuristic software able to give a number of different correct results, all of them near to the best solution. Its outputs show that the most important areas to be protected, in order to ensure long-term habitat life and adequate propagule supply, are mainly located around the Gulf islands. In addition through statistical analyses it allowed us to prove that different choices on conservation features lead to statistically different scenarios. The presence of propagule supply patches forces MARXAN to select almost the same areas to protect decreasingly different MARXAN results and, thus, choices for reserves area selection. The multivariate analyses applied here to marine spatial planning proved to be very helpful allowing to identify i) how different scenario input data affect MARXAN and ii) what features have to be taken into account in study areas characterized by peculiar biological and economic interests. Copyright © 2018 Elsevier Ltd. All rights reserved.

Design, Simulation, and Preliminary Testing of a 20 Ampere Energy Management System

DTIC Science & Technology

2015-06-01

Vre f 0.5 V 0.58 V Vil 0.8 V 1.1 V Vih 1.9 V 2.25 V An important feature of this power module is the smart shutdown feature [15]. A simpli- fied...protection is removed when the pin voltage reaches the high-logic level Vih [15]. Values for Rshunt , RSD, and CSD had to be selected to implement this over...0.58 V Vil 0.8 V Vih 2.25 V Table 3.3. Truth table for H-bridge IGBTs, from [16]. Logic Input Output Shutdown Pin Lower IGBT Upper IGBT Lower IGBT

Noise Reduction in Brainwaves by Using Both EEG Signals and Frontal Viewing Camera Images

PubMed Central

Bang, Jae Won; Choi, Jong-Suk; Park, Kang Ryoung

2013-01-01

Electroencephalogram (EEG)-based brain-computer interfaces (BCIs) have been used in various applications, including human–computer interfaces, diagnosis of brain diseases, and measurement of cognitive status. However, EEG signals can be contaminated with noise caused by user's head movements. Therefore, we propose a new method that combines an EEG acquisition device and a frontal viewing camera to isolate and exclude the sections of EEG data containing these noises. This method is novel in the following three ways. First, we compare the accuracies of detecting head movements based on the features of EEG signals in the frequency and time domains and on the motion features of images captured by the frontal viewing camera. Second, the features of EEG signals in the frequency domain and the motion features captured by the frontal viewing camera are selected as optimal ones. The dimension reduction of the features and feature selection are performed using linear discriminant analysis. Third, the combined features are used as inputs to support vector machine (SVM), which improves the accuracy in detecting head movements. The experimental results show that the proposed method can detect head movements with an average error rate of approximately 3.22%, which is smaller than that of other methods. PMID:23669713

A Novel Feature Optimization for Wearable Human-Computer Interfaces Using Surface Electromyography Sensors

PubMed Central

Zhang, Xiong; Zhao, Yacong; Zhang, Yu; Zhong, Xuefei; Fan, Zhaowen

2018-01-01

The novel human-computer interface (HCI) using bioelectrical signals as input is a valuable tool to improve the lives of people with disabilities. In this paper, surface electromyography (sEMG) signals induced by four classes of wrist movements were acquired from four sites on the lower arm with our designed system. Forty-two features were extracted from the time, frequency and time-frequency domains. Optimal channels were determined from single-channel classification performance rank. The optimal-feature selection was according to a modified entropy criteria (EC) and Fisher discrimination (FD) criteria. The feature selection results were evaluated by four different classifiers, and compared with other conventional feature subsets. In online tests, the wearable system acquired real-time sEMG signals. The selected features and trained classifier model were used to control a telecar through four different paradigms in a designed environment with simple obstacles. Performance was evaluated based on travel time (TT) and recognition rate (RR). The results of hardware evaluation verified the feasibility of our acquisition systems, and ensured signal quality. Single-channel analysis results indicated that the channel located on the extensor carpi ulnaris (ECU) performed best with mean classification accuracy of 97.45% for all movement’s pairs. Channels placed on ECU and the extensor carpi radialis (ECR) were selected according to the accuracy rank. Experimental results showed that the proposed FD method was better than other feature selection methods and single-type features. The combination of FD and random forest (RF) performed best in offline analysis, with 96.77% multi-class RR. Online results illustrated that the state-machine paradigm with a 125 ms window had the highest maneuverability and was closest to real-life control. Subjects could accomplish online sessions by three sEMG-based paradigms, with average times of 46.02, 49.06 and 48.08 s, respectively. These experiments validate the feasibility of proposed real-time wearable HCI system and algorithms, providing a potential assistive device interface for persons with disabilities. PMID:29543737

Selective Erasure of Distinct Forms of Long-Term Synaptic Plasticity Underlying Different Forms of Memory in the Same Postsynaptic Neuron.

PubMed

Hu, Jiangyuan; Ferguson, Larissa; Adler, Kerry; Farah, Carole A; Hastings, Margaret H; Sossin, Wayne S; Schacher, Samuel

2017-07-10

Generalization of fear responses to non-threatening stimuli is a feature of anxiety disorders. It has been challenging to target maladaptive generalized memories without affecting adaptive memories. Synapse-specific long-term plasticity underlying memory involves the targeting of plasticity-related proteins (PRPs) to activated synapses. If distinct tags and PRPs are used for different forms of plasticity, one could selectively remove distinct forms of memory. Using a stimulation paradigm in which associative long-term facilitation (LTF) occurs at one input and non-associative LTF at another input to the same postsynaptic neuron in an Aplysia sensorimotor preparation, we found that each form of LTF is reversed by inhibiting distinct isoforms of protein kinase M (PKM), putative PRPs, in the postsynaptic neuron. A dominant-negative (dn) atypical PKM selectively reversed associative LTF, while a dn classical PKM selectively reversed non-associative LTF. Although both PKMs are formed from calpain-mediated cleavage of protein kinase C (PKC) isoforms, each form of LTF is sensitive to a distinct dn calpain expressed in the postsynaptic neuron. Associative LTF is blocked by dn classical calpain, whereas non-associative LTF is blocked by dn small optic lobe (SOL) calpain. Interfering with a putative synaptic tag, the adaptor protein KIBRA, which protects the atypical PKM from degradation, selectively erases associative LTF. Thus, the activity of distinct PRPs and tags in a postsynaptic neuron contribute to the maintenance of different forms of synaptic plasticity at separate inputs, allowing for selective reversal of synaptic plasticity and providing a cellular basis for developing therapeutic strategies for selectively reversing maladaptive memories. Copyright © 2017 Elsevier Ltd. All rights reserved.

Efficient and sparse feature selection for biomedical text classification via the elastic net: Application to ICU risk stratification from nursing notes.

PubMed

Marafino, Ben J; Boscardin, W John; Dudley, R Adams

2015-04-01

Sparsity is often a desirable property of statistical models, and various feature selection methods exist so as to yield sparser and interpretable models. However, their application to biomedical text classification, particularly to mortality risk stratification among intensive care unit (ICU) patients, has not been thoroughly studied. To develop and characterize sparse classifiers based on the free text of nursing notes in order to predict ICU mortality risk and to discover text features most strongly associated with mortality. We selected nursing notes from the first 24h of ICU admission for 25,826 adult ICU patients from the MIMIC-II database. We then developed a pair of stochastic gradient descent-based classifiers with elastic-net regularization. We also studied the performance-sparsity tradeoffs of both classifiers as their regularization parameters were varied. The best-performing classifier achieved a 10-fold cross-validated AUC of 0.897 under the log loss function and full L2 regularization, while full L1 regularization used just 0.00025% of candidate input features and resulted in an AUC of 0.889. Using the log loss (range of AUCs 0.889-0.897) yielded better performance compared to the hinge loss (0.850-0.876), but the latter yielded even sparser models. Most features selected by both classifiers appear clinically relevant and correspond to predictors already present in existing ICU mortality models. The sparser classifiers were also able to discover a number of informative - albeit nonclinical - features. The elastic-net-regularized classifiers perform reasonably well and are capable of reducing the number of features required by over a thousandfold, with only a modest impact on performance. Copyright © 2015 Elsevier Inc. All rights reserved.

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.

Chemical function based pharmacophore generation of endothelin-A selective receptor antagonists.

PubMed

Funk, Oliver F; Kettmann, Viktor; Drimal, Jan; Langer, Thierry

2004-05-20

Both quantitative and qualitative chemical function based pharmacophore models of endothelin-A (ET(A)) selective receptor antagonists were generated by using the two algorithms HypoGen and HipHop, respectively, which are implemented in the Catalyst molecular modeling software. The input for HypoGen is a training set of 18 ET(A) antagonists exhibiting IC(50) values ranging between 0.19 nM and 67 microM. The best output hypothesis consists of five features: two hydrophobic (HY), one ring aromatic (RA), one hydrogen bond acceptor (HBA), and one negative ionizable (NI) function. The highest scoring Hip Hop model consists of six features: three hydrophobic (HY), one ring aromatic (RA), one hydrogen bond acceptor (HBA), and one negative ionizable (NI). It is the result of an input of three highly active, selective, and structurally diverse ET(A) antagonists. The predictive power of the quantitative model could be approved by using a test set of 30 compounds, whose activity values spread over 6 orders of magnitude. The two pharmacophores were tested according to their ability to extract known endothelin antagonists from the 3D molecular structure database of Derwent's World Drug Index. Thereby the main part of selective ET(A) antagonistic entries was detected by the two hypotheses. Furthermore, the pharmacophores were used to screen the Maybridge database. Six compounds were chosen from the output hit lists for in vitro testing of their ability to displace endothelin-1 from its receptor. Two of these are new potential lead compounds because they are structurally novel and exhibit satisfactory activity in the binding assay.

Electrometer Amplifier With Overload Protection

NASA Technical Reports Server (NTRS)

Woeller, F. H.; Alexander, R.

1986-01-01

Circuit features low noise, input offset, and high linearity. Input preamplifier includes input-overload protection and nulling circuit to subtract dc offset from output. Prototype dc amplifier designed for use with ion detector has features desirable in general laboratory and field instrumentation.

Particle Swarm Optimization approach to defect detection in armour ceramics.

PubMed

Kesharaju, Manasa; Nagarajah, Romesh

2017-03-01

In this research, various extracted features were used in the development of an automated ultrasonic sensor based inspection system that enables defect classification in each ceramic component prior to despatch to the field. Classification is an important task and large number of irrelevant, redundant features commonly introduced to a dataset reduces the classifiers performance. Feature selection aims to reduce the dimensionality of the dataset while improving the performance of a classification system. In the context of a multi-criteria optimization problem (i.e. to minimize classification error rate and reduce number of features) such as one discussed in this research, the literature suggests that evolutionary algorithms offer good results. Besides, it is noted that Particle Swarm Optimization (PSO) has not been explored especially in the field of classification of high frequency ultrasonic signals. Hence, a binary coded Particle Swarm Optimization (BPSO) technique is investigated in the implementation of feature subset selection and to optimize the classification error rate. In the proposed method, the population data is used as input to an Artificial Neural Network (ANN) based classification system to obtain the error rate, as ANN serves as an evaluator of PSO fitness function. Copyright © 2016. Published by Elsevier B.V.

Stationary Wavelet Transform and AdaBoost with SVM Based Pathological Brain Detection in MRI Scanning.

PubMed

Nayak, Deepak Ranjan; Dash, Ratnakar; Majhi, Banshidhar

2017-01-01

This paper presents an automatic classification system for segregating pathological brain from normal brains in magnetic resonance imaging scanning. The proposed system employs contrast limited adaptive histogram equalization scheme to enhance the diseased region in brain MR images. Two-dimensional stationary wavelet transform is harnessed to extract features from the preprocessed images. The feature vector is constructed using the energy and entropy values, computed from the level- 2 SWT coefficients. Then, the relevant and uncorrelated features are selected using symmetric uncertainty ranking filter. Subsequently, the selected features are given input to the proposed AdaBoost with support vector machine classifier, where SVM is used as the base classifier of AdaBoost algorithm. To validate the proposed system, three standard MR image datasets, Dataset-66, Dataset-160, and Dataset- 255 have been utilized. The 5 runs of k-fold stratified cross validation results indicate the suggested scheme offers better performance than other existing schemes in terms of accuracy and number of features. The proposed system earns ideal classification over Dataset-66 and Dataset-160; whereas, for Dataset- 255, an accuracy of 99.45% is achieved. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

A Comparison of Physiological Signal Analysis Techniques and Classifiers for Automatic Emotional Evaluation of Audiovisual Contents

PubMed Central

Colomer Granero, Adrián; Fuentes-Hurtado, Félix; Naranjo Ornedo, Valery; Guixeres Provinciale, Jaime; Ausín, Jose M.; Alcañiz Raya, Mariano

2016-01-01

This work focuses on finding the most discriminatory or representative features that allow to classify commercials according to negative, neutral and positive effectiveness based on the Ace Score index. For this purpose, an experiment involving forty-seven participants was carried out. In this experiment electroencephalography (EEG), electrocardiography (ECG), Galvanic Skin Response (GSR) and respiration data were acquired while subjects were watching a 30-min audiovisual content. This content was composed by a submarine documentary and nine commercials (one of them the ad under evaluation). After the signal pre-processing, four sets of features were extracted from the physiological signals using different state-of-the-art metrics. These features computed in time and frequency domains are the inputs to several basic and advanced classifiers. An average of 89.76% of the instances was correctly classified according to the Ace Score index. The best results were obtained by a classifier consisting of a combination between AdaBoost and Random Forest with automatic selection of features. The selected features were those extracted from GSR and HRV signals. These results are promising in the audiovisual content evaluation field by means of physiological signal processing. PMID:27471462

Predictive analysis effectiveness in determining the epidemic disease infected area

NASA Astrophysics Data System (ADS)

Ibrahim, Najihah; Akhir, Nur Shazwani Md.; Hassan, Fadratul Hafinaz

2017-10-01

Epidemic disease outbreak had caused nowadays community to raise their great concern over the infectious disease controlling, preventing and handling methods to diminish the disease dissemination percentage and infected area. Backpropagation method was used for the counter measure and prediction analysis of the epidemic disease. The predictive analysis based on the backpropagation method can be determine via machine learning process that promotes the artificial intelligent in pattern recognition, statistics and features selection. This computational learning process will be integrated with data mining by measuring the score output as the classifier to the given set of input features through classification technique. The classification technique is the features selection of the disease dissemination factors that likely have strong interconnection between each other in causing infectious disease outbreaks. The predictive analysis of epidemic disease in determining the infected area was introduced in this preliminary study by using the backpropagation method in observation of other's findings. This study will classify the epidemic disease dissemination factors as the features for weight adjustment on the prediction of epidemic disease outbreaks. Through this preliminary study, the predictive analysis is proven to be effective method in determining the epidemic disease infected area by minimizing the error value through the features classification.

A Comparison of Physiological Signal Analysis Techniques and Classifiers for Automatic Emotional Evaluation of Audiovisual Contents.

PubMed

Colomer Granero, Adrián; Fuentes-Hurtado, Félix; Naranjo Ornedo, Valery; Guixeres Provinciale, Jaime; Ausín, Jose M; Alcañiz Raya, Mariano

2016-01-01

This work focuses on finding the most discriminatory or representative features that allow to classify commercials according to negative, neutral and positive effectiveness based on the Ace Score index. For this purpose, an experiment involving forty-seven participants was carried out. In this experiment electroencephalography (EEG), electrocardiography (ECG), Galvanic Skin Response (GSR) and respiration data were acquired while subjects were watching a 30-min audiovisual content. This content was composed by a submarine documentary and nine commercials (one of them the ad under evaluation). After the signal pre-processing, four sets of features were extracted from the physiological signals using different state-of-the-art metrics. These features computed in time and frequency domains are the inputs to several basic and advanced classifiers. An average of 89.76% of the instances was correctly classified according to the Ace Score index. The best results were obtained by a classifier consisting of a combination between AdaBoost and Random Forest with automatic selection of features. The selected features were those extracted from GSR and HRV signals. These results are promising in the audiovisual content evaluation field by means of physiological signal processing.

Using learning automata to determine proper subset size in high-dimensional spaces

NASA Astrophysics Data System (ADS)

Seyyedi, Seyyed Hossein; Minaei-Bidgoli, Behrouz

2017-03-01

In this paper, we offer a new method called FSLA (Finding the best candidate Subset using Learning Automata), which combines the filter and wrapper approaches for feature selection in high-dimensional spaces. Considering the difficulties of dimension reduction in high-dimensional spaces, FSLA's multi-objective functionality is to determine, in an efficient manner, a feature subset that leads to an appropriate tradeoff between the learning algorithm's accuracy and efficiency. First, using an existing weighting function, the feature list is sorted and selected subsets of the list of different sizes are considered. Then, a learning automaton verifies the performance of each subset when it is used as the input space of the learning algorithm and estimates its fitness upon the algorithm's accuracy and the subset size, which determines the algorithm's efficiency. Finally, FSLA introduces the fittest subset as the best choice. We tested FSLA in the framework of text classification. The results confirm its promising performance of attaining the identified goal.

Autonomous learning in gesture recognition by using lobe component analysis

NASA Astrophysics Data System (ADS)

Lu, Jian; Weng, Juyang

2007-02-01

Gesture recognition is a new human-machine interface method implemented by pattern recognition(PR).In order to assure robot safety when gesture is used in robot control, it is required to implement the interface reliably and accurately. Similar with other PR applications, 1) feature selection (or model establishment) and 2) training from samples, affect the performance of gesture recognition largely. For 1), a simple model with 6 feature points at shoulders, elbows, and hands, is established. The gestures to be recognized are restricted to still arm gestures, and the movement of arms is not considered. These restrictions are to reduce the misrecognition, but are not so unreasonable. For 2), a new biological network method, called lobe component analysis(LCA), is used in unsupervised learning. Lobe components, corresponding to high-concentrations in probability of the neuronal input, are orientation selective cells follow Hebbian rule and lateral inhibition. Due to the advantage of LCA method for balanced learning between global and local features, large amount of samples can be used in learning efficiently.

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%.

Effects of band selection on endmember extraction for forestry applications

NASA Astrophysics Data System (ADS)

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

2014-10-01

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

Uncertainty Analysis for a Jet Flap Airfoil

NASA Technical Reports Server (NTRS)

Green, Lawrence L.; Cruz, Josue

2006-01-01

An analysis of variance (ANOVA) study was performed to quantify the potential uncertainties of lift and pitching moment coefficient calculations from a computational fluid dynamics code, relative to an experiment, for a jet flap airfoil configuration. Uncertainties due to a number of factors including grid density, angle of attack and jet flap blowing coefficient were examined. The ANOVA software produced a numerical model of the input coefficient data, as functions of the selected factors, to a user-specified order (linear, 2-factor interference, quadratic, or cubic). Residuals between the model and actual data were also produced at each of the input conditions, and uncertainty confidence intervals (in the form of Least Significant Differences or LSD) for experimental, computational, and combined experimental / computational data sets were computed. The LSD bars indicate the smallest resolvable differences in the functional values (lift or pitching moment coefficient) attributable solely to changes in independent variable, given just the input data points from selected data sets. The software also provided a collection of diagnostics which evaluate the suitability of the input data set for use within the ANOVA process, and which examine the behavior of the resultant data, possibly suggesting transformations which should be applied to the data to reduce the LSD. The results illustrate some of the key features of, and results from, the uncertainty analysis studies, including the use of both numerical (continuous) and categorical (discrete) factors, the effects of the number and range of the input data points, and the effects of the number of factors considered simultaneously.

Synaptic Inputs Compete during Rapid Formation of the Calyx of Held: A New Model System for Neural Development

PubMed Central

Holcomb, Paul S.; Hoffpauir, Brian K.; Hoyson, Mitchell C.; Jackson, Dakota R.; Deerinck, Thomas J.; Marrs, Glenn S.; Dehoff, Marlin; Wu, Jonathan; Ellisman, Mark H.

2013-01-01

Hallmark features of neural circuit development include early exuberant innervation followed by competition and pruning to mature innervation topography. Several neural systems, including the neuromuscular junction and climbing fiber innervation of Purkinje cells, are models to study neural development in part because they establish a recognizable endpoint of monoinnervation of their targets and because the presynaptic terminals are large and easily monitored. We demonstrate here that calyx of Held (CH) innervation of its target, which forms a key element of auditory brainstem binaural circuitry, exhibits all of these characteristics. To investigate CH development, we made the first application of serial block-face scanning electron microscopy to neural development with fine temporal resolution and thereby accomplished the first time series for 3D ultrastructural analysis of neural circuit formation. This approach revealed a growth spurt of added apposed surface area (ASA) >200 μm2/d centered on a single age at postnatal day 3 in mice and an initial rapid phase of growth and competition that resolved to monoinnervation in two-thirds of cells within 3 d. This rapid growth occurred in parallel with an increase in action potential threshold, which may mediate selection of the strongest input as the winning competitor. ASAs of competing inputs were segregated on the cell body surface. These data suggest mechanisms to select “winning” inputs by regional reinforcement of postsynaptic membrane to mediate size and strength of competing synaptic inputs. PMID:23926251

A radial map of multi-whisker correlation selectivity in the rat barrel cortex

PubMed Central

Estebanez, Luc; Bertherat, Julien; Shulz, Daniel E.; Bourdieu, Laurent; Léger, Jean- François

2016-01-01

In the barrel cortex, several features of single-whisker stimuli are organized in functional maps. The barrel cortex also encodes spatio-temporal correlation patterns of multi-whisker inputs, but so far the cortical mapping of neurons tuned to such input statistics is unknown. Here we report that layer 2/3 of the rat barrel cortex contains an additional functional map based on neuronal tuning to correlated versus uncorrelated multi-whisker stimuli: neuron responses to uncorrelated multi-whisker stimulation are strongest above barrel centres, whereas neuron responses to correlated and anti-correlated multi-whisker stimulation peak above the barrel–septal borders, forming rings of multi-whisker synchrony-preferring cells. PMID:27869114

A radial map of multi-whisker correlation selectivity in the rat barrel cortex.

PubMed

Estebanez, Luc; Bertherat, Julien; Shulz, Daniel E; Bourdieu, Laurent; Léger, Jean-François

2016-11-21

In the barrel cortex, several features of single-whisker stimuli are organized in functional maps. The barrel cortex also encodes spatio-temporal correlation patterns of multi-whisker inputs, but so far the cortical mapping of neurons tuned to such input statistics is unknown. Here we report that layer 2/3 of the rat barrel cortex contains an additional functional map based on neuronal tuning to correlated versus uncorrelated multi-whisker stimuli: neuron responses to uncorrelated multi-whisker stimulation are strongest above barrel centres, whereas neuron responses to correlated and anti-correlated multi-whisker stimulation peak above the barrel-septal borders, forming rings of multi-whisker synchrony-preferring cells.

Feasibility of streamlining an interactive Bayesian-based diagnostic support tool designed for clinical practice

NASA Astrophysics Data System (ADS)

Chen, Po-Hao; Botzolakis, Emmanuel; Mohan, Suyash; Bryan, R. N.; Cook, Tessa

2016-03-01

In radiology, diagnostic errors occur either through the failure of detection or incorrect interpretation. Errors are estimated to occur in 30-35% of all exams and contribute to 40-54% of medical malpractice litigations. In this work, we focus on reducing incorrect interpretation of known imaging features. Existing literature categorizes cognitive bias leading a radiologist to an incorrect diagnosis despite having correctly recognized the abnormal imaging features: anchoring bias, framing effect, availability bias, and premature closure. Computational methods make a unique contribution, as they do not exhibit the same cognitive biases as a human. Bayesian networks formalize the diagnostic process. They modify pre-test diagnostic probabilities using clinical and imaging features, arriving at a post-test probability for each possible diagnosis. To translate Bayesian networks to clinical practice, we implemented an entirely web-based open-source software tool. In this tool, the radiologist first selects a network of choice (e.g. basal ganglia). Then, large, clearly labeled buttons displaying salient imaging features are displayed on the screen serving both as a checklist and for input. As the radiologist inputs the value of an extracted imaging feature, the conditional probabilities of each possible diagnosis are updated. The software presents its level of diagnostic discrimination using a Pareto distribution chart, updated with each additional imaging feature. Active collaboration with the clinical radiologist is a feasible approach to software design and leads to design decisions closely coupling the complex mathematics of conditional probability in Bayesian networks with practice.

Specific excitatory connectivity for feature integration in mouse primary visual cortex

PubMed Central

Molina-Luna, Patricia; Roth, Morgane M.

2017-01-01

Local excitatory connections in mouse primary visual cortex (V1) are stronger and more prevalent between neurons that share similar functional response features. However, the details of how functional rules for local connectivity shape neuronal responses in V1 remain unknown. We hypothesised that complex responses to visual stimuli may arise as a consequence of rules for selective excitatory connectivity within the local network in the superficial layers of mouse V1. In mouse V1 many neurons respond to overlapping grating stimuli (plaid stimuli) with highly selective and facilitatory responses, which are not simply predicted by responses to single gratings presented alone. This complexity is surprising, since excitatory neurons in V1 are considered to be mainly tuned to single preferred orientations. Here we examined the consequences for visual processing of two alternative connectivity schemes: in the first case, local connections are aligned with visual properties inherited from feedforward input (a ‘like-to-like’ scheme specifically connecting neurons that share similar preferred orientations); in the second case, local connections group neurons into excitatory subnetworks that combine and amplify multiple feedforward visual properties (a ‘feature binding’ scheme). By comparing predictions from large scale computational models with in vivo recordings of visual representations in mouse V1, we found that responses to plaid stimuli were best explained by assuming feature binding connectivity. Unlike under the like-to-like scheme, selective amplification within feature-binding excitatory subnetworks replicated experimentally observed facilitatory responses to plaid stimuli; explained selective plaid responses not predicted by grating selectivity; and was consistent with broad anatomical selectivity observed in mouse V1. Our results show that visual feature binding can occur through local recurrent mechanisms without requiring feedforward convergence, and that such a mechanism is consistent with visual responses and cortical anatomy in mouse V1. PMID:29240769

Wire bonding quality monitoring via refining process of electrical signal from ultrasonic generator

NASA Astrophysics Data System (ADS)

Feng, Wuwei; Meng, Qingfeng; Xie, Youbo; Fan, Hong

2011-04-01

In this paper, a technique for on-line quality detection of ultrasonic wire bonding is developed. The electrical signals from the ultrasonic generator supply, namely, voltage and current, are picked up by a measuring circuit and transformed into digital signals by a data acquisition system. A new feature extraction method is presented to characterize the transient property of the electrical signals and further evaluate the bond quality. The method includes three steps. First, the captured voltage and current are filtered by digital bandpass filter banks to obtain the corresponding subband signals such as fundamental signal, second harmonic, and third harmonic. Second, each subband envelope is obtained using the Hilbert transform for further feature extraction. Third, the subband envelopes are, respectively, separated into three phases, namely, envelope rising, stable, and damping phases, to extract the tiny waveform changes. The different waveform features are extracted from each phase of these subband envelopes. The principal components analysis (PCA) method is used for the feature selection in order to remove the relevant information and reduce the dimension of original feature variables. Using the selected features as inputs, an artificial neural network (ANN) is constructed to identify the complex bond fault pattern. By analyzing experimental data with the proposed feature extraction method and neural network, the results demonstrate the advantages of the proposed feature extraction method and the constructed artificial neural network in detecting and identifying bond quality.

A multiscale Markov random field model in wavelet domain for image segmentation

NASA Astrophysics Data System (ADS)

Dai, Peng; Cheng, Yu; Wang, Shengchun; Du, Xinyu; Wu, Dan

2017-07-01

The human vision system has abilities for feature detection, learning and selective attention with some properties of hierarchy and bidirectional connection in the form of neural population. In this paper, a multiscale Markov random field model in the wavelet domain is proposed by mimicking some image processing functions of vision system. For an input scene, our model provides its sparse representations using wavelet transforms and extracts its topological organization using MRF. In addition, the hierarchy property of vision system is simulated using a pyramid framework in our model. There are two information flows in our model, i.e., a bottom-up procedure to extract input features and a top-down procedure to provide feedback controls. The two procedures are controlled simply by two pyramidal parameters, and some Gestalt laws are also integrated implicitly. Equipped with such biological inspired properties, our model can be used to accomplish different image segmentation tasks, such as edge detection and region segmentation.

A data-driven multi-model methodology with deep feature selection for short-term wind forecasting

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

Feng, Cong; Cui, Mingjian; Hodge, Bri-Mathias

With the growing wind penetration into the power system worldwide, improving wind power forecasting accuracy is becoming increasingly important to ensure continued economic and reliable power system operations. In this paper, a data-driven multi-model wind forecasting methodology is developed with a two-layer ensemble machine learning technique. The first layer is composed of multiple machine learning models that generate individual forecasts. A deep feature selection framework is developed to determine the most suitable inputs to the first layer machine learning models. Then, a blending algorithm is applied in the second layer to create an ensemble of the forecasts produced by firstmore » layer models and generate both deterministic and probabilistic forecasts. This two-layer model seeks to utilize the statistically different characteristics of each machine learning algorithm. A number of machine learning algorithms are selected and compared in both layers. This developed multi-model wind forecasting methodology is compared to several benchmarks. The effectiveness of the proposed methodology is evaluated to provide 1-hour-ahead wind speed forecasting at seven locations of the Surface Radiation network. Numerical results show that comparing to the single-algorithm models, the developed multi-model framework with deep feature selection procedure has improved the forecasting accuracy by up to 30%.« less

A selective-update affine projection algorithm with selective input vectors

NASA Astrophysics Data System (ADS)

Kong, NamWoong; Shin, JaeWook; Park, PooGyeon

2011-10-01

This paper proposes an affine projection algorithm (APA) with selective input vectors, which based on the concept of selective-update in order to reduce estimation errors and computations. The algorithm consists of two procedures: input- vector-selection and state-decision. The input-vector-selection procedure determines the number of input vectors by checking with mean square error (MSE) whether the input vectors have enough information for update. The state-decision procedure determines the current state of the adaptive filter by using the state-decision criterion. As the adaptive filter is in transient state, the algorithm updates the filter coefficients with the selected input vectors. On the other hand, as soon as the adaptive filter reaches the steady state, the update procedure is not performed. Through these two procedures, the proposed algorithm achieves small steady-state estimation errors, low computational complexity and low update complexity for colored input signals.

[Long-term memory, neurogenesis and novelty signal].

PubMed

Sokolova, E N; Nezlina, N I

2003-01-01

In accordance with the advanced hypothesis the long-term memory is a collection of "gnostic units" selectively tuned to experienced events. The long-term memory is continuously supplemented by new neurons differentiated from stem cells during neurogenesis (particularly, in adults). The transformation of neuronal progenitors into event-selective gnostic units is accomplished with participation of hippocampal "novelty neurons" emphasizing information inputs to be stored in the long-term memory. The formation of the gnostic units is preceded by informational processes occurring in the ventral ("what?") and dorsal ("where?") systems. The formation of a new gnostic unit selectively tuned to a particular event is a result of combination of feature-detector excitation and novelty signal generated by hippocampal novelty neurons.

Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifiers.

PubMed

Mougiakakou, Stavroula G; Valavanis, Ioannis K; Nikita, Alexandra; Nikita, Konstantina S

2007-09-01

The aim of the present study is to define an optimally performing computer-aided diagnosis (CAD) architecture for the classification of liver tissue from non-enhanced computed tomography (CT) images into normal liver (C1), hepatic cyst (C2), hemangioma (C3), and hepatocellular carcinoma (C4). To this end, various CAD architectures, based on texture features and ensembles of classifiers (ECs), are comparatively assessed. Number of regions of interests (ROIs) corresponding to C1-C4 have been defined by experienced radiologists in non-enhanced liver CT images. For each ROI, five distinct sets of texture features were extracted using first order statistics, spatial gray level dependence matrix, gray level difference method, Laws' texture energy measures, and fractal dimension measurements. Two different ECs were constructed and compared. The first one consists of five multilayer perceptron neural networks (NNs), each using as input one of the computed texture feature sets or its reduced version after genetic algorithm-based feature selection. The second EC comprised five different primary classifiers, namely one multilayer perceptron NN, one probabilistic NN, and three k-nearest neighbor classifiers, each fed with the combination of the five texture feature sets or their reduced versions. The final decision of each EC was extracted by using appropriate voting schemes, while bootstrap re-sampling was utilized in order to estimate the generalization ability of the CAD architectures based on the available relatively small-sized data set. The best mean classification accuracy (84.96%) is achieved by the second EC using a fused feature set, and the weighted voting scheme. The fused feature set was obtained after appropriate feature selection applied to specific subsets of the original feature set. The comparative assessment of the various CAD architectures shows that combining three types of classifiers with a voting scheme, fed with identical feature sets obtained after appropriate feature selection and fusion, may result in an accurate system able to assist differential diagnosis of focal liver lesions from non-enhanced CT images.

Image processing tool for automatic feature recognition and quantification

DOEpatents

Chen, Xing; Stoddard, Ryan J.

2017-05-02

A system for defining structures within an image is described. The system includes reading of an input file, preprocessing the input file while preserving metadata such as scale information and then detecting features of the input file. In one version the detection first uses an edge detector followed by identification of features using a Hough transform. The output of the process is identified elements within the image.

LTCP 2D Graphical User Interface. Application Description and User's Guide

NASA Technical Reports Server (NTRS)

Ball, Robert; Navaz, Homayun K.

1996-01-01

A graphical user interface (GUI) written for NASA's LTCP (Liquid Thrust Chamber Performance) 2 dimensional computational fluid dynamic code is described. The GUI is written in C++ for a desktop personal computer running under a Microsoft Windows operating environment. Through the use of common and familiar dialog boxes, features, and tools, the user can easily and quickly create and modify input files for the LTCP code. In addition, old input files used with the LTCP code can be opened and modified using the GUI. The application is written in C++ for a desktop personal computer running under a Microsoft Windows operating environment. The program and its capabilities are presented, followed by a detailed description of each menu selection and the method of creating an input file for LTCP. A cross reference is included to help experienced users quickly find the variables which commonly need changes. Finally, the system requirements and installation instructions are provided.

Parameters Selection for Bivariate Multiscale Entropy Analysis of Postural Fluctuations in Fallers and Non-Fallers Older Adults.

PubMed

Ramdani, Sofiane; Bonnet, Vincent; Tallon, Guillaume; Lagarde, Julien; Bernard, Pierre Louis; Blain, Hubert

2016-08-01

Entropy measures are often used to quantify the regularity of postural sway time series. Recent methodological developments provided both multivariate and multiscale approaches allowing the extraction of complexity features from physiological signals; see "Dynamical complexity of human responses: A multivariate data-adaptive framework," in Bulletin of Polish Academy of Science and Technology, vol. 60, p. 433, 2012. The resulting entropy measures are good candidates for the analysis of bivariate postural sway signals exhibiting nonstationarity and multiscale properties. These methods are dependant on several input parameters such as embedding parameters. Using two data sets collected from institutionalized frail older adults, we numerically investigate the behavior of a recent multivariate and multiscale entropy estimator; see "Multivariate multiscale entropy: A tool for complexity analysis of multichannel data," Physics Review E, vol. 84, p. 061918, 2011. We propose criteria for the selection of the input parameters. Using these optimal parameters, we statistically compare the multivariate and multiscale entropy values of postural sway data of non-faller subjects to those of fallers. These two groups are discriminated by the resulting measures over multiple time scales. We also demonstrate that the typical parameter settings proposed in the literature lead to entropy measures that do not distinguish the two groups. This last result confirms the importance of the selection of appropriate input parameters.

The Face-Processing Network Is Resilient to Focal Resection of Human Visual Cortex

PubMed Central

Jonas, Jacques; Gomez, Jesse; Maillard, Louis; Brissart, Hélène; Hossu, Gabriela; Jacques, Corentin; Loftus, David; Colnat-Coulbois, Sophie; Stigliani, Anthony; Barnett, Michael A.; Grill-Spector, Kalanit; Rossion, Bruno

2016-01-01

Human face perception requires a network of brain regions distributed throughout the occipital and temporal lobes with a right hemisphere advantage. Present theories consider this network as either a processing hierarchy beginning with the inferior occipital gyrus (occipital face area; IOG-faces/OFA) or a multiple-route network with nonhierarchical components. The former predicts that removing IOG-faces/OFA will detrimentally affect downstream stages, whereas the latter does not. We tested this prediction in a human patient (Patient S.P.) requiring removal of the right inferior occipital cortex, including IOG-faces/OFA. We acquired multiple fMRI measurements in Patient S.P. before and after a preplanned surgery and multiple measurements in typical controls, enabling both within-subject/across-session comparisons (Patient S.P. before resection vs Patient S.P. after resection) and between-subject/across-session comparisons (Patient S.P. vs controls). We found that the spatial topology and selectivity of downstream ipsilateral face-selective regions were stable 1 and 8 month(s) after surgery. Additionally, the reliability of distributed patterns of face selectivity in Patient S.P. before versus after resection was not different from across-session reliability in controls. Nevertheless, postoperatively, representations of visual space were typical in dorsal face-selective regions but atypical in ventral face-selective regions and V1 of the resected hemisphere. Diffusion weighted imaging in Patient S.P. and controls identifies white matter tracts connecting retinotopic areas to downstream face-selective regions, which may contribute to the stable and plastic features of the face network in Patient S.P. after surgery. Together, our results support a multiple-route network of face processing with nonhierarchical components and shed light on stable and plastic features of high-level visual cortex following focal brain damage. SIGNIFICANCE STATEMENT Brain networks consist of interconnected functional regions commonly organized in processing hierarchies. Prevailing theories predict that damage to the input of the hierarchy will detrimentally affect later stages. We tested this prediction with multiple brain measurements in a rare human patient requiring surgical removal of the putative input to a network processing faces. Surprisingly, the spatial topology and selectivity of downstream face-selective regions are stable after surgery. Nevertheless, representations of visual space were typical in dorsal face-selective regions but atypical in ventral face-selective regions and V1. White matter connections from outside the face network may support these stable and plastic features. As processing hierarchies are ubiquitous in biological and nonbiological systems, our results have pervasive implications for understanding the construction of resilient networks. PMID:27511014

Multifocus image fusion using phase congruency

NASA Astrophysics Data System (ADS)

Zhan, Kun; Li, Qiaoqiao; Teng, Jicai; Wang, Mingying; Shi, Jinhui

2015-05-01

We address the problem of fusing multifocus images based on the phase congruency (PC). PC provides a sharpness feature of a natural image. The focus measure (FM) is identified as strong PC near a distinctive image feature evaluated by the complex Gabor wavelet. The PC is more robust against noise than other FMs. The fusion image is obtained by a new fusion rule (FR), and the focused region is selected by the FR from one of the input images. Experimental results show that the proposed fusion scheme achieves the fusion performance of the state-of-the-art methods in terms of visual quality and quantitative evaluations.

Input variable selection for data-driven models of Coriolis flowmeters for two-phase flow measurement

NASA Astrophysics Data System (ADS)

Wang, Lijuan; Yan, Yong; Wang, Xue; Wang, Tao

2017-03-01

Input variable selection is an essential step in the development of data-driven models for environmental, biological and industrial applications. Through input variable selection to eliminate the irrelevant or redundant variables, a suitable subset of variables is identified as the input of a model. Meanwhile, through input variable selection the complexity of the model structure is simplified and the computational efficiency is improved. This paper describes the procedures of the input variable selection for the data-driven models for the measurement of liquid mass flowrate and gas volume fraction under two-phase flow conditions using Coriolis flowmeters. Three advanced input variable selection methods, including partial mutual information (PMI), genetic algorithm-artificial neural network (GA-ANN) and tree-based iterative input selection (IIS) are applied in this study. Typical data-driven models incorporating support vector machine (SVM) are established individually based on the input candidates resulting from the selection methods. The validity of the selection outcomes is assessed through an output performance comparison of the SVM based data-driven models and sensitivity analysis. The validation and analysis results suggest that the input variables selected from the PMI algorithm provide more effective information for the models to measure liquid mass flowrate while the IIS algorithm provides a fewer but more effective variables for the models to predict gas volume fraction.

Enhanced Sensitivity to Rapid Input Fluctuations by Nonlinear Threshold Dynamics in Neocortical Pyramidal Neurons.

PubMed

Mensi, Skander; Hagens, Olivier; Gerstner, Wulfram; Pozzorini, Christian

2016-02-01

The way in which single neurons transform input into output spike trains has fundamental consequences for network coding. Theories and modeling studies based on standard Integrate-and-Fire models implicitly assume that, in response to increasingly strong inputs, neurons modify their coding strategy by progressively reducing their selective sensitivity to rapid input fluctuations. Combining mathematical modeling with in vitro experiments, we demonstrate that, in L5 pyramidal neurons, the firing threshold dynamics adaptively adjust the effective timescale of somatic integration in order to preserve sensitivity to rapid signals over a broad range of input statistics. For that, a new Generalized Integrate-and-Fire model featuring nonlinear firing threshold dynamics and conductance-based adaptation is introduced that outperforms state-of-the-art neuron models in predicting the spiking activity of neurons responding to a variety of in vivo-like fluctuating currents. Our model allows for efficient parameter extraction and can be analytically mapped to a Generalized Linear Model in which both the input filter--describing somatic integration--and the spike-history filter--accounting for spike-frequency adaptation--dynamically adapt to the input statistics, as experimentally observed. Overall, our results provide new insights on the computational role of different biophysical processes known to underlie adaptive coding in single neurons and support previous theoretical findings indicating that the nonlinear dynamics of the firing threshold due to Na+-channel inactivation regulate the sensitivity to rapid input fluctuations.

Classification of burn wounds using support vector machines

NASA Astrophysics Data System (ADS)

Acha, Begona; Serrano, Carmen; Palencia, Sergio; Murillo, Juan Jose

2004-05-01

The purpose of this work is to improve a previous method developed by the authors for the classification of burn wounds into their depths. The inputs of the system are color and texture information, as these are the characteristics observed by physicians in order to give a diagnosis. Our previous work consisted in segmenting the burn wound from the rest of the image and classifying the burn into its depth. In this paper we focus on the classification problem only. We already proposed to use a Fuzzy-ARTMAP neural network (NN). However, we may take advantage of new powerful classification tools such as Support Vector Machines (SVM). We apply the five-folded cross validation scheme to divide the database into training and validating sets. Then, we apply a feature selection method for each classifier, which will give us the set of features that yields the smallest classification error for each classifier. Features used to classify are first-order statistical parameters extracted from the L*, u* and v* color components of the image. The feature selection algorithms used are the Sequential Forward Selection (SFS) and the Sequential Backward Selection (SBS) methods. As data of the problem faced here are not linearly separable, the SVM was trained using some different kernels. The validating process shows that the SVM method, when using a Gaussian kernel of variance 1, outperforms classification results obtained with the rest of the classifiers, yielding an error classification rate of 0.7% whereas the Fuzzy-ARTMAP NN attained 1.6 %.

Feature extraction through parallel Probabilistic Principal Component Analysis for heart disease diagnosis

NASA Astrophysics Data System (ADS)

Shah, Syed Muhammad Saqlain; Batool, Safeera; Khan, Imran; Ashraf, Muhammad Usman; Abbas, Syed Hussnain; Hussain, Syed Adnan

2017-09-01

Automatic diagnosis of human diseases are mostly achieved through decision support systems. The performance of these systems is mainly dependent on the selection of the most relevant features. This becomes harder when the dataset contains missing values for the different features. Probabilistic Principal Component Analysis (PPCA) has reputation to deal with the problem of missing values of attributes. This research presents a methodology which uses the results of medical tests as input, extracts a reduced dimensional feature subset and provides diagnosis of heart disease. The proposed methodology extracts high impact features in new projection by using Probabilistic Principal Component Analysis (PPCA). PPCA extracts projection vectors which contribute in highest covariance and these projection vectors are used to reduce feature dimension. The selection of projection vectors is done through Parallel Analysis (PA). The feature subset with the reduced dimension is provided to radial basis function (RBF) kernel based Support Vector Machines (SVM). The RBF based SVM serves the purpose of classification into two categories i.e., Heart Patient (HP) and Normal Subject (NS). The proposed methodology is evaluated through accuracy, specificity and sensitivity over the three datasets of UCI i.e., Cleveland, Switzerland and Hungarian. The statistical results achieved through the proposed technique are presented in comparison to the existing research showing its impact. The proposed technique achieved an accuracy of 82.18%, 85.82% and 91.30% for Cleveland, Hungarian and Switzerland dataset respectively.

An affine projection algorithm using grouping selection of input vectors

NASA Astrophysics Data System (ADS)

Shin, JaeWook; Kong, NamWoong; Park, PooGyeon

2011-10-01

This paper present an affine projection algorithm (APA) using grouping selection of input vectors. To improve the performance of conventional APA, the proposed algorithm adjusts the number of the input vectors using two procedures: grouping procedure and selection procedure. In grouping procedure, the some input vectors that have overlapping information for update is grouped using normalized inner product. Then, few input vectors that have enough information for for coefficient update is selected using steady-state mean square error (MSE) in selection procedure. Finally, the filter coefficients update using selected input vectors. The experimental results show that the proposed algorithm has small steady-state estimation errors comparing with the existing algorithms.

Our Selections and Decisions: Inherent Features of the Nervous System?

NASA Astrophysics Data System (ADS)

Rösler, Frank

The chapter summarizes findings on the neuronal bases of decisionmaking. Taking the phenomenon of selection it will be explained that systems built only from excitatory and inhibitory neuron (populations) have the emergent property of selecting between different alternatives. These considerations suggest that there exists a hierarchical architecture with central selection switches. However, in such a system, functions of selection and decision-making are not localized, but rather emerge from an interaction of several participating networks. These are, on the one hand, networks that process specific input and output representations and, on the other hand, networks that regulate the relative activation/inhibition of the specific input and output networks. These ideas are supported by recent empirical evidence. Moreover, other studies show that rather complex psychological variables, like subjective probability estimates, expected gains and losses, prediction errors, etc., do have biological correlates, i.e., they can be localized in time and space as activation states of neural networks and single cells. These findings suggest that selections and decisions are consequences of an architecture which, seen from a biological perspective, is fully deterministic. However, a transposition of such nomothetic functional principles into the idiographic domain, i.e., using them as elements for comprehensive 'mechanistic' explanations of individual decisions, seems not to be possible because of principle limitations. Therefore, individual decisions will remain predictable by means of probabilistic models alone.

Fusion of Heterogeneous Intrusion Detection Systems for Network Attack Detection

PubMed Central

Kaliappan, Jayakumar; Thiagarajan, Revathi; Sundararajan, Karpagam

2015-01-01

An intrusion detection system (IDS) helps to identify different types of attacks in general, and the detection rate will be higher for some specific category of attacks. This paper is designed on the idea that each IDS is efficient in detecting a specific type of attack. In proposed Multiple IDS Unit (MIU), there are five IDS units, and each IDS follows a unique algorithm to detect attacks. The feature selection is done with the help of genetic algorithm. The selected features of the input traffic are passed on to the MIU for processing. The decision from each IDS is termed as local decision. The fusion unit inside the MIU processes all the local decisions with the help of majority voting rule and makes the final decision. The proposed system shows a very good improvement in detection rate and reduces the false alarm rate. PMID:26295058

Fusion of Heterogeneous Intrusion Detection Systems for Network Attack Detection.

PubMed

Kaliappan, Jayakumar; Thiagarajan, Revathi; Sundararajan, Karpagam

2015-01-01

An intrusion detection system (IDS) helps to identify different types of attacks in general, and the detection rate will be higher for some specific category of attacks. This paper is designed on the idea that each IDS is efficient in detecting a specific type of attack. In proposed Multiple IDS Unit (MIU), there are five IDS units, and each IDS follows a unique algorithm to detect attacks. The feature selection is done with the help of genetic algorithm. The selected features of the input traffic are passed on to the MIU for processing. The decision from each IDS is termed as local decision. The fusion unit inside the MIU processes all the local decisions with the help of majority voting rule and makes the final decision. The proposed system shows a very good improvement in detection rate and reduces the false alarm rate.

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

PubMed

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

2018-01-01

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

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

PubMed Central

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

2018-01-01

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

Thalamic neuron models encode stimulus information by burst-size modulation

PubMed Central

Elijah, Daniel H.; Samengo, Inés; Montemurro, Marcelo A.

2015-01-01

Thalamic neurons have been long assumed to fire in tonic mode during perceptive states, and in burst mode during sleep and unconsciousness. However, recent evidence suggests that bursts may also be relevant in the encoding of sensory information. Here, we explore the neural code of such thalamic bursts. In order to assess whether the burst code is generic or whether it depends on the detailed properties of each bursting neuron, we analyzed two neuron models incorporating different levels of biological detail. One of the models contained no information of the biophysical processes entailed in spike generation, and described neuron activity at a phenomenological level. The second model represented the evolution of the individual ionic conductances involved in spiking and bursting, and required a large number of parameters. We analyzed the models' input selectivity using reverse correlation methods and information theory. We found that n-spike bursts from both models transmit information by modulating their spike count in response to changes to instantaneous input features, such as slope, phase, amplitude, etc. The stimulus feature that is most efficiently encoded by bursts, however, need not coincide with one of such classical features. We therefore searched for the optimal feature among all those that could be expressed as a linear transformation of the time-dependent input current. We found that bursting neurons transmitted 6 times more information about such more general features. The relevant events in the stimulus were located in a time window spanning ~100 ms before and ~20 ms after burst onset. Most importantly, the neural code employed by the simple and the biologically realistic models was largely the same, implying that the simple thalamic neuron model contains the essential ingredients that account for the computational properties of the thalamic burst code. Thus, our results suggest the n-spike burst code is a general property of thalamic neurons. PMID:26441623

Thalamic neuron models encode stimulus information by burst-size modulation.

PubMed

Elijah, Daniel H; Samengo, Inés; Montemurro, Marcelo A

2015-01-01

Thalamic neurons have been long assumed to fire in tonic mode during perceptive states, and in burst mode during sleep and unconsciousness. However, recent evidence suggests that bursts may also be relevant in the encoding of sensory information. Here, we explore the neural code of such thalamic bursts. In order to assess whether the burst code is generic or whether it depends on the detailed properties of each bursting neuron, we analyzed two neuron models incorporating different levels of biological detail. One of the models contained no information of the biophysical processes entailed in spike generation, and described neuron activity at a phenomenological level. The second model represented the evolution of the individual ionic conductances involved in spiking and bursting, and required a large number of parameters. We analyzed the models' input selectivity using reverse correlation methods and information theory. We found that n-spike bursts from both models transmit information by modulating their spike count in response to changes to instantaneous input features, such as slope, phase, amplitude, etc. The stimulus feature that is most efficiently encoded by bursts, however, need not coincide with one of such classical features. We therefore searched for the optimal feature among all those that could be expressed as a linear transformation of the time-dependent input current. We found that bursting neurons transmitted 6 times more information about such more general features. The relevant events in the stimulus were located in a time window spanning ~100 ms before and ~20 ms after burst onset. Most importantly, the neural code employed by the simple and the biologically realistic models was largely the same, implying that the simple thalamic neuron model contains the essential ingredients that account for the computational properties of the thalamic burst code. Thus, our results suggest the n-spike burst code is a general property of thalamic neurons.

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.

Analysis and prediction of presynaptic and postsynaptic neurotoxins by Chou's general pseudo amino acid composition and motif features.

PubMed

Mei, Juan; Zhao, Ji

2018-06-14

Presynaptic neurotoxins and postsynaptic neurotoxins are two important neurotoxins isolated from venoms of venomous animals and have been proven to be potential effective in neurosciences and pharmacology. With the number of toxin sequences appeared in the public databases, there was a need for developing a computational method for fast and accurate identification and classification of the novel presynaptic neurotoxins and postsynaptic neurotoxins in the large databases. In this study, the Multinomial Naive Bayes Classifier (MNBC) had been developed to discriminate the presynaptic neurotoxins and postsynaptic neurotoxins based on the different kinds of features. The Minimum Redundancy Maximum Relevance (MRMR) feature selection method was used for ranking 400 pseudo amino acid (PseAA) compositions and 50 top ranked PseAA compositions were selected for improving the prediction results. The motif features, 400 PseAA compositions and 50 PseAA compositions were combined together, and selected as the input parameters of MNBC. The best correlation coefficient (CC) value of 0.8213 was obtained when the prediction quality was evaluated by the jackknife test. It was anticipated that the algorithm presented in this study may become a useful tool for identification of presynaptic neurotoxin and postsynaptic neurotoxin sequences and may provide some useful help for in-depth investigation into the biological mechanism of presynaptic neurotoxins and postsynaptic neurotoxins. Copyright © 2018 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.

Epileptic Seizure Detection Based on Time-Frequency Images of EEG Signals using Gaussian Mixture Model and Gray Level Co-Occurrence Matrix Features.

PubMed

Li, Yang; Cui, Weigang; Luo, Meilin; Li, Ke; Wang, Lina

2018-01-25

The electroencephalogram (EEG) signal analysis is a valuable tool in the evaluation of neurological disorders, which is commonly used for the diagnosis of epileptic seizures. This paper presents a novel automatic EEG signal classification method for epileptic seizure detection. The proposed method first employs a continuous wavelet transform (CWT) method for obtaining the time-frequency images (TFI) of EEG signals. The processed EEG signals are then decomposed into five sub-band frequency components of clinical interest since these sub-band frequency components indicate much better discriminative characteristics. Both Gaussian Mixture Model (GMM) features and Gray Level Co-occurrence Matrix (GLCM) descriptors are then extracted from these sub-band TFI. Additionally, in order to improve classification accuracy, a compact feature selection method by combining the ReliefF and the support vector machine-based recursive feature elimination (RFE-SVM) algorithm is adopted to select the most discriminative feature subset, which is an input to the SVM with the radial basis function (RBF) for classifying epileptic seizure EEG signals. The experimental results from a publicly available benchmark database demonstrate that the proposed approach provides better classification accuracy than the recently proposed methods in the literature, indicating the effectiveness of the proposed method in the detection of epileptic seizures.

Constructing a Database from Multiple 2D Images for Camera Pose Estimation and Robot Localization

NASA Technical Reports Server (NTRS)

Wolf, Michael; Ansar, Adnan I.; Brennan, Shane; Clouse, Daniel S.; Padgett, Curtis W.

2012-01-01

The LMDB (Landmark Database) Builder software identifies persistent image features (landmarks) in a scene viewed multiple times and precisely estimates the landmarks 3D world positions. The software receives as input multiple 2D images of approximately the same scene, along with an initial guess of the camera poses for each image, and a table of features matched pair-wise in each frame. LMDB Builder aggregates landmarks across an arbitrarily large collection of frames with matched features. Range data from stereo vision processing can also be passed to improve the initial guess of the 3D point estimates. The LMDB Builder aggregates feature lists across all frames, manages the process to promote selected features to landmarks, and iteratively calculates the 3D landmark positions using the current camera pose estimations (via an optimal ray projection method), and then improves the camera pose estimates using the 3D landmark positions. Finally, it extracts image patches for each landmark from auto-selected key frames and constructs the landmark database. The landmark database can then be used to estimate future camera poses (and therefore localize a robotic vehicle that may be carrying the cameras) by matching current imagery to landmark database image patches and using the known 3D landmark positions to estimate the current pose.

Redesigning U.S. currency

NASA Astrophysics Data System (ADS)

Ferguson, Thomas A.; Church, Sara E.

1996-03-01

The first new design of United States currency in over 60 years will soon be issued. Its issuance will be the culmination of a 6-year effort to make U.S. currency more secure against widely available advanced reprographic technology. The cooperative effort was directed by the Advanced Counterfeit Deterrence (ACD) Steering Committee, with executive representatives from the Federal Reserve System (FRS), U.S. Secret Service (USSS), Bureau of Engraving and Printing (BEP) and Treasury Department. A task force of technical experts from each agency carried out the necessary evaluations. The overall strategy to determine the new design and new features applied a comprehensive, synergistic approach to target each type of currency user and each type of counterfeiting. To maximize objectivity yet expedite final selection, deterrent and detection technologies were evaluated through several parallel channels. These efforts included an open request for feature samples through the Commerce Business Daily, in-house testing of each feature, independent evaluation by the National Research Council, in-house design development and survey of world currencies. Recommendations were submitted by the Steering Committee to the Treasury Secretary for concept approval, announced in July 1994. Beginning in 1996, new designs will be issued by denomination approximately one per year, starting with the $100 bill. Future new design efforts will include input from the recently founded Securities Technology Institute (STI) at Johns Hopkins Applied Physics Laboratory. Input will include evaluation of existing features, development of new techniques and adversarial analysis.

[Research on spectra recognition method for cabbages and weeds based on PCA and SIMCA].

PubMed

Zu, Qin; Deng, Wei; Wang, Xiu; Zhao, Chun-Jiang

2013-10-01

In order to improve the accuracy and efficiency of weed identification, the difference of spectral reflectance was employed to distinguish between crops and weeds. Firstly, the different combinations of Savitzky-Golay (SG) convolutional derivation and multiplicative scattering correction (MSC) method were applied to preprocess the raw spectral data. Then the clustering analysis of various types of plants was completed by using principal component analysis (PCA) method, and the feature wavelengths which were sensitive for classifying various types of plants were extracted according to the corresponding loading plots of the optimal principal components in PCA results. Finally, setting the feature wavelengths as the input variables, the soft independent modeling of class analogy (SIMCA) classification method was used to identify the various types of plants. The experimental results of classifying cabbages and weeds showed that on the basis of the optimal pretreatment by a synthetic application of MSC and SG convolutional derivation with SG's parameters set as 1rd order derivation, 3th degree polynomial and 51 smoothing points, 23 feature wavelengths were extracted in accordance with the top three principal components in PCA results. When SIMCA method was used for classification while the previously selected 23 feature wavelengths were set as the input variables, the classification rates of the modeling set and the prediction set were respectively up to 98.6% and 100%.

Optimal algorithm for automatic detection of microaneurysms based on receiver operating characteristic curve

NASA Astrophysics Data System (ADS)

Xu, Lili; Luo, Shuqian

2010-11-01

Microaneurysms (MAs) are the first manifestations of the diabetic retinopathy (DR) as well as an indicator for its progression. Their automatic detection plays a key role for both mass screening and monitoring and is therefore in the core of any system for computer-assisted diagnosis of DR. The algorithm basically comprises the following stages: candidate detection aiming at extracting the patterns possibly corresponding to MAs based on mathematical morphological black top hat, feature extraction to characterize these candidates, and classification based on support vector machine (SVM), to validate MAs. Feature vector and kernel function of SVM selection is very important to the algorithm. We use the receiver operating characteristic (ROC) curve to evaluate the distinguishing performance of different feature vectors and different kernel functions of SVM. The ROC analysis indicates the quadratic polynomial SVM with a combination of features as the input shows the best discriminating performance.

Optimal algorithm for automatic detection of microaneurysms based on receiver operating characteristic curve.

PubMed

Xu, Lili; Luo, Shuqian

2010-01-01

Microaneurysms (MAs) are the first manifestations of the diabetic retinopathy (DR) as well as an indicator for its progression. Their automatic detection plays a key role for both mass screening and monitoring and is therefore in the core of any system for computer-assisted diagnosis of DR. The algorithm basically comprises the following stages: candidate detection aiming at extracting the patterns possibly corresponding to MAs based on mathematical morphological black top hat, feature extraction to characterize these candidates, and classification based on support vector machine (SVM), to validate MAs. Feature vector and kernel function of SVM selection is very important to the algorithm. We use the receiver operating characteristic (ROC) curve to evaluate the distinguishing performance of different feature vectors and different kernel functions of SVM. The ROC analysis indicates the quadratic polynomial SVM with a combination of features as the input shows the best discriminating performance.

Hierarchical Feature Extraction With Local Neural Response for Image Recognition.

PubMed

Li, Hong; Wei, Yantao; Li, Luoqing; Chen, C L P

2013-04-01

In this paper, a hierarchical feature extraction method is proposed for image recognition. The key idea of the proposed method is to extract an effective feature, called local neural response (LNR), of the input image with nontrivial discrimination and invariance properties by alternating between local coding and maximum pooling operation. The local coding, which is carried out on the locally linear manifold, can extract the salient feature of image patches and leads to a sparse measure matrix on which maximum pooling is carried out. The maximum pooling operation builds the translation invariance into the model. We also show that other invariant properties, such as rotation and scaling, can be induced by the proposed model. In addition, a template selection algorithm is presented to reduce computational complexity and to improve the discrimination ability of the LNR. Experimental results show that our method is robust to local distortion and clutter compared with state-of-the-art algorithms.

Derivative component analysis for mass spectral serum proteomic profiles.

PubMed

Han, Henry

2014-01-01

As a promising way to transform medicine, mass spectrometry based proteomics technologies have seen a great progress in identifying disease biomarkers for clinical diagnosis and prognosis. However, there is a lack of effective feature selection methods that are able to capture essential data behaviors to achieve clinical level disease diagnosis. Moreover, it faces a challenge from data reproducibility, which means that no two independent studies have been found to produce same proteomic patterns. Such reproducibility issue causes the identified biomarker patterns to lose repeatability and prevents it from real clinical usage. In this work, we propose a novel machine-learning algorithm: derivative component analysis (DCA) for high-dimensional mass spectral proteomic profiles. As an implicit feature selection algorithm, derivative component analysis examines input proteomics data in a multi-resolution approach by seeking its derivatives to capture latent data characteristics and conduct de-noising. We further demonstrate DCA's advantages in disease diagnosis by viewing input proteomics data as a profile biomarker via integrating it with support vector machines to tackle the reproducibility issue, besides comparing it with state-of-the-art peers. Our results show that high-dimensional proteomics data are actually linearly separable under proposed derivative component analysis (DCA). As a novel multi-resolution feature selection algorithm, DCA not only overcomes the weakness of the traditional methods in subtle data behavior discovery, but also suggests an effective resolution to overcoming proteomics data's reproducibility problem and provides new techniques and insights in translational bioinformatics and machine learning. The DCA-based profile biomarker diagnosis makes clinical level diagnostic performances reproducible across different proteomic data, which is more robust and systematic than the existing biomarker discovery based diagnosis. Our findings demonstrate the feasibility and power of the proposed DCA-based profile biomarker diagnosis in achieving high sensitivity and conquering the data reproducibility issue in serum proteomics. Furthermore, our proposed derivative component analysis suggests the subtle data characteristics gleaning and de-noising are essential in separating true signals from red herrings for high-dimensional proteomic profiles, which can be more important than the conventional feature selection or dimension reduction. In particular, our profile biomarker diagnosis can be generalized to other omics data for derivative component analysis (DCA)'s nature of generic data analysis.

Supervised Learning Applied to Air Traffic Trajectory Classification

NASA Technical Reports Server (NTRS)

Bosson, Christabelle S.; Nikoleris, Tasos

2018-01-01

Given the recent increase of interest in introducing new vehicle types and missions into the National Airspace System, a transition towards a more autonomous air traffic control system is required in order to enable and handle increased density and complexity. This paper presents an exploratory effort of the needed autonomous capabilities by exploring supervised learning techniques in the context of aircraft trajectories. In particular, it focuses on the application of machine learning algorithms and neural network models to a runway recognition trajectory-classification study. It investigates the applicability and effectiveness of various classifiers using datasets containing trajectory records for a month of air traffic. A feature importance and sensitivity analysis are conducted to challenge the chosen time-based datasets and the ten selected features. The study demonstrates that classification accuracy levels of 90% and above can be reached in less than 40 seconds of training for most machine learning classifiers when one track data point, described by the ten selected features at a particular time step, per trajectory is used as input. It also shows that neural network models can achieve similar accuracy levels but at higher training time costs.

Adaptive fusion of infrared and visible images in dynamic scene

NASA Astrophysics Data System (ADS)

Yang, Guang; Yin, Yafeng; Man, Hong; Desai, Sachi

2011-11-01

Multiple modalities sensor fusion has been widely employed in various surveillance and military applications. A variety of image fusion techniques including PCA, wavelet, curvelet and HSV has been proposed in recent years to improve human visual perception for object detection. One of the main challenges for visible and infrared image fusion is to automatically determine an optimal fusion strategy for different input scenes along with an acceptable computational cost. This paper, we propose a fast and adaptive feature selection based image fusion method to obtain high a contrast image from visible and infrared sensors for targets detection. At first, fuzzy c-means clustering is applied on the infrared image to highlight possible hotspot regions, which will be considered as potential targets' locations. After that, the region surrounding the target area is segmented as the background regions. Then image fusion is locally applied on the selected target and background regions by computing different linear combination of color components from registered visible and infrared images. After obtaining different fused images, histogram distributions are computed on these local fusion images as the fusion feature set. The variance ratio which is based on Linear Discriminative Analysis (LDA) measure is employed to sort the feature set and the most discriminative one is selected for the whole image fusion. As the feature selection is performed over time, the process will dynamically determine the most suitable feature for the image fusion in different scenes. Experiment is conducted on the OSU Color-Thermal database, and TNO Human Factor dataset. The fusion results indicate that our proposed method achieved a competitive performance compared with other fusion algorithms at a relatively low computational cost.

Audio-visual synchrony and feature-selective attention co-amplify early visual processing.

PubMed

Keitel, Christian; Müller, Matthias M

2016-05-01

Our brain relies on neural mechanisms of selective attention and converging sensory processing to efficiently cope with rich and unceasing multisensory inputs. One prominent assumption holds that audio-visual synchrony can act as a strong attractor for spatial attention. Here, we tested for a similar effect of audio-visual synchrony on feature-selective attention. We presented two superimposed Gabor patches that differed in colour and orientation. On each trial, participants were cued to selectively attend to one of the two patches. Over time, spatial frequencies of both patches varied sinusoidally at distinct rates (3.14 and 3.63 Hz), giving rise to pulse-like percepts. A simultaneously presented pure tone carried a frequency modulation at the pulse rate of one of the two visual stimuli to introduce audio-visual synchrony. Pulsed stimulation elicited distinct time-locked oscillatory electrophysiological brain responses. These steady-state responses were quantified in the spectral domain to examine individual stimulus processing under conditions of synchronous versus asynchronous tone presentation and when respective stimuli were attended versus unattended. We found that both, attending to the colour of a stimulus and its synchrony with the tone, enhanced its processing. Moreover, both gain effects combined linearly for attended in-sync stimuli. Our results suggest that audio-visual synchrony can attract attention to specific stimulus features when stimuli overlap in space.

Classification of brain tumours using short echo time 1H MR spectra

NASA Astrophysics Data System (ADS)

Devos, A.; Lukas, L.; Suykens, J. A. K.; Vanhamme, L.; Tate, A. R.; Howe, F. A.; Majós, C.; Moreno-Torres, A.; van der Graaf, M.; Arús, C.; Van Huffel, S.

2004-09-01

The purpose was to objectively compare the application of several techniques and the use of several input features for brain tumour classification using Magnetic Resonance Spectroscopy (MRS). Short echo time 1H MRS signals from patients with glioblastomas ( n = 87), meningiomas ( n = 57), metastases ( n = 39), and astrocytomas grade II ( n = 22) were provided by six centres in the European Union funded INTERPRET project. Linear discriminant analysis, least squares support vector machines (LS-SVM) with a linear kernel and LS-SVM with radial basis function kernel were applied and evaluated over 100 stratified random splittings of the dataset into training and test sets. The area under the receiver operating characteristic curve (AUC) was used to measure the performance of binary classifiers, while the percentage of correct classifications was used to evaluate the multiclass classifiers. The influence of several factors on the classification performance has been tested: L2- vs. water normalization, magnitude vs. real spectra and baseline correction. The effect of input feature reduction was also investigated by using only the selected frequency regions containing the most discriminatory information, and peak integrated values. Using L2-normalized complete spectra the automated binary classifiers reached a mean test AUC of more than 0.95, except for glioblastomas vs. metastases. Similar results were obtained for all classification techniques and input features except for water normalized spectra, where classification performance was lower. This indicates that data acquisition and processing can be simplified for classification purposes, excluding the need for separate water signal acquisition, baseline correction or phasing.

Phytoplankton global mapping from space with a support vector machine algorithm

NASA Astrophysics Data System (ADS)

de Boissieu, Florian; Menkes, Christophe; Dupouy, Cécile; Rodier, Martin; Bonnet, Sophie; Mangeas, Morgan; Frouin, Robert J.

2014-11-01

In recent years great progress has been made in global mapping of phytoplankton from space. Two main trends have emerged, the recognition of phytoplankton functional types (PFT) based on reflectance normalized to chlorophyll-a concentration, and the recognition of phytoplankton size class (PSC) based on the relationship between cell size and chlorophyll-a concentration. However, PFTs and PSCs are not decorrelated, and one approach can complement the other in a recognition task. In this paper, we explore the recognition of several dominant PFTs by combining reflectance anomalies, chlorophyll-a concentration and other environmental parameters, such as sea surface temperature and wind speed. Remote sensing pixels are labeled thanks to coincident in-situ pigment data from GeP&CO, NOMAD and MAREDAT datasets, covering various oceanographic environments. The recognition is made with a supervised Support Vector Machine classifier trained on the labeled pixels. This algorithm enables a non-linear separation of the classes in the input space and is especially adapted for small training datasets as available here. Moreover, it provides a class probability estimate, allowing one to enhance the robustness of the classification results through the choice of a minimum probability threshold. A greedy feature selection associated to a 10-fold cross-validation procedure is applied to select the most discriminative input features and evaluate the classification performance. The best classifiers are finally applied on daily remote sensing datasets (SeaWIFS, MODISA) and the resulting dominant PFT maps are compared with other studies. Several conclusions are drawn: (1) the feature selection highlights the weight of temperature, chlorophyll-a and wind speed variables in phytoplankton recognition; (2) the classifiers show good results and dominant PFT maps in agreement with phytoplankton distribution knowledge; (3) classification on MODISA data seems to perform better than on SeaWIFS data, (4) the probability threshold screens correctly the areas of smallest confidence such as the interclass regions.

Programmable in vivo selection of arbitrary DNA sequences.

PubMed

Ben Yehezkel, Tuval; Biezuner, Tamir; Linshiz, Gregory; Mazor, Yair; Shapiro, Ehud

2012-01-01

The extraordinary fidelity, sensory and regulatory capacity of natural intracellular machinery is generally confined to their endogenous environment. Nevertheless, synthetic bio-molecular components have been engineered to interface with the cellular transcription, splicing and translation machinery in vivo by embedding functional features such as promoters, introns and ribosome binding sites, respectively, into their design. Tapping and directing the power of intracellular molecular processing towards synthetic bio-molecular inputs is potentially a powerful approach, albeit limited by our ability to streamline the interface of synthetic components with the intracellular machinery in vivo. Here we show how a library of synthetic DNA devices, each bearing an input DNA sequence and a logical selection module, can be designed to direct its own probing and processing by interfacing with the bacterial DNA mismatch repair (MMR) system in vivo and selecting for the most abundant variant, regardless of its function. The device provides proof of concept for programmable, function-independent DNA selection in vivo and provides a unique example of a logical-functional interface of an engineered synthetic component with a complex endogenous cellular system. Further research into the design, construction and operation of synthetic devices in vivo may lead to other functional devices that interface with other complex cellular processes for both research and applied purposes.

Subject-based feature extraction by using fisher WPD-CSP in brain-computer interfaces.

PubMed

Yang, Banghua; Li, Huarong; Wang, Qian; Zhang, Yunyuan

2016-06-01

Feature extraction of electroencephalogram (EEG) plays a vital role in brain-computer interfaces (BCIs). In recent years, common spatial pattern (CSP) has been proven to be an effective feature extraction method. However, the traditional CSP has disadvantages of requiring a lot of input channels and the lack of frequency information. In order to remedy the defects of CSP, wavelet packet decomposition (WPD) and CSP are combined to extract effective features. But WPD-CSP method considers less about extracting specific features that are fitted for the specific subject. So a subject-based feature extraction method using fisher WPD-CSP is proposed in this paper. The idea of proposed method is to adapt fisher WPD-CSP to each subject separately. It mainly includes the following six steps: (1) original EEG signals from all channels are decomposed into a series of sub-bands using WPD; (2) average power values of obtained sub-bands are computed; (3) the specified sub-bands with larger values of fisher distance according to average power are selected for that particular subject; (4) each selected sub-band is reconstructed to be regarded as a new EEG channel; (5) all new EEG channels are used as input of the CSP and a six-dimensional feature vector is obtained by the CSP. The subject-based feature extraction model is so formed; (6) the probabilistic neural network (PNN) is used as the classifier and the classification accuracy is obtained. Data from six subjects are processed by the subject-based fisher WPD-CSP, the non-subject-based fisher WPD-CSP and WPD-CSP, respectively. Compared with non-subject-based fisher WPD-CSP and WPD-CSP, the results show that the proposed method yields better performance (sensitivity: 88.7±0.9%, and specificity: 91±1%) and the classification accuracy from subject-based fisher WPD-CSP is increased by 6-12% and 14%, respectively. The proposed subject-based fisher WPD-CSP method can not only remedy disadvantages of CSP by WPD but also discriminate helpless sub-bands for each subject and make remaining fewer sub-bands keep better separability by fisher distance, which leads to a higher classification accuracy than WPD-CSP method. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

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.

Setting and changing feature priorities in visual short-term memory.

PubMed

Kalogeropoulou, Zampeta; Jagadeesh, Akshay V; Ohl, Sven; Rolfs, Martin

2017-04-01

Many everyday tasks require prioritizing some visual features over competing ones, both during the selection from the rich sensory input and while maintaining information in visual short-term memory (VSTM). Here, we show that observers can change priorities in VSTM when, initially, they attended to a different feature. Observers reported from memory the orientation of one of two spatially interspersed groups of black and white gratings. Using colored pre-cues (presented before stimulus onset) and retro-cues (presented after stimulus offset) predicting the to-be-reported group, we manipulated observers' feature priorities independently during stimulus encoding and maintenance, respectively. Valid pre-cues reliably increased observers' performance (reduced guessing, increased report precision) as compared to neutral ones; invalid pre-cues had the opposite effect. Valid retro-cues also consistently improved performance (by reducing random guesses), even if the unexpected group suddenly became relevant (invalid-valid condition). Thus, feature-based attention can reshape priorities in VSTM protecting information that would otherwise be forgotten.

Enhanced Sensitivity to Rapid Input Fluctuations by Nonlinear Threshold Dynamics in Neocortical Pyramidal Neurons

PubMed Central

Mensi, Skander; Hagens, Olivier; Gerstner, Wulfram; Pozzorini, Christian

2016-01-01

The way in which single neurons transform input into output spike trains has fundamental consequences for network coding. Theories and modeling studies based on standard Integrate-and-Fire models implicitly assume that, in response to increasingly strong inputs, neurons modify their coding strategy by progressively reducing their selective sensitivity to rapid input fluctuations. Combining mathematical modeling with in vitro experiments, we demonstrate that, in L5 pyramidal neurons, the firing threshold dynamics adaptively adjust the effective timescale of somatic integration in order to preserve sensitivity to rapid signals over a broad range of input statistics. For that, a new Generalized Integrate-and-Fire model featuring nonlinear firing threshold dynamics and conductance-based adaptation is introduced that outperforms state-of-the-art neuron models in predicting the spiking activity of neurons responding to a variety of in vivo-like fluctuating currents. Our model allows for efficient parameter extraction and can be analytically mapped to a Generalized Linear Model in which both the input filter—describing somatic integration—and the spike-history filter—accounting for spike-frequency adaptation—dynamically adapt to the input statistics, as experimentally observed. Overall, our results provide new insights on the computational role of different biophysical processes known to underlie adaptive coding in single neurons and support previous theoretical findings indicating that the nonlinear dynamics of the firing threshold due to Na+-channel inactivation regulate the sensitivity to rapid input fluctuations. PMID:26907675

COSP for Windows: Strategies for Rapid Analyses of Cyclic Oxidation Behavior

NASA Technical Reports Server (NTRS)

Smialek, James L.; Auping, Judith V.

2002-01-01

COSP is a publicly available computer program that models the cyclic oxidation weight gain and spallation process. Inputs to the model include the selection of an oxidation growth law and a spalling geometry, plus oxide phase, growth rate, spall constant, and cycle duration parameters. Output includes weight change, the amounts of retained and spalled oxide, the total oxygen and metal consumed, and the terminal rates of weight loss and metal consumption. The present version is Windows based and can accordingly be operated conveniently while other applications remain open for importing experimental weight change data, storing model output data, or plotting model curves. Point-and-click operating features include multiple drop-down menus for input parameters, data importing, and quick, on-screen plots showing one selection of the six output parameters for up to 10 models. A run summary text lists various characteristic parameters that are helpful in describing cyclic behavior, such as the maximum weight change, the number of cycles to reach the maximum weight gain or zero weight change, the ratio of these, and the final rate of weight loss. The program includes save and print options as well as a help file. Families of model curves readily show the sensitivity to various input parameters. The cyclic behaviors of nickel aluminide (NiAl) and a complex superalloy are shown to be properly fitted by model curves. However, caution is always advised regarding the uniqueness claimed for any specific set of input parameters,

Application of Classification Methods for Forecasting Mid-Term Power Load Patterns

NASA Astrophysics Data System (ADS)

Piao, Minghao; Lee, Heon Gyu; Park, Jin Hyoung; Ryu, Keun Ho

Currently an automated methodology based on data mining techniques is presented for the prediction of customer load patterns in long duration load profiles. The proposed approach in this paper consists of three stages: (i) data preprocessing: noise or outlier is removed and the continuous attribute-valued features are transformed to discrete values, (ii) cluster analysis: k-means clustering is used to create load pattern classes and the representative load profiles for each class and (iii) classification: we evaluated several supervised learning methods in order to select a suitable prediction method. According to the proposed methodology, power load measured from AMR (automatic meter reading) system, as well as customer indexes, were used as inputs for clustering. The output of clustering was the classification of representative load profiles (or classes). In order to evaluate the result of forecasting load patterns, the several classification methods were applied on a set of high voltage customers of the Korea power system and derived class labels from clustering and other features are used as input to produce classifiers. Lastly, the result of our experiments was presented.

A stock market forecasting model combining two-directional two-dimensional principal component analysis and radial basis function neural network.

PubMed

Guo, Zhiqiang; Wang, Huaiqing; Yang, Jie; Miller, David J

2015-01-01

In this paper, we propose and implement a hybrid model combining two-directional two-dimensional principal component analysis ((2D)2PCA) and a Radial Basis Function Neural Network (RBFNN) to forecast stock market behavior. First, 36 stock market technical variables are selected as the input features, and a sliding window is used to obtain the input data of the model. Next, (2D)2PCA is utilized to reduce the dimension of the data and extract its intrinsic features. Finally, an RBFNN accepts the data processed by (2D)2PCA to forecast the next day's stock price or movement. The proposed model is used on the Shanghai stock market index, and the experiments show that the model achieves a good level of fitness. The proposed model is then compared with one that uses the traditional dimension reduction method principal component analysis (PCA) and independent component analysis (ICA). The empirical results show that the proposed model outperforms the PCA-based model, as well as alternative models based on ICA and on the multilayer perceptron.

A Stock Market Forecasting Model Combining Two-Directional Two-Dimensional Principal Component Analysis and Radial Basis Function Neural Network

PubMed Central

Guo, Zhiqiang; Wang, Huaiqing; Yang, Jie; Miller, David J.

2015-01-01

In this paper, we propose and implement a hybrid model combining two-directional two-dimensional principal component analysis ((2D)2PCA) and a Radial Basis Function Neural Network (RBFNN) to forecast stock market behavior. First, 36 stock market technical variables are selected as the input features, and a sliding window is used to obtain the input data of the model. Next, (2D)2PCA is utilized to reduce the dimension of the data and extract its intrinsic features. Finally, an RBFNN accepts the data processed by (2D)2PCA to forecast the next day's stock price or movement. The proposed model is used on the Shanghai stock market index, and the experiments show that the model achieves a good level of fitness. The proposed model is then compared with one that uses the traditional dimension reduction method principal component analysis (PCA) and independent component analysis (ICA). The empirical results show that the proposed model outperforms the PCA-based model, as well as alternative models based on ICA and on the multilayer perceptron. PMID:25849483

Improving permafrost distribution modelling using feature selection algorithms

NASA Astrophysics Data System (ADS)

Deluigi, Nicola; Lambiel, Christophe; Kanevski, Mikhail

2016-04-01

The availability of an increasing number of spatial data on the occurrence of mountain permafrost allows the employment of machine learning (ML) classification algorithms for modelling the distribution of the phenomenon. One of the major problems when dealing with high-dimensional dataset is the number of input features (variables) involved. Application of ML classification algorithms to this large number of variables leads to the risk of overfitting, with the consequence of a poor generalization/prediction. For this reason, applying feature selection (FS) techniques helps simplifying the amount of factors required and improves the knowledge on adopted features and their relation with the studied phenomenon. Moreover, taking away irrelevant or redundant variables from the dataset effectively improves the quality of the ML prediction. This research deals with a comparative analysis of permafrost distribution models supported by FS variable importance assessment. The input dataset (dimension = 20-25, 10 m spatial resolution) was constructed using landcover maps, climate data and DEM derived variables (altitude, aspect, slope, terrain curvature, solar radiation, etc.). It was completed with permafrost evidences (geophysical and thermal data and rock glacier inventories) that serve as training permafrost data. Used FS algorithms informed about variables that appeared less statistically important for permafrost presence/absence. Three different algorithms were compared: Information Gain (IG), Correlation-based Feature Selection (CFS) and Random Forest (RF). IG is a filter technique that evaluates the worth of a predictor by measuring the information gain with respect to the permafrost presence/absence. Conversely, CFS is a wrapper technique that evaluates the worth of a subset of predictors by considering the individual predictive ability of each variable along with the degree of redundancy between them. Finally, RF is a ML algorithm that performs FS as part of its overall operation. It operates by constructing a large collection of decorrelated classification trees, and then predicts the permafrost occurrence through a majority vote. With the so-called out-of-bag (OOB) error estimate, the classification of permafrost data can be validated as well as the contribution of each predictor can be assessed. The performances of compared permafrost distribution models (computed on independent testing sets) increased with the application of FS algorithms on the original dataset and irrelevant or redundant variables were removed. As a consequence, the process provided faster and more cost-effective predictors and a better understanding of the underlying structures residing in permafrost data. Our work demonstrates the usefulness of a feature selection step prior to applying a machine learning algorithm. In fact, permafrost predictors could be ranked not only based on their heuristic and subjective importance (expert knowledge), but also based on their statistical relevance in relation of the permafrost distribution.

Linearly Additive Shape and Color Signals in Monkey Inferotemporal Cortex

PubMed Central

McMahon, David B. T.; Olson, Carl R.

2009-01-01

How does the brain represent a red circle? One possibility is that there is a specialized and possibly time-consuming process whereby the attributes of shape and color, carried by separate populations of neurons in low-order visual cortex, are bound together into a unitary neural representation. Another possibility is that neurons in high-order visual cortex are selective, by virtue of their bottom-up input from low-order visual areas, for particular conjunctions of shape and color. A third possibility is that they simply sum shape and color signals linearly. We tested these ideas by measuring the responses of inferotemporal cortex neurons to sets of stimuli in which two attributes—shape and color—varied independently. We find that a few neurons exhibit conjunction selectivity but that in most neurons the influences of shape and color sum linearly. Contrary to the idea of conjunction coding, few neurons respond selectively to a particular combination of shape and color. Contrary to the idea that binding requires time, conjunction signals, when present, occur as early as feature signals. We argue that neither conjunction selectivity nor a specialized feature binding process is necessary for the effective representation of shape–color combinations. PMID:19144745

Linearly additive shape and color signals in monkey inferotemporal cortex.

PubMed

McMahon, David B T; Olson, Carl R

2009-04-01

How does the brain represent a red circle? One possibility is that there is a specialized and possibly time-consuming process whereby the attributes of shape and color, carried by separate populations of neurons in low-order visual cortex, are bound together into a unitary neural representation. Another possibility is that neurons in high-order visual cortex are selective, by virtue of their bottom-up input from low-order visual areas, for particular conjunctions of shape and color. A third possibility is that they simply sum shape and color signals linearly. We tested these ideas by measuring the responses of inferotemporal cortex neurons to sets of stimuli in which two attributes-shape and color-varied independently. We find that a few neurons exhibit conjunction selectivity but that in most neurons the influences of shape and color sum linearly. Contrary to the idea of conjunction coding, few neurons respond selectively to a particular combination of shape and color. Contrary to the idea that binding requires time, conjunction signals, when present, occur as early as feature signals. We argue that neither conjunction selectivity nor a specialized feature binding process is necessary for the effective representation of shape-color combinations.

Volumetric data analysis using Morse-Smale complexes

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

Natarajan, V; Pascucci, V

2005-10-13

The 3D Morse-Smale complex is a fundamental topological construct that partitions the domain of a real-valued function into regions having uniform gradient flow behavior. In this paper, we consider the construction and selective presentation of cells of the Morse-Smale complex and their use in the analysis and visualization of scientific datasets. We take advantage of the fact that cells of different dimension often characterize different types of features present in the data. For example, critical points pinpoint changes in topology by showing where components of the level sets are created, destroyed or modified in genus. Edges of the Morse-Smale complexmore » extract filament-like features that are not explicitly modeled in the original data. Interactive selection and rendering of portions of the Morse-Smale complex introduces fundamental data management challenges due to the unstructured nature of the complex even for structured inputs. We describe a data structure that stores the Morse-Smale complex and allows efficient selective traversal of regions of interest. Finally, we illustrate the practical use of this approach by applying it to cryo-electron microscopy data of protein molecules.« less

Autonomous mental development with selective attention, object perception, and knowledge representation

NASA Astrophysics Data System (ADS)

Ban, Sang-Woo; Lee, Minho

2008-04-01

Knowledge-based clustering and autonomous mental development remains a high priority research topic, among which the learning techniques of neural networks are used to achieve optimal performance. In this paper, we present a new framework that can automatically generate a relevance map from sensory data that can represent knowledge regarding objects and infer new knowledge about novel objects. The proposed model is based on understating of the visual what pathway in our brain. A stereo saliency map model can selectively decide salient object areas by additionally considering local symmetry feature. The incremental object perception model makes clusters for the construction of an ontology map in the color and form domains in order to perceive an arbitrary object, which is implemented by the growing fuzzy topology adaptive resonant theory (GFTART) network. Log-polar transformed color and form features for a selected object are used as inputs of the GFTART. The clustered information is relevant to describe specific objects, and the proposed model can automatically infer an unknown object by using the learned information. Experimental results with real data have demonstrated the validity of this approach.

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

Kuo, J; Su, K; Department of Radiology, University Hospitals Case Medical Center, Case Western Reserve University, Cleveland, Ohio

Purpose: Accurate and robust photon attenuation derived from MR is essential for PET/MR and MR-based radiation treatment planning applications. Although the fuzzy C-means (FCM) algorithm has been applied for pseudo-CT generation, the input feature combination and the number of clusters have not been optimized. This study aims to optimize both for clinically practical pseudo-CT generation. Methods: Nine volunteers were recruited. A 190-second, single-acquisition UTE-mDixon with 25% (angular) sampling and 3D radial readout was performed to acquire three primitive MR features at TEs of 0.1, 1.5, and 2.8 ms: the free-induction-decay (FID), the first and the second echo images. Three derivedmore » images, Dixon-fat and Dixon-water generated by two-point Dixon water/fat separation, and R2* (1/T2*) map, were also created. To identify informative inputs for generating a pseudo-CT image volume, all 63 combinations, choosing one to six of the feature images, were used as inputs to FCM for pseudo-CT generation. Further, the number of clusters was varied from four to seven to find the optimal approach. Mean prediction deviation (MPD), mean absolute prediction deviation (MAPD), and correlation coefficient (R) of different combinations were compared for feature selection. Results: Among the 63 feature combinations, the four that resulted in the best MAPD and R were further compared along with the set containing all six features. The results suggested that R2* and Dixon-water are the most informative features. Further, including FID also improved the performance of pseudo-CT generation. Consequently, the set containing FID, Dixon-water, and R2* resulted in the most accurate, robust pseudo-CT when the number of cluster equals to five (5C). The clusters were interpreted as air, fat, bone, brain, and fluid. The six-cluster Result additionally included bone marrow. Conclusion: The results suggested that FID, Dixon-water, R2* are the most important features. The findings can be used to facilitate pseudo-CT generation for unsupervised clustering. Please note that the project was completed with partial funding from the Ohio Department of Development grant TECH 11-063 and a sponsored research agreement with Philips Healthcare that is managed by Case Western Reserve University. As noted in the affiliations, some of the authors are Philips employees.« less

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.

An EEG-based functional connectivity measure for automatic detection of alcohol use disorder.

PubMed

Mumtaz, Wajid; Saad, Mohamad Naufal B Mohamad; Kamel, Nidal; Ali, Syed Saad Azhar; Malik, Aamir Saeed

2018-01-01

The abnormal alcohol consumption could cause toxicity and could alter the human brain's structure and function, termed as alcohol used disorder (AUD). Unfortunately, the conventional screening methods for AUD patients are subjective and manual. Hence, to perform automatic screening of AUD patients, objective methods are needed. The electroencephalographic (EEG) data have been utilized to study the differences of brain signals between alcoholics and healthy controls that could further developed as an automatic screening tool for alcoholics. In this work, resting-state EEG-derived features were utilized as input data to the proposed feature selection and classification method. The aim was to perform automatic classification of AUD patients and healthy controls. The validation of the proposed method involved real-EEG data acquired from 30 AUD patients and 30 age-matched healthy controls. The resting-state EEG-derived features such as synchronization likelihood (SL) were computed involving 19 scalp locations resulted into 513 features. Furthermore, the features were rank-ordered to select the most discriminant features involving a rank-based feature selection method according to a criterion, i.e., receiver operating characteristics (ROC). Consequently, a reduced set of most discriminant features was identified and utilized further during classification of AUD patients and healthy controls. In this study, three different classification models such as Support Vector Machine (SVM), Naïve Bayesian (NB), and Logistic Regression (LR) were used. The study resulted into SVM classification accuracy=98%, sensitivity=99.9%, specificity=95%, and f-measure=0.97; LR classification accuracy=91.7%, sensitivity=86.66%, specificity=96.6%, and f-measure=0.90; NB classification accuracy=93.6%, sensitivity=100%, specificity=87.9%, and f-measure=0.95. The SL features could be utilized as objective markers to screen the AUD patients and healthy controls. Copyright © 2017 Elsevier B.V. All rights reserved.

The Face-Processing Network Is Resilient to Focal Resection of Human Visual Cortex.

PubMed

Weiner, Kevin S; Jonas, Jacques; Gomez, Jesse; Maillard, Louis; Brissart, Hélène; Hossu, Gabriela; Jacques, Corentin; Loftus, David; Colnat-Coulbois, Sophie; Stigliani, Anthony; Barnett, Michael A; Grill-Spector, Kalanit; Rossion, Bruno

2016-08-10

Human face perception requires a network of brain regions distributed throughout the occipital and temporal lobes with a right hemisphere advantage. Present theories consider this network as either a processing hierarchy beginning with the inferior occipital gyrus (occipital face area; IOG-faces/OFA) or a multiple-route network with nonhierarchical components. The former predicts that removing IOG-faces/OFA will detrimentally affect downstream stages, whereas the latter does not. We tested this prediction in a human patient (Patient S.P.) requiring removal of the right inferior occipital cortex, including IOG-faces/OFA. We acquired multiple fMRI measurements in Patient S.P. before and after a preplanned surgery and multiple measurements in typical controls, enabling both within-subject/across-session comparisons (Patient S.P. before resection vs Patient S.P. after resection) and between-subject/across-session comparisons (Patient S.P. vs controls). We found that the spatial topology and selectivity of downstream ipsilateral face-selective regions were stable 1 and 8 month(s) after surgery. Additionally, the reliability of distributed patterns of face selectivity in Patient S.P. before versus after resection was not different from across-session reliability in controls. Nevertheless, postoperatively, representations of visual space were typical in dorsal face-selective regions but atypical in ventral face-selective regions and V1 of the resected hemisphere. Diffusion weighted imaging in Patient S.P. and controls identifies white matter tracts connecting retinotopic areas to downstream face-selective regions, which may contribute to the stable and plastic features of the face network in Patient S.P. after surgery. Together, our results support a multiple-route network of face processing with nonhierarchical components and shed light on stable and plastic features of high-level visual cortex following focal brain damage. Brain networks consist of interconnected functional regions commonly organized in processing hierarchies. Prevailing theories predict that damage to the input of the hierarchy will detrimentally affect later stages. We tested this prediction with multiple brain measurements in a rare human patient requiring surgical removal of the putative input to a network processing faces. Surprisingly, the spatial topology and selectivity of downstream face-selective regions are stable after surgery. Nevertheless, representations of visual space were typical in dorsal face-selective regions but atypical in ventral face-selective regions and V1. White matter connections from outside the face network may support these stable and plastic features. As processing hierarchies are ubiquitous in biological and nonbiological systems, our results have pervasive implications for understanding the construction of resilient networks. Copyright © 2016 the authors 0270-6474/16/368426-16$15.00/0.

Blade Assessment for Ice Impact (BLASIM). User's manual, version 1.0

NASA Technical Reports Server (NTRS)

Reddy, E. S.; Abumeri, G. H.

1993-01-01

The Blade Assessment Ice Impact (BLASIM) computer code can analyze solid, hollow, composite, and super hybrid blades. The solid blade is made up of a single material where hollow, composite, and super hybrid blades are constructed with prescribed composite layup. The properties of a composite blade can be specified by inputting one of two options: (1) individual ply properties, or (2) fiber/matrix combinations. When the second option is selected, BLASIM utilizes ICAN (Integrated Composite ANalyzer) to generate the temperature/moisture dependent ply properties of the composite blade. Two types of geometry input can be given: airfoil coordinates or NASTRAN type finite element model. These features increase the flexibility of the program. The user's manual provides sample cases to facilitate efficient use of the code while gaining familiarity.

Heliocentric interplanetary low thrust trajectory optimization program, supplement 1, part 2

NASA Technical Reports Server (NTRS)

Mann, F. I.; Horsewood, J. L.

1978-01-01

The improvements made to the HILTOP electric propulsion trajectory computer program are described. A more realistic propulsion system model was implemented in which various thrust subsystem efficiencies and specific impulse are modeled as variable functions of power available to the propulsion system. The number of operating thrusters are staged, and the beam voltage is selected from a set of five (or less) constant voltages, based upon the application of variational calculus. The constant beam voltages may be optimized individually or collectively. The propulsion system logic is activated by a single program input key in such a manner as to preserve the HILTOP logic. An analysis describing these features, a complete description of program input quantities, and sample cases of computer output illustrating the program capabilities are presented.

Relevant, irredundant feature selection and noisy example elimination.

PubMed

Lashkia, George V; Anthony, Laurence

2004-04-01

In many real-world situations, the method for computing the desired output from a set of inputs is unknown. One strategy for solving these types of problems is to learn the input-output functionality from examples in a training set. However, in many situations it is difficult to know what information is relevant to the task at hand. Subsequently, researchers have investigated ways to deal with the so-called problem of consistency of attributes, i.e., attributes that can distinguish examples from different classes. In this paper, we first prove that the notion of relevance of attributes is directly related to the consistency of attributes, and show how relevant, irredundant attributes can be selected. We then compare different relevant attribute selection algorithms, and show the superiority of algorithms that select irredundant attributes over those that select relevant attributes. We also show that searching for an "optimal" subset of attributes, which is considered to be the main purpose of attribute selection, is not the best way to improve the accuracy of classifiers. Employing sets of relevant, irredundant attributes improves classification accuracy in many more cases. Finally, we propose a new method for selecting relevant examples, which is based on filtering the so-called pattern frequency domain. By identifying examples that are nontypical in the determination of relevant, irredundant attributes, irrelevant examples can be eliminated prior to the learning process. Empirical results using artificial and real databases show the effectiveness of the proposed method in selecting relevant examples leading to improved performance even on greatly reduced training sets.

The Construct of Attention in Schizophrenia

PubMed Central

Luck, Steven J.; Gold, James M.

2008-01-01

Schizophrenia is widely thought to involve deficits of attention. However, the term attention can be defined so broadly that impaired performance on virtually any task could be construed as evidence for a deficit in attention, and this has slowed cumulative progress in understanding attention deficits in schizophrenia. To address this problem, we divide the general concept of attention into two distinct constructs: input selection, the selection of task-relevant inputs for further processing; and rule selection, the selective activation of task-appropriate rules. These constructs are closely tied to working memory, because input selection mechanisms are used to control the transfer of information into working memory and because working memory stores the rules used by rule selection mechanisms. These constructs are also closely tied to executive function, because executive systems are used to guide input selection and because rule selection is itself at key aspect of executive function. Within the domain of input selection, it is important to distinguish between the control of selection—the processes that guide attention to task-relevant inputs—and the implementation of selection—the processes that enhance the processing of the relevant inputs and suppress the irrelevant inputs. Current evidence suggests that schizophrenia involves a significant impairment in the control of selection but little or no impairment in the implementation of selection. Consequently, the CNTRICS participants agreed by consensus that attentional control should be a priority target for measurement and treatment research in schizophrenia. PMID:18374901

Adaptive neuro-heuristic hybrid model for fruit peel defects detection.

PubMed

Woźniak, Marcin; Połap, Dawid

2018-02-01

Fusion of machine learning methods benefits in decision support systems. A composition of approaches gives a possibility to use the most efficient features composed into one solution. In this article we would like to present an approach to the development of adaptive method based on fusion of proposed novel neural architecture and heuristic search into one co-working solution. We propose a developed neural network architecture that adapts to processed input co-working with heuristic method used to precisely detect areas of interest. Input images are first decomposed into segments. This is to make processing easier, since in smaller images (decomposed segments) developed Adaptive Artificial Neural Network (AANN) processes less information what makes numerical calculations more precise. For each segment a descriptor vector is composed to be presented to the proposed AANN architecture. Evaluation is run adaptively, where the developed AANN adapts to inputs and their features by composed architecture. After evaluation, selected segments are forwarded to heuristic search, which detects areas of interest. As a result the system returns the image with pixels located over peel damages. Presented experimental research results on the developed solution are discussed and compared with other commonly used methods to validate the efficacy and the impact of the proposed fusion in the system structure and training process on classification results. Copyright © 2017 Elsevier Ltd. All rights reserved.

Monitoring the Depth of Anesthesia Using a New Adaptive Neurofuzzy System.

PubMed

Shalbaf, Ahmad; Saffar, Mohsen; Sleigh, Jamie W; Shalbaf, Reza

2018-05-01

Accurate and noninvasive monitoring of the depth of anesthesia (DoA) is highly desirable. Since the anesthetic drugs act mainly on the central nervous system, the analysis of brain activity using electroencephalogram (EEG) is very useful. This paper proposes a novel automated method for assessing the DoA using EEG. First, 11 features including spectral, fractal, and entropy are extracted from EEG signal and then, by applying an algorithm according to exhaustive search of all subsets of features, a combination of the best features (Beta-index, sample entropy, shannon permutation entropy, and detrended fluctuation analysis) is selected. Accordingly, we feed these extracted features to a new neurofuzzy classification algorithm, adaptive neurofuzzy inference system with linguistic hedges (ANFIS-LH). This structure can successfully model systems with nonlinear relationships between input and output, and also classify overlapped classes accurately. ANFIS-LH, which is based on modified classical fuzzy rules, reduces the effects of the insignificant features in input space, which causes overlapping and modifies the output layer structure. The presented method classifies EEG data into awake, light, general, and deep states during anesthesia with sevoflurane in 17 patients. Its accuracy is 92% compared to a commercial monitoring system (response entropy index) successfully. Moreover, this method reaches the classification accuracy of 93% to categorize EEG signal to awake and general anesthesia states by another database of propofol and volatile anesthesia in 50 patients. To sum up, this method is potentially applicable to a new real-time monitoring system to help the anesthesiologist with continuous assessment of DoA quickly and accurately.

Automated Detection of Epileptic Biomarkers in Resting-State Interictal MEG Data

PubMed Central

Soriano, Miguel C.; Niso, Guiomar; Clements, Jillian; Ortín, Silvia; Carrasco, Sira; Gudín, María; Mirasso, Claudio R.; Pereda, Ernesto

2017-01-01

Certain differences between brain networks of healthy and epilectic subjects have been reported even during the interictal activity, in which no epileptic seizures occur. Here, magnetoencephalography (MEG) data recorded in the resting state is used to discriminate between healthy subjects and patients with either idiopathic generalized epilepsy or frontal focal epilepsy. Signal features extracted from interictal periods without any epileptiform activity are used to train a machine learning algorithm to draw a diagnosis. This is potentially relevant to patients without frequent or easily detectable spikes. To analyze the data, we use an up-to-date machine learning algorithm and explore the benefits of including different features obtained from the MEG data as inputs to the algorithm. We find that the relative power spectral density of the MEG time-series is sufficient to distinguish between healthy and epileptic subjects with a high prediction accuracy. We also find that a combination of features such as the phase-locked value and the relative power spectral density allow to discriminate generalized and focal epilepsy, when these features are calculated over a filtered version of the signals in certain frequency bands. Machine learning algorithms are currently being applied to the analysis and classification of brain signals. It is, however, less evident to identify the proper features of these signals that are prone to be used in such machine learning algorithms. Here, we evaluate the influence of the input feature selection on a clinical scenario to distinguish between healthy and epileptic subjects. Our results indicate that such distinction is possible with a high accuracy (86%), allowing the discrimination between idiopathic generalized and frontal focal epilepsy types. PMID:28713260

Surprise! Infants consider possible bases of generalization for a single input example.

PubMed

Gerken, LouAnn; Dawson, Colin; Chatila, Razanne; Tenenbaum, Josh

2015-01-01

Infants have been shown to generalize from a small number of input examples. However, existing studies allow two possible means of generalization. One is via a process of noting similarities shared by several examples. Alternatively, generalization may reflect an implicit desire to explain the input. The latter view suggests that generalization might occur when even a single input example is surprising, given the learner's current model of the domain. To test the possibility that infants are able to generalize based on a single example, we familiarized 9-month-olds with a single three-syllable input example that contained either one surprising feature (syllable repetition, Experiment 1) or two features (repetition and a rare syllable, Experiment 2). In both experiments, infants generalized only to new strings that maintained all of the surprising features from familiarization. This research suggests that surprise can promote very rapid generalization. © 2014 John Wiley & Sons Ltd.

Systems and methods for predicting materials properties

DOEpatents

Ceder, Gerbrand; Fischer, Chris; Tibbetts, Kevin; Morgan, Dane; Curtarolo, Stefano

2007-11-06

Systems and methods for predicting features of materials of interest. Reference data are analyzed to deduce relationships between the input data sets and output data sets. Reference data includes measured values and/or computed values. The deduced relationships can be specified as equations, correspondences, and/or algorithmic processes that produce appropriate output data when suitable input data is used. In some instances, the output data set is a subset of the input data set, and computational results may be refined by optionally iterating the computational procedure. To deduce features of a new material of interest, a computed or measured input property of the material is provided to an equation, correspondence, or algorithmic procedure previously deduced, and an output is obtained. In some instances, the output is iteratively refined. In some instances, new features deduced for the material of interest are added to a database of input and output data for known materials.

A multiple-feature and multiple-kernel scene segmentation algorithm for humanoid robot.

PubMed

Liu, Zhi; Xu, Shuqiong; Zhang, Yun; Chen, Chun Lung Philip

2014-11-01

This technical correspondence presents a multiple-feature and multiple-kernel support vector machine (MFMK-SVM) methodology to achieve a more reliable and robust segmentation performance for humanoid robot. The pixel wise intensity, gradient, and C1 SMF features are extracted via the local homogeneity model and Gabor filter, which would be used as inputs of MFMK-SVM model. It may provide multiple features of the samples for easier implementation and efficient computation of MFMK-SVM model. A new clustering method, which is called feature validity-interval type-2 fuzzy C-means (FV-IT2FCM) clustering algorithm, is proposed by integrating a type-2 fuzzy criterion in the clustering optimization process to improve the robustness and reliability of clustering results by the iterative optimization. Furthermore, the clustering validity is employed to select the training samples for the learning of the MFMK-SVM model. The MFMK-SVM scene segmentation method is able to fully take advantage of the multiple features of scene image and the ability of multiple kernels. Experiments on the BSDS dataset and real natural scene images demonstrate the superior performance of our proposed method.

Input variable selection and calibration data selection for storm water quality regression models.

PubMed

Sun, Siao; Bertrand-Krajewski, Jean-Luc

2013-01-01

Storm water quality models are useful tools in storm water management. Interest has been growing in analyzing existing data for developing models for urban storm water quality evaluations. It is important to select appropriate model inputs when many candidate explanatory variables are available. Model calibration and verification are essential steps in any storm water quality modeling. This study investigates input variable selection and calibration data selection in storm water quality regression models. The two selection problems are mutually interacted. A procedure is developed in order to fulfil the two selection tasks in order. The procedure firstly selects model input variables using a cross validation method. An appropriate number of variables are identified as model inputs to ensure that a model is neither overfitted nor underfitted. Based on the model input selection results, calibration data selection is studied. Uncertainty of model performances due to calibration data selection is investigated with a random selection method. An approach using the cluster method is applied in order to enhance model calibration practice based on the principle of selecting representative data for calibration. The comparison between results from the cluster selection method and random selection shows that the former can significantly improve performances of calibrated models. It is found that the information content in calibration data is important in addition to the size of calibration data.

The Performance of Short-Term Heart Rate Variability in the Detection of Congestive Heart Failure

PubMed Central

Barros, Allan Kardec; Ohnishi, Noboru

2016-01-01

Congestive heart failure (CHF) is a cardiac disease associated with the decreasing capacity of the cardiac output. It has been shown that the CHF is the main cause of the cardiac death around the world. Some works proposed to discriminate CHF subjects from healthy subjects using either electrocardiogram (ECG) or heart rate variability (HRV) from long-term recordings. In this work, we propose an alternative framework to discriminate CHF from healthy subjects by using HRV short-term intervals based on 256 RR continuous samples. Our framework uses a matching pursuit algorithm based on Gabor functions. From the selected Gabor functions, we derived a set of features that are inputted into a hybrid framework which uses a genetic algorithm and k-nearest neighbour classifier to select a subset of features that has the best classification performance. The performance of the framework is analyzed using both Fantasia and CHF database from Physionet archives which are, respectively, composed of 40 healthy volunteers and 29 subjects. From a set of nonstandard 16 features, the proposed framework reaches an overall accuracy of 100% with five features. Our results suggest that the application of hybrid frameworks whose classifier algorithms are based on genetic algorithms has outperformed well-known classifier methods. PMID:27891509

Genetic algorithm based input selection for a neural network function approximator with applications to SSME health monitoring

NASA Technical Reports Server (NTRS)

Peck, Charles C.; Dhawan, Atam P.; Meyer, Claudia M.

1991-01-01

A genetic algorithm is used to select the inputs to a neural network function approximator. In the application considered, modeling critical parameters of the space shuttle main engine (SSME), the functional relationship between measured parameters is unknown and complex. Furthermore, the number of possible input parameters is quite large. Many approaches have been used for input selection, but they are either subjective or do not consider the complex multivariate relationships between parameters. Due to the optimization and space searching capabilities of genetic algorithms they were employed to systematize the input selection process. The results suggest that the genetic algorithm can generate parameter lists of high quality without the explicit use of problem domain knowledge. Suggestions for improving the performance of the input selection process are also provided.

Ventricular Fibrillation and Tachycardia detection from surface ECG using time-frequency representation images as input dataset for machine learning.

PubMed

Mjahad, A; Rosado-Muñoz, A; Bataller-Mompeán, M; Francés-Víllora, J V; Guerrero-Martínez, J F

2017-04-01

To safely select the proper therapy for Ventricullar Fibrillation (VF) is essential to distinct it correctly from Ventricular Tachycardia (VT) and other rhythms. Provided that the required therapy would not be the same, an erroneous detection might lead to serious injuries to the patient or even cause Ventricular Fibrillation (VF). The main novelty of this paper is the use of time-frequency (t-f) representation images as the direct input to the classifier. We hypothesize that this method allow to improve classification results as it allows to eliminate the typical feature selection and extraction stage, and its corresponding loss of information. The standard AHA and MIT-BIH databases were used for evaluation and comparison with other authors. Previous to t-f Pseudo Wigner-Ville (PWV) calculation, only a basic preprocessing for denoising and signal alignment is necessary. In order to check the validity of the method independently of the classifier, four different classifiers are used: Logistic Regression with L2 Regularization (L2 RLR), Adaptive Neural Network Classifier (ANNC), Support Vector Machine (SSVM), and Bagging classifier (BAGG). The main classification results for VF detection (including flutter episodes) are 95.56% sensitivity and 98.8% specificity, 88.80% sensitivity and 99.5% specificity for ventricular tachycardia (VT), 98.98% sensitivity and 97.7% specificity for normal sinus, and 96.87% sensitivity and 99.55% specificity for other rhythms. Results shows that using t-f data representations to feed classifiers provide superior performance values than the feature selection strategies used in previous works. It opens the door to be used in any other detection applications. Copyright © 2017 Elsevier B.V. All rights reserved.

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.

Method to assess the temporal persistence of potential biometric features: Application to oculomotor, gait, face and brain structure databases

PubMed Central

Nixon, Mark S.; Komogortsev, Oleg V.

2017-01-01

We introduce the intraclass correlation coefficient (ICC) to the biometric community as an index of the temporal persistence, or stability, of a single biometric feature. It requires, as input, a feature on an interval or ratio scale, and which is reasonably normally distributed, and it can only be calculated if each subject is tested on 2 or more occasions. For a biometric system, with multiple features available for selection, the ICC can be used to measure the relative stability of each feature. We show, for 14 distinct data sets (1 synthetic, 8 eye-movement-related, 2 gait-related, and 2 face-recognition-related, and one brain-structure-related), that selecting the most stable features, based on the ICC, resulted in the best biometric performance generally. Analyses based on using only the most stable features produced superior Rank-1-Identification Rate (Rank-1-IR) performance in 12 of 14 databases (p = 0.0065, one-tailed), when compared to other sets of features, including the set of all features. For Equal Error Rate (EER), using a subset of only high-ICC features also produced superior performance in 12 of 14 databases (p = 0. 0065, one-tailed). In general, then, for our databases, prescreening potential biometric features, and choosing only highly reliable features yields better performance than choosing lower ICC features or than choosing all features combined. We also determined that, as the ICC of a group of features increases, the median of the genuine similarity score distribution increases and the spread of this distribution decreases. There was no statistically significant similar relationships for the impostor distributions. We believe that the ICC will find many uses in biometric research. In case of the eye movement-driven biometrics, the use of reliable features, as measured by ICC, allowed to us achieve the authentication performance with EER = 2.01%, which was not possible before. PMID:28575030

Method to assess the temporal persistence of potential biometric features: Application to oculomotor, gait, face and brain structure databases.

PubMed

Friedman, Lee; Nixon, Mark S; Komogortsev, Oleg V

2017-01-01

We introduce the intraclass correlation coefficient (ICC) to the biometric community as an index of the temporal persistence, or stability, of a single biometric feature. It requires, as input, a feature on an interval or ratio scale, and which is reasonably normally distributed, and it can only be calculated if each subject is tested on 2 or more occasions. For a biometric system, with multiple features available for selection, the ICC can be used to measure the relative stability of each feature. We show, for 14 distinct data sets (1 synthetic, 8 eye-movement-related, 2 gait-related, and 2 face-recognition-related, and one brain-structure-related), that selecting the most stable features, based on the ICC, resulted in the best biometric performance generally. Analyses based on using only the most stable features produced superior Rank-1-Identification Rate (Rank-1-IR) performance in 12 of 14 databases (p = 0.0065, one-tailed), when compared to other sets of features, including the set of all features. For Equal Error Rate (EER), using a subset of only high-ICC features also produced superior performance in 12 of 14 databases (p = 0. 0065, one-tailed). In general, then, for our databases, prescreening potential biometric features, and choosing only highly reliable features yields better performance than choosing lower ICC features or than choosing all features combined. We also determined that, as the ICC of a group of features increases, the median of the genuine similarity score distribution increases and the spread of this distribution decreases. There was no statistically significant similar relationships for the impostor distributions. We believe that the ICC will find many uses in biometric research. In case of the eye movement-driven biometrics, the use of reliable features, as measured by ICC, allowed to us achieve the authentication performance with EER = 2.01%, which was not possible before.

PSSP-RFE: accurate prediction of protein structural class by recursive feature extraction from PSI-BLAST profile, physical-chemical property and functional annotations.

PubMed

Li, Liqi; Cui, Xiang; Yu, Sanjiu; Zhang, Yuan; Luo, Zhong; Yang, Hua; Zhou, Yue; Zheng, Xiaoqi

2014-01-01

Protein structure prediction is critical to functional annotation of the massively accumulated biological sequences, which prompts an imperative need for the development of high-throughput technologies. As a first and key step in protein structure prediction, protein structural class prediction becomes an increasingly challenging task. Amongst most homological-based approaches, the accuracies of protein structural class prediction are sufficiently high for high similarity datasets, but still far from being satisfactory for low similarity datasets, i.e., below 40% in pairwise sequence similarity. Therefore, we present a novel method for accurate and reliable protein structural class prediction for both high and low similarity datasets. This method is based on Support Vector Machine (SVM) in conjunction with integrated features from position-specific score matrix (PSSM), PROFEAT and Gene Ontology (GO). A feature selection approach, SVM-RFE, is also used to rank the integrated feature vectors through recursively removing the feature with the lowest ranking score. The definitive top features selected by SVM-RFE are input into the SVM engines to predict the structural class of a query protein. To validate our method, jackknife tests were applied to seven widely used benchmark datasets, reaching overall accuracies between 84.61% and 99.79%, which are significantly higher than those achieved by state-of-the-art tools. These results suggest that our method could serve as an accurate and cost-effective alternative to existing methods in protein structural classification, especially for low similarity datasets.

Prediction of beta-turns at over 80% accuracy based on an ensemble of predicted secondary structures and multiple alignments.

PubMed

Zheng, Ce; Kurgan, Lukasz

2008-10-10

beta-turn is a secondary protein structure type that plays significant role in protein folding, stability, and molecular recognition. To date, several methods for prediction of beta-turns from protein sequences were developed, but they are characterized by relatively poor prediction quality. The novelty of the proposed sequence-based beta-turn predictor stems from the usage of a window based information extracted from four predicted three-state secondary structures, which together with a selected set of position specific scoring matrix (PSSM) values serve as an input to the support vector machine (SVM) predictor. We show that (1) all four predicted secondary structures are useful; (2) the most useful information extracted from the predicted secondary structure includes the structure of the predicted residue, secondary structure content in a window around the predicted residue, and features that indicate whether the predicted residue is inside a secondary structure segment; (3) the PSSM values of Asn, Asp, Gly, Ile, Leu, Met, Pro, and Val were among the top ranked features, which corroborates with recent studies. The Asn, Asp, Gly, and Pro indicate potential beta-turns, while the remaining four amino acids are useful to predict non-beta-turns. Empirical evaluation using three nonredundant datasets shows favorable Q total, Q predicted and MCC values when compared with over a dozen of modern competing methods. Our method is the first to break the 80% Q total barrier and achieves Q total = 80.9%, MCC = 0.47, and Q predicted higher by over 6% when compared with the second best method. We use feature selection to reduce the dimensionality of the feature vector used as the input for the proposed prediction method. The applied feature set is smaller by 86, 62 and 37% when compared with the second and two third-best (with respect to MCC) competing methods, respectively. Experiments show that the proposed method constitutes an improvement over the competing prediction methods. The proposed prediction model can better discriminate between beta-turns and non-beta-turns due to obtaining lower numbers of false positive predictions. The prediction model and datasets are freely available at http://biomine.ece.ualberta.ca/BTNpred/BTNpred.html.

Prediction of beta-turns at over 80% accuracy based on an ensemble of predicted secondary structures and multiple alignments

PubMed Central

Zheng, Ce; Kurgan, Lukasz

2008-01-01

Background β-turn is a secondary protein structure type that plays significant role in protein folding, stability, and molecular recognition. To date, several methods for prediction of β-turns from protein sequences were developed, but they are characterized by relatively poor prediction quality. The novelty of the proposed sequence-based β-turn predictor stems from the usage of a window based information extracted from four predicted three-state secondary structures, which together with a selected set of position specific scoring matrix (PSSM) values serve as an input to the support vector machine (SVM) predictor. Results We show that (1) all four predicted secondary structures are useful; (2) the most useful information extracted from the predicted secondary structure includes the structure of the predicted residue, secondary structure content in a window around the predicted residue, and features that indicate whether the predicted residue is inside a secondary structure segment; (3) the PSSM values of Asn, Asp, Gly, Ile, Leu, Met, Pro, and Val were among the top ranked features, which corroborates with recent studies. The Asn, Asp, Gly, and Pro indicate potential β-turns, while the remaining four amino acids are useful to predict non-β-turns. Empirical evaluation using three nonredundant datasets shows favorable Qtotal, Qpredicted and MCC values when compared with over a dozen of modern competing methods. Our method is the first to break the 80% Qtotal barrier and achieves Qtotal = 80.9%, MCC = 0.47, and Qpredicted higher by over 6% when compared with the second best method. We use feature selection to reduce the dimensionality of the feature vector used as the input for the proposed prediction method. The applied feature set is smaller by 86, 62 and 37% when compared with the second and two third-best (with respect to MCC) competing methods, respectively. Conclusion Experiments show that the proposed method constitutes an improvement over the competing prediction methods. The proposed prediction model can better discriminate between β-turns and non-β-turns due to obtaining lower numbers of false positive predictions. The prediction model and datasets are freely available at . PMID:18847492

Uncovering Spatial Variation in Acoustic Environments Using Sound Mapping.

PubMed

Job, Jacob R; Myers, Kyle; Naghshineh, Koorosh; Gill, Sharon A

2016-01-01

Animals select and use habitats based on environmental features relevant to their ecology and behavior. For animals that use acoustic communication, the sound environment itself may be a critical feature, yet acoustic characteristics are not commonly measured when describing habitats and as a result, how habitats vary acoustically over space and time is poorly known. Such considerations are timely, given worldwide increases in anthropogenic noise combined with rapidly accumulating evidence that noise hampers the ability of animals to detect and interpret natural sounds. Here, we used microphone arrays to record the sound environment in three terrestrial habitats (forest, prairie, and urban) under ambient conditions and during experimental noise introductions. We mapped sound pressure levels (SPLs) over spatial scales relevant to diverse taxa to explore spatial variation in acoustic habitats and to evaluate the number of microphones needed within arrays to capture this variation under both ambient and noisy conditions. Even at small spatial scales and over relatively short time spans, SPLs varied considerably, especially in forest and urban habitats, suggesting that quantifying and mapping acoustic features could improve habitat descriptions. Subset maps based on input from 4, 8, 12 and 16 microphones differed slightly (< 2 dBA/pixel) from those based on full arrays of 24 microphones under ambient conditions across habitats. Map differences were more pronounced with noise introductions, particularly in forests; maps made from only 4-microphones differed more (> 4 dBA/pixel) from full maps than the remaining subset maps, but maps with input from eight microphones resulted in smaller differences. Thus, acoustic environments varied over small spatial scales and variation could be mapped with input from 4-8 microphones. Mapping sound in different environments will improve understanding of acoustic environments and allow us to explore the influence of spatial variation in sound on animal ecology and behavior.

Deep Learning for Population Genetic Inference.

PubMed

Sheehan, Sara; Song, Yun S

2016-03-01

Given genomic variation data from multiple individuals, computing the likelihood of complex population genetic models is often infeasible. To circumvent this problem, we introduce a novel likelihood-free inference framework by applying deep learning, a powerful modern technique in machine learning. Deep learning makes use of multilayer neural networks to learn a feature-based function from the input (e.g., hundreds of correlated summary statistics of data) to the output (e.g., population genetic parameters of interest). We demonstrate that deep learning can be effectively employed for population genetic inference and learning informative features of data. As a concrete application, we focus on the challenging problem of jointly inferring natural selection and demography (in the form of a population size change history). Our method is able to separate the global nature of demography from the local nature of selection, without sequential steps for these two factors. Studying demography and selection jointly is motivated by Drosophila, where pervasive selection confounds demographic analysis. We apply our method to 197 African Drosophila melanogaster genomes from Zambia to infer both their overall demography, and regions of their genome under selection. We find many regions of the genome that have experienced hard sweeps, and fewer under selection on standing variation (soft sweep) or balancing selection. Interestingly, we find that soft sweeps and balancing selection occur more frequently closer to the centromere of each chromosome. In addition, our demographic inference suggests that previously estimated bottlenecks for African Drosophila melanogaster are too extreme.

Deep Learning for Population Genetic Inference

PubMed Central

Sheehan, Sara; Song, Yun S.

2016-01-01

Given genomic variation data from multiple individuals, computing the likelihood of complex population genetic models is often infeasible. To circumvent this problem, we introduce a novel likelihood-free inference framework by applying deep learning, a powerful modern technique in machine learning. Deep learning makes use of multilayer neural networks to learn a feature-based function from the input (e.g., hundreds of correlated summary statistics of data) to the output (e.g., population genetic parameters of interest). We demonstrate that deep learning can be effectively employed for population genetic inference and learning informative features of data. As a concrete application, we focus on the challenging problem of jointly inferring natural selection and demography (in the form of a population size change history). Our method is able to separate the global nature of demography from the local nature of selection, without sequential steps for these two factors. Studying demography and selection jointly is motivated by Drosophila, where pervasive selection confounds demographic analysis. We apply our method to 197 African Drosophila melanogaster genomes from Zambia to infer both their overall demography, and regions of their genome under selection. We find many regions of the genome that have experienced hard sweeps, and fewer under selection on standing variation (soft sweep) or balancing selection. Interestingly, we find that soft sweeps and balancing selection occur more frequently closer to the centromere of each chromosome. In addition, our demographic inference suggests that previously estimated bottlenecks for African Drosophila melanogaster are too extreme. PMID:27018908

Artificial Neural Network and Genetic Algorithm Hybrid Intelligence for Predicting Thai Stock Price Index Trend

PubMed Central

Boonjing, Veera; Intakosum, Sarun

2016-01-01

This study investigated the use of Artificial Neural Network (ANN) and Genetic Algorithm (GA) for prediction of Thailand's SET50 index trend. ANN is a widely accepted machine learning method that uses past data to predict future trend, while GA is an algorithm that can find better subsets of input variables for importing into ANN, hence enabling more accurate prediction by its efficient feature selection. The imported data were chosen technical indicators highly regarded by stock analysts, each represented by 4 input variables that were based on past time spans of 4 different lengths: 3-, 5-, 10-, and 15-day spans before the day of prediction. This import undertaking generated a big set of diverse input variables with an exponentially higher number of possible subsets that GA culled down to a manageable number of more effective ones. SET50 index data of the past 6 years, from 2009 to 2014, were used to evaluate this hybrid intelligence prediction accuracy, and the hybrid's prediction results were found to be more accurate than those made by a method using only one input variable for one fixed length of past time span. PMID:27974883

Artificial Neural Network and Genetic Algorithm Hybrid Intelligence for Predicting Thai Stock Price Index Trend.

PubMed

Inthachot, Montri; Boonjing, Veera; Intakosum, Sarun

2016-01-01

This study investigated the use of Artificial Neural Network (ANN) and Genetic Algorithm (GA) for prediction of Thailand's SET50 index trend. ANN is a widely accepted machine learning method that uses past data to predict future trend, while GA is an algorithm that can find better subsets of input variables for importing into ANN, hence enabling more accurate prediction by its efficient feature selection. The imported data were chosen technical indicators highly regarded by stock analysts, each represented by 4 input variables that were based on past time spans of 4 different lengths: 3-, 5-, 10-, and 15-day spans before the day of prediction. This import undertaking generated a big set of diverse input variables with an exponentially higher number of possible subsets that GA culled down to a manageable number of more effective ones. SET50 index data of the past 6 years, from 2009 to 2014, were used to evaluate this hybrid intelligence prediction accuracy, and the hybrid's prediction results were found to be more accurate than those made by a method using only one input variable for one fixed length of past time span.

Orientation selectivity sharpens motion detection in Drosophila

PubMed Central

Fisher, Yvette E.; Silies, Marion; Clandinin, Thomas R.

2015-01-01

SUMMARY Detecting the orientation and movement of edges in a scene is critical to visually guided behaviors of many animals. What are the circuit algorithms that allow the brain to extract such behaviorally vital visual cues? Using in vivo two-photon calcium imaging in Drosophila, we describe direction selective signals in the dendrites of T4 and T5 neurons, detectors of local motion. We demonstrate that this circuit performs selective amplification of local light inputs, an observation that constrains motion detection models and confirms a core prediction of the Hassenstein-Reichardt Correlator (HRC). These neurons are also orientation selective, responding strongly to static features that are orthogonal to their preferred axis of motion, a tuning property not predicted by the HRC. This coincident extraction of orientation and direction sharpens directional tuning through surround inhibition and reveals a striking parallel between visual processing in flies and vertebrate cortex, suggesting a universal strategy for motion processing. PMID:26456048

Revised Multi-Node Well (MNW2) Package for MODFLOW Ground-Water Flow Model

USGS Publications Warehouse

Konikow, Leonard F.; Hornberger, George Z.; Halford, Keith J.; Hanson, Randall T.; Harbaugh, Arlen W.

2009-01-01

Wells that are open to multiple aquifers can provide preferential pathways to flow and solute transport that short-circuit normal fluid flowlines. Representing these features in a regional flow model can produce a more realistic and reliable simulation model. This report describes modifications to the Multi-Node Well (MNW) Package of the U.S. Geological Survey (USGS) three-dimensional ground-water flow model (MODFLOW). The modifications build on a previous version and add several new features, processes, and input and output options. The input structure of the revised MNW (MNW2) is more well-centered than the original verion of MNW (MNW1) and allows the user to easily define hydraulic characteristics of each multi-node well. MNW2 also allows calculations of additional head changes due to partial penetration effects, flow into a borehole through a seepage face, changes in well discharge related to changes in lift for a given pump, and intraborehole flows with a pump intake located at any specified depth within the well. MNW2 also offers an improved capability to simulate nonvertical wells. A new output option allows selected multi-node wells to be designated as 'observation wells' for which changes in selected variables with time will be written to separate output files to facilitate postprocessing. MNW2 is compatible with the MODFLOW-2000 and MODFLOW-2005 versions of MODFLOW and with the version of MODFLOW that includes the Ground-Water Transport process (MODFLOW-GWT).

Conjunction of wavelet transform and SOM-mutual information data pre-processing approach for AI-based Multi-Station nitrate modeling of watersheds

NASA Astrophysics Data System (ADS)

Nourani, Vahid; Andalib, Gholamreza; Dąbrowska, Dominika

2017-05-01

Accurate nitrate load predictions can elevate decision management of water quality of watersheds which affects to environment and drinking water. In this paper, two scenarios were considered for Multi-Station (MS) nitrate load modeling of the Little River watershed. In the first scenario, Markovian characteristics of streamflow-nitrate time series were proposed for the MS modeling. For this purpose, feature extraction criterion of Mutual Information (MI) was employed for input selection of artificial intelligence models (Feed Forward Neural Network, FFNN and least square support vector machine). In the second scenario for considering seasonality-based characteristics of the time series, wavelet transform was used to extract multi-scale features of streamflow-nitrate time series of the watershed's sub-basins to model MS nitrate loads. Self-Organizing Map (SOM) clustering technique which finds homogeneous sub-series clusters was also linked to MI for proper cluster agent choice to be imposed into the models for predicting the nitrate loads of the watershed's sub-basins. The proposed MS method not only considers the prediction of the outlet nitrate but also covers predictions of interior sub-basins nitrate load values. The results indicated that the proposed FFNN model coupled with the SOM-MI improved the performance of MS nitrate predictions compared to the Markovian-based models up to 39%. Overall, accurate selection of dominant inputs which consider seasonality-based characteristics of streamflow-nitrate process could enhance the efficiency of nitrate load predictions.

An Extended Normalization Model of Attention Accounts for Feature-Based Attentional Enhancement of Both Response and Coherence Gain

PubMed Central

Krishna, B. Suresh; Treue, Stefan

2016-01-01

Paying attention to a sensory feature improves its perception and impairs that of others. Recent work has shown that a Normalization Model of Attention (NMoA) can account for a wide range of physiological findings and the influence of different attentional manipulations on visual performance. A key prediction of the NMoA is that attention to a visual feature like an orientation or a motion direction will increase the response of neurons preferring the attended feature (response gain) rather than increase the sensory input strength of the attended stimulus (input gain). This effect of feature-based attention on neuronal responses should translate to similar patterns of improvement in behavioral performance, with psychometric functions showing response gain rather than input gain when attention is directed to the task-relevant feature. In contrast, we report here that when human subjects are cued to attend to one of two motion directions in a transparent motion display, attentional effects manifest as a combination of input and response gain. Further, the impact on input gain is greater when attention is directed towards a narrow range of motion directions than when it is directed towards a broad range. These results are captured by an extended NMoA, which either includes a stimulus-independent attentional contribution to normalization or utilizes direction-tuned normalization. The proposed extensions are consistent with the feature-similarity gain model of attention and the attentional modulation in extrastriate area MT, where neuronal responses are enhanced and suppressed by attention to preferred and non-preferred motion directions respectively. PMID:27977679

Contribution of intrinsic properties and synaptic inputs to motoneuron discharge patterns: a simulation study

PubMed Central

ElBasiouny, Sherif M.; Rymer, W. Zev; Heckman, C. J.

2012-01-01

Motoneuron discharge patterns reflect the interaction of synaptic inputs with intrinsic conductances. Recent work has focused on the contribution of conductances mediating persistent inward currents (PICs), which amplify and prolong the effects of synaptic inputs on motoneuron discharge. Certain features of human motor unit discharge are thought to reflect a relatively stereotyped activation of PICs by excitatory synaptic inputs; these features include rate saturation and de-recruitment at a lower level of net excitation than that required for recruitment. However, PIC activation is also influenced by the pattern and spatial distribution of inhibitory inputs that are activated concurrently with excitatory inputs. To estimate the potential contributions of PIC activation and synaptic input patterns to motor unit discharge patterns, we examined the responses of a set of cable motoneuron models to different patterns of excitatory and inhibitory inputs. The models were first tuned to approximate the current- and voltage-clamp responses of low- and medium-threshold spinal motoneurons studied in decerebrate cats and then driven with different patterns of excitatory and inhibitory inputs. The responses of the models to excitatory inputs reproduced a number of features of human motor unit discharge. However, the pattern of rate modulation was strongly influenced by the temporal and spatial pattern of concurrent inhibitory inputs. Thus, even though PIC activation is likely to exert a strong influence on firing rate modulation, PIC activation in combination with different patterns of excitatory and inhibitory synaptic inputs can produce a wide variety of motor unit discharge patterns. PMID:22031773

The challenge of non-invasive cognitive physiology of the human brain: how to negotiate the irrelevant background noise without spoiling the recorded data through electronic averaging.

PubMed

Tomberg, C; Desmedt, J E

1999-07-29

Brain mechanisms involved in selective attention in humans can be studied by measures of regional blood flow and metabolism (by positron emission tomography) which help identify the various locations with enhanced activities over a period of time of seconds. The physiological measures provided by scalp-recorded brain electrical potentials have a better resolution (milliseconds) and can reveal the actual sequences of distinct neural events and their precise timing. We studied selective attention to sensory inputs from fingers because the brain somatic representations are deployed over the brain convexity under the scalp thereby making it possible to assess distinct stages of cortical processing and representation through their characteristic scalp topographies. In the electrical response to a finger input attended by the subject, the well-known P300 manifests a widespread inhibitory mechanism which is released after a target stimulus has been identified. P300 is preceded by distinct cognitive electrogeneses such as P40, P100 and N140 which can be differentiated from the control (obligatory) profile by superimposition or electronic subtraction. The first cortical response N20 is stable across conditions, suggesting that the first afferent thalamocortical volley is not affected by selective attention. At the next stage of modality-specific cortex in which the sensory features are processed and represented, responses were enhanced (cognitive P40) only a very few milliseconds after arrival of the afferent volley at the cortex, thus documenting a remarkable precocity of attention gain control in the somatic modality. The physiology of selective attention also provides useful cues in relation to non-target inputs which the subject must differentiate in order to perform the task. When having to tell fingers apart, the brain strategy for non-target fingers is not to inhibit or filter them out, but rather to submit their input to several processing operations that are actually enhanced when the discrimination from targets becomes more difficult. While resolving a number of such issues, averaged data cannot disclose the flexibility of brain mechanisms nor the detailed features of cognitive electrogeneses because response variations along time have been ironed out by the bulk treatment. We attempted to address the remarkable versatility of humans in dealing with their sensory environment under ecological conditions by studying single non-averaged responses. We identified distinct cognitive P40, P100, N140 and P300 electrogeneses in spite of the noise by numerically assessing their characteristic scalp topography signatures. Single-trial data suggest reconsiderations of current psychophysiological issues. The study of non-averaged responses can clarify issues raised by averaging studies as illustrated by our recent study of cognitive brain potentials for finger stimuli which remain outside the subject's awareness. This has to do with the physiological basis of the 'cognitive unconscious', that is, current mental processes lying on the fringe or outside of phenomenal awareness and voluntary control, but which can influence ongoing behaviour. Averaged data suggest that, in selective auditory attention, the subject may not notice mild concomitant finger inputs. The study of non-averaged responses documents the optional and independent occurrence of the cognitive P40, P100 and N140 (but not P300) electrogeneses while the finger inputs remain outside phenomenal awareness. These results suggest that the subject unconsciously assigns limited cognitive resources to distinct somatic cortical areas thereby submitting finger inputs to an intermittent curtailed surveillance which can remain on the fringe or outside consciousness. The study of cognitive electrogeneses in single non-averaged responses is making possible a neurophysiology of cognition in real time.

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.

Systematic review of the information and communication technology features of web- and mobile-based psychoeducational interventions for depression.

PubMed

Zhao, Danyang; Lustria, Mia Liza A; Hendrickse, Joshua

2017-06-01

To examine the information and communication technology (ICT) features of psychoeducational interventions for depression delivered via the Internet or via mobile technology. Web- and mobile-based psychoeducational intervention studies published from 2004 to 2014 were selected and reviewed by two independent coders. A total of 55 unique studies satisfied the selection criteria. The review revealed a diverse range of ICTs used to support the psychoeducational programs. Most interventions used websites as their main mode of delivery and reported greater use of communication tools compared to effective approaches like tailoring or interactive technologies games, videos, and self-monitoring tools. Many of the studies relied on medium levels of clinician involvement and only a few were entirely self-guided. Programs that reported higher levels of clinician involvement also reported using more communication tools, and reported greater compliance to treatment. Future experimental studies may help unpack the effects of technology features and reveal new ways to automate aspects of clinician input. There is a need to further examine ways ICTs can be optimized to reduce the burden on clinicians whilst enhancing the delivery of proven effective therapeutic approaches. Copyright © 2017 Elsevier B.V. All rights reserved.

From attentional gating in macaque primary visual cortex to dyslexia in humans.

PubMed

Vidyasagar, T R

2001-01-01

Selective attention is an important aspect of brain function that we need in coping with the immense and constant barrage of sensory information. One model of attention (Feature Integration Theory) that suggests an early selection of spatial locations of objects via an attentional spotlight would also solve the 'binding problem' (that is how do different attributes of each object get correctly bound together?). Our experiments have demonstrated modulation of specific locations of interest at the level of the primary visual cortex both in visual discrimination and memory tasks, where the actual locations of the targets was also important in being able to perform the task. It is suggested that the feedback mediating the modulation arises from the posterior parietal cortex, which would also be consistent with its known role in attentional control. In primates, the magnocellular (M) and parvocellular (P) pathways are the two major streams of inputs from the retina, carrying distinctly different types of information and they remain fairly segregated in their projections to the primary visual cortex and further into the extra-striate regions. The P inputs go mainly into the ventral (temporal) stream, while the dorsal (parietal) stream is dominated by M inputs. A theory of attentional gating is proposed here where the M dominated dorsal stream gates the P inputs into the ventral stream. This framework is used to provide a neural explanation of the processes involved in reading and in learning to read. This scheme also explains how a magnocellular deficit could cause the common reading impairment, dyslexia.

Scene segmentation of natural images using texture measures and back-propagation

NASA Technical Reports Server (NTRS)

Sridhar, Banavar; Phatak, Anil; Chatterji, Gano

1993-01-01

Knowledge of the three-dimensional world is essential for many guidance and navigation applications. A sequence of images from an electro-optical sensor can be processed using optical flow algorithms to provide a sparse set of ranges as a function of azimuth and elevation. A natural way to enhance the range map is by interpolation. However, this should be undertaken with care since interpolation assumes continuity of range. The range is continuous in certain parts of the image and can jump at object boundaries. In such situations, the ability to detect homogeneous object regions by scene segmentation can be used to determine regions in the range map that can be enhanced by interpolation. The use of scalar features derived from the spatial gray-level dependence matrix for texture segmentation is explored. Thresholding of histograms of scalar texture features is done for several images to select scalar features which result in a meaningful segmentation of the images. Next, the selected scalar features are used with a neural net to automate the segmentation procedure. Back-propagation is used to train the feed forward neural network. The generalization of the network approach to subsequent images in the sequence is examined. It is shown that the use of multiple scalar features as input to the neural network result in a superior segmentation when compared with a single scalar feature. It is also shown that the scalar features, which are not useful individually, result in a good segmentation when used together. The methodology is applied to both indoor and outdoor images.

Analytical solutions for one-, two-, and three-dimensional solute transport in ground-water systems with uniform flow

USGS Publications Warehouse

Wexler, Eliezer J.

1992-01-01

Analytical solutions to the advective-dispersive solute-transport equation are useful in predicting the fate of solutes in ground water. Analytical solutions compiled from available literature or derived by the author are presented for a variety of boundary condition types and solute-source configurations in one-, two-, and three-dimensional systems having uniform ground-water flow. A set of user-oriented computer programs was created to evaluate these solutions and to display the results in tabular and computer-graphics format. These programs incorporate many features that enhance their accuracy, ease of use, and versatility. Documentation for the programs describes their operation and required input data, and presents the results of sample problems. Derivations of selected solutions, source codes for the computer programs, and samples of program input and output also are included.

Characterization of selected elementary motion detector cells to image primitives.

PubMed

Benson, Leslie A; Barrett, Steven F; Wright, Cameron H G

2008-01-01

Developing a visual sensing system, complete with motion processing hardware and software would have many applications to current technology. It could be mounted on many autonomous vehicles to provide information about the navigational environment, as well as obstacle avoidance features. Incorporating the motion processing capabilities into the sensor requires a new approach to the algorithm implementation. This research, and that of many others, have turned to nature for inspiration. Elementary motion detector (EMD) cells are involved in a biological preprocessing network to provide information to the motion processing lobes of the house degrees y Musca domestica. This paper describes the response of the photoreceptor inputs to the EMDs. The inputs to the EMD components are tested as they are stimulated with varying image primitives. This is the first of many steps in characterizing the EMD response to image primitives.

Spatial-area selective retrieval of multiple object-place associations in a hierarchical cognitive map formed by theta phase coding.

PubMed

Sato, Naoyuki; Yamaguchi, Yoko

2009-06-01

The human cognitive map is known to be hierarchically organized consisting of a set of perceptually clustered landmarks. Patient studies have demonstrated that these cognitive maps are maintained by the hippocampus, while the neural dynamics are still poorly understood. The authors have shown that the neural dynamic "theta phase precession" observed in the rodent hippocampus may be capable of forming hierarchical cognitive maps in humans. In the model, a visual input sequence consisting of object and scene features in the central and peripheral visual fields, respectively, results in the formation of a hierarchical cognitive map for object-place associations. Surprisingly, it is possible for such a complex memory structure to be formed in a few seconds. In this paper, we evaluate the memory retrieval of object-place associations in the hierarchical network formed by theta phase precession. The results show that multiple object-place associations can be retrieved with the initial cue of a scene input. Importantly, according to the wide-to-narrow unidirectional connections among scene units, the spatial area for object-place retrieval can be controlled by the spatial area of the initial cue input. These results indicate that the hierarchical cognitive maps have computational advantages on a spatial-area selective retrieval of multiple object-place associations. Theta phase precession dynamics is suggested as a fundamental neural mechanism of the human cognitive map.

Robotics control using isolated word recognition of voice input

NASA Technical Reports Server (NTRS)

Weiner, J. M.

1977-01-01

A speech input/output system is presented that can be used to communicate with a task oriented system. Human speech commands and synthesized voice output extend conventional information exchange capabilities between man and machine by utilizing audio input and output channels. The speech input facility is comprised of a hardware feature extractor and a microprocessor implemented isolated word or phrase recognition system. The recognizer offers a medium sized (100 commands), syntactically constrained vocabulary, and exhibits close to real time performance. The major portion of the recognition processing required is accomplished through software, minimizing the complexity of the hardware feature extractor.

A Feedback Model of Attention Explains the Diverse Effects of Attention on Neural Firing Rates and Receptive Field Structure.

PubMed

Miconi, Thomas; VanRullen, Rufin

2016-02-01

Visual attention has many effects on neural responses, producing complex changes in firing rates, as well as modifying the structure and size of receptive fields, both in topological and feature space. Several existing models of attention suggest that these effects arise from selective modulation of neural inputs. However, anatomical and physiological observations suggest that attentional modulation targets higher levels of the visual system (such as V4 or MT) rather than input areas (such as V1). Here we propose a simple mechanism that explains how a top-down attentional modulation, falling on higher visual areas, can produce the observed effects of attention on neural responses. Our model requires only the existence of modulatory feedback connections between areas, and short-range lateral inhibition within each area. Feedback connections redistribute the top-down modulation to lower areas, which in turn alters the inputs of other higher-area cells, including those that did not receive the initial modulation. This produces firing rate modulations and receptive field shifts. Simultaneously, short-range lateral inhibition between neighboring cells produce competitive effects that are automatically scaled to receptive field size in any given area. Our model reproduces the observed attentional effects on response rates (response gain, input gain, biased competition automatically scaled to receptive field size) and receptive field structure (shifts and resizing of receptive fields both spatially and in complex feature space), without modifying model parameters. Our model also makes the novel prediction that attentional effects on response curves should shift from response gain to contrast gain as the spatial focus of attention drifts away from the studied cell.

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.

Electroencephalogram Signal Classification for Automated Epileptic Seizure Detection Using Genetic Algorithm

PubMed Central

Nanthini, B. Suguna; Santhi, B.

2017-01-01

Background: Epilepsy causes when the repeated seizure occurs in the brain. Electroencephalogram (EEG) test provides valuable information about the brain functions and can be useful to detect brain disorder, especially for epilepsy. In this study, application for an automated seizure detection model has been introduced successfully. Materials and Methods: The EEG signals are decomposed into sub-bands by discrete wavelet transform using db2 (daubechies) wavelet. The eight statistical features, the four gray level co-occurrence matrix and Renyi entropy estimation with four different degrees of order, are extracted from the raw EEG and its sub-bands. Genetic algorithm (GA) is used to select eight relevant features from the 16 dimension features. The model has been trained and tested using support vector machine (SVM) classifier successfully for EEG signals. The performance of the SVM classifier is evaluated for two different databases. Results: The study has been experimented through two different analyses and achieved satisfactory performance for automated seizure detection using relevant features as the input to the SVM classifier. Conclusion: Relevant features using GA give better accuracy performance for seizure detection. PMID:28781480

Unsupervised feature relevance analysis applied to improve ECG heartbeat clustering.

PubMed

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

2012-10-01

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

Slow feature analysis: unsupervised learning of invariances.

PubMed

Wiskott, Laurenz; Sejnowski, Terrence J

2002-04-01

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

DISCOS- Current Status and Future Developments

NASA Astrophysics Data System (ADS)

Flohrer, T.; Lemmens, S.; Bastida Virgili, B.; Krag, H.; Klinkrad, H.; Parrilla, E.; Sanchez, N.; Oliveira, J.; Pina, F.

2013-08-01

We present ESA's Database and Information System Characterizing Objects in Space (DISCOS). DISCOS not only plays an essential role in the collision avoidance and re-entry prediction services provided by ESA's Space Debris Office, it is also providing input to numerous and very differently scoped engineering activities, within ESA and throughout industry. We introduce the central functionalities of DISCOS, present the available reporting capabilities, and describe selected data modelling features. Finally, we revisit the developments of the recent years and take a sneak preview of the on-going replacement of DISCOS web front-end.

Knowledge-based low-level image analysis for computer vision systems

NASA Technical Reports Server (NTRS)

Dhawan, Atam P.; Baxi, Himanshu; Ranganath, M. V.

1988-01-01

Two algorithms for entry-level image analysis and preliminary segmentation are proposed which are flexible enough to incorporate local properties of the image. The first algorithm involves pyramid-based multiresolution processing and a strategy to define and use interlevel and intralevel link strengths. The second algorithm, which is designed for selected window processing, extracts regions adaptively using local histograms. The preliminary segmentation and a set of features are employed as the input to an efficient rule-based low-level analysis system, resulting in suboptimal meaningful segmentation.

Single neuron computation: from dynamical system to feature detector.

PubMed

Hong, Sungho; Agüera y Arcas, Blaise; Fairhall, Adrienne L

2007-12-01

White noise methods are a powerful tool for characterizing the computation performed by neural systems. These methods allow one to identify the feature or features that a neural system extracts from a complex input and to determine how these features are combined to drive the system's spiking response. These methods have also been applied to characterize the input-output relations of single neurons driven by synaptic inputs, simulated by direct current injection. To interpret the results of white noise analysis of single neurons, we would like to understand how the obtained feature space of a single neuron maps onto the biophysical properties of the membrane, in particular, the dynamics of ion channels. Here, through analysis of a simple dynamical model neuron, we draw explicit connections between the output of a white noise analysis and the underlying dynamical system. We find that under certain assumptions, the form of the relevant features is well defined by the parameters of the dynamical system. Further, we show that under some conditions, the feature space is spanned by the spike-triggered average and its successive order time derivatives.

Inverse Proportional Relationship Between Switching-Time Length and Fractal-Like Structure for Continuous Tracking Movement

NASA Astrophysics Data System (ADS)

Hirakawa, Takehito; Suzuki, Hiroo; Gohara, Kazutoshi; Yamamoto, Yuji

We investigate the relationship between the switching-time length T and the fractal-like feature that characterizes the behavior of dissipative dynamical systems excited by external temporal inputs for tracking movement. Seven healthy right-handed male participants were asked to continuously track light-emitting diodes that were located on the right and left sides in front of them. These movements were performed under two conditions: when the same input pattern was repeated (the periodic-input condition) and when two different input patterns were switched stochastically (the switching-input condition). The repeated time lengths of input patterns during these conditions were 2.00, 1.00, 0.75, 0.50, 0.35, and 0.25s. The movements of a lever held between a participant’s thumb and index finger were measured by a motion-capture system and were analyzed with respect to position and velocity. The condition in which the same input was repeated revealed that two different stable trajectories existed in a cylindrical state space, while the condition in which the inputs were switched induced transitions between these two trajectories. These two different trajectories were considered as excited attractors. The transitions between the two excited attractors produced eight trajectories; they were then characterized by a fractal-like feature as a third-order sequence effect. Moreover, correlation dimensions, which are typically used to evaluate fractal-like features, calculated from the set on the Poincaré section increased as the switching-time length T decreased. These results suggest that an inverse proportional relationship exists between the switching-time length T and the fractal-like feature of human movement.

Spatial attention improves the quality of population codes in human visual cortex.

PubMed

Saproo, Sameer; Serences, John T

2010-08-01

Selective attention enables sensory input from behaviorally relevant stimuli to be processed in greater detail, so that these stimuli can more accurately influence thoughts, actions, and future goals. Attention has been shown to modulate the spiking activity of single feature-selective neurons that encode basic stimulus properties (color, orientation, etc.). However, the combined output from many such neurons is required to form stable representations of relevant objects and little empirical work has formally investigated the relationship between attentional modulations on population responses and improvements in encoding precision. Here, we used functional MRI and voxel-based feature tuning functions to show that spatial attention induces a multiplicative scaling in orientation-selective population response profiles in early visual cortex. In turn, this multiplicative scaling correlates with an improvement in encoding precision, as evidenced by a concurrent increase in the mutual information between population responses and the orientation of attended stimuli. These data therefore demonstrate how multiplicative scaling of neural responses provides at least one mechanism by which spatial attention may improve the encoding precision of population codes. Increased encoding precision in early visual areas may then enhance the speed and accuracy of perceptual decisions computed by higher-order neural mechanisms.

From Input to Intake: Towards a Brain-Based Perspective of Selective Attention.

ERIC Educational Resources Information Center

Sato, Edynn; Jacobs, Bob

1992-01-01

Addresses, from a neurobiological perspective, the input-intake distinction commonly made in applied linguistics and the role of selective attention in transforming input to intake. The study places primary emphasis upon a neural structure (the nucleus reticularis thalami) that appears to be essential for selective attention. (79 references)…

Domain-General Brain Regions Do Not Track Linguistic Input as Closely as Language-Selective Regions.

PubMed

Blank, Idan A; Fedorenko, Evelina

2017-10-11

Language comprehension engages a cortical network of left frontal and temporal regions. Activity in this network is language-selective, showing virtually no modulation by nonlinguistic tasks. In addition, language comprehension engages a second network consisting of bilateral frontal, parietal, cingulate, and insular regions. Activity in this "multiple demand" (MD) network scales with comprehension difficulty, but also with cognitive effort across a wide range of nonlinguistic tasks in a domain-general fashion. Given the functional dissociation between the language and MD networks, their respective contributions to comprehension are likely distinct, yet such differences remain elusive. Prior neuroimaging studies have suggested that activity in each network covaries with some linguistic features that, behaviorally, influence on-line processing and comprehension. This sensitivity of the language and MD networks to local input characteristics has often been interpreted, implicitly or explicitly, as evidence that both networks track linguistic input closely, and in a manner consistent across individuals. Here, we used fMRI to directly test this assumption by comparing the BOLD signal time courses in each network across different people ( n = 45, men and women) listening to the same story. Language network activity showed fewer individual differences, indicative of closer input tracking, whereas MD network activity was more idiosyncratic and, moreover, showed lower reliability within an individual across repetitions of a story. These findings constrain cognitive models of language comprehension by suggesting a novel distinction between the processes implemented in the language and MD networks. SIGNIFICANCE STATEMENT Language comprehension recruits both language-specific mechanisms and domain-general mechanisms that are engaged in many cognitive processes. In the human cortex, language-selective mechanisms are implemented in the left-lateralized "core language network", whereas domain-general mechanisms are implemented in the bilateral "multiple demand" (MD) network. Here, we report the first direct comparison of the respective contributions of these networks to naturalistic story comprehension. Using a novel combination of neuroimaging approaches we find that MD regions track stories less closely than language regions. This finding constrains the possible contributions of the MD network to comprehension, contrasts with accounts positing that this network has continuous access to linguistic input, and suggests a new typology of comprehension processes based on their extent of input tracking. Copyright © 2017 the authors 0270-6474/17/3710000-13$15.00/0.

Domain-General Brain Regions Do Not Track Linguistic Input as Closely as Language-Selective Regions

PubMed Central

Fedorenko, Evelina

2017-01-01

Language comprehension engages a cortical network of left frontal and temporal regions. Activity in this network is language-selective, showing virtually no modulation by nonlinguistic tasks. In addition, language comprehension engages a second network consisting of bilateral frontal, parietal, cingulate, and insular regions. Activity in this “multiple demand” (MD) network scales with comprehension difficulty, but also with cognitive effort across a wide range of nonlinguistic tasks in a domain-general fashion. Given the functional dissociation between the language and MD networks, their respective contributions to comprehension are likely distinct, yet such differences remain elusive. Prior neuroimaging studies have suggested that activity in each network covaries with some linguistic features that, behaviorally, influence on-line processing and comprehension. This sensitivity of the language and MD networks to local input characteristics has often been interpreted, implicitly or explicitly, as evidence that both networks track linguistic input closely, and in a manner consistent across individuals. Here, we used fMRI to directly test this assumption by comparing the BOLD signal time courses in each network across different people (n = 45, men and women) listening to the same story. Language network activity showed fewer individual differences, indicative of closer input tracking, whereas MD network activity was more idiosyncratic and, moreover, showed lower reliability within an individual across repetitions of a story. These findings constrain cognitive models of language comprehension by suggesting a novel distinction between the processes implemented in the language and MD networks. SIGNIFICANCE STATEMENT Language comprehension recruits both language-specific mechanisms and domain-general mechanisms that are engaged in many cognitive processes. In the human cortex, language-selective mechanisms are implemented in the left-lateralized “core language network”, whereas domain-general mechanisms are implemented in the bilateral “multiple demand” (MD) network. Here, we report the first direct comparison of the respective contributions of these networks to naturalistic story comprehension. Using a novel combination of neuroimaging approaches we find that MD regions track stories less closely than language regions. This finding constrains the possible contributions of the MD network to comprehension, contrasts with accounts positing that this network has continuous access to linguistic input, and suggests a new typology of comprehension processes based on their extent of input tracking. PMID:28871034

Reconstruction of nonlinear wave propagation

DOEpatents

Fleischer, Jason W; Barsi, Christopher; Wan, Wenjie

2013-04-23

Disclosed are systems and methods for characterizing a nonlinear propagation environment by numerically propagating a measured output waveform resulting from a known input waveform. The numerical propagation reconstructs the input waveform, and in the process, the nonlinear environment is characterized. In certain embodiments, knowledge of the characterized nonlinear environment facilitates determination of an unknown input based on a measured output. Similarly, knowledge of the characterized nonlinear environment also facilitates formation of a desired output based on a configurable input. In both situations, the input thus characterized and the output thus obtained include features that would normally be lost in linear propagations. Such features can include evanescent waves and peripheral waves, such that an image thus obtained are inherently wide-angle, farfield form of microscopy.

Evaluation and recommendation of sensitivity analysis methods for application to Stochastic Human Exposure and Dose Simulation models.

PubMed

Mokhtari, Amirhossein; Christopher Frey, H; Zheng, Junyu

2006-11-01

Sensitivity analyses of exposure or risk models can help identify the most significant factors to aid in risk management or to prioritize additional research to reduce uncertainty in the estimates. However, sensitivity analysis is challenged by non-linearity, interactions between inputs, and multiple days or time scales. Selected sensitivity analysis methods are evaluated with respect to their applicability to human exposure models with such features using a testbed. The testbed is a simplified version of a US Environmental Protection Agency's Stochastic Human Exposure and Dose Simulation (SHEDS) model. The methods evaluated include the Pearson and Spearman correlation, sample and rank regression, analysis of variance, Fourier amplitude sensitivity test (FAST), and Sobol's method. The first five methods are known as "sampling-based" techniques, wheras the latter two methods are known as "variance-based" techniques. The main objective of the test cases was to identify the main and total contributions of individual inputs to the output variance. Sobol's method and FAST directly quantified these measures of sensitivity. Results show that sensitivity of an input typically changed when evaluated under different time scales (e.g., daily versus monthly). All methods provided similar insights regarding less important inputs; however, Sobol's method and FAST provided more robust insights with respect to sensitivity of important inputs compared to the sampling-based techniques. Thus, the sampling-based methods can be used in a screening step to identify unimportant inputs, followed by application of more computationally intensive refined methods to a smaller set of inputs. The implications of time variation in sensitivity results for risk management are briefly discussed.

ProQ3D: improved model quality assessments using deep learning.

PubMed

Uziela, Karolis; Menéndez Hurtado, David; Shu, Nanjiang; Wallner, Björn; Elofsson, Arne

2017-05-15

Protein quality assessment is a long-standing problem in bioinformatics. For more than a decade we have developed state-of-art predictors by carefully selecting and optimising inputs to a machine learning method. The correlation has increased from 0.60 in ProQ to 0.81 in ProQ2 and 0.85 in ProQ3 mainly by adding a large set of carefully tuned descriptions of a protein. Here, we show that a substantial improvement can be obtained using exactly the same inputs as in ProQ2 or ProQ3 but replacing the support vector machine by a deep neural network. This improves the Pearson correlation to 0.90 (0.85 using ProQ2 input features). ProQ3D is freely available both as a webserver and a stand-alone program at http://proq3.bioinfo.se/. arne@bioinfo.se. Supplementary data are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

Research on oral test modeling based on multi-feature fusion

NASA Astrophysics Data System (ADS)

Shi, Yuliang; Tao, Yiyue; Lei, Jun

2018-04-01

In this paper, the spectrum of speech signal is taken as an input of feature extraction. The advantage of PCNN in image segmentation and other processing is used to process the speech spectrum and extract features. And a new method combining speech signal processing and image processing is explored. At the same time of using the features of the speech map, adding the MFCC to establish the spectral features and integrating them with the features of the spectrogram to further improve the accuracy of the spoken language recognition. Considering that the input features are more complicated and distinguishable, we use Support Vector Machine (SVM) to construct the classifier, and then compare the extracted test voice features with the standard voice features to achieve the spoken standard detection. Experiments show that the method of extracting features from spectrograms using PCNN is feasible, and the fusion of image features and spectral features can improve the detection accuracy.

Power selective optical filter devices and optical systems using same

DOEpatents

Koplow, Jeffrey P

2014-10-07

In an embodiment, a power selective optical filter device includes an input polarizer for selectively transmitting an input signal. The device includes a wave-plate structure positioned to receive the input signal, which includes at least one substantially zero-order, zero-wave plate. The zero-order, zero-wave plate is configured to alter a polarization state of the input signal passing in a manner that depends on the power of the input signal. The zero-order, zero-wave plate includes an entry and exit wave plate each having a fast axis, with the fast axes oriented substantially perpendicular to each other. Each entry wave plate is oriented relative to a transmission axis of the input polarizer at a respective angle. An output polarizer is positioned to receive a signal output from the wave-plate structure and selectively transmits the signal based on the polarization state.

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.

High dynamic range charge measurements

DOEpatents

De Geronimo, Gianluigi

2012-09-04

A charge amplifier for use in radiation sensing includes an amplifier, at least one switch, and at least one capacitor. The switch selectively couples the input of the switch to one of at least two voltages. The capacitor is electrically coupled in series between the input of the amplifier and the input of the switch. The capacitor is electrically coupled to the input of the amplifier without a switch coupled therebetween. A method of measuring charge in radiation sensing includes selectively diverting charge from an input of an amplifier to an input of at least one capacitor by selectively coupling an output of the at least one capacitor to one of at least two voltages. The input of the at least one capacitor is operatively coupled to the input of the amplifier without a switch coupled therebetween. The method also includes calculating a total charge based on a sum of the amplified charge and the diverted charge.

Fukunaga-Koontz feature transformation for statistical structural damage detection and hierarchical neuro-fuzzy damage localisation

NASA Astrophysics Data System (ADS)

Hoell, Simon; Omenzetter, Piotr

2017-07-01

Considering jointly damage sensitive features (DSFs) of signals recorded by multiple sensors, applying advanced transformations to these DSFs and assessing systematically their contribution to damage detectability and localisation can significantly enhance the performance of structural health monitoring systems. This philosophy is explored here for partial autocorrelation coefficients (PACCs) of acceleration responses. They are interrogated with the help of the linear discriminant analysis based on the Fukunaga-Koontz transformation using datasets of the healthy and selected reference damage states. Then, a simple but efficient fast forward selection procedure is applied to rank the DSF components with respect to statistical distance measures specialised for either damage detection or localisation. For the damage detection task, the optimal feature subsets are identified based on the statistical hypothesis testing. For damage localisation, a hierarchical neuro-fuzzy tool is developed that uses the DSF ranking to establish its own optimal architecture. The proposed approaches are evaluated experimentally on data from non-destructively simulated damage in a laboratory scale wind turbine blade. The results support our claim of being able to enhance damage detectability and localisation performance by transforming and optimally selecting DSFs. It is demonstrated that the optimally selected PACCs from multiple sensors or their Fukunaga-Koontz transformed versions can not only improve the detectability of damage via statistical hypothesis testing but also increase the accuracy of damage localisation when used as inputs into a hierarchical neuro-fuzzy network. Furthermore, the computational effort of employing these advanced soft computing models for damage localisation can be significantly reduced by using transformed DSFs.

Analytical solutions for one-, two-, and three-dimensional solute transport in ground-water systems with uniform flow

USGS Publications Warehouse

Wexler, Eliezer J.

1989-01-01

Analytical solutions to the advective-dispersive solute-transport equation are useful in predicting the fate of solutes in ground water. Analytical solutions compiled from available literature or derived by the author are presented in this report for a variety of boundary condition types and solute-source configurations in one-, two-, and three-dimensional systems with uniform ground-water flow. A set of user-oriented computer programs was created to evaluate these solutions and to display the results in tabular and computer-graphics format. These programs incorporate many features that enhance their accuracy, ease of use, and versatility. Documentation for the programs describes their operation and required input data, and presents the results of sample problems. Derivations of select solutions, source codes for the computer programs, and samples of program input and output also are included.

Sensitive method for characterizing liquid helium cooled preamplifier feedback resistors

NASA Technical Reports Server (NTRS)

Smeins, L. G.; Arentz, R. F.

1983-01-01

It is pointed out that the simple and traditional method of measuring resistance using an electrometer is ineffective since it is limited to a narrow and nonrepresentative range of terminal voltages. The present investigation is concerned with a resistor measurement technique which was developed to select and calibrate the Transimpedance Mode Amplifier (TIA) load resistors on the Infrared Astronomical Satellite (IRAS) for the wide variety of time and voltage varying signals which will be processed during the flight. The developed method has great versatility and power, and makes it possible to measure the varied and complex responses of nonideal feedback resistors to IR photo-detector currents. When employed with a stable input coupling capacitor, and a narrow band RMS voltmeter, the five input waveforms thouroughly test and calibrate all the features of interest in a load resistor and its associated TIA circuitry.

Cell Assembly Dynamics of Sparsely-Connected Inhibitory Networks: A Simple Model for the Collective Activity of Striatal Projection Neurons.

PubMed

Angulo-Garcia, David; Berke, Joshua D; Torcini, Alessandro

2016-02-01

Striatal projection neurons form a sparsely-connected inhibitory network, and this arrangement may be essential for the appropriate temporal organization of behavior. Here we show that a simplified, sparse inhibitory network of Leaky-Integrate-and-Fire neurons can reproduce some key features of striatal population activity, as observed in brain slices. In particular we develop a new metric to determine the conditions under which sparse inhibitory networks form anti-correlated cell assemblies with time-varying activity of individual cells. We find that under these conditions the network displays an input-specific sequence of cell assembly switching, that effectively discriminates similar inputs. Our results support the proposal that GABAergic connections between striatal projection neurons allow stimulus-selective, temporally-extended sequential activation of cell assemblies. Furthermore, we help to show how altered intrastriatal GABAergic signaling may produce aberrant network-level information processing in disorders such as Parkinson's and Huntington's diseases.

Diagnosable structured logic array

NASA Technical Reports Server (NTRS)

Whitaker, Sterling (Inventor); Miles, Lowell (Inventor); Gambles, Jody (Inventor); Maki, Gary K. (Inventor)

2009-01-01

A diagnosable structured logic array and associated process is provided. A base cell structure is provided comprising a logic unit comprising a plurality of input nodes, a plurality of selection nodes, and an output node, a plurality of switches coupled to the selection nodes, where the switches comprises a plurality of input lines, a selection line and an output line, a memory cell coupled to the output node, and a test address bus and a program control bus coupled to the plurality of input lines and the selection line of the plurality of switches. A state on each of the plurality of input nodes is verifiably loaded and read from the memory cell. A trusted memory block is provided. The associated process is provided for testing and verifying a plurality of truth table inputs of the logic unit.

Characterization of coronary plaque regions in intravascular ultrasound images using a hybrid ensemble classifier.

PubMed

Hwang, Yoo Na; Lee, Ju Hwan; Kim, Ga Young; Shin, Eun Seok; Kim, Sung Min

2018-01-01

The purpose of this study was to propose a hybrid ensemble classifier to characterize coronary plaque regions in intravascular ultrasound (IVUS) images. Pixels were allocated to one of four tissues (fibrous tissue (FT), fibro-fatty tissue (FFT), necrotic core (NC), and dense calcium (DC)) through processes of border segmentation, feature extraction, feature selection, and classification. Grayscale IVUS images and their corresponding virtual histology images were acquired from 11 patients with known or suspected coronary artery disease using 20 MHz catheter. A total of 102 hybrid textural features including first order statistics (FOS), gray level co-occurrence matrix (GLCM), extended gray level run-length matrix (GLRLM), Laws, local binary pattern (LBP), intensity, and discrete wavelet features (DWF) were extracted from IVUS images. To select optimal feature sets, genetic algorithm was implemented. A hybrid ensemble classifier based on histogram and texture information was then used for plaque characterization in this study. The optimal feature set was used as input of this ensemble classifier. After tissue characterization, parameters including sensitivity, specificity, and accuracy were calculated to validate the proposed approach. A ten-fold cross validation approach was used to determine the statistical significance of the proposed method. Our experimental results showed that the proposed method had reliable performance for tissue characterization in IVUS images. The hybrid ensemble classification method outperformed other existing methods by achieving characterization accuracy of 81% for FFT and 75% for NC. In addition, this study showed that Laws features (SSV and SAV) were key indicators for coronary tissue characterization. The proposed method had high clinical applicability for image-based tissue characterization. Copyright © 2017 Elsevier B.V. All rights reserved.

Contributions of Rod and Cone Pathways to Retinal Direction Selectivity Through Development

PubMed Central

Rosa, Juliana M.; Morrie, Ryan D.; Baertsch, Hans C.

2016-01-01

Direction selectivity is a robust computation across a broad stimulus space that is mediated by activity of both rod and cone photoreceptors through the ON and OFF pathways. However, rods, S-cones, and M-cones activate the ON and OFF circuits via distinct pathways and the relative contribution of each to direction selectivity is unknown. Using a variety of stimulation paradigms, pharmacological agents, and knockout mice that lack rod transduction, we found that inputs from the ON pathway were critical for strong direction-selective (DS) tuning in the OFF pathway. For UV light stimulation, the ON pathway inputs to the OFF pathway originated with rod signaling, whereas for visible stimulation, the ON pathway inputs to the OFF pathway originated with both rod and M-cone signaling. Whole-cell voltage-clamp recordings revealed that blocking the ON pathway reduced directional tuning in the OFF pathway via a reduction in null-side inhibition, which is provided by OFF starburst amacrine cells (SACs). Consistent with this, our recordings from OFF SACs confirmed that signals originating in the ON pathway contribute to their excitation. Finally, we observed that, for UV stimulation, ON contributions to OFF DS tuning matured earlier than direct signaling via the OFF pathway. These data indicate that the retina uses multiple strategies for computing DS responses across different colors and stages of development. SIGNIFICANCE STATEMENT The retina uses parallel pathways to encode different features of the visual scene. In some cases, these distinct pathways converge on circuits that mediate a distinct computation. For example, rod and cone pathways enable direction-selective (DS) ganglion cells to encode motion over a wide range of light intensities. Here, we show that although direction selectivity is robust across light intensities, motion discrimination for OFF signals is dependent upon ON signaling. At eye opening, ON directional tuning is mature, whereas OFF DS tuning is significantly reduced due to a delayed maturation of S-cone to OFF cone bipolar signaling. These results provide evidence that the retina uses multiple strategies for computing DS responses across different stimulus conditions. PMID:27629718

Mars Global Reference Atmospheric Model 2000 Version (Mars-GRAM 2000): Users Guide

NASA Technical Reports Server (NTRS)

Justus, C. G.; James, B. F.

2000-01-01

This report presents Mars Global Reference Atmospheric Model 2000 Version (Mars-GRAM 2000) and its new features. All parameterizations for temperature, pressure, density, and winds versus height, latitude, longitude, time of day, and L(sub s) have been replaced by input data tables from NASA Ames Mars General Circulation Model (MGCM) for the surface through 80-km altitude and the University of Arizona Mars Thermospheric General Circulation Model (MTGCM) for 80 to 170 km. A modified Stewart thermospheric model is still used for higher altitudes and for dependence on solar activity. "Climate factors" to tune for agreement with GCM data are no longer needed. Adjustment of exospheric temperature is still an option. Consistent with observations from Mars Global Surveyor, a new longitude-dependent wave model is included with user input to specify waves having 1 to 3 wavelengths around the planet. A simplified perturbation model has been substituted for the earlier one. An input switch allows users to select either East or West longitude positive. This memorandum includes instructions on obtaining Mars-GRAM source code and data files and for running the program. It also provides sample input and output and an example for incorporating Mars-GRAM as an atmospheric subroutine in a trajectory code.

Eye-gaze and intent: Application in 3D interface control

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

Schryver, J.C.; Goldberg, J.H.

1993-06-01

Computer interface control is typically accomplished with an input ``device`` such as keyboard, mouse, trackball, etc. An input device translates a users input actions, such as mouse clicks and key presses, into appropriate computer commands. To control the interface, the user must first convert intent into the syntax of the input device. A more natural means of computer control is possible when the computer can directly infer user intent, without need of intervening input devices. We describe an application of eye-gaze-contingent control of an interactive three-dimensional (3D) user interface. A salient feature of the user interface is natural input, withmore » a heightened impression of controlling the computer directly by the mind. With this interface, input of rotation and translation are intuitive, whereas other abstract features, such as zoom, are more problematic to match with user intent. This paper describes successes with implementation to date, and ongoing efforts to develop a more sophisticated intent inferencing methodology.« less

Eye-gaze and intent: Application in 3D interface control

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

Schryver, J.C.; Goldberg, J.H.

1993-01-01

Computer interface control is typically accomplished with an input device'' such as keyboard, mouse, trackball, etc. An input device translates a users input actions, such as mouse clicks and key presses, into appropriate computer commands. To control the interface, the user must first convert intent into the syntax of the input device. A more natural means of computer control is possible when the computer can directly infer user intent, without need of intervening input devices. We describe an application of eye-gaze-contingent control of an interactive three-dimensional (3D) user interface. A salient feature of the user interface is natural input, withmore » a heightened impression of controlling the computer directly by the mind. With this interface, input of rotation and translation are intuitive, whereas other abstract features, such as zoom, are more problematic to match with user intent. This paper describes successes with implementation to date, and ongoing efforts to develop a more sophisticated intent inferencing methodology.« less

A family of variable step-size affine projection adaptive filter algorithms using statistics of channel impulse response

NASA Astrophysics Data System (ADS)

Shams Esfand Abadi, Mohammad; AbbasZadeh Arani, Seyed Ali Asghar

2011-12-01

This paper extends the recently introduced variable step-size (VSS) approach to the family of adaptive filter algorithms. This method uses prior knowledge of the channel impulse response statistic. Accordingly, optimal step-size vector is obtained by minimizing the mean-square deviation (MSD). The presented algorithms are the VSS affine projection algorithm (VSS-APA), the VSS selective partial update NLMS (VSS-SPU-NLMS), the VSS-SPU-APA, and the VSS selective regressor APA (VSS-SR-APA). In VSS-SPU adaptive algorithms the filter coefficients are partially updated which reduce the computational complexity. In VSS-SR-APA, the optimal selection of input regressors is performed during the adaptation. The presented algorithms have good convergence speed, low steady state mean square error (MSE), and low computational complexity features. We demonstrate the good performance of the proposed algorithms through several simulations in system identification scenario.

RET selection on state-of-the-art NAND flash

NASA Astrophysics Data System (ADS)

Lafferty, Neal V.; He, Yuan; Pei, Jinhua; Shao, Feng; Liu, QingWei; Shi, Xuelong

2015-03-01

We present results generated using a new gauge-based Resolution Enhancement Technique (RET) Selection flow during the technology set up phase of a 3x-node NAND Flash product. As a testcase, we consider a challenging critical level for this ash product. The RET solutions include inverse lithography technology (ILT) optimized masks with sub-resolution assist features (SRAF) and companion illumination sources developed using a new pixel based Source Mask Optimization (SMO) tool that uses measurement gauges as a primary input. The flow includes verification objectives which allow tolerancing of particular measurement gauges based on lithographic criteria. Relative importance for particular gauges may also be set, to aid in down-selection from several candidate sources. The end result is a sensitive, objective score of RET performance. Using these custom-defined importance metrics, decisions on the final RET style can be made in an objective way.

Prediction of enzyme activity with neural network models based on electronic and geometrical features of substrates.

PubMed

Szaleniec, Maciej

2012-01-01

Artificial Neural Networks (ANNs) are introduced as robust and versatile tools in quantitative structure-activity relationship (QSAR) modeling. Their application to the modeling of enzyme reactivity is discussed, along with methodological issues. Methods of input variable selection, optimization of network internal structure, data set division and model validation are discussed. The application of ANNs in the modeling of enzyme activity over the last 20 years is briefly recounted. The discussed methodology is exemplified by the case of ethylbenzene dehydrogenase (EBDH). Intelligent Problem Solver and genetic algorithms are applied for input vector selection, whereas k-means clustering is used to partition the data into training and test cases. The obtained models exhibit high correlation between the predicted and experimental values (R(2) > 0.9). Sensitivity analyses and study of the response curves are used as tools for the physicochemical interpretation of the models in terms of the EBDH reaction mechanism. Neural networks are shown to be a versatile tool for the construction of robust QSAR models that can be applied to a range of aspects important in drug design and the prediction of biological activity.

Investigation into the influence of laser energy input on selective laser melted thin-walled parts by response surface method

NASA Astrophysics Data System (ADS)

Liu, Yang; Zhang, Jian; Pang, Zhicong; Wu, Weihui

2018-04-01

Selective laser melting (SLM) provides a feasible way for manufacturing of complex thin-walled parts directly, however, the energy input during SLM process, namely derived from the laser power, scanning speed, layer thickness and scanning space, etc. has great influence on the thin wall's qualities. The aim of this work is to relate the thin wall's parameters (responses), namely track width, surface roughness and hardness to the process parameters considered in this research (laser power, scanning speed and layer thickness) and to find out the optimal manufacturing conditions. Design of experiment (DoE) was used by implementing composite central design to achieve better manufacturing qualities. Mathematical models derived from the statistical analysis were used to establish the relationships between the process parameters and the responses. Also, the effects of process parameters on each response were determined. Then, a numerical optimization was performed to find out the optimal process set at which the quality features are at their desired values. Based on this study, the relationship between process parameters and SLMed thin-walled structure was revealed and thus, the corresponding optimal process parameters can be used to manufactured thin-walled parts with high quality.

A multimedia guide to spinal cord injury: empowerment through self instruction.

PubMed

Van Biervliet, A; Gest, T R

1995-01-01

The Spinal Cord Injury (SCI) Project is developing a series of instructional modules on SCI that will be distributed via CD-ROM for patient and family education. The modules are based on an instructional program and patient manual distributed by the Paralyzed Veterans of America. The program includes topics ranging from the anatomy and physiology of spinal cord injuries to legal rights established under the Americans With Disabilities Act. The SCI project expands on the instructional manual by combining digital multimedia techniques with motivational features such as games and personal guides. The user selects a personal guide from among a selection of individuals with spinal cord injuries to guide them through tutorials that include accounts of personal experiences. The guides appear in small video windows at various points throughout the tutorials and give personal insight into the topic at hand. The user can also query the other guides to hear their views on a topic. The user interface incorporates 'seamless access' features, which enable persons with a wide range of disabilities to use the program. Innovative features of these modules are the use of personal instructional guides, motivational games and activities, incorporation of alternative input or access strategies, and the use of high quality, low cost, multimedia production strategies.

In-process and post-process measurements of drill wear for control of the drilling process

NASA Astrophysics Data System (ADS)

Liu, Tien-I.; Liu, George; Gao, Zhiyu

2011-12-01

Optical inspection was used in this research for the post-process measurements of drill wear. A precision toolmakers" microscope was used. Indirect index, cutting force, is used for in-process drill wear measurements. Using in-process measurements to estimate the drill wear for control purpose can decrease the operation cost and enhance the product quality and safety. The challenge is to correlate the in-process cutting force measurements with the post-process optical inspection of drill wear. To find the most important feature, the energy principle was used in this research. It is necessary to select only the cutting force feature which shows the highest sensitivity to drill wear. The best feature selected is the peak of torque in the drilling process. Neuro-fuzzy systems were used for correlation purposes. The Adaptive-Network-Based Fuzzy Inference System (ANFIS) can construct fuzzy rules with membership functions to generate an input-output pair. A 1x6 ANFIS architecture with product of sigmoid membership functions can in-process measure the drill wear with an error as low as 0.15%. This is extremely important for control of the drilling process. Furthermore, the measurement of drill wear was performed under different drilling conditions. This shows that ANFIS has the capability of generalization.

Modeling the Time-Course of Responses for the Border Ownership Selectivity Based on the Integration of Feedforward Signals and Visual Cortical Interactions

PubMed Central

Wagatsuma, Nobuhiko; Sakai, Ko

2017-01-01

Border ownership (BO) indicates which side of a contour owns a border, and it plays a fundamental role in figure-ground segregation. The majority of neurons in V2 and V4 areas of monkeys exhibit BO selectivity. A physiological work reported that the responses of BO-selective cells show a rapid transition when a presented square is flipped along its classical receptive field (CRF) so that the opposite BO is presented, whereas the transition is significantly slower when a square with a clear BO is replaced by an ambiguous edge, e.g., when the square is enlarged greatly. The rapid transition seemed to reflect the influence of feedforward processing on BO selectivity. Herein, we investigated the role of feedforward signals and cortical interactions for time-courses in BO-selective cells by modeling a visual cortical network comprising V1, V2, and posterior parietal (PP) modules. In our computational model, the recurrent pathways among these modules gradually established the visual progress and the BO assignments. Feedforward inputs mainly determined the activities of these modules. Surrounding suppression/facilitation of early-level areas modulates the activities of V2 cells to provide BO signals. Weak feedback signals from the PP module enhanced the contrast gain extracted in V1, which underlies the attentional modulation of BO signals. Model simulations exhibited time-courses depending on the BO ambiguity, which were caused by the integration delay of V1 and V2 cells and the local inhibition therein given the difference in input stimulus. However, our model did not fully explain the characteristics of crucially slow transition: the responses of BO-selective physiological cells indicated the persistent activation several times longer than that of our model after the replacement with the ambiguous edge. Furthermore, the time-course of BO-selective model cells replicated the attentional modulation of response time in human psychophysical experiments. These attentional modulations for time-courses were induced by selective enhancement of early-level features due to interactions between V1 and PP. Our proposed model suggests fundamental roles of surrounding suppression/facilitation based on feedforward inputs as well as the interactions between early and parietal visual areas with respect to the ambiguity dependence of the neural dynamics in intermediate-level vision. PMID:28163688

Modeling the Time-Course of Responses for the Border Ownership Selectivity Based on the Integration of Feedforward Signals and Visual Cortical Interactions.

PubMed

Wagatsuma, Nobuhiko; Sakai, Ko

2016-01-01

Border ownership (BO) indicates which side of a contour owns a border, and it plays a fundamental role in figure-ground segregation. The majority of neurons in V2 and V4 areas of monkeys exhibit BO selectivity. A physiological work reported that the responses of BO-selective cells show a rapid transition when a presented square is flipped along its classical receptive field (CRF) so that the opposite BO is presented, whereas the transition is significantly slower when a square with a clear BO is replaced by an ambiguous edge, e.g., when the square is enlarged greatly. The rapid transition seemed to reflect the influence of feedforward processing on BO selectivity. Herein, we investigated the role of feedforward signals and cortical interactions for time-courses in BO-selective cells by modeling a visual cortical network comprising V1, V2, and posterior parietal (PP) modules. In our computational model, the recurrent pathways among these modules gradually established the visual progress and the BO assignments. Feedforward inputs mainly determined the activities of these modules. Surrounding suppression/facilitation of early-level areas modulates the activities of V2 cells to provide BO signals. Weak feedback signals from the PP module enhanced the contrast gain extracted in V1, which underlies the attentional modulation of BO signals. Model simulations exhibited time-courses depending on the BO ambiguity, which were caused by the integration delay of V1 and V2 cells and the local inhibition therein given the difference in input stimulus. However, our model did not fully explain the characteristics of crucially slow transition: the responses of BO-selective physiological cells indicated the persistent activation several times longer than that of our model after the replacement with the ambiguous edge. Furthermore, the time-course of BO-selective model cells replicated the attentional modulation of response time in human psychophysical experiments. These attentional modulations for time-courses were induced by selective enhancement of early-level features due to interactions between V1 and PP. Our proposed model suggests fundamental roles of surrounding suppression/facilitation based on feedforward inputs as well as the interactions between early and parietal visual areas with respect to the ambiguity dependence of the neural dynamics in intermediate-level vision.

Identification of eggs from different production systems based on hyperspectra and CS-SVM.

PubMed

Sun, J; Cong, S L; Mao, H P; Zhou, X; Wu, X H; Zhang, X D

2017-06-01

1. To identify the origin of table eggs more accurately, a method based on hyperspectral imaging technology was studied. 2. The hyperspectral data of 200 samples of intensive and extensive eggs were collected. Standard normalised variables combined with a Savitzky-Golay were used to eliminate noise, then stepwise regression (SWR) was used for feature selection. Grid search algorithm (GS), genetic search algorithm (GA), particle swarm optimisation algorithm (PSO) and cuckoo search algorithm (CS) were applied by support vector machine (SVM) methods to establish an SVM identification model with the optimal parameters. The full spectrum data and the data after feature selection were the input of the model, while egg category was the output. 3. The SWR-CS-SVM model performed better than the other models, including SWR-GS-SVM, SWR-GA-SVM, SWR-PSO-SVM and others based on full spectral data. The training and test classification accuracy of the SWR-CS-SVM model were respectively 99.3% and 96%. 4. SWR-CS-SVM proved effective for identifying egg varieties and could also be useful for the non-destructive identification of other types of egg.

Clustering molecular dynamics trajectories for optimizing docking experiments.

PubMed

De Paris, Renata; Quevedo, Christian V; Ruiz, Duncan D; Norberto de Souza, Osmar; Barros, Rodrigo C

2015-01-01

Molecular dynamics simulations of protein receptors have become an attractive tool for rational drug discovery. However, the high computational cost of employing molecular dynamics trajectories in virtual screening of large repositories threats the feasibility of this task. Computational intelligence techniques have been applied in this context, with the ultimate goal of reducing the overall computational cost so the task can become feasible. Particularly, clustering algorithms have been widely used as a means to reduce the dimensionality of molecular dynamics trajectories. In this paper, we develop a novel methodology for clustering entire trajectories using structural features from the substrate-binding cavity of the receptor in order to optimize docking experiments on a cloud-based environment. The resulting partition was selected based on three clustering validity criteria, and it was further validated by analyzing the interactions between 20 ligands and a fully flexible receptor (FFR) model containing a 20 ns molecular dynamics simulation trajectory. Our proposed methodology shows that taking into account features of the substrate-binding cavity as input for the k-means algorithm is a promising technique for accurately selecting ensembles of representative structures tailored to a specific ligand.

Exploring nonlinear feature space dimension reduction and data representation in breast Cadx with Laplacian eigenmaps and t-SNE.

PubMed

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

2010-01-01

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

The emergence of polychronization and feature binding in a spiking neural network model of the primate ventral visual system.

PubMed

Eguchi, Akihiro; Isbister, James B; Ahmad, Nasir; Stringer, Simon

2018-07-01

We present a hierarchical neural network model, in which subpopulations of neurons develop fixed and regularly repeating temporal chains of spikes (polychronization), which respond specifically to randomized Poisson spike trains representing the input training images. The performance is improved by including top-down and lateral synaptic connections, as well as introducing multiple synaptic contacts between each pair of pre- and postsynaptic neurons, with different synaptic contacts having different axonal delays. Spike-timing-dependent plasticity thus allows the model to select the most effective axonal transmission delay between neurons. Furthermore, neurons representing the binding relationship between low-level and high-level visual features emerge through visually guided learning. This begins to provide a way forward to solving the classic feature binding problem in visual neuroscience and leads to a new hypothesis concerning how information about visual features at every spatial scale may be projected upward through successive neuronal layers. We name this hypothetical upward projection of information the "holographic principle." (PsycINFO Database Record (c) 2018 APA, all rights reserved).

Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture.

PubMed

Chen, C L Philip; Liu, Zhulin

2018-01-01

Broad Learning System (BLS) that aims to offer an alternative way of learning in deep structure is proposed in this paper. Deep structure and learning suffer from a time-consuming training process because of a large number of connecting parameters in filters and layers. Moreover, it encounters a complete retraining process if the structure is not sufficient to model the system. The BLS is established in the form of a flat network, where the original inputs are transferred and placed as "mapped features" in feature nodes and the structure is expanded in wide sense in the "enhancement nodes." The incremental learning algorithms are developed for fast remodeling in broad expansion without a retraining process if the network deems to be expanded. Two incremental learning algorithms are given for both the increment of the feature nodes (or filters in deep structure) and the increment of the enhancement nodes. The designed model and algorithms are very versatile for selecting a model rapidly. In addition, another incremental learning is developed for a system that has been modeled encounters a new incoming input. Specifically, the system can be remodeled in an incremental way without the entire retraining from the beginning. Satisfactory result for model reduction using singular value decomposition is conducted to simplify the final structure. Compared with existing deep neural networks, experimental results on the Modified National Institute of Standards and Technology database and NYU NORB object recognition dataset benchmark data demonstrate the effectiveness of the proposed BLS.

Neural network classification of sweet potato embryos

NASA Astrophysics Data System (ADS)

Molto, Enrique; Harrell, Roy C.

1993-05-01

Somatic embryogenesis is a process that allows for the in vitro propagation of thousands of plants in sub-liter size vessels and has been successfully applied to many significant species. The heterogeneity of maturity and quality of embryos produced with this technique requires sorting to obtain a uniform product. An automated harvester is being developed at the University of Florida to sort embryos in vitro at different stages of maturation in a suspension culture. The system utilizes machine vision to characterize embryo morphology and a fluidic based separation device to isolate embryos associated with a pre-defined, targeted morphology. Two different backpropagation neural networks (BNN) were used to classify embryos based on information extracted from the vision system. One network utilized geometric features such as embryo area, length, and symmetry as inputs. The alternative network utilized polar coordinates of an embryo's perimeter with respect to its centroid as inputs. The performances of both techniques were compared with each other and with an embryo classification method based on linear discriminant analysis (LDA). Similar results were obtained with all three techniques. Classification efficiency was improved by reducing the dimension of the feature vector trough a forward stepwise analysis by LDA. In order to enhance the purity of the sample selected as harvestable, a reject to classify option was introduced in the model and analyzed. The best classifier performances (76% overall correct classifications, 75% harvestable objects properly classified, homogeneity improvement ratio 1.5) were obtained using 8 features in a BNN.

Walsh-Hadamard transform kernel-based feature vector for shot boundary detection.

PubMed

Lakshmi, Priya G G; Domnic, S

2014-12-01

Video shot boundary detection (SBD) is the first step of video analysis, summarization, indexing, and retrieval. In SBD process, videos are segmented into basic units called shots. In this paper, a new SBD method is proposed using color, edge, texture, and motion strength as vector of features (feature vector). Features are extracted by projecting the frames on selected basis vectors of Walsh-Hadamard transform (WHT) kernel and WHT matrix. After extracting the features, based on the significance of the features, weights are calculated. The weighted features are combined to form a single continuity signal, used as input for Procedure Based shot transition Identification process (PBI). Using the procedure, shot transitions are classified into abrupt and gradual transitions. Experimental results are examined using large-scale test sets provided by the TRECVID 2007, which has evaluated hard cut and gradual transition detection. To evaluate the robustness of the proposed method, the system evaluation is performed. The proposed method yields F1-Score of 97.4% for cut, 78% for gradual, and 96.1% for overall transitions. We have also evaluated the proposed feature vector with support vector machine classifier. The results show that WHT-based features can perform well than the other existing methods. In addition to this, few more video sequences are taken from the Openvideo project and the performance of the proposed method is compared with the recent existing SBD method.

Orientation selectivity and the functional clustering of synaptic inputs in primary visual cortex

PubMed Central

Wilson, Daniel E.; Whitney, David E.; Scholl, Benjamin; Fitzpatrick, David

2016-01-01

The majority of neurons in primary visual cortex are tuned for stimulus orientation, but the factors that account for the range of orientation selectivities exhibited by cortical neurons remain unclear. To address this issue, we used in vivo 2-photon calcium imaging to characterize the orientation tuning and spatial arrangement of synaptic inputs to the dendritic spines of individual pyramidal neurons in layer 2/3 of ferret visual cortex. The summed synaptic input to individual neurons reliably predicted the neuron’s orientation preference, but did not account for differences in orientation selectivity among neurons. These differences reflected a robust input-output nonlinearity that could not be explained by spike threshold alone, and was strongly correlated with the spatial clustering of co-tuned synaptic inputs within the dendritic field. Dendritic branches with more co-tuned synaptic clusters exhibited greater rates of local dendritic calcium events supporting a prominent role for functional clustering of synaptic inputs in dendritic nonlinearities that shape orientation selectivity. PMID:27294510

Visual attention mitigates information loss in small- and large-scale neural codes

PubMed Central

Sprague, Thomas C; Saproo, Sameer; Serences, John T

2015-01-01

Summary The visual system transforms complex inputs into robust and parsimonious neural codes that efficiently guide behavior. Because neural communication is stochastic, the amount of encoded visual information necessarily decreases with each synapse. This constraint requires processing sensory signals in a manner that protects information about relevant stimuli from degradation. Such selective processing – or selective attention – is implemented via several mechanisms, including neural gain and changes in tuning properties. However, examining each of these effects in isolation obscures their joint impact on the fidelity of stimulus feature representations by large-scale population codes. Instead, large-scale activity patterns can be used to reconstruct representations of relevant and irrelevant stimuli, providing a holistic understanding about how neuron-level modulations collectively impact stimulus encoding. PMID:25769502

A neuromorphic VLSI device for implementing 2-D selective attention systems.

PubMed

Indiveri, G

2001-01-01

Selective attention is a mechanism used to sequentially select and process salient subregions of the input space, while suppressing inputs arriving from nonsalient regions. By processing small amounts of sensory information in a serial fashion, rather than attempting to process all the sensory data in parallel, this mechanism overcomes the problem of flooding limited processing capacity systems with sensory inputs. It is found in many biological systems and can be a useful engineering tool for developing artificial systems that need to process in real-time sensory data. In this paper we present a neuromorphic hardware model of a selective attention mechanism implemented on a very large scale integration (VLSI) chip, using analog circuits. The chip makes use of a spike-based representation for receiving input signals, transmitting output signals and for shifting the selection of the attended input stimulus over time. It can be interfaced to neuromorphic sensors and actuators, for implementing multichip selective attention systems. We describe the characteristics of the circuits used in the architecture and present experimental data measured from the system.

Prediction of rat protein subcellular localization with pseudo amino acid composition based on multiple sequential features.

PubMed

Shi, Ruijia; Xu, Cunshuan

2011-06-01

The study of rat proteins is an indispensable task in experimental medicine and drug development. The function of a rat protein is closely related to its subcellular location. Based on the above concept, we construct the benchmark rat proteins dataset and develop a combined approach for predicting the subcellular localization of rat proteins. From protein primary sequence, the multiple sequential features are obtained by using of discrete Fourier analysis, position conservation scoring function and increment of diversity, and these sequential features are selected as input parameters of the support vector machine. By the jackknife test, the overall success rate of prediction is 95.6% on the rat proteins dataset. Our method are performed on the apoptosis proteins dataset and the Gram-negative bacterial proteins dataset with the jackknife test, the overall success rates are 89.9% and 96.4%, respectively. The above results indicate that our proposed method is quite promising and may play a complementary role to the existing predictors in this area.

Age and gender classification in the wild with unsupervised feature learning

NASA Astrophysics Data System (ADS)

Wan, Lihong; Huo, Hong; Fang, Tao

2017-03-01

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

Artificial Neural Network Based Fault Diagnostics of Rolling Element Bearings Using Time-Domain Features

NASA Astrophysics Data System (ADS)

Samanta, B.; Al-Balushi, K. R.

2003-03-01

A procedure is presented for fault diagnosis of rolling element bearings through artificial neural network (ANN). The characteristic features of time-domain vibration signals of the rotating machinery with normal and defective bearings have been used as inputs to the ANN consisting of input, hidden and output layers. The features are obtained from direct processing of the signal segments using very simple preprocessing. The input layer consists of five nodes, one each for root mean square, variance, skewness, kurtosis and normalised sixth central moment of the time-domain vibration signals. The inputs are normalised in the range of 0.0 and 1.0 except for the skewness which is normalised between -1.0 and 1.0. The output layer consists of two binary nodes indicating the status of the machine—normal or defective bearings. Two hidden layers with different number of neurons have been used. The ANN is trained using backpropagation algorithm with a subset of the experimental data for known machine conditions. The ANN is tested using the remaining set of data. The effects of some preprocessing techniques like high-pass, band-pass filtration, envelope detection (demodulation) and wavelet transform of the vibration signals, prior to feature extraction, are also studied. The results show the effectiveness of the ANN in diagnosis of the machine condition. The proposed procedure requires only a few features extracted from the measured vibration data either directly or with simple preprocessing. The reduced number of inputs leads to faster training requiring far less iterations making the procedure suitable for on-line condition monitoring and diagnostics of machines.

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

Classification of focal liver lesions on ultrasound images by extracting hybrid textural features and using an artificial neural network.

PubMed

Hwang, Yoo Na; Lee, Ju Hwan; Kim, Ga Young; Jiang, Yuan Yuan; Kim, Sung Min

2015-01-01

This paper focuses on the improvement of the diagnostic accuracy of focal liver lesions by quantifying the key features of cysts, hemangiomas, and malignant lesions on ultrasound images. The focal liver lesions were divided into 29 cysts, 37 hemangiomas, and 33 malignancies. A total of 42 hybrid textural features that composed of 5 first order statistics, 18 gray level co-occurrence matrices, 18 Law's, and echogenicity were extracted. A total of 29 key features that were selected by principal component analysis were used as a set of inputs for a feed-forward neural network. For each lesion, the performance of the diagnosis was evaluated by using the positive predictive value, negative predictive value, sensitivity, specificity, and accuracy. The results of the experiment indicate that the proposed method exhibits great performance, a high diagnosis accuracy of over 96% among all focal liver lesion groups (cyst vs. hemangioma, cyst vs. malignant, and hemangioma vs. malignant) on ultrasound images. The accuracy was slightly increased when echogenicity was included in the optimal feature set. These results indicate that it is possible for the proposed method to be applied clinically.

Phonological Feature Re-Assembly and the Importance of Phonetic Cues

ERIC Educational Resources Information Center

Archibald, John

2009-01-01

It is argued that new phonological features can be acquired in second languages, but that both feature acquisition and feature re-assembly are affected by the robustness of phonetic cues in the input.

Real-time high-resolution PC-based system for measurement of errors on compact disks

NASA Astrophysics Data System (ADS)

Tehranchi, Babak; Howe, Dennis G.

1994-10-01

Hardware and software utilities are developed to directly monitor the Eight-to-Fourteen (EFM) demodulated data bytes at the input of a CD player's Cross-Interleaved Reed-Solomon Code (CIRC) block decoder. The hardware is capable of identifying erroneous data with single-byte resolution in the serial data stream read from a Compact Disc by a CDD 461 Philips CD-ROM drive. In addition, the system produces graphical maps that show the physical location of the measured errors on the entire disc, or via a zooming and planning feature, on user selectable local disc regions.

Biomedical engineering tasks. [electrode development for electrocardiography and electroencephalography

NASA Technical Reports Server (NTRS)

1972-01-01

Electrocardiographic and vectorcardiographic bioinstrumentation work centered on the development of a new electrode system harness for Project Skylab. Evaluation of several silver electrode configurations proved superior impedance voltage performance for silver/silver chloride electrodes mounted flush by using a paste adhesive. A portable ECG processor has been designed and a breadboard unit has been built to sample ECG input data at a rate of 500 samples per second for arrhythmia detection. A small real time display driver program has been developed for statistical analysis on selected QPS features. Engineering work on a sleep monitoring cap assembly continued.

A method to estimate weight and dimensions of aircraft gas turbine engines. Volume 1: Method of analysis

NASA Technical Reports Server (NTRS)

Pera, R. J.; Onat, E.; Klees, G. W.; Tjonneland, E.

1977-01-01

Weight and envelope dimensions of aircraft gas turbine engines are estimated within plus or minus 5% to 10% using a computer method based on correlations of component weight and design features of 29 data base engines. Rotating components are estimated by a preliminary design procedure where blade geometry, operating conditions, material properties, shaft speed, hub-tip ratio, etc., are the primary independent variables used. The development and justification of the method selected, the various methods of analysis, the use of the program, and a description of the input/output data are discussed.

Measurand transient signal suppressor

NASA Technical Reports Server (NTRS)

Bozeman, Richard J., Jr. (Inventor)

1994-01-01

A transient signal suppressor for use in a controls system which is adapted to respond to a change in a physical parameter whenever it crosses a predetermined threshold value in a selected direction of increasing or decreasing values with respect to the threshold value and is sustained for a selected discrete time interval is presented. The suppressor includes a sensor transducer for sensing the physical parameter and generating an electrical input signal whenever the sensed physical parameter crosses the threshold level in the selected direction. A manually operated switch is provided for adapting the suppressor to produce an output drive signal whenever the physical parameter crosses the threshold value in the selected direction of increasing or decreasing values. A time delay circuit is selectively adjustable for suppressing the transducer input signal for a preselected one of a plurality of available discrete suppression time and producing an output signal only if the input signal is sustained for a time greater than the selected suppression time. An electronic gate is coupled to receive the transducer input signal and the timer output signal and produce an output drive signal for energizing a control relay whenever the transducer input is a non-transient signal which is sustained beyond the selected time interval.

Olfactory Bulb Deep Short-Axon Cells Mediate Widespread Inhibition of Tufted Cell Apical Dendrites

PubMed Central

LaRocca, Greg

2017-01-01

In the main olfactory bulb (MOB), the first station of sensory processing in the olfactory system, GABAergic interneuron signaling shapes principal neuron activity to regulate olfaction. However, a lack of known selective markers for MOB interneurons has strongly impeded cell-type-selective investigation of interneuron function. Here, we identify the first selective marker of glomerular layer-projecting deep short-axon cells (GL-dSACs) and investigate systematically the structure, abundance, intrinsic physiology, feedforward sensory input, neuromodulation, synaptic output, and functional role of GL-dSACs in the mouse MOB circuit. GL-dSACs are located in the internal plexiform layer, where they integrate centrifugal cholinergic input with highly convergent feedforward sensory input. GL-dSAC axons arborize extensively across the glomerular layer to provide highly divergent yet selective output onto interneurons and principal tufted cells. GL-dSACs are thus capable of shifting the balance of principal tufted versus mitral cell activity across large expanses of the MOB in response to diverse sensory and top-down neuromodulatory input. SIGNIFICANCE STATEMENT The identification of cell-type-selective molecular markers has fostered tremendous insight into how distinct interneurons shape sensory processing and behavior. In the main olfactory bulb (MOB), inhibitory circuits regulate the activity of principal cells precisely to drive olfactory-guided behavior. However, selective markers for MOB interneurons remain largely unknown, limiting mechanistic understanding of olfaction. Here, we identify the first selective marker of a novel population of deep short-axon cell interneurons with superficial axonal projections to the sensory input layer of the MOB. Using this marker, together with immunohistochemistry, acute slice electrophysiology, and optogenetic circuit mapping, we reveal that this novel interneuron population integrates centrifugal cholinergic input with broadly tuned feedforward sensory input to modulate principal cell activity selectively. PMID:28003347

Enhancement of the CAVE computer code

NASA Astrophysics Data System (ADS)

Rathjen, K. A.; Burk, H. O.

1983-12-01

The computer code CAVE (Conduction Analysis via Eigenvalues) is a convenient and efficient computer code for predicting two dimensional temperature histories within thermal protection systems for hypersonic vehicles. The capabilities of CAVE were enhanced by incorporation of the following features into the code: real gas effects in the aerodynamic heating predictions, geometry and aerodynamic heating package for analyses of cone shaped bodies, input option to change from laminar to turbulent heating predictions on leading edges, modification to account for reduction in adiabatic wall temperature with increase in leading sweep, geometry package for two dimensional scramjet engine sidewall, with an option for heat transfer to external and internal surfaces, print out modification to provide tables of select temperatures for plotting and storage, and modifications to the radiation calculation procedure to eliminate temperature oscillations induced by high heating rates. These new features are described.

Evidence for Working Memory Storage Operations in Perceptual Cortex

PubMed Central

Sreenivasan, Kartik K.; Gratton, Caterina; Vytlacil, Jason; D’Esposito, Mark

2014-01-01

Isolating the short-term storage component of working memory (WM) from the myriad of associated executive processes has been an enduring challenge. Recent efforts have identified patterns of activity in visual regions that contain information about items being held in WM. However, it remains unclear (i) whether these representations withstand intervening sensory input and (ii) how communication between multimodal association cortex and unimodal perceptual regions supporting WM representations is involved in WM storage. We present evidence that the features of a face held in WM are stored within face processing regions, that these representations persist across subsequent sensory input, and that information about the match between sensory input and memory representation is relayed forward from perceptual to prefrontal regions. Participants were presented with a series of probe faces and indicated whether each probe matched a Target face held in WM. We parametrically varied the feature similarity between probe and Target faces. Activity within face processing regions scaled linearly with the degree of feature similarity between the probe face and the features of the Target face, suggesting that the features of the Target face were stored in these regions. Furthermore, directed connectivity measures revealed that the direction of information flow that was optimal for performance was from sensory regions that stored the features of the Target face to dorsal prefrontal regions, supporting the notion that sensory input is compared to representations stored within perceptual regions and relayed forward. Together, these findings indicate that WM storage operations are carried out within perceptual cortex. PMID:24436009

Is that a belt or a snake? object attentional selection affects the early stages of visual sensory processing

PubMed Central

2012-01-01

Background There is at present crescent empirical evidence deriving from different lines of ERPs research that, unlike previously observed, the earliest sensory visual response, known as C1 component or P/N80, generated within the striate cortex, might be modulated by selective attention to visual stimulus features. Up to now, evidence of this modulation has been related to space location, and simple features such as spatial frequency, luminance, and texture. Additionally, neurophysiological conditions, such as emotion, vigilance, the reflexive or voluntary nature of input attentional selection, and workload have also been related to C1 modulations, although at least the workload status has received controversial indications. No information is instead available, at present, for objects attentional selection. Methods In this study object- and space-based attention mechanisms were conjointly investigated by presenting complex, familiar shapes of artefacts and animals, intermixed with distracters, in different tasks requiring the selection of a relevant target-category within a relevant spatial location, while ignoring the other shape categories within this location, and, overall, all the categories at an irrelevant location. EEG was recorded from 30 scalp electrode sites in 21 right-handed participants. Results and Conclusions ERP findings showed that visual processing was modulated by both shape- and location-relevance per se, beginning separately at the latency of the early phase of a precocious negativity (60-80 ms) at mesial scalp sites consistent with the C1 component, and a positivity at more lateral sites. The data also showed that the attentional modulation progressed conjointly at the latency of the subsequent P1 (100-120 ms) and N1 (120-180 ms), as well as later-latency components. These findings support the views that (1) V1 may be precociously modulated by direct top-down influences, and participates to object, besides simple features, attentional selection; (2) object spatial and non-spatial features selection might begin with an early, parallel detection of a target object in the visual field, followed by the progressive focusing of spatial attention onto the location of an actual target for its identification, somehow in line with neural mechanisms reported in the literature as "object-based space selection", or with those proposed for visual search. PMID:22300540

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.

Mapping Forest Height in Gabon Using UAVSAR Multi-Baseline Polarimetric SAR Interferometry and Lidar Fusion

NASA Astrophysics Data System (ADS)

Simard, M.; Denbina, M. W.

2017-12-01

Using data collected by NASA's Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) and Land, Vegetation, and Ice Sensor (LVIS) lidar, we have estimated forest canopy height for a number of study areas in the country of Gabon using a new machine learning data fusion approach. Using multi-baseline polarimetric synthetic aperture radar interferometry (PolInSAR) data collected by UAVSAR, forest heights can be estimated using the random volume over ground model. In the case of multi-baseline UAVSAR data consisting of many repeat passes with spatially separated flight tracks, we can estimate different forest height values for each different image pair, or baseline. In order to choose the best forest height estimate for each pixel, the baselines must be selected or ranked, taking care to avoid baselines with unsuitable spatial separation, or severe temporal decorrelation effects. The current baseline selection algorithms in the literature use basic quality metrics derived from the PolInSAR data which are not necessarily indicative of the true height accuracy in all cases. We have developed a new data fusion technique which treats PolInSAR baseline selection as a supervised classification problem, where the classifier is trained using a sparse sampling of lidar data within the PolInSAR coverage area. The classifier uses a large variety of PolInSAR-derived features as input, including radar backscatter as well as features based on the PolInSAR coherence region shape and the PolInSAR complex coherences. The resulting data fusion method produces forest height estimates which are more accurate than a purely radar-based approach, while having a larger coverage area than the input lidar training data, combining some of the strengths of each sensor. The technique demonstrates the strong potential for forest canopy height and above-ground biomass mapping using fusion of PolInSAR with data from future spaceborne lidar missions such as the upcoming Global Ecosystems Dynamics Investigation (GEDI) lidar.

Classifying human operator functional state based on electrophysiological and performance measures and fuzzy clustering method.

PubMed

Zhang, Jian-Hua; Peng, Xiao-Di; Liu, Hua; Raisch, Jörg; Wang, Ru-Bin

2013-12-01

The human operator's ability to perform their tasks can fluctuate over time. Because the cognitive demands of the task can also vary it is possible that the capabilities of the operator are not sufficient to satisfy the job demands. This can lead to serious errors when the operator is overwhelmed by the task demands. Psychophysiological measures, such as heart rate and brain activity, can be used to monitor operator cognitive workload. In this paper, the most influential psychophysiological measures are extracted to characterize Operator Functional State (OFS) in automated tasks under a complex form of human-automation interaction. The fuzzy c-mean (FCM) algorithm is used and tested for its OFS classification performance. The results obtained have shown the feasibility and effectiveness of the FCM algorithm as well as the utility of the selected input features for OFS classification. Besides being able to cope with nonlinearity and fuzzy uncertainty in the psychophysiological data it can provide information about the relative importance of the input features as well as the confidence estimate of the classification results. The OFS pattern classification method developed can be incorporated into an adaptive aiding system in order to enhance the overall performance of a large class of safety-critical human-machine cooperative systems.

Computational diagnosis of canine lymphoma

NASA Astrophysics Data System (ADS)

Mirkes, E. M.; Alexandrakis, I.; Slater, K.; Tuli, R.; Gorban, A. N.

2014-03-01

One out of four dogs will develop cancer in their lifetime and 20% of those will be lymphoma cases. PetScreen developed a lymphoma blood test using serum samples collected from several veterinary practices. The samples were fractionated and analysed by mass spectrometry. Two protein peaks, with the highest diagnostic power, were selected and further identified as acute phase proteins, C-Reactive Protein and Haptoglobin. Data mining methods were then applied to the collected data for the development of an online computer-assisted veterinary diagnostic tool. The generated software can be used as a diagnostic, monitoring and screening tool. Initially, the diagnosis of lymphoma was formulated as a classification problem and then later refined as a lymphoma risk estimation. Three methods, decision trees, kNN and probability density evaluation, were used for classification and risk estimation and several preprocessing approaches were implemented to create the diagnostic system. For the differential diagnosis the best solution gave a sensitivity and specificity of 83.5% and 77%, respectively (using three input features, CRP, Haptoglobin and standard clinical symptom). For the screening task, the decision tree method provided the best result, with sensitivity and specificity of 81.4% and >99%, respectively (using the same input features). Furthermore, the development and application of new techniques for the generation of risk maps allowed their user-friendly visualization.

Nonlinear features for product inspection

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.

1999-03-01

Classification of real-time X-ray images of randomly oriented touching pistachio nuts is discussed. The ultimate objective is the development of a system for automated non-invasive detection of defective product items on a conveyor belt. We discuss the extraction of new features that allow better discrimination between damaged and clean items (pistachio nuts). This feature extraction and classification stage is the new aspect of this paper; our new maximum representation and discriminating feature (MRDF) extraction method computes nonlinear features that are used as inputs to a new modified k nearest neighbor classifier. In this work, the MRDF is applied to standard features (rather than iconic data). The MRDF is robust to various probability distributions of the input class and is shown to provide good classification and new ROC (receiver operating characteristic) data.

SU-G-BRC-13: Model Based Classification for Optimal Position Selection for Left-Sided Breast Radiotherapy: Free Breathing, DIBH, Or Prone

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

Lin, H; Liu, T; Xu, X

Purpose: There are clinical decision challenges to select optimal treatment positions for left-sided breast cancer patients—supine free breathing (FB), supine Deep Inspiration Breath Hold (DIBH) and prone free breathing (prone). Physicians often make the decision based on experiences and trials, which might not always result optimal OAR doses. We herein propose a mathematical model to predict the lowest OAR doses among these three positions, providing a quantitative tool for corresponding clinical decision. Methods: Patients were scanned in FB, DIBH, and prone positions under an IRB approved protocol. Tangential beam plans were generated for each position, and OAR doses were calculated.more » The position with least OAR doses is defined as the optimal position. The following features were extracted from each scan to build the model: heart, ipsilateral lung, breast volume, in-field heart, ipsilateral lung volume, distance between heart and target, laterality of heart, and dose to heart and ipsilateral lung. Principal Components Analysis (PCA) was applied to remove the co-linearity of the input data and also to lower the data dimensionality. Feature selection, another method to reduce dimensionality, was applied as a comparison. Support Vector Machine (SVM) was then used for classification. Thirtyseven patient data were acquired; up to now, five patient plans were available. K-fold cross validation was used to validate the accuracy of the classifier model with small training size. Results: The classification results and K-fold cross validation demonstrated the model is capable of predicting the optimal position for patients. The accuracy of K-fold cross validations has reached 80%. Compared to PCA, feature selection allows causal features of dose to be determined. This provides more clinical insights. Conclusion: The proposed classification system appeared to be feasible. We are generating plans for the rest of the 37 patient images, and more statistically significant results are to be presented.« less

Interdicting an Adversary’s Economy Viewed As a Trade Sanction Inoperability Input Output Model

DTIC Science & Technology

2017-03-01

set of sectors. The design of an economic sanction, in the context of this thesis, is the selection of the sector or set of sectors to sanction...We propose two optimization models. The first, the Trade Sanction Inoperability Input-output Model (TS-IIM), selects the sector or set of sectors that...Interdependency analysis: Extensions to demand reduction inoperability input-output modeling and portfolio selection . Unpublished doctoral dissertation

Recognizing Banknote Fitness with a Visible Light One Dimensional Line Image Sensor

PubMed Central

Pham, Tuyen Danh; Park, Young Ho; Kwon, Seung Yong; Nguyen, Dat Tien; Vokhidov, Husan; Park, Kang Ryoung; Jeong, Dae Sik; Yoon, Sungsoo

2015-01-01

In general, dirty banknotes that have creases or soiled surfaces should be replaced by new banknotes, whereas clean banknotes should be recirculated. Therefore, the accurate classification of banknote fitness when sorting paper currency is an important and challenging task. Most previous research has focused on sensors that used visible, infrared, and ultraviolet light. Furthermore, there was little previous research on the fitness classification for Indian paper currency. Therefore, we propose a new method for classifying the fitness of Indian banknotes, with a one-dimensional line image sensor that uses only visible light. The fitness of banknotes is usually determined by various factors such as soiling, creases, and tears, etc. although we just consider banknote soiling in our research. This research is novel in the following four ways: first, there has been little research conducted on fitness classification for the Indian Rupee using visible-light images. Second, the classification is conducted based on the features extracted from the regions of interest (ROIs), which contain little texture. Third, 1-level discrete wavelet transformation (DWT) is used to extract the features for discriminating between fit and unfit banknotes. Fourth, the optimal DWT features that represent the fitness and unfitness of banknotes are selected based on linear regression analysis with ground-truth data measured by densitometer. In addition, the selected features are used as the inputs to a support vector machine (SVM) for the final classification of banknote fitness. Experimental results showed that our method outperforms other methods. PMID:26343654

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.

Monte Carlo simulation for uncertainty estimation on structural data in implicit 3-D geological modeling, a guide for disturbance distribution selection and parameterization

NASA Astrophysics Data System (ADS)

Pakyuz-Charrier, Evren; Lindsay, Mark; Ogarko, Vitaliy; Giraud, Jeremie; Jessell, Mark

2018-04-01

Three-dimensional (3-D) geological structural modeling aims to determine geological information in a 3-D space using structural data (foliations and interfaces) and topological rules as inputs. This is necessary in any project in which the properties of the subsurface matters; they express our understanding of geometries in depth. For that reason, 3-D geological models have a wide range of practical applications including but not restricted to civil engineering, the oil and gas industry, the mining industry, and water management. These models, however, are fraught with uncertainties originating from the inherent flaws of the modeling engines (working hypotheses, interpolator's parameterization) and the inherent lack of knowledge in areas where there are no observations combined with input uncertainty (observational, conceptual and technical errors). Because 3-D geological models are often used for impactful decision-making it is critical that all 3-D geological models provide accurate estimates of uncertainty. This paper's focus is set on the effect of structural input data measurement uncertainty propagation in implicit 3-D geological modeling. This aim is achieved using Monte Carlo simulation for uncertainty estimation (MCUE), a stochastic method which samples from predefined disturbance probability distributions that represent the uncertainty of the original input data set. MCUE is used to produce hundreds to thousands of altered unique data sets. The altered data sets are used as inputs to produce a range of plausible 3-D models. The plausible models are then combined into a single probabilistic model as a means to propagate uncertainty from the input data to the final model. In this paper, several improved methods for MCUE are proposed. The methods pertain to distribution selection for input uncertainty, sample analysis and statistical consistency of the sampled distribution. Pole vector sampling is proposed as a more rigorous alternative than dip vector sampling for planar features and the use of a Bayesian approach to disturbance distribution parameterization is suggested. The influence of incorrect disturbance distributions is discussed and propositions are made and evaluated on synthetic and realistic cases to address the sighted issues. The distribution of the errors of the observed data (i.e., scedasticity) is shown to affect the quality of prior distributions for MCUE. Results demonstrate that the proposed workflows improve the reliability of uncertainty estimation and diminish the occurrence of artifacts.

A novel Gaussian process regression model for state-of-health estimation of lithium-ion battery using charging curve

NASA Astrophysics Data System (ADS)

Yang, Duo; Zhang, Xu; Pan, Rui; Wang, Yujie; Chen, Zonghai

2018-04-01

The state-of-health (SOH) estimation is always a crucial issue for lithium-ion batteries. In order to provide an accurate and reliable SOH estimation, a novel Gaussian process regression (GPR) model based on charging curve is proposed in this paper. Different from other researches where SOH is commonly estimated by cycle life, in this work four specific parameters extracted from charging curves are used as inputs of the GPR model instead of cycle numbers. These parameters can reflect the battery aging phenomenon from different angles. The grey relational analysis method is applied to analyze the relational grade between selected features and SOH. On the other hand, some adjustments are made in the proposed GPR model. Covariance function design and the similarity measurement of input variables are modified so as to improve the SOH estimate accuracy and adapt to the case of multidimensional input. Several aging data from NASA data repository are used for demonstrating the estimation effect by the proposed method. Results show that the proposed method has high SOH estimation accuracy. Besides, a battery with dynamic discharging profile is used to verify the robustness and reliability of this method.

Sensitivity Analysis for Probabilistic Neural Network Structure Reduction.

PubMed

Kowalski, Piotr A; Kusy, Maciej

2018-05-01

In this paper, we propose the use of local sensitivity analysis (LSA) for the structure simplification of the probabilistic neural network (PNN). Three algorithms are introduced. The first algorithm applies LSA to the PNN input layer reduction by selecting significant features of input patterns. The second algorithm utilizes LSA to remove redundant pattern neurons of the network. The third algorithm combines the proposed two and constitutes the solution of how they can work together. PNN with a product kernel estimator is used, where each multiplicand computes a one-dimensional Cauchy function. Therefore, the smoothing parameter is separately calculated for each dimension by means of the plug-in method. The classification qualities of the reduced and full structure PNN are compared. Furthermore, we evaluate the performance of PNN, for which global sensitivity analysis (GSA) and the common reduction methods are applied, both in the input layer and the pattern layer. The models are tested on the classification problems of eight repository data sets. A 10-fold cross validation procedure is used to determine the prediction ability of the networks. Based on the obtained results, it is shown that the LSA can be used as an alternative PNN reduction approach.

Orientation selectivity in inhibition-dominated networks of spiking neurons: effect of single neuron properties and network dynamics.

PubMed

Sadeh, Sadra; Rotter, Stefan

2015-01-01

The neuronal mechanisms underlying the emergence of orientation selectivity in the primary visual cortex of mammals are still elusive. In rodents, visual neurons show highly selective responses to oriented stimuli, but neighboring neurons do not necessarily have similar preferences. Instead of a smooth map, one observes a salt-and-pepper organization of orientation selectivity. Modeling studies have recently confirmed that balanced random networks are indeed capable of amplifying weakly tuned inputs and generating highly selective output responses, even in absence of feature-selective recurrent connectivity. Here we seek to elucidate the neuronal mechanisms underlying this phenomenon by resorting to networks of integrate-and-fire neurons, which are amenable to analytic treatment. Specifically, in networks of perfect integrate-and-fire neurons, we observe that highly selective and contrast invariant output responses emerge, very similar to networks of leaky integrate-and-fire neurons. We then demonstrate that a theory based on mean firing rates and the detailed network topology predicts the output responses, and explains the mechanisms underlying the suppression of the common-mode, amplification of modulation, and contrast invariance. Increasing inhibition dominance in our networks makes the rectifying nonlinearity more prominent, which in turn adds some distortions to the otherwise essentially linear prediction. An extension of the linear theory can account for all the distortions, enabling us to compute the exact shape of every individual tuning curve in our networks. We show that this simple form of nonlinearity adds two important properties to orientation selectivity in the network, namely sharpening of tuning curves and extra suppression of the modulation. The theory can be further extended to account for the nonlinearity of the leaky model by replacing the rectifier by the appropriate smooth input-output transfer function. These results are robust and do not depend on the state of network dynamics, and hold equally well for mean-driven and fluctuation-driven regimes of activity.

Orientation Selectivity in Inhibition-Dominated Networks of Spiking Neurons: Effect of Single Neuron Properties and Network Dynamics

PubMed Central

Sadeh, Sadra; Rotter, Stefan

2015-01-01

The neuronal mechanisms underlying the emergence of orientation selectivity in the primary visual cortex of mammals are still elusive. In rodents, visual neurons show highly selective responses to oriented stimuli, but neighboring neurons do not necessarily have similar preferences. Instead of a smooth map, one observes a salt-and-pepper organization of orientation selectivity. Modeling studies have recently confirmed that balanced random networks are indeed capable of amplifying weakly tuned inputs and generating highly selective output responses, even in absence of feature-selective recurrent connectivity. Here we seek to elucidate the neuronal mechanisms underlying this phenomenon by resorting to networks of integrate-and-fire neurons, which are amenable to analytic treatment. Specifically, in networks of perfect integrate-and-fire neurons, we observe that highly selective and contrast invariant output responses emerge, very similar to networks of leaky integrate-and-fire neurons. We then demonstrate that a theory based on mean firing rates and the detailed network topology predicts the output responses, and explains the mechanisms underlying the suppression of the common-mode, amplification of modulation, and contrast invariance. Increasing inhibition dominance in our networks makes the rectifying nonlinearity more prominent, which in turn adds some distortions to the otherwise essentially linear prediction. An extension of the linear theory can account for all the distortions, enabling us to compute the exact shape of every individual tuning curve in our networks. We show that this simple form of nonlinearity adds two important properties to orientation selectivity in the network, namely sharpening of tuning curves and extra suppression of the modulation. The theory can be further extended to account for the nonlinearity of the leaky model by replacing the rectifier by the appropriate smooth input-output transfer function. These results are robust and do not depend on the state of network dynamics, and hold equally well for mean-driven and fluctuation-driven regimes of activity. PMID:25569445

Fast Solution in Sparse LDA for Binary Classification

NASA Technical Reports Server (NTRS)

Moghaddam, Baback

2010-01-01

An algorithm that performs sparse linear discriminant analysis (Sparse-LDA) finds near-optimal solutions in far less time than the prior art when specialized to binary classification (of 2 classes). Sparse-LDA is a type of feature- or variable- selection problem with numerous applications in statistics, machine learning, computer vision, computational finance, operations research, and bio-informatics. Because of its combinatorial nature, feature- or variable-selection problems are NP-hard or computationally intractable in cases involving more than 30 variables or features. Therefore, one typically seeks approximate solutions by means of greedy search algorithms. The prior Sparse-LDA algorithm was a greedy algorithm that considered the best variable or feature to add/ delete to/ from its subsets in order to maximally discriminate between multiple classes of data. The present algorithm is designed for the special but prevalent case of 2-class or binary classification (e.g. 1 vs. 0, functioning vs. malfunctioning, or change versus no change). The present algorithm provides near-optimal solutions on large real-world datasets having hundreds or even thousands of variables or features (e.g. selecting the fewest wavelength bands in a hyperspectral sensor to do terrain classification) and does so in typical computation times of minutes as compared to days or weeks as taken by the prior art. Sparse LDA requires solving generalized eigenvalue problems for a large number of variable subsets (represented by the submatrices of the input within-class and between-class covariance matrices). In the general (fullrank) case, the amount of computation scales at least cubically with the number of variables and thus the size of the problems that can be solved is limited accordingly. However, in binary classification, the principal eigenvalues can be found using a special analytic formula, without resorting to costly iterative techniques. The present algorithm exploits this analytic form along with the inherent sequential nature of greedy search itself. Together this enables the use of highly-efficient partitioned-matrix-inverse techniques that result in large speedups of computation in both the forward-selection and backward-elimination stages of greedy algorithms in general.

Search time critically depends on irrelevant subset size in visual search.

PubMed

Benjamins, Jeroen S; Hooge, Ignace T C; van Elst, Jacco C; Wertheim, Alexander H; Verstraten, Frans A J

2009-02-01

In order for our visual system to deal with the massive amount of sensory input, some of this input is discarded, while other parts are processed [Wolfe, J. M. (1994). Guided search 2.0: a revised model of visual search. Psychonomic Bulletin and Review, 1, 202-238]. From the visual search literature it is unclear how well one set of items can be selected that differs in only one feature from target (a 1F set), while another set of items can be ignored that differs in two features from target (a 2F set). We systematically varied the percentage of 2F non-targets to determine the contribution of these non-targets to search behaviour. Increasing the percentage 2F non-targets, that have to be ignored, was expected to result in increasingly faster search, since it decreases the size of 1F set that has to be searched. Observers searched large displays for a target in the 1F set with a variable percentage of 2F non-targets. Interestingly, when the search displays contained 5% 2F non-targets, the search time was longer compared to the search time in other conditions. This effect of 2F non-targets on performance was independent of set size. An inspection of the saccades revealed that saccade target selection did not contribute to the longer search times in displays with 5% 2F non-targets. Occurrence of longer search times in displays containing 5% 2F non-targets might be attributed to covert processes related to visual analysis of the fixated part of the display. Apparently, visual search performance critically depends on the percentage of irrelevant 2F non-targets.

New nonlinear features for inspection, robotics, and face recognition

NASA Astrophysics Data System (ADS)

Casasent, David P.; Talukder, Ashit

1999-10-01

Classification of real-time X-ray images of randomly oriented touching pistachio nuts is discussed. The ultimate objective is the development of a system for automated non- invasive detection of defective product items on a conveyor belt. We discuss the extraction of new features that allow better discrimination between damaged and clean items (pistachio nuts). This feature extraction and classification stage is the new aspect of this paper; our new maximum representation and discriminating feature (MRDF) extraction method computes nonlinear features that are used as inputs to a new modified k nearest neighbor classifier. In this work, the MRDF is applied to standard features (rather than iconic data). The MRDF is robust to various probability distributions of the input class and is shown to provide good classification and new ROC (receiver operating characteristic) data. Other applications of these new feature spaces in robotics and face recognition are also noted.

New feature extraction method for classification of agricultural products from x-ray images

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.; Lee, Ha-Woon; Keagy, Pamela M.; Schatzki, Thomas F.

1999-01-01

Classification of real-time x-ray images of randomly oriented touching pistachio nuts is discussed. The ultimate objective is the development of a system for automated non- invasive detection of defective product items on a conveyor belt. We discuss the extraction of new features that allow better discrimination between damaged and clean items. This feature extraction and classification stage is the new aspect of this paper; our new maximum representation and discrimination between damaged and clean items. This feature extraction and classification stage is the new aspect of this paper; our new maximum representation and discriminating feature (MRDF) extraction method computes nonlinear features that are used as inputs to a new modified k nearest neighbor classifier. In this work the MRDF is applied to standard features. The MRDF is robust to various probability distributions of the input class and is shown to provide good classification and new ROC data.

Community models for wildlife impact assessment: a review of concepts and approaches

USGS Publications Warehouse

Schroeder, Richard L.

1987-01-01

The first two sections of this paper are concerned with defining and bounding communities, and describing those attributes of the community that are quantifiable and suitable for wildlife impact assessment purposes. Prior to the development or use of a community model, it is important to have a clear understanding of the concept of a community and a knowledge of the types of community attributes that can serve as outputs for the development of models. Clearly defined, unambiguous model outputs are essential for three reasons: (1) to ensure that the measured community attributes relate to the wildlife resource objectives of the study; (2) to allow testing of the outputs in experimental studies, to determine accuracy, and to allow for improvements based on such testing; and (3) to enable others to clearly understand the community attribute that has been measured. The third section of this paper described input variables that may be used to predict various community attributes. These input variables do not include direct measures of wildlife populations. Most impact assessments involve projects that result in drastic changes in habitat, such as changes in land use, vegetation, or available area. Therefore, the model input variables described in this section deal primarily with habitat related features. Several existing community models are described in the fourth section of this paper. A general description of each model is provided, including the nature of the input variables and the model output. The logic and assumptions of each model are discussed, along with data requirements needed to use the model. The fifth section provides guidance on the selection and development of community models. Identification of the community attribute that is of concern will determine the type of model most suitable for a particular application. This section provides guidelines on selected an existing model, as well as a discussion of the major steps to be followed in modifying an existing model or developing a new model. Considerations associated with the use of community models with the Habitat Evaluation Procedures are also discussed. The final section of the paper summarizes major findings of interest to field biologists and provides recommendations concerning the implementation of selected concepts in wildlife community analyses.

Using different classification models in wheat grading utilizing visual features

NASA Astrophysics Data System (ADS)

Basati, Zahra; Rasekh, Mansour; Abbaspour-Gilandeh, Yousef

2018-04-01

Wheat is one of the most important strategic crops in Iran and in the world. The major component that distinguishes wheat from other grains is the gluten section. In Iran, sunn pest is one of the most important factors influencing the characteristics of wheat gluten and in removing it from a balanced state. The existence of bug-damaged grains in wheat will reduce the quality and price of the product. In addition, damaged grains reduce the enrichment of wheat and the quality of bread products. In this study, after preprocessing and segmentation of images, 25 features including 9 colour features, 10 morphological features, and 6 textual statistical features were extracted so as to classify healthy and bug-damaged wheat grains of Azar cultivar of four levels of moisture content (9, 11.5, 14 and 16.5% w.b.) and two lighting colours (yellow light, the composition of yellow and white lights). Using feature selection methods in the WEKA software and the CfsSubsetEval evaluator, 11 features were chosen as inputs of artificial neural network, decision tree and discriment analysis classifiers. The results showed that the decision tree with the J.48 algorithm had the highest classification accuracy of 90.20%. This was followed by artificial neural network classifier with the topology of 11-19-2 and discrimient analysis classifier at 87.46 and 81.81%, respectively

Deep Learning Based Binaural Speech Separation in Reverberant Environments.

PubMed

Zhang, Xueliang; Wang, DeLiang

2017-05-01

Speech signal is usually degraded by room reverberation and additive noises in real environments. This paper focuses on separating target speech signal in reverberant conditions from binaural inputs. Binaural separation is formulated as a supervised learning problem, and we employ deep learning to map from both spatial and spectral features to a training target. With binaural inputs, we first apply a fixed beamformer and then extract several spectral features. A new spatial feature is proposed and extracted to complement the spectral features. The training target is the recently suggested ideal ratio mask. Systematic evaluations and comparisons show that the proposed system achieves very good separation performance and substantially outperforms related algorithms under challenging multi-source and reverberant environments.

Visual attention mitigates information loss in small- and large-scale neural codes.

PubMed

Sprague, Thomas C; Saproo, Sameer; Serences, John T

2015-04-01

The visual system transforms complex inputs into robust and parsimonious neural codes that efficiently guide behavior. Because neural communication is stochastic, the amount of encoded visual information necessarily decreases with each synapse. This constraint requires that sensory signals are processed in a manner that protects information about relevant stimuli from degradation. Such selective processing--or selective attention--is implemented via several mechanisms, including neural gain and changes in tuning properties. However, examining each of these effects in isolation obscures their joint impact on the fidelity of stimulus feature representations by large-scale population codes. Instead, large-scale activity patterns can be used to reconstruct representations of relevant and irrelevant stimuli, thereby providing a holistic understanding about how neuron-level modulations collectively impact stimulus encoding. Copyright © 2015 Elsevier Ltd. All rights reserved.

Web-based newborn screening system for metabolic diseases: machine learning versus clinicians.

PubMed

Chen, Wei-Hsin; Hsieh, Sheau-Ling; Hsu, Kai-Ping; Chen, Han-Ping; Su, Xing-Yu; Tseng, Yi-Ju; Chien, Yin-Hsiu; Hwu, Wuh-Liang; Lai, Feipei

2013-05-23

A hospital information system (HIS) that integrates screening data and interpretation of the data is routinely requested by hospitals and parents. However, the accuracy of disease classification may be low because of the disease characteristics and the analytes used for classification. The objective of this study is to describe a system that enhanced the neonatal screening system of the Newborn Screening Center at the National Taiwan University Hospital. The system was designed and deployed according to a service-oriented architecture (SOA) framework under the Web services .NET environment. The system consists of sample collection, testing, diagnosis, evaluation, treatment, and follow-up services among collaborating hospitals. To improve the accuracy of newborn screening, machine learning and optimal feature selection mechanisms were investigated for screening newborns for inborn errors of metabolism. The framework of the Newborn Screening Hospital Information System (NSHIS) used the embedded Health Level Seven (HL7) standards for data exchanges among heterogeneous platforms integrated by Web services in the C# language. In this study, machine learning classification was used to predict phenylketonuria (PKU), hypermethioninemia, and 3-methylcrotonyl-CoA-carboxylase (3-MCC) deficiency. The classification methods used 347,312 newborn dried blood samples collected at the Center between 2006 and 2011. Of these, 220 newborns had values over the diagnostic cutoffs (positive cases) and 1557 had values that were over the screening cutoffs but did not meet the diagnostic cutoffs (suspected cases). The original 35 analytes and the manifested features were ranked based on F score, then combinations of the top 20 ranked features were selected as input features to support vector machine (SVM) classifiers to obtain optimal feature sets. These feature sets were tested using 5-fold cross-validation and optimal models were generated. The datasets collected in year 2011 were used as predicting cases. The feature selection strategies were implemented and the optimal markers for PKU, hypermethioninemia, and 3-MCC deficiency were obtained. The results of the machine learning approach were compared with the cutoff scheme. The number of the false positive cases were reduced from 21 to 2 for PKU, from 30 to 10 for hypermethioninemia, and 209 to 46 for 3-MCC deficiency. This SOA Web service-based newborn screening system can accelerate screening procedures effectively and efficiently. An SVM learning methodology for PKU, hypermethioninemia, and 3-MCC deficiency metabolic diseases classification, including optimal feature selection strategies, is presented. By adopting the results of this study, the number of suspected cases could be reduced dramatically.

Web-Based Newborn Screening System for Metabolic Diseases: Machine Learning Versus Clinicians

PubMed Central

Chen, Wei-Hsin; Hsu, Kai-Ping; Chen, Han-Ping; Su, Xing-Yu; Tseng, Yi-Ju; Chien, Yin-Hsiu; Hwu, Wuh-Liang; Lai, Feipei

2013-01-01

Background A hospital information system (HIS) that integrates screening data and interpretation of the data is routinely requested by hospitals and parents. However, the accuracy of disease classification may be low because of the disease characteristics and the analytes used for classification. Objective The objective of this study is to describe a system that enhanced the neonatal screening system of the Newborn Screening Center at the National Taiwan University Hospital. The system was designed and deployed according to a service-oriented architecture (SOA) framework under the Web services .NET environment. The system consists of sample collection, testing, diagnosis, evaluation, treatment, and follow-up services among collaborating hospitals. To improve the accuracy of newborn screening, machine learning and optimal feature selection mechanisms were investigated for screening newborns for inborn errors of metabolism. Methods The framework of the Newborn Screening Hospital Information System (NSHIS) used the embedded Health Level Seven (HL7) standards for data exchanges among heterogeneous platforms integrated by Web services in the C# language. In this study, machine learning classification was used to predict phenylketonuria (PKU), hypermethioninemia, and 3-methylcrotonyl-CoA-carboxylase (3-MCC) deficiency. The classification methods used 347,312 newborn dried blood samples collected at the Center between 2006 and 2011. Of these, 220 newborns had values over the diagnostic cutoffs (positive cases) and 1557 had values that were over the screening cutoffs but did not meet the diagnostic cutoffs (suspected cases). The original 35 analytes and the manifested features were ranked based on F score, then combinations of the top 20 ranked features were selected as input features to support vector machine (SVM) classifiers to obtain optimal feature sets. These feature sets were tested using 5-fold cross-validation and optimal models were generated. The datasets collected in year 2011 were used as predicting cases. Results The feature selection strategies were implemented and the optimal markers for PKU, hypermethioninemia, and 3-MCC deficiency were obtained. The results of the machine learning approach were compared with the cutoff scheme. The number of the false positive cases were reduced from 21 to 2 for PKU, from 30 to 10 for hypermethioninemia, and 209 to 46 for 3-MCC deficiency. Conclusions This SOA Web service–based newborn screening system can accelerate screening procedures effectively and efficiently. An SVM learning methodology for PKU, hypermethioninemia, and 3-MCC deficiency metabolic diseases classification, including optimal feature selection strategies, is presented. By adopting the results of this study, the number of suspected cases could be reduced dramatically. PMID:23702487

Automated Inference of Chemical Discriminants of Biological Activity.

PubMed

Raschka, Sebastian; Scott, Anne M; Huertas, Mar; Li, Weiming; Kuhn, Leslie A

2018-01-01

Ligand-based virtual screening has become a standard technique for the efficient discovery of bioactive small molecules. Following assays to determine the activity of compounds selected by virtual screening, or other approaches in which dozens to thousands of molecules have been tested, machine learning techniques make it straightforward to discover the patterns of chemical groups that correlate with the desired biological activity. Defining the chemical features that generate activity can be used to guide the selection of molecules for subsequent rounds of screening and assaying, as well as help design new, more active molecules for organic synthesis.The quantitative structure-activity relationship machine learning protocols we describe here, using decision trees, random forests, and sequential feature selection, take as input the chemical structure of a single, known active small molecule (e.g., an inhibitor, agonist, or substrate) for comparison with the structure of each tested molecule. Knowledge of the atomic structure of the protein target and its interactions with the active compound are not required. These protocols can be modified and applied to any data set that consists of a series of measured structural, chemical, or other features for each tested molecule, along with the experimentally measured value of the response variable you would like to predict or optimize for your project, for instance, inhibitory activity in a biological assay or ΔG binding . To illustrate the use of different machine learning algorithms, we step through the analysis of a dataset of inhibitor candidates from virtual screening that were tested recently for their ability to inhibit GPCR-mediated signaling in a vertebrate.

Inferring Nonlinear Neuronal Computation Based on Physiologically Plausible Inputs

PubMed Central

McFarland, James M.; Cui, Yuwei; Butts, Daniel A.

2013-01-01

The computation represented by a sensory neuron's response to stimuli is constructed from an array of physiological processes both belonging to that neuron and inherited from its inputs. Although many of these physiological processes are known to be nonlinear, linear approximations are commonly used to describe the stimulus selectivity of sensory neurons (i.e., linear receptive fields). Here we present an approach for modeling sensory processing, termed the Nonlinear Input Model (NIM), which is based on the hypothesis that the dominant nonlinearities imposed by physiological mechanisms arise from rectification of a neuron's inputs. Incorporating such ‘upstream nonlinearities’ within the standard linear-nonlinear (LN) cascade modeling structure implicitly allows for the identification of multiple stimulus features driving a neuron's response, which become directly interpretable as either excitatory or inhibitory. Because its form is analogous to an integrate-and-fire neuron receiving excitatory and inhibitory inputs, model fitting can be guided by prior knowledge about the inputs to a given neuron, and elements of the resulting model can often result in specific physiological predictions. Furthermore, by providing an explicit probabilistic model with a relatively simple nonlinear structure, its parameters can be efficiently optimized and appropriately regularized. Parameter estimation is robust and efficient even with large numbers of model components and in the context of high-dimensional stimuli with complex statistical structure (e.g. natural stimuli). We describe detailed methods for estimating the model parameters, and illustrate the advantages of the NIM using a range of example sensory neurons in the visual and auditory systems. We thus present a modeling framework that can capture a broad range of nonlinear response functions while providing physiologically interpretable descriptions of neural computation. PMID:23874185

Improved artificial neural networks in prediction of malignancy of lesions in contrast-enhanced MR-mammography.

PubMed

Vomweg, T W; Buscema, M; Kauczor, H U; Teifke, A; Intraligi, M; Terzi, S; Heussel, C P; Achenbach, T; Rieker, O; Mayer, D; Thelen, M

2003-09-01

The aim of this study was to evaluate the capability of improved artificial neural networks (ANN) and additional novel training methods in distinguishing between benign and malignant breast lesions in contrast-enhanced magnetic resonance-mammography (MRM). A total of 604 histologically proven cases of contrast-enhanced lesions of the female breast at MRI were analyzed. Morphological, dynamic and clinical parameters were collected and stored in a database. The data set was divided into several groups using random or experimental methods [Training & Testing (T&T) algorithm] to train and test different ANNs. An additional novel computer program for input variable selection was applied. Sensitivity and specificity were calculated and compared with a statistical method and an expert radiologist. After optimization of the distribution of cases among the training and testing sets by the T & T algorithm and the reduction of input variables by the Input Selection procedure a highly sophisticated ANN achieved a sensitivity of 93.6% and a specificity of 91.9% in predicting malignancy of lesions within an independent prediction sample set. The best statistical method reached a sensitivity of 90.5% and a specificity of 68.9%. An expert radiologist performed better than the statistical method but worse than the ANN (sensitivity 92.1%, specificity 85.6%). Features extracted out of dynamic contrast-enhanced MRM and additional clinical data can be successfully analyzed by advanced ANNs. The quality of the resulting network strongly depends on the training methods, which are improved by the use of novel training tools. The best results of an improved ANN outperform expert radiologists.

Olfactory Bulb Deep Short-Axon Cells Mediate Widespread Inhibition of Tufted Cell Apical Dendrites.

PubMed

Burton, Shawn D; LaRocca, Greg; Liu, Annie; Cheetham, Claire E J; Urban, Nathaniel N

2017-02-01

In the main olfactory bulb (MOB), the first station of sensory processing in the olfactory system, GABAergic interneuron signaling shapes principal neuron activity to regulate olfaction. However, a lack of known selective markers for MOB interneurons has strongly impeded cell-type-selective investigation of interneuron function. Here, we identify the first selective marker of glomerular layer-projecting deep short-axon cells (GL-dSACs) and investigate systematically the structure, abundance, intrinsic physiology, feedforward sensory input, neuromodulation, synaptic output, and functional role of GL-dSACs in the mouse MOB circuit. GL-dSACs are located in the internal plexiform layer, where they integrate centrifugal cholinergic input with highly convergent feedforward sensory input. GL-dSAC axons arborize extensively across the glomerular layer to provide highly divergent yet selective output onto interneurons and principal tufted cells. GL-dSACs are thus capable of shifting the balance of principal tufted versus mitral cell activity across large expanses of the MOB in response to diverse sensory and top-down neuromodulatory input. The identification of cell-type-selective molecular markers has fostered tremendous insight into how distinct interneurons shape sensory processing and behavior. In the main olfactory bulb (MOB), inhibitory circuits regulate the activity of principal cells precisely to drive olfactory-guided behavior. However, selective markers for MOB interneurons remain largely unknown, limiting mechanistic understanding of olfaction. Here, we identify the first selective marker of a novel population of deep short-axon cell interneurons with superficial axonal projections to the sensory input layer of the MOB. Using this marker, together with immunohistochemistry, acute slice electrophysiology, and optogenetic circuit mapping, we reveal that this novel interneuron population integrates centrifugal cholinergic input with broadly tuned feedforward sensory input to modulate principal cell activity selectively. Copyright © 2017 the authors 0270-6474/17/371117-22$15.00/0.

Enhancement of the CAVE computer code. [aerodynamic heating package for nose cones and scramjet engine sidewalls

NASA Technical Reports Server (NTRS)

Rathjen, K. A.; Burk, H. O.

1983-01-01

The computer code CAVE (Conduction Analysis via Eigenvalues) is a convenient and efficient computer code for predicting two dimensional temperature histories within thermal protection systems for hypersonic vehicles. The capabilities of CAVE were enhanced by incorporation of the following features into the code: real gas effects in the aerodynamic heating predictions, geometry and aerodynamic heating package for analyses of cone shaped bodies, input option to change from laminar to turbulent heating predictions on leading edges, modification to account for reduction in adiabatic wall temperature with increase in leading sweep, geometry package for two dimensional scramjet engine sidewall, with an option for heat transfer to external and internal surfaces, print out modification to provide tables of select temperatures for plotting and storage, and modifications to the radiation calculation procedure to eliminate temperature oscillations induced by high heating rates. These new features are described.

The application of improved NeuroEvolution of Augmenting Topologies neural network in Marcellus Shale lithofacies prediction

NASA Astrophysics Data System (ADS)

Wang, Guochang; Cheng, Guojian; Carr, Timothy R.

2013-04-01

The organic-rich Marcellus Shale was deposited in a foreland basin during Middle Devonian. In terms of mineral composition and organic matter richness, we define seven mudrock lithofacies: three organic-rich lithofacies and four organic-poor lithofacies. The 3D lithofacies model is very helpful to determine geologic and engineering sweet spots, and consequently useful for designing horizontal well trajectories and stimulation strategies. The NeuroEvolution of Augmenting Topologies (NEAT) is relatively new idea in the design of neural networks, and shed light on classification (i.e., Marcellus Shale lithofacies prediction). We have successfully enhanced the capability and efficiency of NEAT in three aspects. First, we introduced two new attributes of node gene, the node location and recurrent connection (RCC), to increase the calculation efficiency. Second, we evolved the population size from an initial small value to big, instead of using the constant value, which saves time and computer memory, especially for complex learning tasks. Third, in multiclass pattern recognition problems, we combined feature selection of input variables and modular neural network to automatically select input variables and optimize network topology for each binary classifier. These improvements were tested and verified by true if an odd number of its arguments are true and false otherwise (XOR) experiments, and were powerful for classification.

Proceedings of the 2015 A.S.P.E.N. Research Workshop - Taste Signaling: Impact on Food Selection, Intake, and Health

PubMed Central

Spector, Alan C.; le Roux, Carel W; Munger, Steven D.; Travers, Susan P.; Sclafani, Anthony; Mennella, Julie A.

2016-01-01

This paper summarizes research findings from six experts in the field of taste and feeding that were presented at the 2015 ASPEN Research Workshop. The theme was focused on the interaction of taste signals with those of a postingestive origin and how this contributes to regulation of food intake through both physiological and learning processes. Gastric bypass results in exceptional loss of fat mass, increases in circulating levels of key gut peptides, some of which are also expressed along with their cognate receptors in taste buds. Changes in taste preference and food selection in both bariatric surgery patients and rodent models have been reported. Accordingly, the effects of this surgery on taste-related behavior were examined. The conservation of receptor and peptide signaling mechanisms in gustatory and extraoral tissues was discussed in the context of taste responsiveness and the regulation of metabolism. New findings detailing the features of neural circuits between the caudal nucleus of the solitary tract (NST), receiving visceral input from the vagus nerve, and the rostral NST, receiving taste input, were discussed, as was how early life experience with taste stimuli and learned associations between flavor and postoral consequences of nutrients can exert potent and long-lasting effects on feeding PMID:26598504

xiSPEC: web-based visualization, analysis and sharing of proteomics data.

PubMed

Kolbowski, Lars; Combe, Colin; Rappsilber, Juri

2018-05-08

We present xiSPEC, a standard compliant, next-generation web-based spectrum viewer for visualizing, analyzing and sharing mass spectrometry data. Peptide-spectrum matches from standard proteomics and cross-linking experiments are supported. xiSPEC is to date the only browser-based tool supporting the standardized file formats mzML and mzIdentML defined by the proteomics standards initiative. Users can either upload data directly or select files from the PRIDE data repository as input. xiSPEC allows users to save and share their datasets publicly or password protected for providing access to collaborators or readers and reviewers of manuscripts. The identification table features advanced interaction controls and spectra are presented in three interconnected views: (i) annotated mass spectrum, (ii) peptide sequence fragmentation key and (iii) quality control error plots of matched fragments. Highlighting or selecting data points in any view is represented in all other views. Views are interactive scalable vector graphic elements, which can be exported, e.g. for use in publication. xiSPEC allows for re-annotation of spectra for easy hypothesis testing by modifying input data. xiSPEC is freely accessible at http://spectrumviewer.org and the source code is openly available on https://github.com/Rappsilber-Laboratory/xiSPEC.

Identification of compound-protein interactions through the analysis of gene ontology, KEGG enrichment for proteins and molecular fragments of compounds.

PubMed

Chen, Lei; Zhang, Yu-Hang; Zheng, Mingyue; Huang, Tao; Cai, Yu-Dong

2016-12-01

Compound-protein interactions play important roles in every cell via the recognition and regulation of specific functional proteins. The correct identification of compound-protein interactions can lead to a good comprehension of this complicated system and provide useful input for the investigation of various attributes of compounds and proteins. In this study, we attempted to understand this system by extracting properties from both proteins and compounds, in which proteins were represented by gene ontology and KEGG pathway enrichment scores and compounds were represented by molecular fragments. Advanced feature selection methods, including minimum redundancy maximum relevance, incremental feature selection, and the basic machine learning algorithm random forest, were used to analyze these properties and extract core factors for the determination of actual compound-protein interactions. Compound-protein interactions reported in The Binding Databases were used as positive samples. To improve the reliability of the results, the analytic procedure was executed five times using different negative samples. Simultaneously, five optimal prediction methods based on a random forest and yielding maximum MCCs of approximately 77.55 % were constructed and may be useful tools for the prediction of compound-protein interactions. This work provides new clues to understanding the system of compound-protein interactions by analyzing extracted core features. Our results indicate that compound-protein interactions are related to biological processes involving immune, developmental and hormone-associated pathways.

Exploring nonlinear feature space dimension reduction and data representation in breast CADx with Laplacian eigenmaps and t-SNE

PubMed Central

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

2010-01-01

Purpose: In this preliminary study, recently developed unsupervised nonlinear dimension reduction (DR) and data representation techniques were applied to computer-extracted breast lesion feature spaces across three separate imaging modalities: Ultrasound (U.S.) with 1126 cases, dynamic contrast enhanced magnetic resonance imaging with 356 cases, and full-field digital mammography with 245 cases. Two methods for nonlinear DR were explored: Laplacian eigenmaps [M. Belkin and P. Niyogi, “Laplacian eigenmaps for dimensionality reduction and data representation,” Neural Comput. 15, 1373–1396 (2003)] and t-distributed stochastic neighbor embedding (t-SNE) [L. van der Maaten and G. Hinton, “Visualizing data using t-SNE,” J. Mach. Learn. Res. 9, 2579–2605 (2008)]. Methods: These methods attempt to map originally high dimensional feature spaces to more human interpretable lower dimensional spaces while preserving both local and global information. The properties of these methods as applied to breast computer-aided diagnosis (CADx) were evaluated in the context of malignancy classification performance as well as in the visual inspection of the sparseness within the two-dimensional and three-dimensional mappings. Classification performance was estimated by using the reduced dimension mapped feature output as input into both linear and nonlinear classifiers: Markov chain Monte Carlo based Bayesian artificial neural network (MCMC-BANN) and linear discriminant analysis. The new techniques were compared to previously developed breast CADx methodologies, including automatic relevance determination and linear stepwise (LSW) feature selection, as well as a linear DR method based on principal component analysis. Using ROC analysis and 0.632+bootstrap validation, 95% empirical confidence intervals were computed for the each classifier’s AUC performance. Results: In the large U.S. data set, sample high performance results include, AUC0.632+=0.88 with 95% empirical bootstrap interval [0.787;0.895] for 13 ARD selected features and AUC0.632+=0.87 with interval [0.817;0.906] for four LSW selected features compared to 4D t-SNE mapping (from the original 81D feature space) giving AUC0.632+=0.90 with interval [0.847;0.919], all using the MCMC-BANN. Conclusions: Preliminary results appear to indicate capability for the new methods to match or exceed classification performance of current advanced breast lesion CADx algorithms. While not appropriate as a complete replacement of feature selection in CADx problems, DR techniques offer a complementary approach, which can aid elucidation of additional properties associated with the data. Specifically, the new techniques were shown to possess the added benefit of delivering sparse lower dimensional representations for visual interpretation, revealing intricate data structure of the feature space. PMID:20175497

A Secure and Reliable High-Performance Field Programmable Gate Array for Information Processing

DTIC Science & Technology

2012-03-01

receives a data token from its control input (shown as a horizontal arrow above). The value of this data token is used to select an input port. The input...dual of a merge. It receives a data token from its control input (shown as a horizontal arrow above). The value of this data token is used to select...Transactions on Computer-Aided Design of Intergrated Circuits and Systems, Vol. 26, No. 2, February 2007. [12] Cadence Design Systems, “Clock Domain

Color image segmentation with support vector machines: applications to road signs detection.

PubMed

Cyganek, Bogusław

2008-08-01

In this paper we propose efficient color segmentation method which is based on the Support Vector Machine classifier operating in a one-class mode. The method has been developed especially for the road signs recognition system, although it can be used in other applications. The main advantage of the proposed method comes from the fact that the segmentation of characteristic colors is performed not in the original but in the higher dimensional feature space. By this a better data encapsulation with a linear hypersphere can be usually achieved. Moreover, the classifier does not try to capture the whole distribution of the input data which is often difficult to achieve. Instead, the characteristic data samples, called support vectors, are selected which allow construction of the tightest hypersphere that encloses majority of the input data. Then classification of a test data simply consists in a measurement of its distance to a centre of the found hypersphere. The experimental results show high accuracy and speed of the proposed method.

A distributed data acquisition system for aeronautics test facilities

NASA Technical Reports Server (NTRS)

Fronek, Dennis L.; Setter, Robert N.; Blumenthal, Philip Z.; Smalley, Robert R.

1987-01-01

The NASA Lewis Research Center is in the process of installing a new data acquisition and display system. This new system will provide small and medium sized aeronautics test facilities with a state-of-the-art real-time data acquisition and display system. The new data system will provide for the acquisition of signals from a variety of instrumentation sources. They include analog measurements of temperatures, pressures, and other steady state voltage inputs; frequency inputs to measure speed and flow; discrete I/O for significant events, and modular instrument systems such as multiplexed pressure modules or electronic instrumentation with a IEEE 488 interface. The data system is designed to acquire data, convert it to engineering units, compute test dependent performance calculations, limit check selected channels or calculations, and display the information in alphanumeric or graphical form with a cycle time of one second for the alphanumeric data. This paper describes the system configuration, its salient features, and the expected impact on testing.

Analyzing Distributional Learning of Phonemic Categories in Unsupervised Deep Neural Networks

PubMed Central

Räsänen, Okko; Nagamine, Tasha; Mesgarani, Nima

2017-01-01

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

Spatially Distributed Dendritic Resonance Selectively Filters Synaptic Input

PubMed Central

Segev, Idan; Shamma, Shihab

2014-01-01

An important task performed by a neuron is the selection of relevant inputs from among thousands of synapses impinging on the dendritic tree. Synaptic plasticity enables this by strenghtening a subset of synapses that are, presumably, functionally relevant to the neuron. A different selection mechanism exploits the resonance of the dendritic membranes to preferentially filter synaptic inputs based on their temporal rates. A widely held view is that a neuron has one resonant frequency and thus can pass through one rate. Here we demonstrate through mathematical analyses and numerical simulations that dendritic resonance is inevitably a spatially distributed property; and therefore the resonance frequency varies along the dendrites, and thus endows neurons with a powerful spatiotemporal selection mechanism that is sensitive both to the dendritic location and the temporal structure of the incoming synaptic inputs. PMID:25144440

Going beyond Input Quantity: "Wh"-Questions Matter for Toddlers' Language and Cognitive Development

ERIC Educational Resources Information Center

Rowe, Meredith L.; Leech, Kathryn A.; Cabrera, Natasha

2017-01-01

There are clear associations between the overall quantity of input children are exposed to and their vocabulary acquisition. However, by uncovering specific features of the input that matter, we can better understand the mechanisms involved in vocabulary learning. We examine whether exposure to "wh"-questions, a challenging quality of…

Effects of Textual Enhancement and Input Enrichment on L2 Development

ERIC Educational Resources Information Center

Rassaei, Ehsan

2015-01-01

Research on second language (L2) acquisition has recently sought to include formal instruction into second and foreign language classrooms in a more unobtrusive and implicit manner. Textual enhancement and input enrichment are two techniques which are aimed at drawing learners' attention to specific linguistic features in input and at the same…

Response measurement by laser Doppler vibrometry in vibration qualification tests with non-Gaussian random excitation

NASA Astrophysics Data System (ADS)

Troncossi, M.; Di Sante, R.; Rivola, A.

2016-10-01

In the field of vibration qualification testing, random excitations are typically imposed on the tested system in terms of a power spectral density (PSD) profile. This is the one of the most popular ways to control the shaker or slip table for durability tests. However, these excitations (and the corresponding system responses) exhibit a Gaussian probability distribution, whereas not all real-life excitations are Gaussian, causing the response to be also non-Gaussian. In order to introduce non-Gaussian peaks, a further parameter, i.e., kurtosis, has to be controlled in addition to the PSD. However, depending on the specimen behaviour and input signal characteristics, the use of non-Gaussian excitations with high kurtosis and a given PSD does not automatically imply a non-Gaussian stress response. For an experimental investigation of these coupled features, suitable measurement methods need to be developed in order to estimate the stress amplitude response at critical failure locations and consequently evaluate the input signals most representative for real-life, non-Gaussian excitations. In this paper, a simple test rig with a notched cantilevered specimen was developed to measure the response and examine the kurtosis values in the case of stationary Gaussian, stationary non-Gaussian, and burst non-Gaussian excitation signals. The laser Doppler vibrometry technique was used in this type of test for the first time, in order to estimate the specimen stress amplitude response as proportional to the differential displacement measured at the notch section ends. A method based on the use of measurements using accelerometers to correct for the occasional signal dropouts occurring during the experiment is described. The results demonstrate the ability of the test procedure to evaluate the output signal features and therefore to select the most appropriate input signal for the fatigue test.

Using Differential Evolution to Optimize Learning from Signals and Enhance Network Security

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

Harmer, Paul K; Temple, Michael A; Buckner, Mark A

2011-01-01

Computer and communication network attacks are commonly orchestrated through Wireless Access Points (WAPs). This paper summarizes proof-of-concept research activity aimed at developing a physical layer Radio Frequency (RF) air monitoring capability to limit unauthorizedWAP access and mprove network security. This is done using Differential Evolution (DE) to optimize the performance of a Learning from Signals (LFS) classifier implemented with RF Distinct Native Attribute (RF-DNA) fingerprints. Performance of the resultant DE-optimized LFS classifier is demonstrated using 802.11a WiFi devices under the most challenging conditions of intra-manufacturer classification, i.e., using emissions of like-model devices that only differ in serial number. Using identicalmore » classifier input features, performance of the DE-optimized LFS classifier is assessed relative to a Multiple Discriminant Analysis / Maximum Likelihood (MDA/ML) classifier that has been used for previous demonstrations. The comparative assessment is made using both Time Domain (TD) and Spectral Domain (SD) fingerprint features. For all combinations of classifier type, feature type, and signal-to-noise ratio considered, results show that the DEoptimized LFS classifier with TD features is uperior and provides up to 20% improvement in classification accuracy with proper selection of DE parameters.« less

Synaptic State Matching: A Dynamical Architecture for Predictive Internal Representation and Feature Detection

PubMed Central

Tavazoie, Saeed

2013-01-01

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

Inverter ratio failure detector

NASA Technical Reports Server (NTRS)

Wagner, A. P.; Ebersole, T. J.; Andrews, R. E. (Inventor)

1974-01-01

A failure detector which detects the failure of a dc to ac inverter is disclosed. The inverter under failureless conditions is characterized by a known linear relationship of its input and output voltages and by a known linear relationship of its input and output currents. The detector includes circuitry which is responsive to the detector's input and output voltages and which provides a failure-indicating signal only when the monitored output voltage is less by a selected factor, than the expected output voltage for the monitored input voltage, based on the known voltages' relationship. Similarly, the detector includes circuitry which is responsive to the input and output currents and provides a failure-indicating signal only when the input current exceeds by a selected factor the expected input current for the monitored output current based on the known currents' relationship.

Improving hot region prediction by parameter optimization of density clustering in PPI.

PubMed

Hu, Jing; Zhang, Xiaolong

2016-11-01

This paper proposed an optimized algorithm which combines density clustering of parameter selection with feature-based classification for hot region prediction. First, all the residues are classified by SVM to remove non-hot spot residues, then density clustering of parameter selection is used to find hot regions. In the density clustering, this paper studies how to select input parameters. There are two parameters radius and density in density-based incremental clustering. We firstly fix density and enumerate radius to find a pair of parameters which leads to maximum number of clusters, and then we fix radius and enumerate density to find another pair of parameters which leads to maximum number of clusters. Experiment results show that the proposed method using both two pairs of parameters provides better prediction performance than the other method, and compare these two predictive results, the result by fixing radius and enumerating density have slightly higher prediction accuracy than that by fixing density and enumerating radius. Copyright © 2016. Published by Elsevier Inc.

Classification of vocal aging using parameters extracted from the glottal signal.

PubMed

Forero Mendoza, Leonardo A; Cataldo, Edson; Vellasco, Marley M B R; Silva, Marco A; Apolinário, José A

2014-09-01

This article proposes and evaluates a method to classify vocal aging using artificial neural network (ANN) and support vector machine (SVM), using the parameters extracted from the speech signal as inputs. For each recorded speech, from a corpus of male and female speakers of different ages, the corresponding glottal signal is obtained using an inverse filtering algorithm. The Mel Frequency Cepstrum Coefficients (MFCC) also extracted from the voice signal and the features extracted from the glottal signal are supplied to an ANN and an SVM with a previous selection. The selection is performed by a wrapper approach of the most relevant parameters. Three groups are considered for the aging-voice classification: young (aged 15-30 years), adult (aged 31-60 years), and senior (aged 61-90 years). The results are compared using different possibilities: with only the parameters extracted from the glottal signal, with only the MFCC, and with a combination of both. The results demonstrate that the best classification rate is obtained using the glottal signal features, which is a novel result and the main contribution of this article. Copyright © 2014 The Voice Foundation. Published by Elsevier Inc. All rights reserved.

Selection of yeasts with multifunctional features for application as starters in natural black table olive processing.

PubMed

Bonatsou, S; Benítez, A; Rodríguez-Gómez, F; Panagou, E Z; Arroyo-López, F N

2015-04-01

Yeasts are unicellular eukaryotic microorganisms with a great importance in the elaboration on many foods and beverages. In the last years, researches have focused their attention to determine the favourable effects that these microorganisms could provide to table olive processing. In this context, the present study assesses, at laboratory scale, the potential technological (resistance to salt, lipase, esterase and β-glucosidase activities) and probiotic (phytase activity, survival to gastric and pancreatic digestions) features of 12 yeast strains originally isolated from Greek natural black table olive fermentations. The multivariate classification analysis carried out with all information obtained (a total of 336 quantitative input data), revealed that the most promising strains (clearly discriminated from the rest of isolates) were Pichia guilliermondii Y16 (which showed overall the highest resistance to salt and simulated digestions) and Wickerhamomyces anomalus Y18 (with the overall highest technological enzymatic activities), while the rest of strains were grouped together in two clearly differentiated clusters. Thus, this work opens the possibility for the evaluation of these two selected yeasts as multifunctional starters, alone or in combination with lactic acid bacteria, in real table olive fermentations. Copyright © 2014 Elsevier Ltd. All rights reserved.

Software platform for managing the classification of error- related potentials of observers

NASA Astrophysics Data System (ADS)

Asvestas, P.; Ventouras, E.-C.; Kostopoulos, S.; Sidiropoulos, K.; Korfiatis, V.; Korda, A.; Uzunolglu, A.; Karanasiou, I.; Kalatzis, I.; Matsopoulos, G.

2015-09-01

Human learning is partly based on observation. Electroencephalographic recordings of subjects who perform acts (actors) or observe actors (observers), contain a negative waveform in the Evoked Potentials (EPs) of the actors that commit errors and of observers who observe the error-committing actors. This waveform is called the Error-Related Negativity (ERN). Its detection has applications in the context of Brain-Computer Interfaces. The present work describes a software system developed for managing EPs of observers, with the aim of classifying them into observations of either correct or incorrect actions. It consists of an integrated platform for the storage, management, processing and classification of EPs recorded during error-observation experiments. The system was developed using C# and the following development tools and frameworks: MySQL, .NET Framework, Entity Framework and Emgu CV, for interfacing with the machine learning library of OpenCV. Up to six features can be computed per EP recording per electrode. The user can select among various feature selection algorithms and then proceed to train one of three types of classifiers: Artificial Neural Networks, Support Vector Machines, k-nearest neighbour. Next the classifier can be used for classifying any EP curve that has been inputted to the database.

Clustering Molecular Dynamics Trajectories for Optimizing Docking Experiments

PubMed Central

De Paris, Renata; Quevedo, Christian V.; Ruiz, Duncan D.; Norberto de Souza, Osmar; Barros, Rodrigo C.

2015-01-01

Molecular dynamics simulations of protein receptors have become an attractive tool for rational drug discovery. However, the high computational cost of employing molecular dynamics trajectories in virtual screening of large repositories threats the feasibility of this task. Computational intelligence techniques have been applied in this context, with the ultimate goal of reducing the overall computational cost so the task can become feasible. Particularly, clustering algorithms have been widely used as a means to reduce the dimensionality of molecular dynamics trajectories. In this paper, we develop a novel methodology for clustering entire trajectories using structural features from the substrate-binding cavity of the receptor in order to optimize docking experiments on a cloud-based environment. The resulting partition was selected based on three clustering validity criteria, and it was further validated by analyzing the interactions between 20 ligands and a fully flexible receptor (FFR) model containing a 20 ns molecular dynamics simulation trajectory. Our proposed methodology shows that taking into account features of the substrate-binding cavity as input for the k-means algorithm is a promising technique for accurately selecting ensembles of representative structures tailored to a specific ligand. PMID:25873944

Recursive Feature Extraction in Graphs

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

2014-08-14

ReFeX extracts recursive topological features from graph data. The input is a graph as a csv file and the output is a csv file containing feature values for each node in the graph. The features are based on topological counts in the neighborhoods of each nodes, as well as recursive summaries of neighbors' features.

Wave-plate structures, power selective optical filter devices, and optical systems using same

DOEpatents

Koplow, Jeffrey P [San Ramon, CA

2012-07-03

In an embodiment, an optical filter device includes an input polarizer for selectively transmitting an input signal. The device includes a wave-plate structure positioned to receive the input signal, which includes first and second substantially zero-order, zero-wave plates arranged in series with and oriented at an angle relative to each other. The first and second zero-wave plates are configured to alter a polarization state of the input signal passing in a manner that depends on the power of the input signal. Each zero-wave plate includes an entry and exit wave plate each having a fast axis, with the fast axes oriented substantially perpendicular to each other. Each entry wave plate is oriented relative to a transmission axis of the input polarizer at a respective angle. An output polarizer is positioned to receive a signal output from the wave-plate structure and selectively transmits the signal based on the polarization state.

Artificial neural networks for acoustic target recognition

NASA Astrophysics Data System (ADS)

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

1995-04-01

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

An interactive framework for acquiring vision models of 3-D objects from 2-D images.

PubMed

Motai, Yuichi; Kak, Avinash

2004-02-01

This paper presents a human-computer interaction (HCI) framework for building vision models of three-dimensional (3-D) objects from their two-dimensional (2-D) images. Our framework is based on two guiding principles of HCI: 1) provide the human with as much visual assistance as possible to help the human make a correct input; and 2) verify each input provided by the human for its consistency with the inputs previously provided. For example, when stereo correspondence information is elicited from a human, his/her job is facilitated by superimposing epipolar lines on the images. Although that reduces the possibility of error in the human marked correspondences, such errors are not entirely eliminated because there can be multiple candidate points close together for complex objects. For another example, when pose-to-pose correspondence is sought from a human, his/her job is made easier by allowing the human to rotate the partial model constructed in the previous pose in relation to the partial model for the current pose. While this facility reduces the incidence of human-supplied pose-to-pose correspondence errors, such errors cannot be eliminated entirely because of confusion created when multiple candidate features exist close together. Each input provided by the human is therefore checked against the previous inputs by invoking situation-specific constraints. Different types of constraints (and different human-computer interaction protocols) are needed for the extraction of polygonal features and for the extraction of curved features. We will show results on both polygonal objects and object containing curved features.

Reading with sounds: sensory substitution selectively activates the visual word form area in the blind.

PubMed

Striem-Amit, Ella; Cohen, Laurent; Dehaene, Stanislas; Amedi, Amir

2012-11-08

Using a visual-to-auditory sensory-substitution algorithm, congenitally fully blind adults were taught to read and recognize complex images using "soundscapes"--sounds topographically representing images. fMRI was used to examine key questions regarding the visual word form area (VWFA): its selectivity for letters over other visual categories without visual experience, its feature tolerance for reading in a novel sensory modality, and its plasticity for scripts learned in adulthood. The blind activated the VWFA specifically and selectively during the processing of letter soundscapes relative to both textures and visually complex object categories and relative to mental imagery and semantic-content controls. Further, VWFA recruitment for reading soundscapes emerged after 2 hr of training in a blind adult on a novel script. Therefore, the VWFA shows category selectivity regardless of input sensory modality, visual experience, and long-term familiarity or expertise with the script. The VWFA may perform a flexible task-specific rather than sensory-specific computation, possibly linking letter shapes to phonology. Copyright © 2012 Elsevier Inc. All rights reserved.

MUSIC: An 8 channel readout ASIC for SiPM arrays

NASA Astrophysics Data System (ADS)

Gómez, Sergio; Gascón, David; Fernández, Gerard; Sanuy, Andreu; Mauricio, Joan; Graciani, Ricardo; Sanchez, David

2016-04-01

This paper presents an 8 channel ASIC for SiPM anode readout based on a novel low input impedance current conveyor (under patent1). This Multiple Use SiPM Integrated Circuit (MUSIC) has been designed to serve several purposes, including, for instance, the readout of SiPM arrays for some of the Cherenkov Telescope Array (CTA) cameras. The current division scheme at the very front end part of the circuit splits the input current into differently scaled copies which are connected to independent current mirrors. The circuit contains a tunable pole zero cancellation of the SiPM recovery time constant to deal with sensors from different manufacturers. Decay times up to 100 ns are supported covering most of the available SiPM devices in the market. MUSIC offers three main features: (1) differential output of the sum of the individual input channels; (2) 8 individual single ended analog outputs and; (3) 8 individual binary outputs. The digital outputs encode the amount of collected charge in the duration of the digital signal using a time over threshold technique. For each individual channel, the user must select the analog or digital output. Each functionality, the signal sum and the 8 A/D outputs, include a selectable dual-gain configuration. Moreover, the signal sum implements dual-gain output providing a 15 bit dynamic range. Full die simulation results of the MUSIC designed using AMS 0.35 µm SiGe technology are presented: total die size of 9 mm2, 500 MHz bandwidth for channel sum and 150 MHz bandwidth for A/D channels, low input impedance (≍32 Ω), single photon output pulse width at half maximum (FWHM) between 5 and 10 ns and with a power consumption of ≍ 30 mW/ch plus ≍ 200 mW for the 8 ch sum. Encapsulated prototype samples of the MUSIC are expected by March 2016.

Chemical sensors are hybrid-input memristors

NASA Astrophysics Data System (ADS)

Sysoev, V. I.; Arkhipov, V. E.; Okotrub, A. V.; Pershin, Y. V.

2018-04-01

Memristors are two-terminal electronic devices whose resistance depends on the history of input signal (voltage or current). Here we demonstrate that the chemical gas sensors can be considered as memristors with a generalized (hybrid) input, namely, with the input consisting of the voltage, analyte concentrations and applied temperature. The concept of hybrid-input memristors is demonstrated experimentally using a single-walled carbon nanotubes chemical sensor. It is shown that with respect to the hybrid input, the sensor exhibits some features common with memristors such as the hysteretic input-output characteristics. This different perspective on chemical gas sensors may open new possibilities for smart sensor applications.

Automatic detection and recognition of signs from natural scenes.

PubMed

Chen, Xilin; Yang, Jie; Zhang, Jing; Waibel, Alex

2004-01-01

In this paper, we present an approach to automatic detection and recognition of signs from natural scenes, and its application to a sign translation task. The proposed approach embeds multiresolution and multiscale edge detection, adaptive searching, color analysis, and affine rectification in a hierarchical framework for sign detection, with different emphases at each phase to handle the text in different sizes, orientations, color distributions and backgrounds. We use affine rectification to recover deformation of the text regions caused by an inappropriate camera view angle. The procedure can significantly improve text detection rate and optical character recognition (OCR) accuracy. Instead of using binary information for OCR, we extract features from an intensity image directly. We propose a local intensity normalization method to effectively handle lighting variations, followed by a Gabor transform to obtain local features, and finally a linear discriminant analysis (LDA) method for feature selection. We have applied the approach in developing a Chinese sign translation system, which can automatically detect and recognize Chinese signs as input from a camera, and translate the recognized text into English.

Flame analysis using image processing techniques

NASA Astrophysics Data System (ADS)

Her Jie, Albert Chang; Zamli, Ahmad Faizal Ahmad; Zulazlan Shah Zulkifli, Ahmad; Yee, Joanne Lim Mun; Lim, Mooktzeng

2018-04-01

This paper presents image processing techniques with the use of fuzzy logic and neural network approach to perform flame analysis. Flame diagnostic is important in the industry to extract relevant information from flame images. Experiment test is carried out in a model industrial burner with different flow rates. Flame features such as luminous and spectral parameters are extracted using image processing and Fast Fourier Transform (FFT). Flame images are acquired using FLIR infrared camera. Non-linearities such as thermal acoustic oscillations and background noise affect the stability of flame. Flame velocity is one of the important characteristics that determines stability of flame. In this paper, an image processing method is proposed to determine flame velocity. Power spectral density (PSD) graph is a good tool for vibration analysis where flame stability can be approximated. However, a more intelligent diagnostic system is needed to automatically determine flame stability. In this paper, flame features of different flow rates are compared and analyzed. The selected flame features are used as inputs to the proposed fuzzy inference system to determine flame stability. Neural network is used to test the performance of the fuzzy inference system.

Fusion of pixel and object-based features for weed mapping using unmanned aerial vehicle imagery

NASA Astrophysics Data System (ADS)

Gao, Junfeng; Liao, Wenzhi; Nuyttens, David; Lootens, Peter; Vangeyte, Jürgen; Pižurica, Aleksandra; He, Yong; Pieters, Jan G.

2018-05-01

The developments in the use of unmanned aerial vehicles (UAVs) and advanced imaging sensors provide new opportunities for ultra-high resolution (e.g., less than a 10 cm ground sampling distance (GSD)) crop field monitoring and mapping in precision agriculture applications. In this study, we developed a strategy for inter- and intra-row weed detection in early season maize fields from aerial visual imagery. More specifically, the Hough transform algorithm (HT) was applied to the orthomosaicked images for inter-row weed detection. A semi-automatic Object-Based Image Analysis (OBIA) procedure was developed with Random Forests (RF) combined with feature selection techniques to classify soil, weeds and maize. Furthermore, the two binary weed masks generated from HT and OBIA were fused for accurate binary weed image. The developed RF classifier was evaluated by 5-fold cross validation, and it obtained an overall accuracy of 0.945, and Kappa value of 0.912. Finally, the relationship of detected weeds and their ground truth densities was quantified by a fitted linear model with a coefficient of determination of 0.895 and a root mean square error of 0.026. Besides, the importance of input features was evaluated, and it was found that the ratio of vegetation length and width was the most significant feature for the classification model. Overall, our approach can yield a satisfactory weed map, and we expect that the obtained accurate and timely weed map from UAV imagery will be applicable to realize site-specific weed management (SSWM) in early season crop fields for reducing spraying non-selective herbicides and costs.

Corticothalamic Synaptic Noise as a Mechanism for Selective Attention in Thalamic Neurons.

PubMed

Béhuret, Sébastien; Deleuze, Charlotte; Bal, Thierry

2015-01-01

A reason why the thalamus is more than a passive gateway for sensory signals is that two-third of the synapses of thalamocortical neurons are directly or indirectly related to the activity of corticothalamic axons. While the responses of thalamocortical neurons evoked by sensory stimuli are well characterized, with ON- and OFF-center receptive field structures, the prevalence of synaptic noise resulting from neocortical feedback in intracellularly recorded thalamocortical neurons in vivo has attracted little attention. However, in vitro and modeling experiments point to its critical role for the integration of sensory signals. Here we combine our recent findings in a unified framework suggesting the hypothesis that corticothalamic synaptic activity is adapted to modulate the transfer efficiency of thalamocortical neurons during selective attention at three different levels: First, on ionic channels by interacting with intrinsic membrane properties, second at the neuron level by impacting on the input-output gain, and third even more effectively at the cell assembly level by boosting the information transfer of sensory features encoded in thalamic subnetworks. This top-down population control is achieved by tuning the correlations in subthreshold membrane potential fluctuations and is adapted to modulate the transfer of sensory features encoded by assemblies of thalamocortical relay neurons. We thus propose that cortically-controlled (de-)correlation of subthreshold noise is an efficient and swift dynamic mechanism for selective attention in the thalamus.

Genes@Work: an efficient algorithm for pattern discovery and multivariate feature selection in gene expression data.

PubMed

Lepre, Jorge; Rice, J Jeremy; Tu, Yuhai; Stolovitzky, Gustavo

2004-05-01

Despite the growing literature devoted to finding differentially expressed genes in assays probing different tissues types, little attention has been paid to the combinatorial nature of feature selection inherent to large, high-dimensional gene expression datasets. New flexible data analysis approaches capable of searching relevant subgroups of genes and experiments are needed to understand multivariate associations of gene expression patterns with observed phenotypes. We present in detail a deterministic algorithm to discover patterns of multivariate gene associations in gene expression data. The patterns discovered are differential with respect to a control dataset. The algorithm is exhaustive and efficient, reporting all existent patterns that fit a given input parameter set while avoiding enumeration of the entire pattern space. The value of the pattern discovery approach is demonstrated by finding a set of genes that differentiate between two types of lymphoma. Moreover, these genes are found to behave consistently in an independent dataset produced in a different laboratory using different arrays, thus validating the genes selected using our algorithm. We show that the genes deemed significant in terms of their multivariate statistics will be missed using other methods. Our set of pattern discovery algorithms including a user interface is distributed as a package called Genes@Work. This package is freely available to non-commercial users and can be downloaded from our website (http://www.research.ibm.com/FunGen).

Corticothalamic Synaptic Noise as a Mechanism for Selective Attention in Thalamic Neurons

PubMed Central

Béhuret, Sébastien; Deleuze, Charlotte; Bal, Thierry

2015-01-01

A reason why the thalamus is more than a passive gateway for sensory signals is that two-third of the synapses of thalamocortical neurons are directly or indirectly related to the activity of corticothalamic axons. While the responses of thalamocortical neurons evoked by sensory stimuli are well characterized, with ON- and OFF-center receptive field structures, the prevalence of synaptic noise resulting from neocortical feedback in intracellularly recorded thalamocortical neurons in vivo has attracted little attention. However, in vitro and modeling experiments point to its critical role for the integration of sensory signals. Here we combine our recent findings in a unified framework suggesting the hypothesis that corticothalamic synaptic activity is adapted to modulate the transfer efficiency of thalamocortical neurons during selective attention at three different levels: First, on ionic channels by interacting with intrinsic membrane properties, second at the neuron level by impacting on the input-output gain, and third even more effectively at the cell assembly level by boosting the information transfer of sensory features encoded in thalamic subnetworks. This top-down population control is achieved by tuning the correlations in subthreshold membrane potential fluctuations and is adapted to modulate the transfer of sensory features encoded by assemblies of thalamocortical relay neurons. We thus propose that cortically-controlled (de-)correlation of subthreshold noise is an efficient and swift dynamic mechanism for selective attention in the thalamus. PMID:26733818

Contrast normalization contributes to a biologically-plausible model of receptive-field development in primary visual cortex (V1)

PubMed Central

Willmore, Ben D.B.; Bulstrode, Harry; Tolhurst, David J.

2012-01-01

Neuronal populations in the primary visual cortex (V1) of mammals exhibit contrast normalization. Neurons that respond strongly to simple visual stimuli – such as sinusoidal gratings – respond less well to the same stimuli when they are presented as part of a more complex stimulus which also excites other, neighboring neurons. This phenomenon is generally attributed to generalized patterns of inhibitory connections between nearby V1 neurons. The Bienenstock, Cooper and Munro (BCM) rule is a neural network learning rule that, when trained on natural images, produces model neurons which, individually, have many tuning properties in common with real V1 neurons. However, when viewed as a population, a BCM network is very different from V1 – each member of the BCM population tends to respond to the same dominant features of visual input, producing an incomplete, highly redundant code for visual information. Here, we demonstrate that, by adding contrast normalization into the BCM rule, we arrive at a neurally-plausible Hebbian learning rule that can learn an efficient sparse, overcomplete representation that is a better model for stimulus selectivity in V1. This suggests that one role of contrast normalization in V1 is to guide the neonatal development of receptive fields, so that neurons respond to different features of visual input. PMID:22230381

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.

Analysis and selection of optimal function implementations in massively parallel computer

DOEpatents

Archer, Charles Jens [Rochester, MN; Peters, Amanda [Rochester, MN; Ratterman, Joseph D [Rochester, MN

2011-05-31

An apparatus, program product and method optimize the operation of a parallel computer system by, in part, collecting performance data for a set of implementations of a function capable of being executed on the parallel computer system based upon the execution of the set of implementations under varying input parameters in a plurality of input dimensions. The collected performance data may be used to generate selection program code that is configured to call selected implementations of the function in response to a call to the function under varying input parameters. The collected performance data may be used to perform more detailed analysis to ascertain the comparative performance of the set of implementations of the function under the varying input parameters.

Stereoscopic Feature Tracking System for Retrieving Velocity of Surface Waters

NASA Astrophysics Data System (ADS)

Zuniga Zamalloa, C. C.; Landry, B. J.

2017-12-01

The present work is concerned with the surface velocity retrieval of flows using a stereoscopic setup and finding the correspondence in the images via feature tracking (FT). The feature tracking provides a key benefit of substantially reducing the level of user input. In contrast to other commonly used methods (e.g., normalized cross-correlation), FT does not require the user to prescribe interrogation window sizes and removes the need for masking when specularities are present. The results of the current FT methodology are comparable to those obtained via Large Scale Particle Image Velocimetry while requiring little to no user input which allowed for rapid, automated processing of imagery.

Reconfigurable Fault Tolerance for FPGAs

NASA Technical Reports Server (NTRS)

Shuler, Robert, Jr.

2010-01-01

The invention allows a field-programmable gate array (FPGA) or similar device to be efficiently reconfigured in whole or in part to provide higher capacity, non-redundant operation. The redundant device consists of functional units such as adders or multipliers, configuration memory for the functional units, a programmable routing method, configuration memory for the routing method, and various other features such as block RAM, I/O (random access memory, input/output) capability, dedicated carry logic, etc. The redundant device has three identical sets of functional units and routing resources and majority voters that correct errors. The configuration memory may or may not be redundant, depending on need. For example, SRAM-based FPGAs will need some type of radiation-tolerant configuration memory, or they will need triple-redundant configuration memory. Flash or anti-fuse devices will generally not need redundant configuration memory. Some means of loading and verifying the configuration memory is also required. These are all components of the pre-existing redundant FPGA. This innovation modifies the voter to accept a MODE input, which specifies whether ordinary voting is to occur, or if redundancy is to be split. Generally, additional routing resources will also be required to pass data between sections of the device created by splitting the redundancy. In redundancy mode, the voters produce an output corresponding to the two inputs that agree, in the usual fashion. In the split mode, the voters select just one input and convey this to the output, ignoring the other inputs. In a dual-redundant system (as opposed to triple-redundant), instead of a voter, there is some means to latch or gate a state update only when both inputs agree. In this case, the invention would require modification of the latch or gate so that it would operate normally in redundant mode, and would separately latch or gate the inputs in non-redundant mode.

Role Discovery in Graphs

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

2014-08-14

RolX takes the features from Re-FeX or any other feature matrix as input and outputs role assignments (clusters). The output of RolX is a csv file containing the node-role memberships and a csv file containing the role-feature definitions.

Guidance for Selecting Input Parameters in Modeling the Environmental Fate and Transport of Pesticides

EPA Pesticide Factsheets

Guidance to select and prepare input values for OPP's aquatic exposure models. Intended to improve the consistency in modeling the fate of pesticides in the environment and quality of OPP's aquatic risk assessments.

Selective Attention, Working Memory, and Executive Function as Potential Independent Sources of Cognitive Dysfunction in Schizophrenia.

PubMed

Gold, James M; Robinson, Benjamin; Leonard, Carly J; Hahn, Britta; Chen, Shuo; McMahon, Robert P; Luck, Steven J

2017-11-11

People with schizophrenia demonstrate impairments in selective attention, working memory, and executive function. Given the overlap in these constructs, it is unclear if these represent distinct impairments or different manifestations of one higher-order impairment. To examine this question, we administered tasks from the basic cognitive neuroscience literature to measure visual selective attention, working memory capacity, and executive function in 126 people with schizophrenia and 122 healthy volunteers. Patients demonstrated deficits on all tasks with the exception of selective attention guided by strong bottom-up inputs. Although the measures of top-down control of selective attention, working memory, and executive function were all intercorrelated, several sources of evidence indicate that working memory and executive function are separate sources of variance. Specifically, both working memory and executive function independently contributed to the discrimination of group status and independently accounted for variance in overall general cognitive ability as assessed by the MATRICS battery. These two cognitive functions appear to be separable features of the cognitive impairments observed in schizophrenia. © The Author 2017. Published by Oxford University Press on behalf of the Maryland Psychiatric Research Center. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Selection of relevant input variables in storm water quality modeling by multiobjective evolutionary polynomial regression paradigm

NASA Astrophysics Data System (ADS)

Creaco, E.; Berardi, L.; Sun, Siao; Giustolisi, O.; Savic, D.

2016-04-01

The growing availability of field data, from information and communication technologies (ICTs) in "smart" urban infrastructures, allows data modeling to understand complex phenomena and to support management decisions. Among the analyzed phenomena, those related to storm water quality modeling have recently been gaining interest in the scientific literature. Nonetheless, the large amount of available data poses the problem of selecting relevant variables to describe a phenomenon and enable robust data modeling. This paper presents a procedure for the selection of relevant input variables using the multiobjective evolutionary polynomial regression (EPR-MOGA) paradigm. The procedure is based on scrutinizing the explanatory variables that appear inside the set of EPR-MOGA symbolic model expressions of increasing complexity and goodness of fit to target output. The strategy also enables the selection to be validated by engineering judgement. In such context, the multiple case study extension of EPR-MOGA, called MCS-EPR-MOGA, is adopted. The application of the proposed procedure to modeling storm water quality parameters in two French catchments shows that it was able to significantly reduce the number of explanatory variables for successive analyses. Finally, the EPR-MOGA models obtained after the input selection are compared with those obtained by using the same technique without benefitting from input selection and with those obtained in previous works where other data-modeling techniques were used on the same data. The comparison highlights the effectiveness of both EPR-MOGA and the input selection procedure.

Spectral and spatial selectivity of luminance vision in reef fish.

PubMed

Siebeck, Ulrike E; Wallis, Guy Michael; Litherland, Lenore; Ganeshina, Olga; Vorobyev, Misha

2014-01-01

Luminance vision has high spatial resolution and is used for form vision and texture discrimination. In humans, birds and bees luminance channel is spectrally selective-it depends on the signals of the long-wavelength sensitive photoreceptors (bees) or on the sum of long- and middle-wavelength sensitive cones (humans), but not on the signal of the short-wavelength sensitive (blue) photoreceptors. The reasons of such selectivity are not fully understood. The aim of this study is to reveal the inputs of cone signals to high resolution luminance vision in reef fish. Sixteen freshly caught damselfish, Pomacentrus amboinensis, were trained to discriminate stimuli differing either in their color or in their fine patterns (stripes vs. cheques). Three colors ("bright green", "dark green" and "blue") were used to create two sets of color and two sets of pattern stimuli. The "bright green" and "dark green" were similar in their chromatic properties for fish, but differed in their lightness; the "dark green" differed from "blue" in the signal for the blue cone, but yielded similar signals in the long-wavelength and middle-wavelength cones. Fish easily learned to discriminate "bright green" from "dark green" and "dark green" from "blue" stimuli. Fish also could discriminate the fine patterns created from "dark green" and "bright green". However, fish failed to discriminate fine patterns created from "blue" and "dark green" colors, i.e., the colors that provided contrast for the blue-sensitive photoreceptor, but not for the long-wavelength sensitive one. High resolution luminance vision in damselfish, Pomacentrus amboinensis, does not have input from the blue-sensitive cone, which may indicate that the spectral selectivity of luminance channel is a general feature of visual processing in both aquatic and terrestrial animals.

The Effect of Vocabulary Self-Selection Strategy and Input Enhancement Strategy on the Vocabulary Knowledge of Iranian EFL Learners

ERIC Educational Resources Information Center

Masoudi, Golfam

2017-01-01

The present study was designed to investigate empirically the effect of Vocabulary Self-Selection strategy and Input Enhancement strategy on the vocabulary knowledge of Iranian EFL Learners. After taking a diagnostic pretest, both experimental groups enrolled in two classes. Learners who practiced Vocabulary Self-Selection were allowed to…

Locally excitatory, globally inhibitory oscillator networks: theory and application to scene segmentation

NASA Astrophysics Data System (ADS)

Wang, DeLiang; Terman, David

1995-01-01

A novel class of locally excitatory, globally inhibitory oscillator networks (LEGION) is proposed and investigated analytically and by computer simulation. The model of each oscillator corresponds to a standard relaxation oscillator with two time scales. The network exhibits a mechanism of selective gating, whereby an oscillator jumping up to its active phase rapidly recruits the oscillators stimulated by the same pattern, while preventing other oscillators from jumping up. We show analytically that with the selective gating mechanism the network rapidly achieves both synchronization within blocks of oscillators that are stimulated by connected regions and desynchronization between different blocks. Computer simulations demonstrate LEGION's promising ability for segmenting multiple input patterns in real time. This model lays a physical foundation for the oscillatory correlation theory of feature binding, and may provide an effective computational framework for scene segmentation and figure/ground segregation.

A framework for risk assessment and decision-making strategies in dangerous good transportation.

PubMed

Fabiano, B; Currò, F; Palazzi, E; Pastorino, R

2002-07-01

The risk from dangerous goods transport by road and strategies for selecting road load/routes are faced in this paper, by developing an original site-oriented framework of general applicability at local level. A realistic evaluation of the frequency must take into account on one side inherent factors (e.g. tunnels, rail bridges, bend radii, slope, characteristics of neighborhood, etc.) on the other side factors correlated to the traffic conditions (e.g. dangerous goods trucks, etc.). Field data were collected on the selected highway, by systematic investigation, providing input data for a database reporting tendencies and intrinsic parameter/site-oriented statistics. The developed technique was applied to a pilot area, considering both the individual risk and societal risk and making reference to flammable and explosive scenarios. In this way, a risk assessment, sensitive to route features and population exposed, is proposed, so that the overall uncertainties in risk analysis can be lowered.

V-ELMpiRNAPred: Identification of human piRNAs by the voting-based extreme learning machine (V-ELM) with a new hybrid feature.

PubMed

Pian, Cong; Chen, Yuan-Yuan; Zhang, Jin; Chen, Zhi; Zhang, Guang-Le; Li, Qiang; Yang, Tao; Zhang, Liang-Yun

2017-02-01

Piwi-interacting RNAs (piRNAs) were recently discovered as endogenous small noncoding RNAs. Some recent research suggests that piRNAs may play an important role in cancer. So the precise identification of human piRNAs is a significant work. In this paper, we introduce a series of new features with 80 dimension called short sequence motifs (SSM). A hybrid feature vector with 1444 dimension can be formed by combining 1364 features of [Formula: see text]-mer strings and 80 features of SSM features. We optimize the 1444 dimension features using the feature score criterion (FSC) and list them in descending order according to the scores. The first 462 are selected as the input feature vector in the classifier. Moreover, eight of 80 SSM features appear in the top 20. This indicates that these eight SSM features play an important part in the identification of piRNAs. Since five of the above eight SSM features are associated with nucleotide A and G ('A*G', 'A**G', 'A***G', 'A****G', 'A*****G'). So, we guess there may exist some biological significance. We also use a neural network algorithm called voting-based extreme learning machine (V-ELM) to identify real piRNAs. The Specificity (Sp) and Sensitivity (Sn) of our method are 95.48% and 94.61%, respectively in human species. This result shows that our method is more effective compared with those of the piRPred, piRNApredictor, Asym-Pibomd, Piano and McRUMs. The web service of V-ELMpiRNAPred is available for free at http://mm20132014.wicp.net:38601/velmprepiRNA/Main.jsp .

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.

Applications of information theory, genetic algorithms, and neural models to predict oil flow

NASA Astrophysics Data System (ADS)

Ludwig, Oswaldo; Nunes, Urbano; Araújo, Rui; Schnitman, Leizer; Lepikson, Herman Augusto

2009-07-01

This work introduces a new information-theoretic methodology for choosing variables and their time lags in a prediction setting, particularly when neural networks are used in non-linear modeling. The first contribution of this work is the Cross Entropy Function (XEF) proposed to select input variables and their lags in order to compose the input vector of black-box prediction models. The proposed XEF method is more appropriate than the usually applied Cross Correlation Function (XCF) when the relationship among the input and output signals comes from a non-linear dynamic system. The second contribution is a method that minimizes the Joint Conditional Entropy (JCE) between the input and output variables by means of a Genetic Algorithm (GA). The aim is to take into account the dependence among the input variables when selecting the most appropriate set of inputs for a prediction problem. In short, theses methods can be used to assist the selection of input training data that have the necessary information to predict the target data. The proposed methods are applied to a petroleum engineering problem; predicting oil production. Experimental results obtained with a real-world dataset are presented demonstrating the feasibility and effectiveness of the method.

Effects of amyloid-β plaque proximity on the axon initial segment of pyramidal cells.

PubMed

León-Espinosa, Gonzalo; DeFelipe, Javier; Muñoz, Alberto

2012-01-01

The output of cortical pyramidal cells reflects the balance between excitatory inputs of cortical and subcortical origin, and inhibitory inputs from distinct populations of cortical GABAergic interneurons, each of which selectively innervate different domains of neuronal pyramidal cells (i.e., dendrites, soma and axon initial segment [AIS]). In Alzheimer's disease (AD), the presence of amyloid-β (Aβ) plaques alters the synaptic input to pyramidal cells in a number of ways. However, the effects of Aβ plaques on the AIS have still not been investigated to date. This neuronal domain is involved in input integration, as well as action potential initiation and propagation, and it exhibits Ca2+- and activity-dependent structural plasticity. The AIS is innervated by GABAergic axon terminals from chandelier cells, which are thought to exert a strong influence on pyramidal cell output. In the AβPP/PS1 transgenic mouse model of AD, we have investigated the effects of Aβ plaques on the morphological and neurochemical features of the AIS, including the cisternal organelle, using immunocytochemistry and confocal microscopy, as well as studying the innervation of the AIS by chandelier cell axon terminals. There is a strong reduction in GABAergic terminals that appose AIS membrane surfaces that are in contact with Aβ plaques, indicating altered inhibitory synapsis at the AIS. Thus, despite a lack of gross structural alterations in the AIS, this decrease in GABAergic innervation may deregulate AIS activity and contribute to the hyperactivity of neurons in contact with Aβ plaques.

AQUATOX Features and Tools

EPA Pesticide Factsheets

Numerous features have been included to facilitate the modeling process, from model setup and data input, presentation and analysis of results, to easy export of results to spreadsheet programs for additional analysis.

The intralaminar thalamus—an expressway linking visual stimuli to circuits determining agency and action selection

PubMed Central

Fisher, Simon D.; Reynolds, John N. J.

2014-01-01

Anatomical investigations have revealed connections between the intralaminar thalamic nuclei and areas such as the superior colliculus (SC) that receive short latency input from visual and auditory primary sensory areas. The intralaminar nuclei in turn project to the major input nucleus of the basal ganglia, the striatum, providing this nucleus with a source of subcortical excitatory input. Together with a converging input from the cerebral cortex, and a neuromodulatory dopaminergic input from the midbrain, the components previously found necessary for reinforcement learning in the basal ganglia are present. With this intralaminar sensory input, the basal ganglia are thought to play a primary role in determining what aspect of an organism’s own behavior has caused salient environmental changes. Additionally, subcortical loops through thalamic and basal ganglia nuclei are proposed to play a critical role in action selection. In this mini review we will consider the anatomical and physiological evidence underlying the existence of these circuits. We will propose how the circuits interact to modulate basal ganglia output and solve common behavioral learning problems of agency determination and action selection. PMID:24765070

Tele-Autonomous control involving contact. Final Report Thesis; [object localization

NASA Technical Reports Server (NTRS)

Shao, Lejun; Volz, Richard A.; Conway, Lynn; Walker, Michael W.

1990-01-01

Object localization and its application in tele-autonomous systems are studied. Two object localization algorithms are presented together with the methods of extracting several important types of object features. The first algorithm is based on line-segment to line-segment matching. Line range sensors are used to extract line-segment features from an object. The extracted features are matched to corresponding model features to compute the location of the object. The inputs of the second algorithm are not limited only to the line features. Featured points (point to point matching) and featured unit direction vectors (vector to vector matching) can also be used as the inputs of the algorithm, and there is no upper limit on the number of the features inputed. The algorithm will allow the use of redundant features to find a better solution. The algorithm uses dual number quaternions to represent the position and orientation of an object and uses the least squares optimization method to find an optimal solution for the object's location. The advantage of using this representation is that the method solves for the location estimation by minimizing a single cost function associated with the sum of the orientation and position errors and thus has a better performance on the estimation, both in accuracy and speed, than that of other similar algorithms. The difficulties when the operator is controlling a remote robot to perform manipulation tasks are also discussed. The main problems facing the operator are time delays on the signal transmission and the uncertainties of the remote environment. How object localization techniques can be used together with other techniques such as predictor display and time desynchronization to help to overcome these difficulties are then discussed.

Hierarchical representation of shapes in visual cortex—from localized features to figural shape segregation

PubMed Central

Tschechne, Stephan; Neumann, Heiko

2014-01-01

Visual structures in the environment are segmented into image regions and those combined to a representation of surfaces and prototypical objects. Such a perceptual organization is performed by complex neural mechanisms in the visual cortex of primates. Multiple mutually connected areas in the ventral cortical pathway receive visual input and extract local form features that are subsequently grouped into increasingly complex, more meaningful image elements. Such a distributed network of processing must be capable to make accessible highly articulated changes in shape boundary as well as very subtle curvature changes that contribute to the perception of an object. We propose a recurrent computational network architecture that utilizes hierarchical distributed representations of shape features to encode surface and object boundary over different scales of resolution. Our model makes use of neural mechanisms that model the processing capabilities of early and intermediate stages in visual cortex, namely areas V1–V4 and IT. We suggest that multiple specialized component representations interact by feedforward hierarchical processing that is combined with feedback signals driven by representations generated at higher stages. Based on this, global configurational as well as local information is made available to distinguish changes in the object's contour. Once the outline of a shape has been established, contextual contour configurations are used to assign border ownership directions and thus achieve segregation of figure and ground. The model, thus, proposes how separate mechanisms contribute to distributed hierarchical cortical shape representation and combine with processes of figure-ground segregation. Our model is probed with a selection of stimuli to illustrate processing results at different processing stages. We especially highlight how modulatory feedback connections contribute to the processing of visual input at various stages in the processing hierarchy. PMID:25157228

Hierarchical representation of shapes in visual cortex-from localized features to figural shape segregation.

PubMed

Tschechne, Stephan; Neumann, Heiko

2014-01-01

Visual structures in the environment are segmented into image regions and those combined to a representation of surfaces and prototypical objects. Such a perceptual organization is performed by complex neural mechanisms in the visual cortex of primates. Multiple mutually connected areas in the ventral cortical pathway receive visual input and extract local form features that are subsequently grouped into increasingly complex, more meaningful image elements. Such a distributed network of processing must be capable to make accessible highly articulated changes in shape boundary as well as very subtle curvature changes that contribute to the perception of an object. We propose a recurrent computational network architecture that utilizes hierarchical distributed representations of shape features to encode surface and object boundary over different scales of resolution. Our model makes use of neural mechanisms that model the processing capabilities of early and intermediate stages in visual cortex, namely areas V1-V4 and IT. We suggest that multiple specialized component representations interact by feedforward hierarchical processing that is combined with feedback signals driven by representations generated at higher stages. Based on this, global configurational as well as local information is made available to distinguish changes in the object's contour. Once the outline of a shape has been established, contextual contour configurations are used to assign border ownership directions and thus achieve segregation of figure and ground. The model, thus, proposes how separate mechanisms contribute to distributed hierarchical cortical shape representation and combine with processes of figure-ground segregation. Our model is probed with a selection of stimuli to illustrate processing results at different processing stages. We especially highlight how modulatory feedback connections contribute to the processing of visual input at various stages in the processing hierarchy.

Prediction of Cognitive States During Flight Simulation Using Multimodal Psychophysiological Sensing

NASA Technical Reports Server (NTRS)

Harrivel, Angela R.; Stephens, Chad L.; Milletich, Robert J.; Heinich, Christina M.; Last, Mary Carolyn; Napoli, Nicholas J.; Abraham, Nijo A.; Prinzel, Lawrence J.; Motter, Mark A.; Pope, Alan T.

2017-01-01

The Commercial Aviation Safety Team found the majority of recent international commercial aviation accidents attributable to loss of control inflight involved flight crew loss of airplane state awareness (ASA), and distraction was involved in all of them. Research on attention-related human performance limiting states (AHPLS) such as channelized attention, diverted attention, startle/surprise, and confirmation bias, has been recommended in a Safety Enhancement (SE) entitled "Training for Attention Management." To accomplish the detection of such cognitive and psychophysiological states, a broad suite of sensors was implemented to simultaneously measure their physiological markers during a high fidelity flight simulation human subject study. Twenty-four pilot participants were asked to wear the sensors while they performed benchmark tasks and motion-based flight scenarios designed to induce AHPLS. Pattern classification was employed to predict the occurrence of AHPLS during flight simulation also designed to induce those states. Classifier training data were collected during performance of the benchmark tasks. Multimodal classification was performed, using pre-processed electroencephalography, galvanic skin response, electrocardiogram, and respiration signals as input features. A combination of one, some or all modalities were used. Extreme gradient boosting, random forest and two support vector machine classifiers were implemented. The best accuracy for each modality-classifier combination is reported. Results using a select set of features and using the full set of available features are presented. Further, results are presented for training one classifier with the combined features and for training multiple classifiers with features from each modality separately. Using the select set of features and combined training, multistate prediction accuracy averaged 0.64 +/- 0.14 across thirteen participants and was significantly higher than that for the separate training case. These results support the goal of demonstrating simultaneous real-time classification of multiple states using multiple sensing modalities in high fidelity flight simulators. This detection is intended to support and inform training methods under development to mitigate the loss of ASA and thus reduce accidents and incidents.

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

Weimar, Mark R.; Daly, Don S.; Wood, Thomas W.

Both nuclear power and nuclear weapons programs should have (related) economic signatures which are detectible at some scale. We evaluated this premise in a series of studies using national economic input/output (IO) data. Statistical discrimination models using economic IO tables predict with a high probability whether a country with an unknown predilection for nuclear weapons proliferation is in fact engaged in nuclear power development or nuclear weapons proliferation. We analyzed 93 IO tables, spanning the years 1993 to 2005 for 37 countries that are either members or associates of the Organization for Economic Cooperation and Development (OECD). The 2009 OECDmore » input/output tables featured 48 industrial sectors based on International Standard Industrial Classification (ISIC) Revision 3, and described the respective economies in current country-of-origin valued currency. We converted and transformed these reported values to US 2005 dollars using appropriate exchange rates and implicit price deflators, and addressed discrepancies in reported industrial sectors across tables. We then classified countries with Random Forest using either the adjusted or industry-normalized values. Random Forest, a classification tree technique, separates and categorizes countries using a very small, select subset of the 2304 individual cells in the IO table. A nation’s efforts in nuclear power, be it for electricity or nuclear weapons, are an enterprise with a large economic footprint -- an effort so large that it should discernibly perturb coarse country-level economics data such as that found in yearly input-output economic tables. The neoclassical economic input-output model describes a country’s or region’s economy in terms of the requirements of industries to produce the current level of economic output. An IO table row shows the distribution of an industry’s output to the industrial sectors while a table column shows the input required of each industrial sector by a given industry.« less

Event-driven visual attention for the humanoid robot iCub

PubMed Central

Rea, Francesco; Metta, Giorgio; Bartolozzi, Chiara

2013-01-01

Fast reaction to sudden and potentially interesting stimuli is a crucial feature for safe and reliable interaction with the environment. Here we present a biologically inspired attention system developed for the humanoid robot iCub. It is based on input from unconventional event-driven vision sensors and an efficient computational method. The resulting system shows low-latency and fast determination of the location of the focus of attention. The performance is benchmarked against an instance of the state of the art in robotics artificial attention system used in robotics. Results show that the proposed system is two orders of magnitude faster that the benchmark in selecting a new stimulus to attend. PMID:24379753

STABILIZED OSCILLATOR

DOEpatents

Jessen, P.L.; Price, H.J.

1958-03-18

This patent relates to sine-wave generators and in particular describes a generator with a novel feedback circuit resulting in improved frequency stability. The generator comprises two triodes having a common cathode circuit connected to oscillate at a frequency and amplitude at which the loop galn of the circutt ls unity, and another pair of triodes having a common cathode circuit arranged as a conventional amplifier. A signal is conducted from the osciliator through a frequency selective network to the amplifier and fed back to the osciliator. The unique feature of the feedback circuit is the amplifier operates in the nonlinear portion of its tube characteristics thereby providing a relatively constant feedback voltage to the oscillator irrespective of the amplitude of its input signal.

The Boeing plastic analysis capability for engines

NASA Technical Reports Server (NTRS)

Vos, R. G.

1976-01-01

The current BOPACE program is described as a nonlinear stress analysis program, which is based on a family of isoparametric finite elements. The theoretical, user, programmer, preprocessing aspects are discussed, and example problems are included. New features in the current program version include substructuring, an out-of-core Gauss wavefront equation solver, multipoint constraints, combined material and geometric nonlinearities, automatic calculation of inertia effects, provision for distributed as well as concentrated mechanical loads, follower forces, singular crack-tip elements, the SAIL automatic generation capability, and expanded user control over input quantity definition, output selection, and program execution. BOPACE is written in FORTRAN 4 and is currently available for both the IBM 360/370 and the UNIVAC 1108 machines.

Learned filters for object detection in multi-object visual tracking

NASA Astrophysics Data System (ADS)

Stamatescu, Victor; Wong, Sebastien; McDonnell, Mark D.; Kearney, David

2016-05-01

We investigate the application of learned convolutional filters in multi-object visual tracking. The filters were learned in both a supervised and unsupervised manner from image data using artificial neural networks. This work follows recent results in the field of machine learning that demonstrate the use learned filters for enhanced object detection and classification. Here we employ a track-before-detect approach to multi-object tracking, where tracking guides the detection process. The object detection provides a probabilistic input image calculated by selecting from features obtained using banks of generative or discriminative learned filters. We present a systematic evaluation of these convolutional filters using a real-world data set that examines their performance as generic object detectors.

Maximizing lipocalin prediction through balanced and diversified training set and decision fusion.

PubMed

Nath, Abhigyan; Subbiah, Karthikeyan

2015-12-01

Lipocalins are short in sequence length and perform several important biological functions. These proteins are having less than 20% sequence similarity among paralogs. Experimentally identifying them is an expensive and time consuming process. The computational methods based on the sequence similarity for allocating putative members to this family are also far elusive due to the low sequence similarity existing among the members of this family. Consequently, the machine learning methods become a viable alternative for their prediction by using the underlying sequence/structurally derived features as the input. Ideally, any machine learning based prediction method must be trained with all possible variations in the input feature vector (all the sub-class input patterns) to achieve perfect learning. A near perfect learning can be achieved by training the model with diverse types of input instances belonging to the different regions of the entire input space. Furthermore, the prediction performance can be improved through balancing the training set as the imbalanced data sets will tend to produce the prediction bias towards majority class and its sub-classes. This paper is aimed to achieve (i) the high generalization ability without any classification bias through the diversified and balanced training sets as well as (ii) enhanced the prediction accuracy by combining the results of individual classifiers with an appropriate fusion scheme. Instead of creating the training set randomly, we have first used the unsupervised Kmeans clustering algorithm to create diversified clusters of input patterns and created the diversified and balanced training set by selecting an equal number of patterns from each of these clusters. Finally, probability based classifier fusion scheme was applied on boosted random forest algorithm (which produced greater sensitivity) and K nearest neighbour algorithm (which produced greater specificity) to achieve the enhanced predictive performance than that of individual base classifiers. The performance of the learned models trained on Kmeans preprocessed training set is far better than the randomly generated training sets. The proposed method achieved a sensitivity of 90.6%, specificity of 91.4% and accuracy of 91.0% on the first test set and sensitivity of 92.9%, specificity of 96.2% and accuracy of 94.7% on the second blind test set. These results have established that diversifying training set improves the performance of predictive models through superior generalization ability and balancing the training set improves prediction accuracy. For smaller data sets, unsupervised Kmeans based sampling can be an effective technique to increase generalization than that of the usual random splitting method. Copyright © 2015 Elsevier Ltd. All rights reserved.

Automatic selection of localized region-based active contour models using image content analysis applied to brain tumor segmentation.

PubMed

Ilunga-Mbuyamba, Elisee; Avina-Cervantes, Juan Gabriel; Cepeda-Negrete, Jonathan; Ibarra-Manzano, Mario Alberto; Chalopin, Claire

2017-12-01

Brain tumor segmentation is a routine process in a clinical setting and provides useful information for diagnosis and treatment planning. Manual segmentation, performed by physicians or radiologists, is a time-consuming task due to the large quantity of medical data generated presently. Hence, automatic segmentation methods are needed, and several approaches have been introduced in recent years including the Localized Region-based Active Contour Model (LRACM). There are many popular LRACM, but each of them presents strong and weak points. In this paper, the automatic selection of LRACM based on image content and its application on brain tumor segmentation is presented. Thereby, a framework to select one of three LRACM, i.e., Local Gaussian Distribution Fitting (LGDF), localized Chan-Vese (C-V) and Localized Active Contour Model with Background Intensity Compensation (LACM-BIC), is proposed. Twelve visual features are extracted to properly select the method that may process a given input image. The system is based on a supervised approach. Applied specifically to Magnetic Resonance Imaging (MRI) images, the experiments showed that the proposed system is able to correctly select the suitable LRACM to handle a specific image. Consequently, the selection framework achieves better accuracy performance than the three LRACM separately. Copyright © 2017 Elsevier Ltd. All rights reserved.

The minimal amount of starting DNA for Agilent’s hybrid capture-based targeted massively parallel sequencing

PubMed Central

Chung, Jongsuk; Son, Dae-Soon; Jeon, Hyo-Jeong; Kim, Kyoung-Mee; Park, Gahee; Ryu, Gyu Ha; Park, Woong-Yang; Park, Donghyun

2016-01-01

Targeted capture massively parallel sequencing is increasingly being used in clinical settings, and as costs continue to decline, use of this technology may become routine in health care. However, a limited amount of tissue has often been a challenge in meeting quality requirements. To offer a practical guideline for the minimum amount of input DNA for targeted sequencing, we optimized and evaluated the performance of targeted sequencing depending on the input DNA amount. First, using various amounts of input DNA, we compared commercially available library construction kits and selected Agilent’s SureSelect-XT and KAPA Biosystems’ Hyper Prep kits as the kits most compatible with targeted deep sequencing using Agilent’s SureSelect custom capture. Then, we optimized the adapter ligation conditions of the Hyper Prep kit to improve library construction efficiency and adapted multiplexed hybrid selection to reduce the cost of sequencing. In this study, we systematically evaluated the performance of the optimized protocol depending on the amount of input DNA, ranging from 6.25 to 200 ng, suggesting the minimal input DNA amounts based on coverage depths required for specific applications. PMID:27220682

Optimal input selection for neural machine interfaces predicting multiple non-explicit outputs.

PubMed

Krepkovich, Eileen T; Perreault, Eric J

2008-01-01

This study implemented a novel algorithm that optimally selects inputs for neural machine interface (NMI) devices intended to control multiple outputs and evaluated its performance on systems lacking explicit output. NMIs often incorporate signals from multiple physiological sources and provide predictions for multidimensional control, leading to multiple-input multiple-output systems. Further, NMIs often are used with subjects who have motor disabilities and thus lack explicit motor outputs. Our algorithm was tested on simulated multiple-input multiple-output systems and on electromyogram and kinematic data collected from healthy subjects performing arm reaches. Effects of output noise in simulated systems indicated that the algorithm could be useful for systems with poor estimates of the output states, as is true for systems lacking explicit motor output. To test efficacy on physiological data, selection was performed using inputs from one subject and outputs from a different subject. Selection was effective for these cases, again indicating that this algorithm will be useful for predictions where there is no motor output, as often is the case for disabled subjects. Further, prediction results generalized for different movement types not used for estimation. These results demonstrate the efficacy of this algorithm for the development of neural machine interfaces.

Quantum-enhanced feature selection with forward selection and backward elimination

NASA Astrophysics Data System (ADS)

He, Zhimin; Li, Lvzhou; Huang, Zhiming; Situ, Haozhen

2018-07-01

Feature selection is a well-known preprocessing technique in machine learning, which can remove irrelevant features to improve the generalization capability of a classifier and reduce training and inference time. However, feature selection is time-consuming, particularly for the applications those have thousands of features, such as image retrieval, text mining and microarray data analysis. It is crucial to accelerate the feature selection process. We propose a quantum version of wrapper-based feature selection, which converts a classical feature selection to its quantum counterpart. It is valuable for machine learning on quantum computer. In this paper, we focus on two popular kinds of feature selection methods, i.e., wrapper-based forward selection and backward elimination. The proposed feature selection algorithm can quadratically accelerate the classical one.

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.

Synchronisation hubs in the visual cortex may arise from strong rhythmic inhibition during gamma oscillations.

PubMed

Folias, Stefanos E; Yu, Shan; Snyder, Abigail; Nikolić, Danko; Rubin, Jonathan E

2013-09-01

Neurons in the visual cortex exhibit heterogeneity in feature selectivity and the tendency to generate action potentials synchronously with other nearby neurons. By examining visual responses from cat area 17 we found that, during gamma oscillations, there was a positive correlation between each unit's sharpness of orientation tuning, strength of oscillations, and propensity towards synchronisation with other units. Using a computational model, we demonstrated that heterogeneity in the strength of rhythmic inhibitory inputs can account for the correlations between these three properties. Neurons subject to strong inhibition tend to oscillate strongly in response to both optimal and suboptimal stimuli and synchronise promiscuously with other neurons, even if they have different orientation preferences. Moreover, these strongly inhibited neurons can exhibit sharp orientation selectivity provided that the inhibition they receive is broadly tuned relative to their excitatory inputs. These results predict that the strength and orientation tuning of synaptic inhibition are heterogeneous across area 17 neurons, which could have important implications for these neurons' sensory processing capabilities. Furthermore, although our experimental recordings were conducted in the visual cortex, our model and simulation results can apply more generally to any brain region with analogous neuron types in which heterogeneity in the strength of rhythmic inhibition can arise during gamma oscillations. © 2013 Federation of European Neuroscience Societies and John Wiley & Sons Ltd.

A novel content-based medical image retrieval method based on query topic dependent image features (QTDIF)

NASA Astrophysics Data System (ADS)

Xiong, Wei; Qiu, Bo; Tian, Qi; Mueller, Henning; Xu, Changsheng

2005-04-01

Medical image retrieval is still mainly a research domain with a large variety of applications and techniques. With the ImageCLEF 2004 benchmark, an evaluation framework has been created that includes a database, query topics and ground truth data. Eleven systems (with a total of more than 50 runs) compared their performance in various configurations. The results show that there is not any one feature that performs well on all query tasks. Key to successful retrieval is rather the selection of features and feature weights based on a specific set of input features, thus on the query task. In this paper we propose a novel method based on query topic dependent image features (QTDIF) for content-based medical image retrieval. These feature sets are designed to capture both inter-category and intra-category statistical variations to achieve good retrieval performance in terms of recall and precision. We have used Gaussian Mixture Models (GMM) and blob representation to model medical images and construct the proposed novel QTDIF for CBIR. Finally, trained multi-class support vector machines (SVM) are used for image similarity ranking. The proposed methods have been tested over the Casimage database with around 9000 images, for the given 26 image topics, used for imageCLEF 2004. The retrieval performance has been compared with the medGIFT system, which is based on the GNU Image Finding Tool (GIFT). The experimental results show that the proposed QTDIF-based CBIR can provide significantly better performance than systems based general features only.

Structures of the recurrence plot of heart rate variability signal as a tool for predicting the onset of paroxysmal atrial fibrillation.

PubMed

Mohebbi, Maryam; Ghassemian, Hassan; Asl, Babak Mohammadzadeh

2011-05-01

This paper aims to propose an effective paroxysmal atrial fibrillation (PAF) predictor which is based on the analysis of the heart rate variability (HRV) signal. Predicting the onset of PAF, based on non-invasive techniques, is clinically important and can be invaluable in order to avoid useless therapeutic interventions and to minimize the risks for the patients. This method consists of four steps: Preprocessing, feature extraction, feature reduction, and classification. In the first step, the QRS complexes are detected from the electrocardiogram (ECG) signal and then the HRV signal is extracted. In the next step, the recurrence plot (RP) of HRV signal is obtained and six features are extracted to characterize the basic patterns of the RP. These features consist of length of longest diagonal segments, average length of the diagonal lines, entropy, trapping time, length of longest vertical line, and recurrence trend. In the third step, these features are reduced to three features by the linear discriminant analysis (LDA) technique. Using LDA not only reduces the number of the input features, but also increases the classification accuracy by selecting the most discriminating features. Finally, a support vector machine-based classifier is used to classify the HRV signals. The performance of the proposed method in prediction of PAF episodes was evaluated using the Atrial Fibrillation Prediction Database which consists of both 30-minutes ECG recordings end just prior to the onset of PAF and segments at least 45 min distant from any PAF events. The obtained sensitivity, specificity, and positive predictivity were 96.55%, 100%, and 100%, respectively.

Identification and Description of Alternative Means of Accomplishing IMS Operational Features.

ERIC Educational Resources Information Center

Dave, Ashok

The operational features of feasible alternative configurations for a computer-based instructional management system are identified. Potential alternative means and components of accomplishing these features are briefly described. Included are aspects of data collection, data input, data transmission, data reception, scanning and processing,…

System and method for controlling ammonia levels in a selective catalytic reduction catalyst using a nitrogen oxide sensor

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

None

A system according to the principles of the present disclosure includes an air/fuel ratio determination module and an emission level determination module. The air/fuel ratio determination module determines an air/fuel ratio based on input from an air/fuel ratio sensor positioned downstream from a three-way catalyst that is positioned upstream from a selective catalytic reduction (SCR) catalyst. The emission level determination module selects one of a predetermined value and an input based on the air/fuel ratio. The input is received from a nitrogen oxide sensor positioned downstream from the three-way catalyst. The emission level determination module determines an ammonia level basedmore » on the one of the predetermined value and the input received from the nitrogen oxide sensor.« less

Quantity and Quality of Caregivers' Linguistic Input to 18-Month and 3-Year-Old Children Who Are Hard of Hearing.

PubMed

Ambrose, Sophie E; Walker, Elizabeth A; Unflat-Berry, Lauren M; Oleson, Jacob J; Moeller, Mary Pat

2015-01-01

The primary objective of this study was to examine the quantity and quality of caregiver talk directed to children who are hard of hearing (CHH) compared with children with normal hearing (CNH). For the CHH only, the study explored how caregiver input changed as a function of child age (18 months versus 3 years), which child and family factors contributed to variance in caregiver linguistic input at 18 months and 3 years, and how caregiver talk at 18 months related to child language outcomes at 3 years. Participants were 59 CNH and 156 children with bilateral, mild-to-severe hearing loss. When children were approximately 18 months and/or 3 years of age, caregivers and children participated in a 5-min semistructured, conversational interaction. Interactions were transcribed and coded for two features of caregiver input representing quantity (number of total utterances and number of total words) and four features representing quality (number of different words, mean length of utterance in morphemes, proportion of utterances that were high level, and proportion of utterances that were directing). In addition, at the 18-month visit, parents completed a standardized questionnaire regarding their child's communication development. At the 3-year visit, a clinician administered a standardized language measure. At the 18-month visit, the CHH were exposed to a greater proportion of directing utterances than the CNH. At the 3-year visit, there were significant differences between the CNH and CHH for number of total words and all four of the quality variables, with the CHH being exposed to fewer words and lower quality input. Caregivers generally provided higher quality input to CHH at the 3-year visit compared with the 18-month visit. At the 18-month visit, quantity variables, but not quality variables, were related to several child and family factors. At the 3-year visit, the variable most strongly related to caregiver input was child language. Longitudinal analyses indicated that quality, but not quantity, of caregiver linguistic input at 18 months was related to child language abilities at 3 years, with directing utterances accounting for significant unique variance in child language outcomes. Although caregivers of CHH increased their use of quality features of linguistic input over time, the differences when compared with CNH suggest that some caregivers may need additional support to provide their children with optimal language learning environments. This is particularly important given the relationships that were identified between quality features of caregivers' linguistic input and children's language abilities. Family supports should include a focus on developing a style that is conversational eliciting as opposed to directive.

Computer program for analysis of high speed, single row, angular contact, spherical roller bearing, SASHBEAN. Volume 1: User's guide

NASA Technical Reports Server (NTRS)

Aggarwal, Arun K.

1993-01-01

The computer program SASHBEAN (Sikorsky Aircraft Spherical Roller High Speed Bearing Analysis) analyzes and predicts the operating characteristics of a Single Row, Angular Contact, Spherical Roller Bearing (SRACSRB). The program runs on an IBM or IBM compatible personal computer, and for a given set of input data analyzes the bearing design for it's ring deflections (axial and radial), roller deflections, contact areas and stresses, induced axial thrust, rolling element and cage rotation speeds, lubrication parameters, fatigue lives, and amount of heat generated in the bearing. The dynamic loading of rollers due to centrifugal forces and gyroscopic moments, which becomes quite significant at high speeds, is fully considered in this analysis. For a known application and it's parameters, the program is also capable of performing steady-state and time-transient thermal analyses of the bearing system. The steady-state analysis capability allows the user to estimate the expected steady-state temperature map in and around the bearing under normal operating conditions. On the other hand, the transient analysis feature provides the user a means to simulate the 'lost lubricant' condition and predict a time-temperature history of various critical points in the system. The bearing's 'time-to-failure' estimate may also be made from this (transient) analysis by considering the bearing as failed when a certain temperature limit is reached in the bearing components. The program is fully interactive and allows the user to get started and access most of its features with a minimal of training. For the most part, the program is menu driven, and adequate help messages were provided to guide a new user through various menu options and data input screens. All input data, both for mechanical and thermal analyses, are read through graphical input screens, thereby eliminating any need of a separate text editor/word processor to edit/create data files. Provision is also available to select and view the contents of output files on the monitor screen if no paper printouts are required. A separate volume (Volume-2) of this documentation describes, in detail, the underlying mathematical formulations, assumptions, and solution algorithms of this program.

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.

Segmenting texts from outdoor images taken by mobile phones using color features

NASA Astrophysics Data System (ADS)

Liu, Zongyi; Zhou, Hanning

2011-01-01

Recognizing texts from images taken by mobile phones with low resolution has wide applications. It has been shown that a good image binarization can substantially improve the performances of OCR engines. In this paper, we present a framework to segment texts from outdoor images taken by mobile phones using color features. The framework consists of three steps: (i) the initial process including image enhancement, binarization and noise filtering, where we binarize the input images in each RGB channel, and apply component level noise filtering; (ii) grouping components into blocks using color features, where we compute the component similarities by dynamically adjusting the weights of RGB channels, and merge groups hierachically, and (iii) blocks selection, where we use the run-length features and choose the Support Vector Machine (SVM) as the classifier. We tested the algorithm using 13 outdoor images taken by an old-style LG-64693 mobile phone with 640x480 resolution. We compared the segmentation results with Tsar's algorithm, a state-of-the-art camera text detection algorithm, and show that our algorithm is more robust, particularly in terms of the false alarm rates. In addition, we also evaluated the impacts of our algorithm on the Abbyy's FineReader, one of the most popular commercial OCR engines in the market.

Feature Selection for Chemical Sensor Arrays Using Mutual Information

PubMed Central

Wang, X. Rosalind; Lizier, Joseph T.; Nowotny, Thomas; Berna, Amalia Z.; Prokopenko, Mikhail; Trowell, Stephen C.

2014-01-01

We address the problem of feature selection for classifying a diverse set of chemicals using an array of metal oxide sensors. Our aim is to evaluate a filter approach to feature selection with reference to previous work, which used a wrapper approach on the same data set, and established best features and upper bounds on classification performance. We selected feature sets that exhibit the maximal mutual information with the identity of the chemicals. The selected features closely match those found to perform well in the previous study using a wrapper approach to conduct an exhaustive search of all permitted feature combinations. By comparing the classification performance of support vector machines (using features selected by mutual information) with the performance observed in the previous study, we found that while our approach does not always give the maximum possible classification performance, it always selects features that achieve classification performance approaching the optimum obtained by exhaustive search. We performed further classification using the selected feature set with some common classifiers and found that, for the selected features, Bayesian Networks gave the best performance. Finally, we compared the observed classification performances with the performance of classifiers using randomly selected features. We found that the selected features consistently outperformed randomly selected features for all tested classifiers. The mutual information filter approach is therefore a computationally efficient method for selecting near optimal features for chemical sensor arrays. PMID:24595058

Advancements in automated tissue segmentation pipeline for contrast-enhanced CT scans of adult and pediatric patients

NASA Astrophysics Data System (ADS)

Somasundaram, Elanchezhian; Kaufman, Robert; Brady, Samuel

2017-03-01

The development of a random forests machine learning technique is presented for fully-automated neck, chest, abdomen, and pelvis tissue segmentation of CT images using Trainable WEKA (Waikato Environment for Knowledge Analysis) Segmentation (TWS) plugin of FIJI (ImageJ, NIH). The use of a single classifier model to segment six tissue classes (lung, fat, muscle, solid organ, blood/contrast agent, bone) in the CT images is studied. An automated unbiased scheme to sample pixels from the training images and generate a balanced training dataset over the seven classes is also developed. Two independent training datasets are generated from a pool of 4 adult (>55 kg) and 3 pediatric patients (<=55 kg) with 7 manually contoured slices for each patient. Classifier training investigated 28 image filters comprising a total of 272 features. Highly correlated and insignificant features are eliminated using Correlated Feature Subset (CFS) selection with Best First Search (BFS) algorithms in WEKA. The 2 training models (from the 2 training datasets) had 74 and 71 input training features, respectively. The study also investigated the effect of varying the number of trees (25, 50, 100, and 200) in the random forest algorithm. The performance of the 2 classifier models are evaluated on inter-patient intra-slice, intrapatient inter-slice and inter-patient inter-slice test datasets. The Dice similarity coefficients (DSC) and confusion matrices are used to understand the performance of the classifiers across the tissue segments. The effect of number of features in the training input on the performance of the classifiers for tissue classes with less than optimal DSC values is also studied. The average DSC values for the two training models on the inter-patient intra-slice test data are: 0.98, 0.89, 0.87, 0.79, 0.68, and 0.84, for lung, fat, muscle, solid organ, blood/contrast agent, and bone, respectively. The study demonstrated that a robust segmentation accuracy for lung, muscle and fat tissue classes. For solid-organ, blood/contrast and bone, the performance of the segmentation pipeline improved significantly by using the advanced capabilities of WEKA. However, further improvements are needed to reduce the noise in the segmentation.

Abnormal externally guided movement preparation in recent-onset schizophrenia is associated with impaired selective attention to external input.

PubMed

Smid, Henderikus G O M; Westenbroek, Joanna M; Bruggeman, Richard; Knegtering, Henderikus; Van den Bosch, Robert J

2009-11-30

Several theories propose that the primary cognitive impairment in schizophrenia concerns a deficit in the processing of external input information. There is also evidence, however, for impaired motor preparation in schizophrenia. This provokes the question whether the impaired motor preparation in schizophrenia is a secondary consequence of disturbed (selective) processing of the input needed for that preparation, or an independent primary deficit. The aim of the present study was to discriminate between these hypotheses, by investigating externally guided movement preparation in relation to selective stimulus processing. The sample comprised 16 recent-onset schizophrenia patients and 16 controls who performed a movement-precuing task. In this task, a precue delivered information about one, two or no parameters of a movement summoned by a subsequent stimulus. Performance measures and measures derived from the electroencephalogram showed that patients yielded smaller benefits from the precues and showed less cue-based preparatory activity in advance of the imperative stimulus than the controls, suggesting a response preparation deficit. However, patients also showed less activity reflecting selective attention to the precue. We therefore conclude that the existing evidence for an impairment of externally guided motor preparation in schizophrenia is most likely due to a deficit in selective attention to the external input, which lends support to theories proposing that the primary cognitive deficit in schizophrenia concerns the processing of input information.

Space station Simulation Computer System (SCS) study for NASA/MSFC. Volume 3: Refined conceptual design report

NASA Technical Reports Server (NTRS)

1989-01-01

The results of the refined conceptual design phase (task 5) of the Simulation Computer System (SCS) study are reported. The SCS is the computational portion of the Payload Training Complex (PTC) providing simulation based training on payload operations of the Space Station Freedom (SSF). In task 4 of the SCS study, the range of architectures suitable for the SCS was explored. Identified system architectures, along with their relative advantages and disadvantages for SCS, were presented in the Conceptual Design Report. Six integrated designs-combining the most promising features from the architectural formulations-were additionally identified in the report. The six integrated designs were evaluated further to distinguish the more viable designs to be refined as conceptual designs. The three designs that were selected represent distinct approaches to achieving a capable and cost effective SCS configuration for the PTC. Here, the results of task 4 (input to this task) are briefly reviewed. Then, prior to describing individual conceptual designs, the PTC facility configuration and the SSF systems architecture that must be supported by the SCS are reviewed. Next, basic features of SCS implementation that have been incorporated into all selected SCS designs are considered. The details of the individual SCS designs are then presented before making a final comparison of the three designs.

A new approach for categorizing pig lying behaviour based on a Delaunay triangulation method.

PubMed

Nasirahmadi, A; Hensel, O; Edwards, S A; Sturm, B

2017-01-01

Machine vision-based monitoring of pig lying behaviour is a fast and non-intrusive approach that could be used to improve animal health and welfare. Four pens with 22 pigs in each were selected at a commercial pig farm and monitored for 15 days using top view cameras. Three thermal categories were selected relative to room setpoint temperature. An image processing technique based on Delaunay triangulation (DT) was utilized. Different lying patterns (close, normal and far) were defined regarding the perimeter of each DT triangle and the percentages of each lying pattern were obtained in each thermal category. A method using a multilayer perceptron (MLP) neural network, to automatically classify group lying behaviour of pigs into three thermal categories, was developed and tested for its feasibility. The DT features (mean value of perimeters, maximum and minimum length of sides of triangles) were calculated as inputs for the MLP classifier. The network was trained, validated and tested and the results revealed that MLP could classify lying features into the three thermal categories with high overall accuracy (95.6%). The technique indicates that a combination of image processing, MLP classification and mathematical modelling can be used as a precise method for quantifying pig lying behaviour in welfare investigations.

Retrieval of spheroid particle size distribution from spectral extinction data in the independent mode using PCA approach

NASA Astrophysics Data System (ADS)

Tang, Hong; Lin, Jian-Zhong

2013-01-01

An improved anomalous diffraction approximation (ADA) method is presented for calculating the extinction efficiency of spheroids firstly. In this approach, the extinction efficiency of spheroid particles can be calculated with good accuracy and high efficiency in a wider size range by combining the Latimer method and the ADA theory, and this method can present a more general expression for calculating the extinction efficiency of spheroid particles with various complex refractive indices and aspect ratios. Meanwhile, the visible spectral extinction with varied spheroid particle size distributions and complex refractive indices is surveyed. Furthermore, a selection principle about the spectral extinction data is developed based on PCA (principle component analysis) of first derivative spectral extinction. By calculating the contribution rate of first derivative spectral extinction, the spectral extinction with more significant features can be selected as the input data, and those with less features is removed from the inversion data. In addition, we propose an improved Tikhonov iteration method to retrieve the spheroid particle size distributions in the independent mode. Simulation experiments indicate that the spheroid particle size distributions obtained with the proposed method coincide fairly well with the given distributions, and this inversion method provides a simple, reliable and efficient method to retrieve the spheroid particle size distributions from the spectral extinction data.

Formation enthalpies for transition metal alloys using machine learning

NASA Astrophysics Data System (ADS)

Ubaru, Shashanka; Miedlar, Agnieszka; Saad, Yousef; Chelikowsky, James R.

2017-06-01

The enthalpy of formation is an important thermodynamic property. Developing fast and accurate methods for its prediction is of practical interest in a variety of applications. Material informatics techniques based on machine learning have recently been introduced in the literature as an inexpensive means of exploiting materials data, and can be used to examine a variety of thermodynamics properties. We investigate the use of such machine learning tools for predicting the formation enthalpies of binary intermetallic compounds that contain at least one transition metal. We consider certain easily available properties of the constituting elements complemented by some basic properties of the compounds, to predict the formation enthalpies. We show how choosing these properties (input features) based on a literature study (using prior physics knowledge) seems to outperform machine learning based feature selection methods such as sensitivity analysis and LASSO (least absolute shrinkage and selection operator) based methods. A nonlinear kernel based support vector regression method is employed to perform the predictions. The predictive ability of our model is illustrated via several experiments on a dataset containing 648 binary alloys. We train and validate the model using the formation enthalpies calculated using a model by Miedema, which is a popular semiempirical model used for the prediction of formation enthalpies of metal alloys.

What's what in auditory cortices?

PubMed

Retsa, Chrysa; Matusz, Pawel J; Schnupp, Jan W H; Murray, Micah M

2018-08-01

Distinct anatomical and functional pathways are postulated for analysing a sound's object-related ('what') and space-related ('where') information. It remains unresolved to which extent distinct or overlapping neural resources subserve specific object-related dimensions (i.e. who is speaking and what is being said can both be derived from the same acoustic input). To address this issue, we recorded high-density auditory evoked potentials (AEPs) while participants selectively attended and discriminated sounds according to their pitch, speaker identity, uttered syllable ('what' dimensions) or their location ('where'). Sound acoustics were held constant across blocks; the only manipulation involved the sound dimension that participants had to attend to. The task-relevant dimension was varied across blocks. AEPs from healthy participants were analysed within an electrical neuroimaging framework to differentiate modulations in response strength from modulations in response topography; the latter of which forcibly follow from changes in the configuration of underlying sources. There were no behavioural differences in discrimination of sounds across the 4 feature dimensions. As early as 90ms post-stimulus onset, AEP topographies differed across 'what' conditions, supporting a functional sub-segregation within the auditory 'what' pathway. This study characterises the spatio-temporal dynamics of segregated, yet parallel, processing of multiple sound object-related feature dimensions when selective attention is directed to them. Copyright © 2018 Elsevier Inc. All rights reserved.

Rough sets and Laplacian score based cost-sensitive feature selection

PubMed Central

Yu, Shenglong

2018-01-01

Cost-sensitive feature selection learning is an important preprocessing step in machine learning and data mining. Recently, most existing cost-sensitive feature selection algorithms are heuristic algorithms, which evaluate the importance of each feature individually and select features one by one. Obviously, these algorithms do not consider the relationship among features. In this paper, we propose a new algorithm for minimal cost feature selection called the rough sets and Laplacian score based cost-sensitive feature selection. The importance of each feature is evaluated by both rough sets and Laplacian score. Compared with heuristic algorithms, the proposed algorithm takes into consideration the relationship among features with locality preservation of Laplacian score. We select a feature subset with maximal feature importance and minimal cost when cost is undertaken in parallel, where the cost is given by three different distributions to simulate different applications. Different from existing cost-sensitive feature selection algorithms, our algorithm simultaneously selects out a predetermined number of “good” features. Extensive experimental results show that the approach is efficient and able to effectively obtain the minimum cost subset. In addition, the results of our method are more promising than the results of other cost-sensitive feature selection algorithms. PMID:29912884

Rough sets and Laplacian score based cost-sensitive feature selection.

PubMed

Yu, Shenglong; Zhao, Hong

2018-01-01

Cost-sensitive feature selection learning is an important preprocessing step in machine learning and data mining. Recently, most existing cost-sensitive feature selection algorithms are heuristic algorithms, which evaluate the importance of each feature individually and select features one by one. Obviously, these algorithms do not consider the relationship among features. In this paper, we propose a new algorithm for minimal cost feature selection called the rough sets and Laplacian score based cost-sensitive feature selection. The importance of each feature is evaluated by both rough sets and Laplacian score. Compared with heuristic algorithms, the proposed algorithm takes into consideration the relationship among features with locality preservation of Laplacian score. We select a feature subset with maximal feature importance and minimal cost when cost is undertaken in parallel, where the cost is given by three different distributions to simulate different applications. Different from existing cost-sensitive feature selection algorithms, our algorithm simultaneously selects out a predetermined number of "good" features. Extensive experimental results show that the approach is efficient and able to effectively obtain the minimum cost subset. In addition, the results of our method are more promising than the results of other cost-sensitive feature selection algorithms.

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.

NEBNext Direct: A Novel, Rapid, Hybridization-Based Approach for the Capture and Library Conversion of Genomic Regions of Interest.

PubMed

Emerman, Amy B; Bowman, Sarah K; Barry, Andrew; Henig, Noa; Patel, Kruti M; Gardner, Andrew F; Hendrickson, Cynthia L

2017-07-05

Next-generation sequencing (NGS) is a powerful tool for genomic studies, translational research, and clinical diagnostics that enables the detection of single nucleotide polymorphisms, insertions and deletions, copy number variations, and other genetic variations. Target enrichment technologies improve the efficiency of NGS by only sequencing regions of interest, which reduces sequencing costs while increasing coverage of the selected targets. Here we present NEBNext Direct ® , a hybridization-based, target-enrichment approach that addresses many of the shortcomings of traditional target-enrichment methods. This approach features a simple, 7-hr workflow that uses enzymatic removal of off-target sequences to achieve a high specificity for regions of interest. Additionally, unique molecular identifiers are incorporated for the identification and filtering of PCR duplicates. The same protocol can be used across a wide range of input amounts, input types, and panel sizes, enabling NEBNext Direct to be broadly applicable across a wide variety of research and diagnostic needs. © 2017 by John Wiley & Sons, Inc. Copyright © 2017 John Wiley & Sons, Inc.

An incremental approach to genetic-algorithms-based classification.

PubMed

Guan, Sheng-Uei; Zhu, Fangming

2005-04-01

Incremental learning has been widely addressed in the machine learning literature to cope with learning tasks where the learning environment is ever changing or training samples become available over time. However, most research work explores incremental learning with statistical algorithms or neural networks, rather than evolutionary algorithms. The work in this paper employs genetic algorithms (GAs) as basic learning algorithms for incremental learning within one or more classifier agents in a multiagent environment. Four new approaches with different initialization schemes are proposed. They keep the old solutions and use an "integration" operation to integrate them with new elements to accommodate new attributes, while biased mutation and crossover operations are adopted to further evolve a reinforced solution. The simulation results on benchmark classification data sets show that the proposed approaches can deal with the arrival of new input attributes and integrate them with the original input space. It is also shown that the proposed approaches can be successfully used for incremental learning and improve classification rates as compared to the retraining GA. Possible applications for continuous incremental training and feature selection are also discussed.

Stochastic Resonance in an Underdamped System with Pinning Potential for Weak Signal Detection

PubMed Central

Zhang, Haibin; He, Qingbo; Kong, Fanrang

2015-01-01

Stochastic resonance (SR) has been proved to be an effective approach for weak sensor signal detection. This study presents a new weak signal detection method based on a SR in an underdamped system, which consists of a pinning potential model. The model was firstly discovered from magnetic domain wall (DW) in ferromagnetic strips. We analyze the principle of the proposed underdamped pinning SR (UPSR) system, the detailed numerical simulation and system performance. We also propose the strategy of selecting the proper damping factor and other system parameters to match a weak signal, input noise and to generate the highest output signal-to-noise ratio (SNR). Finally, we have verified its effectiveness with both simulated and experimental input signals. Results indicate that the UPSR performs better in weak signal detection than the conventional SR (CSR) with merits of higher output SNR, better anti-noise and frequency response capability. Besides, the system can be designed accurately and efficiently owing to the sensibility of parameters and potential diversity. The features also weaken the limitation of small parameters on SR system. PMID:26343662

Stochastic Resonance in an Underdamped System with Pinning Potential for Weak Signal Detection.

PubMed

Zhang, Haibin; He, Qingbo; Kong, Fanrang

2015-08-28

Stochastic resonance (SR) has been proved to be an effective approach for weak sensor signal detection. This study presents a new weak signal detection method based on a SR in an underdamped system, which consists of a pinning potential model. The model was firstly discovered from magnetic domain wall (DW) in ferromagnetic strips. We analyze the principle of the proposed underdamped pinning SR (UPSR) system, the detailed numerical simulation and system performance. We also propose the strategy of selecting the proper damping factor and other system parameters to match a weak signal, input noise and to generate the highest output signal-to-noise ratio (SNR). Finally, we have verified its effectiveness with both simulated and experimental input signals. Results indicate that the UPSR performs better in weak signal detection than the conventional SR (CSR) with merits of higher output SNR, better anti-noise and frequency response capability. Besides, the system can be designed accurately and efficiently owing to the sensibility of parameters and potential diversity. The features also weaken the limitation of small parameters on SR system.

Affine Projection Algorithm with Improved Data-Selective Method Using the Condition Number

NASA Astrophysics Data System (ADS)

Ban, Sung Jun; Lee, Chang Woo; Kim, Sang Woo

Recently, a data-selective method has been proposed to achieve low misalignment in affine projection algorithm (APA) by keeping the condition number of an input data matrix small. We present an improved method, and a complexity reduction algorithm for the APA with the data-selective method. Experimental results show that the proposed algorithm has lower misalignment and a lower condition number for an input data matrix than both the conventional APA and the APA with the previous data-selective method.

Machine Learning Classification of Heterogeneous Fields to Estimate Physical Responses

NASA Astrophysics Data System (ADS)

McKenna, S. A.; Akhriev, A.; Alzate, C.; Zhuk, S.

2017-12-01

The promise of machine learning to enhance physics-based simulation is examined here using the transient pressure response to a pumping well in a heterogeneous aquifer. 10,000 random fields of log10 hydraulic conductivity (K) are created and conditioned on a single K measurement at the pumping well. Each K-field is used as input to a forward simulation of drawdown (pressure decline). The differential equations governing groundwater flow to the well serve as a non-linear transform of the input K-field to an output drawdown field. The results are stored and the data set is split into training and testing sets for classification. A Euclidean distance measure between any two fields is calculated and the resulting distances between all pairs of fields define a similarity matrix. Similarity matrices are calculated for both input K-fields and the resulting drawdown fields at the end of the simulation. The similarity matrices are then used as input to spectral clustering to determine groupings of similar input and output fields. Additionally, the similarity matrix is used as input to multi-dimensional scaling to visualize the clustering of fields in lower dimensional spaces. We examine the ability to cluster both input K-fields and output drawdown fields separately with the goal of identifying K-fields that create similar drawdowns and, conversely, given a set of simulated drawdown fields, identify meaningful clusters of input K-fields. Feature extraction based on statistical parametric mapping provides insight into what features of the fields drive the classification results. The final goal is to successfully classify input K-fields into the correct output class, and also, given an output drawdown field, be able to infer the correct class of input field that created it.

Comparative evaluation of support vector machine classification for computer aided detection of breast masses in mammography

NASA Astrophysics Data System (ADS)

Lesniak, J. M.; Hupse, R.; Blanc, R.; Karssemeijer, N.; Székely, G.

2012-08-01

False positive (FP) marks represent an obstacle for effective use of computer-aided detection (CADe) of breast masses in mammography. Typically, the problem can be approached either by developing more discriminative features or by employing different classifier designs. In this paper, the usage of support vector machine (SVM) classification for FP reduction in CADe is investigated, presenting a systematic quantitative evaluation against neural networks, k-nearest neighbor classification, linear discriminant analysis and random forests. A large database of 2516 film mammography examinations and 73 input features was used to train the classifiers and evaluate for their performance on correctly diagnosed exams as well as false negatives. Further, classifier robustness was investigated using varying training data and feature sets as input. The evaluation was based on the mean exam sensitivity in 0.05-1 FPs on normals on the free-response receiver operating characteristic curve (FROC), incorporated into a tenfold cross validation framework. It was found that SVM classification using a Gaussian kernel offered significantly increased detection performance (P = 0.0002) compared to the reference methods. Varying training data and input features, SVMs showed improved exploitation of large feature sets. It is concluded that with the SVM-based CADe a significant reduction of FPs is possible outperforming other state-of-the-art approaches for breast mass CADe.

A High-Performance Reconfigurable Fabric for Cognitive Information Processing

DTIC Science & Technology

2010-12-01

receives a data token from its control input (shown as a horizontal arrow above). The value of this data token is used to select an input port. The...dual of a merge. It receives a data token from its control input (shown as a horizontal arrow above). The value of this data token is used to select...Computer-Aided Design of Intergrated Circuits and Systems, Vol. 26, No. 2, February 2007. [12] Cadence Design Systems. Clock Domain Crossing: Closing the

Kanerva's sparse distributed memory with multiple hamming thresholds

NASA Technical Reports Server (NTRS)

Pohja, Seppo; Kaski, Kimmo

1992-01-01

If the stored input patterns of Kanerva's Sparse Distributed Memory (SDM) are highly correlated, utilization of the storage capacity is very low compared to the case of uniformly distributed random input patterns. We consider a variation of SDM that has a better storage capacity utilization for correlated input patterns. This approach uses a separate selection threshold for each physical storage address or hard location. The selection of the hard locations for reading or writing can be done in parallel of which SDM implementations can benefit.

Gamma motor neurons survive and exacerbate alpha motor neuron degeneration in ALS.

PubMed

Lalancette-Hebert, Melanie; Sharma, Aarti; Lyashchenko, Alexander K; Shneider, Neil A

2016-12-20

The molecular and cellular basis of selective motor neuron (MN) vulnerability in amyotrophic lateral sclerosis (ALS) is not known. In genetically distinct mouse models of familial ALS expressing mutant superoxide dismutase-1 (SOD1), TAR DNA-binding protein 43 (TDP-43), and fused in sarcoma (FUS), we demonstrate selective degeneration of alpha MNs (α-MNs) and complete sparing of gamma MNs (γ-MNs), which selectively innervate muscle spindles. Resistant γ-MNs are distinct from vulnerable α-MNs in that they lack synaptic contacts from primary afferent (I A ) fibers. Elimination of these synapses protects α-MNs in the SOD1 mutant, implicating this excitatory input in MN degeneration. Moreover, reduced I A activation by targeted reduction of γ-MNs in SOD1 G93A mutants delays symptom onset and prolongs lifespan, demonstrating a pathogenic role of surviving γ-MNs in ALS. This study establishes the resistance of γ-MNs as a general feature of ALS mouse models and demonstrates that synaptic excitation of MNs within a complex circuit is an important determinant of relative vulnerability in ALS.

Gamma motor neurons survive and exacerbate alpha motor neuron degeneration in ALS

PubMed Central

Lalancette-Hebert, Melanie; Sharma, Aarti; Lyashchenko, Alexander K.; Shneider, Neil A.

2016-01-01

The molecular and cellular basis of selective motor neuron (MN) vulnerability in amyotrophic lateral sclerosis (ALS) is not known. In genetically distinct mouse models of familial ALS expressing mutant superoxide dismutase-1 (SOD1), TAR DNA-binding protein 43 (TDP-43), and fused in sarcoma (FUS), we demonstrate selective degeneration of alpha MNs (α-MNs) and complete sparing of gamma MNs (γ-MNs), which selectively innervate muscle spindles. Resistant γ-MNs are distinct from vulnerable α-MNs in that they lack synaptic contacts from primary afferent (IA) fibers. Elimination of these synapses protects α-MNs in the SOD1 mutant, implicating this excitatory input in MN degeneration. Moreover, reduced IA activation by targeted reduction of γ-MNs in SOD1G93A mutants delays symptom onset and prolongs lifespan, demonstrating a pathogenic role of surviving γ-MNs in ALS. This study establishes the resistance of γ-MNs as a general feature of ALS mouse models and demonstrates that synaptic excitation of MNs within a complex circuit is an important determinant of relative vulnerability in ALS. PMID:27930290

Applications of Mars Global Reference Atmospheric Model (Mars-GRAM 2005) Supporting Mission Site Selection for Mars Science Laboratory

NASA Technical Reports Server (NTRS)

Justh, Hilary L.; Justus, Carl G.

2008-01-01

The Mars Global Reference Atmospheric Model (Mars-GRAM 2005) is an engineering level atmospheric model widely used for diverse mission applications. An overview is presented of Mars-GRAM 2005 and its new features. One new feature of Mars-GRAM 2005 is the 'auxiliary profile' option. In this option, an input file of temperature and density versus altitude is used to replace mean atmospheric values from Mars-GRAM's conventional (General Circulation Model) climatology. An auxiliary profile can be generated from any source of data or alternate model output. Auxiliary profiles for this study were produced from mesoscale model output (Southwest Research Institute's Mars Regional Atmospheric Modeling System (MRAMS) model and Oregon State University's Mars mesoscale model (MMM5)model) and a global Thermal Emission Spectrometer(TES) database. The global TES database has been specifically generated for purposes of making Mars-GRAM auxiliary profiles. This data base contains averages and standard deviations of temperature, density, and thermal wind components,averaged over 5-by-5 degree latitude-longitude bins and 15 degree L(s) bins, for each of three Mars years of TES nadir data. Results are presented using auxiliary profiles produced from the mesoscale model output and TES observed data for candidate Mars Science Laboratory (MSL) landing sites. Input parameters rpscale (for density perturbations) and rwscale (for wind perturbations) can be used to "recalibrate" Mars-GRAM perturbation magnitudes to better replicate observed or mesoscale model variability.

Revisiting the Robustness of PET-Based Textural Features in the Context of Multi-Centric Trials.

PubMed

Bailly, Clément; Bodet-Milin, Caroline; Couespel, Solène; Necib, Hatem; Kraeber-Bodéré, Françoise; Ansquer, Catherine; Carlier, Thomas

2016-01-01

This study aimed to investigate the variability of textural features (TF) as a function of acquisition and reconstruction parameters within the context of multi-centric trials. The robustness of 15 selected TFs were studied as a function of the number of iterations, the post-filtering level, input data noise, the reconstruction algorithm and the matrix size. A combination of several reconstruction and acquisition settings was devised to mimic multi-centric conditions. We retrospectively studied data from 26 patients enrolled in a diagnostic study that aimed to evaluate the performance of PET/CT 68Ga-DOTANOC in gastro-entero-pancreatic neuroendocrine tumors. Forty-one tumors were extracted and served as the database. The coefficient of variation (COV) or the absolute deviation (for the noise study) was derived and compared statistically with SUVmax and SUVmean results. The majority of investigated TFs can be used in a multi-centric context when each parameter is considered individually. The impact of voxel size and noise in the input data were predominant as only 4 TFs presented a high/intermediate robustness against SUV-based metrics (Entropy, Homogeneity, RP and ZP). When combining several reconstruction settings to mimic multi-centric conditions, most of the investigated TFs were robust enough against SUVmax except Correlation, Contrast, LGRE, LGZE and LZLGE. Considering previously published results on either reproducibility or sensitivity against delineation approach and our findings, it is feasible to consider Homogeneity, Entropy, Dissimilarity, HGRE, HGZE and ZP as relevant for being used in multi-centric trials.

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.

Evaluation of Spectral and Prosodic Features of Speech Affected by Orthodontic Appliances Using the Gmm Classifier

NASA Astrophysics Data System (ADS)

Přibil, Jiří; Přibilová, Anna; Ďuračkoá, Daniela

2014-01-01

The paper describes our experiment with using the Gaussian mixture models (GMM) for classification of speech uttered by a person wearing orthodontic appliances. For the GMM classification, the input feature vectors comprise the basic and the complementary spectral properties as well as the supra-segmental parameters. Dependence of classification correctness on the number of the parameters in the input feature vector and on the computation complexity is also evaluated. In addition, an influence of the initial setting of the parameters for GMM training process was analyzed. Obtained recognition results are compared visually in the form of graphs as well as numerically in the form of tables and confusion matrices for tested sentences uttered using three configurations of orthodontic appliances.

A novel comparator featured with input data characteristic

NASA Astrophysics Data System (ADS)

Jiang, Xiaobo; Ye, Desheng; Xu, Xiangmin; Zheng, Shuai

2016-03-01

Two types of low-power asynchronous comparators featured with input data statistical characteristic are proposed in this article. The asynchronous ripple comparator stops comparing at the first unequal bit but delivers the result to the least significant bit. The pre-stop asynchronous comparator can completely stop comparing and obtain results immediately. The proposed and contrastive comparators were implemented in SMIC 0.18 μm process with different bit widths. Simulation shows that the proposed pre-stop asynchronous comparator features the lowest power consumption, shortest average propagation delay and highest area efficiency among the comparators. Data path of low-density parity check decoder using the proposed pre-stop asynchronous comparators are most power efficient compared with other data paths with synthesised, clock gating and bitwise competition logic comparators.

Hierarchical Interactions Model for Predicting Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD) Conversion

PubMed Central

Li, Han; Liu, Yashu; Gong, Pinghua; Zhang, Changshui; Ye, Jieping

2014-01-01

Identifying patients with Mild Cognitive Impairment (MCI) who are likely to convert to dementia has recently attracted increasing attention in Alzheimer's disease (AD) research. An accurate prediction of conversion from MCI to AD can aid clinicians to initiate treatments at early stage and monitor their effectiveness. However, existing prediction systems based on the original biosignatures are not satisfactory. In this paper, we propose to fit the prediction models using pairwise biosignature interactions, thus capturing higher-order relationship among biosignatures. Specifically, we employ hierarchical constraints and sparsity regularization to prune the high-dimensional input features. Based on the significant biosignatures and underlying interactions identified, we build classifiers to predict the conversion probability based on the selected features. We further analyze the underlying interaction effects of different biosignatures based on the so-called stable expectation scores. We have used 293 MCI subjects from Alzheimer's Disease Neuroimaging Initiative (ADNI) database that have MRI measurements at the baseline to evaluate the effectiveness of the proposed method. Our proposed method achieves better classification performance than state-of-the-art methods. Moreover, we discover several significant interactions predictive of MCI-to-AD conversion. These results shed light on improving the prediction performance using interaction features. PMID:24416143

An accelerated training method for back propagation networks

NASA Technical Reports Server (NTRS)

Shelton, Robert O. (Inventor)

1993-01-01

The principal objective is to provide a training procedure for a feed forward, back propagation neural network which greatly accelerates the training process. A set of orthogonal singular vectors are determined from the input matrix such that the standard deviations of the projections of the input vectors along these singular vectors, as a set, are substantially maximized, thus providing an optimal means of presenting the input data. Novelty exists in the method of extracting from the set of input data, a set of features which can serve to represent the input data in a simplified manner, thus greatly reducing the time/expense to training the system.

Activity Recognition in Egocentric video using SVM, kNN and Combined SVMkNN Classifiers

NASA Astrophysics Data System (ADS)

Sanal Kumar, K. P.; Bhavani, R., Dr.

2017-08-01

Egocentric vision is a unique perspective in computer vision which is human centric. The recognition of egocentric actions is a challenging task which helps in assisting elderly people, disabled patients and so on. In this work, life logging activity videos are taken as input. There are 2 categories, first one is the top level and second one is second level. Here, the recognition is done using the features like Histogram of Oriented Gradients (HOG), Motion Boundary Histogram (MBH) and Trajectory. The features are fused together and it acts as a single feature. The extracted features are reduced using Principal Component Analysis (PCA). The features that are reduced are provided as input to the classifiers like Support Vector Machine (SVM), k nearest neighbor (kNN) and combined Support Vector Machine (SVM) and k Nearest Neighbor (kNN) (combined SVMkNN). These classifiers are evaluated and the combined SVMkNN provided better results than other classifiers in the literature.

Delay selection by spike-timing-dependent plasticity in recurrent networks of spiking neurons receiving oscillatory inputs.

PubMed

Kerr, Robert R; Burkitt, Anthony N; Thomas, Doreen A; Gilson, Matthieu; Grayden, David B

2013-01-01

Learning rules, such as spike-timing-dependent plasticity (STDP), change the structure of networks of neurons based on the firing activity. A network level understanding of these mechanisms can help infer how the brain learns patterns and processes information. Previous studies have shown that STDP selectively potentiates feed-forward connections that have specific axonal delays, and that this underlies behavioral functions such as sound localization in the auditory brainstem of the barn owl. In this study, we investigate how STDP leads to the selective potentiation of recurrent connections with different axonal and dendritic delays during oscillatory activity. We develop analytical models of learning with additive STDP in recurrent networks driven by oscillatory inputs, and support the results using simulations with leaky integrate-and-fire neurons. Our results show selective potentiation of connections with specific axonal delays, which depended on the input frequency. In addition, we demonstrate how this can lead to a network becoming selective in the amplitude of its oscillatory response to this frequency. We extend this model of axonal delay selection within a single recurrent network in two ways. First, we show the selective potentiation of connections with a range of both axonal and dendritic delays. Second, we show axonal delay selection between multiple groups receiving out-of-phase, oscillatory inputs. We discuss the application of these models to the formation and activation of neuronal ensembles or cell assemblies in the cortex, and also to missing fundamental pitch perception in the auditory brainstem.

Delay Selection by Spike-Timing-Dependent Plasticity in Recurrent Networks of Spiking Neurons Receiving Oscillatory Inputs

PubMed Central

Kerr, Robert R.; Burkitt, Anthony N.; Thomas, Doreen A.; Gilson, Matthieu; Grayden, David B.

2013-01-01

Learning rules, such as spike-timing-dependent plasticity (STDP), change the structure of networks of neurons based on the firing activity. A network level understanding of these mechanisms can help infer how the brain learns patterns and processes information. Previous studies have shown that STDP selectively potentiates feed-forward connections that have specific axonal delays, and that this underlies behavioral functions such as sound localization in the auditory brainstem of the barn owl. In this study, we investigate how STDP leads to the selective potentiation of recurrent connections with different axonal and dendritic delays during oscillatory activity. We develop analytical models of learning with additive STDP in recurrent networks driven by oscillatory inputs, and support the results using simulations with leaky integrate-and-fire neurons. Our results show selective potentiation of connections with specific axonal delays, which depended on the input frequency. In addition, we demonstrate how this can lead to a network becoming selective in the amplitude of its oscillatory response to this frequency. We extend this model of axonal delay selection within a single recurrent network in two ways. First, we show the selective potentiation of connections with a range of both axonal and dendritic delays. Second, we show axonal delay selection between multiple groups receiving out-of-phase, oscillatory inputs. We discuss the application of these models to the formation and activation of neuronal ensembles or cell assemblies in the cortex, and also to missing fundamental pitch perception in the auditory brainstem. PMID:23408878

Analytical modeling of operating characteristics of premixing-prevaporizing fuel-air mixing passages. Volume 2: User's manual

NASA Technical Reports Server (NTRS)

Anderson, O. L.; Chiappetta, L. M.; Edwards, D. E.; Mcvey, J. B.

1982-01-01

A user's manual describing the operation of three computer codes (ADD code, PTRAK code, and VAPDIF code) is presented. The general features of the computer codes, the input/output formats, run streams, and sample input cases are described.

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

A Web Browsing System by Eye-gaze Input

NASA Astrophysics Data System (ADS)

Abe, Kiyohiko; Owada, Kosuke; Ohi, Shoichi; Ohyama, Minoru

We have developed an eye-gaze input system for people with severe physical disabilities, such as amyotrophic lateral sclerosis (ALS) patients. This system utilizes a personal computer and a home video camera to detect eye-gaze under natural light. The system detects both vertical and horizontal eye-gaze by simple image analysis, and does not require special image processing units or sensors. We also developed the platform for eye-gaze input based on our system. In this paper, we propose a new web browsing system for physically disabled computer users as an application of the platform for eye-gaze input. The proposed web browsing system uses a method of direct indicator selection. The method categorizes indicators by their function. These indicators are hierarchized relations; users can select the felicitous function by switching indicators group. This system also analyzes the location of selectable object on web page, such as hyperlink, radio button, edit box, etc. This system stores the locations of these objects, in other words, the mouse cursor skips to the object of candidate input. Therefore it enables web browsing at a faster pace.

Features Extraction of Flotation Froth Images and BP Neural Network Soft-Sensor Model of Concentrate Grade Optimized by Shuffled Cuckoo Searching Algorithm

PubMed Central

Wang, Jie-sheng; Han, Shuang; Shen, Na-na; Li, Shu-xia

2014-01-01

For meeting the forecasting target of key technology indicators in the flotation process, a BP neural network soft-sensor model based on features extraction of flotation froth images and optimized by shuffled cuckoo search algorithm is proposed. Based on the digital image processing technique, the color features in HSI color space, the visual features based on the gray level cooccurrence matrix, and the shape characteristics based on the geometric theory of flotation froth images are extracted, respectively, as the input variables of the proposed soft-sensor model. Then the isometric mapping method is used to reduce the input dimension, the network size, and learning time of BP neural network. Finally, a shuffled cuckoo search algorithm is adopted to optimize the BP neural network soft-sensor model. Simulation results show that the model has better generalization results and prediction accuracy. PMID:25133210

Hybrid feature selection algorithm using symmetrical uncertainty and a harmony search algorithm

NASA Astrophysics Data System (ADS)

Salameh Shreem, Salam; Abdullah, Salwani; Nazri, Mohd Zakree Ahmad

2016-04-01

Microarray technology can be used as an efficient diagnostic system to recognise diseases such as tumours or to discriminate between different types of cancers in normal tissues. This technology has received increasing attention from the bioinformatics community because of its potential in designing powerful decision-making tools for cancer diagnosis. However, the presence of thousands or tens of thousands of genes affects the predictive accuracy of this technology from the perspective of classification. Thus, a key issue in microarray data is identifying or selecting the smallest possible set of genes from the input data that can achieve good predictive accuracy for classification. In this work, we propose a two-stage selection algorithm for gene selection problems in microarray data-sets called the symmetrical uncertainty filter and harmony search algorithm wrapper (SU-HSA). Experimental results show that the SU-HSA is better than HSA in isolation for all data-sets in terms of the accuracy and achieves a lower number of genes on 6 out of 10 instances. Furthermore, the comparison with state-of-the-art methods shows that our proposed approach is able to obtain 5 (out of 10) new best results in terms of the number of selected genes and competitive results in terms of the classification accuracy.

Development of orientation tuning in simple cells of primary visual cortex

PubMed Central

Moore, Bartlett D.

2012-01-01

Orientation selectivity and its development are basic features of visual cortex. The original model of orientation selectivity proposes that elongated simple cell receptive fields are constructed from convergent input of an array of lateral geniculate nucleus neurons. However, orientation selectivity of simple cells in the visual cortex is generally greater than the linear contributions based on projections from spatial receptive field profiles. This implies that additional selectivity may arise from intracortical mechanisms. The hierarchical processing idea implies mainly linear connections, whereas cortical contributions are generally considered to be nonlinear. We have explored development of orientation selectivity in visual cortex with a focus on linear and nonlinear factors in a population of anesthetized 4-wk postnatal kittens and adult cats. Linear contributions are estimated from receptive field maps by which orientation tuning curves are generated and bandwidth is quantified. Nonlinear components are estimated as the magnitude of the power function relationship between responses measured from drifting sinusoidal gratings and those predicted from the spatial receptive field. Measured bandwidths for kittens are slightly larger than those in adults, whereas predicted bandwidths are substantially broader. These results suggest that relatively strong nonlinearities in early postnatal stages are substantially involved in the development of orientation tuning in visual cortex. PMID:22323631

Development and Characterization of a Rate-Dependent Three-Dimensional Macroscopic Plasticity Model Suitable for Use in Composite Impact Problems

NASA Technical Reports Server (NTRS)

Goldberg, Robert K.; Carney, Kelly S.; DuBois, Paul; Hoffarth, Canio; Rajan, Subramaniam; Blankenhorn, Gunther

2015-01-01

Several key capabilities have been identified by the aerospace community as lacking in the material/models for composite materials currently available within commercial transient dynamic finite element codes such as LS-DYNA. Some of the specific desired features that have been identified include the incorporation of both plasticity and damage within the material model, the capability of using the material model to analyze the response of both three-dimensional solid elements and two dimensional shell elements, and the ability to simulate the response of composites composed with a variety of composite architectures, including laminates, weaves and braids. In addition, a need has been expressed to have a material model that utilizes tabulated experimentally based input to define the evolution of plasticity and damage as opposed to utilizing discrete input parameters (such as modulus and strength) and analytical functions based on curve fitting. To begin to address these needs, an orthotropic macroscopic plasticity based model suitable for implementation within LS-DYNA has been developed. Specifically, the Tsai-Wu composite failure model has been generalized and extended to a strain-hardening based orthotropic plasticity model with a non-associative flow rule. The coefficients in the yield function are determined based on tabulated stress-strain curves in the various normal and shear directions, along with selected off-axis curves. Incorporating rate dependence into the yield function is achieved by using a series of tabluated input curves, each at a different constant strain rate. The non-associative flow-rule is used to compute the evolution of the effective plastic strain. Systematic procedures have been developed to determine the values of the various coefficients in the yield function and the flow rule based on the tabulated input data. An algorithm based on the radial return method has been developed to facilitate the numerical implementation of the material model. The presented paper will present in detail the development of the orthotropic plasticity model and the procedures used to obtain the required material parameters. Methods in which a combination of actual testing and selective numerical testing can be combined to yield the appropriate input data for the model will be described. A specific laminated polymer matrix composite will be examined to demonstrate the application of the model.

Feature extraction from high resolution satellite imagery as an input to the development and rapid update of a METRANS geographic information system (GIS).

DOT National Transportation Integrated Search

2011-06-01

This report describes an accuracy assessment of extracted features derived from three : subsets of Quickbird pan-sharpened high resolution satellite image for the area of the : Port of Los Angeles, CA. Visual Learning Systems Feature Analyst and D...

Rotation invariant features for wear particle classification

NASA Astrophysics Data System (ADS)

Arof, Hamzah; Deravi, Farzin

1997-09-01

This paper investigates the ability of a set of rotation invariant features to classify images of wear particles found in used lubricating oil of machinery. The rotation invariant attribute of the features is derived from the property of the magnitudes of Fourier transform coefficients that do not change with spatial shift of the input elements. By analyzing individual circular neighborhoods centered at every pixel in an image, local and global texture characteristics of an image can be described. A number of input sequences are formed by the intensities of pixels on concentric rings of various radii measured from the center of each neighborhood. Fourier transforming the sequences would generate coefficients whose magnitudes are invariant to rotation. Rotation invariant features extracted from these coefficients were utilized to classify wear particle images that were obtained from a number of different particles captured at different orientations. In an experiment involving images of 6 classes, the circular neighborhood features obtained a 91% recognition rate which compares favorably to a 76% rate achieved by features of a 6 by 6 co-occurrence matrix.

Alternative Computer Access for Young Handicapped Children: A Systematic Selection Procedure.

ERIC Educational Resources Information Center

Morris, Karen J.

The paper describes the type of computer access products appropriate for use by handicapped children and presents a systematic procedure for selection of such input and output devices. Modification of computer input is accomplished by three strategies: modifying the keyboard, adding alternative keyboards, and attaching switches to the keyboard.…

Where do we store the memory representations that guide attention?

PubMed Central

Woodman, Geoffrey F.; Carlisle, Nancy B.; Reinhart, Robert M. G.

2013-01-01

During the last decade one of the most contentious and heavily studied topics in the attention literature has been the role that working memory representations play in controlling perceptual selection. The hypothesis has been advanced that to have attention select a certain perceptual input from the environment, we only need to represent that item in working memory. Here we summarize the work indicating that the relationship between what representations are maintained in working memory and what perceptual inputs are selected is not so simple. First, it appears that attentional selection is also determined by high-level task goals that mediate the relationship between working memory storage and attentional selection. Second, much of the recent work from our laboratory has focused on the role of long-term memory in controlling attentional selection. We review recent evidence supporting the proposal that working memory representations are critical during the initial configuration of attentional control settings, but that after those settings are established long-term memory representations play an important role in controlling which perceptual inputs are selected by mechanisms of attention. PMID:23444390

The Comparison of Visual Working Memory Representations with Perceptual Inputs

PubMed Central

Hyun, Joo-seok; Woodman, Geoffrey F.; Vogel, Edward K.; Hollingworth, Andrew

2008-01-01

The human visual system can notice differences between memories of previous visual inputs and perceptions of new visual inputs, but the comparison process that detects these differences has not been well characterized. This study tests the hypothesis that differences between the memory of a stimulus array and the perception of a new array are detected in a manner that is analogous to the detection of simple features in visual search tasks. That is, just as the presence of a task-relevant feature in visual search can be detected in parallel, triggering a rapid shift of attention to the object containing the feature, the presence of a memory-percept difference along a task-relevant dimension can be detected in parallel, triggering a rapid shift of attention to the changed object. Supporting evidence was obtained in a series of experiments that examined manual reaction times, saccadic reaction times, and event-related potential latencies. However, these experiments also demonstrated that a slow, limited-capacity process must occur before the observer can make a manual change-detection response. PMID:19653755

Contribution of sublinear and supralinear dendritic integration to neuronal computations

PubMed Central

Tran-Van-Minh, Alexandra; Cazé, Romain D.; Abrahamsson, Therése; Cathala, Laurence; Gutkin, Boris S.; DiGregorio, David A.

2015-01-01

Nonlinear dendritic integration is thought to increase the computational ability of neurons. Most studies focus on how supralinear summation of excitatory synaptic responses arising from clustered inputs within single dendrites result in the enhancement of neuronal firing, enabling simple computations such as feature detection. Recent reports have shown that sublinear summation is also a prominent dendritic operation, extending the range of subthreshold input-output (sI/O) transformations conferred by dendrites. Like supralinear operations, sublinear dendritic operations also increase the repertoire of neuronal computations, but feature extraction requires different synaptic connectivity strategies for each of these operations. In this article we will review the experimental and theoretical findings describing the biophysical determinants of the three primary classes of dendritic operations: linear, sublinear, and supralinear. We then review a Boolean algebra-based analysis of simplified neuron models, which provides insight into how dendritic operations influence neuronal computations. We highlight how neuronal computations are critically dependent on the interplay of dendritic properties (morphology and voltage-gated channel expression), spiking threshold and distribution of synaptic inputs carrying particular sensory features. Finally, we describe how global (scattered) and local (clustered) integration strategies permit the implementation of similar classes of computations, one example being the object feature binding problem. PMID:25852470

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.

A mixture of sparse coding models explaining properties of face neurons related to holistic and parts-based processing

PubMed Central

2017-01-01

Experimental studies have revealed evidence of both parts-based and holistic representations of objects and faces in the primate visual system. However, it is still a mystery how such seemingly contradictory types of processing can coexist within a single system. Here, we propose a novel theory called mixture of sparse coding models, inspired by the formation of category-specific subregions in the inferotemporal (IT) cortex. We developed a hierarchical network that constructed a mixture of two sparse coding submodels on top of a simple Gabor analysis. The submodels were each trained with face or non-face object images, which resulted in separate representations of facial parts and object parts. Importantly, evoked neural activities were modeled by Bayesian inference, which had a top-down explaining-away effect that enabled recognition of an individual part to depend strongly on the category of the whole input. We show that this explaining-away effect was indeed crucial for the units in the face submodel to exhibit significant selectivity to face images over object images in a similar way to actual face-selective neurons in the macaque IT cortex. Furthermore, the model explained, qualitatively and quantitatively, several tuning properties to facial features found in the middle patch of face processing in IT as documented by Freiwald, Tsao, and Livingstone (2009). These included, in particular, tuning to only a small number of facial features that were often related to geometrically large parts like face outline and hair, preference and anti-preference of extreme facial features (e.g., very large/small inter-eye distance), and reduction of the gain of feature tuning for partial face stimuli compared to whole face stimuli. Thus, we hypothesize that the coding principle of facial features in the middle patch of face processing in the macaque IT cortex may be closely related to mixture of sparse coding models. PMID:28742816

A mixture of sparse coding models explaining properties of face neurons related to holistic and parts-based processing.

PubMed

Hosoya, Haruo; Hyvärinen, Aapo

2017-07-01

Experimental studies have revealed evidence of both parts-based and holistic representations of objects and faces in the primate visual system. However, it is still a mystery how such seemingly contradictory types of processing can coexist within a single system. Here, we propose a novel theory called mixture of sparse coding models, inspired by the formation of category-specific subregions in the inferotemporal (IT) cortex. We developed a hierarchical network that constructed a mixture of two sparse coding submodels on top of a simple Gabor analysis. The submodels were each trained with face or non-face object images, which resulted in separate representations of facial parts and object parts. Importantly, evoked neural activities were modeled by Bayesian inference, which had a top-down explaining-away effect that enabled recognition of an individual part to depend strongly on the category of the whole input. We show that this explaining-away effect was indeed crucial for the units in the face submodel to exhibit significant selectivity to face images over object images in a similar way to actual face-selective neurons in the macaque IT cortex. Furthermore, the model explained, qualitatively and quantitatively, several tuning properties to facial features found in the middle patch of face processing in IT as documented by Freiwald, Tsao, and Livingstone (2009). These included, in particular, tuning to only a small number of facial features that were often related to geometrically large parts like face outline and hair, preference and anti-preference of extreme facial features (e.g., very large/small inter-eye distance), and reduction of the gain of feature tuning for partial face stimuli compared to whole face stimuli. Thus, we hypothesize that the coding principle of facial features in the middle patch of face processing in the macaque IT cortex may be closely related to mixture of sparse coding models.

Event-related potentials reveal the relations between feature representations at different levels of abstraction.

PubMed

Hannah, Samuel D; Shedden, Judith M; Brooks, Lee R; Grundy, John G

2016-11-01

In this paper, we use behavioural methods and event-related potentials (ERPs) to explore the relations between informational and instantiated features, as well as the relation between feature abstraction and rule type. Participants are trained to categorize two species of fictitious animals and then identify perceptually novel exemplars. Critically, two groups are given a perfectly predictive counting rule that, according to Hannah and Brooks (2009. Featuring familiarity: How a familiar feature instantiation influences categorization. Canadian Journal of Experimental Psychology/Revue Canadienne de Psychologie Expérimentale, 63, 263-275. Retrieved from http://doi.org/10.1037/a0017919), should orient them to using abstract informational features when categorizing the novel transfer items. A third group is taught a feature list rule, which should orient them to using detailed instantiated features. One counting-rule group were taught their rule before any exposure to the actual stimuli, and the other immediately after training, having learned the instantiations first. The feature-list group were also taught their rule after training. The ERP results suggest that at test, the two counting-rule groups processed items differently, despite their identical rule. This not only supports the distinction that informational and instantiated features are qualitatively different feature representations, but also implies that rules can readily operate over concrete inputs, in contradiction to traditional approaches that assume that rules necessarily act on abstract inputs.

A general prediction model for the detection of ADHD and Autism using structural and functional MRI.

PubMed

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

2018-01-01

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

Online feature selection with streaming features.

PubMed

Wu, Xindong; Yu, Kui; Ding, Wei; Wang, Hao; Zhu, Xingquan

2013-05-01

We propose a new online feature selection framework for applications with streaming features where the knowledge of the full feature space is unknown in advance. We define streaming features as features that flow in one by one over time whereas the number of training examples remains fixed. This is in contrast with traditional online learning methods that only deal with sequentially added observations, with little attention being paid to streaming features. The critical challenges for Online Streaming Feature Selection (OSFS) include 1) the continuous growth of feature volumes over time, 2) a large feature space, possibly of unknown or infinite size, and 3) the unavailability of the entire feature set before learning starts. In the paper, we present a novel Online Streaming Feature Selection method to select strongly relevant and nonredundant features on the fly. An efficient Fast-OSFS algorithm is proposed to improve feature selection performance. The proposed algorithms are evaluated extensively on high-dimensional datasets and also with a real-world case study on impact crater detection. Experimental results demonstrate that the algorithms achieve better compactness and higher prediction accuracy than existing streaming feature selection algorithms.

Harmonic wavelet packet transform for on-line system health diagnosis

NASA Astrophysics Data System (ADS)

Yan, Ruqiang; Gao, Robert X.

2004-07-01

This paper presents a new approach to on-line health diagnosis of mechanical systems, based on the wavelet packet transform. Specifically, signals acquired from vibration sensors are decomposed into sub-bands by means of the discrete harmonic wavelet packet transform (DHWPT). Based on the Fisher linear discriminant criterion, features in the selected sub-bands are then used as inputs to three classifiers (Nearest Neighbor rule-based and two Neural Network-based), for system health condition assessment. Experimental results have confirmed that, comparing to the conventional approach where statistical parameters from raw signals are used, the presented approach enabled higher signal-to-noise ratio for more effective and intelligent use of the sensory information, thus leading to more accurate system health diagnosis.

Multi-degree of freedom joystick for virtual reality simulation.

PubMed

Head, M J; Nelson, C A; Siu, K C

2013-11-01

A modular control interface and simulated virtual reality environment were designed and created in order to determine how the kinematic architecture of a control interface affects minimally invasive surgery training. A user is able to selectively determine the kinematic configuration of an input device (number, type and location of degrees of freedom) for a specific surgical simulation through the use of modular joints and constraint components. Furthermore, passive locking was designed and implemented through the use of inflated latex tubing around rotational joints in order to allow a user to step away from a simulation without unwanted tool motion. It is believed that these features will facilitate improved simulation of a variety of surgical procedures and, thus, improve surgical skills training.

An EEG-based machine learning method to screen alcohol use disorder.

PubMed

Mumtaz, Wajid; Vuong, Pham Lam; Xia, Likun; Malik, Aamir Saeed; Rashid, Rusdi Bin Abd

2017-04-01

Screening alcohol use disorder (AUD) patients has been challenging due to the subjectivity involved in the process. Hence, robust and objective methods are needed to automate the screening of AUD patients. In this paper, a machine learning method is proposed that utilized resting-state electroencephalography (EEG)-derived features as input data to classify the AUD patients and healthy controls and to perform automatic screening of AUD patients. In this context, the EEG data were recorded during 5 min of eyes closed and 5 min of eyes open conditions. For this purpose, 30 AUD patients and 15 aged-matched healthy controls were recruited. After preprocessing the EEG data, EEG features such as inter-hemispheric coherences and spectral power for EEG delta, theta, alpha, beta and gamma bands were computed involving 19 scalp locations. The selection of most discriminant features was performed with a rank-based feature selection method assigning a weight value to each feature according to a criterion, i.e., receiver operating characteristics curve. For example, a feature with large weight was considered more relevant to the target labels than a feature with less weight. Therefore, a reduced set of most discriminant features was identified and further be utilized during classification of AUD patients and healthy controls. As results, the inter-hemispheric coherences between the brain regions were found significantly different between the study groups and provided high classification efficiency ( Accuracy  = 80.8, sensitivity  = 82.5, and specificity  = 80, F - Measure  = 0.78). In addition, the power computed in different EEG bands were found significant and provided an overall classification efficiency as ( Accuracy  = 86.6, sensitivity  = 95, specificity  = 82.5, and F - Measure  = 0.88). Further, the integration of these EEG feature resulted into even higher results ( Accuracy  = 89.3 %, sensitivity  = 88.5 %, specificity  = 91 %, and F - Measure  = 0.90). Based on the results, it is concluded that the EEG data (integration of the theta, beta, and gamma power and inter-hemispheric coherence) could be utilized as objective markers to screen the AUD patients and healthy controls.

Enhancing the Discrimination Ability of a Gas Sensor Array Based on a Novel Feature Selection and Fusion Framework.

PubMed

Deng, Changjian; Lv, Kun; Shi, Debo; Yang, Bo; Yu, Song; He, Zhiyi; Yan, Jia

2018-06-12

In this paper, a novel feature selection and fusion framework is proposed to enhance the discrimination ability of gas sensor arrays for odor identification. Firstly, we put forward an efficient feature selection method based on the separability and the dissimilarity to determine the feature selection order for each type of feature when increasing the dimension of selected feature subsets. Secondly, the K-nearest neighbor (KNN) classifier is applied to determine the dimensions of the optimal feature subsets for different types of features. Finally, in the process of establishing features fusion, we come up with a classification dominance feature fusion strategy which conducts an effective basic feature. Experimental results on two datasets show that the recognition rates of Database I and Database II achieve 97.5% and 80.11%, respectively, when k = 1 for KNN classifier and the distance metric is correlation distance (COR), which demonstrates the superiority of the proposed feature selection and fusion framework in representing signal features. The novel feature selection method proposed in this paper can effectively select feature subsets that are conducive to the classification, while the feature fusion framework can fuse various features which describe the different characteristics of sensor signals, for enhancing the discrimination ability of gas sensors and, to a certain extent, suppressing drift effect.

Structures of the Recurrence Plot of Heart Rate Variability Signal as a Tool for Predicting the Onset of Paroxysmal Atrial Fibrillation

PubMed Central

Mohebbi, Maryam; Ghassemian, Hassan; Asl, Babak Mohammadzadeh

2011-01-01

This paper aims to propose an effective paroxysmal atrial fibrillation (PAF) predictor which is based on the analysis of the heart rate variability (HRV) signal. Predicting the onset of PAF, based on non-invasive techniques, is clinically important and can be invaluable in order to avoid useless therapeutic interventions and to minimize the risks for the patients. This method consists of four steps: Preprocessing, feature extraction, feature reduction, and classification. In the first step, the QRS complexes are detected from the electrocardiogram (ECG) signal and then the HRV signal is extracted. In the next step, the recurrence plot (RP) of HRV signal is obtained and six features are extracted to characterize the basic patterns of the RP. These features consist of length of longest diagonal segments, average length of the diagonal lines, entropy, trapping time, length of longest vertical line, and recurrence trend. In the third step, these features are reduced to three features by the linear discriminant analysis (LDA) technique. Using LDA not only reduces the number of the input features, but also increases the classification accuracy by selecting the most discriminating features. Finally, a support vector machine-based classifier is used to classify the HRV signals. The performance of the proposed method in prediction of PAF episodes was evaluated using the Atrial Fibrillation Prediction Database which consists of both 30-minutes ECG recordings end just prior to the onset of PAF and segments at least 45 min distant from any PAF events. The obtained sensitivity, specificity, and positive predictivity were 96.55%, 100%, and 100%, respectively. PMID:22606666

Portable data collection device

DOEpatents

French, P.D.

1996-06-11

The present invention provides a portable data collection device that has a variety of sensors that are interchangeable with a variety of input ports in the device. The various sensors include a data identification feature that provides information to the device regarding the type of physical data produced by each sensor and therefore the type of sensor itself. The data identification feature enables the device to locate the input port where the sensor is connected and self adjust when a sensor is removed or replaced. The device is able to collect physical data, whether or not a function of a time. 7 figs.

Portable data collection device

DOEpatents

French, Patrick D.

1996-01-01

The present invention provides a portable data collection device that has a variety of sensors that are interchangeable with a variety of input ports in the device. The various sensors include a data identification feature that provides information to the device regarding the type of physical data produced by each sensor and therefore the type of sensor itself. The data identification feature enables the device to locate the input port where the sensor is connected and self adjust when a sensor is removed or replaced. The device is able to collect physical data, whether or not a function of a time.

Pedestrian Detection Based on Adaptive Selection of Visible Light or Far-Infrared Light Camera Image by Fuzzy Inference System and Convolutional Neural Network-Based Verification.

PubMed

Kang, Jin Kyu; Hong, Hyung Gil; Park, Kang Ryoung

2017-07-08

A number of studies have been conducted to enhance the pedestrian detection accuracy of intelligent surveillance systems. However, detecting pedestrians under outdoor conditions is a challenging problem due to the varying lighting, shadows, and occlusions. In recent times, a growing number of studies have been performed on visible light camera-based pedestrian detection systems using a convolutional neural network (CNN) in order to make the pedestrian detection process more resilient to such conditions. However, visible light cameras still cannot detect pedestrians during nighttime, and are easily affected by shadows and lighting. There are many studies on CNN-based pedestrian detection through the use of far-infrared (FIR) light cameras (i.e., thermal cameras) to address such difficulties. However, when the solar radiation increases and the background temperature reaches the same level as the body temperature, it remains difficult for the FIR light camera to detect pedestrians due to the insignificant difference between the pedestrian and non-pedestrian features within the images. Researchers have been trying to solve this issue by inputting both the visible light and the FIR camera images into the CNN as the input. This, however, takes a longer time to process, and makes the system structure more complex as the CNN needs to process both camera images. This research adaptively selects a more appropriate candidate between two pedestrian images from visible light and FIR cameras based on a fuzzy inference system (FIS), and the selected candidate is verified with a CNN. Three types of databases were tested, taking into account various environmental factors using visible light and FIR cameras. The results showed that the proposed method performs better than the previously reported methods.

Enhancing Critical Infrastructure and Key Resources (CIKR) Level-0 Physical Process Security Using Field Device Distinct Native Attribute Features

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

Lopez, Juan; Liefer, Nathan C.; Busho, Colin R.

Here, the need for improved Critical Infrastructure and Key Resource (CIKR) security is unquestioned and there has been minimal emphasis on Level-0 (PHY Process) improvements. Wired Signal Distinct Native Attribute (WS-DNA) Fingerprinting is investigated here as a non-intrusive PHY-based security augmentation to support an envisioned layered security strategy. Results are based on experimental response collections from Highway Addressable Remote Transducer (HART) Differential Pressure Transmitter (DPT) devices from three manufacturers (Yokogawa, Honeywell, Endress+Hauer) installed in an automated process control system. Device discrimination is assessed using Time Domain (TD) and Slope-Based FSK (SB-FSK) fingerprints input to Multiple Discriminant Analysis, Maximum Likelihood (MDA/ML)more » and Random Forest (RndF) classifiers. For 12 different classes (two devices per manufacturer at two distinct set points), both classifiers performed reliably and achieved an arbitrary performance benchmark of average cross-class percent correct of %C > 90%. The least challenging cross-manufacturer results included near-perfect %C ≈ 100%, while the more challenging like-model (serial number) discrimination results included 90%< %C < 100%, with TD Fingerprinting marginally outperforming SB-FSK Fingerprinting; SB-FSK benefits from having less stringent response alignment and registration requirements. The RndF classifier was most beneficial and enabled reliable selection of dimensionally reduced fingerprint subsets that minimize data storage and computational requirements. The RndF selected feature sets contained 15% of the full-dimensional feature sets and only suffered a worst case %CΔ = 3% to 4% performance degradation.« less

Selective Audiovisual Semantic Integration Enabled by Feature-Selective Attention.

PubMed

Li, Yuanqing; Long, Jinyi; Huang, Biao; Yu, Tianyou; Wu, Wei; Li, Peijun; Fang, Fang; Sun, Pei

2016-01-13

An audiovisual object may contain multiple semantic features, such as the gender and emotional features of the speaker. Feature-selective attention and audiovisual semantic integration are two brain functions involved in the recognition of audiovisual objects. Humans often selectively attend to one or several features while ignoring the other features of an audiovisual object. Meanwhile, the human brain integrates semantic information from the visual and auditory modalities. However, how these two brain functions correlate with each other remains to be elucidated. In this functional magnetic resonance imaging (fMRI) study, we explored the neural mechanism by which feature-selective attention modulates audiovisual semantic integration. During the fMRI experiment, the subjects were presented with visual-only, auditory-only, or audiovisual dynamical facial stimuli and performed several feature-selective attention tasks. Our results revealed that a distribution of areas, including heteromodal areas and brain areas encoding attended features, may be involved in audiovisual semantic integration. Through feature-selective attention, the human brain may selectively integrate audiovisual semantic information from attended features by enhancing functional connectivity and thus regulating information flows from heteromodal areas to brain areas encoding the attended features.

Is the place cell a "supple" engram?

PubMed

Routtenberg, Aryeh

2015-06-01

This short note, which honors Nobelists O'Keefe and the Mosers, asks how the patterning of inputs to a single place cell regulates its firing. Because the combination of inputs to a single CA1 place cell is very large, the generally accepted view is rejected that inputs to a place cell are relatively restricted, near identical repetition upon re-presentation of the environment. The alternative proposed here is that when any 100 excitatory inputs are fired activating a subset combination, which is a large number, selected from the 30,000 synapses, this leads to CA1 cell firing. The selection of the combination of inputs is a very large number it nonetheless leads to the conclusion that even though the same cell dutifully fires when the animal is in an identical location, the inputs that fire the place cell are nonetheless obligatorily non-identical. This CA1 input combinatorial proposal may help us understand the physiological underpinnings of the memory mechanism arising from supple synapses (Routtenberg (2013), Hippocampus 23:202-206). © 2015 Wiley Periodicals, Inc.

Robust Indoor Human Activity Recognition Using Wireless Signals.

PubMed

Wang, Yi; Jiang, Xinli; Cao, Rongyu; Wang, Xiyang

2015-07-15

Wireless signals-based activity detection and recognition technology may be complementary to the existing vision-based methods, especially under the circumstance of occlusions, viewpoint change, complex background, lighting condition change, and so on. This paper explores the properties of the channel state information (CSI) of Wi-Fi signals, and presents a robust indoor daily human activity recognition framework with only one pair of transmission points (TP) and access points (AP). First of all, some indoor human actions are selected as primitive actions forming a training set. Then, an online filtering method is designed to make actions' CSI curves smooth and allow them to contain enough pattern information. Each primitive action pattern can be segmented from the outliers of its multi-input multi-output (MIMO) signals by a proposed segmentation method. Lastly, in online activities recognition, by selecting proper features and Support Vector Machine (SVM) based multi-classification, activities constituted by primitive actions can be recognized insensitive to the locations, orientations, and speeds.

Speaker-independent phoneme recognition with a binaural auditory image model

NASA Astrophysics Data System (ADS)

Francis, Keith Ivan

1997-09-01

This dissertation presents phoneme recognition techniques based on a binaural fusion of outputs of the auditory image model and subsequent azimuth-selective phoneme recognition in a noisy environment. Background information concerning speech variations, phoneme recognition, current binaural fusion techniques and auditory modeling issues is explained. The research is constrained to sources in the frontal azimuthal plane of a simulated listener. A new method based on coincidence detection of neural activity patterns from the auditory image model of Patterson is used for azimuth-selective phoneme recognition. The method is tested in various levels of noise and the results are reported in contrast to binaural fusion methods based on various forms of correlation to demonstrate the potential of coincidence- based binaural phoneme recognition. This method overcomes smearing of fine speech detail typical of correlation based methods. Nevertheless, coincidence is able to measure similarity of left and right inputs and fuse them into useful feature vectors for phoneme recognition in noise.

UV-B measurements in India

NASA Astrophysics Data System (ADS)

Prasad, B. S. N.; Gayathri, H. B.; Muralikrishnan, N.

1992-01-01

Global UV-B flux (sum of direct and diffuse radiations) data at four wavelengths 280, 290, 300 and 310 nm are recorded at several locations in India as part of Indian Middle Atmosphere Programme (IMAP). The stations have been selected considering distinct geographic features and possible influence of atmospheric aerosols and particulates on the ground reaching UV-B flux. Mysore (12.6°N, 76.6°E) has been selected as a continental station largely free from any industrial pollution and large scale bio-mass burning. An examination of the ground reaching UV-B flux at Mysore shows a marked dirunal and seasonal asymmetry. This can be attributed to the seasonally varying atmospheric aerosols and particulates which influence the scattering of UV-B radiation. The available parameterization models are used to reproduce the experimental UV-B irradiance by varying the input parameters to the model. These results on the dirunal and seasonal variation of global UV-B flux from experiment and models are discussed in this paper.

Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks

PubMed Central

Miconi, Thomas

2017-01-01

Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Chaotic recurrent networks, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing methods for training these networks are either biologically implausible, and/or require a continuous, real-time error signal to guide learning. Here we show that a biologically plausible learning rule can train such recurrent networks, guided solely by delayed, phasic rewards at the end of each trial. Networks endowed with this learning rule can successfully learn nontrivial tasks requiring flexible (context-dependent) associations, memory maintenance, nonlinear mixed selectivities, and coordination among multiple outputs. The resulting networks replicate complex dynamics previously observed in animal cortex, such as dynamic encoding of task features and selective integration of sensory inputs. We conclude that recurrent neural networks offer a plausible model of cortical dynamics during both learning and performance of flexible behavior. DOI: http://dx.doi.org/10.7554/eLife.20899.001 PMID:28230528

Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks.

PubMed

Miconi, Thomas

2017-02-23

Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Chaotic recurrent networks, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing methods for training these networks are either biologically implausible, and/or require a continuous, real-time error signal to guide learning. Here we show that a biologically plausible learning rule can train such recurrent networks, guided solely by delayed, phasic rewards at the end of each trial. Networks endowed with this learning rule can successfully learn nontrivial tasks requiring flexible (context-dependent) associations, memory maintenance, nonlinear mixed selectivities, and coordination among multiple outputs. The resulting networks replicate complex dynamics previously observed in animal cortex, such as dynamic encoding of task features and selective integration of sensory inputs. We conclude that recurrent neural networks offer a plausible model of cortical dynamics during both learning and performance of flexible behavior.