Neural Mechanisms and Information Processing in Recognition Systems

Directory of Open Access Journals (Sweden)

Mamiko Ozaki

2014-10-01

Full Text Available Nestmate recognition is a hallmark of social insects. It is based on the match/mismatch of an identity signal carried by members of the society with that of the perceiving individual. While the behavioral response, amicable or aggressive, is very clear, the neural systems underlying recognition are not fully understood. Here we contrast two alternative hypotheses for the neural mechanisms that are responsible for the perception and information processing in recognition. We focus on recognition via chemical signals, as the common modality in social insects. The first, classical, hypothesis states that upon perception of recognition cues by the sensory system the information is passed as is to the antennal lobes and to higher brain centers where the information is deciphered and compared to a neural template. Match or mismatch information is then transferred to some behavior-generating centers where the appropriate response is elicited. An alternative hypothesis, that of “pre-filter mechanism”, posits that the decision as to whether to pass on the information to the central nervous system takes place in the peripheral sensory system. We suggest that, through sensory adaptation, only alien signals are passed on to the brain, specifically to an “aggressive-behavior-switching center”, where the response is generated if the signal is above a certain threshold.

Automatic Speech Recognition from Neural Signals: A Focused Review

Directory of Open Access Journals (Sweden)

Christian Herff

2016-09-01

Full Text Available Speech interfaces have become widely accepted and are nowadays integrated in various real-life applications and devices. They have become a part of our daily life. However, speech interfaces presume the ability to produce intelligible speech, which might be impossible due to either loud environments, bothering bystanders or incapabilities to produce speech (i.e.~patients suffering from locked-in syndrome. For these reasons it would be highly desirable to not speak but to simply envision oneself to say words or sentences. Interfaces based on imagined speech would enable fast and natural communication without the need for audible speech and would give a voice to otherwise mute people.This focused review analyzes the potential of different brain imaging techniques to recognize speech from neural signals by applying Automatic Speech Recognition technology. We argue that modalities based on metabolic processes, such as functional Near Infrared Spectroscopy and functional Magnetic Resonance Imaging, are less suited for Automatic Speech Recognition from neural signals due to low temporal resolution but are very useful for the investigation of the underlying neural mechanisms involved in speech processes. In contrast, electrophysiologic activity is fast enough to capture speech processes and is therefor better suited for ASR. Our experimental results indicate the potential of these signals for speech recognition from neural data with a focus on invasively measured brain activity (electrocorticography. As a first example of Automatic Speech Recognition techniques used from neural signals, we discuss the emph{Brain-to-text} system.

Recognition of sign language gestures using neural networks

OpenAIRE

Simon Vamplew

2007-01-01

This paper describes the structure and performance of the SLARTI sign language recognition system developed at the University of Tasmania. SLARTI uses a modular architecture consisting of multiple feature-recognition neural networks and a nearest-neighbour classifier to recognise Australian sign language (Auslan) hand gestures.

Higher-order neural network software for distortion invariant object recognition

Science.gov (United States)

Reid, Max B.; Spirkovska, Lilly

1991-01-01

The state-of-the-art in pattern recognition for such applications as automatic target recognition and industrial robotic vision relies on digital image processing. We present a higher-order neural network model and software which performs the complete feature extraction-pattern classification paradigm required for automatic pattern recognition. Using a third-order neural network, we demonstrate complete, 100 percent accurate invariance to distortions of scale, position, and in-plate rotation. In a higher-order neural network, feature extraction is built into the network, and does not have to be learned. Only the relatively simple classification step must be learned. This is key to achieving very rapid training. The training set is much smaller than with standard neural network software because the higher-order network only has to be shown one view of each object to be learned, not every possible view. The software and graphical user interface run on any Sun workstation. Results of the use of the neural software in autonomous robotic vision systems are presented. Such a system could have extensive application in robotic manufacturing.

Goal-seeking neural net for recall and recognition

Science.gov (United States)

Omidvar, Omid M.

1990-07-01

Neural networks have been used to mimic cognitive processes which take place in animal brains. The learning capability inherent in neural networks makes them suitable candidates for adaptive tasks such as recall and recognition. The synaptic reinforcements create a proper condition for adaptation, which results in memorization, formation of perception, and higher order information processing activities. In this research a model of a goal seeking neural network is studied and the operation of the network with regard to recall and recognition is analyzed. In these analyses recall is defined as retrieval of stored information where little or no matching is involved. On the other hand recognition is recall with matching; therefore it involves memorizing a piece of information with complete presentation. This research takes the generalized view of reinforcement in which all the signals are potential reinforcers. The neuronal response is considered to be the source of the reinforcement. This local approach to adaptation leads to the goal seeking nature of the neurons as network components. In the proposed model all the synaptic strengths are reinforced in parallel while the reinforcement among the layers is done in a distributed fashion and pipeline mode from the last layer inward. A model of complex neuron with varying threshold is developed to account for inhibitory and excitatory behavior of real neuron. A goal seeking model of a neural network is presented. This network is utilized to perform recall and recognition tasks. The performance of the model with regard to the assigned tasks is presented.

Convolutional Neural Network for Image Recognition

CERN Document Server

Seifnashri, Sahand

2015-01-01

The aim of this project is to use machine learning techniques especially Convolutional Neural Networks for image processing. These techniques can be used for Quark-Gluon discrimination using calorimeters data, but unfortunately I didn’t manage to get the calorimeters data and I just used the Jet data fromminiaodsim(ak4 chs). The Jet data was not good enough for Convolutional Neural Network which is designed for ’image’ recognition. This report is made of twomain part, part one is mainly about implementing Convolutional Neural Network on unphysical data such as MNIST digits and CIFAR-10 dataset and part 2 is about the Jet data.

Character recognition from trajectory by recurrent spiking neural networks.

Science.gov (United States)

Jiangrong Shen; Kang Lin; Yueming Wang; Gang Pan

2017-07-01

Spiking neural networks are biologically plausible and power-efficient on neuromorphic hardware, while recurrent neural networks have been proven to be efficient on time series data. However, how to use the recurrent property to improve the performance of spiking neural networks is still a problem. This paper proposes a recurrent spiking neural network for character recognition using trajectories. In the network, a new encoding method is designed, in which varying time ranges of input streams are used in different recurrent layers. This is able to improve the generalization ability of our model compared with general encoding methods. The experiments are conducted on four groups of the character data set from University of Edinburgh. The results show that our method can achieve a higher average recognition accuracy than existing methods.

Down image recognition based on deep convolutional neural network

Directory of Open Access Journals (Sweden)

Wenzhu Yang

2018-06-01

Full Text Available Since of the scale and the various shapes of down in the image, it is difficult for traditional image recognition method to correctly recognize the type of down image and get the required recognition accuracy, even for the Traditional Convolutional Neural Network (TCNN. To deal with the above problems, a Deep Convolutional Neural Network (DCNN for down image classification is constructed, and a new weight initialization method is proposed. Firstly, the salient regions of a down image were cut from the image using the visual saliency model. Then, these salient regions of the image were used to train a sparse autoencoder and get a collection of convolutional filters, which accord with the statistical characteristics of dataset. At last, a DCNN with Inception module and its variants was constructed. To improve the recognition accuracy, the depth of the network is deepened. The experiment results indicate that the constructed DCNN increases the recognition accuracy by 2.7% compared to TCNN, when recognizing the down in the images. The convergence rate of the proposed DCNN with the new weight initialization method is improved by 25.5% compared to TCNN. Keywords: Deep convolutional neural network, Weight initialization, Sparse autoencoder, Visual saliency model, Image recognition

Discrete Neural Correlates for the Recognition of Negative Emotions: Insights from Frontotemporal Dementia

Science.gov (United States)

Kumfor, Fiona; Irish, Muireann; Hodges, John R.; Piguet, Olivier

2013-01-01

Patients with frontotemporal dementia have pervasive changes in emotion recognition and social cognition, yet the neural changes underlying these emotion processing deficits remain unclear. The multimodal system model of emotion proposes that basic emotions are dependent on distinct brain regions, which undergo significant pathological changes in frontotemporal dementia. As such, this syndrome may provide important insight into the impact of neural network degeneration upon the innate ability to recognise emotions. This study used voxel-based morphometry to identify discrete neural correlates involved in the recognition of basic emotions (anger, disgust, fear, sadness, surprise and happiness) in frontotemporal dementia. Forty frontotemporal dementia patients (18 behavioural-variant, 11 semantic dementia, 11 progressive nonfluent aphasia) and 27 healthy controls were tested on two facial emotion recognition tasks: The Ekman 60 and Ekman Caricatures. Although each frontotemporal dementia group showed impaired recognition of negative emotions, distinct associations between emotion-specific task performance and changes in grey matter intensity emerged. Fear recognition was associated with the right amygdala; disgust recognition with the left insula; anger recognition with the left middle and superior temporal gyrus; and sadness recognition with the left subcallosal cingulate, indicating that discrete neural substrates are necessary for emotion recognition in frontotemporal dementia. The erosion of emotion-specific neural networks in neurodegenerative disorders may produce distinct profiles of performance that are relevant to understanding the neurobiological basis of emotion processing. PMID:23805313

Handwritten Digits Recognition Using Neural Computing

Directory of Open Access Journals (Sweden)

Călin Enăchescu

2009-12-01

Full Text Available In this paper we present a method for the recognition of handwritten digits and a practical implementation of this method for real-time recognition. A theoretical framework for the neural networks used to classify the handwritten digits is also presented.The classification task is performed using a Convolutional Neural Network (CNN. CNN is a special type of multy-layer neural network, being trained with an optimized version of the back-propagation learning algorithm.CNN is designed to recognize visual patterns directly from pixel images with minimal preprocessing, being capable to recognize patterns with extreme variability (such as handwritten characters, and with robustness to distortions and simple geometric transformations.The main contributions of this paper are related to theoriginal methods for increasing the efficiency of the learning algorithm by preprocessing the images before the learning process and a method for increasing the precision and performance for real-time applications, by removing the non useful information from the background.By combining these strategies we have obtained an accuracy of 96.76%, using as training set the NIST (National Institute of Standards and Technology database.

Recognition of sign language gestures using neural networks

Directory of Open Access Journals (Sweden)

Simon Vamplew

2007-04-01

Full Text Available This paper describes the structure and performance of the SLARTI sign language recognition system developed at the University of Tasmania. SLARTI uses a modular architecture consisting of multiple feature-recognition neural networks and a nearest-neighbour classifier to recognise Australian sign language (Auslan hand gestures.

Face Recognition using Artificial Neural Network | Endeshaw | Zede ...

African Journals Online (AJOL)

Face recognition (FR) is one of the biometric methods to identify the individuals by the features of face. Two Face Recognition Systems (FRS) based on Artificial Neural Network (ANN) have been proposed in this paper based on feature extraction techniques. In the first system, Principal Component Analysis (PCA) has been ...

An Introduction to Neural Networks for Hearing Aid Noise Recognition.

Science.gov (United States)

Kim, Jun W.; Tyler, Richard S.

1995-01-01

This article introduces the use of multilayered artificial neural networks in hearing aid noise recognition. It reviews basic principles of neural networks, and offers an example of an application in which a neural network is used to identify the presence or absence of noise in speech. The ability of neural networks to "learn" the…

The neural cell adhesion molecule

DEFF Research Database (Denmark)

Berezin, V; Bock, E; Poulsen, F M

2000-01-01

During the past year, the understanding of the structure and function of neural cell adhesion has advanced considerably. The three-dimensional structures of several of the individual modules of the neural cell adhesion molecule (NCAM) have been determined, as well as the structure of the complex...... between two identical fragments of the NCAM. Also during the past year, a link between homophilic cell adhesion and several signal transduction pathways has been proposed, connecting the event of cell surface adhesion to cellular responses such as neurite outgrowth. Finally, the stimulation of neurite...

Modular Neural Networks and Type-2 Fuzzy Systems for Pattern Recognition

CERN Document Server

Melin, Patricia

2012-01-01

This book describes hybrid intelligent systems using type-2 fuzzy logic and modular neural networks for pattern recognition applications. Hybrid intelligent systems combine several intelligent computing paradigms, including fuzzy logic, neural networks, and bio-inspired optimization algorithms, which can be used to produce powerful pattern recognition systems. Type-2 fuzzy logic is an extension of traditional type-1 fuzzy logic that enables managing higher levels of uncertainty in complex real world problems, which are of particular importance in the area of pattern recognition. The book is organized in three main parts, each containing a group of chapters built around a similar subject. The first part consists of chapters with the main theme of theory and design algorithms, which are basically chapters that propose new models and concepts, which are the basis for achieving intelligent pattern recognition. The second part contains chapters with the main theme of using type-2 fuzzy models and modular neural ne...

The neural correlates of gist-based true and false recognition

Science.gov (United States)

Gutchess, Angela H.; Schacter, Daniel L.

2012-01-01

When information is thematically related to previously studied information, gist-based processes contribute to false recognition. Using functional MRI, we examined the neural correlates of gist-based recognition as a function of increasing numbers of studied exemplars. Sixteen participants incidentally encoded small, medium, and large sets of pictures, and we compared the neural response at recognition using parametric modulation analyses. For hits, regions in middle occipital, middle temporal, and posterior parietal cortex linearly modulated their activity according to the number of related encoded items. For false alarms, visual, parietal, and hippocampal regions were modulated as a function of the encoded set size. The present results are consistent with prior work in that the neural regions supporting veridical memory also contribute to false memory for related information. The results also reveal that these regions respond to the degree of relatedness among similar items, and implicate perceptual and constructive processes in gist-based false memory. PMID:22155331

Pattern recognition neural-net by spatial mapping of biology visual field

Science.gov (United States)

Lin, Xin; Mori, Masahiko

2000-05-01

The method of spatial mapping in biology vision field is applied to artificial neural networks for pattern recognition. By the coordinate transform that is called the complex-logarithm mapping and Fourier transform, the input images are transformed into scale- rotation- and shift- invariant patterns, and then fed into a multilayer neural network for learning and recognition. The results of computer simulation and an optical experimental system are described.

Image object recognition based on the Zernike moment and neural networks

Science.gov (United States)

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

1998-03-01

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

A Particle Swarm Optimization Algorithm for Neural Networks in Recognition of Maize Leaf Diseases

Directory of Open Access Journals (Sweden)

Zhiyong ZHANG

2014-03-01

Full Text Available The neural networks have significance on recognition of crops disease diagnosis? but it has disadvantage of slow convergent speed and shortcoming of local optimum. In order to identify the maize leaf diseases by using machine vision more accurately, we propose an improved particle swarm optimization algorithm for neural networks. With the algorithm, the neural network property is improved. It reasonably confirms threshold and connection weight of neural network, and improves capability of solving problems in the image recognition. At last, an example of the emulation shows that neural network model based on recognizes significantly better than without optimization. Model accuracy has been improved to a certain extent to meet the actual needs of maize leaf diseases recognition.

Distorted Character Recognition Via An Associative Neural Network

Science.gov (United States)

Messner, Richard A.; Szu, Harold H.

1987-03-01

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

Deep Recurrent Neural Networks for Human Activity Recognition

Directory of Open Access Journals (Sweden)

Abdulmajid Murad

2017-11-01

Full Text Available Adopting deep learning methods for human activity recognition has been effective in extracting discriminative features from raw input sequences acquired from body-worn sensors. Although human movements are encoded in a sequence of successive samples in time, typical machine learning methods perform recognition tasks without exploiting the temporal correlations between input data samples. Convolutional neural networks (CNNs address this issue by using convolutions across a one-dimensional temporal sequence to capture dependencies among input data. However, the size of convolutional kernels restricts the captured range of dependencies between data samples. As a result, typical models are unadaptable to a wide range of activity-recognition configurations and require fixed-length input windows. In this paper, we propose the use of deep recurrent neural networks (DRNNs for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences. We present unidirectional, bidirectional, and cascaded architectures based on long short-term memory (LSTM DRNNs and evaluate their effectiveness on miscellaneous benchmark datasets. Experimental results show that our proposed models outperform methods employing conventional machine learning, such as support vector machine (SVM and k-nearest neighbors (KNN. Additionally, the proposed models yield better performance than other deep learning techniques, such as deep believe networks (DBNs and CNNs.

Deep Recurrent Neural Networks for Human Activity Recognition.

Science.gov (United States)

Murad, Abdulmajid; Pyun, Jae-Young

2017-11-06

Adopting deep learning methods for human activity recognition has been effective in extracting discriminative features from raw input sequences acquired from body-worn sensors. Although human movements are encoded in a sequence of successive samples in time, typical machine learning methods perform recognition tasks without exploiting the temporal correlations between input data samples. Convolutional neural networks (CNNs) address this issue by using convolutions across a one-dimensional temporal sequence to capture dependencies among input data. However, the size of convolutional kernels restricts the captured range of dependencies between data samples. As a result, typical models are unadaptable to a wide range of activity-recognition configurations and require fixed-length input windows. In this paper, we propose the use of deep recurrent neural networks (DRNNs) for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences. We present unidirectional, bidirectional, and cascaded architectures based on long short-term memory (LSTM) DRNNs and evaluate their effectiveness on miscellaneous benchmark datasets. Experimental results show that our proposed models outperform methods employing conventional machine learning, such as support vector machine (SVM) and k-nearest neighbors (KNN). Additionally, the proposed models yield better performance than other deep learning techniques, such as deep believe networks (DBNs) and CNNs.

Hypothetical Pattern Recognition Design Using Multi-Layer Perceptorn Neural Network For Supervised Learning

Directory of Open Access Journals (Sweden)

Md. Abdullah-al-mamun

2015-08-01

Full Text Available Abstract Humans are capable to identifying diverse shape in the different pattern in the real world as effortless fashion due to their intelligence is grow since born with facing several learning process. Same way we can prepared an machine using human like brain called Artificial Neural Network that can be recognize different pattern from the real world object. Although the various techniques is exists to implementation the pattern recognition but recently the artificial neural network approaches have been giving the significant attention. Because the approached of artificial neural network is like a human brain that is learn from different observation and give a decision the previously learning rule. Over the 50 years research now a days pattern recognition for machine learning using artificial neural network got a significant achievement. For this reason many real world problem can be solve by modeling the pattern recognition process. The objective of this paper is to present the theoretical concept for pattern recognition design using Multi-Layer Perceptorn neural networkin the algorithm of artificial Intelligence as the best possible way of utilizing available resources to make a decision that can be a human like performance.

Multi-digit handwritten sindhi numerals recognition using som neural network

International Nuclear Information System (INIS)

Chandio, A.A.; Jalbani, A.H.; Awan, S.A.

2017-01-01

In this research paper a multi-digit Sindhi handwritten numerals recognition system using SOM Neural Network is presented. Handwritten digits recognition is one of the challenging tasks and a lot of research is being carried out since many years. A remarkable work has been done for recognition of isolated handwritten characters as well as digits in many languages like English, Arabic, Devanagari, Chinese, Urdu and Pashto. However, the literature reviewed does not show any remarkable work done for Sindhi numerals recognition. The recognition of Sindhi digits is a difficult task due to the various writing styles and different font sizes. Therefore, SOM (Self-Organizing Map), a NN (Neural Network) method is used which can recognize digits with various writing styles and different font sizes. Only one sample is required to train the network for each pair of multi-digit numerals. A database consisting of 4000 samples of multi-digits consisting only two digits from 10-50 and other matching numerals have been collected by 50 users and the experimental results of proposed method show that an accuracy of 86.89% is achieved. (author)

What Types of Visual Recognition Tasks Are Mediated by the Neural Subsystem that Subserves Face Recognition?

Science.gov (United States)

Brooks, Brian E.; Cooper, Eric E.

2006-01-01

Three divided visual field experiments tested current hypotheses about the types of visual shape representation tasks that recruit the cognitive and neural mechanisms underlying face recognition. Experiment 1 found a right hemisphere advantage for subordinate but not basic-level face recognition. Experiment 2 found a right hemisphere advantage for…

Neural speech recognition: continuous phoneme decoding using spatiotemporal representations of human cortical activity

Science.gov (United States)

Moses, David A.; Mesgarani, Nima; Leonard, Matthew K.; Chang, Edward F.

2016-10-01

Objective. The superior temporal gyrus (STG) and neighboring brain regions play a key role in human language processing. Previous studies have attempted to reconstruct speech information from brain activity in the STG, but few of them incorporate the probabilistic framework and engineering methodology used in modern speech recognition systems. In this work, we describe the initial efforts toward the design of a neural speech recognition (NSR) system that performs continuous phoneme recognition on English stimuli with arbitrary vocabulary sizes using the high gamma band power of local field potentials in the STG and neighboring cortical areas obtained via electrocorticography. Approach. The system implements a Viterbi decoder that incorporates phoneme likelihood estimates from a linear discriminant analysis model and transition probabilities from an n-gram phonemic language model. Grid searches were used in an attempt to determine optimal parameterizations of the feature vectors and Viterbi decoder. Main results. The performance of the system was significantly improved by using spatiotemporal representations of the neural activity (as opposed to purely spatial representations) and by including language modeling and Viterbi decoding in the NSR system. Significance. These results emphasize the importance of modeling the temporal dynamics of neural responses when analyzing their variations with respect to varying stimuli and demonstrate that speech recognition techniques can be successfully leveraged when decoding speech from neural signals. Guided by the results detailed in this work, further development of the NSR system could have applications in the fields of automatic speech recognition and neural prosthetics.

Human Face Recognition Using Convolutional Neural Networks

Directory of Open Access Journals (Sweden)

Răzvan-Daniel Albu

2009-10-01

Full Text Available In this paper, I present a novel hybrid face recognition approach based on a convolutional neural architecture, designed to robustly detect highly variable face patterns. The convolutional network extracts successively larger features in a hierarchical set of layers. With the weights of the trained neural networks there are created kernel windows used for feature extraction in a 3-stage algorithm. I present experimental results illustrating the efficiency of the proposed approach. I use a database of 796 images of 159 individuals from Reims University which contains quite a high degree of variability in expression, pose, and facial details.

DMPD: CD14 and other recognition molecules for lipopolysaccharide: a review. [Dynamic Macrophage Pathway CSML Database

Lifescience Database Archive (English)

Full Text Available 7542643 CD14 and other recognition molecules for lipopolysaccharide: a review. Kiel...her recognition molecules for lipopolysaccharide: a review. PubmedID 7542643 Title CD14 and other recognitio...n molecules for lipopolysaccharide: a review. Authors Kielian TL, Blecha F. Publi

Deep Recurrent Convolutional Neural Network: Improving Performance For Speech Recognition

OpenAIRE

Zhang, Zewang; Sun, Zheng; Liu, Jiaqi; Chen, Jingwen; Huo, Zhao; Zhang, Xiao

2016-01-01

A deep learning approach has been widely applied in sequence modeling problems. In terms of automatic speech recognition (ASR), its performance has significantly been improved by increasing large speech corpus and deeper neural network. Especially, recurrent neural network and deep convolutional neural network have been applied in ASR successfully. Given the arising problem of training speed, we build a novel deep recurrent convolutional network for acoustic modeling and then apply deep resid...

Very deep recurrent convolutional neural network for object recognition

Science.gov (United States)

Brahimi, Sourour; Ben Aoun, Najib; Ben Amar, Chokri

2017-03-01

In recent years, Computer vision has become a very active field. This field includes methods for processing, analyzing, and understanding images. The most challenging problems in computer vision are image classification and object recognition. This paper presents a new approach for object recognition task. This approach exploits the success of the Very Deep Convolutional Neural Network for object recognition. In fact, it improves the convolutional layers by adding recurrent connections. This proposed approach was evaluated on two object recognition benchmarks: Pascal VOC 2007 and CIFAR-10. The experimental results prove the efficiency of our method in comparison with the state of the art methods.

Application of artificial neural network for medical image recognition and diagnostic decision making

International Nuclear Information System (INIS)

Asada, N.; Eiho, S.; Doi, K.; MacMahon, H.; Montner, S.M.; Giger, M.L.

1989-01-01

An artificial neural network has been applied for pattern recognition and used as a tool in an expert system. The purpose of this study is to examine the potential usefulness of the neural network approach in medical applications for image recognition and decision making. The authors designed multilayer feedforward neural networks with a back-propagation algorithm for our study. Using first-pass radionuclide ventriculograms, we attempted to identify the right and left ventricles of the heart and the lungs by training the neural network from patterns of time-activity curves. In a preliminary study, the neural network enabled identification of the lungs and heart chambers once the network was trained sufficiently by means of repeated entries of data from the same case

The neural correlates of visual self-recognition.

Science.gov (United States)

Devue, Christel; Brédart, Serge

2011-03-01

This paper presents a review of studies that were aimed at determining which brain regions are recruited during visual self-recognition, with a particular focus on self-face recognition. A complex bilateral network, involving frontal, parietal and occipital areas, appears to be associated with self-face recognition, with a particularly high implication of the right hemisphere. Results indicate that it remains difficult to determine which specific cognitive operation is reflected by each recruited brain area, in part due to the variability of used control stimuli and experimental tasks. A synthesis of the interpretations provided by previous studies is presented. The relevance of using self-recognition as an indicator of self-awareness is discussed. We argue that a major aim of future research in the field should be to identify more clearly the cognitive operations induced by the perception of the self-face, and search for dissociations between neural correlates and cognitive components. Copyright © 2010 Elsevier Inc. All rights reserved.

Study on recognition algorithm for paper currency numbers based on neural network

Science.gov (United States)

Li, Xiuyan; Liu, Tiegen; Li, Yuanyao; Zhang, Zhongchuan; Deng, Shichao

2008-12-01

Based on the unique characteristic, the paper currency numbers can be put into record and the automatic identification equipment for paper currency numbers is supplied to currency circulation market in order to provide convenience for financial sectors to trace the fiduciary circulation socially and provide effective supervision on paper currency. Simultaneously it is favorable for identifying forged notes, blacklisting the forged notes numbers and solving the major social problems, such as armor cash carrier robbery, money laundering. For the purpose of recognizing the paper currency numbers, a recognition algorithm based on neural network is presented in the paper. Number lines in original paper currency images can be draw out through image processing, such as image de-noising, skew correction, segmentation, and image normalization. According to the different characteristics between digits and letters in serial number, two kinds of classifiers are designed. With the characteristics of associative memory, optimization-compute and rapid convergence, the Discrete Hopfield Neural Network (DHNN) is utilized to recognize the letters; with the characteristics of simple structure, quick learning and global optimum, the Radial-Basis Function Neural Network (RBFNN) is adopted to identify the digits. Then the final recognition results are obtained by combining the two kinds of recognition results in regular sequence. Through the simulation tests, it is confirmed by simulation results that the recognition algorithm of combination of two kinds of recognition methods has such advantages as high recognition rate and faster recognition simultaneously, which is worthy of broad application prospect.

Fine-grained vehicle type recognition based on deep convolution neural networks

Directory of Open Access Journals (Sweden)

Hongcai CHEN

2017-12-01

Full Text Available Public security and traffic department put forward higher requirements for real-time performance and accuracy of vehicle type recognition in complex traffic scenes. Aiming at the problems of great plice forces occupation, low retrieval efficiency, and lacking of intelligence for dealing with false license, fake plate vehicles and vehicles without plates, this paper proposes a vehicle type fine-grained recognition method based GoogleNet deep convolution neural networks. The filter size and numbers of convolution neural network are designed, the activation function and vehicle type classifier are optimally selected, and a new network framework is constructed for vehicle type fine-grained recognition. The experimental results show that the proposed method has 97% accuracy for vehicle type fine-grained recognition and has greater improvement than the original GoogleNet model. Moreover, the new model effectively reduces the number of training parameters, and saves computer memory. Fine-grained vehicle type recognition can be used in intelligent traffic management area, and has important theoretical research value and practical significance.

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

Science.gov (United States)

Xing, Weiwei; Li, Ying; Zhang, Shunli

2018-01-01

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

Static facial expression recognition with convolution neural networks

Science.gov (United States)

Zhang, Feng; Chen, Zhong; Ouyang, Chao; Zhang, Yifei

2018-03-01

Facial expression recognition is a currently active research topic in the fields of computer vision, pattern recognition and artificial intelligence. In this paper, we have developed a convolutional neural networks (CNN) for classifying human emotions from static facial expression into one of the seven facial emotion categories. We pre-train our CNN model on the combined FER2013 dataset formed by train, validation and test set and fine-tune on the extended Cohn-Kanade database. In order to reduce the overfitting of the models, we utilized different techniques including dropout and batch normalization in addition to data augmentation. According to the experimental result, our CNN model has excellent classification performance and robustness for facial expression recognition.

Influence of auditory attention on sentence recognition captured by the neural phase.

Science.gov (United States)

Müller, Jana Annina; Kollmeier, Birger; Debener, Stefan; Brand, Thomas

2018-03-07

The aim of this study was to investigate whether attentional influences on speech recognition are reflected in the neural phase entrained by an external modulator. Sentences were presented in 7 Hz sinusoidally modulated noise while the neural response to that modulation frequency was monitored by electroencephalogram (EEG) recordings in 21 participants. We implemented a selective attention paradigm including three different attention conditions while keeping physical stimulus parameters constant. The participants' task was either to repeat the sentence as accurately as possible (speech recognition task), to count the number of decrements implemented in modulated noise (decrement detection task), or to do both (dual task), while the EEG was recorded. Behavioural analysis revealed reduced performance in the dual task condition for decrement detection, possibly reflecting limited cognitive resources. EEG analysis revealed no significant differences in power for the 7 Hz modulation frequency, but an attention-dependent phase difference between tasks. Further phase analysis revealed a significant difference 500 ms after sentence onset between trials with correct and incorrect responses for speech recognition, indicating that speech recognition performance and the neural phase are linked via selective attention mechanisms, at least shortly after sentence onset. However, the neural phase effects identified were small and await further investigation. © 2018 Federation of European Neuroscience Societies and John Wiley & Sons Ltd.

Banknote recognition: investigating processing and cognition framework using competitive neural network.

Science.gov (United States)

Oyedotun, Oyebade K; Khashman, Adnan

2017-02-01

Humans are apt at recognizing patterns and discovering even abstract features which are sometimes embedded therein. Our ability to use the banknotes in circulation for business transactions lies in the effortlessness with which we can recognize the different banknote denominations after seeing them over a period of time. More significant is that we can usually recognize these banknote denominations irrespective of what parts of the banknotes are exposed to us visually. Furthermore, our recognition ability is largely unaffected even when these banknotes are partially occluded. In a similar analogy, the robustness of intelligent systems to perform the task of banknote recognition should not collapse under some minimum level of partial occlusion. Artificial neural networks are intelligent systems which from inception have taken many important cues related to structure and learning rules from the human nervous/cognition processing system. Likewise, it has been shown that advances in artificial neural network simulations can help us understand the human nervous/cognition system even furthermore. In this paper, we investigate three cognition hypothetical frameworks to vision-based recognition of banknote denominations using competitive neural networks. In order to make the task more challenging and stress-test the investigated hypotheses, we also consider the recognition of occluded banknotes. The implemented hypothetical systems are tasked to perform fast recognition of banknotes with up to 75 % occlusion. The investigated hypothetical systems are trained on Nigeria's Naira banknotes and several experiments are performed to demonstrate the findings presented within this work.

Compact holographic optical neural network system for real-time pattern recognition

Science.gov (United States)

Lu, Taiwei; Mintzer, David T.; Kostrzewski, Andrew A.; Lin, Freddie S.

1996-08-01

One of the important characteristics of artificial neural networks is their capability for massive interconnection and parallel processing. Recently, specialized electronic neural network processors and VLSI neural chips have been introduced in the commercial market. The number of parallel channels they can handle is limited because of the limited parallel interconnections that can be implemented with 1D electronic wires. High-resolution pattern recognition problems can require a large number of neurons for parallel processing of an image. This paper describes a holographic optical neural network (HONN) that is based on high- resolution volume holographic materials and is capable of performing massive 3D parallel interconnection of tens of thousands of neurons. A HONN with more than 16,000 neurons packaged in an attache case has been developed. Rotation- shift-scale-invariant pattern recognition operations have been demonstrated with this system. System parameters such as the signal-to-noise ratio, dynamic range, and processing speed are discussed.

Convolutional neural networks and face recognition task

Science.gov (United States)

Sochenkova, A.; Sochenkov, I.; Makovetskii, A.; Vokhmintsev, A.; Melnikov, A.

2017-09-01

Computer vision tasks are remaining very important for the last couple of years. One of the most complicated problems in computer vision is face recognition that could be used in security systems to provide safety and to identify person among the others. There is a variety of different approaches to solve this task, but there is still no universal solution that would give adequate results in some cases. Current paper presents following approach. Firstly, we extract an area containing face, then we use Canny edge detector. On the next stage we use convolutional neural networks (CNN) to finally solve face recognition and person identification task.

Recognition of power quality events by using multiwavelet-based neural networks

Energy Technology Data Exchange (ETDEWEB)

Kaewarsa, Suriya; Attakitmongcol, Kitti; Kulworawanichpong, Thanatchai [School of Electrical Engineering, Suranaree University of Technology, 111 University Avenue, Muang District, Nakhon Ratchasima 30000 (Thailand)

2008-05-15

Recognition of power quality events by analyzing the voltage and current waveform disturbances is a very important task for the power system monitoring. This paper presents a novel approach for the recognition of power quality disturbances using multiwavelet transform and neural networks. The proposed method employs the multiwavelet transform using multiresolution signal decomposition techniques working together with multiple neural networks using a learning vector quantization network as a powerful classifier. Various transient events are tested, such as voltage sag, swell, interruption, notching, impulsive transient, and harmonic distortion show that the classifier can detect and classify different power quality signal types efficiency. (author)

Face recognition: a convolutional neural-network approach.

Science.gov (United States)

Lawrence, S; Giles, C L; Tsoi, A C; Back, A D

1997-01-01

We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image sampling, a self-organizing map (SOM) neural network, and a convolutional neural network. The SOM provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the SOM, and a multilayer perceptron (MLP) in place of the convolutional network for comparison. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details. We analyze the computational complexity and discuss how new classes could be added to the trained recognizer.

Spaced Learning Enhances Subsequent Recognition Memory by Reducing Neural Repetition Suppression

Science.gov (United States)

Xue, Gui; Mei, Leilei; Chen, Chuansheng; Lu, Zhong-Lin; Poldrack, Russell; Dong, Qi

2011-01-01

Spaced learning usually leads to better recognition memory as compared with massed learning, yet the underlying neural mechanisms remain elusive. One open question is whether the spacing effect is achieved by reducing neural repetition suppression. In this fMRI study, participants were scanned while intentionally memorizing 120 novel faces, half…

Electrolarynx Voice Recognition Utilizing Pulse Coupled Neural Network

Directory of Open Access Journals (Sweden)

Fatchul Arifin

2010-08-01

Full Text Available The laryngectomies patient has no ability to speak normally because their vocal chords have been removed. The easiest option for the patient to speak again is by using electrolarynx speech. This tool is placed on the lower chin. Vibration of the neck while speaking is used to produce sound. Meanwhile, the technology of "voice recognition" has been growing very rapidly. It is expected that the technology of "voice recognition" can also be used by laryngectomies patients who use electrolarynx.This paper describes a system for electrolarynx speech recognition. Two main parts of the system are feature extraction and pattern recognition. The Pulse Coupled Neural Network – PCNN is used to extract the feature and characteristic of electrolarynx speech. Varying of β (one of PCNN parameter also was conducted. Multi layer perceptron is used to recognize the sound patterns. There are two kinds of recognition conducted in this paper: speech recognition and speaker recognition. The speech recognition recognizes specific speech from every people. Meanwhile, speaker recognition recognizes specific speech from specific person. The system ran well. The "electrolarynx speech recognition" has been tested by recognizing of “A” and "not A" voice. The results showed that the system had 94.4% validation. Meanwhile, the electrolarynx speaker recognition has been tested by recognizing of “saya” voice from some different speakers. The results showed that the system had 92.2% validation. Meanwhile, the best β parameter of PCNN for electrolarynx recognition is 3.

Fractionating the Neural Substrates of Incidental Recognition Memory

Science.gov (United States)

Greene, Ciara M.; Vidaki, Kleio; Soto, David

2015-01-01

Familiar stimuli are typically accompanied by decreases in neural response relative to the presentation of novel items, but these studies often include explicit instructions to discriminate old and new items; this creates difficulties in partialling out the contribution of top-down intentional orientation to the items based on recognition goals.…

Recognition of neural brain activity patterns correlated with complex motor activity

Science.gov (United States)

Kurkin, Semen; Musatov, Vyacheslav Yu.; Runnova, Anastasia E.; Grubov, Vadim V.; Efremova, Tatyana Yu.; Zhuravlev, Maxim O.

2018-04-01

In this paper, based on the apparatus of artificial neural networks, a technique for recognizing and classifying patterns corresponding to imaginary movements on electroencephalograms (EEGs) obtained from a group of untrained subjects was developed. The works on the selection of the optimal type, topology, training algorithms and neural network parameters were carried out from the point of view of the most accurate and fast recognition and classification of patterns on multi-channel EEGs associated with the imagination of movements. The influence of the number and choice of the analyzed channels of a multichannel EEG on the quality of recognition of imaginary movements was also studied, and optimal configurations of electrode arrangements were obtained. The effect of pre-processing of EEG signals is analyzed from the point of view of improving the accuracy of recognition of imaginary movements.

Neural network application to the neutral meson recognition

International Nuclear Information System (INIS)

Lefevre, F.; Delagrange, H.; Merrouch, R.; Ostendorf, R.; Schutz, Y.; Matulewicz, T.

1991-01-01

The combinatorial background produced by high photon multiplicities expected in TAPS experiments causes problems in precise meson recognition. We use neural networks to reduce this background. First we give a description of this technique, hereafter the first results obtained by applying this method to simulated events and future perspective will be discussed [fr

Interactions of the humoral pattern recognition molecule PTX3 with the complement system

DEFF Research Database (Denmark)

Doni, Andrea; Garlanda, Cecilia; Bottazzi, Barbara

2012-01-01

The innate immune system comprises a cellular and a humoral arm. The long pentraxin PTX3 is a fluid phase pattern recognition molecule, which acts as an essential component of the humoral arm of innate immunity. PTX3 has antibody-like properties including interactions with complement components....... PTX3 interacts with C1q, ficolin-1 and ficolin-2 as well as mannose-binding lectin, recognition molecules in the classical and lectin complement pathways. The formation of these heterocomplexes results in cooperative pathogen recognition and complement activation. Interactions with C4b binding protein...

Recurrent Convolutional Neural Networks: A Better Model of Biological Object Recognition.

Science.gov (United States)

Spoerer, Courtney J; McClure, Patrick; Kriegeskorte, Nikolaus

2017-01-01

Feedforward neural networks provide the dominant model of how the brain performs visual object recognition. However, these networks lack the lateral and feedback connections, and the resulting recurrent neuronal dynamics, of the ventral visual pathway in the human and non-human primate brain. Here we investigate recurrent convolutional neural networks with bottom-up (B), lateral (L), and top-down (T) connections. Combining these types of connections yields four architectures (B, BT, BL, and BLT), which we systematically test and compare. We hypothesized that recurrent dynamics might improve recognition performance in the challenging scenario of partial occlusion. We introduce two novel occluded object recognition tasks to test the efficacy of the models, digit clutter (where multiple target digits occlude one another) and digit debris (where target digits are occluded by digit fragments). We find that recurrent neural networks outperform feedforward control models (approximately matched in parametric complexity) at recognizing objects, both in the absence of occlusion and in all occlusion conditions. Recurrent networks were also found to be more robust to the inclusion of additive Gaussian noise. Recurrent neural networks are better in two respects: (1) they are more neurobiologically realistic than their feedforward counterparts; (2) they are better in terms of their ability to recognize objects, especially under challenging conditions. This work shows that computer vision can benefit from using recurrent convolutional architectures and suggests that the ubiquitous recurrent connections in biological brains are essential for task performance.

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

Science.gov (United States)

Greenberg, Shlomo; Guterman, Hugo

1996-08-01

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

Design and Implementation of Behavior Recognition System Based on Convolutional Neural Network

Directory of Open Access Journals (Sweden)

Yu Bo

2017-01-01

Full Text Available We build a set of human behavior recognition system based on the convolution neural network constructed for the specific human behavior in public places. Firstly, video of human behavior data set will be segmented into images, then we process the images by the method of background subtraction to extract moving foreground characters of body. Secondly, the training data sets are trained into the designed convolution neural network, and the depth learning network is constructed by stochastic gradient descent. Finally, the various behaviors of samples are classified and identified with the obtained network model, and the recognition results are compared with the current mainstream methods. The result show that the convolution neural network can study human behavior model automatically and identify human’s behaviors without any manually annotated trainings.

The Neural Cell Adhesion Molecule NCAM2/OCAM/RNCAM, a Close Relative to NCAM

DEFF Research Database (Denmark)

Kulahin, Nikolaj; Walmod, Peter

2008-01-01

molecule (NCAM) is a well characterized, ubiquitously expressed CAM that is highly expressed in the nervous system. In addition to mediating cell adhesion, NCAM participates in a multitude of cellular events, including survival, migration, and differentiation of cells, outgrowth of neurites, and formation......Cell adhesion molecules (CAMs) constitute a large class of plasma membrane-anchored proteins that mediate attachment between neighboring cells and between cells and the surrounding extracellular matrix (ECM). However, CAMs are more than simple mediators of cell adhesion. The neural cell adhesion...... and plasticity of synapses. NCAM shares an overall sequence identity of approximately 44% with the neural cell adhesion molecule 2 (NCAM2), a protein also known as olfactory cell adhesion molecule (OCAM) and Rb-8 neural cell adhesion molecule (RNCAM), and the region-for-region sequence homology between the two...

Investigating the Influence of Biological Sex on the Behavioral and Neural Basis of Face Recognition.

Science.gov (United States)

Scherf, K Suzanne; Elbich, Daniel B; Motta-Mena, Natalie V

2017-01-01

There is interest in understanding the influence of biological factors, like sex, on the organization of brain function. We investigated the influence of biological sex on the behavioral and neural basis of face recognition in healthy, young adults. In behavior, there were no sex differences on the male Cambridge Face Memory Test (CFMT)+ or the female CFMT+ (that we created) and no own-gender bias (OGB) in either group. We evaluated the functional topography of ventral stream organization by measuring the magnitude and functional neural size of 16 individually defined face-, two object-, and two place-related regions bilaterally. There were no sex differences in any of these measures of neural function in any of the regions of interest (ROIs) or in group level comparisons. These findings reveal that men and women have similar category-selective topographic organization in the ventral visual pathway. Next, in a separate task, we measured activation within the 16 face-processing ROIs specifically during recognition of target male and female faces. There were no sex differences in the magnitude of the neural responses in any face-processing region. Furthermore, there was no OGB in the neural responses of either the male or female participants. Our findings suggest that face recognition behavior, including the OGB, is not inherently sexually dimorphic. Face recognition is an essential skill for navigating human social interactions, which is reflected equally in the behavior and neural architecture of men and women.

Investigating the Influence of Biological Sex on the Behavioral and Neural Basis of Face Recognition

Science.gov (United States)

2017-01-01

Abstract There is interest in understanding the influence of biological factors, like sex, on the organization of brain function. We investigated the influence of biological sex on the behavioral and neural basis of face recognition in healthy, young adults. In behavior, there were no sex differences on the male Cambridge Face Memory Test (CFMT)+ or the female CFMT+ (that we created) and no own-gender bias (OGB) in either group. We evaluated the functional topography of ventral stream organization by measuring the magnitude and functional neural size of 16 individually defined face-, two object-, and two place-related regions bilaterally. There were no sex differences in any of these measures of neural function in any of the regions of interest (ROIs) or in group level comparisons. These findings reveal that men and women have similar category-selective topographic organization in the ventral visual pathway. Next, in a separate task, we measured activation within the 16 face-processing ROIs specifically during recognition of target male and female faces. There were no sex differences in the magnitude of the neural responses in any face-processing region. Furthermore, there was no OGB in the neural responses of either the male or female participants. Our findings suggest that face recognition behavior, including the OGB, is not inherently sexually dimorphic. Face recognition is an essential skill for navigating human social interactions, which is reflected equally in the behavior and neural architecture of men and women. PMID:28497111

PEAK TRACKING WITH A NEURAL NETWORK FOR SPECTRAL RECOGNITION

NARCIS (Netherlands)

COENEGRACHT, PMJ; METTING, HJ; VANLOO, EM; SNOEIJER, GJ; DOORNBOS, DA

1993-01-01

A peak tracking method based on a simulated feed-forward neural network with back-propagation is presented. The network uses the normalized UV spectra and peak areas measured in one chromatogram for peak recognition. It suffices to train the network with only one set of spectra recorded in one

Three-dimensional fingerprint recognition by using convolution neural network

Science.gov (United States)

Tian, Qianyu; Gao, Nan; Zhang, Zonghua

2018-01-01

With the development of science and technology and the improvement of social information, fingerprint recognition technology has become a hot research direction and been widely applied in many actual fields because of its feasibility and reliability. The traditional two-dimensional (2D) fingerprint recognition method relies on matching feature points. This method is not only time-consuming, but also lost three-dimensional (3D) information of fingerprint, with the fingerprint rotation, scaling, damage and other issues, a serious decline in robustness. To solve these problems, 3D fingerprint has been used to recognize human being. Because it is a new research field, there are still lots of challenging problems in 3D fingerprint recognition. This paper presents a new 3D fingerprint recognition method by using a convolution neural network (CNN). By combining 2D fingerprint and fingerprint depth map into CNN, and then through another CNN feature fusion, the characteristics of the fusion complete 3D fingerprint recognition after classification. This method not only can preserve 3D information of fingerprints, but also solves the problem of CNN input. Moreover, the recognition process is simpler than traditional feature point matching algorithm. 3D fingerprint recognition rate by using CNN is compared with other fingerprint recognition algorithms. The experimental results show that the proposed 3D fingerprint recognition method has good recognition rate and robustness.

Neural Dissociation of Number from Letter Recognition and Its Relationship to Parietal Numerical Processing

Science.gov (United States)

Park, Joonkoo; Hebrank, Andrew; Polk, Thad A.; Park, Denise C.

2012-01-01

The visual recognition of letters dissociates from the recognition of numbers at both the behavioral and neural level. In this article, using fMRI, we investigate whether the visual recognition of numbers dissociates from letters, thereby establishing a double dissociation. In Experiment 1, participants viewed strings of consonants and Arabic…

Automatic target recognition using a feature-based optical neural network

Science.gov (United States)

Chao, Tien-Hsin

1992-01-01

An optical neural network based upon the Neocognitron paradigm (K. Fukushima et al. 1983) is introduced. A novel aspect of the architectural design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by iteratively feeding back the output of the feature correlator to the input spatial light modulator and updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intra-class fault tolerance and inter-class discrimination is achieved. A detailed system description is provided. Experimental demonstration of a two-layer neural network for space objects discrimination is also presented.

Reduction of the dimension of neural network models in problems of pattern recognition and forecasting

Science.gov (United States)

Nasertdinova, A. D.; Bochkarev, V. V.

2017-11-01

Deep neural networks with a large number of parameters are a powerful tool for solving problems of pattern recognition, prediction and classification. Nevertheless, overfitting remains a serious problem in the use of such networks. A method of solving the problem of overfitting is proposed in this article. This method is based on reducing the number of independent parameters of a neural network model using the principal component analysis, and can be implemented using existing libraries of neural computing. The algorithm was tested on the problem of recognition of handwritten symbols from the MNIST database, as well as on the task of predicting time series (rows of the average monthly number of sunspots and series of the Lorentz system were used). It is shown that the application of the principal component analysis enables reducing the number of parameters of the neural network model when the results are good. The average error rate for the recognition of handwritten figures from the MNIST database was 1.12% (which is comparable to the results obtained using the "Deep training" methods), while the number of parameters of the neural network can be reduced to 130 times.

The use of global image characteristics for neural network pattern recognitions

Science.gov (United States)

Kulyas, Maksim O.; Kulyas, Oleg L.; Loshkarev, Aleksey S.

2017-04-01

The recognition system is observed, where the information is transferred by images of symbols generated by a television camera. For descriptors of objects the coefficients of two-dimensional Fourier transformation generated in a special way. For solution of the task of classification the one-layer neural network trained on reference images is used. Fast learning of a neural network with a single neuron calculation of coefficients is applied.

THE COMPARISON OF ALGORITHMS OF RECOGNITION OF IMAGES HOPFILD’S NEURAL NETWORKS

Directory of Open Access Journals (Sweden)

Anna Illarionovna Pavlova

2016-05-01

Full Text Available The main advantage of artificial neural networks (ANN in recognition of the cottages, is in their functioning like a human brain. The paper deals with image recognition neuron Hopfield’s networks, a comparative analysis of the recognition images by a projection’s method and the Hebb’s rule. For these purposes, was developed program with C# in Microsoft Visual Studio 2012. In this article to recognition for images with different levels of distortion were used. The analysis of results of recognition of images has shown that the method of projections allows to restore strongly distorted images (level of distortions up to 25–30 percent

New domains of neural cell-adhesion molecule L1 implicated in X-linked hydrocephalus and MASA syndrome

Energy Technology Data Exchange (ETDEWEB)

Jouet, M.; Kenwick, S. [Univ. of Cambridge (United Kingdom); Moncla, A. [Hopital d`Enfants de la Timone, Marseillas (United Kingdom)] [and others

1995-06-01

The neural cell-adhesion molecule L1 is involved in intercellular recognition and neuronal migration in the CNS. Recently, we have shown that mutations in the gene encoding L1 are responsible for three related disorders; X-linked hydrocephalus, MASA (mental retardation, aphasia, shuffling gait, and adducted thumbs) syndrome, and spastic paraplegia type I (SPG1). These three disorders represent a clinical spectrum that varies not only between families but sometimes also within families. To date, 14 independent L1 mutations have been reported and shown to be disease causing. Here we report nine novel L1 mutations in X-linked hydrocephalus and MASA-syndrome families, including the first examples of mutations affecting the fibronectin type III domains of the molecule. They are discussed in relation both to phenotypes and to the insights that they provide into L1 function. 39 refs., 5 figs., 3 tabs.

Recognition of edible oil by using BP neural network and laser induced fluorescence spectrum

Science.gov (United States)

Mu, Tao-tao; Chen, Si-ying; Zhang, Yin-chao; Guo, Pan; Chen, He; Zhang, Hong-yan; Liu, Xiao-hua; Wang, Yuan; Bu, Zhi-chao

2013-09-01

In order to accomplish recognition of the different edible oil we set up a laser induced fluorescence spectrum system in the laboratory based on Laser induced fluorescence spectrum technology, and then collect the fluorescence spectrum of different edible oil by using that system. Based on this, we set up a fluorescence spectrum database of different cooking oil. It is clear that there are three main peak position of different edible oil from fluorescence spectrum chart. Although the peak positions of all cooking oil were almost the same, the relative intensity of different edible oils was totally different. So it could easily accomplish that oil recognition could take advantage of the difference of relative intensity. Feature invariants were extracted from the spectrum data, which were chosen from the fluorescence spectrum database randomly, before distinguishing different cooking oil. Then back propagation (BP) neural network was established and trained by the chosen data from the spectrum database. On that basis real experiment data was identified by BP neural network. It was found that the overall recognition rate could reach as high as 83.2%. Experiments showed that the laser induced fluorescence spectrum of different cooking oil was very different from each other, which could be used to accomplish the oil recognition. Laser induced fluorescence spectrum technology, combined BP neural network，was fast, high sensitivity, non-contact, and high recognition rate. It could become a new technique to accomplish the edible oil recognition and quality detection.

Finger vein recognition based on convolutional neural network

Directory of Open Access Journals (Sweden)

Meng Gesi

2017-01-01

Full Text Available Biometric Authentication Technology has been widely used in this information age. As one of the most important technology of authentication, finger vein recognition attracts our attention because of its high security, reliable accuracy and excellent performance. However, the current finger vein recognition system is difficult to be applied widely because its complicated image pre-processing and not representative feature vectors. To solve this problem, a finger vein recognition method based on the convolution neural network (CNN is proposed in the paper. The image samples are directly input into the CNN model to extract its feature vector so that we can make authentication by comparing the Euclidean distance between these vectors. Finally, the Deep Learning Framework Caffe is adopted to verify this method. The result shows that there are great improvements in both speed and accuracy rate compared to the previous research. And the model has nice robustness in illumination and rotation.

Iterative principles of recognition in probabilistic neural networks

Czech Academy of Sciences Publication Activity Database

Grim, Jiří; Hora, Jan

2008-01-01

Roč. 21, č. 6 (2008), s. 838-846 ISSN 0893-6080 R&D Projects: GA MŠk 1M0572; GA ČR GA102/07/1594 Grant - others:GA MŠk(CZ) 2C06019 Institutional research plan: CEZ:AV0Z10750506 Keywords : Probabilistic neural networks * Distribution mixtures * EM algorithm * Recognition of numerals * Recurrent reasoning Subject RIV: IN - Informatics, Computer Science Impact factor: 2.656, year: 2008

Simple test system for single molecule recognition force microscopy

International Nuclear Information System (INIS)

Riener, Christian K.; Stroh, Cordula M.; Ebner, Andreas; Klampfl, Christian; Gall, Alex A.; Romanin, Christoph; Lyubchenko, Yuri L.; Hinterdorfer, Peter; Gruber, Hermann J.

2003-01-01

We have established an easy-to-use test system for detecting receptor-ligand interactions on the single molecule level using atomic force microscopy (AFM). For this, avidin-biotin, probably the best characterized receptor-ligand pair, was chosen. AFM sensors were prepared containing tethered biotin molecules at sufficiently low surface concentrations appropriate for single molecule studies. A biotin tether, consisting of a 6 nm poly(ethylene glycol) (PEG) chain and a functional succinimide group at the other end, was newly synthesized and covalently coupled to amine-functionalized AFM tips. In particular, PEG 800 diamine was glutarylated, the mono-adduct NH 2 -PEG-COOH was isolated by ion exchange chromatography and reacted with biotin succinimidylester to give biotin-PEG-COOH which was then activated as N-hydroxysuccinimide (NHS) ester to give the biotin-PEG-NHS conjugate which was coupled to the aminofunctionalized AFM tip. The motional freedom provided by PEG allows for free rotation of the biotin molecule on the AFM sensor and for specific binding to avidin which had been adsorbed to mica surfaces via electrostatic interactions. Specific avidin-biotin recognition events were discriminated from nonspecific tip-mica adhesion by their typical unbinding force (∼40 pN at 1.4 nN/s loading rate), unbinding length (<13 nm), the characteristic nonlinear force-distance relation of the PEG linker, and by specific block with excess of free d-biotin. The convenience of the test system allowed to evaluate, and compare, different methods and conditions of tip aminofunctionalization with respect to specific binding and nonspecific adhesion. It is concluded that this system is well suited as calibration or start-up kit for single molecule recognition force microscopy

Ficolins and FIBCD1: Soluble and membrane bound pattern recognition molecules with acetyl group selectivity

DEFF Research Database (Denmark)

Thomsen, Theresa; Schlosser, Anders; Holmskov, Uffe

2011-01-01

as pattern recognition molecules. Ficolins are soluble oligomeric proteins composed of trimeric collagen-like regions linked to fibrinogen-related domains (FReDs) that have the ability to sense molecular patterns on both pathogens and apoptotic cell surfaces and activate the complement system. The ficolins......D-containing molecules, and discusses structural resemblance but also diversity in recognition of acetylated ligands....

Object recognition using deep convolutional neural networks with complete transfer and partial frozen layers

NARCIS (Netherlands)

Kruithof, M.C.; Bouma, H.; Fischer, N.M.; Schutte, K.

2016-01-01

Object recognition is important to understand the content of video and allow flexible querying in a large number of cameras, especially for security applications. Recent benchmarks show that deep convolutional neural networks are excellent approaches for object recognition. This paper describes an

A Grey Wolf Optimizer for Modular Granular Neural Networks for Human Recognition

Directory of Open Access Journals (Sweden)

Daniela Sánchez

2017-01-01

Full Text Available A grey wolf optimizer for modular neural network (MNN with a granular approach is proposed. The proposed method performs optimal granulation of data and design of modular neural networks architectures to perform human recognition, and to prove its effectiveness benchmark databases of ear, iris, and face biometric measures are used to perform tests and comparisons against other works. The design of a modular granular neural network (MGNN consists in finding optimal parameters of its architecture; these parameters are the number of subgranules, percentage of data for the training phase, learning algorithm, goal error, number of hidden layers, and their number of neurons. Nowadays, there is a great variety of approaches and new techniques within the evolutionary computing area, and these approaches and techniques have emerged to help find optimal solutions to problems or models and bioinspired algorithms are part of this area. In this work a grey wolf optimizer is proposed for the design of modular granular neural networks, and the results are compared against a genetic algorithm and a firefly algorithm in order to know which of these techniques provides better results when applied to human recognition.

Neural Mechanism for Mirrored Self-face Recognition.

Science.gov (United States)

Sugiura, Motoaki; Miyauchi, Carlos Makoto; Kotozaki, Yuka; Akimoto, Yoritaka; Nozawa, Takayuki; Yomogida, Yukihito; Hanawa, Sugiko; Yamamoto, Yuki; Sakuma, Atsushi; Nakagawa, Seishu; Kawashima, Ryuta

2015-09-01

Self-face recognition in the mirror is considered to involve multiple processes that integrate 2 perceptual cues: temporal contingency of the visual feedback on one's action (contingency cue) and matching with self-face representation in long-term memory (figurative cue). The aim of this study was to examine the neural bases of these processes by manipulating 2 perceptual cues using a "virtual mirror" system. This system allowed online dynamic presentations of real-time and delayed self- or other facial actions. Perception-level processes were identified as responses to only a single perceptual cue. The effect of the contingency cue was identified in the cuneus. The regions sensitive to the figurative cue were subdivided by the response to a static self-face, which was identified in the right temporal, parietal, and frontal regions, but not in the bilateral occipitoparietal regions. Semantic- or integration-level processes, including amodal self-representation and belief validation, which allow modality-independent self-recognition and the resolution of potential conflicts between perceptual cues, respectively, were identified in distinct regions in the right frontal and insular cortices. The results are supportive of the multicomponent notion of self-recognition and suggest a critical role for contingency detection in the co-emergence of self-recognition and empathy in infants. © The Author 2014. Published by Oxford University Press.

End-to-End Multimodal Emotion Recognition Using Deep Neural Networks

Science.gov (United States)

Tzirakis, Panagiotis; Trigeorgis, George; Nicolaou, Mihalis A.; Schuller, Bjorn W.; Zafeiriou, Stefanos

2017-12-01

Automatic affect recognition is a challenging task due to the various modalities emotions can be expressed with. Applications can be found in many domains including multimedia retrieval and human computer interaction. In recent years, deep neural networks have been used with great success in determining emotional states. Inspired by this success, we propose an emotion recognition system using auditory and visual modalities. To capture the emotional content for various styles of speaking, robust features need to be extracted. To this purpose, we utilize a Convolutional Neural Network (CNN) to extract features from the speech, while for the visual modality a deep residual network (ResNet) of 50 layers. In addition to the importance of feature extraction, a machine learning algorithm needs also to be insensitive to outliers while being able to model the context. To tackle this problem, Long Short-Term Memory (LSTM) networks are utilized. The system is then trained in an end-to-end fashion where - by also taking advantage of the correlations of the each of the streams - we manage to significantly outperform the traditional approaches based on auditory and visual handcrafted features for the prediction of spontaneous and natural emotions on the RECOLA database of the AVEC 2016 research challenge on emotion recognition.

Fast recognition of single molecules based on single-event photon statistics

International Nuclear Information System (INIS)

Dong Shuangli; Huang Tao; Liu Yuan; Wang Jun; Zhang Guofeng; Xiao Liantuan; Jia Suotang

2007-01-01

Mandel's Q parameter, which is determined from single-event photon statistics, provides an alternative way to recognize single molecules with fluorescence detection, other than the second-order correlation function. It is shown that the Q parameter of an assumed ideal double-molecule fluorescence with the same average photon number as that of the sample fluorescence can act as the criterion for single-molecule recognition. The influence of signal-to-background ratio and the error estimates for photon statistics are also presented. We have applied this method to ascertain single Cy5 dye molecules within hundreds of milliseconds

Granular neural networks, pattern recognition and bioinformatics

CERN Document Server

Pal, Sankar K; Ganivada, Avatharam

2017-01-01

This book provides a uniform framework describing how fuzzy rough granular neural network technologies can be formulated and used in building efficient pattern recognition and mining models. It also discusses the formation of granules in the notion of both fuzzy and rough sets. Judicious integration in forming fuzzy-rough information granules based on lower approximate regions enables the network to determine the exactness in class shape as well as to handle the uncertainties arising from overlapping regions, resulting in efficient and speedy learning with enhanced performance. Layered network and self-organizing analysis maps, which have a strong potential in big data, are considered as basic modules,. The book is structured according to the major phases of a pattern recognition system (e.g., classification, clustering, and feature selection) with a balanced mixture of theory, algorithm, and application. It covers the latest findings as well as directions for future research, particularly highlighting bioinf...

Neural correlates of recognition memory of social information in people with schizophrenia.

Science.gov (United States)

Harvey, Philippe-Olivier; Lepage, Martin

2014-03-01

Social dysfunction is a hallmark characteristic of schizophrenia. Part of it may stem from an inability to efficiently encode social information into memory and retrieve it later. This study focused on whether patients with schizophrenia show a memory boost for socially relevant information and engage the same neural network as controls when processing social stimuli that were previously encoded into memory. Patients with schizophrenia and healthy controls performed a social and nonsocial picture recognition memory task while being scanned. We calculated memory performance using d'. Our main analysis focused on brain activity associated with recognition memory of social and nonsocial pictures. Our study included 28 patients with schizophrenia and 26 controls. Healthy controls demonstrated a memory boost for socially relevant information. In contrast, patients with schizophrenia failed to show enhanced recognition sensitivity for social pictures. At the neural level, patients did not engage the dorsomedial prefrontal cortex (DMPFC) as much as controls while recognizing social pictures. Our study did not include direct measures of self-referential processing. All but 3 patients were taking antipsychotic medications, which may have altered both the behavioural performance during the picture recognition memory task and brain activity. Impaired social memory in patients with schizophrenia may be associated with altered DMPFC activity. A reduction of DMPFC activity may reflect less involvement of self-referential processes during memory retrieval. Our functional MRI results contribute to a better mapping of the neural disturbances associated with social memory impairment in patients with schizophrenia and may facilitate the development of innovative treatments, such as transcranial magnetic stimulation.

Morphological self-organizing feature map neural network with applications to automatic target recognition

Science.gov (United States)

Zhang, Shijun; Jing, Zhongliang; Li, Jianxun

2005-01-01

The rotation invariant feature of the target is obtained using the multi-direction feature extraction property of the steerable filter. Combining the morphological operation top-hat transform with the self-organizing feature map neural network, the adaptive topological region is selected. Using the erosion operation, the topological region shrinkage is achieved. The steerable filter based morphological self-organizing feature map neural network is applied to automatic target recognition of binary standard patterns and real-world infrared sequence images. Compared with Hamming network and morphological shared-weight networks respectively, the higher recognition correct rate, robust adaptability, quick training, and better generalization of the proposed method are achieved.

Recognition of decays of charged tracks with neural network techniques

International Nuclear Information System (INIS)

Stimpfl-Abele, G.

1991-01-01

We developed neural-network learning techniques for the recognition of decays of charged tracks using a feed-forward network with error back-propagation. Two completely different methods are described in detail and their efficiencies for several NN architectures are compared with conventional methods. Excellent results are obtained. (orig.)

Basic perceptual changes that alter meaning and neural correlates of recognition memory.

Science.gov (United States)

Gao, Chuanji; Hermiller, Molly S; Voss, Joel L; Guo, Chunyan

2015-01-01

It is difficult to pinpoint the border between perceptual and conceptual processing, despite their treatment as distinct entities in many studies of recognition memory. For instance, alteration of simple perceptual characteristics of a stimulus can radically change meaning, such as the color of bread changing from white to green. We sought to better understand the role of perceptual and conceptual processing in memory by identifying the effects of changing a basic perceptual feature (color) on behavioral and neural correlates of memory in circumstances when this change would be expected to either change the meaning of a stimulus or to have no effect on meaning (i.e., to influence conceptual processing or not). Abstract visual shapes ("squiggles") were colorized during study and presented during test in either the same color or a different color. Those squiggles that subjects found to resemble meaningful objects supported behavioral measures of conceptual priming, whereas meaningless squiggles did not. Further, changing color from study to test had a selective effect on behavioral correlates of priming for meaningful squiggles, indicating that color change altered conceptual processing. During a recognition memory test, color change altered event-related brain potential (ERP) correlates of memory for meaningful squiggles but not for meaningless squiggles. Specifically, color change reduced the amplitude of frontally distributed N400 potentials (FN400), implying that these potentials indicated conceptual processing during recognition memory that was sensitive to color change. In contrast, color change had no effect on FN400 correlates of recognition for meaningless squiggles, which were overall smaller in amplitude than for meaningful squiggles (further indicating that these potentials signal conceptual processing during recognition). Thus, merely changing the color of abstract visual shapes can alter their meaning, changing behavioral and neural correlates of memory

Pattern classification and recognition of invertebrate functional groups using self-organizing neural networks.

Science.gov (United States)

Zhang, WenJun

2007-07-01

Self-organizing neural networks can be used to mimic non-linear systems. The main objective of this study is to make pattern classification and recognition on sampling information using two self-organizing neural network models. Invertebrate functional groups sampled in the irrigated rice field were classified and recognized using one-dimensional self-organizing map and self-organizing competitive learning neural networks. Comparisons between neural network models, distance (similarity) measures, and number of neurons were conducted. The results showed that self-organizing map and self-organizing competitive learning neural network models were effective in pattern classification and recognition of sampling information. Overall the performance of one-dimensional self-organizing map neural network was better than self-organizing competitive learning neural network. The number of neurons could determine the number of classes in the classification. Different neural network models with various distance (similarity) measures yielded similar classifications. Some differences, dependent upon the specific network structure, would be found. The pattern of an unrecognized functional group was recognized with the self-organizing neural network. A relative consistent classification indicated that the following invertebrate functional groups, terrestrial blood sucker; terrestrial flyer; tourist (nonpredatory species with no known functional role other than as prey in ecosystem); gall former; collector (gather, deposit feeder); predator and parasitoid; leaf miner; idiobiont (acarine ectoparasitoid), were classified into the same group, and the following invertebrate functional groups, external plant feeder; terrestrial crawler, walker, jumper or hunter; neustonic (water surface) swimmer (semi-aquatic), were classified into another group. It was concluded that reliable conclusions could be drawn from comparisons of different neural network models that use different distance

Mexican sign language recognition using normalized moments and artificial neural networks

Science.gov (United States)

Solís-V., J.-Francisco; Toxqui-Quitl, Carina; Martínez-Martínez, David; H.-G., Margarita

2014-09-01

This work presents a framework designed for the Mexican Sign Language (MSL) recognition. A data set was recorded with 24 static signs from the MSL using 5 different versions, this MSL dataset was captured using a digital camera in incoherent light conditions. Digital Image Processing was used to segment hand gestures, a uniform background was selected to avoid using gloved hands or some special markers. Feature extraction was performed by calculating normalized geometric moments of gray scaled signs, then an Artificial Neural Network performs the recognition using a 10-fold cross validation tested in weka, the best result achieved 95.83% of recognition rate.

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

Science.gov (United States)

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

2001-03-01

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

Modified-hybrid optical neural network filter for multiple object recognition within cluttered scenes

Science.gov (United States)

Kypraios, Ioannis; Young, Rupert C. D.; Chatwin, Chris R.

2009-08-01

Motivated by the non-linear interpolation and generalization abilities of the hybrid optical neural network filter between the reference and non-reference images of the true-class object we designed the modifiedhybrid optical neural network filter. We applied an optical mask to the hybrid optical neural network's filter input. The mask was built with the constant weight connections of a randomly chosen image included in the training set. The resulted design of the modified-hybrid optical neural network filter is optimized for performing best in cluttered scenes of the true-class object. Due to the shift invariance properties inherited by its correlator unit the filter can accommodate multiple objects of the same class to be detected within an input cluttered image. Additionally, the architecture of the neural network unit of the general hybrid optical neural network filter allows the recognition of multiple objects of different classes within the input cluttered image by modifying the output layer of the unit. We test the modified-hybrid optical neural network filter for multiple objects of the same and of different classes' recognition within cluttered input images and video sequences of cluttered scenes. The filter is shown to exhibit with a single pass over the input data simultaneously out-of-plane rotation, shift invariance and good clutter tolerance. It is able to successfully detect and classify correctly the true-class objects within background clutter for which there has been no previous training.

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

OpenAIRE

Francisco Javier Ordóñez; Daniel Roggen

2016-01-01

Human activity recognition (HAR) tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we pro...

Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods.

Science.gov (United States)

Arcos-García, Álvaro; Álvarez-García, Juan A; Soria-Morillo, Luis M

2018-03-01

This paper presents a Deep Learning approach for traffic sign recognition systems. Several classification experiments are conducted over publicly available traffic sign datasets from Germany and Belgium using a Deep Neural Network which comprises Convolutional layers and Spatial Transformer Networks. Such trials are built to measure the impact of diverse factors with the end goal of designing a Convolutional Neural Network that can improve the state-of-the-art of traffic sign classification task. First, different adaptive and non-adaptive stochastic gradient descent optimisation algorithms such as SGD, SGD-Nesterov, RMSprop and Adam are evaluated. Subsequently, multiple combinations of Spatial Transformer Networks placed at distinct positions within the main neural network are analysed. The recognition rate of the proposed Convolutional Neural Network reports an accuracy of 99.71% in the German Traffic Sign Recognition Benchmark, outperforming previous state-of-the-art methods and also being more efficient in terms of memory requirements. Copyright © 2018 Elsevier Ltd. All rights reserved.

Novel roles for immune molecules in neural development: Implications for neurodevelopmental disoders

Directory of Open Access Journals (Sweden)

Paula A Garay

2010-09-01

Full Text Available Although the brain has classically been considered "immune-privileged," current research suggests extensive communication between the nervous and the immune systems in both health and disease. Recent studies demonstrate that immune molecules are present at the right place and time to modulate the development and function of the healthy and diseased CNS. Indeed, immune molecules play integral roles in the CNS throughout neural development, including affecting neurogenesis, neuronal migration, axon guidance, synapse formation, activity-dependent refinement of circuits, and synaptic plasticity. Moreover, the roles of individual immune molecules in the nervous system may change over development. This review focuses on the effects of immune molecules on neuronal connections in the mammalian central nervous system—specifically the roles for MHCI and its receptors, complement, and cytokines on the function, refinement, and plasticity of cortical and hippocampal synapses and their relationship to neurodevelopmental disorders. These functions for immune molecules during neural development suggest that they could also mediate pathological responses to chronic elevations of cytokines in neurodevelopmental disorders, including autism spectrum disorders (ASD and schizophrenia.

Dual Temporal Scale Convolutional Neural Network for Micro-Expression Recognition

Directory of Open Access Journals (Sweden)

Min Peng

2017-10-01

Full Text Available Facial micro-expression is a brief involuntary facial movement and can reveal the genuine emotion that people try to conceal. Traditional methods of spontaneous micro-expression recognition rely excessively on sophisticated hand-crafted feature design and the recognition rate is not high enough for its practical application. In this paper, we proposed a Dual Temporal Scale Convolutional Neural Network (DTSCNN for spontaneous micro-expressions recognition. The DTSCNN is a two-stream network. Different of stream of DTSCNN is used to adapt to different frame rate of micro-expression video clips. Each stream of DSTCNN consists of independent shallow network for avoiding the overfitting problem. Meanwhile, we fed the networks with optical-flow sequences to ensure that the shallow networks can further acquire higher-level features. Experimental results on spontaneous micro-expression databases (CASME I/II showed that our method can achieve a recognition rate almost 10% higher than what some state-of-the-art method can achieve.

Dual Temporal Scale Convolutional Neural Network for Micro-Expression Recognition.

Science.gov (United States)

Peng, Min; Wang, Chongyang; Chen, Tong; Liu, Guangyuan; Fu, Xiaolan

2017-01-01

Facial micro-expression is a brief involuntary facial movement and can reveal the genuine emotion that people try to conceal. Traditional methods of spontaneous micro-expression recognition rely excessively on sophisticated hand-crafted feature design and the recognition rate is not high enough for its practical application. In this paper, we proposed a Dual Temporal Scale Convolutional Neural Network (DTSCNN) for spontaneous micro-expressions recognition. The DTSCNN is a two-stream network. Different of stream of DTSCNN is used to adapt to different frame rate of micro-expression video clips. Each stream of DSTCNN consists of independent shallow network for avoiding the overfitting problem. Meanwhile, we fed the networks with optical-flow sequences to ensure that the shallow networks can further acquire higher-level features. Experimental results on spontaneous micro-expression databases (CASME I/II) showed that our method can achieve a recognition rate almost 10% higher than what some state-of-the-art method can achieve.

Dual Temporal Scale Convolutional Neural Network for Micro-Expression Recognition

Science.gov (United States)

Peng, Min; Wang, Chongyang; Chen, Tong; Liu, Guangyuan; Fu, Xiaolan

2017-01-01

Facial micro-expression is a brief involuntary facial movement and can reveal the genuine emotion that people try to conceal. Traditional methods of spontaneous micro-expression recognition rely excessively on sophisticated hand-crafted feature design and the recognition rate is not high enough for its practical application. In this paper, we proposed a Dual Temporal Scale Convolutional Neural Network (DTSCNN) for spontaneous micro-expressions recognition. The DTSCNN is a two-stream network. Different of stream of DTSCNN is used to adapt to different frame rate of micro-expression video clips. Each stream of DSTCNN consists of independent shallow network for avoiding the overfitting problem. Meanwhile, we fed the networks with optical-flow sequences to ensure that the shallow networks can further acquire higher-level features. Experimental results on spontaneous micro-expression databases (CASME I/II) showed that our method can achieve a recognition rate almost 10% higher than what some state-of-the-art method can achieve. PMID:29081753

A neural cell adhesion molecule-derived peptide reduces neuropathological signs and cognitive impairment induced by Abeta25-35

DEFF Research Database (Denmark)

Klementiev, B; Novikova, T; Novitskaya, V

2007-01-01

death and brain atrophy in response to Abeta25-35. Finally, the Abeta25-35-administration led to a reduced short-term memory as determined by the social recognition test. A synthetic peptide termed FGL derived from the neural cell adhesion molecule (NCAM) was able to prevent or, if already manifest......, strongly reduce all investigated signs of Abeta25-35-induced neuropathology and cognitive impairment. The FGL peptide was recently demonstrated to be able to cross the blood-brain-barrier. Accordingly, we found that the beneficial effects of FGL were achieved not only by intracisternal, but also...... and cognitive impairment involves the modulation of intracellular signal-transduction mediated through GSK3beta....

Artificial neural network for bubbles pattern recognition on the images

International Nuclear Information System (INIS)

Poletaev, I E; Pervunin, K S; Tokarev, M P

2016-01-01

Two-phase bubble flows have been used in many technological and energy processes as processing oil, chemical and nuclear reactors. This explains large interest to experimental and numerical studies of such flows last several decades. Exploiting of optical diagnostics for analysis of the bubble flows allows researchers obtaining of instantaneous velocity fields and gaseous phase distribution with the high spatial resolution non-intrusively. Behavior of light rays exhibits an intricate manner when they cross interphase boundaries of gaseous bubbles hence the identification of the bubbles images is a complicated problem. This work presents a method of bubbles images identification based on a modern technology of deep learning called convolutional neural networks (CNN). Neural networks are able to determine overlapping, blurred, and non-spherical bubble images. They can increase accuracy of the bubble image recognition, reduce the number of outliers, lower data processing time, and significantly decrease the number of settings for the identification in comparison with standard recognition methods developed before. In addition, usage of GPUs speeds up the learning process of CNN owning to the modern adaptive subgradient optimization techniques. (paper)

Single-molecule spectroscopy of amino acids and peptides by recognition tunnelling

Science.gov (United States)

Zhao, Yanan; Ashcroft, Brian; Zhang, Peiming; Liu, Hao; Sen, Suman; Song, Weisi; Im, Jongone; Gyarfas, Brett; Manna, Saikat; Biswas, Sovan; Borges, Chad; Lindsay, Stuart

2014-06-01

The human proteome has millions of protein variants due to alternative RNA splicing and post-translational modifications, and variants that are related to diseases are frequently present in minute concentrations. For DNA and RNA, low concentrations can be amplified using the polymerase chain reaction, but there is no such reaction for proteins. Therefore, the development of single-molecule protein sequencing is a critical step in the search for protein biomarkers. Here, we show that single amino acids can be identified by trapping the molecules between two electrodes that are coated with a layer of recognition molecules, then measuring the electron tunnelling current across the junction. A given molecule can bind in more than one way in the junction, and we therefore use a machine-learning algorithm to distinguish between the sets of electronic `fingerprints' associated with each binding motif. With this recognition tunnelling technique, we are able to identify D and L enantiomers, a methylated amino acid, isobaric isomers and short peptides. The results suggest that direct electronic sequencing of single proteins could be possible by sequentially measuring the products of processive exopeptidase digestion, or by using a molecular motor to pull proteins through a tunnel junction integrated with a nanopore.

Neural network application for thermal image recognition of low-resolution objects

Science.gov (United States)

Fang, Yi-Chin; Wu, Bo-Wen

2007-02-01

In the ever-changing situation on a battle field, accurate recognition of a distant object is critical to a commander's decision-making and the general public's safety. Efficiently distinguishing between an enemy's armoured vehicles and ordinary civilian houses under all weather conditions has become an important research topic. This study presents a system for recognizing an armoured vehicle by distinguishing marks and contours. The characteristics of 12 different shapes and 12 characters are used to explore thermal image recognition under the circumstance of long distance and low resolution. Although the recognition capability of human eyes is superior to that of artificial intelligence under normal conditions, it tends to deteriorate substantially under long-distance and low-resolution scenarios. This study presents an effective method for choosing features and processing images. The artificial neural network technique is applied to further improve the probability of accurate recognition well beyond the limit of the recognition capability of human eyes.

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

Science.gov (United States)

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

2017-06-06

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

Different neural processes accompany self-recognition in photographs across the lifespan: an ERP study using dizygotic twins.

Science.gov (United States)

Butler, David L; Mattingley, Jason B; Cunnington, Ross; Suddendorf, Thomas

2013-01-01

Our appearance changes over time, yet we can recognize ourselves in photographs from across the lifespan. Researchers have extensively studied self-recognition in photographs and have proposed that specific neural correlates are involved, but few studies have examined self-recognition using images from different periods of life. Here we compared ERP responses to photographs of participants when they were 5-15, 16-25, and 26-45 years old. We found marked differences between the responses to photographs from these time periods in terms of the neural markers generally assumed to reflect (i) the configural processing of faces (i.e., the N170), (ii) the matching of the currently perceived face to a representation already stored in memory (i.e., the P250), and (iii) the retrieval of information about the person being recognized (i.e., the N400). There was no uniform neural signature of visual self-recognition. To test whether there was anything specific to self-recognition in these brain responses, we also asked participants to identify photographs of their dizygotic twins taken from the same time periods. Critically, this allowed us to minimize the confounding effects of exposure, for it is likely that participants have been similarly exposed to each other's faces over the lifespan. The same pattern of neural response emerged with only one exception: the neural marker reflecting the retrieval of mnemonic information (N400) differed across the lifespan for self but not for twin. These results, as well as our novel approach using twins and photographs from across the lifespan, have wide-ranging consequences for the study of self-recognition and the nature of our personal identity through time.

Different neural processes accompany self-recognition in photographs across the lifespan: an ERP study using dizygotic twins.

Directory of Open Access Journals (Sweden)

David L Butler

Full Text Available Our appearance changes over time, yet we can recognize ourselves in photographs from across the lifespan. Researchers have extensively studied self-recognition in photographs and have proposed that specific neural correlates are involved, but few studies have examined self-recognition using images from different periods of life. Here we compared ERP responses to photographs of participants when they were 5-15, 16-25, and 26-45 years old. We found marked differences between the responses to photographs from these time periods in terms of the neural markers generally assumed to reflect (i the configural processing of faces (i.e., the N170, (ii the matching of the currently perceived face to a representation already stored in memory (i.e., the P250, and (iii the retrieval of information about the person being recognized (i.e., the N400. There was no uniform neural signature of visual self-recognition. To test whether there was anything specific to self-recognition in these brain responses, we also asked participants to identify photographs of their dizygotic twins taken from the same time periods. Critically, this allowed us to minimize the confounding effects of exposure, for it is likely that participants have been similarly exposed to each other's faces over the lifespan. The same pattern of neural response emerged with only one exception: the neural marker reflecting the retrieval of mnemonic information (N400 differed across the lifespan for self but not for twin. These results, as well as our novel approach using twins and photographs from across the lifespan, have wide-ranging consequences for the study of self-recognition and the nature of our personal identity through time.

Self-Assembled Core-Satellite Gold Nanoparticle Networks for Ultrasensitive Detection of Chiral Molecules by Recognition Tunneling Current.

Science.gov (United States)

Zhang, Yuanchao; Liu, Jingquan; Li, Da; Dai, Xing; Yan, Fuhua; Conlan, Xavier A; Zhou, Ruhong; Barrow, Colin J; He, Jin; Wang, Xin; Yang, Wenrong

2016-05-24

Chirality sensing is a very challenging task. Here, we report a method for ultrasensitive detection of chiral molecule l/d-carnitine based on changes in the recognition tunneling current across self-assembled core-satellite gold nanoparticle (GNP) networks. The recognition tunneling technique has been demonstrated to work at the single molecule level where the binding between the reader molecules and the analytes in a nanojunction. This process was observed to generate a unique and sensitive change in tunneling current, which can be used to identify the analytes of interest. The molecular recognition mechanism between amino acid l-cysteine and l/d-carnitine has been studied with the aid of SERS. The different binding strength between homo- or heterochiral pairs can be effectively probed by the copper ion replacement fracture. The device resistance was measured before and after the sequential exposures to l/d-carnitine and copper ions. The normalized resistance change was found to be extremely sensitive to the chirality of carnitine molecule. The results suggested that a GNP networks device optimized for recognition tunneling was successfully built and that such a device can be used for ultrasensitive detection of chiral molecules.

End-to-End Neural Optical Music Recognition of Monophonic Scores

Directory of Open Access Journals (Sweden)

Jorge Calvo-Zaragoza

2018-04-01

Full Text Available Optical Music Recognition is a field of research that investigates how to computationally decode music notation from images. Despite the efforts made so far, there are hardly any complete solutions to the problem. In this work, we study the use of neural networks that work in an end-to-end manner. This is achieved by using a neural model that combines the capabilities of convolutional neural networks, which work on the input image, and recurrent neural networks, which deal with the sequential nature of the problem. Thanks to the use of the the so-called Connectionist Temporal Classification loss function, these models can be directly trained from input images accompanied by their corresponding transcripts into music symbol sequences. We also present the Printed Music Scores dataset, containing more than 80,000 monodic single-staff real scores in common western notation, that is used to train and evaluate the neural approach. In our experiments, it is demonstrated that this formulation can be carried out successfully. Additionally, we study several considerations about the codification of the output musical sequences, the convergence and scalability of the neural models, as well as the ability of this approach to locate symbols in the input score.

Whose Balance Sheet is this? Neural Networks for Banks' Pattern Recognition

NARCIS (Netherlands)

Leon Rincon, Carlos; Moreno, José Fernando; Cely, Jorge

2017-01-01

The balance sheet is a snapshot that portraits the financial position of a firm at a specific point of time. Under the reasonable assumption that the financial position of a firm is unique and representative, we use a basic artificial neural network pattern recognition method on Colombian banks’

Transfer Learning with Convolutional Neural Networks for SAR Ship Recognition

Science.gov (United States)

Zhang, Di; Liu, Jia; Heng, Wang; Ren, Kaijun; Song, Junqiang

2018-03-01

Ship recognition is the backbone of marine surveillance systems. Recent deep learning methods, e.g. Convolutional Neural Networks (CNNs), have shown high performance for optical images. Learning CNNs, however, requires a number of annotated samples to estimate numerous model parameters, which prevents its application to Synthetic Aperture Radar (SAR) images due to the limited annotated training samples. Transfer learning has been a promising technique for applications with limited data. To this end, a novel SAR ship recognition method based on CNNs with transfer learning has been developed. In this work, we firstly start with a CNNs model that has been trained in advance on Moving and Stationary Target Acquisition and Recognition (MSTAR) database. Next, based on the knowledge gained from this image recognition task, we fine-tune the CNNs on a new task to recognize three types of ships in the OpenSARShip database. The experimental results show that our proposed approach can obviously increase the recognition rate comparing with the result of merely applying CNNs. In addition, compared to existing methods, the proposed method proves to be very competitive and can learn discriminative features directly from training data instead of requiring pre-specification or pre-selection manually.

Static sign language recognition using 1D descriptors and neural networks

Science.gov (United States)

Solís, José F.; Toxqui, Carina; Padilla, Alfonso; Santiago, César

2012-10-01

A frame work for static sign language recognition using descriptors which represents 2D images in 1D data and artificial neural networks is presented in this work. The 1D descriptors were computed by two methods, first one consists in a correlation rotational operator.1 and second is based on contour analysis of hand shape. One of the main problems in sign language recognition is segmentation; most of papers report a special color in gloves or background for hand shape analysis. In order to avoid the use of gloves or special clothing, a thermal imaging camera was used to capture images. Static signs were picked up from 1 to 9 digits of American Sign Language, a multilayer perceptron reached 100% recognition with cross-validation.

[Neural basis of self-face recognition: social aspects].

Science.gov (United States)

Sugiura, Motoaki

2012-07-01

Considering the importance of the face in social survival and evidence from evolutionary psychology of visual self-recognition, it is reasonable that we expect neural mechanisms for higher social-cognitive processes to underlie self-face recognition. A decade of neuroimaging studies so far has, however, not provided an encouraging finding in this respect. Self-face specific activation has typically been reported in the areas for sensory-motor integration in the right lateral cortices. This observation appears to reflect the physical nature of the self-face which representation is developed via the detection of contingency between one's own action and sensory feedback. We have recently revealed that the medial prefrontal cortex, implicated in socially nuanced self-referential process, is activated during self-face recognition under a rich social context where multiple other faces are available for reference. The posterior cingulate cortex has also exhibited this activation modulation, and in the separate experiment showed a response to attractively manipulated self-face suggesting its relevance to positive self-value. Furthermore, the regions in the right lateral cortices typically showing self-face-specific activation have responded also to the face of one's close friend under the rich social context. This observation is potentially explained by the fact that the contingency detection for physical self-recognition also plays a role in physical social interaction, which characterizes the representation of personally familiar people. These findings demonstrate that neuroscientific exploration reveals multiple facets of the relationship between self-face recognition and social-cognitive process, and that technically the manipulation of social context is key to its success.

Noisy Ocular Recognition Based on Three Convolutional Neural Networks

Directory of Open Access Journals (Sweden)

Min Beom Lee

2017-12-01

Full Text Available In recent years, the iris recognition system has been gaining increasing acceptance for applications such as access control and smartphone security. When the images of the iris are obtained under unconstrained conditions, an issue of undermined quality is caused by optical and motion blur, off-angle view (the user’s eyes looking somewhere else, not into the front of the camera, specular reflection (SR and other factors. Such noisy iris images increase intra-individual variations and, as a result, reduce the accuracy of iris recognition. A typical iris recognition system requires a near-infrared (NIR illuminator along with an NIR camera, which are larger and more expensive than fingerprint recognition equipment. Hence, many studies have proposed methods of using iris images captured by a visible light camera without the need for an additional illuminator. In this research, we propose a new recognition method for noisy iris and ocular images by using one iris and two periocular regions, based on three convolutional neural networks (CNNs. Experiments were conducted by using the noisy iris challenge evaluation-part II (NICE.II training dataset (selected from the university of Beira iris (UBIRIS.v2 database, mobile iris challenge evaluation (MICHE database, and institute of automation of Chinese academy of sciences (CASIA-Iris-Distance database. As a result, the method proposed by this study outperformed previous methods.

Noisy Ocular Recognition Based on Three Convolutional Neural Networks.

Science.gov (United States)

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

2017-12-17

In recent years, the iris recognition system has been gaining increasing acceptance for applications such as access control and smartphone security. When the images of the iris are obtained under unconstrained conditions, an issue of undermined quality is caused by optical and motion blur, off-angle view (the user's eyes looking somewhere else, not into the front of the camera), specular reflection (SR) and other factors. Such noisy iris images increase intra-individual variations and, as a result, reduce the accuracy of iris recognition. A typical iris recognition system requires a near-infrared (NIR) illuminator along with an NIR camera, which are larger and more expensive than fingerprint recognition equipment. Hence, many studies have proposed methods of using iris images captured by a visible light camera without the need for an additional illuminator. In this research, we propose a new recognition method for noisy iris and ocular images by using one iris and two periocular regions, based on three convolutional neural networks (CNNs). Experiments were conducted by using the noisy iris challenge evaluation-part II (NICE.II) training dataset (selected from the university of Beira iris (UBIRIS).v2 database), mobile iris challenge evaluation (MICHE) database, and institute of automation of Chinese academy of sciences (CASIA)-Iris-Distance database. As a result, the method proposed by this study outperformed previous methods.

Strabismus Recognition Using Eye-Tracking Data and Convolutional Neural Networks

Directory of Open Access Journals (Sweden)

Zenghai Chen

2018-01-01

Full Text Available Strabismus is one of the most common vision diseases that would cause amblyopia and even permanent vision loss. Timely diagnosis is crucial for well treating strabismus. In contrast to manual diagnosis, automatic recognition can significantly reduce labor cost and increase diagnosis efficiency. In this paper, we propose to recognize strabismus using eye-tracking data and convolutional neural networks. In particular, an eye tracker is first exploited to record a subject’s eye movements. A gaze deviation (GaDe image is then proposed to characterize the subject’s eye-tracking data according to the accuracies of gaze points. The GaDe image is fed to a convolutional neural network (CNN that has been trained on a large image database called ImageNet. The outputs of the full connection layers of the CNN are used as the GaDe image’s features for strabismus recognition. A dataset containing eye-tracking data of both strabismic subjects and normal subjects is established for experiments. Experimental results demonstrate that the natural image features can be well transferred to represent eye-tracking data, and strabismus can be effectively recognized by our proposed method.

Analog design of a new neural network for optical character recognition.

Science.gov (United States)

Morns, I P; Dlay, S S

1999-01-01

An electronic circuit is presented for a new type of neural network, which gives a recognition rate of over 100 kHz. The network is used to classify handwritten numerals, presented as Fourier and wavelet descriptors, and has been shown to train far quicker than the popular backpropagation network while maintaining classification accuracy.

Sign Language Recognition System using Neural Network for Digital Hardware Implementation

International Nuclear Information System (INIS)

Vargas, Lorena P; Barba, Leiner; Torres, C O; Mattos, L

2011-01-01

This work presents an image pattern recognition system using neural network for the identification of sign language to deaf people. The system has several stored image that show the specific symbol in this kind of language, which is employed to teach a multilayer neural network using a back propagation algorithm. Initially, the images are processed to adapt them and to improve the performance of discriminating of the network, including in this process of filtering, reduction and elimination noise algorithms as well as edge detection. The system is evaluated using the signs without including movement in their representation.

New baseline correction algorithm for text-line recognition with bidirectional recurrent neural networks

Science.gov (United States)

Morillot, Olivier; Likforman-Sulem, Laurence; Grosicki, Emmanuèle

2013-04-01

Many preprocessing techniques have been proposed for isolated word recognition. However, recently, recognition systems have dealt with text blocks and their compound text lines. In this paper, we propose a new preprocessing approach to efficiently correct baseline skew and fluctuations. Our approach is based on a sliding window within which the vertical position of the baseline is estimated. Segmentation of text lines into subparts is, thus, avoided. Experiments conducted on a large publicly available database (Rimes), with a BLSTM (bidirectional long short-term memory) recurrent neural network recognition system, show that our baseline correction approach highly improves performance.

Facial Expression Recognition By Using Fisherface Methode With Backpropagation Neural Network

Directory of Open Access Journals (Sweden)

Zaenal Abidin

2011-01-01

Full Text Available Abstract— In daily lives, especially in interpersonal communication, face often used for expression. Facial expressions give information about the emotional state of the person. A facial expression is one of the behavioral characteristics. The components of a basic facial expression analysis system are face detection, face data extraction, and facial expression recognition. Fisherface method with backpropagation artificial neural network approach can be used for facial expression recognition. This method consists of two-stage process, namely PCA and LDA. PCA is used to reduce the dimension, while the LDA is used for features extraction of facial expressions. The system was tested with 2 databases namely JAFFE database and MUG database. The system correctly classified the expression with accuracy of 86.85%, and false positive 25 for image type I of JAFFE, for image type II of JAFFE 89.20% and false positive 15,  for type III of JAFFE 87.79%, and false positive for 16. The image of MUG are 98.09%, and false positive 5. Keywords— facial expression, fisherface method, PCA, LDA, backpropagation neural network.

Bilinear Convolutional Neural Networks for Fine-grained Visual Recognition.

Science.gov (United States)

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

2017-07-04

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

Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition

Science.gov (United States)

Yin, Xi; Liu, Xiaoming

2018-02-01

This paper explores multi-task learning (MTL) for face recognition. We answer the questions of how and why MTL can improve the face recognition performance. First, we propose a multi-task Convolutional Neural Network (CNN) for face recognition where identity classification is the main task and pose, illumination, and expression estimations are the side tasks. Second, we develop a dynamic-weighting scheme to automatically assign the loss weight to each side task, which is a crucial problem in MTL. Third, we propose a pose-directed multi-task CNN by grouping different poses to learn pose-specific identity features, simultaneously across all poses. Last but not least, we propose an energy-based weight analysis method to explore how CNN-based MTL works. We observe that the side tasks serve as regularizations to disentangle the variations from the learnt identity features. Extensive experiments on the entire Multi-PIE dataset demonstrate the effectiveness of the proposed approach. To the best of our knowledge, this is the first work using all data in Multi-PIE for face recognition. Our approach is also applicable to in-the-wild datasets for pose-invariant face recognition and achieves comparable or better performance than state of the art on LFW, CFP, and IJB-A datasets.

Facial Emotions Recognition using Gabor Transform and Facial Animation Parameters with Neural Networks

Science.gov (United States)

Harit, Aditya; Joshi, J. C., Col; Gupta, K. K.

2018-03-01

The paper proposed an automatic facial emotion recognition algorithm which comprises of two main components: feature extraction and expression recognition. The algorithm uses a Gabor filter bank on fiducial points to find the facial expression features. The resulting magnitudes of Gabor transforms, along with 14 chosen FAPs (Facial Animation Parameters), compose the feature space. There are two stages: the training phase and the recognition phase. Firstly, for the present 6 different emotions, the system classifies all training expressions in 6 different classes (one for each emotion) in the training stage. In the recognition phase, it recognizes the emotion by applying the Gabor bank to a face image, then finds the fiducial points, and then feeds it to the trained neural architecture.

Application of neural network and pattern recognition software to the automated analysis of continuous nuclear monitoring of on-load reactors

Energy Technology Data Exchange (ETDEWEB)

Howell, J.A.; Eccleston, G.W.; Halbig, J.K.; Klosterbuer, S.F. [Los Alamos National Lab., NM (United States); Larson, T.W. [California Polytechnic State Univ., San Luis Obispo, CA (US)

1993-08-01

Automated analysis using pattern recognition and neural network software can help interpret data, call attention to potential anomalies, and improve safeguards effectiveness. Automated software analysis, based on pattern recognition and neural networks, was applied to data collected from a radiation core discharge monitor system located adjacent to an on-load reactor core. Unattended radiation sensors continuously collect data to monitor on-line refueling operations in the reactor. The huge volume of data collected from a number of radiation channels makes it difficult for a safeguards inspector to review it all, check for consistency among the measurement channels, and find anomalies. Pattern recognition and neural network software can analyze large volumes of data from continuous, unattended measurements, thereby improving and automating the detection of anomalies. The authors developed a prototype pattern recognition program that determines the reactor power level and identifies the times when fuel bundles are pushed through the core during on-line refueling. Neural network models were also developed to predict fuel bundle burnup to calculate the region on the on-load reactor face from which fuel bundles were discharged based on the radiation signals. In the preliminary data set, which was limited and consisted of four distinct burnup regions, the neural network model correctly predicted the burnup region with an accuracy of 92%.

Cross-cultural differences in the neural correlates of specific and general recognition.

Science.gov (United States)

Paige, Laura E; Ksander, John C; Johndro, Hunter A; Gutchess, Angela H

2017-06-01

Research suggests that culture influences how people perceive the world, which extends to memory specificity, or how much perceptual detail is remembered. The present study investigated cross-cultural differences (Americans vs East Asians) at the time of encoding in the neural correlates of specific versus general memory formation. Participants encoded photos of everyday items in the scanner and 48 h later completed a surprise recognition test. The recognition test consisted of same (i.e., previously seen in scanner), similar (i.e., same name, different features), or new photos (i.e., items not previously seen in scanner). For Americans compared to East Asians, we predicted greater activation in the hippocampus and right fusiform for specific memory at recognition, as these regions were implicated previously in encoding perceptual details. Results revealed that East Asians activated the left fusiform and left hippocampus more than Americans for specific versus general memory. Follow-up analyses ruled out alternative explanations of retrieval difficulty and familiarity for this pattern of cross-cultural differences at encoding. Results overall suggest that culture should be considered as another individual difference that affects memory specificity and modulates neural regions underlying these processes. Copyright © 2017 Elsevier Ltd. All rights reserved.

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

Directory of Open Access Journals (Sweden)

Francisco Javier Ordóñez

2016-01-01

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

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

Science.gov (United States)

Ordóñez, Francisco Javier; Roggen, Daniel

2016-01-18

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

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

Science.gov (United States)

Ordóñez, Francisco Javier; Roggen, Daniel

2016-01-01

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

Dissecting Repulsive Guidance Molecule/Neogenin function and signaling during neural development

NARCIS (Netherlands)

van den Heuvel, D.M.A.

2013-01-01

During neural development a series of precisely ordered cellular processes acts to establish a functional brain comprising millions of neurons and many more neuronal connections. Neogenin and its repulsive guidance molecule (RGM) ligands contribute to neuronal network formation by inducing axon

The image recognition based on neural network and Bayesian decision

Science.gov (United States)

Wang, Chugege

2018-04-01

The artificial neural network began in 1940, which is an important part of artificial intelligence. At present, it has become a hot topic in the fields of neuroscience, computer science, brain science, mathematics, and psychology. Thomas Bayes firstly reported the Bayesian theory in 1763. After the development in the twentieth century, it has been widespread in all areas of statistics. In recent years, due to the solution of the problem of high-dimensional integral calculation, Bayesian Statistics has been improved theoretically, which solved many problems that cannot be solved by classical statistics and is also applied to the interdisciplinary fields. In this paper, the related concepts and principles of the artificial neural network are introduced. It also summarizes the basic content and principle of Bayesian Statistics, and combines the artificial neural network technology and Bayesian decision theory and implement them in all aspects of image recognition, such as enhanced face detection method based on neural network and Bayesian decision, as well as the image classification based on the Bayesian decision. It can be seen that the combination of artificial intelligence and statistical algorithms has always been the hot research topic.

The nuclear fuel rod character recognition system based on neural network technique

International Nuclear Information System (INIS)

Kim, Woong-Ki; Park, Soon-Yong; Lee, Yong-Bum; Kim, Seung-Ho; Lee, Jong-Min; Chien, Sung-Il.

1994-01-01

The nuclear fuel rods should be discriminated and managed systematically by numeric characters which are printed at the end part of each rod in the process of producing fuel assembly. The characters are used to examine manufacturing process of the fuel rods in the inspection process of irradiated fuel rod. Therefore automatic character recognition is one of the most important technologies to establish automatic manufacturing process of fuel assembly. In the developed character recognition system, mesh feature set extracted from each character written in the fuel rod is employed to train a neural network based on back-propagation algorithm as a classifier for character recognition system. Performance evaluation has been achieved on a test set which is not included in a training character set. (author)

Neural activity during emotion recognition after combined cognitive plus social-cognitive training in schizophrenia

Science.gov (United States)

Hooker, Christine I.; Bruce, Lori; Fisher, Melissa; Verosky, Sara C.; Miyakawa, Asako; Vinogradov, Sophia

2012-01-01

Cognitive remediation training has been shown to improve both cognitive and social-cognitive deficits in people with schizophrenia, but the mechanisms that support this behavioral improvement are largely unknown. One hypothesis is that intensive behavioral training in cognition and/or social-cognition restores the underlying neural mechanisms that support targeted skills. However, there is little research on the neural effects of cognitive remediation training. This study investigated whether a 50 hour (10-week) remediation intervention which included both cognitive and social-cognitive training would influence neural function in regions that support social-cognition. Twenty-two stable, outpatient schizophrenia participants were randomized to a treatment condition consisting of auditory-based cognitive training (AT) [Brain Fitness Program/auditory module ~60 minutes/day] plus social-cognition training (SCT) which was focused on emotion recognition [~5–15 minutes per day] or a placebo condition of non-specific computer games (CG) for an equal amount of time. Pre and post intervention assessments included an fMRI task of positive and negative facial emotion recognition, and standard behavioral assessments of cognition, emotion processing, and functional outcome. There were no significant intervention-related improvements in general cognition or functional outcome. FMRI results showed the predicted group-by-time interaction. Specifically, in comparison to CG, AT+SCT participants had a greater pre-to-post intervention increase in postcentral gyrus activity during emotion recognition of both positive and negative emotions. Furthermore, among all participants, the increase in postcentral gyrus activity predicted behavioral improvement on a standardized test of emotion processing (MSCEIT: Perceiving Emotions). Results indicate that combined cognition and social-cognition training impacts neural mechanisms that support social-cognition skills. PMID:22695257

FPGA IMPLEMENTATION OF ADAPTIVE INTEGRATED SPIKING NEURAL NETWORK FOR EFFICIENT IMAGE RECOGNITION SYSTEM

Directory of Open Access Journals (Sweden)

T. Pasupathi

2014-05-01

Full Text Available Image recognition is a technology which can be used in various applications such as medical image recognition systems, security, defense video tracking, and factory automation. In this paper we present a novel pipelined architecture of an adaptive integrated Artificial Neural Network for image recognition. In our proposed work we have combined the feature of spiking neuron concept with ANN to achieve the efficient architecture for image recognition. The set of training images are trained by ANN and target output has been identified. Real time videos are captured and then converted into frames for testing purpose and the image were recognized. The machine can operate at up to 40 frames/sec using images acquired from the camera. The system has been implemented on XC3S400 SPARTAN-3 Field Programmable Gate Arrays.

Comparison of eye imaging pattern recognition using neural network

Science.gov (United States)

Bukhari, W. M.; Syed A., M.; Nasir, M. N. M.; Sulaima, M. F.; Yahaya, M. S.

2015-05-01

The beauty of eye recognition system that it is used in automatic identifying and verifies a human weather from digital images or video source. There are various behaviors of the eye such as the color of the iris, size of pupil and shape of the eye. This study represents the analysis, design and implementation of a system for recognition of eye imaging. All the eye images that had been captured from the webcam in RGB format must through several techniques before it can be input for the pattern and recognition processes. The result shows that the final value of weight and bias after complete training 6 eye images for one subject is memorized by the neural network system and be the reference value of the weight and bias for the testing part. The target classifies to 5 different types for 5 subjects. The eye images can recognize the subject based on the target that had been set earlier during the training process. When the values between new eye image and the eye image in the database are almost equal, it is considered the eye image is matched.

Neural mechanisms of individual and sexual recognition in Syrian hamsters (Mesocricetus auratus).

Science.gov (United States)

Petrulis, Aras

2009-06-25

Recognizing the individual and sexual identities of conspecifics is critical for adaptive social behavior and, in most mammals this information is communicated primarily by chemosensory cues. Due to its heavy reliance on odor cues, we have used the Syrian hamster as our model species for investigating the neural regulation of social recognition. Using lesion, electrophysiological and immunocytochemical techniques, separate neural pathways underlying recognition of individual odors and guidance of sex-typical responses to opposite-sex odors have been identified in both male and female hamsters. Specifically, we have found that recognition of individual odor identity requires olfactory bulb connections to entorhinal cortex (ENT) rather than other chemoreceptive brain regions. This kind of social memory does not appear to require the hippocampus and may, instead, depend on ENT connections with piriform cortex. In contrast, sexual recognition, through either differential investigation or scent marking toward opposite-sex odors, depends on both olfactory and vomeronasal system input to the corticomedial amygdala. Preference for investigating opposite-sex odors requires primarily olfactory input to the medial amygdala (ME) whereas appropriately targeted scent marking responses require vomeronasal input to ME as well as to other structures. Within the ME, the anterior section (MEa) appears important for evaluating or classifying social odors whereas the posterodorsal region (MEpd) may be more involved in generating approach to social odors. Evidence is presented that analysis of social odors may initially be done in MEa and then communicated to MEpd, perhaps through micro-circuits that separately process male and female odors.

Optical implementation of a feature-based neural network with application to automatic target recognition

Science.gov (United States)

Chao, Tien-Hsin; Stoner, William W.

1993-01-01

An optical neural network based on the neocognitron paradigm is introduced. A novel aspect of the architecture design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by feeding back the ouput of the feature correlator interatively to the input spatial light modulator and by updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intraclass fault tolerance and interclass discrimination is achieved. A detailed system description is provided. Experimental demonstrations of a two-layer neural network for space-object discrimination is also presented.

Basic perceptual changes that alter meaning and neural correlates of recognition memory

Directory of Open Access Journals (Sweden)

Chuanji eGao

2015-02-01

Full Text Available It is difficult to pinpoint the border between perceptual and conceptual processing, despite their treatment as distinct entities in many studies of recognition memory. For instance, alteration of simple perceptual characteristics of a stimulus can radically change meaning, such as the color of bread changing from white to green. We sought to better understand the role of perceptual and conceptual processing in memory by identifying the effects of changing a basic perceptual feature (color on behavioral and neural correlates of memory in circumstances when this change would be expected to either change the meaning of a stimulus or to have no effect on meaning (i.e., to influence conceptual processing or not. Abstract visual shapes (squiggles were colorized during study and presented during test in either the same color or a different color. Those squiggles that subjects found to resemble meaningful objects supported behavioral measures of conceptual priming, whereas meaningless squiggles did not. Further, changing color from study to test had a selective effect on behavioral correlates of priming for meaningful squiggles, indicating that color change altered conceptual processing. During a recognition memory test, color change altered event-related brain potential correlates of memory for meaningful squiggles but not for meaningless squiggles. Specifically, color change reduced the amplitude of frontally distributed N400 potentials (FN400, indicating that these potentials indicated conceptual processing during recognition memory that was sensitive to color change. In contrast, color change had no effect on FN400 correlates of recognition for meaningless squiggles, which were overall smaller in amplitude than for meaningful squiggles (further indicating that these potentials signal conceptual processing during recognition. Thus, merely changing the color of abstract visual shapes can alter their meaning, changing behavioral and neural correlates

Fuzzy-cellular neural network for face recognition HCI Authentication

Science.gov (United States)

Hoomod, Haider K.; ali, Ahmed abd

2018-05-01

Because of the rapid development of mobile devices technology, ease of use and interact with humans. May have found a mobile device most uses in our communications. Mobile devices can carry large amounts of personal and sensitive data, but often left not guaranteed (pin) locks are inconvenient to use and thus have seen low adoption while biometrics is more convenient and less susceptible to fraud and manipulation. Were propose in this paper authentication technique for using a mobile face recognition based on cellular neural networks [1] and fuzzy rules control. The good speed and get recognition rate from applied the proposed system in Android system. The images obtained in real time for 60 persons each person has 20 t0 60 different shot face images (about 3600 images), were the results for (FAR = 0), (FRR = 1.66%), (FER = 1.66) and accuracy = 98.34

Emmprin (basigin/CD147): matrix metalloproteinase modulator and multifunctional cell recognition molecule that plays a critical role in cancer progression.

Science.gov (United States)

Nabeshima, Kazuki; Iwasaki, Hiroshi; Koga, Kaori; Hojo, Hironobu; Suzumiya, Junji; Kikuchi, Masahiro

2006-07-01

Emmprin (basigin, CD147) is a cell surface glycoprotein that belongs to the immunoglobulin superfamily. It is highly expressed on the surface of tumor cells and stimulates adjacent fibroblasts or tumor cells to produce matrix metalloproteinases. Moreover, it has recently been shown that emmprin also stimulates expression of vascular endothelial growth factor and hyaluronan, which leads to angiogenesis and anchorage-independent growth/multidrug resistance, respectively. These findings have made emmprin an important molecule in tumor progression and, thus, more attractive as a target for antitumor treatment. However, other functions of emmprin, including as an activator of T cells, a chaperone for monocarboxylate transporters, a receptor for cyclophilin A and a neural recognition molecule, are also being identified in physiological and pathological conditions. Therefore, it is essential to develop specific means to control particular functions of emmprin, for which elucidation of each mechanism is crucial. This review will discuss the role of emmprin in tumor progression and recent advances in the molecular mechanisms of diverse phenomena regulated by emmprin.

Designing a Pattern Recognition Neural Network with a Reject Output and Many Sets of Weights and Biases

OpenAIRE

Dung, Le; Mizukawa, Makoto

2008-01-01

Adding the reject output to the pattern recognition neural network is an approach to help the neural network can classify almost all patterns of a training data set by using many sets of weights and biases, even if the neural network is small. With a smaller number of neurons, we can implement the neural network on a hardware-based platform more easily and also reduce the response time of it. With the reject output the neural network can produce not only right or wrong results but also reject...

Definition of new 3D invariants. Applications to pattern recognition problems with neural networks

International Nuclear Information System (INIS)

Proriol, J.

1996-01-01

We propose a definition of new 3D invariants. Usual pattern recognition methods use 2D descriptions of 3D objects, we propose a 2D approximation of the defined 3D invariants which can be used with neural networks to solve pattern recognition problems. We describe some methods to use the 2 D approximants. This work is an extension of previous 3D invariants used to solve some high energy physics problems. (author)

Contributions of feature shapes and surface cues to the recognition and neural representation of facial identity.

Science.gov (United States)

Andrews, Timothy J; Baseler, Heidi; Jenkins, Rob; Burton, A Mike; Young, Andrew W

2016-10-01

A full understanding of face recognition will involve identifying the visual information that is used to discriminate different identities and how this is represented in the brain. The aim of this study was to explore the importance of shape and surface properties in the recognition and neural representation of familiar faces. We used image morphing techniques to generate hybrid faces that mixed shape properties (more specifically, second order spatial configural information as defined by feature positions in the 2D-image) from one identity and surface properties from a different identity. Behavioural responses showed that recognition and matching of these hybrid faces was primarily based on their surface properties. These behavioural findings contrasted with neural responses recorded using a block design fMRI adaptation paradigm to test the sensitivity of Haxby et al.'s (2000) core face-selective regions in the human brain to the shape or surface properties of the face. The fusiform face area (FFA) and occipital face area (OFA) showed a lower response (adaptation) to repeated images of the same face (same shape, same surface) compared to different faces (different shapes, different surfaces). From the behavioural data indicating the critical contribution of surface properties to the recognition of identity, we predicted that brain regions responsible for familiar face recognition should continue to adapt to faces that vary in shape but not surface properties, but show a release from adaptation to faces that vary in surface properties but not shape. However, we found that the FFA and OFA showed an equivalent release from adaptation to changes in both shape and surface properties. The dissociation between the neural and perceptual responses suggests that, although they may play a role in the process, these core face regions are not solely responsible for the recognition of facial identity. Copyright © 2016 Elsevier Ltd. All rights reserved.

Review of Data Preprocessing Methods for Sign Language Recognition Systems based on Artificial Neural Networks

Directory of Open Access Journals (Sweden)

Zorins Aleksejs

2016-12-01

Full Text Available The article presents an introductory analysis of relevant research topic for Latvian deaf society, which is the development of the Latvian Sign Language Recognition System. More specifically the data preprocessing methods are discussed in the paper and several approaches are shown with a focus on systems based on artificial neural networks, which are one of the most successful solutions for sign language recognition task.

Complement activating soluble pattern recognition molecules with collagen-like regions, mannan-binding lectin, ficolins and associated proteins

DEFF Research Database (Denmark)

Thiel, Steffen

2007-01-01

Mannan-binding lectin (MBL), L-ficolin, M-ficolin and H-ficolin are all complement activating soluble pattern recognition molecules with recognition domains linked to collagen-like regions. All four may form complexes with four structurally related proteins, the three MBL-associated serine...... proteases (MASPs), MASP-1, MASP-2 and MASP-3, and a smaller MBL-associated protein (MAp19). The four recognition molecules recognize patterns of carbohydrate or acetyl-group containing ligands. After binding to the relevant targets all four are able to activate the complement system. We thus have a system...... where four different and/or overlapping patterns of microbial origin or patterns of altered-self may be recognized, but in all cases the signalling molecules, the MASPs, are shared. MASP-1 and MASP-3 are formed from one gene, MASP1/3, by alternative splicing generating two different mRNAs from a single...

Neural activity during emotion recognition after combined cognitive plus social cognitive training in schizophrenia.

Science.gov (United States)

Hooker, Christine I; Bruce, Lori; Fisher, Melissa; Verosky, Sara C; Miyakawa, Asako; Vinogradov, Sophia

2012-08-01

Cognitive remediation training has been shown to improve both cognitive and social cognitive deficits in people with schizophrenia, but the mechanisms that support this behavioral improvement are largely unknown. One hypothesis is that intensive behavioral training in cognition and/or social cognition restores the underlying neural mechanisms that support targeted skills. However, there is little research on the neural effects of cognitive remediation training. This study investigated whether a 50 h (10-week) remediation intervention which included both cognitive and social cognitive training would influence neural function in regions that support social cognition. Twenty-two stable, outpatient schizophrenia participants were randomized to a treatment condition consisting of auditory-based cognitive training (AT) [Brain Fitness Program/auditory module ~60 min/day] plus social cognition training (SCT) which was focused on emotion recognition [~5-15 min per day] or a placebo condition of non-specific computer games (CG) for an equal amount of time. Pre and post intervention assessments included an fMRI task of positive and negative facial emotion recognition, and standard behavioral assessments of cognition, emotion processing, and functional outcome. There were no significant intervention-related improvements in general cognition or functional outcome. fMRI results showed the predicted group-by-time interaction. Specifically, in comparison to CG, AT+SCT participants had a greater pre-to-post intervention increase in postcentral gyrus activity during emotion recognition of both positive and negative emotions. Furthermore, among all participants, the increase in postcentral gyrus activity predicted behavioral improvement on a standardized test of emotion processing (MSCEIT: Perceiving Emotions). Results indicate that combined cognition and social cognition training impacts neural mechanisms that support social cognition skills. Copyright © 2012 Elsevier B.V. All

Image Classification Using Biomimetic Pattern Recognition with Convolutional Neural Networks Features

Science.gov (United States)

Huo, Guanying

2017-01-01

As a typical deep-learning model, Convolutional Neural Networks (CNNs) can be exploited to automatically extract features from images using the hierarchical structure inspired by mammalian visual system. For image classification tasks, traditional CNN models employ the softmax function for classification. However, owing to the limited capacity of the softmax function, there are some shortcomings of traditional CNN models in image classification. To deal with this problem, a new method combining Biomimetic Pattern Recognition (BPR) with CNNs is proposed for image classification. BPR performs class recognition by a union of geometrical cover sets in a high-dimensional feature space and therefore can overcome some disadvantages of traditional pattern recognition. The proposed method is evaluated on three famous image classification benchmarks, that is, MNIST, AR, and CIFAR-10. The classification accuracies of the proposed method for the three datasets are 99.01%, 98.40%, and 87.11%, respectively, which are much higher in comparison with the other four methods in most cases. PMID:28316614

Assay for the pattern recognition molecule collectin liver 1 (CL-L1)

DEFF Research Database (Denmark)

Axelgaard, Esben; Jensenius, Jens Christian; Thiel, Steffen

Collectin liver 1 (also termed collectin 10 and CL-L1) is a C-type lectin that functions as a pattern recognition molecule (PRM) in the innate immune system1. We have produced antibodies against CL-L1 and have developed a sandwich-type time-resolved immuno-fluorometric assay (TRIFMA...... to co-purify with MASPs, possibly rendering it a role in complement. CL-L1 showed binding activity towards mannose-TSK beads in a Ca2+-dependent manner. This binding could be inhibited by mannose and glucose, but not by galactose, indicating that CL-L1 binds via its carbohydrate-recognition domain (CRD)....

Automatic Pavement Crack Recognition Based on BP Neural Network

Directory of Open Access Journals (Sweden)

Li Li

2014-02-01

Full Text Available A feasible pavement crack detection system plays an important role in evaluating the road condition and providing the necessary road maintenance. In this paper, a back propagation neural network (BPNN is used to recognize pavement cracks from images. To improve the recognition accuracy of the BPNN, a complete framework of image processing is proposed including image preprocessing and crack information extraction. In this framework, the redundant image information is reduced as much as possible and two sets of feature parameters are constructed to classify the crack images. Then a BPNN is adopted to distinguish pavement images between linear and alligator cracks to acquire high recognition accuracy. Besides, the linear cracks can be further classified into transversal and longitudinal cracks according to the direction angle. Finally, the proposed method is evaluated on the data of 400 pavement images obtained by the Automatic Road Analyzer (ARAN in Northern China and the results show that the proposed method seems to be a powerful tool for pavement crack recognition. The rates of correct classification for alligator, transversal and longitudinal cracks are 97.5%, 100% and 88.0%, respectively. Compared to some previous studies, the method proposed in this paper is effective for all three kinds of cracks and the results are also acceptable for engineering application.

Higher-Order Neural Networks Applied to 2D and 3D Object Recognition

Science.gov (United States)

Spirkovska, Lilly; Reid, Max B.

1994-01-01

A Higher-Order Neural Network (HONN) can be designed to be invariant to geometric transformations such as scale, translation, and in-plane rotation. Invariances are built directly into the architecture of a HONN and do not need to be learned. Thus, for 2D object recognition, the network needs to be trained on just one view of each object class, not numerous scaled, translated, and rotated views. Because the 2D object recognition task is a component of the 3D object recognition task, built-in 2D invariance also decreases the size of the training set required for 3D object recognition. We present results for 2D object recognition both in simulation and within a robotic vision experiment and for 3D object recognition in simulation. We also compare our method to other approaches and show that HONNs have distinct advantages for position, scale, and rotation-invariant object recognition. The major drawback of HONNs is that the size of the input field is limited due to the memory required for the large number of interconnections in a fully connected network. We present partial connectivity strategies and a coarse-coding technique for overcoming this limitation and increasing the input field to that required by practical object recognition problems.

Chinese Herbal Medicine Image Recognition and Retrieval by Convolutional Neural Network.

Science.gov (United States)

Sun, Xin; Qian, Huinan

2016-01-01

Chinese herbal medicine image recognition and retrieval have great potential of practical applications. Several previous studies have focused on the recognition with hand-crafted image features, but there are two limitations in them. Firstly, most of these hand-crafted features are low-level image representation, which is easily affected by noise and background. Secondly, the medicine images are very clean without any backgrounds, which makes it difficult to use in practical applications. Therefore, designing high-level image representation for recognition and retrieval in real world medicine images is facing a great challenge. Inspired by the recent progress of deep learning in computer vision, we realize that deep learning methods may provide robust medicine image representation. In this paper, we propose to use the Convolutional Neural Network (CNN) for Chinese herbal medicine image recognition and retrieval. For the recognition problem, we use the softmax loss to optimize the recognition network; then for the retrieval problem, we fine-tune the recognition network by adding a triplet loss to search for the most similar medicine images. To evaluate our method, we construct a public database of herbal medicine images with cluttered backgrounds, which has in total 5523 images with 95 popular Chinese medicine categories. Experimental results show that our method can achieve the average recognition precision of 71% and the average retrieval precision of 53% over all the 95 medicine categories, which are quite promising given the fact that the real world images have multiple pieces of occluded herbal and cluttered backgrounds. Besides, our proposed method achieves the state-of-the-art performance by improving previous studies with a large margin.

Logarithmic r-θ mapping for hybrid optical neural network filter for multiple objects recognition within cluttered scenes

Science.gov (United States)

Kypraios, Ioannis; Young, Rupert C. D.; Chatwin, Chris R.; Birch, Phil M.

2009-04-01

θThe window unit in the design of the complex logarithmic r-θ mapping for hybrid optical neural network filter can allow multiple objects of the same class to be detected within the input image. Additionally, the architecture of the neural network unit of the complex logarithmic r-θ mapping for hybrid optical neural network filter becomes attractive for accommodating the recognition of multiple objects of different classes within the input image by modifying the output layer of the unit. We test the overall filter for multiple objects of the same and of different classes' recognition within cluttered input images and video sequences of cluttered scenes. Logarithmic r-θ mapping for hybrid optical neural network filter is shown to exhibit with a single pass over the input data simultaneously in-plane rotation, out-of-plane rotation, scale, log r-θ map translation and shift invariance, and good clutter tolerance by recognizing correctly the different objects within the cluttered scenes. We record in our results additional extracted information from the cluttered scenes about the objects' relative position, scale and in-plane rotation.

IMPLEMENTATION OF ARTIFICIAL NEURAL NETWORK FOR FACE RECOGNITION USING GABOR FEATURE EXTRACTION

Directory of Open Access Journals (Sweden)

Muthukannan K

2013-11-01

Full Text Available Face detection and recognition is the first step for many applications in various fields such as identification and is used as a key to enter into the various electronic devices, video surveillance, and human computer interface and image database management. This paper focuses on feature extraction in an image using Gabor filter and the extracted image feature vector is then given as an input to the neural network. The neural network is trained with the input data. The Gabor wavelet concentrates on the important components of the face including eye, mouth, nose, cheeks. The main requirement of this technique is the threshold, which gives privileged sensitivity. The threshold values are the feature vectors taken from the faces. These feature vectors are given into the feed forward neural network to train the network. Using the feed forward neural network as a classifier, the recognized and unrecognized faces are classified. This classifier attains a higher face deduction rate. By training more input vectors the system proves to be effective. The effectiveness of the proposed method is demonstrated by the experimental results.

Global Neural Pattern Similarity as a Common Basis for Categorization and Recognition Memory

Science.gov (United States)

Xue, Gui; Love, Bradley C.; Preston, Alison R.; Poldrack, Russell A.

2014-01-01

Familiarity, or memory strength, is a central construct in models of cognition. In previous categorization and long-term memory research, correlations have been found between psychological measures of memory strength and activation in the medial temporal lobes (MTLs), which suggests a common neural locus for memory strength. However, activation alone is insufficient for determining whether the same mechanisms underlie neural function across domains. Guided by mathematical models of categorization and long-term memory, we develop a theory and a method to test whether memory strength arises from the global similarity among neural representations. In human subjects, we find significant correlations between global similarity among activation patterns in the MTLs and both subsequent memory confidence in a recognition memory task and model-based measures of memory strength in a category learning task. Our work bridges formal cognitive theories and neuroscientific models by illustrating that the same global similarity computations underlie processing in multiple cognitive domains. Moreover, by establishing a link between neural similarity and psychological memory strength, our findings suggest that there may be an isomorphism between psychological and neural representational spaces that can be exploited to test cognitive theories at both the neural and behavioral levels. PMID:24872552

Development of Filtered Bispectrum for EEG Signal Feature Extraction in Automatic Emotion Recognition Using Artificial Neural Networks

Directory of Open Access Journals (Sweden)

Prima Dewi Purnamasari

2017-05-01

Full Text Available The development of automatic emotion detection systems has recently gained significant attention due to the growing possibility of their implementation in several applications, including affective computing and various fields within biomedical engineering. Use of the electroencephalograph (EEG signal is preferred over facial expression, as people cannot control the EEG signal generated by their brain; the EEG ensures a stronger reliability in the psychological signal. However, because of its uniqueness between individuals and its vulnerability to noise, use of EEG signals can be rather complicated. In this paper, we propose a methodology to conduct EEG-based emotion recognition by using a filtered bispectrum as the feature extraction subsystem and an artificial neural network (ANN as the classifier. The bispectrum is theoretically superior to the power spectrum because it can identify phase coupling between the nonlinear process components of the EEG signal. In the feature extraction process, to extract the information contained in the bispectrum matrices, a 3D pyramid filter is used for sampling and quantifying the bispectrum value. Experiment results show that the mean percentage of the bispectrum value from 5 × 5 non-overlapped 3D pyramid filters produces the highest recognition rate. We found that reducing the number of EEG channels down to only eight in the frontal area of the brain does not significantly affect the recognition rate, and the number of data samples used in the training process is then increased to improve the recognition rate of the system. We have also utilized a probabilistic neural network (PNN as another classifier and compared its recognition rate with that of the back-propagation neural network (BPNN, and the results show that the PNN produces a comparable recognition rate and lower computational costs. Our research shows that the extracted bispectrum values of an EEG signal using 3D filtering as a feature extraction

Handwritten Sindhi Character Recognition Using Neural Networks

Directory of Open Access Journals (Sweden)

Shafique Ahmed Awan

2018-01-01

Full Text Available OCR (OpticalCharacter Recognition is a technology in which text image is used to understand and write text by machines. The work on languages containing isolated characters such as German, English, French and others is at its peak. The OCR and ICR (Intelligent Character Recognition research in Sindhi script is currently at in starting stages and not sufficient work have been cited in this area even though Sindhi language is rich in culture and history. This paper presents one of the initial steps in recognizing Sindhi handwritten characters. The isolated characters of Sindhi script written by thesubjects have been recognized. The various subjects were asked to write Sindhi characters in unconstrained form and then the written samples were collected and scanned through a flatbed scanner. The scanned documents were preprocessedwith the help of binary conversion, removing noise by pepper noise and the lines were segmented with the help of horizontal profile technique. The segmented lines were used to extract characters from scanned pages.This character segmentation was done by vertical projection. The extracted characters have been used to extract features so that the characters can be classified easily. Zoning was used for the feature extraction technique. For the classification, neural network has been used. The recognized characters converted into editable text with an average accuracy of 85%.

HONTIOR - HIGHER-ORDER NEURAL NETWORK FOR TRANSFORMATION INVARIANT OBJECT RECOGNITION

Science.gov (United States)

Spirkovska, L.

1994-01-01

Neural networks have been applied in numerous fields, including transformation invariant object recognition, wherein an object is recognized despite changes in the object's position in the input field, size, or rotation. One of the more successful neural network methods used in invariant object recognition is the higher-order neural network (HONN) method. With a HONN, known relationships are exploited and the desired invariances are built directly into the architecture of the network, eliminating the need for the network to learn invariance to transformations. This results in a significant reduction in the training time required, since the network needs to be trained on only one view of each object, not on numerous transformed views. Moreover, one hundred percent accuracy is guaranteed for images characterized by the built-in distortions, providing noise is not introduced through pixelation. The program HONTIOR implements a third-order neural network having invariance to translation, scale, and in-plane rotation built directly into the architecture, Thus, for 2-D transformation invariance, the network needs only to be trained on just one view of each object. HONTIOR can also be used for 3-D transformation invariant object recognition by training the network only on a set of out-of-plane rotated views. Historically, the major drawback of HONNs has been that the size of the input field was limited to the memory required for the large number of interconnections in a fully connected network. HONTIOR solves this problem by coarse coding the input images (coding an image as a set of overlapping but offset coarser images). Using this scheme, large input fields (4096 x 4096 pixels) can easily be represented using very little virtual memory (30Mb). The HONTIOR distribution consists of three main programs. The first program contains the training and testing routines for a third-order neural network. The second program contains the same training and testing procedures as the

Classification of remotely sensed data using OCR-inspired neural network techniques. [Optical Character Recognition

Science.gov (United States)

Kiang, Richard K.

1992-01-01

Neural networks have been applied to classifications of remotely sensed data with some success. To improve the performance of this approach, an examination was made of how neural networks are applied to the optical character recognition (OCR) of handwritten digits and letters. A three-layer, feedforward network, along with techniques adopted from OCR, was used to classify Landsat-4 Thematic Mapper data. Good results were obtained. To overcome the difficulties that are characteristic of remote sensing applications and to attain significant improvements in classification accuracy, a special network architecture may be required.

An fMRI comparison of neural activity associated with recognition of familiar melodies in younger and older adults.

Science.gov (United States)

Sikka, Ritu; Cuddy, Lola L; Johnsrude, Ingrid S; Vanstone, Ashley D

2015-01-01

Several studies of semantic memory in non-musical domains involving recognition of items from long-term memory have shown an age-related shift from the medial temporal lobe structures to the frontal lobe. However, the effects of aging on musical semantic memory remain unexamined. We compared activation associated with recognition of familiar melodies in younger and older adults. Recognition follows successful retrieval from the musical lexicon that comprises a lifetime of learned musical phrases. We used the sparse-sampling technique in fMRI to determine the neural correlates of melody recognition by comparing activation when listening to familiar vs. unfamiliar melodies, and to identify age differences. Recognition-related cortical activation was detected in the right superior temporal, bilateral inferior and superior frontal, left middle orbitofrontal, bilateral precentral, and left supramarginal gyri. Region-of-interest analysis showed greater activation for younger adults in the left superior temporal gyrus and for older adults in the left superior frontal, left angular, and bilateral superior parietal regions. Our study provides powerful evidence for these musical memory networks due to a large sample (N = 40) that includes older adults. This study is the first to investigate the neural basis of melody recognition in older adults and to compare the findings to younger adults.

An fMRI comparison of neural activity associated with recognition of familiar melodies in younger and older adults

Directory of Open Access Journals (Sweden)

Ritu eSikka

2015-10-01

Full Text Available Several studies of semantic memory in non-musical domains involving recognition of items from long-term memory have shown an age-related shift from the medial temporal lobe structures to the frontal lobe. However, the effects of aging on musical semantic memory remain unexamined. We compared activation associated with recognition of familiar melodies in younger and older adults. Recognition follows successful retrieval from the musical lexicon that comprises a lifetime of learned musical phrases. We used the sparse-sampling technique in fMRI to determine the neural correlates of melody recognition by comparing activation when listening to familiar versus unfamiliar melodies, and to identify age differences. Recognition-related cortical activation was detected in the right superior temporal, bilateral inferior and superior frontal, left middle orbitofrontal, bilateral precentral, and left supramarginal gyri. Region-of-interest analysis showed greater activation for younger adults in the left superior temporal gyrus and for older adults in the left superior frontal, left angular, and bilateral superior parietal regions. Our study provides powerful evidence for these musical memory networks due to a large sample (N = 40 that includes older adults. This study is the first to investigate the neural basis of melody recognition in older adults and to compare the findings to younger adults.

Neural Network Based Recognition of Signal Patterns in Application to Automatic Testing of Rails

Directory of Open Access Journals (Sweden)

Tomasz Ciszewski

2006-01-01

Full Text Available The paper describes the application of neural network for recognition of signal patterns in measuring data gathered by the railroad ultrasound testing car. Digital conversion of the measuring signal allows to store and process large quantities of data. The elaboration of smart, effective and automatic procedures recognizing the obtained patterns on the basisof measured signal amplitude has been presented. The test shows only two classes of pattern recognition. In authors’ opinion if we deliver big enough quantity of training data, presented method is applicable to a system that recognizes many classes.

Character-level neural network for biomedical named entity recognition.

Science.gov (United States)

Gridach, Mourad

2017-06-01

Biomedical named entity recognition (BNER), which extracts important named entities such as genes and proteins, is a challenging task in automated systems that mine knowledge in biomedical texts. The previous state-of-the-art systems required large amounts of task-specific knowledge in the form of feature engineering, lexicons and data pre-processing to achieve high performance. In this paper, we introduce a novel neural network architecture that benefits from both word- and character-level representations automatically, by using a combination of bidirectional long short-term memory (LSTM) and conditional random field (CRF) eliminating the need for most feature engineering tasks. We evaluate our system on two datasets: JNLPBA corpus and the BioCreAtIvE II Gene Mention (GM) corpus. We obtained state-of-the-art performance by outperforming the previous systems. To the best of our knowledge, we are the first to investigate the combination of deep neural networks, CRF, word embeddings and character-level representation in recognizing biomedical named entities. Copyright © 2017 Elsevier Inc. All rights reserved.

An Efficient Feature Extraction Method with Pseudo-Zernike Moment in RBF Neural Network-Based Human Face Recognition System

Directory of Open Access Journals (Sweden)

Ahmadi Majid

2003-01-01

Full Text Available This paper introduces a novel method for the recognition of human faces in digital images using a new feature extraction method that combines the global and local information in frontal view of facial images. Radial basis function (RBF neural network with a hybrid learning algorithm (HLA has been used as a classifier. The proposed feature extraction method includes human face localization derived from the shape information. An efficient distance measure as facial candidate threshold (FCT is defined to distinguish between face and nonface images. Pseudo-Zernike moment invariant (PZMI with an efficient method for selecting moment order has been used. A newly defined parameter named axis correction ratio (ACR of images for disregarding irrelevant information of face images is introduced. In this paper, the effect of these parameters in disregarding irrelevant information in recognition rate improvement is studied. Also we evaluate the effect of orders of PZMI in recognition rate of the proposed technique as well as RBF neural network learning speed. Simulation results on the face database of Olivetti Research Laboratory (ORL indicate that the proposed method for human face recognition yielded a recognition rate of 99.3%.

Mechanisms and Neural Basis of Object and Pattern Recognition: A Study with Chess Experts

Science.gov (United States)

Bilalic, Merim; Langner, Robert; Erb, Michael; Grodd, Wolfgang

2010-01-01

Comparing experts with novices offers unique insights into the functioning of cognition, based on the maximization of individual differences. Here we used this expertise approach to disentangle the mechanisms and neural basis behind two processes that contribute to everyday expertise: object and pattern recognition. We compared chess experts and…

Age-Related Cognitive Impairments in Mice with a Conditional Ablation of the Neural Cell Adhesion Molecule

Science.gov (United States)

Bisaz, Reto; Boadas-Vaello, Pere; Genoux, David; Sandi, Carmen

2013-01-01

Most of the mechanisms involved in neural plasticity support cognition, and aging has a considerable effect on some of these processes. The neural cell adhesion molecule (NCAM) of the immunoglobulin superfamily plays a pivotal role in structural and functional plasticity and is required to modulate cognitive and emotional behaviors. However,…

ALPHABET SIGN LANGUAGE RECOGNITION USING LEAP MOTION TECHNOLOGY AND RULE BASED BACKPROPAGATION-GENETIC ALGORITHM NEURAL NETWORK (RBBPGANN

Directory of Open Access Journals (Sweden)

Wijayanti Nurul Khotimah

2017-01-01

Full Text Available Sign Language recognition was used to help people with normal hearing communicate effectively with the deaf and hearing-impaired. Based on survey that conducted by Multi-Center Study in Southeast Asia, Indonesia was on the top four position in number of patients with hearing disability (4.6%. Therefore, the existence of Sign Language recognition is important. Some research has been conducted on this field. Many neural network types had been used for recognizing many kinds of sign languages. However, their performance are need to be improved. This work focuses on the ASL (Alphabet Sign Language in SIBI (Sign System of Indonesian Language which uses one hand and 26 gestures. Here, thirty four features were extracted by using Leap Motion. Further, a new method, Rule Based-Backpropagation Genetic Al-gorithm Neural Network (RB-BPGANN, was used to recognize these Sign Languages. This method is combination of Rule and Back Propagation Neural Network (BPGANN. Based on experiment this pro-posed application can recognize Sign Language up to 93.8% accuracy. It was very good to recognize large multiclass instance and can be solution of overfitting problem in Neural Network algorithm.

Behavioral and Physiological Neural Network Analyses: A Common Pathway toward Pattern Recognition and Prediction

Science.gov (United States)

Ninness, Chris; Lauter, Judy L.; Coffee, Michael; Clary, Logan; Kelly, Elizabeth; Rumph, Marilyn; Rumph, Robin; Kyle, Betty; Ninness, Sharon K.

2012-01-01

Using 3 diversified datasets, we explored the pattern-recognition ability of the Self-Organizing Map (SOM) artificial neural network as applied to diversified nonlinear data distributions in the areas of behavioral and physiological research. Experiment 1 employed a dataset obtained from the UCI Machine Learning Repository. Data for this study…

Subject independent facial expression recognition with robust face detection using a convolutional neural network.

Science.gov (United States)

Matsugu, Masakazu; Mori, Katsuhiko; Mitari, Yusuke; Kaneda, Yuji

2003-01-01

Reliable detection of ordinary facial expressions (e.g. smile) despite the variability among individuals as well as face appearance is an important step toward the realization of perceptual user interface with autonomous perception of persons. We describe a rule-based algorithm for robust facial expression recognition combined with robust face detection using a convolutional neural network. In this study, we address the problem of subject independence as well as translation, rotation, and scale invariance in the recognition of facial expression. The result shows reliable detection of smiles with recognition rate of 97.6% for 5600 still images of more than 10 subjects. The proposed algorithm demonstrated the ability to discriminate smiling from talking based on the saliency score obtained from voting visual cues. To the best of our knowledge, it is the first facial expression recognition model with the property of subject independence combined with robustness to variability in facial appearance.

Detection and recognition of bridge crack based on convolutional neural network

Directory of Open Access Journals (Sweden)

Honggong LIU

2016-10-01

Full Text Available Aiming at the backward artificial visual detection status of bridge crack in China, which has a great danger coefficient, a digital and intelligent detection method of improving the diagnostic efficiency and reducing the risk coefficient is studied. Combing with machine vision and convolutional neural network technology, Raspberry Pi is used to acquire and pre-process image, and the crack image is analyzed; the processing algorithm which has the best effect in detecting and recognizing is selected; the convolutional neural network(CNN for crack classification is optimized; finally, a new intelligent crack detection method is put forward. The experimental result shows that the system can find all cracks beyond the maximum limit, and effectively identify the type of fracture, and the recognition rate is above 90%. The study provides reference data for engineering detection.

Modeling the Process of Color Image Recognition Using ART2 Neural Network

Directory of Open Access Journals (Sweden)

Todor Petkov

2015-09-01

Full Text Available This paper thoroughly describes the use of unsupervised adaptive resonance theory ART2 neural network for the purposes of image color recognition of x-ray images and images taken by nuclear magnetic resonance. In order to train the network, the pixel values of RGB colors are regarded as learning vectors with three values, one for red, one for green and one for blue were used. At the end the trained network was tested by the values of pictures and determines the design, or how to visualize the converted picture. As a result we had the same pictures with colors according to the network. Here we use the generalized net to prepare a model that describes the process of the color image recognition.

The Improvement of Behavior Recognition Accuracy of Micro Inertial Accelerometer by Secondary Recognition Algorithm

Directory of Open Access Journals (Sweden)

Yu Liu

2014-05-01

Full Text Available Behaviors of “still”, “walking”, “running”, “jumping”, “upstairs” and “downstairs” can be recognized by micro inertial accelerometer of low cost. By using the features as inputs to the well-trained BP artificial neural network which is selected as classifier, those behaviors can be recognized. But the experimental results show that the recognition accuracy is not satisfactory. This paper presents secondary recognition algorithm and combine it with BP artificial neural network to improving the recognition accuracy. The Algorithm is verified by the Android mobile platform, and the recognition accuracy can be improved more than 8 %. Through extensive testing statistic analysis, the recognition accuracy can reach 95 % through BP artificial neural network and the secondary recognition, which is a reasonable good result from practical point of view.

Electronic single-molecule identification of carbohydrate isomers by recognition tunnelling

Science.gov (United States)

Im, Jongone; Biswas, Sovan; Liu, Hao; Zhao, Yanan; Sen, Suman; Biswas, Sudipta; Ashcroft, Brian; Borges, Chad; Wang, Xu; Lindsay, Stuart; Zhang, Peiming

2016-12-01

Carbohydrates are one of the four main building blocks of life, and are categorized as monosaccharides (sugars), oligosaccharides and polysaccharides. Each sugar can exist in two alternative anomers (in which a hydroxy group at C-1 takes different orientations) and each pair of sugars can form different epimers (isomers around the stereocentres connecting the sugars). This leads to a vast combinatorial complexity, intractable to mass spectrometry and requiring large amounts of sample for NMR characterization. Combining measurements of collision cross section with mass spectrometry (IM-MS) helps, but many isomers are still difficult to separate. Here, we show that recognition tunnelling (RT) can classify many anomers and epimers via the current fluctuations they produce when captured in a tunnel junction functionalized with recognition molecules. Most importantly, RT is a nanoscale technique utilizing sub-picomole quantities of analyte. If integrated into a nanopore, RT would provide a unique approach to sequencing linear polysaccharides.

PANP is a novel O-glycosylated PILR{alpha} ligand expressed in neural tissues

Energy Technology Data Exchange (ETDEWEB)

Kogure, Amane [Department of Immunochemistry, Research Institute for Microbial Diseases, Osaka University, Osaka 565-0871 (Japan); Laboratory of Immunochemistry, WPI Immunology Frontier Research Center, Osaka University, Osaka 565-0871 (Japan); Shiratori, Ikuo [Department of Immunochemistry, Research Institute for Microbial Diseases, Osaka University, Osaka 565-0871 (Japan); Wang, Jing [Department of Immunochemistry, Research Institute for Microbial Diseases, Osaka University, Osaka 565-0871 (Japan); Laboratory of Immunochemistry, WPI Immunology Frontier Research Center, Osaka University, Osaka 565-0871 (Japan); Lanier, Lewis L. [Department of Microbiology and Immunology and the Cancer Research Institute, University of California San Francisco, San Francisco, CA 94143 (United States); Arase, Hisashi, E-mail: arase@biken.osaka-u.ac.jp [Department of Immunochemistry, Research Institute for Microbial Diseases, Osaka University, Osaka 565-0871 (Japan); Laboratory of Immunochemistry, WPI Immunology Frontier Research Center, Osaka University, Osaka 565-0871 (Japan); JST CREST, Saitama 332-0012 (Japan)

2011-02-18

Research highlights: {yields} A Novel molecule, PANP, was identified to be a PILR{alpha} ligand. {yields} Sialylated O-glycan structures on PANP were required for PILR{alpha} recognition. {yields} Transcription of PANP was mainly observed in neural tissues. {yields} PANP seems to be involved in immune regulation as a ligand for PILR{alpha}. -- Abstract: PILR{alpha} is an immune inhibitory receptor possessing an immunoreceptor tyrosine-based inhibitory motif (ITIM) in its cytoplasmic domain enabling it to deliver inhibitory signals. Binding of PILR{alpha} to its ligand CD99 is involved in immune regulation; however, whether there are other PILR{alpha} ligands in addition to CD99 is not known. Here, we report that a novel molecule, PILR-associating neural protein (PANP), acts as an additional ligand for PILR{alpha}. Transcription of PANP was mainly observed in neural tissues. PILR{alpha}-Ig fusion protein bound cells transfected with PANP and the transfectants stimulated PILR{alpha} reporter cells. Specific O-glycan structures on PANP were found to be required for PILR recognition of this ligand. These results suggest that PANP is involved in immune regulation as a ligand of the PILR{alpha}.

An automatic system for Turkish word recognition using Discrete Wavelet Neural Network based on adaptive entropy

International Nuclear Information System (INIS)

Avci, E.

2007-01-01

In this paper, an automatic system is presented for word recognition using real Turkish word signals. This paper especially deals with combination of the feature extraction and classification from real Turkish word signals. A Discrete Wavelet Neural Network (DWNN) model is used, which consists of two layers: discrete wavelet layer and multi-layer perceptron. The discrete wavelet layer is used for adaptive feature extraction in the time-frequency domain and is composed of Discrete Wavelet Transform (DWT) and wavelet entropy. The multi-layer perceptron used for classification is a feed-forward neural network. The performance of the used system is evaluated by using noisy Turkish word signals. Test results showing the effectiveness of the proposed automatic system are presented in this paper. The rate of correct recognition is about 92.5% for the sample speech signals. (author)

Recognition of underground nuclear explosion and natural earthquake based on neural network

International Nuclear Information System (INIS)

Yang Hong; Jia Weimin

2000-01-01

Many features are extracted to improve the identified rate and reliability of underground nuclear explosion and natural earthquake. But how to synthesize these characters is the key of pattern recognition. Based on the improved Delta algorithm, features of underground nuclear explosion and natural earthquake are inputted into BP neural network, and friendship functions are constructed to identify the output values. The identified rate is up to 92.0%, which shows that: the way is feasible

Entity recognition from clinical texts via recurrent neural network.

Science.gov (United States)

Liu, Zengjian; Yang, Ming; Wang, Xiaolong; Chen, Qingcai; Tang, Buzhou; Wang, Zhe; Xu, Hua

2017-07-05

Entity recognition is one of the most primary steps for text analysis and has long attracted considerable attention from researchers. In the clinical domain, various types of entities, such as clinical entities and protected health information (PHI), widely exist in clinical texts. Recognizing these entities has become a hot topic in clinical natural language processing (NLP), and a large number of traditional machine learning methods, such as support vector machine and conditional random field, have been deployed to recognize entities from clinical texts in the past few years. In recent years, recurrent neural network (RNN), one of deep learning methods that has shown great potential on many problems including named entity recognition, also has been gradually used for entity recognition from clinical texts. In this paper, we comprehensively investigate the performance of LSTM (long-short term memory), a representative variant of RNN, on clinical entity recognition and protected health information recognition. The LSTM model consists of three layers: input layer - generates representation of each word of a sentence; LSTM layer - outputs another word representation sequence that captures the context information of each word in this sentence; Inference layer - makes tagging decisions according to the output of LSTM layer, that is, outputting a label sequence. Experiments conducted on corpora of the 2010, 2012 and 2014 i2b2 NLP challenges show that LSTM achieves highest micro-average F1-scores of 85.81% on the 2010 i2b2 medical concept extraction, 92.29% on the 2012 i2b2 clinical event detection, and 94.37% on the 2014 i2b2 de-identification, which is considerably competitive with other state-of-the-art systems. LSTM that requires no hand-crafted feature has great potential on entity recognition from clinical texts. It outperforms traditional machine learning methods that suffer from fussy feature engineering. A possible future direction is how to integrate knowledge

Taxon and trait recognition from digitized herbarium specimens using deep convolutional neural networks

KAUST Repository

Younis, Sohaib; Weiland, Claus; Hoehndorf, Robert; Dressler, Stefan; Hickler, Thomas; Seeger, Bernhard; Schmidt, Marco

2018-01-01

Herbaria worldwide are housing a treasure of hundreds of millions of herbarium specimens, which are increasingly being digitized and thereby more accessible to the scientific community. At the same time, deep-learning algorithms are rapidly improving pattern recognition from images and these techniques are more and more being applied to biological objects. In this study, we are using digital images of herbarium specimens in order to identify taxa and traits of these collection objects by applying convolutional neural networks (CNN). Images of the 1000 species most frequently documented by herbarium specimens on GBIF have been downloaded and combined with morphological trait data, preprocessed and divided into training and test datasets for species and trait recognition. Good performance in both domains suggests substantial potential of this approach for supporting taxonomy and natural history collection management. Trait recognition is also promising for applications in functional ecology.

Taxon and trait recognition from digitized herbarium specimens using deep convolutional neural networks

KAUST Repository

Younis, Sohaib

2018-03-13

Herbaria worldwide are housing a treasure of hundreds of millions of herbarium specimens, which are increasingly being digitized and thereby more accessible to the scientific community. At the same time, deep-learning algorithms are rapidly improving pattern recognition from images and these techniques are more and more being applied to biological objects. In this study, we are using digital images of herbarium specimens in order to identify taxa and traits of these collection objects by applying convolutional neural networks (CNN). Images of the 1000 species most frequently documented by herbarium specimens on GBIF have been downloaded and combined with morphological trait data, preprocessed and divided into training and test datasets for species and trait recognition. Good performance in both domains suggests substantial potential of this approach for supporting taxonomy and natural history collection management. Trait recognition is also promising for applications in functional ecology.

Convolutional Neural Networks for Human Activity Recognition Using Body-Worn Sensors

Directory of Open Access Journals (Sweden)

Fernando Moya Rueda

2018-05-01

Full Text Available Human activity recognition (HAR is a classification task for recognizing human movements. Methods of HAR are of great interest as they have become tools for measuring occurrences and durations of human actions, which are the basis of smart assistive technologies and manual processes analysis. Recently, deep neural networks have been deployed for HAR in the context of activities of daily living using multichannel time-series. These time-series are acquired from body-worn devices, which are composed of different types of sensors. The deep architectures process these measurements for finding basic and complex features in human corporal movements, and for classifying them into a set of human actions. As the devices are worn at different parts of the human body, we propose a novel deep neural network for HAR. This network handles sequence measurements from different body-worn devices separately. An evaluation of the architecture is performed on three datasets, the Oportunity, Pamap2, and an industrial dataset, outperforming the state-of-the-art. In addition, different network configurations will also be evaluated. We find that applying convolutions per sensor channel and per body-worn device improves the capabilities of convolutional neural network (CNNs.

Real-Time (Vision-Based) Road Sign Recognition Using an Artificial Neural Network

Science.gov (United States)

Islam, Kh Tohidul; Raj, Ram Gopal

2017-01-01

Road sign recognition is a driver support function that can be used to notify and warn the driver by showing the restrictions that may be effective on the current stretch of road. Examples for such regulations are ‘traffic light ahead’ or ‘pedestrian crossing’ indications. The present investigation targets the recognition of Malaysian road and traffic signs in real-time. Real-time video is taken by a digital camera from a moving vehicle and real world road signs are then extracted using vision-only information. The system is based on two stages, one performs the detection and another one is for recognition. In the first stage, a hybrid color segmentation algorithm has been developed and tested. In the second stage, an introduced robust custom feature extraction method is used for the first time in a road sign recognition approach. Finally, a multilayer artificial neural network (ANN) has been created to recognize and interpret various road signs. It is robust because it has been tested on both standard and non-standard road signs with significant recognition accuracy. This proposed system achieved an average of 99.90% accuracy with 99.90% of sensitivity, 99.90% of specificity, 99.90% of f-measure, and 0.001 of false positive rate (FPR) with 0.3 s computational time. This low FPR can increase the system stability and dependability in real-time applications. PMID:28406471

Real-Time (Vision-Based) Road Sign Recognition Using an Artificial Neural Network.

Science.gov (United States)

Islam, Kh Tohidul; Raj, Ram Gopal

2017-04-13

Road sign recognition is a driver support function that can be used to notify and warn the driver by showing the restrictions that may be effective on the current stretch of road. Examples for such regulations are 'traffic light ahead' or 'pedestrian crossing' indications. The present investigation targets the recognition of Malaysian road and traffic signs in real-time. Real-time video is taken by a digital camera from a moving vehicle and real world road signs are then extracted using vision-only information. The system is based on two stages, one performs the detection and another one is for recognition. In the first stage, a hybrid color segmentation algorithm has been developed and tested. In the second stage, an introduced robust custom feature extraction method is used for the first time in a road sign recognition approach. Finally, a multilayer artificial neural network (ANN) has been created to recognize and interpret various road signs. It is robust because it has been tested on both standard and non-standard road signs with significant recognition accuracy. This proposed system achieved an average of 99.90% accuracy with 99.90% of sensitivity, 99.90% of specificity, 99.90% of f-measure, and 0.001 of false positive rate (FPR) with 0.3 s computational time. This low FPR can increase the system stability and dependability in real-time applications.

Neural correlates of auditory recognition memory in primate lateral prefrontal cortex.

Science.gov (United States)

Plakke, B; Ng, C-W; Poremba, A

2013-08-06

The neural underpinnings of working and recognition memory have traditionally been studied in the visual domain and these studies pinpoint the lateral prefrontal cortex (lPFC) as a primary region for visual memory processing (Miller et al., 1996; Ranganath et al., 2004; Kennerley and Wallis, 2009). Herein, we utilize single-unit recordings for the same region in monkeys (Macaca mulatta) but investigate a second modality examining auditory working and recognition memory during delayed matching-to-sample (DMS) performance. A large portion of neurons in the dorsal and ventral banks of the principal sulcus (area 46, 46/9) show DMS event-related activity to one or more of the following task events: auditory cues, memory delay, decision wait time, response, and/or reward portions. Approximately 50% of the neurons show evidence of auditory-evoked activity during the task and population activity demonstrated encoding of recognition memory in the form of match enhancement. However, neither robust nor sustained delay activity was observed. The neuronal responses during the auditory DMS task are similar in many respects to those found within the visual working memory domain, which supports the hypothesis that the lPFC, particularly area 46, functionally represents key pieces of information for recognition memory inclusive of decision-making, but regardless of modality. Copyright © 2013 IBRO. Published by Elsevier Ltd. All rights reserved.

Traffic sign recognition based on deep convolutional neural network

Science.gov (United States)

Yin, Shi-hao; Deng, Ji-cai; Zhang, Da-wei; Du, Jing-yuan

2017-11-01

Traffic sign recognition (TSR) is an important component of automated driving systems. It is a rather challenging task to design a high-performance classifier for the TSR system. In this paper, we propose a new method for TSR system based on deep convolutional neural network. In order to enhance the expression of the network, a novel structure (dubbed block-layer below) which combines network-in-network and residual connection is designed. Our network has 10 layers with parameters (block-layer seen as a single layer): the first seven are alternate convolutional layers and block-layers, and the remaining three are fully-connected layers. We train our TSR network on the German traffic sign recognition benchmark (GTSRB) dataset. To reduce overfitting, we perform data augmentation on the training images and employ a regularization method named "dropout". The activation function we employ in our network adopts scaled exponential linear units (SELUs), which can induce self-normalizing properties. To speed up the training, we use an efficient GPU to accelerate the convolutional operation. On the test dataset of GTSRB, we achieve the accuracy rate of 99.67%, exceeding the state-of-the-art results.

A neural network based artificial vision system for licence plate recognition.

Science.gov (United States)

Draghici, S

1997-02-01

This paper presents a neural network based artificial vision system able to analyze the image of a car given by a camera, locate the registration plate and recognize the registration number of the car. The paper describes in detail various practical problems encountered in implementing this particular application and the solutions used to solve them. The main features of the system presented are: controlled stability-plasticity behavior, controlled reliability threshold, both off-line and on-line learning, self assessment of the output reliability and high reliability based on high level multiple feedback. The system has been designed using a modular approach. Sub-modules can be upgraded and/or substituted independently, thus making the system potentially suitable in a large variety of vision applications. The OCR engine was designed as an interchangeable plug-in module. This allows the user to choose an OCR engine which is suited to the particular application and to upgrade it easily in the future. At present, there are several versions of this OCR engine. One of them is based on a fully connected feedforward artificial neural network with sigmoidal activation functions. This network can be trained with various training algorithms such as error backpropagation. An alternative OCR engine is based on the constraint based decomposition (CBD) training architecture. The system has showed the following performances (on average) on real-world data: successful plate location and segmentation about 99%, successful character recognition about 98% and successful recognition of complete registration plates about 80%.

СHIRAL RECOGNITION OF CYSTEINE MOLECULES BY CHIRAL CdSe AND CdS QUANTUM DOTS

Directory of Open Access Journals (Sweden)

M. V. Mukhina

2015-11-01

Full Text Available Here, we report the investigation of mechanism of chiral molecular recognition of cysteine biomolecules by chiral CdSe and CdS semiconductor nanocrystals. To observe chiral recognition process, we prepared enantioenriched ensembles of the nanocrystals capped with achiral ligand. The enantioenriched samples of intrinsically chiral CdSe quantum dots were prepared by separation of initial racemic mixture of the nanocrystals using chiral phase transfer from chloroform to water driven by L- and D-cysteine. Chiral molecules of cysteine and penicillamine were substituted for achiral molecules of dodecanethiol on the surfaces of CdSe and CdS samples, respectively, via reverse phase transfer from water to chloroform. We estimated an efficiency of the hetero- (d-L or l-D and homocomplexes (l-L formation by comparing the extents of corresponding complexing reactions. Using circular dichroism spectroscopy data we show an ability of nanocrystals enantiomers to discriminate between left-handed and right-handed enantiomers of biomolecules via preferential formation of heterocomplexes. Development of approaches for obtaining chiral nanocrystals via chiral phase transfer offers opportunities for investigation of molecular recognition at the nano/bio interfaces.

Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification

Directory of Open Access Journals (Sweden)

Srdjan Sladojevic

2016-01-01

Full Text Available The latest generation of convolutional neural networks (CNNs has achieved impressive results in the field of image classification. This paper is concerned with a new approach to the development of plant disease recognition model, based on leaf image classification, by the use of deep convolutional networks. Novel way of training and the methodology used facilitate a quick and easy system implementation in practice. The developed model is able to recognize 13 different types of plant diseases out of healthy leaves, with the ability to distinguish plant leaves from their surroundings. According to our knowledge, this method for plant disease recognition has been proposed for the first time. All essential steps required for implementing this disease recognition model are fully described throughout the paper, starting from gathering images in order to create a database, assessed by agricultural experts. Caffe, a deep learning framework developed by Berkley Vision and Learning Centre, was used to perform the deep CNN training. The experimental results on the developed model achieved precision between 91% and 98%, for separate class tests, on average 96.3%.

Handwritten Javanese Character Recognition Using Several Artificial Neural Network Methods

Directory of Open Access Journals (Sweden)

Gregorius Satia Budhi

2015-07-01

Full Text Available Javanese characters are traditional characters that are used to write the Javanese language. The Javanese language is a language used by many people on the island of Java, Indonesia. The use of Javanese characters is diminishing more and more because of the difficulty of studying the Javanese characters themselves. The Javanese character set consists of basic characters, numbers, complementary characters, and so on. In this research we have developed a system to recognize Javanese characters. Input for the system is a digital image containing several handwritten Javanese characters. Preprocessing and segmentation are performed on the input image to get each character. For each character, feature extraction is done using the ICZ-ZCZ method. The output from feature extraction will become input for an artificial neural network. We used several artificial neural networks, namely a bidirectional associative memory network, a counterpropagation network, an evolutionary network, a backpropagation network, and a backpropagation network combined with chi2. From the experimental results it can be seen that the combination of chi2 and backpropagation achieved better recognition accuracy than the other methods.

Heme as a danger molecule in pathogen recognition.

Science.gov (United States)

Wegiel, Barbara; Hauser, Carl J; Otterbein, Leo E

2015-12-01

Appropriate control of redox mechanisms are critical for and effective innate immune response, which employs multiple cell types, receptors and molecules that recognize danger signals when they reach the host. Recognition of pathogen-associated pattern molecules (PAMPs) is a fundamental host survival mechanism for efficient elimination of invading pathogens and resolution of the infection and inflammation. In addition to PAMPs, eukaryotic cells contain a plethora of intracellular molecules that are normally secured within the confines of the plasma membrane, but if liberated and encountered in the extracellular milieu can provoke rapid cell activation. These are known as Alarmins or Danger-Associated Molecular Patterns (DAMPs) and can be released actively by cells or passively as a result of sterile cellular injury after trauma, ischemia, or toxin-induced cell rupture. Both PAMPs and DAMPs are recognized by a series of cognate receptors that increase the generation of free radicals and activate specific signaling pathways that result in regulation of a variety of stress response, redox sensitive genes. Multiple mediators released, as cells die include, but are not limited to ATP, hydrogen peroxide, heme, formyl peptides, DNA or mitochondria provide the second signal to amplify immune responses. In this review, we will focus on how sterile and infective stimuli activate the stress response gene heme oxygenase-1 (Hmox1, HO-1), a master gene critical to an appropriate host response that is now recognized as one with enormous therapeutic potential. HO-1 gene expression is regulated in large part by redox-sensitive proteins including but not limited to nrf2. Both PAMPs and DAMPs increase the activation of nrf2 and HO-1. Heme is a powerful pro-oxidant and as such should be qualified as a DAMP. With its degradation by HO-1a molecule of carbon monoxide (CO) is generated that in turn serves as a bioactive signaling molecule. PAMPs such as bacterial endotoxin activate HO-1

Face recognition: Eigenface, elastic matching, and neural nets

International Nuclear Information System (INIS)

Zhang, J.; Lades, M.

1997-01-01

This paper is a comparative study of three recently proposed algorithms for face recognition: eigenface, autoassociation and classification neural nets, and elastic matching. After these algorithms were analyzed under a common statistical decision framework, they were evaluated experimentally on four individual data bases, each with a moderate subject size, and a combined data base with more than a hundred different subjects. Analysis and experimental results indicate that the eigenface algorithm, which is essentially a minimum distance classifier, works well when lighting variation is small. Its performance deteriorates significantly as lighting variation increases. The elastic matching algorithm, on the other hand, is insensitive to lighting, face position, and expression variations and therefore is more versatile. The performance of the autoassociation and classification nets is upper bounded by that of the eigenface but is more difficult to implement in practice

Knowledge Based 3d Building Model Recognition Using Convolutional Neural Networks from LIDAR and Aerial Imageries

Science.gov (United States)

Alidoost, F.; Arefi, H.

2016-06-01

In recent years, with the development of the high resolution data acquisition technologies, many different approaches and algorithms have been presented to extract the accurate and timely updated 3D models of buildings as a key element of city structures for numerous applications in urban mapping. In this paper, a novel and model-based approach is proposed for automatic recognition of buildings' roof models such as flat, gable, hip, and pyramid hip roof models based on deep structures for hierarchical learning of features that are extracted from both LiDAR and aerial ortho-photos. The main steps of this approach include building segmentation, feature extraction and learning, and finally building roof labeling in a supervised pre-trained Convolutional Neural Network (CNN) framework to have an automatic recognition system for various types of buildings over an urban area. In this framework, the height information provides invariant geometric features for convolutional neural network to localize the boundary of each individual roofs. CNN is a kind of feed-forward neural network with the multilayer perceptron concept which consists of a number of convolutional and subsampling layers in an adaptable structure and it is widely used in pattern recognition and object detection application. Since the training dataset is a small library of labeled models for different shapes of roofs, the computation time of learning can be decreased significantly using the pre-trained models. The experimental results highlight the effectiveness of the deep learning approach to detect and extract the pattern of buildings' roofs automatically considering the complementary nature of height and RGB information.

Nonlinear analysis and synthesis of video images using deep dynamic bottleneck neural networks for face recognition.

Science.gov (United States)

Moghadam, Saeed Montazeri; Seyyedsalehi, Seyyed Ali

2018-05-31

Nonlinear components extracted from deep structures of bottleneck neural networks exhibit a great ability to express input space in a low-dimensional manifold. Sharing and combining the components boost the capability of the neural networks to synthesize and interpolate new and imaginary data. This synthesis is possibly a simple model of imaginations in human brain where the components are expressed in a nonlinear low dimensional manifold. The current paper introduces a novel Dynamic Deep Bottleneck Neural Network to analyze and extract three main features of videos regarding the expression of emotions on the face. These main features are identity, emotion and expression intensity that are laid in three different sub-manifolds of one nonlinear general manifold. The proposed model enjoying the advantages of recurrent networks was used to analyze the sequence and dynamics of information in videos. It is noteworthy to mention that this model also has also the potential to synthesize new videos showing variations of one specific emotion on the face of unknown subjects. Experiments on discrimination and recognition ability of extracted components showed that the proposed model has an average of 97.77% accuracy in recognition of six prominent emotions (Fear, Surprise, Sadness, Anger, Disgust, and Happiness), and 78.17% accuracy in the recognition of intensity. The produced videos revealed variations from neutral to the apex of an emotion on the face of the unfamiliar test subject which is on average 0.8 similar to reference videos in the scale of the SSIM method. Copyright © 2018 Elsevier Ltd. All rights reserved.

Single-Molecule View of Small RNA-Guided Target Search and Recognition.

Science.gov (United States)

Globyte, Viktorija; Kim, Sung Hyun; Joo, Chirlmin

2018-05-20

Most everyday processes in life involve a necessity for an entity to locate its target. On a cellular level, many proteins have to find their target to perform their function. From gene-expression regulation to DNA repair to host defense, numerous nucleic acid-interacting proteins use distinct target search mechanisms. Several proteins achieve that with the help of short RNA strands known as guides. This review focuses on single-molecule advances studying the target search and recognition mechanism of Argonaute and CRISPR (clustered regularly interspaced short palindromic repeats) systems. We discuss different steps involved in search and recognition, from the initial complex prearrangement into the target-search competent state to the final proofreading steps. We focus on target search mechanisms that range from weak interactions, to one- and three-dimensional diffusion, to conformational proofreading. We compare the mechanisms of Argonaute and CRISPR with a well-studied target search system, RecA.

The DSFPN, a new neural network for optical character recognition.

Science.gov (United States)

Morns, L P; Dlay, S S

1999-01-01

A new type of neural network for recognition tasks is presented in this paper. The network, called the dynamic supervised forward-propagation network (DSFPN), is based on the forward only version of the counterpropagation network (CPN). The DSFPN, trains using a supervised algorithm and can grow dynamically during training, allowing subclasses in the training data to be learnt in an unsupervised manner. It is shown to train in times comparable to the CPN while giving better classification accuracies than the popular backpropagation network. Both Fourier descriptors and wavelet descriptors are used for image preprocessing and the wavelets are proven to give a far better performance.

Pattern recognition and data mining software based on artificial neural networks applied to proton transfer in aqueous environments

International Nuclear Information System (INIS)

Tahat Amani; Marti Jordi; Khwaldeh Ali; Tahat Kaher

2014-01-01

In computational physics proton transfer phenomena could be viewed as pattern classification problems based on a set of input features allowing classification of the proton motion into two categories: transfer ‘occurred’ and transfer ‘not occurred’. The goal of this paper is to evaluate the use of artificial neural networks in the classification of proton transfer events, based on the feed-forward back propagation neural network, used as a classifier to distinguish between the two transfer cases. In this paper, we use a new developed data mining and pattern recognition tool for automating, controlling, and drawing charts of the output data of an Empirical Valence Bond existing code. The study analyzes the need for pattern recognition in aqueous proton transfer processes and how the learning approach in error back propagation (multilayer perceptron algorithms) could be satisfactorily employed in the present case. We present a tool for pattern recognition and validate the code including a real physical case study. The results of applying the artificial neural networks methodology to crowd patterns based upon selected physical properties (e.g., temperature, density) show the abilities of the network to learn proton transfer patterns corresponding to properties of the aqueous environments, which is in turn proved to be fully compatible with previous proton transfer studies. (condensed matter: structural, mechanical, and thermal properties)

Fuzzy logic and neural networks in artificial intelligence and pattern recognition

Science.gov (United States)

Sanchez, Elie

1991-10-01

With the use of fuzzy logic techniques, neural computing can be integrated in symbolic reasoning to solve complex real world problems. In fact, artificial neural networks, expert systems, and fuzzy logic systems, in the context of approximate reasoning, share common features and techniques. A model of Fuzzy Connectionist Expert System is introduced, in which an artificial neural network is designed to construct the knowledge base of an expert system from, training examples (this model can also be used for specifications of rules in fuzzy logic control). Two types of weights are associated with the synaptic connections in an AND-OR structure: primary linguistic weights, interpreted as labels of fuzzy sets, and secondary numerical weights. Cell activation is computed through min-max fuzzy equations of the weights. Learning consists in finding the (numerical) weights and the network topology. This feedforward network is described and first illustrated in a biomedical application (medical diagnosis assistance from inflammatory-syndromes/proteins profiles). Then, it is shown how this methodology can be utilized for handwritten pattern recognition (characters play the role of diagnoses): in a fuzzy neuron describing a number for example, the linguistic weights represent fuzzy sets on cross-detecting lines and the numerical weights reflect the importance (or weakness) of connections between cross-detecting lines and characters.

Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano’s Continuous Note Recognition

Directory of Open Access Journals (Sweden)

YuKang Jia

2017-01-01

Full Text Available Long Short-Term Memory (LSTM is a kind of Recurrent Neural Networks (RNN relating to time series, which has achieved good performance in speech recogniton and image recognition. Long Short-Term Memory Projection (LSTMP is a variant of LSTM to further optimize speed and performance of LSTM by adding a projection layer. As LSTM and LSTMP have performed well in pattern recognition, in this paper, we combine them with Connectionist Temporal Classification (CTC to study piano’s continuous note recognition for robotics. Based on the Beijing Forestry University music library, we conduct experiments to show recognition rates and numbers of iterations of LSTM with a single layer, LSTMP with a single layer, and Deep LSTM (DLSTM, LSTM with multilayers. As a result, the single layer LSTMP proves performing much better than the single layer LSTM in both time and the recognition rate; that is, LSTMP has fewer parameters and therefore reduces the training time, and, moreover, benefiting from the projection layer, LSTMP has better performance, too. The best recognition rate of LSTMP is 99.8%. As for DLSTM, the recognition rate can reach 100% because of the effectiveness of the deep structure, but compared with the single layer LSTMP, DLSTM needs more training time.

Improving Pattern Recognition and Neural Network Algorithms with Applications to Solar Panel Energy Optimization

Science.gov (United States)

Zamora Ramos, Ernesto

Artificial Intelligence is a big part of automation and with today's technological advances, artificial intelligence has taken great strides towards positioning itself as the technology of the future to control, enhance and perfect automation. Computer vision includes pattern recognition and classification and machine learning. Computer vision is at the core of decision making and it is a vast and fruitful branch of artificial intelligence. In this work, we expose novel algorithms and techniques built upon existing technologies to improve pattern recognition and neural network training, initially motivated by a multidisciplinary effort to build a robot that helps maintain and optimize solar panel energy production. Our contributions detail an improved non-linear pre-processing technique to enhance poorly illuminated images based on modifications to the standard histogram equalization for an image. While the original motivation was to improve nocturnal navigation, the results have applications in surveillance, search and rescue, medical imaging enhancing, and many others. We created a vision system for precise camera distance positioning motivated to correctly locate the robot for capture of solar panel images for classification. The classification algorithm marks solar panels as clean or dirty for later processing. Our algorithm extends past image classification and, based on historical and experimental data, it identifies the optimal moment in which to perform maintenance on marked solar panels as to minimize the energy and profit loss. In order to improve upon the classification algorithm, we delved into feedforward neural networks because of their recent advancements, proven universal approximation and classification capabilities, and excellent recognition rates. We explore state-of-the-art neural network training techniques offering pointers and insights, culminating on the implementation of a complete library with support for modern deep learning architectures

Coarse-coded higher-order neural networks for PSRI object recognition. [position, scale, and rotation invariant

Science.gov (United States)

Spirkovska, Lilly; Reid, Max B.

1993-01-01

A higher-order neural network (HONN) can be designed to be invariant to changes in scale, translation, and inplane rotation. Invariances are built directly into the architecture of a HONN and do not need to be learned. Consequently, fewer training passes and a smaller training set are required to learn to distinguish between objects. The size of the input field is limited, however, because of the memory required for the large number of interconnections in a fully connected HONN. By coarse coding the input image, the input field size can be increased to allow the larger input scenes required for practical object recognition problems. We describe a coarse coding technique and present simulation results illustrating its usefulness and its limitations. Our simulations show that a third-order neural network can be trained to distinguish between two objects in a 4096 x 4096 pixel input field independent of transformations in translation, in-plane rotation, and scale in less than ten passes through the training set. Furthermore, we empirically determine the limits of the coarse coding technique in the object recognition domain.

Pattern recognition

CERN Document Server

Theodoridis, Sergios

2003-01-01

Pattern recognition is a scientific discipline that is becoming increasingly important in the age of automation and information handling and retrieval. Patter Recognition, 2e covers the entire spectrum of pattern recognition applications, from image analysis to speech recognition and communications. This book presents cutting-edge material on neural networks, - a set of linked microprocessors that can form associations and uses pattern recognition to ""learn"" -and enhances student motivation by approaching pattern recognition from the designer's point of view. A direct result of more than 10

Deep neural networks rival the representation of primate IT cortex for core visual object recognition.

Directory of Open Access Journals (Sweden)

Charles F Cadieu

2014-12-01

Full Text Available The primate visual system achieves remarkable visual object recognition performance even in brief presentations, and under changes to object exemplar, geometric transformations, and background variation (a.k.a. core visual object recognition. This remarkable performance is mediated by the representation formed in inferior temporal (IT cortex. In parallel, recent advances in machine learning have led to ever higher performing models of object recognition using artificial deep neural networks (DNNs. It remains unclear, however, whether the representational performance of DNNs rivals that of the brain. To accurately produce such a comparison, a major difficulty has been a unifying metric that accounts for experimental limitations, such as the amount of noise, the number of neural recording sites, and the number of trials, and computational limitations, such as the complexity of the decoding classifier and the number of classifier training examples. In this work, we perform a direct comparison that corrects for these experimental limitations and computational considerations. As part of our methodology, we propose an extension of "kernel analysis" that measures the generalization accuracy as a function of representational complexity. Our evaluations show that, unlike previous bio-inspired models, the latest DNNs rival the representational performance of IT cortex on this visual object recognition task. Furthermore, we show that models that perform well on measures of representational performance also perform well on measures of representational similarity to IT, and on measures of predicting individual IT multi-unit responses. Whether these DNNs rely on computational mechanisms similar to the primate visual system is yet to be determined, but, unlike all previous bio-inspired models, that possibility cannot be ruled out merely on representational performance grounds.

Differential theory of learning for efficient neural network pattern recognition

Science.gov (United States)

Hampshire, John B., II; Vijaya Kumar, Bhagavatula

1993-09-01

We describe a new theory of differential learning by which a broad family of pattern classifiers (including many well-known neural network paradigms) can learn stochastic concepts efficiently. We describe the relationship between a classifier's ability to generate well to unseen test examples and the efficiency of the strategy by which it learns. We list a series of proofs that differential learning is efficient in its information and computational resource requirements, whereas traditional probabilistic learning strategies are not. The proofs are illustrated by a simple example that lends itself to closed-form analysis. We conclude with an optical character recognition task for which three different types of differentially generated classifiers generalize significantly better than their probabilistically generated counterparts.

Recognition and detection of seismic phases by artificial neural network detector; Jinko neural network ni yoru jishinha no ninshiki to kenshutsu

Energy Technology Data Exchange (ETDEWEB)

Yamazaki, K; Wang, W [Tokyo Gakugei University, Tokyo (Japan)

1997-05-27

Initial parts of P-waves, medium or high in intensity, are detected using an artificial neural network (ANN). The ANN is the generic name given to information processing systems of the non-Neumann type configured to human brain in point of information processing function, and is packaged into computers in the form of software capable of parallel processing, self-organizing, learning, etc. In this paper, a hierarchical ANN-assisted seismic motion recognition system is constructed on the basis of an error reverse propagation algorithm. It is reported here, with a remark that this study wants much more data from tests for the evaluation of the quality of the recognition, that P-wave recognition has been achieved. When this technique is applied to the S-wave, much more real-time information will become available. For the improvement of the system, a number of problems have to be solved, including the establishment of automatic refurbishment through adaptation-and-learning and configuration that incorporates frequency-related matters. It is found that this system is effective in seismic wave phase recognition but that it is not suitable for precision measurement. 7 refs., 4 figs.

Gait pattern recognition in cerebral palsy patients using neural network modelling

International Nuclear Information System (INIS)

Muhammad, J.; Gibbs, S.; Abboud, R.; Anand, S.

2015-01-01

Interpretation of gait data obtained from modern 3D gait analysis is a challenging and time consuming task. The aim of this study was to create neural network models which can recognise the gait patterns from pre- and post-treatment and the normal ones. Neural network is a method which works on the principle of learning from experience and then uses the obtained knowledge to predict the unknown. Methods: Twenty-eight patients with cerebral palsy were recruited as subjects whose gait was analysed in pre- and post-treatment. A group of twenty-six normal subjects also participated in this study as control group. All subjects gait was analysed using Vicon Nexus to obtain the gait parameters and kinetic and kinematic parameters of hip, knee and ankle joints in three planes of both limbs. The gait data was used as input to create neural network models. A total of approximately 300 trials were split into 70% and 30% to train and test the models, respectively. Different models were built using different parameters. The gait was categorised as three patterns, i.e., normal, pre- and post-treatments. Result: The results showed that the models using all parameters or using the joint angles and moments could predict the gait patterns with approximately 95% accuracy. Some of the models e.g., the models using joint power and moments, had lower rate in recognition of gait patterns with approximately 70-90% successful ratio. Conclusion: Neural network model can be used in clinical practice to recognise the gait pattern for cerebral palsy patients. (author)

[A wavelet neural network algorithm of EEG signals data compression and spikes recognition].

Science.gov (United States)

Zhang, Y; Liu, A; Yu, K

1999-06-01

A novel method of EEG signals compression representation and epileptiform spikes recognition based on wavelet neural network and its algorithm is presented. The wavelet network not only can compress data effectively but also can recover original signal. In addition, the characters of the spikes and the spike-slow rhythm are auto-detected from the time-frequency isoline of EEG signal. This method is well worth using in the field of the electrophysiological signal processing and time-frequency analyzing.

Comparison of the neural correlates of retrieval success in tests of cued recall and recognition memory.

Science.gov (United States)

Okada, Kayoko; Vilberg, Kaia L; Rugg, Michael D

2012-03-01

The neural correlates of successful retrieval on tests of word stem recall and recognition memory were compared. In the recall test, subjects viewed word stems, half of which were associated with studied items and half with unstudied items, and for each stem attempted to recall a corresponding study word. In the recognition test, old/new judgments were made on old and new words. The neural correlates of successful retrieval were identified by contrasting activity elicited by correctly endorsed test items. Old > new effects common to the two tasks were found in medial and lateral parietal and right entorhinal cortex. Common new > old effects were identified in medial and left frontal cortex, and left anterior intra-parietal sulcus. Greater old > new effects were evident for cued recall in inferior parietal regions abutting those demonstrating common effects, whereas larger new > old effects were found for recall in left frontal cortex and the anterior cingulate. New > old effects were also found for the recall task in right lateral anterior prefrontal cortex, where they were accompanied by old > new effects during recognition. It is concluded that successful recall and recognition are associated with enhanced activity in a common set of recollection-sensitive parietal regions, and that the greater activation in these regions during recall reflects the greater dependence of that task on recollection. Larger new > old effects during recall are interpreted as reflections of the greater opportunity for iterative retrieval attempts when retrieval cues are partial rather than copy cues. Copyright © 2011 Wiley Periodicals, Inc.

Molecular tips for scanning tunneling microscopy: intermolecular electron tunneling for single-molecule recognition and electronics.

Science.gov (United States)

Nishino, Tomoaki

2014-01-01

This paper reviews the development of molecular tips for scanning tunneling microscopy (STM). Molecular tips offer many advantages: first is their ability to perform chemically selective imaging because of chemical interactions between the sample and the molecular tip, thus improving a major drawback of conventional STM. Rational design of the molecular tip allows sophisticated chemical recognition; e.g., chiral recognition and selective visualization of atomic defects in carbon nanotubes. Another advantage is that they provide a unique method to quantify electron transfer between single molecules. Understanding such electron transfer is mandatory for the realization of molecular electronics.

An analog VLSI real time optical character recognition system based on a neural architecture

International Nuclear Information System (INIS)

Bo, G.; Caviglia, D.; Valle, M.

1999-01-01

In this paper a real time Optical Character Recognition system is presented: it is based on a feature extraction module and a neural network classifier which have been designed and fabricated in analog VLSI technology. Experimental results validate the circuit functionality. The results obtained from a validation based on a mixed approach (i.e., an approach based on both experimental and simulation results) confirm the soundness and reliability of the system

An analog VLSI real time optical character recognition system based on a neural architecture

Energy Technology Data Exchange (ETDEWEB)

Bo, G.; Caviglia, D.; Valle, M. [Genoa Univ. (Italy). Dip. of Biophysical and Electronic Engineering

1999-03-01

In this paper a real time Optical Character Recognition system is presented: it is based on a feature extraction module and a neural network classifier which have been designed and fabricated in analog VLSI technology. Experimental results validate the circuit functionality. The results obtained from a validation based on a mixed approach (i.e., an approach based on both experimental and simulation results) confirm the soundness and reliability of the system.

Crystal structure of the Ig1 domain of the neural cell adhesion molecule NCAM2 displays domain swapping

DEFF Research Database (Denmark)

Rasmussen, Kim Krighaar; Kulahin, Nikolaj; Kristensen, Ole

2008-01-01

The crystal structure of the first immunoglobulin (Ig1) domain of neural cell adhesion molecule 2 (NCAM2/OCAM/RNCAM) is presented at a resolution of 2.7 A. NCAM2 is a member of the immunoglobulin superfamily of cell adhesion molecules (IgCAMs). In the structure, two Ig domains interact by domain...

Modular Adaptive System Based on a Multi-Stage Neural Structure for Recognition of 2D Objects of Discontinuous Production

Directory of Open Access Journals (Sweden)

I. Topalova

2005-03-01

Full Text Available This is a presentation of a new system for invariant recognition of 2D objects with overlapping classes, that can not be effectively recognized with the traditional methods. The translation, scale and partial rotation invariant contour object description is transformed in a DCT spectrum space. The obtained frequency spectrums are decomposed into frequency bands in order to feed different BPG neural nets (NNs. The NNs are structured in three stages - filtering and full rotation invariance; partial recognition; general classification. The designed multi-stage BPG Neural Structure shows very good accuracy and flexibility when tested with 2D objects used in the discontinuous production. The reached speed and the opportunuty for an easy restructuring and reprogramming of the system makes it suitable for application in different applied systems for real time work.

Modular Adaptive System Based on a Multi-Stage Neural Structure for Recognition of 2D Objects of Discontinuous Production

Directory of Open Access Journals (Sweden)

I. Topalova

2008-11-01

Full Text Available This is a presentation of a new system for invariant recognition of 2D objects with overlapping classes, that can not be effectively recognized with the traditional methods. The translation, scale and partial rotation invariant contour object description is transformed in a DCT spectrum space. The obtained frequency spectrums are decomposed into frequency bands in order to feed different BPG neural nets (NNs. The NNs are structured in three stages - filtering and full rotation invariance; partial recognition; general classification. The designed multi-stage BPG Neural Structure shows very good accuracy and flexibility when tested with 2D objects used in the discontinuous production. The reached speed and the opportunuty for an easy restructuring and reprogramming of the system makes it suitable for application in different applied systems for real time work.

Effects of acute psychosocial stress on neural activity to emotional and neutral faces in a face recognition memory paradigm.

Science.gov (United States)

Li, Shijia; Weerda, Riklef; Milde, Christopher; Wolf, Oliver T; Thiel, Christiane M

2014-12-01

Previous studies have shown that acute psychosocial stress impairs recognition of declarative memory and that emotional material is especially sensitive to this effect. Animal studies suggest a central role of the amygdala which modulates memory processes in hippocampus, prefrontal cortex and other brain areas. We used functional magnetic resonance imaging (fMRI) to investigate neural correlates of stress-induced modulation of emotional recognition memory in humans. Twenty-seven healthy, right-handed, non-smoker male volunteers performed an emotional face recognition task. During encoding, participants were presented with 50 fearful and 50 neutral faces. One hour later, they underwent either a stress (Trier Social Stress Test) or a control procedure outside the scanner which was followed immediately by the recognition session inside the scanner, where participants had to discriminate between 100 old and 50 new faces. Stress increased salivary cortisol, blood pressure and pulse, and decreased the mood of participants but did not impact recognition memory. BOLD data during recognition revealed a stress condition by emotion interaction in the left inferior frontal gyrus and right hippocampus which was due to a stress-induced increase of neural activity to fearful and a decrease to neutral faces. Functional connectivity analyses revealed a stress-induced increase in coupling between the right amygdala and the right fusiform gyrus, when processing fearful as compared to neutral faces. Our results provide evidence that acute psychosocial stress affects medial temporal and frontal brain areas differentially for neutral and emotional items, with a stress-induced privileged processing of emotional stimuli.

Conformational Smear Characterization and Binning of Single-Molecule Conductance Measurements for Enhanced Molecular Recognition.

Science.gov (United States)

Korshoj, Lee E; Afsari, Sepideh; Chatterjee, Anushree; Nagpal, Prashant

2017-11-01

Electronic conduction or charge transport through single molecules depends primarily on molecular structure and anchoring groups and forms the basis for a wide range of studies from molecular electronics to DNA sequencing. Several high-throughput nanoelectronic methods such as mechanical break junctions, nanopores, conductive atomic force microscopy, scanning tunneling break junctions, and static nanoscale electrodes are often used for measuring single-molecule conductance. In these measurements, "smearing" due to conformational changes and other entropic factors leads to large variances in the observed molecular conductance, especially in individual measurements. Here, we show a method for characterizing smear in single-molecule conductance measurements and demonstrate how binning measurements according to smear can significantly enhance the use of individual conductance measurements for molecular recognition. Using quantum point contact measurements on single nucleotides within DNA macromolecules, we demonstrate that the distance over which molecular junctions are maintained is a measure of smear, and the resulting variance in unbiased single measurements depends on this smear parameter. Our ability to identify individual DNA nucleotides at 20× coverage increases from 81.3% accuracy without smear analysis to 93.9% with smear characterization and binning (SCRIB). Furthermore, merely 7 conductance measurements (7× coverage) are needed to achieve 97.8% accuracy for DNA nucleotide recognition when only low molecular smear measurements are used, which represents a significant improvement over contemporary sequencing methods. These results have important implications in a broad range of molecular electronics applications from designing robust molecular switches to nanoelectronic DNA sequencing.

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

Science.gov (United States)

Khellal, Atmane; Ma, Hongbin; Fei, Qing

2018-05-09

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

Artificial Neural Network Application for Partial Discharge Recognition: Survey and Future Directions

Directory of Open Access Journals (Sweden)

Abdullahi Abubakar Mas’ud

2016-07-01

Full Text Available In order to investigate how artificial neural networks (ANNs have been applied for partial discharge (PD pattern recognition, this paper reviews recent progress made on ANN development for PD classification by a literature survey. Contributions from several authors have been presented and discussed. High recognition rate has been recorded for several PD faults, but there are still many factors that hinder correct recognition of PD by the ANN, such as high-amplitude noise or wide spectral content typical from industrial environments, trial and error approaches in determining an optimum ANN, multiple PD sources acting simultaneously, lack of comprehensive and up to date databank of PD faults, and the appropriate selection of the characteristics that allow a correct recognition of the type of source which are currently being addressed by researchers. Several suggestions for improvement are proposed by the authors include: (1 determining the optimum weights in training the ANN; (2 using PD data captured over long stressing period in training the ANN; (3 ANN recognizing different PD degradation levels; (4 using the same resolution sizes of the PD patterns when training and testing the ANN with different PD dataset; (5 understanding the characteristics of multiple concurrent PD faults and effectively recognizing them; and (6 developing techniques in order to shorten the training time for the ANN as applied for PD recognition Finally, this paper critically assesses the suitability of ANNs for both online and offline PD detections outlining the advantages to the practitioners in the field. It is possible for the ANNs to determine the stage of degradation of the PD, thereby giving an indication of the seriousness of the fault.

Face Recognition by Bunch Graph Method Using a Group Based Adaptive Tolerant Neural Network

OpenAIRE

Aradhana D.; Girish H.; Karibasappa K.; Reddy A. Chennakeshava

2011-01-01

This paper presents a new method for feature extraction from the facial image by using bunch graph method. These extracted geometric features of the face are used subsequently for face recognition by utilizing the group based adaptive neural network. This method is suitable, when the facial images are rotation and translation invariant. Further the technique also free from size invariance of facial image and is capable of identifying the facial images correctly when corrupted w...

An acidic microenvironment sets the humoral pattern recognition molecule PTX3 in a tissue repair mode

Science.gov (United States)

Doni, Andrea; Musso, Tiziana; Morone, Diego; Bastone, Antonio; Zambelli, Vanessa; Sironi, Marina; Castagnoli, Carlotta; Cambieri, Irene; Stravalaci, Matteo; Pasqualini, Fabio; Laface, Ilaria; Valentino, Sonia; Tartari, Silvia; Ponzetta, Andrea; Maina, Virginia; Barbieri, Silvia S.; Tremoli, Elena; Catapano, Alberico L.; Norata, Giuseppe D.; Bottazzi, Barbara; Garlanda, Cecilia

2015-01-01

Pentraxin 3 (PTX3) is a fluid-phase pattern recognition molecule and a key component of the humoral arm of innate immunity. In four different models of tissue damage in mice, PTX3 deficiency was associated with increased fibrin deposition and persistence, and thicker clots, followed by increased collagen deposition, when compared with controls. Ptx3-deficient macrophages showed defective pericellular fibrinolysis in vitro. PTX3-bound fibrinogen/fibrin and plasminogen at acidic pH and increased plasmin-mediated fibrinolysis. The second exon-encoded N-terminal domain of PTX3 recapitulated the activity of the intact molecule. Thus, a prototypic component of humoral innate immunity, PTX3, plays a nonredundant role in the orchestration of tissue repair and remodeling. Tissue acidification resulting from metabolic adaptation during tissue repair sets PTX3 in a tissue remodeling and repair mode, suggesting that matrix and microbial recognition are common, ancestral features of the humoral arm of innate immunity. PMID:25964372

A peptide derived from a trans-homophilic binding site in neural cell adhesion molecule induces neurite outgrowth and neuronal survival

DEFF Research Database (Denmark)

Køhler, Lene B; Soroka, Vladislav; Korshunova, Irina

2010-01-01

The neural cell adhesion molecule (NCAM) plays a key role in neural development, regeneration, and synaptic plasticity. The crystal structure of a fragment of NCAM comprising the three N-terminal immunoglobulin (Ig)-like modules indicates that the first and second Ig modules bind to each other, t...

Recognition of malignant processes with neural nets from ESR spectra of serum albumin

Energy Technology Data Exchange (ETDEWEB)

Seidel, P. [Inst. of Medical Physics and Biophysics, Univ. Leipzig (Germany); Gurachevsky, A.; Muravsky, V.; Schnurr, K.; Seibt, G. [Medinnovation GmbH, Wildau (Germany); Matthes, G. [Inst. of Transfusion Medicine, Univ. Hospital Leipzig (Germany)

2005-07-01

Cancer diseases are the focus of intense research due to their frequent occurrence. It is known from the literature that serum proteins are changed in the case of malignant processes. Changes of albumin conformation, transport efficiency, and binding characteristics can be determined by electron spin resonance spectroscopy (ESR). The present study analysed the binding/dissociation function of albumin with an ESR method using 16-doxyl stearate spin probe as reporter molecule and ethanol as modifier of hydrophobic interactions. Native and frozen plasma of healthy donors (608 samples), patients with malignant diseases (423 samples), and patients with benign conditions (221 samples) were analysed. The global specificity was 91% and the sensitivity 96%. In look-back samples of 27 donors, a malignant process could be detected up to 30 months before clinical diagnosis. To recognise different entities of malignant diseases from the ESR spectra, Artificial neural networks were implemented. For 48 female donors with breast cancer, the recognition specificity was 85%. Other carcinoma entities (22 colon, 18 prostate, 12 stomach) were recognised with specificities between 75% and 84%. Should these specificity values be reproduced in larger studies, the described method could be used as a new specific tumour marker for the early detection of malignant processes. Since transmission of cancer via blood transfusion cannot be excluded as yet, the described ESR method could also be used as a quality test for plasma products. (orig.)

Recognition of malignant processes with neural nets from ESR spectra of serum albumin

International Nuclear Information System (INIS)

Seidel, P.; Gurachevsky, A.; Muravsky, V.; Schnurr, K.; Seibt, G.; Matthes, G.

2005-01-01

Cancer diseases are the focus of intense research due to their frequent occurrence. It is known from the literature that serum proteins are changed in the case of malignant processes. Changes of albumin conformation, transport efficiency, and binding characteristics can be determined by electron spin resonance spectroscopy (ESR). The present study analysed the binding/dissociation function of albumin with an ESR method using 16-doxyl stearate spin probe as reporter molecule and ethanol as modifier of hydrophobic interactions. Native and frozen plasma of healthy donors (608 samples), patients with malignant diseases (423 samples), and patients with benign conditions (221 samples) were analysed. The global specificity was 91% and the sensitivity 96%. In look-back samples of 27 donors, a malignant process could be detected up to 30 months before clinical diagnosis. To recognise different entities of malignant diseases from the ESR spectra, Artificial neural networks were implemented. For 48 female donors with breast cancer, the recognition specificity was 85%. Other carcinoma entities (22 colon, 18 prostate, 12 stomach) were recognised with specificities between 75% and 84%. Should these specificity values be reproduced in larger studies, the described method could be used as a new specific tumour marker for the early detection of malignant processes. Since transmission of cancer via blood transfusion cannot be excluded as yet, the described ESR method could also be used as a quality test for plasma products. (orig.)

A neural network approach to the study of dynamics and structure of molecular systems

International Nuclear Information System (INIS)

Getino, C.; Sumpter, B.G.; Noid, D.W.

1994-01-01

Neural networks are used to study intramolecular energy flow in molecular systems (tetratomics to macromolecules), developing new techniques for efficient analysis of data obtained from molecular-dynamics and quantum mechanics calculations. Neural networks can map phase space points to intramolecular vibrational energies along a classical trajectory (example of complicated coordinate transformation), producing reasonably accurate values for any region of the multidimensional phase space of a tetratomic molecule. Neural network energy flow predictions are found to significantly enhance the molecular-dynamics method to longer time-scales and extensive averaging of trajectories for macromolecular systems. Pattern recognition abilities of neural networks can be used to discern phase space features. Neural networks can also expand model calculations by interpolation of costly quantum mechanical ab initio data, used to develop semiempirical potential energy functions

Through your eyes or mine? The neural correlates of mental state recognition in Huntington's disease.

Science.gov (United States)

Eddy, Clare M; Rickards, Hugh E; Hansen, Peter C

2018-03-01

Huntington's disease (HD) can impair social cognition. This study investigated whether patients with HD exhibit neural differences to healthy controls when they are considering mental and physical states relating to the static expressions of human eyes. Thirty-two patients with HD and 28 age-matched controls were scanned with fMRI during two versions of the Reading the Mind in the Eyes Task: The standard version requiring mental state judgments, and a comparison version requiring judgments about age. HD was associated with behavioral deficits on only the mental state eyes task. Contrasting the two versions of the eyes task (mental state > age judgment) revealed hypoactivation within left middle frontal gyrus and supramarginal gyrus in HD. Subgroup analyses comparing premanifest HD patients to age-matched controls revealed reduced activity in right supramarginal gyrus and increased activity in anterior cingulate during mental state recognition in these patients, while manifest HD was associated with hypoactivity in left insula and left supramarginal gyrus. When controlling for the effects of healthy aging, manifest patients exhibited declining activation within areas including right temporal pole. Our findings provide compelling evidence for a selective impairment of internal emotional status when patients with HD appraise facial features in order to make social judgements. Differential activity in temporal and anterior cingulate cortices may suggest that poor emotion regulation and emotional egocentricity underlie impaired mental state recognition in premanifest patients, while more extensive mental state recognition impairments in manifest disease reflect dysfunction in neural substrates underlying executive functions, and the experience and interpretation of emotion. © 2017 Wiley Periodicals, Inc.

Convolutional neural networks based on augmented training samples for synthetic aperture radar target recognition

Science.gov (United States)

Yan, Yue

2018-03-01

A synthetic aperture radar (SAR) automatic target recognition (ATR) method based on the convolutional neural networks (CNN) trained by augmented training samples is proposed. To enhance the robustness of CNN to various extended operating conditions (EOCs), the original training images are used to generate the noisy samples at different signal-to-noise ratios (SNRs), multiresolution representations, and partially occluded images. Then, the generated images together with the original ones are used to train a designed CNN for target recognition. The augmented training samples can contrapuntally improve the robustness of the trained CNN to the covered EOCs, i.e., the noise corruption, resolution variance, and partial occlusion. Moreover, the significantly larger training set effectively enhances the representation capability for other conditions, e.g., the standard operating condition (SOC), as well as the stability of the network. Therefore, better performance can be achieved by the proposed method for SAR ATR. For experimental evaluation, extensive experiments are conducted on the Moving and Stationary Target Acquisition and Recognition dataset under SOC and several typical EOCs.

A biologically inspired neural network model to transformation invariant object recognition

Science.gov (United States)

Iftekharuddin, Khan M.; Li, Yaqin; Siddiqui, Faraz

2007-09-01

Transformation invariant image recognition has been an active research area due to its widespread applications in a variety of fields such as military operations, robotics, medical practices, geographic scene analysis, and many others. The primary goal for this research is detection of objects in the presence of image transformations such as changes in resolution, rotation, translation, scale and occlusion. We investigate a biologically-inspired neural network (NN) model for such transformation-invariant object recognition. In a classical training-testing setup for NN, the performance is largely dependent on the range of transformation or orientation involved in training. However, an even more serious dilemma is that there may not be enough training data available for successful learning or even no training data at all. To alleviate this problem, a biologically inspired reinforcement learning (RL) approach is proposed. In this paper, the RL approach is explored for object recognition with different types of transformations such as changes in scale, size, resolution and rotation. The RL is implemented in an adaptive critic design (ACD) framework, which approximates the neuro-dynamic programming of an action network and a critic network, respectively. Two ACD algorithms such as Heuristic Dynamic Programming (HDP) and Dual Heuristic dynamic Programming (DHP) are investigated to obtain transformation invariant object recognition. The two learning algorithms are evaluated statistically using simulated transformations in images as well as with a large-scale UMIST face database with pose variations. In the face database authentication case, the 90° out-of-plane rotation of faces from 20 different subjects in the UMIST database is used. Our simulations show promising results for both designs for transformation-invariant object recognition and authentication of faces. Comparing the two algorithms, DHP outperforms HDP in learning capability, as DHP takes fewer steps to

Evolutionary Design of Convolutional Neural Networks for Human Activity Recognition in Sensor-Rich Environments.

Science.gov (United States)

Baldominos, Alejandro; Saez, Yago; Isasi, Pedro

2018-04-23

Human activity recognition is a challenging problem for context-aware systems and applications. It is gaining interest due to the ubiquity of different sensor sources, wearable smart objects, ambient sensors, etc. This task is usually approached as a supervised machine learning problem, where a label is to be predicted given some input data, such as the signals retrieved from different sensors. For tackling the human activity recognition problem in sensor network environments, in this paper we propose the use of deep learning (convolutional neural networks) to perform activity recognition using the publicly available OPPORTUNITY dataset. Instead of manually choosing a suitable topology, we will let an evolutionary algorithm design the optimal topology in order to maximize the classification F1 score. After that, we will also explore the performance of committees of the models resulting from the evolutionary process. Results analysis indicates that the proposed model was able to perform activity recognition within a heterogeneous sensor network environment, achieving very high accuracies when tested with new sensor data. Based on all conducted experiments, the proposed neuroevolutionary system has proved to be able to systematically find a classification model which is capable of outperforming previous results reported in the state-of-the-art, showing that this approach is useful and improves upon previously manually-designed architectures.

Contemporary deep recurrent learning for recognition

Science.gov (United States)

Iftekharuddin, K. M.; Alam, M.; Vidyaratne, L.

2017-05-01

Large-scale feed-forward neural networks have seen intense application in many computer vision problems. However, these networks can get hefty and computationally intensive with increasing complexity of the task. Our work, for the first time in literature, introduces a Cellular Simultaneous Recurrent Network (CSRN) based hierarchical neural network for object detection. CSRN has shown to be more effective to solving complex tasks such as maze traversal and image processing when compared to generic feed forward networks. While deep neural networks (DNN) have exhibited excellent performance in object detection and recognition, such hierarchical structure has largely been absent in neural networks with recurrency. Further, our work introduces deep hierarchy in SRN for object recognition. The simultaneous recurrency results in an unfolding effect of the SRN through time, potentially enabling the design of an arbitrarily deep network. This paper shows experiments using face, facial expression and character recognition tasks using novel deep recurrent model and compares recognition performance with that of generic deep feed forward model. Finally, we demonstrate the flexibility of incorporating our proposed deep SRN based recognition framework in a humanoid robotic platform called NAO.

Connectivity strategies for higher-order neural networks applied to pattern recognition

Science.gov (United States)

Spirkovska, Lilly; Reid, Max B.

1990-01-01

Different strategies for non-fully connected HONNs (higher-order neural networks) are discussed, showing that by using such strategies an input field of 128 x 128 pixels can be attained while still achieving in-plane rotation and translation-invariant recognition. These techniques allow HONNs to be used with the larger input scenes required for practical pattern-recognition applications. The number of interconnections that must be stored has been reduced by a factor of approximately 200,000 in a T/C case and about 2000 in a Space Shuttle/F-18 case by using regional connectivity. Third-order networks have been simulated using several connection strategies. The method found to work best is regional connectivity. The main advantages of this strategy are the following: (1) it considers features of various scales within the image and thus gets a better sample of what the image looks like; (2) it is invariant to shape-preserving geometric transformations, such as translation and rotation; (3) the connections are predetermined so that no extra computations are necessary during run time; and (4) it does not require any extra storage for recording which connections were formed.

Face Recognition in Humans and Machines

Science.gov (United States)

O'Toole, Alice; Tistarelli, Massimo

The study of human face recognition by psychologists and neuroscientists has run parallel to the development of automatic face recognition technologies by computer scientists and engineers. In both cases, there are analogous steps of data acquisition, image processing, and the formation of representations that can support the complex and diverse tasks we accomplish with faces. These processes can be understood and compared in the context of their neural and computational implementations. In this chapter, we present the essential elements of face recognition by humans and machines, taking a perspective that spans psychological, neural, and computational approaches. From the human side, we overview the methods and techniques used in the neurobiology of face recognition, the underlying neural architecture of the system, the role of visual attention, and the nature of the representations that emerges. From the computational side, we discuss face recognition technologies and the strategies they use to overcome challenges to robust operation over viewing parameters. Finally, we conclude the chapter with a look at some recent studies that compare human and machine performances at face recognition.

Identifying Broadband Rotational Spectra with Neural Networks

Science.gov (United States)

Zaleski, Daniel P.; Prozument, Kirill

2017-06-01

A typical broadband rotational spectrum may contain several thousand observable transitions, spanning many species. Identifying the individual spectra, particularly when the dynamic range reaches 1,000:1 or even 10,000:1, can be challenging. One approach is to apply automated fitting routines. In this approach, combinations of 3 transitions can be created to form a "triple", which allows fitting of the A, B, and C rotational constants in a Watson-type Hamiltonian. On a standard desktop computer, with a target molecule of interest, a typical AUTOFIT routine takes 2-12 hours depending on the spectral density. A new approach is to utilize machine learning to train a computer to recognize the patterns (frequency spacing and relative intensities) inherit in rotational spectra and to identify the individual spectra in a raw broadband rotational spectrum. Here, recurrent neural networks have been trained to identify different types of rotational spectra and classify them accordingly. Furthermore, early results in applying convolutional neural networks for spectral object recognition in broadband rotational spectra appear promising. Perez et al. "Broadband Fourier transform rotational spectroscopy for structure determination: The water heptamer." Chem. Phys. Lett., 2013, 571, 1-15. Seifert et al. "AUTOFIT, an Automated Fitting Tool for Broadband Rotational Spectra, and Applications to 1-Hexanal." J. Mol. Spectrosc., 2015, 312, 13-21. Bishop. "Neural networks for pattern recognition." Oxford university press, 1995.

Transfection of glioma cells with the neural-cell adhesion molecule NCAM

DEFF Research Database (Denmark)

Edvardsen, K; Pedersen, P H; Bjerkvig, R

1994-01-01

The tumor growth and the invasive capacity of a rat glioma cell line (BT4Cn) were studied after transfection with the human transmembrane 140-kDa isoform of the neural-cell adhesion molecule, NCAM. After s.c. injection, the NCAM-transfected cells showed a slower growth rate than the parent cell...... of the injection site, with a sharply demarcated border between the tumor and brain tissue. In contrast, the parental cell line showed single-cell infiltration and more pronounced destruction of normal brain tissue. Using a 51Cr-release assay, spleen cells from rats transplanted with BT4Cn tumor cells generally...

Constructing Long Short-Term Memory based Deep Recurrent Neural Networks for Large Vocabulary Speech Recognition

OpenAIRE

Li, Xiangang; Wu, Xihong

2014-01-01

Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research, deep extensions on LSTM are investigated considering that deep hierarchical model has turned out to be more efficient than a shallow one. Motivated by previous research on constructing deep recurrent neural networks (RNNs), alternative deep LSTM architectures are proposed an...

Exploring multiple feature combination strategies with a recurrent neural network architecture for off-line handwriting recognition

Science.gov (United States)

Mioulet, L.; Bideault, G.; Chatelain, C.; Paquet, T.; Brunessaux, S.

2015-01-01

The BLSTM-CTC is a novel recurrent neural network architecture that has outperformed previous state of the art algorithms in tasks such as speech recognition or handwriting recognition. It has the ability to process long term dependencies in temporal signals in order to label unsegmented data. This paper describes different ways of combining features using a BLSTM-CTC architecture. Not only do we explore the low level combination (feature space combination) but we also explore high level combination (decoding combination) and mid-level (internal system representation combination). The results are compared on the RIMES word database. Our results show that the low level combination works best, thanks to the powerful data modeling of the LSTM neurons.

The pattern recognition molecule ficolin-1 exhibits differential binding to lymphocyte subsets, providing a novel link between innate and adaptive immunity

DEFF Research Database (Denmark)

Genster, Ninette; Ma, Ying Jie; Munthe-Fog, Lea

2014-01-01

is unknown. Recognition of healthy host cells by a pattern recognition molecule constitutes a potential hazard to self cells and tissues, emphasizing the importance of further elucidating the reported self-recognition. In the current study we investigated the potential recognition of lymphocytes by ficolin-1...... and demonstrated that CD56(dim) NK-cells and both CD4(+) and CD8(+) subsets of activated T-cells were recognized by ficolin-1. In contrast we did not detect binding of ficolin-1 to CD56(bright) NK-cells, NKT-cells, resting T-cells or B-cells. Furthermore, we showed that the protein-lymphocyte interaction occurred...

Evolutionary Design of Convolutional Neural Networks for Human Activity Recognition in Sensor-Rich Environments

Directory of Open Access Journals (Sweden)

Alejandro Baldominos

2018-04-01

Full Text Available Human activity recognition is a challenging problem for context-aware systems and applications. It is gaining interest due to the ubiquity of different sensor sources, wearable smart objects, ambient sensors, etc. This task is usually approached as a supervised machine learning problem, where a label is to be predicted given some input data, such as the signals retrieved from different sensors. For tackling the human activity recognition problem in sensor network environments, in this paper we propose the use of deep learning (convolutional neural networks to perform activity recognition using the publicly available OPPORTUNITY dataset. Instead of manually choosing a suitable topology, we will let an evolutionary algorithm design the optimal topology in order to maximize the classification F1 score. After that, we will also explore the performance of committees of the models resulting from the evolutionary process. Results analysis indicates that the proposed model was able to perform activity recognition within a heterogeneous sensor network environment, achieving very high accuracies when tested with new sensor data. Based on all conducted experiments, the proposed neuroevolutionary system has proved to be able to systematically find a classification model which is capable of outperforming previous results reported in the state-of-the-art, showing that this approach is useful and improves upon previously manually-designed architectures.

Evolutionary Design of Convolutional Neural Networks for Human Activity Recognition in Sensor-Rich Environments

Science.gov (United States)

2018-01-01

Human activity recognition is a challenging problem for context-aware systems and applications. It is gaining interest due to the ubiquity of different sensor sources, wearable smart objects, ambient sensors, etc. This task is usually approached as a supervised machine learning problem, where a label is to be predicted given some input data, such as the signals retrieved from different sensors. For tackling the human activity recognition problem in sensor network environments, in this paper we propose the use of deep learning (convolutional neural networks) to perform activity recognition using the publicly available OPPORTUNITY dataset. Instead of manually choosing a suitable topology, we will let an evolutionary algorithm design the optimal topology in order to maximize the classification F1 score. After that, we will also explore the performance of committees of the models resulting from the evolutionary process. Results analysis indicates that the proposed model was able to perform activity recognition within a heterogeneous sensor network environment, achieving very high accuracies when tested with new sensor data. Based on all conducted experiments, the proposed neuroevolutionary system has proved to be able to systematically find a classification model which is capable of outperforming previous results reported in the state-of-the-art, showing that this approach is useful and improves upon previously manually-designed architectures. PMID:29690587

Deep learning for single-molecule science

Science.gov (United States)

Albrecht, Tim; Slabaugh, Gregory; Alonso, Eduardo; Al-Arif, SM Masudur R.

2017-10-01

Exploring and making predictions based on single-molecule data can be challenging, not only due to the sheer size of the datasets, but also because a priori knowledge about the signal characteristics is typically limited and poor signal-to-noise ratio. For example, hypothesis-driven data exploration, informed by an expectation of the signal characteristics, can lead to interpretation bias or loss of information. Equally, even when the different data categories are known, e.g., the four bases in DNA sequencing, it is often difficult to know how to make best use of the available information content. The latest developments in machine learning (ML), so-called deep learning (DL) offer interesting, new avenues to address such challenges. In some applications, such as speech and image recognition, DL has been able to outperform conventional ML strategies and even human performance. However, to date DL has not been applied much in single-molecule science, presumably in part because relatively little is known about the ‘internal workings’ of such DL tools within single-molecule science as a field. In this Tutorial, we make an attempt to illustrate in a step-by-step guide how one of those, a convolutional neural network (CNN), may be used for base calling in DNA sequencing applications. We compare it with a SVM as a more conventional ML method, and discuss some of the strengths and weaknesses of the approach. In particular, a ‘deep’ neural network has many features of a ‘black box’, which has important implications on how we look at and interpret data.

The neural cell adhesion molecule L1 is distinct from the N-CAM related group of surface antigens BSP-2 and D2

DEFF Research Database (Denmark)

Faissner, A; Kruse, J; Goridis, C

1984-01-01

The neural cell adhesion molecule L1 and the group of N-CAM related molecules, BSP-2 and D2 antigen, are immunochemically distinct molecular species. The two groups of surface molecules are also functionally distinct entities, since inhibition of Ca2+-independent adhesion among early post-natal m...

Neural correlates of recognition and naming of musical instruments.

Science.gov (United States)

Belfi, Amy M; Bruss, Joel; Karlan, Brett; Abel, Taylor J; Tranel, Daniel

2016-10-01

Retrieval of lexical (names) and conceptual (semantic) information is frequently impaired in individuals with neurological damage. One category of items that is often affected is musical instruments. However, distinct neuroanatomical correlates underlying lexical and conceptual knowledge for musical instruments have not been identified. We used a neuropsychological approach to explore the neural correlates of knowledge retrieval for musical instruments. A large sample of individuals with focal brain damage (N = 298), viewed pictures of 16 musical instruments and were asked to name and identify each instrument. Neuroanatomical data were analyzed with a proportional MAP-3 method to create voxelwise lesion proportion difference maps. Impaired naming (lexical retrieval) of musical instruments was associated with damage to the left temporal pole and inferior pre- and postcentral gyri. Impaired recognition (conceptual knowledge retrieval) of musical instruments was associated with a more broadly and bilaterally distributed network of regions, including ventromedial prefrontal cortices, occipital cortices, and superior temporal gyrus. The findings extend our understanding of how musical instruments are processed at neural system level, and elucidate factors that may explain why brain damage may or may not produce anomia or agnosia for musical instruments. Our findings also help inform broader understanding of category-related knowledge mapping in the brain, as musical instruments possess several characteristics that are similar to various other categories of items: They are inanimate and highly manipulable (similar to tools), produce characteristic sounds (similar to animals), and require fine-grained visual differentiation between each other (similar to people). (PsycINFO Database Record (c) 2016 APA, all rights reserved).

Traffic Command Gesture Recognition for Virtual Urban Scenes Based on a Spatiotemporal Convolution Neural Network

Directory of Open Access Journals (Sweden)

Chunyong Ma

2018-01-01

Full Text Available Intelligent recognition of traffic police command gestures increases authenticity and interactivity in virtual urban scenes. To actualize real-time traffic gesture recognition, a novel spatiotemporal convolution neural network (ST-CNN model is presented. We utilized Kinect 2.0 to construct a traffic police command gesture skeleton (TPCGS dataset collected from 10 volunteers. Subsequently, convolution operations on the locational change of each skeletal point were performed to extract temporal features, analyze the relative positions of skeletal points, and extract spatial features. After temporal and spatial features based on the three-dimensional positional information of traffic police skeleton points were extracted, the ST-CNN model classified positional information into eight types of Chinese traffic police gestures. The test accuracy of the ST-CNN model was 96.67%. In addition, a virtual urban traffic scene in which real-time command tests were carried out was set up, and a real-time test accuracy rate of 93.0% was achieved. The proposed ST-CNN model ensured a high level of accuracy and robustness. The ST-CNN model recognized traffic command gestures, and such recognition was found to control vehicles in virtual traffic environments, which enriches the interactive mode of the virtual city scene. Traffic command gesture recognition contributes to smart city construction.

Neural Substrates of Auditory Emotion Recognition Deficits in Schizophrenia.

Science.gov (United States)

Kantrowitz, Joshua T; Hoptman, Matthew J; Leitman, David I; Moreno-Ortega, Marta; Lehrfeld, Jonathan M; Dias, Elisa; Sehatpour, Pejman; Laukka, Petri; Silipo, Gail; Javitt, Daniel C

2015-11-04

Deficits in auditory emotion recognition (AER) are a core feature of schizophrenia and a key component of social cognitive impairment. AER deficits are tied behaviorally to impaired ability to interpret tonal ("prosodic") features of speech that normally convey emotion, such as modulations in base pitch (F0M) and pitch variability (F0SD). These modulations can be recreated using synthetic frequency modulated (FM) tones that mimic the prosodic contours of specific emotional stimuli. The present study investigates neural mechanisms underlying impaired AER using a combined event-related potential/resting-state functional connectivity (rsfMRI) approach in 84 schizophrenia/schizoaffective disorder patients and 66 healthy comparison subjects. Mismatch negativity (MMN) to FM tones was assessed in 43 patients/36 controls. rsfMRI between auditory cortex and medial temporal (insula) regions was assessed in 55 patients/51 controls. The relationship between AER, MMN to FM tones, and rsfMRI was assessed in the subset who performed all assessments (14 patients, 21 controls). As predicted, patients showed robust reductions in MMN across FM stimulus type (p = 0.005), particularly to modulations in F0M, along with impairments in AER and FM tone discrimination. MMN source analysis indicated dipoles in both auditory cortex and anterior insula, whereas rsfMRI analyses showed reduced auditory-insula connectivity. MMN to FM tones and functional connectivity together accounted for ∼50% of the variance in AER performance across individuals. These findings demonstrate that impaired preattentive processing of tonal information and reduced auditory-insula connectivity are critical determinants of social cognitive dysfunction in schizophrenia, and thus represent key targets for future research and clinical intervention. Schizophrenia patients show deficits in the ability to infer emotion based upon tone of voice [auditory emotion recognition (AER)] that drive impairments in social cognition

Orientation Encoding and Viewpoint Invariance in Face Recognition: Inferring Neural Properties from Large-Scale Signals.

Science.gov (United States)

Ramírez, Fernando M

2018-05-01

Viewpoint-invariant face recognition is thought to be subserved by a distributed network of occipitotemporal face-selective areas that, except for the human anterior temporal lobe, have been shown to also contain face-orientation information. This review begins by highlighting the importance of bilateral symmetry for viewpoint-invariant recognition and face-orientation perception. Then, monkey electrophysiological evidence is surveyed describing key tuning properties of face-selective neurons-including neurons bimodally tuned to mirror-symmetric face-views-followed by studies combining functional magnetic resonance imaging (fMRI) and multivariate pattern analyses to probe the representation of face-orientation and identity information in humans. Altogether, neuroimaging studies suggest that face-identity is gradually disentangled from face-orientation information along the ventral visual processing stream. The evidence seems to diverge, however, regarding the prevalent form of tuning of neural populations in human face-selective areas. In this context, caveats possibly leading to erroneous inferences regarding mirror-symmetric coding are exposed, including the need to distinguish angular from Euclidean distances when interpreting multivariate pattern analyses. On this basis, this review argues that evidence from the fusiform face area is best explained by a view-sensitive code reflecting head angular disparity, consistent with a role of this area in face-orientation perception. Finally, the importance is stressed of explicit models relating neural properties to large-scale signals.

Artificial neural networks in NDT

International Nuclear Information System (INIS)

Abdul Aziz Mohamed

2001-01-01

Artificial neural networks, simply known as neural networks, have attracted considerable interest in recent years largely because of a growing recognition of the potential of these computational paradigms as powerful alternative models to conventional pattern recognition or function approximation techniques. The neural networks approach is having a profound effect on almost all fields, and has been utilised in fields Where experimental inter-disciplinary work is being carried out. Being a multidisciplinary subject with a broad knowledge base, Nondestructive Testing (NDT) or Nondestructive Evaluation (NDE) is no exception. This paper explains typical applications of neural networks in NDT/NDE. Three promising types of neural networks are highlighted, namely, back-propagation, binary Hopfield and Kohonen's self-organising maps. (Author)

Neural correlates of own- and other-race face recognition in children: a functional near-infrared spectroscopy study.

Science.gov (United States)

Ding, Xiao Pan; Fu, Genyue; Lee, Kang

2014-01-15

The present study used the functional Near-infrared Spectroscopy (fNIRS) methodology to investigate the neural correlates of elementary school children's own- and other-race face processing. An old-new paradigm was used to assess children's recognition ability of own- and other-race faces. FNIRS data revealed that other-race faces elicited significantly greater [oxy-Hb] changes than own-race faces in the right middle frontal gyrus and inferior frontal gyrus regions (BA9) and the left cuneus (BA18). With increased age, the [oxy-Hb] activity differences between own- and other-race faces, or the neural other-race effect (NORE), underwent significant changes in these two cortical areas: at younger ages, the neural response to the other-race faces was modestly greater than that to the own-race faces, but with increased age, the neural response to the own-race faces became increasingly greater than that to the other-race faces. Moreover, these areas had strong regional functional connectivity with a swath of the cortical regions in terms of the neural other-race effect that also changed with increased age. We also found significant and positive correlations between the behavioral other-race effect (reaction time) and the neural other-race effect in the right middle frontal gyrus and inferior frontal gyrus regions (BA9). These results taken together suggest that children, like adults, devote different amounts of neural resources to processing own- and other-race faces, but the size and direction of the neural other-race effect and associated functional regional connectivity change with increased age. © 2013.

Differential expression of the neural cell adhesion molecule NCAM 140 in human pituitary tumors

OpenAIRE

Aletsee-Ufrecht, M. C.; Langley, O. K.; Gratzl, O.; Gratzl, Manfred

1990-01-01

We have analyzed the expression of the intracellular marker protein neuron specific enolase (NSE), synaptophysin (SYN) and of the cell surface marker NCAM (neural cell adhesion molecule) in both normal human hypophysis and in pituitary adenomas in order to explore their potential use as diagnostic tools. All adenomas (4 prolactinomas, 3 growth hormone (GH) producing adenomas and 4 inactive adenomas) showed SYN and NSE immunoreactivity on tissue sections and this was confirmed by immunoblots. ...

Development and Comparative Study of Effects of Training Algorithms on Performance of Artificial Neural Network Based Analog and Digital Automatic Modulation Recognition

Directory of Open Access Journals (Sweden)

Jide Julius Popoola

2015-11-01

Full Text Available This paper proposes two new classifiers that automatically recognise twelve combined analog and digital modulated signals without any a priori knowledge of the modulation schemes and the modulation parameters. The classifiers are developed using pattern recognition approach. Feature keys extracted from the instantaneous amplitude, instantaneous phase and the spectrum symmetry of the simulated signals are used as inputs to the artificial neural network employed in developing the classifiers. The two developed classifiers are trained using scaled conjugate gradient (SCG and conjugate gradient (CONJGRAD training algorithms. Sample results of the two classifiers show good success recognition performance with an average overall recognition rate above 99.50% at signal-to-noise ratio (SNR value from 0 dB and above with the two training algorithms employed and an average overall recognition rate slightly above 99.00% and 96.40% respectively at - 5 dB SNR value for SCG and CONJGRAD training algorithms. The comparative performance evaluation of the two developed classifiers using the two training algorithms shows that the two training algorithms have different effects on both the response rate and efficiency of the two developed artificial neural networks classifiers. In addition, the result of the performance evaluation carried out on the overall success recognition rates between the two developed classifiers in this study using pattern recognition approach with the two training algorithms and one reported classifier in surveyed literature using decision-theoretic approach shows that the classifiers developed in this study perform favourably with regard to accuracy and performance probability as compared to classifier presented in previous study.

Infant visual attention and object recognition.

Science.gov (United States)

Reynolds, Greg D

2015-05-15

This paper explores the role visual attention plays in the recognition of objects in infancy. Research and theory on the development of infant attention and recognition memory are reviewed in three major sections. The first section reviews some of the major findings and theory emerging from a rich tradition of behavioral research utilizing preferential looking tasks to examine visual attention and recognition memory in infancy. The second section examines research utilizing neural measures of attention and object recognition in infancy as well as research on brain-behavior relations in the early development of attention and recognition memory. The third section addresses potential areas of the brain involved in infant object recognition and visual attention. An integrated synthesis of some of the existing models of the development of visual attention is presented which may account for the observed changes in behavioral and neural measures of visual attention and object recognition that occur across infancy. Copyright © 2015 Elsevier B.V. All rights reserved.

Adjunctive selective estrogen receptor modulator increases neural activity in the hippocampus and inferior frontal gyrus during emotional face recognition in schizophrenia.

Science.gov (United States)

Ji, E; Weickert, C S; Lenroot, R; Kindler, J; Skilleter, A J; Vercammen, A; White, C; Gur, R E; Weickert, T W

2016-05-03

Estrogen has been implicated in the development and course of schizophrenia with most evidence suggesting a neuroprotective effect. Treatment with raloxifene, a selective estrogen receptor modulator, can reduce symptom severity, improve cognition and normalize brain activity during learning in schizophrenia. People with schizophrenia are especially impaired in the identification of negative facial emotions. The present study was designed to determine the extent to which adjunctive raloxifene treatment would alter abnormal neural activity during angry facial emotion recognition in schizophrenia. Twenty people with schizophrenia (12 men, 8 women) participated in a 13-week, randomized, double-blind, placebo-controlled, crossover trial of adjunctive raloxifene treatment (120 mg per day orally) and performed a facial emotion recognition task during functional magnetic resonance imaging after each treatment phase. Two-sample t-tests in regions of interest selected a priori were performed to assess activation differences between raloxifene and placebo conditions during the recognition of angry faces. Adjunctive raloxifene significantly increased activation in the right hippocampus and left inferior frontal gyrus compared with the placebo condition (family-wise error, Precognition in schizophrenia. These findings support the hypothesis that estrogen plays a modifying role in schizophrenia and shows that adjunctive raloxifene treatment may reverse abnormal neural activity during facial emotion recognition, which is relevant to impaired social functioning in men and women with schizophrenia.

CL-L1 and CL-K1 and other complement associated pattern recognition molecules in systemic lupus erythematosus

DEFF Research Database (Denmark)

Troldborg, Anne; Thiel, Steffen; Jensen, Lisbeth

2015-01-01

The objective of this study was to explore the involvement of collectin liver 1 (CL-L1) and collectin kidney 1 (CL-K1) and other pattern recognition molecules (PRMs) of the lectin pathway of the complement system in a cross-sectional cohort of systemic lupus erythematosus (SLE) patients...

The innate pattern recognition molecule Ficolin-1 is secreted by monocytes/macrophages and is circulating in human plasma

DEFF Research Database (Denmark)

Honoré, Christian; Rørvig, Sara; Munthe-Fog, Lea

2008-01-01

Ficolin-1 (M-Ficolin) is a pattern recognition molecule of the complement system that is expressed by myeloid cells and type II alveolar epithelial cells. Ficolin-1 has been shown to localize in the secretory granules of these cells and attached to cell surfaces, but whether Ficolin-1 exists...

Aberrant neural networks for the recognition memory of socially relevant information in patients with schizophrenia.

Science.gov (United States)

Oh, Jooyoung; Chun, Ji-Won; Kim, Eunseong; Park, Hae-Jeong; Lee, Boreom; Kim, Jae-Jin

2017-01-01

Patients with schizophrenia exhibit several cognitive deficits, including memory impairment. Problems with recognition memory can hinder socially adaptive behavior. Previous investigations have suggested that altered activation of the frontotemporal area plays an important role in recognition memory impairment. However, the cerebral networks related to these deficits are not known. The aim of this study was to elucidate the brain networks required for recognizing socially relevant information in patients with schizophrenia performing an old-new recognition task. Sixteen patients with schizophrenia and 16 controls participated in this study. First, the subjects performed the theme-identification task during functional magnetic resonance imaging. In this task, pictures depicting social situations were presented with three words, and the subjects were asked to select the best theme word for each picture. The subjects then performed an old-new recognition task in which they were asked to discriminate whether the presented words were old or new. Task performance and neural responses in the old-new recognition task were compared between the subject groups. An independent component analysis of the functional connectivity was performed. The patients with schizophrenia exhibited decreased discriminability and increased activation of the right superior temporal gyrus compared with the controls during correct responses. Furthermore, aberrant network activities were found in the frontopolar and language comprehension networks in the patients. The functional connectivity analysis showed aberrant connectivity in the frontopolar and language comprehension networks in the patients with schizophrenia, and these aberrations possibly contribute to their low recognition performance and social dysfunction. These results suggest that the frontopolar and language comprehension networks are potential therapeutic targets in patients with schizophrenia.

Expression of neural cell adhesion molecules and neurofilament protein isoforms in Ewing's sarcoma of bone and soft tissue sarcomas of other than rhabdomyosarcoma

NARCIS (Netherlands)

Molenaar, W.M.; Muntinghe, F.L.H.

1999-01-01

In a previous study, it was shown that rhabdomyosarcomas widely express "neural" markers, such as neural cell adhesion molecules (N-CAM) and neurofilament protein isoforms, In the current study, a series of Ewing's sarcomas of bone and soft tissue sarcomas other than rhabdomyosarcoma was probed for

Intelligent Image Recognition System for Marine Fouling Using Softmax Transfer Learning and Deep Convolutional Neural Networks

Directory of Open Access Journals (Sweden)

C. S. Chin

2017-01-01

Full Text Available The control of biofouling on marine vessels is challenging and costly. Early detection before hull performance is significantly affected is desirable, especially if “grooming” is an option. Here, a system is described to detect marine fouling at an early stage of development. In this study, an image of fouling can be transferred wirelessly via a mobile network for analysis. The proposed system utilizes transfer learning and deep convolutional neural network (CNN to perform image recognition on the fouling image by classifying the detected fouling species and the density of fouling on the surface. Transfer learning using Google’s Inception V3 model with Softmax at last layer was carried out on a fouling database of 10 categories and 1825 images. Experimental results gave acceptable accuracies for fouling detection and recognition.

Online handwritten mathematical expression recognition

Science.gov (United States)

Büyükbayrak, Hakan; Yanikoglu, Berrin; Erçil, Aytül

2007-01-01

We describe a system for recognizing online, handwritten mathematical expressions. The system is designed with a user-interface for writing scientific articles, supporting the recognition of basic mathematical expressions as well as integrals, summations, matrices etc. A feed-forward neural network recognizes symbols which are assumed to be single-stroke and a recursive algorithm parses the expression by combining neural network output and the structure of the expression. Preliminary results show that writer-dependent recognition rates are very high (99.8%) while writer-independent symbol recognition rates are lower (75%). The interface associated with the proposed system integrates the built-in recognition capabilities of the Microsoft's Tablet PC API for recognizing textual input and supports conversion of hand-drawn figures into PNG format. This enables the user to enter text, mathematics and draw figures in a single interface. After recognition, all output is combined into one LATEX code and compiled into a PDF file.

Convolutional neural networks with balanced batches for facial expressions recognition

Science.gov (United States)

Battini Sönmez, Elena; Cangelosi, Angelo

2017-03-01

This paper considers the issue of fully automatic emotion classification on 2D faces. In spite of the great effort done in recent years, traditional machine learning approaches based on hand-crafted feature extraction followed by the classification stage failed to develop a real-time automatic facial expression recognition system. The proposed architecture uses Convolutional Neural Networks (CNN), which are built as a collection of interconnected processing elements to simulate the brain of human beings. The basic idea of CNNs is to learn a hierarchical representation of the input data, which results in a better classification performance. In this work we present a block-based CNN algorithm, which uses noise, as data augmentation technique, and builds batches with a balanced number of samples per class. The proposed architecture is a very simple yet powerful CNN, which can yield state-of-the-art accuracy on the very competitive benchmark algorithm of the Extended Cohn Kanade database.

Hierarchical Feature Extraction With Local Neural Response for Image Recognition.

Science.gov (United States)

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.

Automatic modulation format recognition for the next generation optical communication networks using artificial neural networks

Science.gov (United States)

Guesmi, Latifa; Hraghi, Abir; Menif, Mourad

2015-03-01

A new technique for Automatic Modulation Format Recognition (AMFR) in next generation optical communication networks is presented. This technique uses the Artificial Neural Network (ANN) in conjunction with the features of Linear Optical Sampling (LOS) of the detected signal at high bit rates using direct detection or coherent detection. The use of LOS method for this purpose mainly driven by the increase of bit rates which enables the measurement of eye diagrams. The efficiency of this technique is demonstrated under different transmission impairments such as chromatic dispersion (CD) in the range of -500 to 500 ps/nm, differential group delay (DGD) in the range of 0-15 ps and the optical signal tonoise ratio (OSNR) in the range of 10-30 dB. The results of numerical simulation for various modulation formats demonstrate successful recognition from a known bit rates with a higher estimation accuracy, which exceeds 99.8%.

Neural Networks: Implementations and Applications

OpenAIRE

Vonk, E.; Veelenturf, L.P.J.; Jain, L.C.

1996-01-01

Artificial neural networks, also called neural networks, have been used successfully in many fields including engineering, science and business. This paper presents the implementation of several neural network simulators and their applications in character recognition and other engineering areas

Neural circuitry for rat recognition memory

Science.gov (United States)

Warburton, E.C.; Brown, M.W.

2015-01-01

Information concerning the roles of different brain regions in recognition memory processes is reviewed. The review concentrates on findings from spontaneous recognition memory tasks performed by rats, including memory for single objects, locations, object–location associations and temporal order. Particular emphasis is given to the potential roles of different regions in the circuit of interacting structures involving the perirhinal cortex, hippocampus, medial prefrontal cortex and medial dorsal thalamus in recognition memory for the association of objects and places. It is concluded that while all structures in this circuit play roles critical to such memory, these roles can potentially be differentiated and differences in the underlying synaptic and biochemical processes involved in each region are beginning to be uncovered. PMID:25315129

Artificial Neural Network Based Optical Character Recognition

OpenAIRE

Vivek Shrivastava; Navdeep Sharma

2012-01-01

Optical Character Recognition deals in recognition and classification of characters from an image. For the recognition to be accurate, certain topological and geometrical properties are calculated, based on which a character is classified and recognized. Also, the Human psychology perceives characters by its overall shape and features such as strokes, curves, protrusions, enclosures etc. These properties, also called Features are extracted from the image by means of spatial pixel-...

Automatic recognition of alertness and drowsiness from EEG by an artificial neural network.

Science.gov (United States)

Vuckovic, Aleksandra; Radivojevic, Vlada; Chen, Andrew C N; Popovic, Dejan

2002-06-01

We present a novel method for classifying alert vs drowsy states from 1 s long sequences of full spectrum EEG recordings in an arbitrary subject. This novel method uses time series of interhemispheric and intrahemispheric cross spectral densities of full spectrum EEG as the input to an artificial neural network (ANN) with two discrete outputs: drowsy and alert. The experimental data were collected from 17 subjects. Two experts in EEG interpretation visually inspected the data and provided the necessary expertise for the training of an ANN. We selected the following three ANNs as potential candidates: (1) the linear network with Widrow-Hoff (WH) algorithm; (2) the non-linear ANN with the Levenberg-Marquardt (LM) rule; and (3) the Learning Vector Quantization (LVQ) neural network. We showed that the LVQ neural network gives the best classification compared with the linear network that uses WH algorithm (the worst), and the non-linear network trained with the LM rule. Classification properties of LVQ were validated using the data recorded in 12 healthy volunteer subjects, yet whose EEG recordings have not been used for the training of the ANN. The statistics were used as a measure of potential applicability of the LVQ: the t-distribution showed that matching between the human assessment and the network output was 94.37+/-1.95%. This result suggests that the automatic recognition algorithm is applicable for distinguishing between alert and drowsy state in recordings that have not been used for the training.

Binary patterns encoded convolutional neural networks for texture recognition and remote sensing scene classification

Science.gov (United States)

Anwer, Rao Muhammad; Khan, Fahad Shahbaz; van de Weijer, Joost; Molinier, Matthieu; Laaksonen, Jorma

2018-04-01

Designing discriminative powerful texture features robust to realistic imaging conditions is a challenging computer vision problem with many applications, including material recognition and analysis of satellite or aerial imagery. In the past, most texture description approaches were based on dense orderless statistical distribution of local features. However, most recent approaches to texture recognition and remote sensing scene classification are based on Convolutional Neural Networks (CNNs). The de facto practice when learning these CNN models is to use RGB patches as input with training performed on large amounts of labeled data (ImageNet). In this paper, we show that Local Binary Patterns (LBP) encoded CNN models, codenamed TEX-Nets, trained using mapped coded images with explicit LBP based texture information provide complementary information to the standard RGB deep models. Additionally, two deep architectures, namely early and late fusion, are investigated to combine the texture and color information. To the best of our knowledge, we are the first to investigate Binary Patterns encoded CNNs and different deep network fusion architectures for texture recognition and remote sensing scene classification. We perform comprehensive experiments on four texture recognition datasets and four remote sensing scene classification benchmarks: UC-Merced with 21 scene categories, WHU-RS19 with 19 scene classes, RSSCN7 with 7 categories and the recently introduced large scale aerial image dataset (AID) with 30 aerial scene types. We demonstrate that TEX-Nets provide complementary information to standard RGB deep model of the same network architecture. Our late fusion TEX-Net architecture always improves the overall performance compared to the standard RGB network on both recognition problems. Furthermore, our final combination leads to consistent improvement over the state-of-the-art for remote sensing scene classification.

Spiking neural networks for handwritten digit recognition-Supervised learning and network optimization.

Science.gov (United States)

Kulkarni, Shruti R; Rajendran, Bipin

2018-07-01

We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classification accuracy of 98.17% on the MNIST test database with four times fewer parameters compared to the state-of-the-art. We present several insights from extensive numerical experiments regarding optimization of learning parameters and network configuration to improve its accuracy. We also describe a number of strategies to optimize the SNN for implementation in memory and energy constrained hardware, including approximations in computing the neuronal dynamics and reduced precision in storing the synaptic weights. Experiments reveal that even with 3-bit synaptic weights, the classification accuracy of the designed SNN does not degrade beyond 1% as compared to the floating-point baseline. Further, the proposed SNN, which is trained based on the precise spike timing information outperforms an equivalent non-spiking artificial neural network (ANN) trained using back propagation, especially at low bit precision. Thus, our study shows the potential for realizing efficient neuromorphic systems that use spike based information encoding and learning for real-world applications. Copyright © 2018 Elsevier Ltd. All rights reserved.

Arabic Handwriting Recognition Using Neural Network Classifier

African Journals Online (AJOL)

pc

2018-03-05

Mar 5, 2018 ... an OCR using Neural Network classifier preceded by a set of preprocessing .... Artificial Neural Networks (ANNs), which we adopt in this research, consist of ... advantage and disadvantages of each technique. In [9],. Khemiri ...

Cognitive disorder and changes in cholinergic receptors, N-methyl-D aspartate receptors, neural cell adhesion molecule, and brain-derived neurotrophic factor following brain injury

Institute of Scientific and Technical Information of China (English)

Weiliang Zhao; Dezhi Kang; Yuanxiang Lin

2008-01-01

BACKGROUND: Learning and memory damage is one of the most permanent and the severest symptoms of traumatic brain injury; it can seriously influence the normal life and work of patients. Some research has demonstrated that cognitive disorder is closely related to nicotine cholinergic receptors, N-methyl-D aspartate receptors, neural cell adhesion molecule, and brain-derived neurotrophic factor. OBJECTIVE: To summarize the cognitive disorder and changes in nicotine cholinergic receptors, N-methyl-D aspartate receptors, neural cell adhesion molecule, and brain-derived neurotrophic factor following brain injury. RETRIEVAL STRATEGY: A computer-based online search was conducted in PUBMED for English language publications containing the key words "brain injured, cognitive handicap, acetylcholine, N-methyl-D aspartate receptors, neural cell adhesion molecule, brain-derived neurotrophic factor" from January 2000 to December 2007. There were 44 papers in total. Inclusion criteria: ① articles about changes in nicotine cholinergic receptors, N-methyl-D aspartate receptors, neural cell adhesion molecule, and brain-derived neurotrophic factor following brain injury; ② articles in the same researching circle published in authoritative journals or recently published. Exclusion criteria: duplicated articles.LITERATURE EVALUATION: References were mainly derived from research on changes in these four factors following brain injury. The 20 included papers were clinical or basic experimental studies. DATA SYNTHESIS: After craniocerebral injury, changes in these four factors in brain were similar to those during recovery from cognitive disorder, to a certain degree. Some data have indicated that activation of nicotine cholinergic receptors, N-methyl-D aspartate receptors, neural cell adhesion molecule, and brain-derived neurotrophic factor could greatly improve cognitive disorder following brain injury. However, there are still a lot of questions remaining; for example, how do these

Pattern activation/recognition theory of mind.

Science.gov (United States)

du Castel, Bertrand

2015-01-01

In his 2012 book How to Create a Mind, Ray Kurzweil defines a "Pattern Recognition Theory of Mind" that states that the brain uses millions of pattern recognizers, plus modules to check, organize, and augment them. In this article, I further the theory to go beyond pattern recognition and include also pattern activation, thus encompassing both sensory and motor functions. In addition, I treat checking, organizing, and augmentation as patterns of patterns instead of separate modules, therefore handling them the same as patterns in general. Henceforth I put forward a unified theory I call "Pattern Activation/Recognition Theory of Mind." While the original theory was based on hierarchical hidden Markov models, this evolution is based on their precursor: stochastic grammars. I demonstrate that a class of self-describing stochastic grammars allows for unifying pattern activation, recognition, organization, consistency checking, metaphor, and learning, into a single theory that expresses patterns throughout. I have implemented the model as a probabilistic programming language specialized in activation/recognition grammatical and neural operations. I use this prototype to compute and present diagrams for each stochastic grammar and corresponding neural circuit. I then discuss the theory as it relates to artificial network developments, common coding, neural reuse, and unity of mind, concluding by proposing potential paths to validation.

The pattern recognition molecule deleted in malignant brain tumors 1 (DMBT1) and synthetic mimics inhibit liposomal nucleic acid delivery

DEFF Research Database (Denmark)

Lund Hansen, Pernille; Blaich, Stephanie; End, Caroline

2011-01-01

Liposomal nucleic acid delivery is a preferred option for therapeutic settings. The cellular pattern recognition molecule DMBT1, secreted at high levels in various diseases, and synthetic mimics efficiently inhibit liposomal nucleic acid delivery to human cells. These findings may have relevance...

Object recognition memory: neurobiological mechanisms of encoding, consolidation and retrieval.

Science.gov (United States)

Winters, Boyer D; Saksida, Lisa M; Bussey, Timothy J

2008-07-01

Tests of object recognition memory, or the judgment of the prior occurrence of an object, have made substantial contributions to our understanding of the nature and neurobiological underpinnings of mammalian memory. Only in recent years, however, have researchers begun to elucidate the specific brain areas and neural processes involved in object recognition memory. The present review considers some of this recent research, with an emphasis on studies addressing the neural bases of perirhinal cortex-dependent object recognition memory processes. We first briefly discuss operational definitions of object recognition and the common behavioural tests used to measure it in non-human primates and rodents. We then consider research from the non-human primate and rat literature examining the anatomical basis of object recognition memory in the delayed nonmatching-to-sample (DNMS) and spontaneous object recognition (SOR) tasks, respectively. The results of these studies overwhelmingly favor the view that perirhinal cortex (PRh) is a critical region for object recognition memory. We then discuss the involvement of PRh in the different stages--encoding, consolidation, and retrieval--of object recognition memory. Specifically, recent work in rats has indicated that neural activity in PRh contributes to object memory encoding, consolidation, and retrieval processes. Finally, we consider the pharmacological, cellular, and molecular factors that might play a part in PRh-mediated object recognition memory. Recent studies in rodents have begun to indicate the remarkable complexity of the neural substrates underlying this seemingly simple aspect of declarative memory.

Korean letter handwritten recognition using deep convolutional neural network on android platform

Science.gov (United States)

Purnamawati, S.; Rachmawati, D.; Lumanauw, G.; Rahmat, R. F.; Taqyuddin, R.

2018-03-01

Currently, popularity of Korean culture attracts many people to learn everything about Korea, particularly its language. To acquire Korean Language, every single learner needs to be able to understand Korean non-Latin character. A digital approach needs to be carried out in order to make Korean learning process easier. This study is done by using Deep Convolutional Neural Network (DCNN). DCNN performs the recognition process on the image based on the model that has been trained such as Inception-v3 Model. Subsequently, re-training process using transfer learning technique with the trained and re-trained value of model is carried though in order to develop a new model with a better performance without any specific systemic errors. The testing accuracy of this research results in 86,9%.

Self-Organizing Neural Integration of Pose-Motion Features for Human Action Recognition

Directory of Open Access Journals (Sweden)

German Ignacio Parisi

2015-06-01

Full Text Available The visual recognition of complex, articulated human movements is fundamental for a wide range of artificial systems oriented towards human-robot communication, action classification, and action-driven perception. These challenging tasks may generally involve the processing of a huge amount of visual information and learning-based mechanisms for generalizing a set of training actions and classifying new samples. To operate in natural environments, a crucial property is the efficient and robust recognition of actions, also under noisy conditions caused by, for instance, systematic sensor errors and temporarily occluded persons. Studies of the mammalian visual system and its outperforming ability to process biological motion information suggest separate neural pathways for the distinct processing of pose and motion features at multiple levels and the subsequent integration of these visual cues for action perception. We present a neurobiologically-motivated approach to achieve noise-tolerant action recognition in real time. Our model consists of self-organizing Growing When Required (GWR networks that obtain progressively generalized representations of sensory inputs and learn inherent spatiotemporal dependencies. During the training, the GWR networks dynamically change their topological structure to better match the input space. We first extract pose and motion features from video sequences and then cluster actions in terms of prototypical pose-motion trajectories. Multi-cue trajectories from matching action frames are subsequently combined to provide action dynamics in the joint feature space. Reported experiments show that our approach outperforms previous results on a dataset of full-body actions captured with a depth sensor, and ranks among the best 21 results for a public benchmark of domestic daily actions.

Neural cell adhesion molecule (NCAM) and prealbumin in cerebrospinal fluid from depressed patients

DEFF Research Database (Denmark)

Jørgensen, Ole Steen

1988-01-01

The size of the soluble form of the human cerebrospinal fluid (CSF) neural cell adhesion molecule, NCAM-sol, was by gel permeation chromatography estimated to 160-250 kDa. Within the CSF the concentration of NCAM-sol was found about 15-25% increased in lumbar fluid and 25% increased in ventricular...... fluid, both compared to cisternal fluid. Whereas prealbumin was found evenly distributed in CSF, albumin was relatively enriched in lumbar fluid. The concentrations of NCAM-sol and prealbumin were measured in lumbar CSF from psychiatric patients. Prealbumin was increased 7.2% and NCAM-sol was decreased...

Distributed Learning, Recognition, and Prediction by ART and ARTMAP Neural Networks.

Science.gov (United States)

Carpenter, Gail A.

1997-11-01

A class of adaptive resonance theory (ART) models for learning, recognition, and prediction with arbitrarily distributed code representations is introduced. Distributed ART neural networks combine the stable fast learning capabilities of winner-take-all ART systems with the noise tolerance and code compression capabilities of multilayer perceptrons. With a winner-take-all code, the unsupervised model dART reduces to fuzzy ART and the supervised model dARTMAP reduces to fuzzy ARTMAP. With a distributed code, these networks automatically apportion learned changes according to the degree of activation of each coding node, which permits fast as well as slow learning without catastrophic forgetting. Distributed ART models replace the traditional neural network path weight with a dynamic weight equal to the rectified difference between coding node activation and an adaptive threshold. Thresholds increase monotonically during learning according to a principle of atrophy due to disuse. However, monotonic change at the synaptic level manifests itself as bidirectional change at the dynamic level, where the result of adaptation resembles long-term potentiation (LTP) for single-pulse or low frequency test inputs but can resemble long-term depression (LTD) for higher frequency test inputs. This paradoxical behavior is traced to dual computational properties of phasic and tonic coding signal components. A parallel distributed match-reset-search process also helps stabilize memory. Without the match-reset-search system, dART becomes a type of distributed competitive learning network.

Organic Zeolite Analogues Based on Multi-Component Liquid Crystals: Recognition and Transformation of Molecules within Constrained Environments

Directory of Open Access Journals (Sweden)

Yasuhiro Ishida

2011-01-01

Full Text Available In liquid crystals (LCs, molecules are confined in peculiar environments, where ordered alignment and certain mobility are realized at the same time. Considering these characteristics, the idea of “controlling molecular events within LC media” seems reasonable. As a suitable system for investigating this challenge, we have recently developed a new class of ionic LCs; the salts of amphiphilic carboxylic acids with 2-amino alcohols, or those of carboxylic acids with amphiphilic 2-amino alcohols, have a strong tendency to exhibit thermotropic LC phases. Because of the noncovalent nature of the interaction between molecules, one of the two components can easily be exchanged with, or transformed into, another molecule, without distorting the original LC architecture. In addition, both components are common organic molecules, and a variety of compounds are easily available. Taking advantage of these characteristics, we have succeeded in applying two‑component LCs as chiral media for molecular recognition and reactions. This review presents an overview of our recent studies, together with notable reports related to this field.

Reducing weight precision of convolutional neural networks towards large-scale on-chip image recognition

Science.gov (United States)

Ji, Zhengping; Ovsiannikov, Ilia; Wang, Yibing; Shi, Lilong; Zhang, Qiang

2015-05-01

In this paper, we develop a server-client quantization scheme to reduce bit resolution of deep learning architecture, i.e., Convolutional Neural Networks, for image recognition tasks. Low bit resolution is an important factor in bringing the deep learning neural network into hardware implementation, which directly determines the cost and power consumption. We aim to reduce the bit resolution of the network without sacrificing its performance. To this end, we design a new quantization algorithm called supervised iterative quantization to reduce the bit resolution of learned network weights. In the training stage, the supervised iterative quantization is conducted via two steps on server - apply k-means based adaptive quantization on learned network weights and retrain the network based on quantized weights. These two steps are alternated until the convergence criterion is met. In this testing stage, the network configuration and low-bit weights are loaded to the client hardware device to recognize coming input in real time, where optimized but expensive quantization becomes infeasible. Considering this, we adopt a uniform quantization for the inputs and internal network responses (called feature maps) to maintain low on-chip expenses. The Convolutional Neural Network with reduced weight and input/response precision is demonstrated in recognizing two types of images: one is hand-written digit images and the other is real-life images in office scenarios. Both results show that the new network is able to achieve the performance of the neural network with full bit resolution, even though in the new network the bit resolution of both weight and input are significantly reduced, e.g., from 64 bits to 4-5 bits.

H-1 and N-15 resonance assignment of the second fibronectin type III module of the neural cell adhesion molecule

DEFF Research Database (Denmark)

Kiselyov, Vladislav V; Berezin, Vladimir; Bock, Elisabeth

2008-01-01

We report here the NMR assignment of the second fibronectin type III module of the neural cell adhesion molecule (NCAM). This module has previously been shown to interact with the fibroblast growth factor receptor (FGFR), and the FGFR-binding site was mapped by NMR to the FG-loop region of the mo......We report here the NMR assignment of the second fibronectin type III module of the neural cell adhesion molecule (NCAM). This module has previously been shown to interact with the fibroblast growth factor receptor (FGFR), and the FGFR-binding site was mapped by NMR to the FG-loop region...... of the module. The FG-loop region also contains a putative nucleotide-binding motif, which was shown by NMR to interact with ATP. Furthermore, ATP was demonstrated to inhibit binding of the second F3 module of NCAM to FGFR....

NATO Advanced Research Workshop on Chemosensors of Ion and Molecule Recognition

CERN Document Server

Czarnik, A

1997-01-01

In the broad field of supramolecular chemistry, the design and hence the use of chemosensors for ion and molecule recognition have developed at an extroardinary rate. This imaginative and creative area which involves the interface of different disciplines, e.g. organic and inorganic chemistry, physical chemistry, biology, medicine, environmental science, is not only fundamental in nature. It is also clear that progress is most rewarding for several new sensor applications deriving from the specific signal delivered by the analyte-probe interaction. Indeed, if calcium sensing in real time for biological purposes is actually possible, owing to the emergence of efficient fluorescent receptors, other elements can also be specifically detected, identified and finally titrated using tailored chemosensors. Pollutants such as heavy metals or radionuclides are among the main targets since their detection and removal could be envisioned at very low concentrations with, in addition, sensors displaying specific and stron...

Paradigms in object recognition

International Nuclear Information System (INIS)

Mutihac, R.; Mutihac, R.C.

1999-09-01

A broad range of approaches has been proposed and applied for the complex and rather difficult task of object recognition that involves the determination of object characteristics and object classification into one of many a priori object types. Our paper revises briefly the three main different paradigms in pattern recognition, namely Bayesian statistics, neural networks, and expert systems. (author)

Recognition of abstract objects via neural oscillators: interaction among topological organization, associative memory and gamma band synchronization.

Science.gov (United States)

Ursino, Mauro; Magosso, Elisa; Cuppini, Cristiano

2009-02-01

Synchronization of neural activity in the gamma band is assumed to play a significant role not only in perceptual processing, but also in higher cognitive functions. Here, we propose a neural network of Wilson-Cowan oscillators to simulate recognition of abstract objects, each represented as a collection of four features. Features are ordered in topological maps of oscillators connected via excitatory lateral synapses, to implement a similarity principle. Experience on previous objects is stored in long-range synapses connecting the different topological maps, and trained via timing dependent Hebbian learning (previous knowledge principle). Finally, a downstream decision network detects the presence of a reliable object representation, when all features are oscillating in synchrony. Simulations performed giving various simultaneous objects to the network (from 1 to 4), with some missing and/or modified properties suggest that the network can reconstruct objects, and segment them from the other simultaneously present objects, even in case of deteriorated information, noise, and moderate correlation among the inputs (one common feature). The balance between sensitivity and specificity depends on the strength of the Hebbian learning. Achieving a correct reconstruction in all cases, however, requires ad hoc selection of the oscillation frequency. The model represents an attempt to investigate the interactions among topological maps, autoassociative memory, and gamma-band synchronization, for recognition of abstract objects.

What are artificial neural networks?

DEFF Research Database (Denmark)

Krogh, Anders

2008-01-01

Artificial neural networks have been applied to problems ranging from speech recognition to prediction of protein secondary structure, classification of cancers and gene prediction. How do they work and what might they be good for? Udgivelsesdato: 2008-Feb......Artificial neural networks have been applied to problems ranging from speech recognition to prediction of protein secondary structure, classification of cancers and gene prediction. How do they work and what might they be good for? Udgivelsesdato: 2008-Feb...

Integration trumps selection in object recognition

Science.gov (United States)

Saarela, Toni P.; Landy, Michael S.

2015-01-01

Summary Finding and recognizing objects is a fundamental task of vision. Objects can be defined by several “cues” (color, luminance, texture etc.), and humans can integrate sensory cues to improve detection and recognition [1–3]. Cortical mechanisms fuse information from multiple cues [4], and shape-selective neural mechanisms can display cue-invariance by responding to a given shape independent of the visual cue defining it [5–8]. Selective attention, in contrast, improves recognition by isolating a subset of the visual information [9]. Humans can select single features (red or vertical) within a perceptual dimension (color or orientation), giving faster and more accurate responses to items having the attended feature [10,11]. Attention elevates neural responses and sharpens neural tuning to the attended feature, as shown by studies in psychophysics and modeling [11,12], imaging [13–16], and single-cell and neural population recordings [17,18]. Besides single features, attention can select whole objects [19–21]. Objects are among the suggested “units” of attention because attention to a single feature of an object causes the selection of all of its features [19–21]. Here, we pit integration against attentional selection in object recognition. We find, first, that humans can integrate information near-optimally from several perceptual dimensions (color, texture, luminance) to improve recognition. They cannot, however, isolate a single dimension even when the other dimensions provide task-irrelevant, potentially conflicting information. For object recognition, it appears that there is mandatory integration of information from multiple dimensions of visual experience. The advantage afforded by this integration, however, comes at the expense of attentional selection. PMID:25802154

Integration trumps selection in object recognition.

Science.gov (United States)

Saarela, Toni P; Landy, Michael S

2015-03-30

Finding and recognizing objects is a fundamental task of vision. Objects can be defined by several "cues" (color, luminance, texture, etc.), and humans can integrate sensory cues to improve detection and recognition [1-3]. Cortical mechanisms fuse information from multiple cues [4], and shape-selective neural mechanisms can display cue invariance by responding to a given shape independent of the visual cue defining it [5-8]. Selective attention, in contrast, improves recognition by isolating a subset of the visual information [9]. Humans can select single features (red or vertical) within a perceptual dimension (color or orientation), giving faster and more accurate responses to items having the attended feature [10, 11]. Attention elevates neural responses and sharpens neural tuning to the attended feature, as shown by studies in psychophysics and modeling [11, 12], imaging [13-16], and single-cell and neural population recordings [17, 18]. Besides single features, attention can select whole objects [19-21]. Objects are among the suggested "units" of attention because attention to a single feature of an object causes the selection of all of its features [19-21]. Here, we pit integration against attentional selection in object recognition. We find, first, that humans can integrate information near optimally from several perceptual dimensions (color, texture, luminance) to improve recognition. They cannot, however, isolate a single dimension even when the other dimensions provide task-irrelevant, potentially conflicting information. For object recognition, it appears that there is mandatory integration of information from multiple dimensions of visual experience. The advantage afforded by this integration, however, comes at the expense of attentional selection. Copyright © 2015 Elsevier Ltd. All rights reserved.

Fluid pipeline system leak detection based on neural network and pattern recognition

International Nuclear Information System (INIS)

Tang Xiujia

1998-01-01

The mechanism of the stress wave propagation along the pipeline system of NPP, caused by turbulent ejection from pipeline leakage, is researched. A series of characteristic index are described in time domain or frequency domain, and compress numerical algorithm is developed for original data compression. A back propagation neural networks (BPNN) with the input matrix composed by stress wave characteristics in time domain or frequency domain is first proposed to classify various situations of the pipeline, in order to detect the leakage in the fluid flow pipelines. The capability of the new method had been demonstrated by experiments and finally used to design a handy instrument for the pipeline leakage detection. Usually a pipeline system has many inner branches and often in adjusting dynamic condition, it is difficult for traditional pipeline diagnosis facilities to identify the difference between inner pipeline operation and pipeline fault. The author first proposed pipeline wave propagation identification by pattern recognition to diagnose pipeline leak. A series of pattern primitives such as peaks, valleys, horizon lines, capstan peaks, dominant relations, slave relations, etc., are used to extract features of the negative pressure wave form. The context-free grammar of symbolic representation of the negative wave form is used, and a negative wave form parsing system with application to structural pattern recognition based on the representation is first proposed to detect and localize leaks of the fluid pipelines

MHC class I molecules with superenhanced CD8 binding properties bypass the requirement for cognate TCR recognition and nonspecifically activate CTLs

NARCIS (Netherlands)

L. Wooldridge (Linda); M. Clement (Mathew); A. Lissina (Anna); E.S.J. Edwards (Emily); K. Ladell (Kristin); J. Ekeruche (Julia); R.E. Hewitt (Rachel); B. Laugel (Bruno); E. Gostick (Emma); D.K. Cole (David); J.E.M.A. Debets (Reno); C.A. Berrevoets (Cor); J.J. Miles (John); S.R. Burrows (Scott); D.A. Price (David); A.K. Sewell (Andrew)

2010-01-01

textabstractCD8+CTLs are essential for effective immune defense against intracellular microbes and neoplasia. CTLs recognize short peptide fragments presented in association with MHC class I (MHCI) molecules on the surface of infected or dysregulated cells. Ag recognition involves the binding of

Soluble Collectin-12 (CL-12) Is a Pattern Recognition Molecule Initiating Complement Activation via the Alternative Pathway

DEFF Research Database (Denmark)

Ma, Ying Jie; Hein, Estrid; Munthe-Fog, Lea

2015-01-01

and may recognize certain bacteria and fungi, leading to opsonophagocytosis. However, based on its structural and functional similarities with soluble collectins, we hypothesized the existence of a fluid-phase analog of CL-12 released from cells, which may function as a soluble pattern-recognition...... of the terminal complement complex. These results demonstrate the existence of CL-12 in a soluble form and indicate a novel mechanism by which the alternative pathway of complement may be triggered directly by a soluble pattern-recognition molecule....... nonreducing conditions it presented multimeric assembly forms. Immunoprecipitation and Western blot analysis of human umbilical cord plasma enabled identification of a natural soluble form of CL-12 having an electrophoretic mobility pattern close to that of shed soluble recombinant CL-12. Soluble CL-12 could...

The Neural Cell Adhesion Molecule-Derived Peptide FGL Facilitates Long-Term Plasticity in the Dentate Gyrus in Vivo

Science.gov (United States)

Dallerac, Glenn; Zerwas, Meike; Novikova, Tatiana; Callu, Delphine; Leblanc-Veyrac, Pascale; Bock, Elisabeth; Berezin, Vladimir; Rampon, Claire; Doyere, Valerie

2011-01-01

The neural cell adhesion molecule (NCAM) is known to play a role in developmental and structural processes but also in synaptic plasticity and memory of the adult animal. Recently, FGL, a NCAM mimetic peptide that binds to the Fibroblast Growth Factor Receptor 1 (FGFR-1), has been shown to have a beneficial impact on normal memory functioning, as…

Creative-Dynamics Approach To Neural Intelligence

Science.gov (United States)

Zak, Michail A.

1992-01-01

Paper discusses approach to mathematical modeling of artificial neural networks exhibiting complicated behaviors reminiscent of creativity and intelligence of biological neural networks. Neural network treated as non-Lipschitzian dynamical system - as described in "Non-Lipschitzian Dynamics For Modeling Neural Networks" (NPO-17814). System serves as tool for modeling of temporal-pattern memories and recognition of complicated spatial patterns.

Automated road marking recognition system

Science.gov (United States)

Ziyatdinov, R. R.; Shigabiev, R. R.; Talipov, D. N.

2017-09-01

Development of the automated road marking recognition systems in existing and future vehicles control systems is an urgent task. One way to implement such systems is the use of neural networks. To test the possibility of using neural network software has been developed with the use of a single-layer perceptron. The resulting system based on neural network has successfully coped with the task both when driving in the daytime and at night.

The neural cell adhesion molecule-derived peptide, FGL, attenuates lipopolysaccharide-induced changes in glia in a CD200-dependent manner

DEFF Research Database (Denmark)

Cox, F F; Berezin, V; Bock, E

2013-01-01

Fibroblast growth loop (FGL) is a neural cell adhesion molecule (NCAM)-mimetic peptide that mimics the interaction of NCAM with fibroblast growth factor receptor (FGFR). FGL increases neurite outgrowth and promotes neuronal survival in vitro, and it has also been shown to have neuroprotective eff...

Feature Set Evaluation for Offline Handwriting Recognition Systems: Application to the Recurrent Neural Network Model.

Science.gov (United States)

Chherawala, Youssouf; Roy, Partha Pratim; Cheriet, Mohamed

2016-12-01

The performance of handwriting recognition systems is dependent on the features extracted from the word image. A large body of features exists in the literature, but no method has yet been proposed to identify the most promising of these, other than a straightforward comparison based on the recognition rate. In this paper, we propose a framework for feature set evaluation based on a collaborative setting. We use a weighted vote combination of recurrent neural network (RNN) classifiers, each trained with a particular feature set. This combination is modeled in a probabilistic framework as a mixture model and two methods for weight estimation are described. The main contribution of this paper is to quantify the importance of feature sets through the combination weights, which reflect their strength and complementarity. We chose the RNN classifier because of its state-of-the-art performance. Also, we provide the first feature set benchmark for this classifier. We evaluated several feature sets on the IFN/ENIT and RIMES databases of Arabic and Latin script, respectively. The resulting combination model is competitive with state-of-the-art systems.

Neural basis of distorted self-face recognition in social anxiety disorder.

Science.gov (United States)

Kim, Min-Kyeong; Yoon, Hyung-Jun; Shin, Yu-Bin; Lee, Seung-Koo; Kim, Jae-Jin

2016-01-01

The observer perspective causes patients with social anxiety disorder (SAD) to excessively inspect their performance and appearance. This study aimed to investigate the neural basis of distorted self-face recognition in non-social situations in patients with SAD. Twenty patients with SAD and 20 age- and gender-matched healthy controls participated in this fMRI study. Data were acquired while participants performed a Composite Face Evaluation Task, during which they had to press a button indicating how much they liked a series of self-faces, attractively transformed self-faces, and attractive others' faces. Patients had a tendency to show more favorable responses to the self-face and unfavorable responses to the others' faces compared with controls, but the two groups' responses to the attractively transformed self-faces did not differ. Significant group differences in regional activity were observed in the middle frontal and supramarginal gyri in the self-face condition (patients self-face condition (patients > controls); and the middle frontal, supramarginal, and angular gyri in the attractive others' face condition (patients > controls). Most fronto-parietal activities during observation of the self-face were negatively correlated with preference scores in patients but not in controls. Patients with SAD have a positive point of view of their own face and experience self-relevance for the attractively transformed self-faces. This distorted cognition may be based on dysfunctions in the frontal and inferior parietal regions. The abnormal engagement of the fronto-parietal attentional network during processing face stimuli in non-social situations may be linked to distorted self-recognition in SAD.

A Survey on Sentiment Classification in Face Recognition

Science.gov (United States)

Qian, Jingyu

2018-01-01

Face recognition has been an important topic for both industry and academia for a long time. K-means clustering, autoencoder, and convolutional neural network, each representing a design idea for face recognition method, are three popular algorithms to deal with face recognition problems. It is worthwhile to summarize and compare these three different algorithms. This paper will focus on one specific face recognition problem-sentiment classification from images. Three different algorithms for sentiment classification problems will be summarized, including k-means clustering, autoencoder, and convolutional neural network. An experiment with the application of these algorithms on a specific dataset of human faces will be conducted to illustrate how these algorithms are applied and their accuracy. Finally, the three algorithms are compared based on the accuracy result.

Wearable Device-Based Gait Recognition Using Angle Embedded Gait Dynamic Images and a Convolutional Neural Network.

Science.gov (United States)

Zhao, Yongjia; Zhou, Suiping

2017-02-28

The widespread installation of inertial sensors in smartphones and other wearable devices provides a valuable opportunity to identify people by analyzing their gait patterns, for either cooperative or non-cooperative circumstances. However, it is still a challenging task to reliably extract discriminative features for gait recognition with noisy and complex data sequences collected from casually worn wearable devices like smartphones. To cope with this problem, we propose a novel image-based gait recognition approach using the Convolutional Neural Network (CNN) without the need to manually extract discriminative features. The CNN's input image, which is encoded straightforwardly from the inertial sensor data sequences, is called Angle Embedded Gait Dynamic Image (AE-GDI). AE-GDI is a new two-dimensional representation of gait dynamics, which is invariant to rotation and translation. The performance of the proposed approach in gait authentication and gait labeling is evaluated using two datasets: (1) the McGill University dataset, which is collected under realistic conditions; and (2) the Osaka University dataset with the largest number of subjects. Experimental results show that the proposed approach achieves competitive recognition accuracy over existing approaches and provides an effective parametric solution for identification among a large number of subjects by gait patterns.

Wearable Device-Based Gait Recognition Using Angle Embedded Gait Dynamic Images and a Convolutional Neural Network

Science.gov (United States)

Zhao, Yongjia; Zhou, Suiping

2017-01-01

The widespread installation of inertial sensors in smartphones and other wearable devices provides a valuable opportunity to identify people by analyzing their gait patterns, for either cooperative or non-cooperative circumstances. However, it is still a challenging task to reliably extract discriminative features for gait recognition with noisy and complex data sequences collected from casually worn wearable devices like smartphones. To cope with this problem, we propose a novel image-based gait recognition approach using the Convolutional Neural Network (CNN) without the need to manually extract discriminative features. The CNN’s input image, which is encoded straightforwardly from the inertial sensor data sequences, is called Angle Embedded Gait Dynamic Image (AE-GDI). AE-GDI is a new two-dimensional representation of gait dynamics, which is invariant to rotation and translation. The performance of the proposed approach in gait authentication and gait labeling is evaluated using two datasets: (1) the McGill University dataset, which is collected under realistic conditions; and (2) the Osaka University dataset with the largest number of subjects. Experimental results show that the proposed approach achieves competitive recognition accuracy over existing approaches and provides an effective parametric solution for identification among a large number of subjects by gait patterns. PMID:28264503

Performance of Deep and Shallow Neural Networks, the Universal Approximation Theorem, Activity Cliffs, and QSAR.

Science.gov (United States)

Winkler, David A; Le, Tu C

2017-01-01

Neural networks have generated valuable Quantitative Structure-Activity/Property Relationships (QSAR/QSPR) models for a wide variety of small molecules and materials properties. They have grown in sophistication and many of their initial problems have been overcome by modern mathematical techniques. QSAR studies have almost always used so-called "shallow" neural networks in which there is a single hidden layer between the input and output layers. Recently, a new and potentially paradigm-shifting type of neural network based on Deep Learning has appeared. Deep learning methods have generated impressive improvements in image and voice recognition, and are now being applied to QSAR and QSAR modelling. This paper describes the differences in approach between deep and shallow neural networks, compares their abilities to predict the properties of test sets for 15 large drug data sets (the kaggle set), discusses the results in terms of the Universal Approximation theorem for neural networks, and describes how DNN may ameliorate or remove troublesome "activity cliffs" in QSAR data sets. © 2017 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim.

Depression-like behaviour in neural cell adhesion molecule (NCAM)-deficient mice and its reversal by an NCAM-derived peptide, FGL

DEFF Research Database (Denmark)

Aonurm-Helm, Anu; Jurgenson, Monika; Zharkovsky, Tamara

2008-01-01

The neural cell adhesion molecule (NCAM) plays a pivotal role in brain plasticity. Brain plasticity itself has a crucial role in the development of depression. The aim of this study was to analyze whether NCAM-deficient (NCAM(-/-)) mice exhibit depression-like behaviour and whether a peptide term...

Improving a Deep Learning based RGB-D Object Recognition Model by Ensemble Learning

DEFF Research Database (Denmark)

Aakerberg, Andreas; Nasrollahi, Kamal; Heder, Thomas

2018-01-01

Augmenting RGB images with depth information is a well-known method to significantly improve the recognition accuracy of object recognition models. Another method to im- prove the performance of visual recognition models is ensemble learning. However, this method has not been widely explored...... in combination with deep convolutional neural network based RGB-D object recognition models. Hence, in this paper, we form different ensembles of complementary deep convolutional neural network models, and show that this can be used to increase the recognition performance beyond existing limits. Experiments...

Perceived Parenting Mediates Serotonin Transporter Gene (5-HTTLPR) and Neural System Function during Facial Recognition: A Pilot Study

Science.gov (United States)

Nishikawa, Saori

2015-01-01

This study examined changes in prefrontal oxy-Hb levels measured by NIRS (Near-Infrared Spectroscopy) during a facial-emotion recognition task in healthy adults, testing a mediational/moderational model of these variables. Fifty-three healthy adults (male = 35, female = 18) aged between 22 to 37 years old (mean age = 24.05 years old) provided saliva samples, completed a EMBU questionnaire (Swedish acronym for Egna Minnen Beträffande Uppfostran [My memories of upbringing]), and participated in a facial-emotion recognition task during NIRS recording. There was a main effect of maternal rejection on RoxH (right frontal activation during an ambiguous task), and a gene × environment (G×E) interaction on RoxH, suggesting that individuals who carry the SL or LL genotype and who endorse greater perceived maternal rejection show less right frontal activation than SL/LL carriers with lower perceived maternal rejection. Finally, perceived parenting style played a mediating role in right frontal activation via the 5-HTTLPR genotype. Early-perceived parenting might influence neural activity in an uncertain situation i.e. rating ambiguous faces among individuals with certain genotypes. This preliminary study makes a small contribution to the mapping of an influence of gene and behaviour on the neural system. More such attempts should be made in order to clarify the links. PMID:26418317

Perceived Parenting Mediates Serotonin Transporter Gene (5-HTTLPR and Neural System Function during Facial Recognition: A Pilot Study.

Directory of Open Access Journals (Sweden)

Saori Nishikawa

Full Text Available This study examined changes in prefrontal oxy-Hb levels measured by NIRS (Near-Infrared Spectroscopy during a facial-emotion recognition task in healthy adults, testing a mediational/moderational model of these variables. Fifty-three healthy adults (male = 35, female = 18 aged between 22 to 37 years old (mean age = 24.05 years old provided saliva samples, completed a EMBU questionnaire (Swedish acronym for Egna Minnen Beträffande Uppfostran [My memories of upbringing], and participated in a facial-emotion recognition task during NIRS recording. There was a main effect of maternal rejection on RoxH (right frontal activation during an ambiguous task, and a gene × environment (G × E interaction on RoxH, suggesting that individuals who carry the SL or LL genotype and who endorse greater perceived maternal rejection show less right frontal activation than SL/LL carriers with lower perceived maternal rejection. Finally, perceived parenting style played a mediating role in right frontal activation via the 5-HTTLPR genotype. Early-perceived parenting might influence neural activity in an uncertain situation i.e. rating ambiguous faces among individuals with certain genotypes. This preliminary study makes a small contribution to the mapping of an influence of gene and behaviour on the neural system. More such attempts should be made in order to clarify the links.

Computer system for structure recognition of polyatomic molecules by i. r. , n. m. r. , u. v. and m. s. methods

Energy Technology Data Exchange (ETDEWEB)

Gribov, L A; Elyashberg, M E; Serov, V V [USSR Academy of Sciences, Moscow (USSR). V.I. Vernadsky Institute of Geochemistry and Analytical Chemistry

1977-12-15

A system of algorithms and programs for the recognition of the structures of polyatomic molecules by means of i.r., n.m.r., u.v. and mass spectra is described. Examples of structures identified are cited. The results are promising and suggest that the system could be used for the identification of complex organic compounds.

Optical Pattern Recognition

Science.gov (United States)

Yu, Francis T. S.; Jutamulia, Suganda

2008-10-01

Contributors; Preface; 1. Pattern recognition with optics Francis T. S. Yu and Don A. Gregory; 2. Hybrid neural networks for nonlinear pattern recognition Taiwei Lu; 3. Wavelets, optics, and pattern recognition Yao Li and Yunglong Sheng; 4. Applications of the fractional Fourier transform to optical pattern recognition David Mendlovic, Zeev Zalesky and Haldum M. Oxaktas; 5. Optical implementation of mathematical morphology Tien-Hsin Chao; 6. Nonlinear optical correlators with improved discrimination capability for object location and recognition Leonid P. Yaroslavsky; 7. Distortion-invariant quadratic filters Gregory Gheen; 8. Composite filter synthesis as applied to pattern recognition Shizhou Yin and Guowen Lu; 9. Iterative procedures in electro-optical pattern recognition Joseph Shamir; 10. Optoelectronic hybrid system for three-dimensional object pattern recognition Guoguang Mu, Mingzhe Lu and Ying Sun; 11. Applications of photrefractive devices in optical pattern recognition Ziangyang Yang; 12. Optical pattern recognition with microlasers Eung-Gi Paek; 13. Optical properties and applications of bacteriorhodopsin Q. Wang Song and Yu-He Zhang; 14. Liquid-crystal spatial light modulators Aris Tanone and Suganda Jutamulia; 15. Representations of fully complex functions on real-time spatial light modulators Robert W. Cohn and Laurence G. Hassbrook; Index.

Impact of negative emotion on the neural correlates of long-term recognition in younger and older adults

Directory of Open Access Journals (Sweden)

Grégoria eKalpouzos

2012-09-01

Full Text Available Some studies have suggested that the memory advantage for negative emotional information over neutral information (negativity effect is reduced in aging. Besides the fact that most findings are based on immediate retrieval, the neural underpinnings of long-term emotional memory in aging have so far not been investigated. To address these issues, we assessed recognition of neutral and negative scenes after one- and 3-week retention intervals in younger and older adults using fMRI. We further used an event-related design in order to disentangle successful, false and true recognition. This study revealed 4 key findings: 1 Increased retention interval induced an increased rate of false recognitions for negative scenes, cancelling out the negativity effect (present for hit rates only on discrimination in both younger and older adults; 2 In younger, but not older, adults, reduced activity of the medial temporal lobe was observed over time for neutral scenes, but not for negative scenes, where stable or increased activity was seen; 3 Engagement of amygdala was observed in older adults after a 3-week delay during successful recognition of negative scenes (hits versus misses in comparison with neutral scenes, which may indicate engagement of automatic processes, but engagement of ventrolateral prefrontal cortex was unrelated to amygdala activity and performance; and 4 After 3 weeks, but not after one week, true recognition of negative scenes was characterized by more activity in left hippocampus and lateral occipito-temporal regions (hits versus false alarms. As these regions are known to be related to consolidation mechanisms, the observed pattern may indicate the presence of delayed consolidation of true memories. Nonetheless, older adults’ low performance in discrimination of negative scenes could reflect the fact that overall, after long delays of retention, they rely more on general information rather than on perceptual detail in making

Artificial neural networks for plasma spectroscopy analysis

International Nuclear Information System (INIS)

Morgan, W.L.; Larsen, J.T.; Goldstein, W.H.

1992-01-01

Artificial neural networks have been applied to a variety of signal processing and image recognition problems. Of the several common neural models the feed-forward, back-propagation network is well suited for the analysis of scientific laboratory data, which can be viewed as a pattern recognition problem. The authors present a discussion of the basic neural network concepts and illustrate its potential for analysis of experiments by applying it to the spectra of laser produced plasmas in order to obtain estimates of electron temperatures and densities. Although these are high temperature and density plasmas, the neural network technique may be of interest in the analysis of the low temperature and density plasmas characteristic of experiments and devices in gaseous electronics

Handwritten Devanagari Character Recognition Using Layer-Wise Training of Deep Convolutional Neural Networks and Adaptive Gradient Methods

Directory of Open Access Journals (Sweden)

Mahesh Jangid

2018-02-01

Full Text Available Handwritten character recognition is currently getting the attention of researchers because of possible applications in assisting technology for blind and visually impaired users, human–robot interaction, automatic data entry for business documents, etc. In this work, we propose a technique to recognize handwritten Devanagari characters using deep convolutional neural networks (DCNN which are one of the recent techniques adopted from the deep learning community. We experimented the ISIDCHAR database provided by (Information Sharing Index ISI, Kolkata and V2DMDCHAR database with six different architectures of DCNN to evaluate the performance and also investigate the use of six recently developed adaptive gradient methods. A layer-wise technique of DCNN has been employed that helped to achieve the highest recognition accuracy and also get a faster convergence rate. The results of layer-wise-trained DCNN are favorable in comparison with those achieved by a shallow technique of handcrafted features and standard DCNN.

[Face recognition in patients with schizophrenia].

Science.gov (United States)

Doi, Hirokazu; Shinohara, Kazuyuki

2012-07-01

It is well known that patients with schizophrenia show severe deficiencies in social communication skills. These deficiencies are believed to be partly derived from abnormalities in face recognition. However, the exact nature of these abnormalities exhibited by schizophrenic patients with respect to face recognition has yet to be clarified. In the present paper, we review the main findings on face recognition deficiencies in patients with schizophrenia, particularly focusing on abnormalities in the recognition of facial expression and gaze direction, which are the primary sources of information of others' mental states. The existing studies reveal that the abnormal recognition of facial expression and gaze direction in schizophrenic patients is attributable to impairments in both perceptual processing of visual stimuli, and cognitive-emotional responses to social information. Furthermore, schizophrenic patients show malfunctions in distributed neural regions, ranging from the fusiform gyrus recruited in the structural encoding of facial stimuli, to the amygdala which plays a primary role in the detection of the emotional significance of stimuli. These findings were obtained from research in patient groups with heterogeneous characteristics. Because previous studies have indicated that impairments in face recognition in schizophrenic patients might vary according to the types of symptoms, it is of primary importance to compare the nature of face recognition deficiencies and the impairments of underlying neural functions across sub-groups of patients.

Finger language recognition based on ensemble artificial neural network learning using armband EMG sensors.

Science.gov (United States)

Kim, Seongjung; Kim, Jongman; Ahn, Soonjae; Kim, Youngho

2018-04-18

Deaf people use sign or finger languages for communication, but these methods of communication are very specialized. For this reason, the deaf can suffer from social inequalities and financial losses due to their communication restrictions. In this study, we developed a finger language recognition algorithm based on an ensemble artificial neural network (E-ANN) using an armband system with 8-channel electromyography (EMG) sensors. The developed algorithm was composed of signal acquisition, filtering, segmentation, feature extraction and an E-ANN based classifier that was evaluated with the Korean finger language (14 consonants, 17 vowels and 7 numbers) in 17 subjects. E-ANN was categorized according to the number of classifiers (1 to 10) and size of training data (50 to 1500). The accuracy of the E-ANN-based classifier was obtained by 5-fold cross validation and compared with an artificial neural network (ANN)-based classifier. As the number of classifiers (1 to 8) and size of training data (50 to 300) increased, the average accuracy of the E-ANN-based classifier increased and the standard deviation decreased. The optimal E-ANN was composed with eight classifiers and 300 size of training data, and the accuracy of the E-ANN was significantly higher than that of the general ANN.

Artificial neural network detects human uncertainty

Science.gov (United States)

Hramov, Alexander E.; Frolov, Nikita S.; Maksimenko, Vladimir A.; Makarov, Vladimir V.; Koronovskii, Alexey A.; Garcia-Prieto, Juan; Antón-Toro, Luis Fernando; Maestú, Fernando; Pisarchik, Alexander N.

2018-03-01

Artificial neural networks (ANNs) are known to be a powerful tool for data analysis. They are used in social science, robotics, and neurophysiology for solving tasks of classification, forecasting, pattern recognition, etc. In neuroscience, ANNs allow the recognition of specific forms of brain activity from multichannel EEG or MEG data. This makes the ANN an efficient computational core for brain-machine systems. However, despite significant achievements of artificial intelligence in recognition and classification of well-reproducible patterns of neural activity, the use of ANNs for recognition and classification of patterns in neural networks still requires additional attention, especially in ambiguous situations. According to this, in this research, we demonstrate the efficiency of application of the ANN for classification of human MEG trials corresponding to the perception of bistable visual stimuli with different degrees of ambiguity. We show that along with classification of brain states associated with multistable image interpretations, in the case of significant ambiguity, the ANN can detect an uncertain state when the observer doubts about the image interpretation. With the obtained results, we describe the possible application of ANNs for detection of bistable brain activity associated with difficulties in the decision-making process.

Artificial Neural Network approach to develop unique Classification and Raga identification tools for Pattern Recognition in Carnatic Music

Science.gov (United States)

Srimani, P. K.; Parimala, Y. G.

2011-12-01

A unique approach has been developed to study patterns in ragas of Carnatic Classical music based on artificial neural networks. Ragas in Carnatic music which have found their roots in the Vedic period, have grown on a Scientific foundation over thousands of years. However owing to its vastness and complexities it has always been a challenge for scientists and musicologists to give an all encompassing perspective both qualitatively and quantitatively. Cognition, comprehension and perception of ragas in Indian classical music have always been the subject of intensive research, highly intriguing and many facets of these are hitherto not unravelled. This paper is an attempt to view the melakartha ragas with a cognitive perspective using artificial neural network based approach which has given raise to very interesting results. The 72 ragas of the melakartha system were defined through the combination of frequencies occurring in each of them. The data sets were trained using several neural networks. 100% accurate pattern recognition and classification was obtained using linear regression, TLRN, MLP and RBF networks. Performance of the different network topologies, by varying various network parameters, were compared. Linear regression was found to be the best performing network.

American Sign Language Alphabet Recognition Using a Neuromorphic Sensor and an Artificial Neural Network

Directory of Open Access Journals (Sweden)

Miguel Rivera-Acosta

2017-09-01

Full Text Available This paper reports the design and analysis of an American Sign Language (ASL alphabet translation system implemented in hardware using a Field-Programmable Gate Array. The system process consists of three stages, the first being the communication with the neuromorphic camera (also called Dynamic Vision Sensor, DVS sensor using the Universal Serial Bus protocol. The feature extraction of the events generated by the DVS is the second part of the process, consisting of a presentation of the digital image processing algorithms developed in software, which aim to reduce redundant information and prepare the data for the third stage. The last stage of the system process is the classification of the ASL alphabet, achieved with a single artificial neural network implemented in digital hardware for higher speed. The overall result is the development of a classification system using the ASL signs contour, fully implemented in a reconfigurable device. The experimental results consist of a comparative analysis of the recognition rate among the alphabet signs using the neuromorphic camera in order to prove the proper operation of the digital image processing algorithms. In the experiments performed with 720 samples of 24 signs, a recognition accuracy of 79.58% was obtained.

Neural networks at the Tevatron

International Nuclear Information System (INIS)

Badgett, W.; Burkett, K.; Campbell, M.K.; Wu, D.Y.; Bianchin, S.; DeNardi, M.; Pauletta, G.; Santi, L.; Caner, A.; Denby, B.; Haggerty, H.; Lindsey, C.S.; Wainer, N.; Dall'Agata, M.; Johns, K.; Dickson, M.; Stanco, L.; Wyss, J.L.

1992-10-01

This paper summarizes neural network applications at the Fermilab Tevatron, including the first online hardware application in high energy physics (muon tracking): the CDF and DO neural network triggers; offline quark/gluon discrimination at CDF; ND a new tool for top to multijets recognition at CDF

New Fault Recognition Method for Rotary Machinery Based on Information Entropy and a Probabilistic Neural Network.

Science.gov (United States)

Jiang, Quansheng; Shen, Yehu; Li, Hua; Xu, Fengyu

2018-01-24

Feature recognition and fault diagnosis plays an important role in equipment safety and stable operation of rotating machinery. In order to cope with the complexity problem of the vibration signal of rotating machinery, a feature fusion model based on information entropy and probabilistic neural network is proposed in this paper. The new method first uses information entropy theory to extract three kinds of characteristics entropy in vibration signals, namely, singular spectrum entropy, power spectrum entropy, and approximate entropy. Then the feature fusion model is constructed to classify and diagnose the fault signals. The proposed approach can combine comprehensive information from different aspects and is more sensitive to the fault features. The experimental results on simulated fault signals verified better performances of our proposed approach. In real two-span rotor data, the fault detection accuracy of the new method is more than 10% higher compared with the methods using three kinds of information entropy separately. The new approach is proved to be an effective fault recognition method for rotating machinery.

Application of machine learning methods for traffic signs recognition

Science.gov (United States)

Filatov, D. V.; Ignatev, K. V.; Deviatkin, A. V.; Serykh, E. V.

2018-02-01

This paper focuses on solving a relevant and pressing safety issue on intercity roads. Two approaches were considered for solving the problem of traffic signs recognition; the approaches involved neural networks to analyze images obtained from a camera in the real-time mode. The first approach is based on a sequential image processing. At the initial stage, with the help of color filters and morphological operations (dilatation and erosion), the area containing the traffic sign is located on the image, then the selected and scaled fragment of the image is analyzed using a feedforward neural network to determine the meaning of the found traffic sign. Learning of the neural network in this approach is carried out using a backpropagation method. The second approach involves convolution neural networks at both stages, i.e. when searching and selecting the area of the image containing the traffic sign, and when determining its meaning. Learning of the neural network in the second approach is carried out using the intersection over union function and a loss function. For neural networks to learn and the proposed algorithms to be tested, a series of videos from a dash cam were used that were shot under various weather and illumination conditions. As a result, the proposed approaches for traffic signs recognition were analyzed and compared by key indicators such as recognition rate percentage and the complexity of neural networks’ learning process.

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

Science.gov (United States)

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

2014-09-01

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

The effects of acute social isolation on long-term social recognition memory.

Science.gov (United States)

Leser, Noam; Wagner, Shlomo

2015-10-01

The abilities to recognize individual animals of the same species and to distinguish them from other individuals are the basis for all mammalian social organizations and relationships. These abilities, termed social recognition memory, can be explored in mice and rats using their innate tendency to investigate novel social stimuli more persistently than familiar ones. Using this methodology it was found that social recognition memory is mediated by a specific neural network in the brain, the activity of which is modulated by several molecules, such the neuropeptides oxytocin and vasopressin. During the last 15 years several independent studies have revealed that social recognition memory of mice and rats depends upon their housing conditions. Specifically, long-term social recognition memory cannot be formed as shortly as few days following social isolation of the animal. This rapid and reversible impairment caused by acute social isolation seems to be specific to social memory and has not been observed in other types of memory. Here we review these studies and suggest that this unique system may serve for exploring of the mechanisms underlying the well-known negative effects of partial or perceived social isolation on human mental health. Copyright © 2015 Elsevier Inc. All rights reserved.

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

Science.gov (United States)

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

2017-03-20

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

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

Science.gov (United States)

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

2017-01-01

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

Modeling of biologically motivated self-learning equivalent-convolutional recurrent-multilayer neural structures (BLM_SL_EC_RMNS) for image fragments clustering and recognition

Science.gov (United States)

Krasilenko, Vladimir G.; Lazarev, Alexander A.; Nikitovich, Diana V.

2018-03-01

The biologically-motivated self-learning equivalence-convolutional recurrent-multilayer neural structures (BLM_SL_EC_RMNS) for fragments images clustering and recognition will be discussed. We shall consider these neural structures and their spatial-invariant equivalental models (SIEMs) based on proposed equivalent two-dimensional functions of image similarity and the corresponding matrix-matrix (or tensor) procedures using as basic operations of continuous logic and nonlinear processing. These SIEMs can simply describe the signals processing during the all training and recognition stages and they are suitable for unipolar-coding multilevel signals. The clustering efficiency in such models and their implementation depends on the discriminant properties of neural elements of hidden layers. Therefore, the main models and architecture parameters and characteristics depends on the applied types of non-linear processing and function used for image comparison or for adaptive-equivalent weighing of input patterns. We show that these SL_EC_RMNSs have several advantages, such as the self-study and self-identification of features and signs of the similarity of fragments, ability to clustering and recognize of image fragments with best efficiency and strong mutual correlation. The proposed combined with learning-recognition clustering method of fragments with regard to their structural features is suitable not only for binary, but also color images and combines self-learning and the formation of weight clustered matrix-patterns. Its model is constructed and designed on the basis of recursively continuous logic and nonlinear processing algorithms and to k-average method or method the winner takes all (WTA). The experimental results confirmed that fragments with a large numbers of elements may be clustered. For the first time the possibility of generalization of these models for space invariant case is shown. The experiment for an images of different dimensions (a reference

Morphological neural networks

Energy Technology Data Exchange (ETDEWEB)

Ritter, G.X.; Sussner, P. [Univ. of Florida, Gainesville, FL (United States)

1996-12-31

The theory of artificial neural networks has been successfully applied to a wide variety of pattern recognition problems. In this theory, the first step in computing the next state of a neuron or in performing the next layer neural network computation involves the linear operation of multiplying neural values by their synaptic strengths and adding the results. Thresholding usually follows the linear operation in order to provide for nonlinearity of the network. In this paper we introduce a novel class of neural networks, called morphological neural networks, in which the operations of multiplication and addition are replaced by addition and maximum (or minimum), respectively. By taking the maximum (or minimum) of sums instead of the sum of products, morphological network computation is nonlinear before thresholding. As a consequence, the properties of morphological neural networks are drastically different than those of traditional neural network models. In this paper we consider some of these differences and provide some particular examples of morphological neural network.

Chronic minocycline treatment improves social recognition memory in adult male Fmr1 knockout mice.

Science.gov (United States)

Yau, Suk Yu; Chiu, Christine; Vetrici, Mariana; Christie, Brian R

2016-10-01

Fragile X syndrome (FXS) is caused by a mutation in the Fmr1 gene that leads to silencing of the gene and a loss of its gene product, Fragile X mental retardation protein (FMRP). Some of the key behavioral phenotypes for FXS include abnormal social anxiety and sociability. Here we show that Fmr1 knock-out (KO) mice exhibit impaired social recognition when presented with a novel mouse, and they display normal social interactions in other sociability tests. Administering minocycline to Fmr1 KO mice throughout critical stages of neural development improved social recognition memory in the novel mouse recognition task. To determine if synaptic changes in the prefrontal cortex (PFC) could have played a role in this improvement, we examined PSD-95, a member of the membrane-associated guanylate kinase family, and signaling molecules (ERK1/2, and Akt) linked to synaptic plasticity in the PFC. Our analyses indicated that while minocycline treatment can enhance behavioral performance, it does not enhance expression of PSD-95, ERK1/2 or Akt in the PFC. Copyright © 2016 Elsevier B.V. All rights reserved.

Neural Networks through Shared Maps in Mobile Devices

Directory of Open Access Journals (Sweden)

William Raveane

2014-12-01

Full Text Available We introduce a hybrid system composed of a convolutional neural network and a discrete graphical model for image recognition. This system improves upon traditional sliding window techniques for analysis of an image larger than the training data by effectively processing the full input scene through the neural network in less time. The final result is then inferred from the neural network output through energy minimization to reach a more precize localization than what traditional maximum value class comparisons yield. These results are apt for applying this process in a mobile device for real time image recognition.

The neural basis of body form and body action agnosia.

Science.gov (United States)

Moro, Valentina; Urgesi, Cosimo; Pernigo, Simone; Lanteri, Paola; Pazzaglia, Mariella; Aglioti, Salvatore Maria

2008-10-23

Visual analysis of faces and nonfacial body stimuli brings about neural activity in different cortical areas. Moreover, processing body form and body action relies on distinct neural substrates. Although brain lesion studies show specific face processing deficits, neuropsychological evidence for defective recognition of nonfacial body parts is lacking. By combining psychophysics studies with lesion-mapping techniques, we found that lesions of ventromedial, occipitotemporal areas induce face and body recognition deficits while lesions involving extrastriate body area seem causatively associated with impaired recognition of body but not of face and object stimuli. We also found that body form and body action recognition deficits can be double dissociated and are causatively associated with lesions to extrastriate body area and ventral premotor cortex, respectively. Our study reports two category-specific visual deficits, called body form and body action agnosia, and highlights their neural underpinnings.

STDP-based spiking deep convolutional neural networks for object recognition.

Science.gov (United States)

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

2018-03-01

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

Neural networks and applications tutorial

Science.gov (United States)

Guyon, I.

1991-09-01

The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear. The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks. Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks. The tutorial is divided into six lectures, that where presented at the Third Graduate Summer Course on Computational Physics (September 3-7, 1990) on Parallel Architectures and Applications, organized by the European Physical Society: (1) Introduction: machine learning and biological computation. (2) Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations. (3) Neural network systems: architectures, learning algorithms. (4) Applications: pattern recognition, signal processing, etc. (5) Elements of learning theory: how to build networks which generalize. (6) A case study: a neural network for on-line recognition of handwritten alphanumeric characters.

Improved RGB-D-T based Face Recognition

DEFF Research Database (Denmark)

Oliu Simon, Marc; Corneanu, Ciprian; Nasrollahi, Kamal

2016-01-01

years. At the same time a multimodal facial recognition is a promising approach. This paper combines the latest successes in both directions by applying deep learning Convolutional Neural Networks (CNN) to the multimodal RGB-D-T based facial recognition problem outperforming previously published results......Reliable facial recognition systems are of crucial importance in various applications from entertainment to security. Thanks to the deep-learning concepts introduced in the field, a significant improvement in the performance of the unimodal facial recognition systems has been observed in the recent...

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

Directory of Open Access Journals (Sweden)

Dat Tien Nguyen

2017-03-01

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

Cortical Networks for Visual Self-Recognition

Science.gov (United States)

Sugiura, Motoaki

This paper briefly reviews recent developments regarding the brain mechanisms of visual self-recognition. A special cognitive mechanism for visual self-recognition has been postulated based on behavioral and neuropsychological evidence, but its neural substrate remains controversial. Recent functional imaging studies suggest that multiple cortical mechanisms play self-specific roles during visual self-recognition, reconciling the existing controversy. Respective roles for the left occipitotemporal, right parietal, and frontal cortices in symbolic, visuospatial, and conceptual aspects of self-representation have been proposed.

Cortical networks for visual self-recognition

International Nuclear Information System (INIS)

Sugiura, Motoaki

2007-01-01

This paper briefly reviews recent developments regarding the brain mechanisms of visual self-recognition. A special cognitive mechanism for visual self-recognition has been postulated based on behavioral and neuropsychological evidence, but its neural substrate remains controversial. Recent functional imaging studies suggest that multiple cortical mechanisms play self-specific roles during visual self-recognition, reconciling the existing controversy. Respective roles for the left occipitotemporal, right parietal, and frontal cortices in symbolic, visuospatial, and conceptual aspects of self-representation have been proposed. (author)

Neural androgen receptors modulate gene expression and social recognition but not social investigation

Directory of Open Access Journals (Sweden)

Sara A Karlsson

2016-03-01

Full Text Available The role of sex and androgen receptors (ARs for social preference and social memory is rather unknown. In this study of mice we compared males, females and males lacking ARs specifically in the nervous system, ARNesDel, with respect to social preference, assessed with the three-chambered apparatus test, and social recognition, assessed with the social discrimination procedure. In the social discrimination test we also evaluated the tentative importance of the sex of the stimulus animal. Novel object recognition and olfaction were investigated to complement the results from the social tests. Gene expression analysis was performed to reveal molecules involved in the effects of sex and androgens on social behaviors. All three test groups showed social preference in the three-chambered apparatus test. In both social tests an AR-independent sexual dimorphism was seen in the persistence of social investigation of female conspecifics, whereas the social interest towards male stimuli mice was similar in all groups. Male and female controls recognized conspecifics independent of their sex, whereas ARNesDel males recognized female but not male stimuli mice. Moreover, the non-social behaviors were not affected by AR deficiency. The gene expression analyses of hypothalamus and amygdala indicated that Oxtr, Cd38, Esr1, Cyp19a1, Ucn3, Crh and Gtf2i were differentially expressed between the three groups. In conclusion, our results suggest that ARs are required for recognition of male but not female conspecifics, while being dispensable for social investigation towards both sexes. In addition, the AR seems to regulate genes related to oxytocin, estrogen and William’s syndrome.

Neural network models: from biology to many - body phenomenology

International Nuclear Information System (INIS)

Clark, J.W.

1993-01-01

The current surge of research on practical side of neural networks and their utility in memory storage/recall, pattern recognition and classification is given in this article. The initial attraction of neural networks as dynamical and statistical system has been investigated. From the view of many-body theorist, the neurons may be thought of as particles, and the weighted connection between the units, as the interaction between these particles. Finally, the author has seen the impressive capabilities of artificial neural networks in pattern recognition and classification may be exploited to solve data management problems in experimental physics and the discovery of radically new theoretically description of physical problems and neural networks can be used in physics. (A.B.)

A NEW RECOGNITION TECHNIQUE NAMED SOMP BASED ON PALMPRINT USING NEURAL NETWORK BASED SELF ORGANIZING MAPS

Directory of Open Access Journals (Sweden)

A. S. Raja

2012-08-01

Full Text Available The word biometrics refers to the use of physiological or biological characteristics of human to recognize and verify the identity of an individual. Palmprint has become a new class of human biometrics for passive identification with uniqueness and stability. This is considered to be reliable due to the lack of expressions and the lesser effect of aging. In this manuscript a new Palmprint based biometric system based on neural networks self organizing maps (SOM is presented. The method is named as SOMP. The paper shows that the proposed SOMP method improves the performance and robustness of recognition. The proposed method is applied to a variety of datasets and the results are shown.

Optimization of multilayer neural network parameters for speaker recognition

Science.gov (United States)

Tovarek, Jaromir; Partila, Pavol; Rozhon, Jan; Voznak, Miroslav; Skapa, Jan; Uhrin, Dominik; Chmelikova, Zdenka

2016-05-01

This article discusses the impact of multilayer neural network parameters for speaker identification. The main task of speaker identification is to find a specific person in the known set of speakers. It means that the voice of an unknown speaker (wanted person) belongs to a group of reference speakers from the voice database. One of the requests was to develop the text-independent system, which means to classify wanted person regardless of content and language. Multilayer neural network has been used for speaker identification in this research. Artificial neural network (ANN) needs to set parameters like activation function of neurons, steepness of activation functions, learning rate, the maximum number of iterations and a number of neurons in the hidden and output layers. ANN accuracy and validation time are directly influenced by the parameter settings. Different roles require different settings. Identification accuracy and ANN validation time were evaluated with the same input data but different parameter settings. The goal was to find parameters for the neural network with the highest precision and shortest validation time. Input data of neural networks are a Mel-frequency cepstral coefficients (MFCC). These parameters describe the properties of the vocal tract. Audio samples were recorded for all speakers in a laboratory environment. Training, testing and validation data set were split into 70, 15 and 15 %. The result of the research described in this article is different parameter setting for the multilayer neural network for four speakers.

[Face recognition in patients with autism spectrum disorders].

Science.gov (United States)

Kita, Yosuke; Inagaki, Masumi

2012-07-01

The present study aimed to review previous research conducted on face recognition in patients with autism spectrum disorders (ASD). Face recognition is a key question in the ASD research field because it can provide clues for elucidating the neural substrates responsible for the social impairment of these patients. Historically, behavioral studies have reported low performance and/or unique strategies of face recognition among ASD patients. However, the performance and strategy of ASD patients is comparable to those of the control group, depending on the experimental situation or developmental stage, suggesting that face recognition of ASD patients is not entirely impaired. Recent brain function studies, including event-related potential and functional magnetic resonance imaging studies, have investigated the cognitive process of face recognition in ASD patients, and revealed impaired function in the brain's neural network comprising the fusiform gyrus and amygdala. This impaired function is potentially involved in the diminished preference for faces, and in the atypical development of face recognition, eliciting symptoms of unstable behavioral characteristics in these patients. Additionally, face recognition in ASD patients is examined from a different perspective, namely self-face recognition, and facial emotion recognition. While the former topic is intimately linked to basic social abilities such as self-other discrimination, the latter is closely associated with mentalizing. Further research on face recognition in ASD patients should investigate the connection between behavioral and neurological specifics in these patients, by considering developmental changes and the spectrum clinical condition of ASD.

Automatic system for localization and recognition of vehicle plate numbers

OpenAIRE

Vázquez, N.; Nakano, M.; Pérez-Meana, H.

2003-01-01

This paper proposes a vehicle numbers plate identification system, which extracts the characters features of a plate from a captured image by a digital camera. Then identify the symbols of the number plate using a multilayer neural network. The proposed recognition system consists of two processes: The training process and the recognition process. During the training process, a database is created using 310 vehicular plate images. Then using this database a multilayer neural network is traine...

Investigating Patterns for Self-Induced Emotion Recognition from EEG Signals

Science.gov (United States)

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

2018-01-01

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

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

Science.gov (United States)

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

2018-03-12

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

Deep Classifiers-Based License Plate Detection, Localization and Recognition on GPU-Powered Mobile Platform

Directory of Open Access Journals (Sweden)

Syed Tahir Hussain Rizvi

2017-10-01

Full Text Available The realization of a deep neural architecture on a mobile platform is challenging, but can open up a number of possibilities for visual analysis applications. A neural network can be realized on a mobile platform by exploiting the computational power of the embedded GPU and simplifying the flow of a neural architecture trained on the desktop workstation or a GPU server. This paper presents an embedded platform-based Italian license plate detection and recognition system using deep neural classifiers. In this work, trained parameters of a highly precise automatic license plate recognition (ALPR system are imported and used to replicate the same neural classifiers on a Nvidia Shield K1 tablet. A CUDA-based framework is used to realize these neural networks. The flow of the trained architecture is simplified to perform the license plate recognition in real-time. Results show that the tasks of plate and character detection and localization can be performed in real-time on a mobile platform by simplifying the flow of the trained architecture. However, the accuracy of the simplified architecture would be decreased accordingly.

[A method of recognizing biology surface spectrum using cascade-connection artificial neural nets].

Science.gov (United States)

Shi, Wei-Jie; Yao, Yong; Zhang, Tie-Qiang; Meng, Xian-Jiang

2008-05-01

A method of recognizing the visible spectrum of micro-areas on the biological surface with cascade-connection artificial neural nets is presented in the present paper. The visible spectra of spots on apples' pericarp, ranging from 500 to 730 nm, were obtained with a fiber-probe spectrometer, and a new spectrum recognition system consisting of three-level cascade-connection neural nets was set up. The experiments show that the spectra of rotten, scar and bumped spot on an apple's pericarp can be recognized by the spectrum recognition system, and the recognition accuracy is higher than 85% even when noise level is 15%. The new recognition system overcomes the disadvantages of poor accuracy and poor anti-noise with the traditional system based on single cascade neural nets. Finally, a new method of expression of recognition results was proved. The method is based on the conception of degree of membership in fuzzing mathematics, and through it the recognition results can be expressed exactly and objectively.

Object recognition with hierarchical discriminant saliency networks.

Science.gov (United States)

Han, Sunhyoung; Vasconcelos, Nuno

2014-01-01

The benefits of integrating attention and object recognition are investigated. While attention is frequently modeled as a pre-processor for recognition, we investigate the hypothesis that attention is an intrinsic component of recognition and vice-versa. This hypothesis is tested with a recognition model, the hierarchical discriminant saliency network (HDSN), whose layers are top-down saliency detectors, tuned for a visual class according to the principles of discriminant saliency. As a model of neural computation, the HDSN has two possible implementations. In a biologically plausible implementation, all layers comply with the standard neurophysiological model of visual cortex, with sub-layers of simple and complex units that implement a combination of filtering, divisive normalization, pooling, and non-linearities. In a convolutional neural network implementation, all layers are convolutional and implement a combination of filtering, rectification, and pooling. The rectification is performed with a parametric extension of the now popular rectified linear units (ReLUs), whose parameters can be tuned for the detection of target object classes. This enables a number of functional enhancements over neural network models that lack a connection to saliency, including optimal feature denoising mechanisms for recognition, modulation of saliency responses by the discriminant power of the underlying features, and the ability to detect both feature presence and absence. In either implementation, each layer has a precise statistical interpretation, and all parameters are tuned by statistical learning. Each saliency detection layer learns more discriminant saliency templates than its predecessors and higher layers have larger pooling fields. This enables the HDSN to simultaneously achieve high selectivity to target object classes and invariance. The performance of the network in saliency and object recognition tasks is compared to those of models from the biological and

Prototype-Incorporated Emotional Neural Network.

Science.gov (United States)

Oyedotun, Oyebade K; Khashman, Adnan

2017-08-15

Artificial neural networks (ANNs) aim to simulate the biological neural activities. Interestingly, many ''engineering'' prospects in ANN have relied on motivations from cognition and psychology studies. So far, two important learning theories that have been subject of active research are the prototype and adaptive learning theories. The learning rules employed for ANNs can be related to adaptive learning theory, where several examples of the different classes in a task are supplied to the network for adjusting internal parameters. Conversely, the prototype-learning theory uses prototypes (representative examples); usually, one prototype per class of the different classes contained in the task. These prototypes are supplied for systematic matching with new examples so that class association can be achieved. In this paper, we propose and implement a novel neural network algorithm based on modifying the emotional neural network (EmNN) model to unify the prototype- and adaptive-learning theories. We refer to our new model as ``prototype-incorporated EmNN''. Furthermore, we apply the proposed model to two real-life challenging tasks, namely, static hand-gesture recognition and face recognition, and compare the result to those obtained using the popular back-propagation neural network (BPNN), emotional BPNN (EmNN), deep networks, an exemplar classification model, and k-nearest neighbor.

Event Recognition Based on Deep Learning in Chinese Texts.

Directory of Open Access Journals (Sweden)

Yajun Zhang

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

Event Recognition Based on Deep Learning in Chinese Texts.

Science.gov (United States)

Zhang, Yajun; Liu, Zongtian; Zhou, Wen

2016-01-01

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

The hierarchical brain network for face recognition.

Science.gov (United States)

Zhen, Zonglei; Fang, Huizhen; Liu, Jia

2013-01-01

Numerous functional magnetic resonance imaging (fMRI) studies have identified multiple cortical regions that are involved in face processing in the human brain. However, few studies have characterized the face-processing network as a functioning whole. In this study, we used fMRI to identify face-selective regions in the entire brain and then explore the hierarchical structure of the face-processing network by analyzing functional connectivity among these regions. We identified twenty-five regions mainly in the occipital, temporal and frontal cortex that showed a reliable response selective to faces (versus objects) across participants and across scan sessions. Furthermore, these regions were clustered into three relatively independent sub-networks in a face-recognition task on the basis of the strength of functional connectivity among them. The functionality of the sub-networks likely corresponds to the recognition of individual identity, retrieval of semantic knowledge and representation of emotional information. Interestingly, when the task was switched to object recognition from face recognition, the functional connectivity between the inferior occipital gyrus and the rest of the face-selective regions were significantly reduced, suggesting that this region may serve as an entry node in the face-processing network. In sum, our study provides empirical evidence for cognitive and neural models of face recognition and helps elucidate the neural mechanisms underlying face recognition at the network level.

sEMG-Based Gesture Recognition with Convolution Neural Networks

Directory of Open Access Journals (Sweden)

Zhen Ding

2018-06-01

Full Text Available The traditional classification methods for limb motion recognition based on sEMG have been deeply researched and shown promising results. However, information loss during feature extraction reduces the recognition accuracy. To obtain higher accuracy, the deep learning method was introduced. In this paper, we propose a parallel multiple-scale convolution architecture. Compared with the state-of-art methods, the proposed architecture fully considers the characteristics of the sEMG signal. Larger sizes of kernel filter than commonly used in other CNN-based hand recognition methods are adopted. Meanwhile, the characteristics of the sEMG signal, that is, muscle independence, is considered when designing the architecture. All the classification methods were evaluated on the NinaPro database. The results show that the proposed architecture has the highest recognition accuracy. Furthermore, the results indicate that parallel multiple-scale convolution architecture with larger size of kernel filter and considering muscle independence can significantly increase the classification accuracy.

The principles of artificial neural network information processing

International Nuclear Information System (INIS)

Dai, Ru-Wei

1993-01-01

In this article, the basic structure of an artificial neuron is first introduced. In addition, principles of artificial neural network as well as several important artificial neural models such as Perceptron, Back propagation model, Hopfield net, and ART model are briefly discussed and analyzed. Finally, the application of artificial neural network for Chinese Character Recognition is also given. (author)

The principles of artificial neural network information processing

International Nuclear Information System (INIS)

Dai, Ru-Wei

1993-01-01

In this article, the basic structure of an artificial neuron is first introduced. In addition, principles of artificial neural network as well as several important artificial neural models such as perception, back propagation model, Hopfield net, and ART model are briefly discussed and analyzed. Finally the application of artificial neural network for Chinese character recognition is also given. (author)

[Comparative studies of face recognition].

Science.gov (United States)

Kawai, Nobuyuki

2012-07-01

Every human being is proficient in face recognition. However, the reason for and the manner in which humans have attained such an ability remain unknown. These questions can be best answered-through comparative studies of face recognition in non-human animals. Studies in both primates and non-primates show that not only primates, but also non-primates possess the ability to extract information from their conspecifics and from human experimenters. Neural specialization for face recognition is shared with mammals in distant taxa, suggesting that face recognition evolved earlier than the emergence of mammals. A recent study indicated that a social insect, the golden paper wasp, can distinguish their conspecific faces, whereas a closely related species, which has a less complex social lifestyle with just one queen ruling a nest of underlings, did not show strong face recognition for their conspecifics. Social complexity and the need to differentiate between one another likely led humans to evolve their face recognition abilities.

SPEECH EMOTION RECOGNITION USING MODIFIED QUADRATIC DISCRIMINATION FUNCTION

Institute of Scientific and Technical Information of China (English)

无

2008-01-01

Quadratic Discrimination Function(QDF)is commonly used in speech emotion recognition,which proceeds on the premise that the input data is normal distribution.In this Paper,we propose a transformation to normalize the emotional features,then derivate a Modified QDF(MQDF) to speech emotion recognition.Features based on prosody and voice quality are extracted and Principal Component Analysis Neural Network (PCANN) is used to reduce dimension of the feature vectors.The results show that voice quality features are effective supplement for recognition.and the method in this paper could improve the recognition ratio effectively.

ERP Correlates of Recognition Memory in Autism Spectrum Disorder

Science.gov (United States)

Massand, Esha; Bowler, Dermot M.; Mottron, Laurent; Hosein, Anthony; Jemel, Boutheina

2013-01-01

Recognition memory in autism spectrum disorder (ASD) tends to be undiminished compared to that of typically developing (TD) individuals (Bowler et al. 2007), but it is still unknown whether memory in ASD relies on qualitatively similar or different neurophysiology. We sought to explore the neural activity underlying recognition by employing the…

Man machine interface based on speech recognition

International Nuclear Information System (INIS)

Jorge, Carlos A.F.; Aghina, Mauricio A.C.; Mol, Antonio C.A.; Pereira, Claudio M.N.A.

2007-01-01

This work reports the development of a Man Machine Interface based on speech recognition. The system must recognize spoken commands, and execute the desired tasks, without manual interventions of operators. The range of applications goes from the execution of commands in an industrial plant's control room, to navigation and interaction in virtual environments. Results are reported for isolated word recognition, the isolated words corresponding to the spoken commands. For the pre-processing stage, relevant parameters are extracted from the speech signals, using the cepstral analysis technique, that are used for isolated word recognition, and corresponds to the inputs of an artificial neural network, that performs recognition tasks. (author)

The neural cell adhesion molecule-derived peptide FGL facilitates long-term plasticity in the dentate gyrus in vivo

DEFF Research Database (Denmark)

Dallérac, Glenn; Zerwas, Meike; Novikova, Tatiana

2011-01-01

The neural cell adhesion molecule (NCAM) is known to play a role in developmental and structural processes but also in synaptic plasticity and memory of the adult animal. Recently, FGL, a NCAM mimetic peptide that binds to the Fibroblast Growth Factor Receptor 1 (FGFR-1), has been shown to have...... a beneficial impact on normal memory functioning, as well as to rescue some pathological cognitive impairments. Whether its facilitating impact may be mediated through promoting neuronal plasticity is not known. The present study was therefore designed to test whether FGL modulates the induction...

Rotation Invariance Neural Network

OpenAIRE

Li, Shiyuan

2017-01-01

Rotation invariance and translation invariance have great values in image recognition tasks. In this paper, we bring a new architecture in convolutional neural network (CNN) named cyclic convolutional layer to achieve rotation invariance in 2-D symbol recognition. We can also get the position and orientation of the 2-D symbol by the network to achieve detection purpose for multiple non-overlap target. Last but not least, this architecture can achieve one-shot learning in some cases using thos...

Neuro System Structure for Vehicle Recognition and Count in Floating Bridge Specific Conditions

Directory of Open Access Journals (Sweden)

Slobodan Beroš

2012-10-01

Full Text Available The paper presents the research of the sophisticated vehiclerecognition and count system based on the application of theneural network. The basic elements of neural network andadaptive logic network for object recognition are discussed. Theadaptive logic network solution ability based on simple digitalcircuits as crucial in real-time applications is pointed out. Thesimulation based on the use of reduced high level noise pictureand a tree 2. 7. software have shown excellent results. The consideredand simulated adaptive neural network based systemwith its good recognition and convergence is a useful real-timesolution for vehicle recognition and count in the floating bridgesevere conditions.

Comparison of crisp and fuzzy character networks in handwritten word recognition

Science.gov (United States)

Gader, Paul; Mohamed, Magdi; Chiang, Jung-Hsien

1992-01-01

Experiments involving handwritten word recognition on words taken from images of handwritten address blocks from the United States Postal Service mailstream are described. The word recognition algorithm relies on the use of neural networks at the character level. The neural networks are trained using crisp and fuzzy desired outputs. The fuzzy outputs were defined using a fuzzy k-nearest neighbor algorithm. The crisp networks slightly outperformed the fuzzy networks at the character level but the fuzzy networks outperformed the crisp networks at the word level.

Point-of-Care Determination of Acetaminophen Levels with Multi-Hydrogen Bond Manipulated Single-Molecule Recognition (eMuHSiR).

Science.gov (United States)

Zhang, Yan; Huang, Zhongyuan; Wang, Letao; Wang, Chunming; Zhang, Changde; Wiese, Tomas; Wang, Guangdi; Riley, Kevin; Wang, Zhe

2018-04-03

This work aims to face the challenge of monitoring small molecule drugs accurately and rapidly for point-of-care (POC) diagnosis in current clinical settings. Overdose of acetaminophen (AP), a commonly used over the counter (OTC) analgesic drug, has been determined to be a major cause of acute liver failure in the US and the UK. However, there is no rapid and accurate detection method available for this drug in the emergency room. The present study examined an AP sensing strategy that relies on a previously unexplored strong interaction between AP and the arginine (Arg) molecule. It was found that as many as 4 hydrogen bonds can be formed between one Arg molecule and one AP molecule. By taking advantages of this structural selectivity and high tenability of hydrogen bonds, Arg, immobilized on a graphene surface via electrostatic interactions, was utilized to structurally capture AP. Interestingly, bonded AP still remained the perfect electrochemical activities. The extent of Arg-AP bonds was quantified using a newly designed electrochemical (EC) sensor. To verify the feasibility of this novel assay, based on multihydrogen bond manipulated single-molecule recognition (eMuHSiR), both pharmaceutical and serum sample were examined. In commercial tablet measurement, no significant difference was seen between the results of eMuHSiR and other standard methods. For measuring AP concentration in the mice blood, the substances in serum, such as sugars and fats, would not bring any interference to the eMuHSiR in a wide concentration range. This eMuHSiR method opens the way for future development of small molecule detection for the POC testing.

Discriminative training of self-structuring hidden control neural models

DEFF Research Database (Denmark)

Sørensen, Helge Bjarup Dissing; Hartmann, Uwe; Hunnerup, Preben

1995-01-01

This paper presents a new training algorithm for self-structuring hidden control neural (SHC) models. The SHC models were trained non-discriminatively for speech recognition applications. Better recognition performance can generally be achieved, if discriminative training is applied instead. Thus...... we developed a discriminative training algorithm for SHC models, where each SHC model for a specific speech pattern is trained with utterances of the pattern to be recognized and with other utterances. The discriminative training of SHC neural models has been tested on the TIDIGITS database...

Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition.

Science.gov (United States)

Kasabov, Nikola; Dhoble, Kshitij; Nuntalid, Nuttapod; Indiveri, Giacomo

2013-05-01

On-line learning and recognition of spatio- and spectro-temporal data (SSTD) is a very challenging task and an important one for the future development of autonomous machine learning systems with broad applications. Models based on spiking neural networks (SNN) have already proved their potential in capturing spatial and temporal data. One class of them, the evolving SNN (eSNN), uses a one-pass rank-order learning mechanism and a strategy to evolve a new spiking neuron and new connections to learn new patterns from incoming data. So far these networks have been mainly used for fast image and speech frame-based recognition. Alternative spike-time learning methods, such as Spike-Timing Dependent Plasticity (STDP) and its variant Spike Driven Synaptic Plasticity (SDSP), can also be used to learn spatio-temporal representations, but they usually require many iterations in an unsupervised or semi-supervised mode of learning. This paper introduces a new class of eSNN, dynamic eSNN, that utilise both rank-order learning and dynamic synapses to learn SSTD in a fast, on-line mode. The paper also introduces a new model called deSNN, that utilises rank-order learning and SDSP spike-time learning in unsupervised, supervised, or semi-supervised modes. The SDSP learning is used to evolve dynamically the network changing connection weights that capture spatio-temporal spike data clusters both during training and during recall. The new deSNN model is first illustrated on simple examples and then applied on two case study applications: (1) moving object recognition using address-event representation (AER) with data collected using a silicon retina device; (2) EEG SSTD recognition for brain-computer interfaces. The deSNN models resulted in a superior performance in terms of accuracy and speed when compared with other SNN models that use either rank-order or STDP learning. The reason is that the deSNN makes use of both the information contained in the order of the first input spikes

A deep convolutional neural network approach to single-particle recognition in cryo-electron microscopy.

Science.gov (United States)

Zhu, Yanan; Ouyang, Qi; Mao, Youdong

2017-07-21

Single-particle cryo-electron microscopy (cryo-EM) has become a mainstream tool for the structural determination of biological macromolecular complexes. However, high-resolution cryo-EM reconstruction often requires hundreds of thousands of single-particle images. Particle extraction from experimental micrographs thus can be laborious and presents a major practical bottleneck in cryo-EM structural determination. Existing computational methods for particle picking often use low-resolution templates for particle matching, making them susceptible to reference-dependent bias. It is critical to develop a highly efficient template-free method for the automatic recognition of particle images from cryo-EM micrographs. We developed a deep learning-based algorithmic framework, DeepEM, for single-particle recognition from noisy cryo-EM micrographs, enabling automated particle picking, selection and verification in an integrated fashion. The kernel of DeepEM is built upon a convolutional neural network (CNN) composed of eight layers, which can be recursively trained to be highly "knowledgeable". Our approach exhibits an improved performance and accuracy when tested on the standard KLH dataset. Application of DeepEM to several challenging experimental cryo-EM datasets demonstrated its ability to avoid the selection of un-wanted particles and non-particles even when true particles contain fewer features. The DeepEM methodology, derived from a deep CNN, allows automated particle extraction from raw cryo-EM micrographs in the absence of a template. It demonstrates an improved performance, objectivity and accuracy. Application of this novel method is expected to free the labor involved in single-particle verification, significantly improving the efficiency of cryo-EM data processing.

Application of deep convolutional neural networks for ocean front recognition

Science.gov (United States)

Lima, Estanislau; Sun, Xin; Yang, Yuting; Dong, Junyu

2017-10-01

Ocean fronts have been a subject of study for many years, a variety of methods and algorithms have been proposed to address the problem of ocean fronts. However, all these existing ocean front recognition methods are built upon human expertise in defining the front based on subjective thresholds of relevant physical variables. This paper proposes a deep learning approach for ocean front recognition that is able to automatically recognize the front. We first investigated four existing deep architectures, i.e., AlexNet, CaffeNet, GoogLeNet, and VGGNet, for the ocean front recognition task using remote sensing (RS) data. We then propose a deep network with fewer layers compared to existing architecture for the front recognition task. This network has a total of five learnable layers. In addition, we extended the proposed network to recognize and classify the front into strong and weak ones. We evaluated and analyzed the proposed network with two strategies of exploiting the deep model: full-training and fine-tuning. Experiments are conducted on three different RS image datasets, which have different properties. Experimental results show that our model can produce accurate recognition results.

Action recognition is sensitive to the identity of the actor.

Science.gov (United States)

Ferstl, Ylva; Bülthoff, Heinrich; de la Rosa, Stephan

2017-09-01

Recognizing who is carrying out an action is essential for successful human interaction. The cognitive mechanisms underlying this ability are little understood and have been subject of discussions in embodied approaches to action recognition. Here we examine one solution, that visual action recognition processes are at least partly sensitive to the actor's identity. We investigated the dependency between identity information and action related processes by testing the sensitivity of neural action recognition processes to clothing and facial identity information with a behavioral adaptation paradigm. Our results show that action adaptation effects are in fact modulated by both clothing information and the actor's facial identity. The finding demonstrates that neural processes underlying action recognition are sensitive to identity information (including facial identity) and thereby not exclusively tuned to actions. We suggest that such response properties are useful to help humans in knowing who carried out an action. Copyright © 2017 The Author(s). Published by Elsevier B.V. All rights reserved.

The fibroblast growth factor receptor (FGFR) agonist FGF1 and the neural cell adhesion molecule-derived peptide FGL activate FGFR substrate 2alpha differently

DEFF Research Database (Denmark)

Chen, Yongshuo; Li, Shizhong; Berezin, Vladimir

2010-01-01

Activation of fibroblast growth factor (FGF) receptors (FGFRs) both by FGFs and by the neural cell adhesion molecule (NCAM) is crucial in the development and function of the nervous system. We found that FGFR substrate 2alpha (FRS2alpha), Src homologous and collagen A (ShcA), and phospholipase-Cg...

Neural correlates of memory encoding and recognition for own-race and other-race faces in an associative-memory task.

Science.gov (United States)

Herzmann, Grit; Minor, Greta; Adkins, Makenzie

2017-01-15

The ability to recognize faces of family members, friends, and acquaintances plays an important role in our daily interactions. The other-race effect is the reduced ability to recognize other-race faces as compared to own-race faces. Previous studies showed different patterns of event-related potentials (ERPs) associated with recollection and familiarity during memory encoding (i.e., Dm) and recognition (i.e., parietal old/new effect) for own-race and other-race faces in a subjective-recollection task (remember-know judgments). The present study investigated the same neural correlates of the other-race effect in an associative-memory task, in which Caucasian and East Asian participants learned and recognized own-race and other-race faces along with background colors. Participants made more false alarms for other-race faces indicating lower memory performance. During the study phase, subsequently recognized other-race faces (with and without correct background information) elicited more positive mean amplitudes than own-race faces, suggesting increased neural activation during encoding of other-race faces. During the test phase, recollection-related old/new effects dissociated between own-race and other-race faces. Old/new effects were significant only for own-race but not for other-race faces, indicating that recognition only of own-race faces was supported by recollection and led to more detailed memory retrieval. Most of these results replicated previous studies that used a subjective-recollection task. Our study also showed that the increased demand on memory encoding during an associative-memory task led to Dm patterns that indicated similarly deep memory encoding for own-race and other-race faces. Copyright © 2016 Elsevier B.V. All rights reserved.

Computerised working memory based cognitive remediation therapy does not affect Reading the Mind in the Eyes test performance or neural activity during a Facial Emotion Recognition test in psychosis.

Science.gov (United States)

Mothersill, David; Dillon, Rachael; Hargreaves, April; Castorina, Marco; Furey, Emilia; Fagan, Andrew J; Meaney, James F; Fitzmaurice, Brian; Hallahan, Brian; McDonald, Colm; Wykes, Til; Corvin, Aiden; Robertson, Ian H; Donohoe, Gary

2018-05-27

Working memory based cognitive remediation therapy (CT) for psychosis has recently been associated with broad improvements in performance on untrained tasks measuring working memory, episodic memory and IQ, and changes in associated brain regions. However, it is unclear if these improvements transfer to the domain of social cognition and neural activity related to performance on social cognitive tasks. We examined performance on the Reading the Mind in the Eyes test (Eyes test) in a large sample of participants with psychosis who underwent working memory based CT (N = 43) compared to a Control Group of participants with psychosis (N = 35). In a subset of this sample, we used functional magnetic resonance imaging (fMRI) to examine changes in neural activity during a facial emotion recognition task in participants who underwent CT (N = 15) compared to a Control Group (N = 15). No significant effects of CT were observed on Eyes test performance or on neural activity during facial emotion recognition, either at pworking memory based CT does not significantly impact an aspect of social cognition which was measured behaviourally and neurally. It provides further evidence that deficits in the ability to decode mental state from facial expressions are dissociable from working memory deficits, and suggests that future CT programs should target social cognition in addition to working memory for the purposes of further enhancing social function. This article is protected by copyright. All rights reserved. This article is protected by copyright. All rights reserved.

PTX3, a Humoral Pattern Recognition Molecule, in Innate Immunity, Tissue Repair, and Cancer.

Science.gov (United States)

Garlanda, Cecilia; Bottazzi, Barbara; Magrini, Elena; Inforzato, Antonio; Mantovani, Alberto

2018-04-01

Innate immunity includes a cellular and a humoral arm. PTX3 is a fluid-phase pattern recognition molecule conserved in evolution which acts as a key component of humoral innate immunity in infections of fungal, bacterial, and viral origin. PTX3 binds conserved microbial structures and self-components under conditions of inflammation and activates effector functions (complement, phagocytosis). Moreover, it has a complex regulatory role in inflammation, such as ischemia/reperfusion injury and cancer-related inflammation, as well as in extracellular matrix organization and remodeling, with profound implications in physiology and pathology. Finally, PTX3 acts as an extrinsic oncosuppressor gene by taming tumor-promoting inflammation in murine and selected human tumors. Thus evidence suggests that PTX3 is a key homeostatic component at the crossroad of innate immunity, inflammation, tissue repair, and cancer. Dissecting the complexity of PTX3 pathophysiology and human genetics paves the way to diagnostic and therapeutic exploitation.

Advances in neural networks computational and theoretical issues

CERN Document Server

Esposito, Anna; Morabito, Francesco

2015-01-01

This book collects research works that exploit neural networks and machine learning techniques from a multidisciplinary perspective. Subjects covered include theoretical, methodological and computational topics which are grouped together into chapters devoted to the discussion of novelties and innovations related to the field of Artificial Neural Networks as well as the use of neural networks for applications, pattern recognition, signal processing, and special topics such as the detection and recognition of multimodal emotional expressions and daily cognitive functions, and  bio-inspired memristor-based networks.  Providing insights into the latest research interest from a pool of international experts coming from different research fields, the volume becomes valuable to all those with any interest in a holistic approach to implement believable, autonomous, adaptive, and context-aware Information Communication Technologies.

Neural Networks

International Nuclear Information System (INIS)

Smith, Patrick I.

2003-01-01

Physicists use large detectors to measure particles created in high-energy collisions at particle accelerators. These detectors typically produce signals indicating either where ionization occurs along the path of the particle, or where energy is deposited by the particle. The data produced by these signals is fed into pattern recognition programs to try to identify what particles were produced, and to measure the energy and direction of these particles. Ideally, there are many techniques used in this pattern recognition software. One technique, neural networks, is particularly suitable for identifying what type of particle caused by a set of energy deposits. Neural networks can derive meaning from complicated or imprecise data, extract patterns, and detect trends that are too complex to be noticed by either humans or other computer related processes. To assist in the advancement of this technology, Physicists use a tool kit to experiment with several neural network techniques. The goal of this research is interface a neural network tool kit into Java Analysis Studio (JAS3), an application that allows data to be analyzed from any experiment. As the final result, a physicist will have the ability to train, test, and implement a neural network with the desired output while using JAS3 to analyze the results or output. Before an implementation of a neural network can take place, a firm understanding of what a neural network is and how it works is beneficial. A neural network is an artificial representation of the human brain that tries to simulate the learning process [5]. It is also important to think of the word artificial in that definition as computer programs that use calculations during the learning process. In short, a neural network learns by representative examples. Perhaps the easiest way to describe the way neural networks learn is to explain how the human brain functions. The human brain contains billions of neural cells that are responsible for processing

ZDHHC3 Tyrosine Phosphorylation Regulates Neural Cell Adhesion Molecule Palmitoylation

Science.gov (United States)

Lievens, Patricia Marie-Jeanne; Kuznetsova, Tatiana; Kochlamazashvili, Gaga; Cesca, Fabrizia; Gorinski, Natalya; Galil, Dalia Abdel; Cherkas, Volodimir; Ronkina, Natalia; Lafera, Juri; Gaestel, Matthias

2016-01-01

The neural cell adhesion molecule (NCAM) mediates cell-cell and cell-matrix adhesion. It is broadly expressed in the nervous system and regulates neurite outgrowth, synaptogenesis, and synaptic plasticity. Previous in vitro studies revealed that palmitoylation of NCAM is required for fibroblast growth factor 2 (FGF2)-stimulated neurite outgrowth and identified the zinc finger DHHC (Asp-His-His-Cys)-containing proteins ZDHHC3 and ZDHHC7 as specific NCAM-palmitoylating enzymes. Here, we verified that FGF2 controlled NCAM palmitoylation in vivo and investigated molecular mechanisms regulating NCAM palmitoylation by ZDHHC3. Experiments with overexpression and pharmacological inhibition of FGF receptor (FGFR) and Src revealed that these kinases control tyrosine phosphorylation of ZDHHC3 and that ZDHHC3 is phosphorylated by endogenously expressed FGFR and Src proteins. By site-directed mutagenesis, we found that Tyr18 is an FGFR1-specific ZDHHC3 phosphorylation site, while Tyr295 and Tyr297 are specifically phosphorylated by Src kinase in cell-based and cell-free assays. Abrogation of tyrosine phosphorylation increased ZDHHC3 autopalmitoylation, enhanced interaction with NCAM, and upregulated NCAM palmitoylation. Expression of ZDHHC3 with tyrosine mutated in cultured hippocampal neurons promoted neurite outgrowth. Our findings for the first time highlight that FGFR- and Src-mediated tyrosine phosphorylation of ZDHHC3 modulates ZDHHC3 enzymatic activity and plays a role in neuronal morphogenesis. PMID:27247265

Pattern Recognition Methods and Features Selection for Speech Emotion Recognition System.

Science.gov (United States)

Partila, Pavol; Voznak, Miroslav; Tovarek, Jaromir

2015-01-01

The impact of the classification method and features selection for the speech emotion recognition accuracy is discussed in this paper. Selecting the correct parameters in combination with the classifier is an important part of reducing the complexity of system computing. This step is necessary especially for systems that will be deployed in real-time applications. The reason for the development and improvement of speech emotion recognition systems is wide usability in nowadays automatic voice controlled systems. Berlin database of emotional recordings was used in this experiment. Classification accuracy of artificial neural networks, k-nearest neighbours, and Gaussian mixture model is measured considering the selection of prosodic, spectral, and voice quality features. The purpose was to find an optimal combination of methods and group of features for stress detection in human speech. The research contribution lies in the design of the speech emotion recognition system due to its accuracy and efficiency.

Localizing Tortoise Nests by Neural Networks.

Directory of Open Access Journals (Sweden)

Roberto Barbuti

Full Text Available The goal of this research is to recognize the nest digging activity of tortoises using a device mounted atop the tortoise carapace. The device classifies tortoise movements in order to discriminate between nest digging, and non-digging activity (specifically walking and eating. Accelerometer data was collected from devices attached to the carapace of a number of tortoises during their two-month nesting period. Our system uses an accelerometer and an activity recognition system (ARS which is modularly structured using an artificial neural network and an output filter. For the purpose of experiment and comparison, and with the aim of minimizing the computational cost, the artificial neural network has been modelled according to three different architectures based on the input delay neural network (IDNN. We show that the ARS can achieve very high accuracy on segments of data sequences, with an extremely small neural network that can be embedded in programmable low power devices. Given that digging is typically a long activity (up to two hours, the application of ARS on data segments can be repeated over time to set up a reliable and efficient system, called Tortoise@, for digging activity recognition.

Artificial neural networks application for horizontal and vertical forecasting radionuclides transport

International Nuclear Information System (INIS)

Khil'ko, O.S.; Kovalenko, V.I.; Kundas, S.P.

2010-01-01

Artificial neural networks approach for horizontal and vertical radionuclide transport forecasting was proposed. Runoff factors analysis was considered. Additional artificial neural network structures for physical-chemical properties recognition were used. (authors)

Can color changes alter the neural correlates of recognition memory? Manipulation of processing affects an electrophysiological indicator of conceptual implicit memory.

Science.gov (United States)

Cui, Xiaoyu; Gao, Chuanji; Zhou, Jianshe; Guo, Chunyan

2016-09-28

It has been widely shown that recognition memory includes two distinct retrieval processes: familiarity and recollection. Many studies have shown that recognition memory can be facilitated when there is a perceptual match between the studied and the tested items. Most event-related potential studies have explored the perceptual match effect on familiarity on the basis of the hypothesis that the specific event-related potential component associated with familiarity is the FN400 (300-500 ms mid-frontal effect). However, it is currently unclear whether the FN400 indexes familiarity or conceptual implicit memory. In addition, on the basis of the findings of a previous study, the so-called perceptual manipulations in previous studies may also involve some conceptual alterations. Therefore, we sought to determine the influence of perceptual manipulation by color changes on recognition memory when the perceptual or the conceptual processes were emphasized. Specifically, different instructions (perceptually or conceptually oriented) were provided to the participants. The results showed that color changes may significantly affect overall recognition memory behaviorally and that congruent items were recognized with a higher accuracy rate than incongruent items in both tasks, but no corresponding neural changes were found. Despite the evident familiarity shown in the two tasks (the behavioral performance of recognition memory was much higher than at the chance level), the FN400 effect was found in conceptually oriented tasks, but not perceptually oriented tasks. It is thus highly interesting that the FN400 effect was not induced, although color manipulation of recognition memory was behaviorally shown, as seen in previous studies. Our findings of the FN400 effect for the conceptual but not perceptual condition support the explanation that the FN400 effect indexes conceptual implicit memory.

Continuous Chinese sign language recognition with CNN-LSTM

Science.gov (United States)

Yang, Su; Zhu, Qing

2017-07-01

The goal of sign language recognition (SLR) is to translate the sign language into text, and provide a convenient tool for the communication between the deaf-mute and the ordinary. In this paper, we formulate an appropriate model based on convolutional neural network (CNN) combined with Long Short-Term Memory (LSTM) network, in order to accomplish the continuous recognition work. With the strong ability of CNN, the information of pictures captured from Chinese sign language (CSL) videos can be learned and transformed into vector. Since the video can be regarded as an ordered sequence of frames, LSTM model is employed to connect with the fully-connected layer of CNN. As a recurrent neural network (RNN), it is suitable for sequence learning tasks with the capability of recognizing patterns defined by temporal distance. Compared with traditional RNN, LSTM has performed better on storing and accessing information. We evaluate this method on our self-built dataset including 40 daily vocabularies. The experimental results show that the recognition method with CNN-LSTM can achieve a high recognition rate with small training sets, which will meet the needs of real-time SLR system.

Development of a System for Automatic Recognition of Speech

Directory of Open Access Journals (Sweden)

Roman Jarina

2003-01-01

Full Text Available The article gives a review of a research on processing and automatic recognition of speech signals (ARR at the Department of Telecommunications of the Faculty of Electrical Engineering, University of iilina. On-going research is oriented to speech parametrization using 2-dimensional cepstral analysis, and to an application of HMMs and neural networks for speech recognition in Slovak language. The article summarizes achieved results and outlines future orientation of our research in automatic speech recognition.

The association between reconstructed phase space and Artificial Neural Networks for vectorcardiographic recognition of myocardial infarction.

Science.gov (United States)

Costa, Cecília M; Silva, Ittalo S; de Sousa, Rafael D; Hortegal, Renato A; Regis, Carlos Danilo M

Myocardial infarction is one of the leading causes of death worldwide. As it is life threatening, it requires an immediate and precise treatment. Due to this, a growing number of research and innovations in the field of biomedical signal processing is in high demand. This paper proposes the association of Reconstructed Phase Space and Artificial Neural Networks for Vectorcardiography Myocardial Infarction Recognition. The algorithm promotes better results for the box size 10 × 10 and the combination of four parameters: box counting (Vx), box counting (Vz), self-similarity method (Vx) and self-similarity method (Vy) with sensitivity = 92%, specificity = 96% and accuracy = 94%. The topographic diagnosis presented different performances for different types of infarctions with better results for anterior wall infarctions and less accurate results for inferior infarctions. Copyright © 2018 Elsevier Inc. All rights reserved.

A novel word spotting method based on recurrent neural networks.

Science.gov (United States)

Frinken, Volkmar; Fischer, Andreas; Manmatha, R; Bunke, Horst

2012-02-01

Keyword spotting refers to the process of retrieving all instances of a given keyword from a document. In the present paper, a novel keyword spotting method for handwritten documents is described. It is derived from a neural network-based system for unconstrained handwriting recognition. As such it performs template-free spotting, i.e., it is not necessary for a keyword to appear in the training set. The keyword spotting is done using a modification of the CTC Token Passing algorithm in conjunction with a recurrent neural network. We demonstrate that the proposed systems outperform not only a classical dynamic time warping-based approach but also a modern keyword spotting system, based on hidden Markov models. Furthermore, we analyze the performance of the underlying neural networks when using them in a recognition task followed by keyword spotting on the produced transcription. We point out the advantages of keyword spotting when compared to classic text line recognition.

Use of Splines in Handwritten Character Recognition

OpenAIRE

Sunil Kumar; Gopinath S,; Satish Kumar; Rajesh Chhikara

2010-01-01

Handwritten Character Recognition is software used to identify the handwritten characters and receive and interpret intelligible andwritten input from sources such as manuscript documents. The recent past several years has seen the development of many systems which are able to simulate the human brain actions. Among the many, the neural networks and the artificial intelligence are the most two important paradigms used. In this paper we propose a new algorithm for recognition of handwritten t...

Acceleration of spiking neural network based pattern recognition on NVIDIA graphics processors.

Science.gov (United States)

Han, Bing; Taha, Tarek M

2010-04-01

There is currently a strong push in the research community to develop biological scale implementations of neuron based vision models. Systems at this scale are computationally demanding and generally utilize more accurate neuron models, such as the Izhikevich and the Hodgkin-Huxley models, in favor of the more popular integrate and fire model. We examine the feasibility of using graphics processing units (GPUs) to accelerate a spiking neural network based character recognition network to enable such large scale systems. Two versions of the network utilizing the Izhikevich and Hodgkin-Huxley models are implemented. Three NVIDIA general-purpose (GP) GPU platforms are examined, including the GeForce 9800 GX2, the Tesla C1060, and the Tesla S1070. Our results show that the GPGPUs can provide significant speedup over conventional processors. In particular, the fastest GPGPU utilized, the Tesla S1070, provided a speedup of 5.6 and 84.4 over highly optimized implementations on the fastest central processing unit (CPU) tested, a quadcore 2.67 GHz Xeon processor, for the Izhikevich and the Hodgkin-Huxley models, respectively. The CPU implementation utilized all four cores and the vector data parallelism offered by the processor. The results indicate that GPUs are well suited for this application domain.

Bio-recognitive photonics of a DNA-guided organic semiconductor

Science.gov (United States)

Back, Seung Hyuk; Park, Jin Hyuk; Cui, Chunzhi; Ahn, Dong June

2016-01-01

Incorporation of duplex DNA with higher molecular weights has attracted attention for a new opportunity towards a better organic light-emitting diode (OLED) capability. However, biological recognition by OLED materials is yet to be addressed. In this study, specific oligomeric DNA-DNA recognition is successfully achieved by tri (8-hydroxyquinoline) aluminium (Alq3), an organic semiconductor. Alq3 rods crystallized with guidance from single-strand DNA molecules show, strikingly, a unique distribution of the DNA molecules with a shape of an `inverted' hourglass. The crystal's luminescent intensity is enhanced by 1.6-fold upon recognition of the perfect-matched target DNA sequence, but not in the case of a single-base mismatched one. The DNA-DNA recognition forming double-helix structure is identified to occur only in the rod's outer periphery. This study opens up new opportunities of Alq3, one of the most widely used OLED materials, enabling biological recognition.

Bio-recognitive photonics of a DNA-guided organic semiconductor.

Science.gov (United States)

Back, Seung Hyuk; Park, Jin Hyuk; Cui, Chunzhi; Ahn, Dong June

2016-01-04

Incorporation of duplex DNA with higher molecular weights has attracted attention for a new opportunity towards a better organic light-emitting diode (OLED) capability. However, biological recognition by OLED materials is yet to be addressed. In this study, specific oligomeric DNA-DNA recognition is successfully achieved by tri (8-hydroxyquinoline) aluminium (Alq3), an organic semiconductor. Alq3 rods crystallized with guidance from single-strand DNA molecules show, strikingly, a unique distribution of the DNA molecules with a shape of an 'inverted' hourglass. The crystal's luminescent intensity is enhanced by 1.6-fold upon recognition of the perfect-matched target DNA sequence, but not in the case of a single-base mismatched one. The DNA-DNA recognition forming double-helix structure is identified to occur only in the rod's outer periphery. This study opens up new opportunities of Alq3, one of the most widely used OLED materials, enabling biological recognition.

Image-based automatic recognition of larvae

Science.gov (United States)

Sang, Ru; Yu, Guiying; Fan, Weijun; Guo, Tiantai

2010-08-01

As the main objects, imagoes have been researched in quarantine pest recognition in these days. However, pests in their larval stage are latent, and the larvae spread abroad much easily with the circulation of agricultural and forest products. It is presented in this paper that, as the new research objects, larvae are recognized by means of machine vision, image processing and pattern recognition. More visional information is reserved and the recognition rate is improved as color image segmentation is applied to images of larvae. Along with the characteristics of affine invariance, perspective invariance and brightness invariance, scale invariant feature transform (SIFT) is adopted for the feature extraction. The neural network algorithm is utilized for pattern recognition, and the automatic identification of larvae images is successfully achieved with satisfactory results.

Predictive Coding Strategies for Invariant Object Recognition and Volitional Motion Control in Neuromorphic Agents

Science.gov (United States)

2015-09-02

model for scene understanding was proposed based on deep convolutional neural networks to improve recognition accuracy. Facial expression recognition ...A deep-learning-based model for facial expression recognition was formulated. It could recognize emotional status of people regardless of...CVPRW), 2014 IEEE Conference on. IEEE, 2014. DISTRIBUTION A: Distribution approved for public release. 4 Facial Expression Recognition

Neural Network for Nanoscience Scanning Electron Microscope Image Recognition.

Science.gov (United States)

Modarres, Mohammad Hadi; Aversa, Rossella; Cozzini, Stefano; Ciancio, Regina; Leto, Angelo; Brandino, Giuseppe Piero

2017-10-16

In this paper we applied transfer learning techniques for image recognition, automatic categorization, and labeling of nanoscience images obtained by scanning electron microscope (SEM). Roughly 20,000 SEM images were manually classified into 10 categories to form a labeled training set, which can be used as a reference set for future applications of deep learning enhanced algorithms in the nanoscience domain. The categories chosen spanned the range of 0-Dimensional (0D) objects such as particles, 1D nanowires and fibres, 2D films and coated surfaces, and 3D patterned surfaces such as pillars. The training set was used to retrain on the SEM dataset and to compare many convolutional neural network models (Inception-v3, Inception-v4, ResNet). We obtained compatible results by performing a feature extraction of the different models on the same dataset. We performed additional analysis of the classifier on a second test set to further investigate the results both on particular cases and from a statistical point of view. Our algorithm was able to successfully classify around 90% of a test dataset consisting of SEM images, while reduced accuracy was found in the case of images at the boundary between two categories or containing elements of multiple categories. In these cases, the image classification did not identify a predominant category with a high score. We used the statistical outcomes from testing to deploy a semi-automatic workflow able to classify and label images generated by the SEM. Finally, a separate training was performed to determine the volume fraction of coherently aligned nanowires in SEM images. The results were compared with what was obtained using the Local Gradient Orientation method. This example demonstrates the versatility and the potential of transfer learning to address specific tasks of interest in nanoscience applications.

Age-related changes in expression of the neural cell adhesion molecule in skeletal muscle

DEFF Research Database (Denmark)

Andersson, A M; Olsen, M; Zhernosekov, D

1993-01-01

Neural cell adhesion molecule (NCAM) is expressed by muscle and involved in muscle-neuron and muscle-muscle cell interactions. The expression in muscle is regulated during myogenesis and by the state of innervation. In aged muscle, both neurogenic and myogenic degenerative processes occur. We here...... report quantitative and qualitative changes in NCAM protein and mRNA forms during aging in normal rat skeletal muscle. Determination of the amount of NCAM by e.l.i.s.a. showed that the level decreased from perinatal to adult age, followed by a considerable increase in 24-month-old rat muscle. Thus NCAM...... concentration in aged muscle was sixfold higher than in young adult muscle. In contrast with previous reports, NCAM polypeptides of 200, 145, 125 and 120 kDa were observed by immunoblotting throughout postnatal development and aging, the relative proportions of the individual NCAM polypeptides remaining...

Optical-Correlator Neural Network Based On Neocognitron

Science.gov (United States)

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.

Preparation and Property Recognition of Nimodipine Molecularly Imprinted Polymer

Directory of Open Access Journals (Sweden)

Fei-fei CHEN

2015-09-01

Full Text Available Objective: To explore the application of molecular imprinting technique in the separation and detection of nimodipine. Methods: Methacrylic acid as functional monomer, pentaerythritol triacrylate as cross-linking agent were used to prepare molecularly imprinted polymer (MIP with the feature of specific recognition performance on imprinting molecule nimodipine under condition of template molecule nimodipine. The preparation conditions, recognition performance of MIP on nimodipine, different proportions of template molecule and functional monomer, the selectivity to other substrate, and the relationship between adsorption quantity (Q and time were observed. Results: MIP was prepared successfully bynimodipine as template and pentaerythritol triacrylate as cross-linking agent, with the feature of specific recognition performance on nimodipine. The static adsorption distribution coefficient (KD was 0.2264. The equation of Q and the concentration of substrate of template MIP was y = -0.21x+0.2204. Combining capacity of template molecule at the same concentration enhanced with the increasing proportion of functional monomer.Conclusion: Nimodipine MIP based on molecular imprinting technique may become a new approach to chiral separation for nimodipine.

The Neural Correlates of Everyday Recognition Memory

Science.gov (United States)

Milton, F.; Muhlert, N.; Butler, C. R.; Benattayallah, A.; Zeman, A. Z.

2011-01-01

We used a novel automatic camera, SenseCam, to create a recognition memory test for real-life events. Adapting a "Remember/Know" paradigm, we asked healthy undergraduates, who wore SenseCam for 2 days, in their everyday environments, to classify images as strongly or weakly remembered, strongly or weakly familiar or novel, while brain activation…

Pattern Recognition Methods and Features Selection for Speech Emotion Recognition System

Directory of Open Access Journals (Sweden)

Pavol Partila

2015-01-01

Full Text Available The impact of the classification method and features selection for the speech emotion recognition accuracy is discussed in this paper. Selecting the correct parameters in combination with the classifier is an important part of reducing the complexity of system computing. This step is necessary especially for systems that will be deployed in real-time applications. The reason for the development and improvement of speech emotion recognition systems is wide usability in nowadays automatic voice controlled systems. Berlin database of emotional recordings was used in this experiment. Classification accuracy of artificial neural networks, k-nearest neighbours, and Gaussian mixture model is measured considering the selection of prosodic, spectral, and voice quality features. The purpose was to find an optimal combination of methods and group of features for stress detection in human speech. The research contribution lies in the design of the speech emotion recognition system due to its accuracy and efficiency.

Altered Expression Profile of IgLON Family of Neural Cell Adhesion Molecules in the Dorsolateral Prefrontal Cortex of Schizophrenic Patients

Directory of Open Access Journals (Sweden)

Karina Karis

2018-01-01

Full Text Available Neural adhesion proteins are crucial in the development and maintenance of functional neural connectivity. Growing evidence suggests that the IgLON family of neural adhesion molecules LSAMP, NTM, NEGR1, and OPCML are important candidates in forming the susceptibility to schizophrenia (SCZ. IgLON proteins have been shown to be involved in neurite outgrowth, synaptic plasticity and neuronal connectivity, all of which have been shown to be altered in the brains of patients with the diagnosis of schizophrenia. Here we optimized custom 5′-isoform-specific TaqMan gene-expression analysis for the transcripts of human IgLON genes to study the expression of IgLONs in the dorsolateral prefrontal cortex (DLPFC of schizophrenic patients (n = 36 and control subjects (n = 36. Uniform 5′-region and a single promoter was confirmed for the human NEGR1 gene by in silico analysis. IgLON5, a recently described family member, was also included in the study. We detected significantly elevated levels of the NEGR1 transcript (1.33-fold increase and the NTM 1b isoform transcript (1.47-fold increase in the DLPFC of schizophrenia patients compared to healthy controls. Consequent protein analysis performed in male subjects confirmed the increase in NEGR1 protein content both in patients with the paranoid subtype and in patients with other subtypes. In-group analysis of patients revealed that lower expression of certain IgLON transcripts, mostly LSAMP 1a and 1b, could be related with concurrent depressive endophenotype in schizophrenic patients. Additionally, our study cohort provides further evidence that cannabis use may be a relevant risk factor associated with suicidal behaviors in psychotic patients. In conclusion, we provide clinical evidence of increased expression levels of particular IgLON family members in the DLPFC of schizophrenic patients. We propose that alterations in the expression profile of IgLON neural adhesion molecules are associated with brain

Neural substrates of view-invariant object recognition developed without experiencing rotations of the objects.

Science.gov (United States)

Okamura, Jun-Ya; Yamaguchi, Reona; Honda, Kazunari; Wang, Gang; Tanaka, Keiji

2014-11-05

One fails to recognize an unfamiliar object across changes in viewing angle when it must be discriminated from similar distractor objects. View-invariant recognition gradually develops as the viewer repeatedly sees the objects in rotation. It is assumed that different views of each object are associated with one another while their successive appearance is experienced in rotation. However, natural experience of objects also contains ample opportunities to discriminate among objects at each of the multiple viewing angles. Our previous behavioral experiments showed that after experiencing a new set of object stimuli during a task that required only discrimination at each of four viewing angles at 30° intervals, monkeys could recognize the objects across changes in viewing angle up to 60°. By recording activities of neurons from the inferotemporal cortex after various types of preparatory experience, we here found a possible neural substrate for the monkeys' performance. For object sets that the monkeys had experienced during the task that required only discrimination at each of four viewing angles, many inferotemporal neurons showed object selectivity covering multiple views. The degree of view generalization found for these object sets was similar to that found for stimulus sets with which the monkeys had been trained to conduct view-invariant recognition. These results suggest that the experience of discriminating new objects in each of several viewing angles develops the partially view-generalized object selectivity distributed over many neurons in the inferotemporal cortex, which in turn bases the monkeys' emergent capability to discriminate the objects across changes in viewing angle. Copyright © 2014 the authors 0270-6474/14/3415047-13$15.00/0.

Optoelectronic Implementation of Neural Networks

Indian Academy of Sciences (India)

neural networks, such as learning, adapting and copying by means of parallel ... to provide robust recognition of hand-printed English text. Engine idle and misfiring .... and s represents the bounded activation function of a neuron. It is typically ...

Application of neural networks in experimental physics

International Nuclear Information System (INIS)

Kisel', I.V.; Neskromnyj, V.N.; Ososkov, G.A.

1993-01-01

The theoretical foundations of numerous models of artificial neural networks (ANN) and their applications to the actual problems of associative memory, optimization and pattern recognition are given. This review contains also numerous using of ANN in the experimental physics both as the hardware realization of fast triggering systems for even selection and for the following software implementation of the trajectory data recognition

Fastest learning in small-world neural networks

International Nuclear Information System (INIS)

Simard, D.; Nadeau, L.; Kroeger, H.

2005-01-01

We investigate supervised learning in neural networks. We consider a multi-layered feed-forward network with back propagation. We find that the network of small-world connectivity reduces the learning error and learning time when compared to the networks of regular or random connectivity. Our study has potential applications in the domain of data-mining, image processing, speech recognition, and pattern recognition

Generalized synthetic aperture radar automatic target recognition by convolutional neural network with joint use of two-dimensional principal component analysis and support vector machine

Science.gov (United States)

Zheng, Ce; Jiang, Xue; Liu, Xingzhao

2017-10-01

Convolutional neural network (CNN), as a vital part of the deep learning research field, has shown powerful potential for automatic target recognition (ATR) of synthetic aperture radar (SAR). However, the high complexity caused by the deep structure of CNN makes it difficult to generalize. An improved form of CNN with higher generalization capability and less probability of overfitting, which further improves the efficiency and robustness of the SAR ATR system, is proposed. The convolution layers of CNN are combined with a two-dimensional principal component analysis algorithm. Correspondingly, the kernel support vector machine is utilized as the classifier layer instead of the multilayer perceptron. The verification experiments are implemented using the moving and stationary target acquisition and recognition database, and the results validate the efficiency of the proposed method.

Support vector machine for automatic pain recognition

Science.gov (United States)

Monwar, Md Maruf; Rezaei, Siamak

2009-02-01

Facial expressions are a key index of emotion and the interpretation of such expressions of emotion is critical to everyday social functioning. In this paper, we present an efficient video analysis technique for recognition of a specific expression, pain, from human faces. We employ an automatic face detector which detects face from the stored video frame using skin color modeling technique. For pain recognition, location and shape features of the detected faces are computed. These features are then used as inputs to a support vector machine (SVM) for classification. We compare the results with neural network based and eigenimage based automatic pain recognition systems. The experiment results indicate that using support vector machine as classifier can certainly improve the performance of automatic pain recognition system.

Electrocardiogram Pattern Recognition and Analysis Based on Artificial Neural Networks and Support Vector Machines: A Review

Directory of Open Access Journals (Sweden)

Mario Sansone

2013-01-01

Full Text Available Computer systems for Electrocardiogram (ECG analysis support the clinician in tedious tasks (e.g., Holter ECG monitored in Intensive Care Units or in prompt detection of dangerous events (e.g., ventricular fibrillation. Together with clinical applications (arrhythmia detection and heart rate variability analysis, ECG is currently being investigated in biometrics (human identification, an emerging area receiving increasing attention. Methodologies for clinical applications can have both differences and similarities with respect to biometrics. This paper reviews methods of ECG processing from a pattern recognition perspective. In particular, we focus on features commonly used for heartbeat classification. Considering the vast literature in the field and the limited space of this review, we dedicated a detailed discussion only to a few classifiers (Artificial Neural Networks and Support Vector Machines because of their popularity; however, other techniques such as Hidden Markov Models and Kalman Filtering will be also mentioned.

Mechanical Fault Diagnosis Using Color Image Recognition of Vibration Spectrogram Based on Quaternion Invariable Moment

Directory of Open Access Journals (Sweden)

Liang Hua

2015-01-01

Full Text Available Automatic extraction of time-frequency spectral image of mechanical faults can be achieved and faults can be identified consequently when rotating machinery spectral image processing technology is applied to fault diagnosis, which is an advantage. Acquired mechanical vibration signals can be converted into color time-frequency spectrum images by the processing of pseudo Wigner-Ville distribution. Then a feature extraction method based on quaternion invariant moment was proposed, combining image processing technology and multiweight neural network technology. The paper adopted quaternion invariant moment feature extraction method and gray level-gradient cooccurrence matrix feature extraction method and combined them with geometric learning algorithm and probabilistic neural network algorithm, respectively, and compared the recognition rates of rolling bearing faults. The experimental results show that the recognition rates of quaternion invariant moment are higher than gray level-gradient cooccurrence matrix in the same recognition method. The recognition rates of geometric learning algorithm are higher than probabilistic neural network algorithm in the same feature extraction method. So the method based on quaternion invariant moment geometric learning and multiweight neural network is superior. What is more, this algorithm has preferable generalization performance under the condition of fewer samples, and it has practical value and acceptation on the field of fault diagnosis for rotating machinery as well.

Toward a multipoint optical fibre sensor system for use in process water systems based on artificial neural network pattern recognition

International Nuclear Information System (INIS)

King, D; Lyons, W B; Flanagan, C; Lewis, E

2005-01-01

An optical fibre sensor capable of detecting various concentrations of ethanol in water supplies is reported. The sensor is based on a U-bend sensor configuration and is incorporated into a 170-metre length of silica cladding silica core optical fibre. The sensor is interrogated using Optical Time Domain Reflectometry (OTDR) and it is proposed to apply artificial neural network (ANN) pattern recognition techniques to the resulting OTDR signals to accurately classify the sensor test conditions. It is also proposed that additional U-bend configuration sensors will be added to the fibre measurement length, in order to implement a multipoint optical fibre sensor system

Perceptual Plasticity for Auditory Object Recognition

Science.gov (United States)

Heald, Shannon L. M.; Van Hedger, Stephen C.; Nusbaum, Howard C.

2017-01-01

In our auditory environment, we rarely experience the exact acoustic waveform twice. This is especially true for communicative signals that have meaning for listeners. In speech and music, the acoustic signal changes as a function of the talker (or instrument), speaking (or playing) rate, and room acoustics, to name a few factors. Yet, despite this acoustic variability, we are able to recognize a sentence or melody as the same across various kinds of acoustic inputs and determine meaning based on listening goals, expectations, context, and experience. The recognition process relates acoustic signals to prior experience despite variability in signal-relevant and signal-irrelevant acoustic properties, some of which could be considered as “noise” in service of a recognition goal. However, some acoustic variability, if systematic, is lawful and can be exploited by listeners to aid in recognition. Perceivable changes in systematic variability can herald a need for listeners to reorganize perception and reorient their attention to more immediately signal-relevant cues. This view is not incorporated currently in many extant theories of auditory perception, which traditionally reduce psychological or neural representations of perceptual objects and the processes that act on them to static entities. While this reduction is likely done for the sake of empirical tractability, such a reduction may seriously distort the perceptual process to be modeled. We argue that perceptual representations, as well as the processes underlying perception, are dynamically determined by an interaction between the uncertainty of the auditory signal and constraints of context. This suggests that the process of auditory recognition is highly context-dependent in that the identity of a given auditory object may be intrinsically tied to its preceding context. To argue for the flexible neural and psychological updating of sound-to-meaning mappings across speech and music, we draw upon examples

An Introduction to Face Recognition Technology

Directory of Open Access Journals (Sweden)

Shang-Hung Lin

2000-01-01

Full Text Available Recently face recognition is attracting much attention in the society of network multimedia information access.  Areas such as network security, content indexing and retrieval, and video compression benefits from face recognition technology because "people" are the center of attention in a lot of video.  Network access control via face recognition not only makes hackers virtually impossible to steal one's "password", but also increases the user-friendliness in human-computer interaction.  Indexing and/or retrieving video data based on the appearances of particular persons will be useful for users such as news reporters, political scientists, and moviegoers.  For the applications of videophone and teleconferencing, the assistance of face recognition also provides a more efficient coding scheme.  In this paper, we give an introductory course of this new information processing technology.  The paper shows the readers the generic framework for the face recognition system, and the variants that are frequently encountered by the face recognizer.  Several famous face recognition algorithms, such as eigenfaces and neural networks, will also be explained.

A Cutting Pattern Recognition Method for Shearers Based on Improved Ensemble Empirical Mode Decomposition and a Probabilistic Neural Network

Directory of Open Access Journals (Sweden)

Jing Xu

2015-10-01

Full Text Available In order to guarantee the stable operation of shearers and promote construction of an automatic coal mining working face, an online cutting pattern recognition method with high accuracy and speed based on Improved Ensemble Empirical Mode Decomposition (IEEMD and Probabilistic Neural Network (PNN is proposed. An industrial microphone is installed on the shearer and the cutting sound is collected as the recognition criterion to overcome the disadvantages of giant size, contact measurement and low identification rate of traditional detectors. To avoid end-point effects and get rid of undesirable intrinsic mode function (IMF components in the initial signal, IEEMD is conducted on the sound. The end-point continuation based on the practical storage data is performed first to overcome the end-point effect. Next the average correlation coefficient, which is calculated by the correlation of the first IMF with others, is introduced to select essential IMFs. Then the energy and standard deviation of the reminder IMFs are extracted as features and PNN is applied to classify the cutting patterns. Finally, a simulation example, with an accuracy of 92.67%, and an industrial application prove the efficiency and correctness of the proposed method.

DEVELOPMENT OF A COMPUTER SYSTEM FOR IDENTITY AUTHENTICATION USING ARTIFICIAL NEURAL NETWORKS

Directory of Open Access Journals (Sweden)

Timur Kartbayev

2017-03-01

Full Text Available The aim of the study is to increase the effectiveness of automated face recognition to authenticate identity, considering features of change of the face parameters over time. The improvement of the recognition accuracy, as well as consideration of the features of temporal changes in a human face can be based on the methodology of artificial neural networks. Hybrid neural networks, combining the advantages of classical neural networks and fuzzy logic systems, allow using the network learnability along with the explanation of the findings. The structural scheme of intelligent system for identification based on artificial neural networks is proposed in this work. It realizes the principles of digital information processing and identity recognition taking into account the forecast of key characteristics’ changes over time (e.g., due to aging. The structural scheme has a three-tier architecture and implements preliminary processing, recognition and identification of images obtained as a result of monitoring. On the basis of expert knowledge, the fuzzy base of products is designed. It allows assessing possible changes in key characteristics, used to authenticate identity based on the image. To take this possibility into consideration, a neuro-fuzzy network of ANFIS type was used, which implements the algorithm of Tagaki-Sugeno. The conducted experiments showed high efficiency of the developed neural network and a low value of learning errors, which allows recommending this approach for practical implementation. Application of the developed system of fuzzy production rules that allow predicting changes in individuals over time, will improve the recognition accuracy, reduce the number of authentication failures and improve the efficiency of information processing and decision-making in applications, such as authentication of bank customers, users of mobile applications, or in video monitoring systems of sensitive sites.

Implementation of neural networks on 'Connection Machine'

International Nuclear Information System (INIS)

Belmonte, Ghislain

1990-12-01

This report is a first approach to the notion of neural networks and their possible applications within the framework of artificial intelligence activities of the Department of Applied Mathematics of the Limeil-Valenton Research Center. The first part is an introduction to the field of neural networks; the main neural network models are described in this section. The applications of neural networks in the field of classification have mainly been studied because they could more particularly help to solve some of the decision support problems dealt with by the C.E.A. As the neural networks perform a large number of parallel operations, it was therefore logical to use a parallel architecture computer: the Connection Machine (which uses 16384 processors and is located at E.T.C.A. Arcueil). The second part presents some generalities on the parallelism and the Connection Machine, and two implementations of neural networks on Connection Machine. The first of these implementations concerns one of the most used algorithms to realize the learning of neural networks: the Gradient Retro-propagation algorithm. The second one, less common, concerns a network of neurons destined mainly to the recognition of forms: the Fukushima Neocognitron. The latter is studied by the C.E.A. of Bruyeres-le-Chatel in order to realize an embedded system (including hardened circuits) for the fast recognition of forms [fr

Self-face recognition in social context.

Science.gov (United States)

Sugiura, Motoaki; Sassa, Yuko; Jeong, Hyeonjeong; Wakusawa, Keisuke; Horie, Kaoru; Sato, Shigeru; Kawashima, Ryuta

2012-06-01

The concept of "social self" is often described as a representation of the self-reflected in the eyes or minds of others. Although the appearance of one's own face has substantial social significance for humans, neuroimaging studies have failed to link self-face recognition and the likely neural substrate of the social self, the medial prefrontal cortex (MPFC). We assumed that the social self is recruited during self-face recognition under a rich social context where multiple other faces are available for comparison of social values. Using functional magnetic resonance imaging (fMRI), we examined the modulation of neural responses to the faces of the self and of a close friend in a social context. We identified an enhanced response in the ventral MPFC and right occipitoparietal sulcus in the social context specifically for the self-face. Neural response in the right lateral parietal and inferior temporal cortices, previously claimed as self-face-specific, was unaffected for the self-face but unexpectedly enhanced for the friend's face in the social context. Self-face-specific activation in the pars triangularis of the inferior frontal gyrus, and self-face-specific reduction of activation in the left middle temporal gyrus and the right supramarginal gyrus, replicating a previous finding, were not subject to such modulation. Our results thus demonstrated the recruitment of a social self during self-face recognition in the social context. At least three brain networks for self-face-specific activation may be dissociated by different patterns of response-modulation in the social context, suggesting multiple dynamic self-other representations in the human brain. Copyright © 2011 Wiley-Liss, Inc.

Cascading neural networks for upper-body gesture recognition

CSIR Research Space (South Africa)

Mangera, R

2014-01-01

Full Text Available Gesture recognition has many applications ranging from health care to entertainment. However for it to be a feasible method of human-computer interaction it is essential that only intentional movements are interpreted and that the system can work...

Multi-stream CNN: Learning representations based on human-related regions for action recognition

NARCIS (Netherlands)

Tu, Zhigang; Xie, Wei; Qin, Qianqing; Poppe, R.W.; Veltkamp, R.C.; Li, Baoxin; Yuan, Junsong

2018-01-01

The most successful video-based human action recognition methods rely on feature representations extracted using Convolutional Neural Networks (CNNs). Inspired by the two-stream network (TS-Net), we propose a multi-stream Convolutional Neural Network (CNN) architecture to recognize human actions. We

Biologically inspired emotion recognition from speech

Directory of Open Access Journals (Sweden)

Buscicchio Cosimo

2011-01-01

Full Text Available Abstract Emotion recognition has become a fundamental task in human-computer interaction systems. In this article, we propose an emotion recognition approach based on biologically inspired methods. Specifically, emotion classification is performed using a long short-term memory (LSTM recurrent neural network which is able to recognize long-range dependencies between successive temporal patterns. We propose to represent data using features derived from two different models: mel-frequency cepstral coefficients (MFCC and the Lyon cochlear model. In the experimental phase, results obtained from the LSTM network and the two different feature sets are compared, showing that features derived from the Lyon cochlear model give better recognition results in comparison with those obtained with the traditional MFCC representation.

Low-power Appliance Recognition using Recurrent Neural Networks

NARCIS (Netherlands)

Rizky Pratama, Azkario; Simanjuntak, Frans Juanda; Lazovik, Aliaksandr; Aiello, Marco

2018-01-01

Indoor energy consumption can be understood by breaking overall power consumption down into individual components and appliance activations. The clas- sification of components of energy usage is known as load disaggregation or ap- pliance recognition. Most of the previous efforts address the

Deep Learning Neural Networks in Cybersecurity - Managing Malware with AI

OpenAIRE

Rayle, Keith

2017-01-01

There’s a lot of talk about the benefits of deep learning (neural networks) and how it’s the new electricity that will power us into the future. Medical diagnosis, computer vision and speech recognition are all examples of use-cases where neural networks are being applied in our everyday business environment. This begs the question…what are the uses of neural-network applications for cyber security? How does the AI process work when applying neural networks to detect malicious software bombar...

Neural networks for event filtering at D/O/

International Nuclear Information System (INIS)

Cutts, D.; Hoftun, J.S.; Sornborger, A.; Johnson, C.R.; Zeller, R.T.

1989-01-01

Neural networks may provide important tools for pattern recognition in high energy physics. We discuss an initial exploration of these techniques, presenting the result of network simulations of several filter algorithms. The D0 data acquisition system, a MicroVAX farm, will perform critical event selection; we describe a possible implementation of neural network algorithms in this system. 7 refs., 4 figs

The neural network z-vertex trigger for the Belle II detector

Energy Technology Data Exchange (ETDEWEB)

Skambraks, Sebastian; Neuhaus, Sara [Technische Universitaet Muenchen (Germany); Chen, Yang; Kiesling, Christian [Max-Planck-Institut fuer Physik, Muenchen (Germany); Collaboration: Belle II-Collaboration

2016-07-01

We present a neural network based first level track trigger for the upcoming Belle II detector at the high luminosity SuperKEKB flavor factory. Using hit and drift time information from the Central Drift Chamber (CDC), neural networks estimate the z-coordinates of single track vertex positions. Especially beam induced background, with vertices outside of the interaction region, can clearly be rejected. This allows to relax the track trigger conditions and thus enhances the efficiency for events with a low track multiplicity. In the CDC trigger pipeline, the preceding 2D pattern recognition enables a unique per track input representation and a sectorization of the track parameter phase space. The precise z-vertices are then estimated by an ensemble of sector-specific local expert neural networks. After an introduction to the neural trigger system, the benefits of an improved 3D pattern recognition are discussed.

Neural networks, D0, and the SSC

International Nuclear Information System (INIS)

Barter, C.; Cutts, D.; Hoftun, J.S.; Partridge, R.A.; Sornborger, A.T.; Johnson, C.T.; Zeller, R.T.

1989-01-01

We outline several exploratory studies involving neural network simulations applied to pattern recognition in high energy physics. We describe the D0 data acquisition system and a natual means by which algorithms derived from neural networks techniques may be incorporated into recently developed hardware associated with the D0 MicroVAX farm nodes. Such applications to the event filtering needed by SSC detectors look interesting. 10 refs., 11 figs

New Serum Markers for Small-Cell Lung Cancer. II. The Neural Cell Adhesion Molecule, NCAM

DEFF Research Database (Denmark)

Vangsted, A.; Drivsholm, L.; Andersen, E.

1994-01-01

The neural cell adhesion molecule (NCAM) was recently suggested as a marker for small-cell lung cancer (SCLC). Immunohistochemical analysis demonstrated the presence of the NCAM in 78% of SCLC patients and in 25% of patients with other cancer forms. NCAM was proposed to be the most sensitive marker...... for SCLC, and it may also be an important prognostic marker for SCLC. We used a competitive ELISA to analyze the concentrations of NCAM in sera from 96 SCLC patients, 16 patients with non-SCLC, 4 patients with other cancer forms, and 16 healthy controls. All sera were collected at the time of diagnosis......, before the patients received chemotherapy. The polyclonal antibody used in the assay recognized all three isoforms of NCAM. The concentration of NCAM was related to clinical parameters of the patients such as age, sex, blood group status, stage of disease, organ site involvement of metastases, survival...

Enhanced Context Recognition by Sensitivity Pruned Vocabularies

DEFF Research Database (Denmark)

Madsen, Rasmus Elsborg; Sigurdsson, Sigurdur; Hansen, Lars Kai

2004-01-01

a latent semantic indexing representation and a probabilistic neural network classifier. Pruning the vocabularies to approximately 20% of the original size, we find consistent context recognition enhancement for two mid size data-sets for a range of training set sizes. We also study the applicability...

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

Science.gov (United States)

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

2017-12-28

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

fMRI characterization of visual working memory recognition.

Science.gov (United States)

Rahm, Benjamin; Kaiser, Jochen; Unterrainer, Josef M; Simon, Juliane; Bledowski, Christoph

2014-04-15

Encoding and maintenance of information in visual working memory have been extensively studied, highlighting the crucial and capacity-limiting role of fronto-parietal regions. In contrast, the neural basis of recognition in visual working memory has remained largely unspecified. Cognitive models suggest that recognition relies on a matching process that compares sensory information with the mental representations held in memory. To characterize the neural basis of recognition we varied both the need for recognition and the degree of similarity between the probe item and the memory contents, while independently manipulating memory load to produce load-related fronto-parietal activations. fMRI revealed a fractionation of working memory functions across four distributed networks. First, fronto-parietal regions were activated independent of the need for recognition. Second, anterior parts of load-related parietal regions contributed to recognition but their activations were independent of the difficulty of matching in terms of sample-probe similarity. These results argue against a key role of the fronto-parietal attention network in recognition. Rather the third group of regions including bilateral temporo-parietal junction, posterior cingulate cortex and superior frontal sulcus reflected demands on matching both in terms of sample-probe-similarity and the number of items to be compared. Also, fourth, bilateral motor regions and right superior parietal cortex showed higher activation when matching provided clear evidence for a decision. Together, the segregation between the well-known fronto-parietal activations attributed to attentional operations in working memory from those regions involved in matching supports the theoretical view of separable attentional and mnemonic contributions to working memory. Yet, the close theoretical and empirical correspondence to perceptual decision making may call for an explicit consideration of decision making mechanisms in

Expression of polysialylated neural cell adhesion molecules on adult stem cells after neuronal differentiation of inner ear spiral ganglion neurons

International Nuclear Information System (INIS)

Park, Kyoung Ho; Yeo, Sang Won; Troy, Frederic A.

2014-01-01

Highlights: • PolySia expressed on neurons primarily during early stages of neuronal development. • PolySia–NCAM is expressed on neural stem cells from adult guinea pig spiral ganglion. • PolySia is a biomarker that modulates neuronal differentiation in inner ear stem cells. - Abstract: During brain development, polysialylated (polySia) neural cell adhesion molecules (polySia–NCAMs) modulate cell–cell adhesive interactions involved in synaptogenesis, neural plasticity, myelination, and neural stem cell (NSC) proliferation and differentiation. Our findings show that polySia–NCAM is expressed on NSC isolated from adult guinea pig spiral ganglion (GPSG), and in neurons and Schwann cells after differentiation of the NSC with epidermal, glia, fibroblast growth factors (GFs) and neurotrophins. These differentiated cells were immunoreactive with mAb’s to polySia, NCAM, β-III tubulin, nestin, S-100 and stained with BrdU. NSC could regenerate and be differentiated into neurons and Schwann cells. We conclude: (1) polySia is expressed on NSC isolated from adult GPSG and on neurons and Schwann cells differentiated from these NSC; (2) polySia is expressed on neurons primarily during the early stage of neuronal development and is expressed on Schwann cells at points of cell–cell contact; (3) polySia is a functional biomarker that modulates neuronal differentiation in inner ear stem cells. These new findings suggest that replacement of defective cells in the inner ear of hearing impaired patients using adult spiral ganglion neurons may offer potential hope to improve the quality of life for patients with auditory dysfunction and impaired hearing disorders

Expression of polysialylated neural cell adhesion molecules on adult stem cells after neuronal differentiation of inner ear spiral ganglion neurons

Energy Technology Data Exchange (ETDEWEB)

Park, Kyoung Ho [Department of Otolaryngology Head and Neck Surgery, College of Medicine, Catholic University, Seoul (Korea, Republic of); Yeo, Sang Won, E-mail: swyeo@catholic.ac.kr [Department of Otolaryngology Head and Neck Surgery, College of Medicine, Catholic University, Seoul (Korea, Republic of); Troy, Frederic A., E-mail: fatroy@ucdavis.edu [Department of Biochemistry and Molecular Medicine, University of California, School of Medicine, Davis, CA 95616 (United States); Xiamen University, School of Medicine, Xiamen City (China)

2014-10-17

Highlights: • PolySia expressed on neurons primarily during early stages of neuronal development. • PolySia–NCAM is expressed on neural stem cells from adult guinea pig spiral ganglion. • PolySia is a biomarker that modulates neuronal differentiation in inner ear stem cells. - Abstract: During brain development, polysialylated (polySia) neural cell adhesion molecules (polySia–NCAMs) modulate cell–cell adhesive interactions involved in synaptogenesis, neural plasticity, myelination, and neural stem cell (NSC) proliferation and differentiation. Our findings show that polySia–NCAM is expressed on NSC isolated from adult guinea pig spiral ganglion (GPSG), and in neurons and Schwann cells after differentiation of the NSC with epidermal, glia, fibroblast growth factors (GFs) and neurotrophins. These differentiated cells were immunoreactive with mAb’s to polySia, NCAM, β-III tubulin, nestin, S-100 and stained with BrdU. NSC could regenerate and be differentiated into neurons and Schwann cells. We conclude: (1) polySia is expressed on NSC isolated from adult GPSG and on neurons and Schwann cells differentiated from these NSC; (2) polySia is expressed on neurons primarily during the early stage of neuronal development and is expressed on Schwann cells at points of cell–cell contact; (3) polySia is a functional biomarker that modulates neuronal differentiation in inner ear stem cells. These new findings suggest that replacement of defective cells in the inner ear of hearing impaired patients using adult spiral ganglion neurons may offer potential hope to improve the quality of life for patients with auditory dysfunction and impaired hearing disorders.

Automatic Number Plate Recognition System for IPhone Devices

Directory of Open Access Journals (Sweden)

Călin Enăchescu

2013-06-01

Full Text Available This paper presents a system for automatic number plate recognition, implemented for devices running the iOS operating system. The methods used for number plate recognition are based on existing methods, but optimized for devices with low hardware resources. To solve the task of automatic number plate recognition we have divided it into the following subtasks: image acquisition, localization of the number plate position on the image and character detection. The first subtask is performed by the camera of an iPhone, the second one is done using image pre-processing methods and template matching. For the character recognition we are using a feed-forward artificial neural network. Each of these methods is presented along with its results.

δ-Protocadherins: Organizers of neural circuit assembly.

Science.gov (United States)

Light, Sarah E W; Jontes, James D

2017-09-01

The δ-protocadherins comprise a small family of homophilic cell adhesion molecules within the larger cadherin superfamily. They are essential for neural development as mutations in these molecules give rise to human neurodevelopmental disorders, such as schizophrenia and epilepsy, and result in behavioral defects in animal models. Despite their importance to neural development, a detailed understanding of their mechanisms and the ways in which their loss leads to changes in neural function is lacking. However, recent results have begun to reveal roles for the δ-protocadherins in both regulation of neurogenesis and lineage-dependent circuit assembly, as well as in contact-dependent motility and selective axon fasciculation. These evolutionarily conserved mechanisms could have a profound impact on the robust assembly of the vertebrate nervous system. Future work should be focused on unraveling the molecular mechanisms of the δ-protocadherins and understanding how this family functions broadly to regulate neural development. Copyright © 2017 Elsevier Ltd. All rights reserved.

Oxytocin Promotes Facial Emotion Recognition and Amygdala Reactivity in Adults with Asperger Syndrome

Science.gov (United States)

Domes, Gregor; Kumbier, Ekkehardt; Heinrichs, Markus; Herpertz, Sabine C

2014-01-01

The neuropeptide oxytocin has recently been shown to enhance eye gaze and emotion recognition in healthy men. Here, we report a randomized double-blind, placebo-controlled trial that examined the neural and behavioral effects of a single dose of intranasal oxytocin on emotion recognition in individuals with Asperger syndrome (AS), a clinical condition characterized by impaired eye gaze and facial emotion recognition. Using functional magnetic resonance imaging, we examined whether oxytocin would enhance emotion recognition from facial sections of the eye vs the mouth region and modulate regional activity in brain areas associated with face perception in both adults with AS, and a neurotypical control group. Intranasal administration of the neuropeptide oxytocin improved performance in a facial emotion recognition task in individuals with AS. This was linked to increased left amygdala reactivity in response to facial stimuli and increased activity in the neural network involved in social cognition. Our data suggest that the amygdala, together with functionally associated cortical areas mediate the positive effect of oxytocin on social cognitive functioning in AS. PMID:24067301

Erythropoietin reduces neural and cognitive processing of fear in human models of antidepressant drug action

DEFF Research Database (Denmark)

Miskowiak, Kamilla; O'Sullivan, Ursula; Harmer, Catherine J

2007-01-01

with reduced attention to fear. Erythropoietin additionally reduced recognition of fearful facial expressions without affecting recognition of other emotional expressions. These actions occurred in the absence of changes in hematological parameters. CONCLUSIONS: The present study demonstrates that Epo directly......) versus saline on the neural processing of happy and fearful faces in 23 healthy volunteers. Facial expression recognition was assessed outside the scanner. RESULTS: One week after administration, Epo reduced neural response to fearful versus neutral faces in the occipito-parietal cortex consistent...... study aimed to explore the effects of Epo on neural and behavioral measures of emotional processing relevant for depression and the effects of conventional antidepressant medication. METHODS: In the present study, we used functional magnetic resonance imaging to explore the effects of Epo (40,000 IU...

Neural network application to diesel generator diagnostics

International Nuclear Information System (INIS)

Logan, K.P.

1990-01-01

Diagnostic problems typically begin with the observation of some system behavior which is recognized as a deviation from the expected. The fundamental underlying process is one involving pattern matching cf observed symptoms to a set of compiled symptoms belonging to a fault-symptom mapping. Pattern recognition is often relied upon for initial fault detection and diagnosis. Parallel distributed processing (PDP) models employing neural network paradigms are known to be good pattern recognition devices. This paper describes the application of neural network processing techniques to the malfunction diagnosis of subsystems within a typical diesel generator configuration. Neural network models employing backpropagation learning were developed to correctly recognize fault conditions from the input diagnostic symptom patterns pertaining to various engine subsystems. The resulting network models proved to be excellent pattern recognizers for malfunction examples within the training set. The motivation for employing network models in lieu of a rule-based expert system, however, is related to the network's potential for generalizing malfunctions outside of the training set, as in the case of noisy or partial symptom patterns

Neural Networks for protein Structure Prediction

DEFF Research Database (Denmark)

Bohr, Henrik

1998-01-01

This is a review about neural network applications in bioinformatics. Especially the applications to protein structure prediction, e.g. prediction of secondary structures, prediction of surface structure, fold class recognition and prediction of the 3-dimensional structure of protein backbones...

Applying Gradient Descent in Convolutional Neural Networks

Science.gov (United States)

Cui, Nan

2018-04-01

With the development of the integrated circuit and computer science, people become caring more about solving practical issues via information technologies. Along with that, a new subject called Artificial Intelligent (AI) comes up. One popular research interest of AI is about recognition algorithm. In this paper, one of the most common algorithms, Convolutional Neural Networks (CNNs) will be introduced, for image recognition. Understanding its theory and structure is of great significance for every scholar who is interested in this field. Convolution Neural Network is an artificial neural network which combines the mathematical method of convolution and neural network. The hieratical structure of CNN provides it reliable computer speed and reasonable error rate. The most significant characteristics of CNNs are feature extraction, weight sharing and dimension reduction. Meanwhile, combining with the Back Propagation (BP) mechanism and the Gradient Descent (GD) method, CNNs has the ability to self-study and in-depth learning. Basically, BP provides an opportunity for backwardfeedback for enhancing reliability and GD is used for self-training process. This paper mainly discusses the CNN and the related BP and GD algorithms, including the basic structure and function of CNN, details of each layer, the principles and features of BP and GD, and some examples in practice with a summary in the end.

Sign Language Recognition using Neural Networks

Directory of Open Access Journals (Sweden)

Sabaheta Djogic

2014-11-01

Full Text Available – Sign language plays a great role as communication media for people with hearing difficulties.In developed countries, systems are made for overcoming a problem in communication with deaf people. This encouraged us to develop a system for the Bosnian sign language since there is a need for such system. The work is done with the use of digital image processing methods providing a system that teaches a multilayer neural network using a back propagation algorithm. Images are processed by feature extraction methods, and by masking method the data set has been created. Training is done using cross validation method for better performance thus; an accuracy of 84% is achieved.

Neural Correlates of Music Recognition in Down Syndrome

Science.gov (United States)

Virji-Babul, N.; Moiseev, A.; Sun, W.; Feng, T.; Moiseeva, N.; Watt, K. J.; Huotilainen, M.

2013-01-01

The brain mechanisms that subserve music recognition remain unclear despite increasing interest in this process. Here we report the results of a magnetoencephalography experiment to determine the temporal dynamics and spatial distribution of brain regions activated during listening to a familiar and unfamiliar instrumental melody in control adults…

An Approach for Pattern Recognition of EEG Applied in Prosthetic Hand Drive

Directory of Open Access Journals (Sweden)

Xiao-Dong Zhang

2011-12-01

Full Text Available For controlling the prosthetic hand by only electroencephalogram (EEG, it has become the hot spot in robotics research to set up a direct communication and control channel between human brain and prosthetic hand. In this paper, the EEG signal is analyzed based on multi-complicated hand activities. And then, two methods of EEG pattern recognition are investigated, a neural prosthesis hand system driven by BCI is set up, which can complete four kinds of actions (arm’s free state, arm movement, hand crawl, hand open. Through several times of off-line and on-line experiments, the result shows that the neural prosthesis hand system driven by BCI is reasonable and feasible, the C-support vector classifiers-based method is better than BP neural network on the EEG pattern recognition for multi-complicated hand activities.

Behavioural and neural evidence for the impact of fluency context on conscious memory.

Science.gov (United States)

Gomes, Carlos Alexandre; Mecklinger, Axel; Zimmer, Hubert

2017-07-01

It has been recently suggested that fluency may impact recognition memory performance when the fluency context varies from trial-to-trial. Surprisingly, such an effect has proved difficult to detect in the masked priming paradigm, one of the most popular means to increase fluency-based memory judgements. We conducted a functional magnetic resonance imaging (fMRI) experiment in which participants encoded words at study and, at test, performed a recognition memory task within a masked priming procedure. In order to optimise the chances of finding priming effects on recognition memory performance, we used low-frequency words, which have been shown to increase hits relative to false alarms and enhance masked priming effects. Fluency context was manipulated by either mixing primed and unprimed trials [Random context (RC) experiment] or blocking primed and unprimed trials [Blocked context (BC) experiment]. Behaviourally, priming affected high-confidence memory performance only in the RC experiment. This behavioural effect correlated positively with neural priming in several recognition memory regions. Moreover, we observed a functional coupling between the left middle temporal gyrus and the left parietal and posterior cingulate cortices that was greater for primed relative to unprimed words. In contrast, in the BC experiment, despite similar activity in recognition-memory-related regions, we did not find any significant correlations between neural and behavioural priming. Finally, we observed striking differences in the neural correlates of masked priming between the RC and BC experiments not only in location but also in direction of the neural response. Possible implications of these findings are discussed. Copyright © 2017 Elsevier Ltd. All rights reserved.

Dynamic Control of Synaptic Adhesion and Organizing Molecules in Synaptic Plasticity

Energy Technology Data Exchange (ETDEWEB)

Rudenko, Gabby (Texas-MED)

2017-01-01

Synapses play a critical role in establishing and maintaining neural circuits, permitting targeted information transfer throughout the brain. A large portfolio of synaptic adhesion/organizing molecules (SAMs) exists in the mammalian brain involved in synapse development and maintenance. SAMs bind protein partners, formingtrans-complexes spanning the synaptic cleft orcis-complexes attached to the same synaptic membrane. SAMs play key roles in cell adhesion and in organizing protein interaction networks; they can also provide mechanisms of recognition, generate scaffolds onto which partners can dock, and likely take part in signaling processes as well. SAMs are regulated through a portfolio of different mechanisms that affect their protein levels, precise localization, stability, and the availability of their partners at synapses. Interaction of SAMs with their partners can further be strengthened or weakened through alternative splicing, competing protein partners, ectodomain shedding, or astrocytically secreted factors. Given that numerous SAMs appear altered by synaptic activity, in vivo, these molecules may be used to dynamically scale up or scale down synaptic communication. Many SAMs, including neurexins, neuroligins, cadherins, and contactins, are now implicated in neuropsychiatric and neurodevelopmental diseases, such as autism spectrum disorder, schizophrenia, and bipolar disorder and studying their molecular mechanisms holds promise for developing novel therapeutics.

Event-related theta synchronization predicts deficit in facial affect recognition in schizophrenia.

Science.gov (United States)

Csukly, Gábor; Stefanics, Gábor; Komlósi, Sarolta; Czigler, István; Czobor, Pál

2014-02-01

Growing evidence suggests that abnormalities in the synchronized oscillatory activity of neurons in schizophrenia may lead to impaired neural activation and temporal coding and thus lead to neurocognitive dysfunctions, such as deficits in facial affect recognition. To gain an insight into the neurobiological processes linked to facial affect recognition, we investigated both induced and evoked oscillatory activity by calculating the Event Related Spectral Perturbation (ERSP) and the Inter Trial Coherence (ITC) during facial affect recognition. Fearful and neutral faces as well as nonface patches were presented to 24 patients with schizophrenia and 24 matched healthy controls while EEG was recorded. The participants' task was to recognize facial expressions. Because previous findings with healthy controls showed that facial feature decoding was associated primarily with oscillatory activity in the theta band, we analyzed ERSP and ITC in this frequency band in the time interval of 140-200 ms, which corresponds to the N170 component. Event-related theta activity and phase-locking to facial expressions, but not to nonface patches, predicted emotion recognition performance in both controls and patients. Event-related changes in theta amplitude and phase-locking were found to be significantly weaker in patients compared with healthy controls, which is in line with previous investigations showing decreased neural synchronization in the low frequency bands in patients with schizophrenia. Neural synchrony is thought to underlie distributed information processing. Our results indicate a less effective functioning in the recognition process of facial features, which may contribute to a less effective social cognition in schizophrenia. PsycINFO Database Record (c) 2014 APA, all rights reserved.

Photonics: From target recognition to lesion detection

Science.gov (United States)

Henry, E. Michael

1994-01-01

Since 1989, Martin Marietta has invested in the development of an innovative concept for robust real-time pattern recognition for any two-dimensioanal sensor. This concept has been tested in simulation, and in laboratory and field hardware, for a number of DOD and commercial uses from automatic target recognition to manufacturing inspection. We have now joined Rose Health Care Systems in developing its use for medical diagnostics. The concept is based on determining regions of interest by using optical Fourier bandpassing as a scene segmentation technique, enhancing those regions using wavelet filters, passing the enhanced regions to a neural network for analysis and initial pattern identification, and following this initial identification with confirmation by optical correlation. The optical scene segmentation and pattern confirmation are performed by the same optical module. The neural network is a recursive error minimization network with a small number of connections and nodes that rapidly converges to a global minimum.

Neural Correlates of Word Recognition: A Systematic Comparison of Natural Reading and Rapid Serial Visual Presentation.

Science.gov (United States)

Kornrumpf, Benthe; Niefind, Florian; Sommer, Werner; Dimigen, Olaf

2016-09-01

Neural correlates of word recognition are commonly studied with (rapid) serial visual presentation (RSVP), a condition that eliminates three fundamental properties of natural reading: parafoveal preprocessing, saccade execution, and the fast changes in attentional processing load occurring from fixation to fixation. We combined eye-tracking and EEG to systematically investigate the impact of all three factors on brain-electric activity during reading. Participants read lists of words either actively with eye movements (eliciting fixation-related potentials) or maintained fixation while the text moved passively through foveal vision at a matched pace (RSVP-with-flankers paradigm, eliciting ERPs). The preview of the upcoming word was manipulated by changing the number of parafoveally visible letters. Processing load was varied by presenting words of varying lexical frequency. We found that all three factors have strong interactive effects on the brain's responses to words: Once a word was fixated, occipitotemporal N1 amplitude decreased monotonically with the amount of parafoveal information available during the preceding fixation; hence, the N1 component was markedly attenuated under reading conditions with preview. Importantly, this preview effect was substantially larger during active reading (with saccades) than during passive RSVP with flankers, suggesting that the execution of eye movements facilitates word recognition by increasing parafoveal preprocessing. Lastly, we found that the N1 component elicited by a word also reflects the lexical processing load imposed by the previously inspected word. Together, these results demonstrate that, under more natural conditions, words are recognized in a spatiotemporally distributed and interdependent manner across multiple eye fixations, a process that is mediated by active motor behavior.

The role of phosphatidylinositol 3-kinase in neural cell adhesion molecule-mediated neuronal differentiation and survival

DEFF Research Database (Denmark)

Ditlevsen, Dorte K; Køhler, Lene B; Pedersen, Martin Volmer

2003-01-01

The neural cell adhesion molecule, NCAM, is known to stimulate neurite outgrowth from primary neurones and PC12 cells presumably through signalling pathways involving the fibroblast growth factor receptor (FGFR), protein kinase A (PKA), protein kinase C (PKC), the Ras-mitogen activated protein...... kinase (MAPK) pathway and an increase in intracellular Ca2+ levels. Stimulation of neurones with the synthetic NCAM-ligand, C3, induces neurite outgrowth through signalling pathways similar to the pathways activated through physiological, homophilic NCAM-stimulation. We present here data indicating...... that phosphatidylinositol 3-kinase (PI3K) is required for NCAM-mediated neurite outgrowth from PC12-E2 cells and from cerebellar and dopaminergic neurones in primary culture, and that the thr/ser kinase Akt/protein kinase B (PKB) is phosphorylated downstream of PI3K after stimulation with C3. Moreover, we present data...

Human face recognition ability is specific and highly heritable

OpenAIRE

Wilmer, Jeremy B.; Germine, Laura; Chabris, Christopher F.; Chatterjee, Garga; Williams, Mark; Loken, Eric; Nakayama, Ken; Duchaine, Bradley

2010-01-01

Compared with notable successes in the genetics of basic sensory transduction, progress on the genetics of higher level perception and cognition has been limited. We propose that investigating specific cognitive abilities with well-defined neural substrates, such as face recognition, may yield additional insights. In a twin study of face recognition, we found that the correlation of scores between monozygotic twins (0.70) was more than double the dizygotic twin correlation (0.29), evidence fo...

Stability and Adaptation of Neural Networks

Science.gov (United States)

1990-11-02

RICE CODE 17. SECURITY CLASSIFICATION 18. SECURI ’(CLASSIFICATION 19. SECURITY CLASSIFICATION 20. LIMITATION OF OF REPORT OF REP( RT OF REPORT...Recognition," Proc. European Conference on neural Netowrks , Prague, Czechoslovakia, September 1990. 3.0 NEXT-YEAR RESEARCH OBJECTIVES In the third

Two processes support visual recognition memory in rhesus monkeys.

Science.gov (United States)

Guderian, Sebastian; Brigham, Danielle; Mishkin, Mortimer

2011-11-29

A large body of evidence in humans suggests that recognition memory can be supported by both recollection and familiarity. Recollection-based recognition is characterized by the retrieval of contextual information about the episode in which an item was previously encountered, whereas familiarity-based recognition is characterized instead by knowledge only that the item had been encountered previously in the absence of any context. To date, it is unknown whether monkeys rely on similar mnemonic processes to perform recognition memory tasks. Here, we present evidence from the analysis of receiver operating characteristics, suggesting that visual recognition memory in rhesus monkeys also can be supported by two separate processes and that these processes have features considered to be characteristic of recollection and familiarity. Thus, the present study provides converging evidence across species for a dual process model of recognition memory and opens up the possibility of studying the neural mechanisms of recognition memory in nonhuman primates on tasks that are highly similar to the ones used in humans.

Human face recognition ability is specific and highly heritable.

Science.gov (United States)

Wilmer, Jeremy B; Germine, Laura; Chabris, Christopher F; Chatterjee, Garga; Williams, Mark; Loken, Eric; Nakayama, Ken; Duchaine, Bradley

2010-03-16

Compared with notable successes in the genetics of basic sensory transduction, progress on the genetics of higher level perception and cognition has been limited. We propose that investigating specific cognitive abilities with well-defined neural substrates, such as face recognition, may yield additional insights. In a twin study of face recognition, we found that the correlation of scores between monozygotic twins (0.70) was more than double the dizygotic twin correlation (0.29), evidence for a high genetic contribution to face recognition ability. Low correlations between face recognition scores and visual and verbal recognition scores indicate that both face recognition ability itself and its genetic basis are largely attributable to face-specific mechanisms. The present results therefore identify an unusual phenomenon: a highly specific cognitive ability that is highly heritable. Our results establish a clear genetic basis for face recognition, opening this intensively studied and socially advantageous cognitive trait to genetic investigation.

Multi-Lingual Deep Neural Networks for Language Recognition

Science.gov (United States)

2016-08-08

system architecture 2. I-VECTOR SYSTEM Most state-of-the- art language recognition systems are based on the i-vector framework [8] depicted in Figure 1...may be possible to achieve more gains on the Arabic and Chinese cluster by adding ad- ditional ASR corpora such as Callhome Egyptian Arabic or HKUST

Braille Character Recognition Using Artificial Neural Network

OpenAIRE

Subur, Joko; Sardjono, Tri Arief; Mardiyanto, Ronny

2015-01-01

Braille letter is characters designed for the blind, consist of six embossed points, arranged in a standard braille character. Braille letters is touched and read using fingers, therefore the sensitivity of the fingers is important. Those characters need to be memorized, so it is very difficult to be learned. The aim of this research is to create a braille characters recognition system and translate it to alpha-numeric text. Webcam camera is used to capture braille image from braille characte...

Recency, repetition, and the multidimensional basis of recognition memory.

Science.gov (United States)

Buchsbaum, Bradley R; Lemire-Rodger, Sabrina; Bondad, Ashley; Chepesiuk, Alexander

2015-02-25

Recency and repetition are two factors that have large effects on human memory performance. One way of viewing the beneficial impact of these variables on recognition memory is to assume that both factors modulate a unidimensional memory trace strength. Although previous functional neuroimaging studies have indicated that recency and repetition may modulate similar brain structures, particularly in the region of the inferior parietal cortex, there is extensive behavioral evidence that human subjects can make independent and accurate recognition memory judgments about both an item's recency and its frequency. In the present study, we used fMRI to examine patterns of brain activity during recognition memory for auditory-verbal stimuli that were parametrically and orthogonally manipulated in terms of recency and number of repetitions. We found in a continuous recognition paradigm that the lateral inferior parietal cortex, a region that has previously been associated with recollective forms of memory, is highly sensitive to recency but not repetition. In a multivariate analysis of whole-brain activation patterns, we found orthogonal components that dissociated recency and repetition variables, indicating largely independent neural bases underlying these two factors. The results demonstrate that although both recency and repetition dramatically improve recognition memory performance, the neural bases for this improvement are dissociable, and thus are difficult to explain in terms of access to a unitary memory trace. Copyright © 2015 the authors 0270-6474/15/353544-11$15.00/0.

Cueing vocabulary during sleep increases theta activity during later recognition testing.

Science.gov (United States)

Schreiner, Thomas; Göldi, Maurice; Rasch, Björn

2015-11-01

Neural oscillations in the theta band have repeatedly been implicated in successful memory encoding and retrieval. Several recent studies have shown that memory retrieval can be facilitated by reactivating memories during their consolidation during sleep. However, it is still unknown whether reactivation during sleep also enhances subsequent retrieval-related neural oscillations. We have recently demonstrated that foreign vocabulary cues presented during sleep improve later recall of the associated translations. Here, we examined the effect of cueing foreign vocabulary during sleep on oscillatory activity during subsequent recognition testing after sleep. We show that those words that were replayed during sleep after learning (cued words) elicited stronger centroparietal theta activity during recognition as compared to noncued words. The reactivation-induced increase in theta oscillations during later recognition testing might reflect a strengthening of individual memory traces and the integration of the newly learned words into the mental lexicon by cueing during sleep. © 2015 Society for Psychophysiological Research.

Automatic recognition of holistic functional brain networks using iteratively optimized convolutional neural networks (IO-CNN) with weak label initialization.

Science.gov (United States)

Zhao, Yu; Ge, Fangfei; Liu, Tianming

2018-07-01

fMRI data decomposition techniques have advanced significantly from shallow models such as Independent Component Analysis (ICA) and Sparse Coding and Dictionary Learning (SCDL) to deep learning models such Deep Belief Networks (DBN) and Convolutional Autoencoder (DCAE). However, interpretations of those decomposed networks are still open questions due to the lack of functional brain atlases, no correspondence across decomposed or reconstructed networks across different subjects, and significant individual variabilities. Recent studies showed that deep learning, especially deep convolutional neural networks (CNN), has extraordinary ability of accommodating spatial object patterns, e.g., our recent works using 3D CNN for fMRI-derived network classifications achieved high accuracy with a remarkable tolerance for mistakenly labelled training brain networks. However, the training data preparation is one of the biggest obstacles in these supervised deep learning models for functional brain network map recognitions, since manual labelling requires tedious and time-consuming labours which will sometimes even introduce label mistakes. Especially for mapping functional networks in large scale datasets such as hundreds of thousands of brain networks used in this paper, the manual labelling method will become almost infeasible. In response, in this work, we tackled both the network recognition and training data labelling tasks by proposing a new iteratively optimized deep learning CNN (IO-CNN) framework with an automatic weak label initialization, which enables the functional brain networks recognition task to a fully automatic large-scale classification procedure. Our extensive experiments based on ABIDE-II 1099 brains' fMRI data showed the great promise of our IO-CNN framework. Copyright © 2018 Elsevier B.V. All rights reserved.

Predicting tool life in turning operations using neural networks and image processing

Science.gov (United States)

Mikołajczyk, T.; Nowicki, K.; Bustillo, A.; Yu Pimenov, D.

2018-05-01

A two-step method is presented for the automatic prediction of tool life in turning operations. First, experimental data are collected for three cutting edges under the same constant processing conditions. In these experiments, the parameter of tool wear, VB, is measured with conventional methods and the same parameter is estimated using Neural Wear, a customized software package that combines flank wear image recognition and Artificial Neural Networks (ANNs). Second, an ANN model of tool life is trained with the data collected from the first two cutting edges and the subsequent model is evaluated on two different subsets for the third cutting edge: the first subset is obtained from the direct measurement of tool wear and the second is obtained from the Neural Wear software that estimates tool wear using edge images. Although the complete-automated solution, Neural Wear software for tool wear recognition plus the ANN model of tool life prediction, presented a slightly higher error than the direct measurements, it was within the same range and can meet all industrial requirements. These results confirm that the combination of image recognition software and ANN modelling could potentially be developed into a useful industrial tool for low-cost estimation of tool life in turning operations.

Human fatigue expression recognition through image-based dynamic multi-information and bimodal deep learning

Science.gov (United States)

Zhao, Lei; Wang, Zengcai; Wang, Xiaojin; Qi, Yazhou; Liu, Qing; Zhang, Guoxin

2016-09-01

Human fatigue is an important cause of traffic accidents. To improve the safety of transportation, we propose, in this paper, a framework for fatigue expression recognition using image-based facial dynamic multi-information and a bimodal deep neural network. First, the landmark of face region and the texture of eye region, which complement each other in fatigue expression recognition, are extracted from facial image sequences captured by a single camera. Then, two stacked autoencoder neural networks are trained for landmark and texture, respectively. Finally, the two trained neural networks are combined by learning a joint layer on top of them to construct a bimodal deep neural network. The model can be used to extract a unified representation that fuses landmark and texture modalities together and classify fatigue expressions accurately. The proposed system is tested on a human fatigue dataset obtained from an actual driving environment. The experimental results demonstrate that the proposed method performs stably and robustly, and that the average accuracy achieves 96.2%.

Perceptual differentiation and category effects in normal object recognition

DEFF Research Database (Denmark)

Gerlach, Christian; Law, I; Gade, A

1999-01-01

The purpose of the present PET study was (i) to investigate the neural correlates of object recognition, i.e. the matching of visual forms to memory, and (ii) to test the hypothesis that this process is more difficult for natural objects than for artefacts. This was done by using object decision...... tasks where subjects decided whether pictures represented real objects or non-objects. The object decision tasks differed in their difficulty (the degree of perceptual differentiation needed to perform them) and in the category of the real objects used (natural objects versus artefacts). A clear effect...... be the neural correlate of matching visual forms to memory, and the amount of activation in these regions may correspond to the degree of perceptual differentiation required for recognition to occur. With respect to behaviour, it took significantly longer to make object decisions on natural objects than...

Molecular recognition of chromophore molecules to amine terminated surfaces

International Nuclear Information System (INIS)

Flores-Perez, Rosangelly; Ivanisevic, Albena

2007-01-01