WorldWideScience

Sample records for network pattern recognition

  1. MEMBRAIN NEURAL NETWORK FOR VISUAL PATTERN RECOGNITION

    Directory of Open Access Journals (Sweden)

    Artur Popko

    2013-06-01

    Full Text Available Recognition of visual patterns is one of significant applications of Artificial Neural Networks, which partially emulate human thinking in the domain of artificial intelligence. In the paper, a simplified neural approach to recognition of visual patterns is portrayed and discussed. This paper is dedicated for investigators in visual patterns recognition, Artificial Neural Networking and related disciplines. The document describes also MemBrain application environment as a powerful and easy to use neural networks’ editor and simulator supporting ANN.

  2. 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...

  3. 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

  4. Patterns recognition of electric brain activity using artificial neural networks

    Science.gov (United States)

    Musatov, V. Yu.; Pchelintseva, S. V.; Runnova, A. E.; Hramov, A. E.

    2017-04-01

    An approach for the recognition of various cognitive processes in the brain activity in the perception of ambiguous images. On the basis of developed theoretical background and the experimental data, we propose a new classification of oscillating patterns in the human EEG by using an artificial neural network approach. After learning of the artificial neural network reliably identified cube recognition processes, for example, left-handed or right-oriented Necker cube with different intensity of their edges, construct an artificial neural network based on Perceptron architecture and demonstrate its effectiveness in the pattern recognition of the EEG in the experimental.

  5. Pattern recognition of state variables by neural networks

    International Nuclear Information System (INIS)

    Faria, Eduardo Fernandes; Pereira, Claubia

    1996-01-01

    An artificial intelligence system based on artificial neural networks can be used to classify predefined events and emergency procedures. These systems are being used in different areas. In the nuclear reactors safety, the goal is the classification of events whose data can be processed and recognized by neural networks. In this works we present a preliminary simple system, using neural networks in the recognition of patterns the recognition of variables which define a situation. (author)

  6. 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.

  7. 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.

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

    Science.gov (United States)

    Chao, Tien-Hsin

    1991-01-01

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

  9. Pattern Recognition for Reliability Assessment of Water Distribution Networks

    NARCIS (Netherlands)

    Trifunovi?, N.

    2012-01-01

    The study presented in this manuscript investigates the patterns that describe reliability of water distribution networks focusing to the node connectivity, energy balance, and economics of construction, operation and maintenance. A number of measures to evaluate the network resilience has been

  10. Pattern Recognition

    Directory of Open Access Journals (Sweden)

    Aleš Procházka

    2018-05-01

    Full Text Available Multimodal signal analysis based on sophisticated sensors, efficient communicationsystems and fast parallel processing methods has a rapidly increasing range of multidisciplinaryapplications. The present paper is devoted to pattern recognition, machine learning, and the analysisof sleep stages in the detection of sleep disorders using polysomnography (PSG data, includingelectroencephalography (EEG, breathing (Flow, and electro-oculogram (EOG signals. The proposedmethod is based on the classification of selected features by a neural network system with sigmoidaland softmax transfer functions using Bayesian methods for the evaluation of the probabilities of theseparate classes. The application is devoted to the analysis of the sleep stages of 184 individualswith different diagnoses, using EEG and further PSG signals. Data analysis points to an averageincrease of the length of the Wake stage by 2.7% per 10 years and a decrease of the length of theRapid Eye Movement (REM stages by 0.8% per 10 years. The mean classification accuracy for givensets of records and single EEG and multimodal features is 88.7% ( standard deviation, STD: 2.1 and89.6% (STD:1.9, respectively. The proposed methods enable the use of adaptive learning processesfor the detection and classification of health disorders based on prior specialist experience andman–machine interaction.

  11. Exploring Spatio-temporal Dynamics of Cellular Automata for Pattern Recognition in Networks

    Science.gov (United States)

    Miranda, Gisele Helena Barboni; Machicao, Jeaneth; Bruno, Odemir Martinez

    2016-11-01

    Network science is an interdisciplinary field which provides an integrative approach for the study of complex systems. In recent years, network modeling has been used for the study of emergent phenomena in many real-world applications. Pattern recognition in networks has been drawing attention to the importance of network characterization, which may lead to understanding the topological properties that are related to the network model. In this paper, the Life-Like Network Automata (LLNA) method is introduced, which was designed for pattern recognition in networks. LLNA uses the network topology as a tessellation of Cellular Automata (CA), whose dynamics produces a spatio-temporal pattern used to extract the feature vector for network characterization. The method was evaluated using synthetic and real-world networks. In the latter, three pattern recognition applications were used: (i) identifying organisms from distinct domains of life through their metabolic networks, (ii) identifying online social networks and (iii) classifying stomata distribution patterns varying according to different lighting conditions. LLNA was compared to structural measurements and surpasses them in real-world applications, achieving improvement in the classification rate as high as 23%, 4% and 7% respectively. Therefore, the proposed method is a good choice for pattern recognition applications using networks and demonstrates potential for general applicability.

  12. Cellular-automata-based learning network for pattern recognition

    Science.gov (United States)

    Tzionas, Panagiotis G.; Tsalides, Phillippos G.; Thanailakis, Adonios

    1991-11-01

    Most classification techniques either adopt an approach based directly on the statistical characteristics of the pattern classes involved, or they transform the patterns in a feature space and try to separate the point clusters in this space. An alternative approach based on memory networks has been presented, its novelty being that it can be implemented in parallel and it utilizes direct features of the patterns rather than statistical characteristics. This study presents a new approach for pattern classification using pseudo 2-D binary cellular automata (CA). This approach resembles the memory network classifier in the sense that it is based on an adaptive knowledge based formed during a training phase, and also in the fact that both methods utilize pattern features that are directly available. The main advantage of this approach is that the sensitivity of the pattern classifier can be controlled. The proposed pattern classifier has been designed using 1.5 micrometers design rules for an N-well CMOS process. Layout has been achieved using SOLO 1400. Binary pseudo 2-D hybrid additive CA (HACA) is described in the second section of this paper. The third section describes the operation of the pattern classifier and the fourth section presents some possible applications. The VLSI implementation of the pattern classifier is presented in the fifth section and, finally, the sixth section draws conclusions from the results obtained.

  13. 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)

  14. 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.

  15. 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...

  16. 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)

  17. 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.

  18. 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.

  19. 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’

  20. 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…

  1. 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.

  2. Network Security via Biometric Recognition of Patterns of Gene Expression

    Science.gov (United States)

    Shaw, Harry C.

    2016-01-01

    Molecular biology provides the ability to implement forms of information and network security completely outside the bounds of legacy security protocols and algorithms. This paper addresses an approach which instantiates the power of gene expression for security. Molecular biology provides a rich source of gene expression and regulation mechanisms, which can be adopted to use in the information and electronic communication domains. Conventional security protocols are becoming increasingly vulnerable due to more intensive, highly capable attacks on the underlying mathematics of cryptography. Security protocols are being undermined by social engineering and substandard implementations by IT organizations. Molecular biology can provide countermeasures to these weak points with the current security approaches. Future advances in instruments for analyzing assays will also enable this protocol to advance from one of cryptographic algorithms to an integrated system of cryptographic algorithms and real-time expression and assay of gene expression products.

  3. Network Security via Biometric Recognition of Patterns of Gene Expression

    Science.gov (United States)

    Shaw, Harry C.

    2016-01-01

    Molecular biology provides the ability to implement forms of information and network security completely outside the bounds of legacy security protocols and algorithms. This paper addresses an approach which instantiates the power of gene expression for security. Molecular biology provides a rich source of gene expression and regulation mechanisms, which can be adopted to use in the information and electronic communication domains. Conventional security protocols are becoming increasingly vulnerable due to more intensive, highly capable attacks on the underlying mathematics of cryptography. Security protocols are being undermined by social engineering and substandard implementations by IT (Information Technology) organizations. Molecular biology can provide countermeasures to these weak points with the current security approaches. Future advances in instruments for analyzing assays will also enable this protocol to advance from one of cryptographic algorithms to an integrated system of cryptographic algorithms and real-time assays of gene expression products.

  4. 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

  5. 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.

  6. 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.

  7. Semantic Network Adaptation Based on QoS Pattern Recognition for Multimedia Streams

    Science.gov (United States)

    Exposito, Ernesto; Gineste, Mathieu; Lamolle, Myriam; Gomez, Jorge

    This article proposes an ontology based pattern recognition methodology to compute and represent common QoS properties of the Application Data Units (ADU) of multimedia streams. The use of this ontology by mechanisms located at different layers of the communication architecture will allow implementing fine per-packet self-optimization of communication services regarding the actual application requirements. A case study showing how this methodology is used by error control mechanisms in the context of wireless networks is presented in order to demonstrate the feasibility and advantages of this approach.

  8. 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

  9. 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)

  10. 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

  11. Bifurcation analysis of oscillating network model of pattern recognition in the rabbit olfactory bulb

    Science.gov (United States)

    Baird, Bill

    1986-08-01

    A neural network model describing pattern recognition in the rabbit olfactory bulb is analysed to explain the changes in neural activity observed experimentally during classical Pavlovian conditioning. EEG activity recorded from an 8×8 arry of 64 electrodes directly on the surface on the bulb shows distinct spatial patterns of oscillation that correspond to the animal's recognition of different conditioned odors and change with conditioning to new odors. The model may be considered a variant of Hopfield's model of continuous analog neural dynamics. Excitatory and inhibitory cell types in the bulb and the anatomical architecture of their connection requires a nonsymmetric coupling matrix. As the mean input level rises during each breath of the animal, the system bifurcates from homogenous equilibrium to a spatially patterned oscillation. The theory of multiple Hopf bifurcations is employed to find coupled equations for the amplitudes of these unstable oscillatory modes independent of frequency. This allows a view of stored periodic attractors as fixed points of a gradient vector field and thereby recovers the more familiar dynamical systems picture of associative memory.

  12. 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

  13. 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

  14. Pattern recognition & machine learning

    CERN Document Server

    Anzai, Y

    1992-01-01

    This is the first text to provide a unified and self-contained introduction to visual pattern recognition and machine learning. It is useful as a general introduction to artifical intelligence and knowledge engineering, and no previous knowledge of pattern recognition or machine learning is necessary. Basic for various pattern recognition and machine learning methods. Translated from Japanese, the book also features chapter exercises, keywords, and summaries.

  15. 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...

  16. 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.

  17. An intelligent signal processing and pattern recognition technique for defect identification using an active sensor network

    Science.gov (United States)

    Su, Zhongqing; Ye, Lin

    2004-08-01

    The practical utilization of elastic waves, e.g. Rayleigh-Lamb waves, in high-performance structural health monitoring techniques is somewhat impeded due to the complicated wave dispersion phenomena, the existence of multiple wave modes, the high susceptibility to diverse interferences, the bulky sampled data and the difficulty in signal interpretation. An intelligent signal processing and pattern recognition (ISPPR) approach using the wavelet transform and artificial neural network algorithms was developed; this was actualized in a signal processing package (SPP). The ISPPR technique comprehensively functions as signal filtration, data compression, characteristic extraction, information mapping and pattern recognition, capable of extracting essential yet concise features from acquired raw wave signals and further assisting in structural health evaluation. For validation, the SPP was applied to the prediction of crack growth in an alloy structural beam and construction of a damage parameter database for defect identification in CF/EP composite structures. It was clearly apparent that the elastic wave propagation-based damage assessment could be dramatically streamlined by introduction of the ISPPR technique.

  18. 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.

  19. 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.

  20. Statistical Pattern Recognition

    CERN Document Server

    Webb, Andrew R

    2011-01-01

    Statistical pattern recognition relates to the use of statistical techniques for analysing data measurements in order to extract information and make justified decisions.  It is a very active area of study and research, which has seen many advances in recent years. Applications such as data mining, web searching, multimedia data retrieval, face recognition, and cursive handwriting recognition, all require robust and efficient pattern recognition techniques. This third edition provides an introduction to statistical pattern theory and techniques, with material drawn from a wide range of fields,

  1. Probabilistic Neural Networks for Chemical Sensor Array Pattern Recognition: Comparison Studies, Improvements and Automated Outlier Rejection

    National Research Council Canada - National Science Library

    Shaffer, Ronald E

    1998-01-01

    For application to chemical sensor arrays, the ideal pattern recognition is accurate, fast, simple to train, robust to outliers, has low memory requirements, and has the ability to produce a measure...

  2. 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)

  3. Method of Parallel-Hierarchical Network Self-Training and its Application for Pattern Classification and Recognition

    Directory of Open Access Journals (Sweden)

    TIMCHENKO, L.

    2012-11-01

    Full Text Available Propositions necessary for development of parallel-hierarchical (PH network training methods are discussed in this article. Unlike already known structures of the artificial neural network, where non-normalized (absolute similarity criteria are used for comparison, the suggested structure uses a normalized criterion. Based on the analysis of training rules, a conclusion is made that application of two training methods with a teacher is optimal for PH network training: error correction-based training and memory-based training. Mathematical models of training and a combined method of PH network training for recognition of static and dynamic patterns are developed.

  4. 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.

  5. Oscillation-Driven Spike-Timing Dependent Plasticity Allows Multiple Overlapping Pattern Recognition in Inhibitory Interneuron Networks

    DEFF Research Database (Denmark)

    Garrido, Jesús A.; Luque, Niceto R.; Tolu, Silvia

    2016-01-01

    The majority of operations carried out by the brain require learning complex signal patterns for future recognition, retrieval and reuse. Although learning is thought to depend on multiple forms of long-term synaptic plasticity, the way this latter contributes to pattern recognition is still poorly...... and at the inhibitory interneuron-interneuron synapses, the interneurons rapidly learned complex input patterns. Interestingly, induction of plasticity required that the network be entrained into theta-frequency band oscillations, setting the internal phase-reference required to drive STDP. Inhibitory plasticity...... effectively distributed multiple patterns among available interneurons, thus allowing the simultaneous detection of multiple overlapping patterns. The addition of plasticity in intrinsic excitability made the system more robust allowing self-adjustment and rescaling in response to a broad range of input...

  6. Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network.

    Science.gov (United States)

    Zhai, Xiaolong; Jelfs, Beth; Chan, Rosa H M; Tin, Chung

    2017-01-01

    Hand movement classification based on surface electromyography (sEMG) pattern recognition is a promising approach for upper limb neuroprosthetic control. However, maintaining day-to-day performance is challenged by the non-stationary nature of sEMG in real-life operation. In this study, we propose a self-recalibrating classifier that can be automatically updated to maintain a stable performance over time without the need for user retraining. Our classifier is based on convolutional neural network (CNN) using short latency dimension-reduced sEMG spectrograms as inputs. The pretrained classifier is recalibrated routinely using a corrected version of the prediction results from recent testing sessions. Our proposed system was evaluated with the NinaPro database comprising of hand movement data of 40 intact and 11 amputee subjects. Our system was able to achieve ~10.18% (intact, 50 movement types) and ~2.99% (amputee, 10 movement types) increase in classification accuracy averaged over five testing sessions with respect to the unrecalibrated classifier. When compared with a support vector machine (SVM) classifier, our CNN-based system consistently showed higher absolute performance and larger improvement as well as more efficient training. These results suggest that the proposed system can be a useful tool to facilitate long-term adoption of prosthetics for amputees in real-life applications.

  7. Comparison of Pattern Recognition, Artificial Neural Network and Pedotransfer Functions for Estimation of Soil Water Parameters

    Directory of Open Access Journals (Sweden)

    Amir LAKZIAN

    2010-09-01

    Full Text Available This paper presents the comparison of three different approaches to estimate soil water content at defined values of soil water potential based on selected parameters of soil solid phase. Forty different sampling locations in northeast of Iran were selected and undisturbed samples were taken to measure the water content at field capacity (FC, -33 kPa, and permanent wilting point (PWP, -1500 kPa. At each location solid particle of each sample including the percentage of sand, silt and clay were measured. Organic carbon percentage and soil texture were also determined for each soil sample at each location. Three different techniques including pattern recognition approach (k nearest neighbour, k-NN, Artificial Neural Network (ANN and pedotransfer functions (PTF were used to predict the soil water at each sampling location. Mean square deviation (MSD and its components, index of agreement (d, root mean square difference (RMSD and normalized RMSD (RMSDr were used to evaluate the performance of all the three approaches. Our results showed that k-NN and PTF performed better than ANN in prediction of water content at both FC and PWP matric potential. Various statistics criteria for simulation performance also indicated that between kNN and PTF, the former, predicted water content at PWP more accurate than PTF, however both approach showed a similar accuracy to predict water content at FC.

  8. Pattern Recognition and Classification of Fatal Traffic Accidents in Israel A Neural Network Approach

    DEFF Research Database (Denmark)

    Prato, Carlo Giacomo; Gitelman, Victoria; Bekhor, Shlomo

    2011-01-01

    on 1,793 fatal traffic accidents occurred during the period between 2003 and 2006 and applies Kohonen and feed-forward back-propagation neural networks with the objective of extracting from the data typical patterns and relevant factors. Kohonen neural networks reveal five compelling accident patterns....... Feed-forward back-propagation neural networks indicate that sociodemographic characteristics of drivers and victims, accident location, and period of the day are extremely relevant factors. Accident patterns suggest that countermeasures are necessary for identified problems concerning mainly vulnerable...

  9. Artificial immune pattern recognition for damage detection in structural health monitoring sensor networks

    Science.gov (United States)

    Chen, Bo; Zang, Chuanzhi

    2009-03-01

    This paper presents an artificial immune pattern recognition (AIPR) approach for the damage detection and classification in structures. An AIPR-based Structure Damage Classifier (AIPR-SDC) has been developed by mimicking immune recognition and learning mechanisms. The structure damage patterns are represented by feature vectors that are extracted from the structure's dynamic response measurements. The training process is designed based on the clonal selection principle in the immune system. The selective and adaptive features of the clonal selection algorithm allow the classifier to generate recognition feature vectors that are able to match the training data. In addition, the immune learning algorithm can learn and remember various data patterns by generating a set of memory cells that contains representative feature vectors for each class (pattern). The performance of the presented structure damage classifier has been validated using a benchmark structure proposed by the IASC-ASCE (International Association for Structural Control - American Society of Civil Engineers) Structural Health Monitoring Task Group. The validation results show a better classification success rate comparing to some of other classification algorithms.

  10. Mining Emerging Sequential Patterns for Activity Recognition in Body Sensor Networks

    DEFF Research Database (Denmark)

    Gu, Tao; Wang, Liang; Chen, Hanhua

    2010-01-01

    Body Sensor Networks oer many applications in healthcare, well-being and entertainment. One of the emerging applications is recognizing activities of daily living. In this paper, we introduce a novel knowledge pattern named Emerging Sequential Pattern (ESP)|a sequential pattern that discovers...... signicant class dierences|to recognize both simple (i.e., sequential) and complex (i.e., interleaved and concurrent) activities. Based on ESPs, we build our complex activity models directly upon the sequential model to recognize both activity types. We conduct comprehensive empirical studies to evaluate...

  11. Pattern Recognition Control Design

    Science.gov (United States)

    Gambone, Elisabeth A.

    2018-01-01

    Spacecraft control algorithms must know the expected vehicle response to any command to the available control effectors, such as reaction thrusters or torque devices. Spacecraft control system design approaches have traditionally relied on the estimated vehicle mass properties to determine the desired force and moment, as well as knowledge of the effector performance to efficiently control the spacecraft. A pattern recognition approach was used to investigate the relationship between the control effector commands and spacecraft responses. Instead of supplying the approximated vehicle properties and the thruster performance characteristics, a database of information relating the thruster ring commands and the desired vehicle response was used for closed-loop control. A Monte Carlo simulation data set of the spacecraft dynamic response to effector commands was analyzed to establish the influence a command has on the behavior of the spacecraft. A tool developed at NASA Johnson Space Center to analyze flight dynamics Monte Carlo data sets through pattern recognition methods was used to perform this analysis. Once a comprehensive data set relating spacecraft responses with commands was established, it was used in place of traditional control methods and gains set. This pattern recognition approach was compared with traditional control algorithms to determine the potential benefits and uses.

  12. 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.

  13. 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.

  14. Acoustic Pattern Recognition on Android Devices

    DEFF Research Database (Denmark)

    Møller, Maiken Bjerg; Gaarsdal, Jesper; Steen, Kim Arild

    2013-01-01

    an Android application developed for acoustic pattern recognition of bird species. The acoustic data is recorded using a built-in microphone, and pattern recognition is performed on the device, requiring no network connection. The algorithm is implemented in C++ as a native Android module and the Open......CV library is used for signal processing. We conclude that the approach presented here is a viable solution to pattern recognition problems. Since it requires no network connection, it shows promise in fields such as wildlife research....

  15. 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

  16. A spiking neural network model of self-organized pattern recognition in the early mammalian olfactory system

    Science.gov (United States)

    Kaplan, Bernhard A.; Lansner, Anders

    2014-01-01

    Olfactory sensory information passes through several processing stages before an odor percept emerges. The question how the olfactory system learns to create odor representations linking those different levels and how it learns to connect and discriminate between them is largely unresolved. We present a large-scale network model with single and multi-compartmental Hodgkin–Huxley type model neurons representing olfactory receptor neurons (ORNs) in the epithelium, periglomerular cells, mitral/tufted cells and granule cells in the olfactory bulb (OB), and three types of cortical cells in the piriform cortex (PC). Odor patterns are calculated based on affinities between ORNs and odor stimuli derived from physico-chemical descriptors of behaviorally relevant real-world odorants. The properties of ORNs were tuned to show saturated response curves with increasing concentration as seen in experiments. On the level of the OB we explored the possibility of using a fuzzy concentration interval code, which was implemented through dendro-dendritic inhibition leading to winner-take-all like dynamics between mitral/tufted cells belonging to the same glomerulus. The connectivity from mitral/tufted cells to PC neurons was self-organized from a mutual information measure and by using a competitive Hebbian–Bayesian learning algorithm based on the response patterns of mitral/tufted cells to different odors yielding a distributed feed-forward projection to the PC. The PC was implemented as a modular attractor network with a recurrent connectivity that was likewise organized through Hebbian–Bayesian learning. We demonstrate the functionality of the model in a one-sniff-learning and recognition task on a set of 50 odorants. Furthermore, we study its robustness against noise on the receptor level and its ability to perform concentration invariant odor recognition. Moreover, we investigate the pattern completion capabilities of the system and rivalry dynamics for odor mixtures. PMID

  17. 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.

  18. Pattern recognition in spectra

    International Nuclear Information System (INIS)

    Gebran, M; Paletou, F

    2017-01-01

    We present a new automated procedure that simultaneously derives the effective temperature T eff , surface gravity log g , metallicity [ Fe/H ], and equatorial projected rotational velocity v e sin i for stars. The procedure is inspired by the well-known PCA-based inversion of spectropolarimetric full-Stokes solar data, which was used both for Zeeman and Hanle effects. The efficiency and accuracy of this procedure have been proven for FGK, A, and late type dwarf stars of K and M spectral types. Learning databases are generated from the Elodie stellar spectra library using observed spectra for which fundamental parameters were already evaluated or with synthetic data. The synthetic spectra are calculated using ATLAS9 model atmospheres. This technique helped us to detect many peculiar stars such as Am, Ap, HgMn, SiEuCr and binaries. This fast and efficient technique could be used every time a pattern recognition is needed. One important application is the understanding of the physical properties of planetary surfaces by comparing aboard instrument data to synthetic ones. (paper)

  19. 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%.

  20. Study on pattern recognition of Raman spectrum based on fuzzy neural network

    Science.gov (United States)

    Zheng, Xiangxiang; Lv, Xiaoyi; Mo, Jiaqing

    2017-10-01

    Hydatid disease is a serious parasitic disease in many regions worldwide, especially in Xinjiang, China. Raman spectrum of the serum of patients with echinococcosis was selected as the research object in this paper. The Raman spectrum of blood samples from healthy people and patients with echinococcosis are measured, of which the spectrum characteristics are analyzed. The fuzzy neural network not only has the ability of fuzzy logic to deal with uncertain information, but also has the ability to store knowledge of neural network, so it is combined with the Raman spectrum on the disease diagnosis problem based on Raman spectrum. Firstly, principal component analysis (PCA) is used to extract the principal components of the Raman spectrum, reducing the network input and accelerating the prediction speed and accuracy of Network based on remaining the original data. Then, the information of the extracted principal component is used as the input of the neural network, the hidden layer of the network is the generation of rules and the inference process, and the output layer of the network is fuzzy classification output. Finally, a part of samples are randomly selected for the use of training network, then the trained network is used for predicting the rest of the samples, and the predicted results are compared with general BP neural network to illustrate the feasibility and advantages of fuzzy neural network. Success in this endeavor would be helpful for the research work of spectroscopic diagnosis of disease and it can be applied in practice in many other spectral analysis technique fields.

  1. 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.

  2. Applications of chaotic neurodynamics in pattern recognition

    Science.gov (United States)

    Baird, Bill; Freeman, Walter J.; Eeckman, Frank H.; Yao, Yong

    1991-08-01

    Network algorithms and architectures for pattern recognition derived from neural models of the olfactory system are reviewed. These span a range from highly abstract to physiologically detailed, and employ the kind of dynamical complexity observed in olfactory cortex, ranging from oscillation to chaos. A simple architecture and algorithm for analytically guaranteed associative memory storage of analog patterns, continuous sequences, and chaotic attractors in the same network is described. A matrix inversion determines network weights, given prototype patterns to be stored. There are N units of capacity in an N node network with 3N2 weights. It costs one unit per static attractor, two per Fourier component of each sequence, and three to four per chaotic attractor. There are no spurious attractors, and for sequences there is a Liapunov function in a special coordinate system which governs the approach of transient states to stored trajectories. Unsupervised or supervised incremental learning algorithms for pattern classification, such as competitive learning or bootstrap Widrow-Hoff can easily be implemented. The architecture can be ''folded'' into a recurrent network with higher order weights that can be used as a model of cortex that stores oscillatory and chaotic attractors by a Hebb rule. Network performance is demonstrated by application to the problem of real-time handwritten digit recognition. An effective system with on-line learning has been written by Eeckman and Baird for the Macintosh. It utilizes static, oscillatory, and/or chaotic attractors of two kinds--Lorenze attractors, or attractors resulting from chaotically interacting oscillatory modes. The successful application to an industrial pattern recognition problem of a network architecture of considerable physiological and dynamical complexity, developed by Freeman and Yao, is described. The data sets of the problem come in three classes of difficulty, and performance of the biological network is

  3. A Parallel Supercomputer Implementation of a Biological Inspired Neural Network and its use for Pattern Recognition

    International Nuclear Information System (INIS)

    De Ladurantaye, Vincent; Lavoie, Jean; Bergeron, Jocelyn; Parenteau, Maxime; Lu Huizhong; Pichevar, Ramin; Rouat, Jean

    2012-01-01

    A parallel implementation of a large spiking neural network is proposed and evaluated. The neural network implements the binding by synchrony process using the Oscillatory Dynamic Link Matcher (ODLM). Scalability, speed and performance are compared for 2 implementations: Message Passing Interface (MPI) and Compute Unified Device Architecture (CUDA) running on clusters of multicore supercomputers and NVIDIA graphical processing units respectively. A global spiking list that represents at each instant the state of the neural network is described. This list indexes each neuron that fires during the current simulation time so that the influence of their spikes are simultaneously processed on all computing units. Our implementation shows a good scalability for very large networks. A complex and large spiking neural network has been implemented in parallel with success, thus paving the road towards real-life applications based on networks of spiking neurons. MPI offers a better scalability than CUDA, while the CUDA implementation on a GeForce GTX 285 gives the best cost to performance ratio. When running the neural network on the GTX 285, the processing speed is comparable to the MPI implementation on RQCHP's Mammouth parallel with 64 notes (128 cores).

  4. Pattern recognition and string matching

    CERN Document Server

    Cheng, Xiuzhen

    2002-01-01

    The research and development of pattern recognition have proven to be of importance in science, technology, and human activity. Many useful concepts and tools from different disciplines have been employed in pattern recognition. Among them is string matching, which receives much theoretical and practical attention. String matching is also an important topic in combinatorial optimization. This book is devoted to recent advances in pattern recognition and string matching. It consists of twenty eight chapters written by different authors, addressing a broad range of topics such as those from classifica­ tion, matching, mining, feature selection, and applications. Each chapter is self-contained, and presents either novel methodological approaches or applications of existing theories and techniques. The aim, intent, and motivation for publishing this book is to pro­ vide a reference tool for the increasing number of readers who depend upon pattern recognition or string matching in some way. This includes student...

  5. Fabric Weave Pattern and Yarn Color Recognition and Classification Using a Deep ELM Network

    Directory of Open Access Journals (Sweden)

    Babar Khan

    2017-10-01

    Full Text Available Usually, a fabric weave pattern is recognized using methods which identify the warp floats and weft floats. Although these methods perform well for uniform or repetitive weave patterns, in the case of complex weave patterns, these methods become computationally complex and the classification error rates are comparatively higher. Furthermore, the fault-tolerance (invariance and stability (selectivity of the existing methods are still to be enhanced. We present a novel biologically-inspired method to invariantly recognize the fabric weave pattern (fabric texture and yarn color from the color image input. We proposed a model in which the fabric weave pattern descriptor is based on the HMAX model for computer vision inspired by the hierarchy in the visual cortex, the color descriptor is based on the opponent color channel inspired by the classical opponent color theory of human vision, and the classification stage is composed of a multi-layer (deep extreme learning machine. Since the weave pattern descriptor, yarn color descriptor, and the classification stage are all biologically inspired, we propose a method which is completely biologically plausible. The classification performance of the proposed algorithm indicates that the biologically-inspired computer-aided-vision models might provide accurate, fast, reliable and cost-effective solution to industrial automation.

  6. Neural network pattern recognition of lingual-palatal pressure for automated detection of swallow.

    Science.gov (United States)

    Hadley, Aaron J; Krival, Kate R; Ridgel, Angela L; Hahn, Elizabeth C; Tyler, Dustin J

    2015-04-01

    We describe a novel device and method for real-time measurement of lingual-palatal pressure and automatic identification of the oral transfer phase of deglutition. Clinical measurement of the oral transport phase of swallowing is a complicated process requiring either placement of obstructive sensors or sitting within a fluoroscope or articulograph for recording. Existing detection algorithms distinguish oral events with EMG, sound, and pressure signals from the head and neck, but are imprecise and frequently result in false detection. We placed seven pressure sensors on a molded mouthpiece fitting over the upper teeth and hard palate and recorded pressure during a variety of swallow and non-swallow activities. Pressure measures and swallow times from 12 healthy and 7 Parkinson's subjects provided training data for a time-delay artificial neural network to categorize the recordings as swallow or non-swallow events. User-specific neural networks properly categorized 96 % of swallow and non-swallow events, while a generalized population-trained network was able to properly categorize 93 % of swallow and non-swallow events across all recordings. Lingual-palatal pressure signals are sufficient to selectively and specifically recognize the initiation of swallowing in healthy and dysphagic patients.

  7. Rotation-invariant neural pattern recognition system with application to coin recognition.

    Science.gov (United States)

    Fukumi, M; Omatu, S; Takeda, F; Kosaka, T

    1992-01-01

    In pattern recognition, it is often necessary to deal with problems to classify a transformed pattern. A neural pattern recognition system which is insensitive to rotation of input pattern by various degrees is proposed. The system consists of a fixed invariance network with many slabs and a trainable multilayered network. The system was used in a rotation-invariant coin recognition problem to distinguish between a 500 yen coin and a 500 won coin. The results show that the approach works well for variable rotation pattern recognition.

  8. Neural-network-based system for recognition of partially occluded shapes and patterns

    Science.gov (United States)

    Mital, Dinesh P.; Teoh, Eam-Khwang; Amarasinghe, S. K.; Suganthan, P. N.

    1996-10-01

    The purpose of this paper is to demonstrate how a structural matching approach can be used to perfonn effective rotational invariant fingerprint identification. In this approach, each of the exiracted features is correlated with Live of its nearest neighbouring features to form a local feature gmup for a first-stage matching. After that, the feature with the highest match is used as a central feature whereby all the other features are correlated to form a global feature group for a second.stage matching. The correlation between the features is in terms of distance and relative angle. This approach actually make the matching method rotational invariant A substantial amount of testing was carried out and it shows that this matching technique is capable of matching the four basic fingerprint patterns with an average matching time of4 seconds on a 66Mhz, 486 DX personal computer.

  9. Fuel pattern recognition device

    International Nuclear Information System (INIS)

    Sato, Tomomi.

    1995-01-01

    The device of the present invention monitors normal fuel exchange upon fuel exchanging operation carried out in a reactor of a nuclear power plant. Namely, a fuel exchanger is movably disposed to the upper portion of the reactor and exchanges fuels. An exclusive computer receives operation signals of the fuel exchanger during operation as inputs, and outputs reactor core fuel pattern information signals to a fuel arrangement diagnosis device. An underwater television camera outputs image signals of a fuel pattern in the reactor core to an image processing device. If there is any change in the image signals for the fuel pattern as a result of the fuel exchange operation of the fuel exchanger, the image processing device outputs the change as image signals to the fuel pattern diagnosis device. The fuel pattern diagnosis device compares the pattern information signals from the exclusive computer with the image signals from the image processing device, to diagnose the result of the fuel exchange operation performed by the fuel exchanger and inform the diagnosis by means of an image display. (I.S.)

  10. Data complexity in pattern recognition

    CERN Document Server

    Kam Ho Tin

    2006-01-01

    Machines capable of automatic pattern recognition have many fascinating uses. Algorithms for supervised classification, where one infers a decision boundary from a set of training examples, are at the core of this capability. This book looks at data complexity and its role in shaping the theories and techniques in different disciplines

  11. Recent progress in invariant pattern recognition

    Science.gov (United States)

    Arsenault, Henri H.; Chang, S.; Gagne, Philippe; Gualdron Gonzalez, Oscar

    1996-12-01

    We present some recent results in invariant pattern recognition, including methods that are invariant under two or more distortions of position, orientation and scale. There are now a few methods that yield good results under changes of both rotation and scale. Some new methods are introduced. These include locally adaptive nonlinear matched filters, scale-adapted wavelet transforms and invariant filters for disjoint noise. Methods using neural networks will also be discussed, including an optical method that allows simultaneous classification of multiple targets.

  12. Data structures, computer graphics, and pattern recognition

    CERN Document Server

    Klinger, A; Kunii, T L

    1977-01-01

    Data Structures, Computer Graphics, and Pattern Recognition focuses on the computer graphics and pattern recognition applications of data structures methodology.This book presents design related principles and research aspects of the computer graphics, system design, data management, and pattern recognition tasks. The topics include the data structure design, concise structuring of geometric data for computer aided design, and data structures for pattern recognition algorithms. The survey of data structures for computer graphics systems, application of relational data structures in computer gr

  13. Neural network recognition of mammographic lesions

    International Nuclear Information System (INIS)

    Oldham, W.J.B.; Downes, P.T.; Hunter, V.

    1987-01-01

    A method for recognition of mammographic lesions through the use of neural networks is presented. Neural networks have exhibited the ability to learn the shape andinternal structure of patterns. Digitized mammograms containing circumscribed and stelate lesions were used to train a feedfoward synchronous neural network that self-organizes to stable attractor states. Encoding of data for submission to the network was accomplished by performing a fractal analysis of the digitized image. This results in scale invariant representation of the lesions. Results are discussed

  14. Mycobacterium tuberculosis Transfer RNA Induces IL-12p70 via Synergistic Activation of Pattern Recognition Receptors within a Cell Network.

    Science.gov (United States)

    Keegan, Caroline; Krutzik, Stephan; Schenk, Mirjam; Scumpia, Philip O; Lu, Jing; Pang, Yan Ling Joy; Russell, Brandon S; Lim, Kok Seong; Shell, Scarlet; Prestwich, Erin; Su, Dan; Elashoff, David; Hershberg, Robert M; Bloom, Barry R; Belisle, John T; Fortune, Sarah; Dedon, Peter C; Pellegrini, Matteo; Modlin, Robert L

    2018-05-01

    Upon recognition of a microbial pathogen, the innate and adaptive immune systems are linked to generate a cell-mediated immune response against the foreign invader. The culture filtrate of Mycobacterium tuberculosis contains ligands, such as M. tuberculosis tRNA, that activate the innate immune response and secreted Ags recognized by T cells to drive adaptive immune responses. In this study, bioinformatics analysis of gene-expression profiles derived from human PBMCs treated with distinct microbial ligands identified a mycobacterial tRNA-induced innate immune network resulting in the robust production of IL-12p70, a cytokine required to instruct an adaptive Th1 response for host defense against intracellular bacteria. As validated by functional studies, this pathway contained a feed-forward loop, whereby the early production of IL-18, type I IFNs, and IL-12p70 primed NK cells to respond to IL-18 and produce IFN-γ, enhancing further production of IL-12p70. Mechanistically, tRNA activates TLR3 and TLR8, and this synergistic induction of IL-12p70 was recapitulated by the addition of a specific TLR8 agonist with a TLR3 ligand to PBMCs. These data indicate that M. tuberculosis tRNA activates a gene network involving the integration of multiple innate signals, including types I and II IFNs, as well as distinct cell types to induce IL-12p70. Copyright © 2018 by The American Association of Immunologists, Inc.

  15. Pattern recognition based on time-frequency analysis and convolutional neural networks for vibrational events in φ-OTDR

    Science.gov (United States)

    Xu, Chengjin; Guan, Junjun; Bao, Ming; Lu, Jiangang; Ye, Wei

    2018-01-01

    Based on vibration signals detected by a phase-sensitive optical time-domain reflectometer distributed optical fiber sensing system, this paper presents an implement of time-frequency analysis and convolutional neural network (CNN), used to classify different types of vibrational events. First, spectral subtraction and the short-time Fourier transform are used to enhance time-frequency features of vibration signals and transform different types of vibration signals into spectrograms, which are input to the CNN for automatic feature extraction and classification. Finally, by replacing the soft-max layer in the CNN with a multiclass support vector machine, the performance of the classifier is enhanced. Experiments show that after using this method to process 4000 vibration signal samples generated by four different vibration events, namely, digging, walking, vehicles passing, and damaging, the recognition rates of vibration events are over 90%. The experimental results prove that this method can automatically make an effective feature selection and greatly improve the classification accuracy of vibrational events in distributed optical fiber sensing systems.

  16. Character Recognition Using Genetically Trained Neural Networks

    Energy Technology Data Exchange (ETDEWEB)

    Diniz, C.; Stantz, K.M.; Trahan, M.W.; Wagner, J.S.

    1998-10-01

    Computationally intelligent recognition of characters and symbols addresses a wide range of applications including foreign language translation and chemical formula identification. The combination of intelligent learning and optimization algorithms with layered neural structures offers powerful techniques for character recognition. These techniques were originally developed by Sandia National Laboratories for pattern and spectral analysis; however, their ability to optimize vast amounts of data make them ideal for character recognition. An adaptation of the Neural Network Designer soflsvare allows the user to create a neural network (NN_) trained by a genetic algorithm (GA) that correctly identifies multiple distinct characters. The initial successfid recognition of standard capital letters can be expanded to include chemical and mathematical symbols and alphabets of foreign languages, especially Arabic and Chinese. The FIN model constructed for this project uses a three layer feed-forward architecture. To facilitate the input of characters and symbols, a graphic user interface (GUI) has been developed to convert the traditional representation of each character or symbol to a bitmap. The 8 x 8 bitmap representations used for these tests are mapped onto the input nodes of the feed-forward neural network (FFNN) in a one-to-one correspondence. The input nodes feed forward into a hidden layer, and the hidden layer feeds into five output nodes correlated to possible character outcomes. During the training period the GA optimizes the weights of the NN until it can successfully recognize distinct characters. Systematic deviations from the base design test the network's range of applicability. Increasing capacity, the number of letters to be recognized, requires a nonlinear increase in the number of hidden layer neurodes. Optimal character recognition performance necessitates a minimum threshold for the number of cases when genetically training the net. And, the

  17. Quantum pattern recognition with multi-neuron interactions

    Science.gov (United States)

    Fard, E. Rezaei; Aghayar, K.; Amniat-Talab, M.

    2018-03-01

    We present a quantum neural network with multi-neuron interactions for pattern recognition tasks by a combination of extended classic Hopfield network and adiabatic quantum computation. This scheme can be used as an associative memory to retrieve partial patterns with any number of unknown bits. Also, we propose a preprocessing approach to classifying the pattern space S to suppress spurious patterns. The results of pattern clustering show that for pattern association, the number of weights (η ) should equal the numbers of unknown bits in the input pattern ( d). It is also remarkable that associative memory function depends on the location of unknown bits apart from the d and load parameter α.

  18. Hopfield's Model of Patterns Recognition and Laws of Artistic Perception

    Science.gov (United States)

    Yevin, Igor; Koblyakov, Alexander

    The model of patterns recognition or attractor network model of associative memory, offered by J.Hopfield 1982, is the most known model in theoretical neuroscience. This paper aims to show, that such well-known laws of art perception as the Wundt curve, perception of visual ambiguity in art, and also the model perception of musical tonalities are nothing else than special cases of the Hopfield’s model of patterns recognition.

  19. Pattern recognition with simple oscillating circuits

    International Nuclear Information System (INIS)

    Hoelzel, R W; Krischer, K

    2011-01-01

    Neural network devices that inherently possess parallel computing capabilities are generally difficult to construct because of the large number of neuron-neuron connections. However, there exists a theoretical approach (Hoppensteadt and Izhikevich 1999 Phys. Rev. Lett. 82 2983) that forgoes the individual connections and uses only a global coupling: systems of weakly coupled oscillators with a time-dependent global coupling are capable of performing pattern recognition in an associative manner similar to Hopfield networks. The information is stored in the phase shifts of the individual oscillators. However, to date, even the feasibility of controlling phase shifts with this kind of coupling has not yet been established experimentally. We present an experimental realization of this neural network device. It consists of eight sinusoidal electrical van der Pol oscillators that are globally coupled through a variable resistor with the electric potential as the coupling variable. We estimate an effective value of the phase coupling strength in our experiment. For that, we derive a general approach that allows one to compare different experimental realizations with each other as well as with phase equation models. We demonstrate that individual phase shifts of oscillators can be experimentally controlled by a weak global coupling. Furthermore, supplied with a distorted input image, the oscillating network can indeed recognize the correct image out of a set of predefined patterns. It can therefore be used as the processing unit of an associative memory device.

  20. Facial expression recognition based on improved deep belief networks

    Science.gov (United States)

    Wu, Yao; Qiu, Weigen

    2017-08-01

    In order to improve the robustness of facial expression recognition, a method of face expression recognition based on Local Binary Pattern (LBP) combined with improved deep belief networks (DBNs) is proposed. This method uses LBP to extract the feature, and then uses the improved deep belief networks as the detector and classifier to extract the LBP feature. The combination of LBP and improved deep belief networks is realized in facial expression recognition. In the JAFFE (Japanese Female Facial Expression) database on the recognition rate has improved significantly.

  1. 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.

  2. Pattern recognition methods in air pollution control

    Energy Technology Data Exchange (ETDEWEB)

    Tauber, S

    1978-01-01

    The use of pattern recognition methods for predicting air pollution developments is discussed. Computer analysis of historical pollution data allows comparison in graphical form. An example of crisis prediction for carbon monoxide concentrations, using the pattern recognition method of analysis, is presented. Results of the analysis agreed well with actual CO conditions. (6 graphs, 4 references, 1 table)

  3. PATTER, Pattern Recognition Data Analysis

    International Nuclear Information System (INIS)

    Cox, L.C. Jr.; Bender, C.F.

    1986-01-01

    1 - Description of program or function: PATTER is an interactive program with extensive facilities for modeling analytical processes and solving complex data analysis problems using statistical methods, spectral analysis, and pattern recognition techniques. PATTER addresses the type of problem generally stated as follows: given a set of objects and a list of measurements made on these objects, is it possible to find or predict a property of the objects which is not directly measurable but is known to define some unknown relationship? When employed intelligently, PATTER will act upon a data set in such a way it becomes apparent if useful information, beyond that already discerned, is contained in the data. 2 - Method of solution: In order to solve the general problem, PATTER contains preprocessing techniques to produce new variables that are related to the values of the measurements which may reduce the number of variables and/or reveal useful information about the 'obscure' property; display techniques to represent the variable space in some way that can be easily projected onto a two- or three-dimensional plot for human observation to see if any significant clustering of points occurs; and learning techniques based on both unsupervised and supervised methods, to extract as much information from the data as possible so that the optimum solution can be found

  4. Hidden neural networks: application to speech recognition

    DEFF Research Database (Denmark)

    Riis, Søren Kamaric

    1998-01-01

    We evaluate the hidden neural network HMM/NN hybrid on two speech recognition benchmark tasks; (1) task independent isolated word recognition on the Phonebook database, and (2) recognition of broad phoneme classes in continuous speech from the TIMIT database. It is shown how hidden neural networks...

  5. Improved pattern recognition systems by hybrid methods

    International Nuclear Information System (INIS)

    Duerr, B.; Haettich, W.; Tropf, H.; Winkler, G.; Fraunhofer-Gesellschaft zur Foerderung der Angewandten Forschung e.V., Karlsruhe

    1978-12-01

    This report describes a combination of statistical and syntactical pattern recongition methods. The hierarchically structured recognition system consists of a conventional statistical classifier, a structural classifier analysing the topological composition of the patterns, a stage reducing the number of hypotheses made by the first two stages, and a mixed stage based on a search for maximum similarity between syntactically generated prototypes and patterns. The stages work on different principles to avoid mistakes made in one stage in the other stages. This concept is applied to the recognition of numerals written without constraints. If no samples are rejected, a recognition rate of 99,5% is obtained. (orig.) [de

  6. Pattern recognition and classification an introduction

    CERN Document Server

    Dougherty, Geoff

    2012-01-01

    The use of pattern recognition and classification is fundamental to many of the automated electronic systems in use today. However, despite the existence of a number of notable books in the field, the subject remains very challenging, especially for the beginner. Pattern Recognition and Classification presents a comprehensive introduction to the core concepts involved in automated pattern recognition. It is designed to be accessible to newcomers from varied backgrounds, but it will also be useful to researchers and professionals in image and signal processing and analysis, and in computer visi

  7. Static human face recognition using artificial neural networks

    International Nuclear Information System (INIS)

    Qamar, R.; Shah, S.H.; Javed-ur-Rehman

    2003-01-01

    This paper presents a novel method of human face recognition using digital computers. A digital PC camera is used to take the BMP images of the human faces. An artificial neural network using Back Propagation Algorithm is developed as a recognition engine. The BMP images of the faces serve as the input patterns for this engine. A software 'Face Recognition' has been developed to recognize the human faces for which it is trained. Once the neural network is trained for patterns of the faces, the software is able to detect and recognize them with success rate of about 97%. (author)

  8. Degraded character recognition based on gradient pattern

    Science.gov (United States)

    Babu, D. R. Ramesh; Ravishankar, M.; Kumar, Manish; Wadera, Kevin; Raj, Aakash

    2010-02-01

    Degraded character recognition is a challenging problem in the field of Optical Character Recognition (OCR). The performance of an optical character recognition depends upon printed quality of the input documents. Many OCRs have been designed which correctly identifies the fine printed documents. But, very few reported work has been found on the recognition of the degraded documents. The efficiency of the OCRs system decreases if the input image is degraded. In this paper, a novel approach based on gradient pattern for recognizing degraded printed character is proposed. The approach makes use of gradient pattern of an individual character for recognition. Experiments were conducted on character image that is either digitally written or a degraded character extracted from historical documents and the results are found to be satisfactory.

  9. Achieving Consistent Near-Optimal Pattern Recognition Accuracy Using Particle Swarm Optimization to Pre-Train Artificial Neural Networks

    Science.gov (United States)

    Nikelshpur, Dmitry O.

    2014-01-01

    Similar to mammalian brains, Artificial Neural Networks (ANN) are universal approximators, capable of yielding near-optimal solutions to a wide assortment of problems. ANNs are used in many fields including medicine, internet security, engineering, retail, robotics, warfare, intelligence control, and finance. "ANNs have a tendency to get…

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

    Science.gov (United States)

    Zhang, Jianhua; Li, Sunan; Wang, Rubin

    2017-01-01

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

  11. 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.

  12. Neural-Network Object-Recognition Program

    Science.gov (United States)

    Spirkovska, L.; Reid, M. B.

    1993-01-01

    HONTIOR computer program implements third-order neural network exhibiting invariance under translation, change of scale, and in-plane rotation. Invariance incorporated directly into architecture of network. Only one view of each object needed to train network for two-dimensional-translation-invariant recognition of object. Also used for three-dimensional-transformation-invariant recognition by training network on only set of out-of-plane rotated views. Written in C language.

  13. Chopper model of pattern recognition

    NARCIS (Netherlands)

    van Hemmen, J.L.; Enter, A.C.D. van

    A simple model is proposed that allows an efficient storage and retrieval of random patterns. Also correlated patterns can be handled. The data are stored in an Ising-spin system with ferromagnetic interactions between all the spins and the main idea is to "chop" the system along the boundaries

  14. Facial expression recognition based on improved local ternary pattern and stacked auto-encoder

    Science.gov (United States)

    Wu, Yao; Qiu, Weigen

    2017-08-01

    In order to enhance the robustness of facial expression recognition, we propose a method of facial expression recognition based on improved Local Ternary Pattern (LTP) combined with Stacked Auto-Encoder (SAE). This method uses the improved LTP extraction feature, and then uses the improved depth belief network as the detector and classifier to extract the LTP feature. The combination of LTP and improved deep belief network is realized in facial expression recognition. The recognition rate on CK+ databases has improved significantly.

  15. Clonal Selection Based Artificial Immune System for Generalized Pattern Recognition

    Science.gov (United States)

    Huntsberger, Terry

    2011-01-01

    The last two decades has seen a rapid increase in the application of AIS (Artificial Immune Systems) modeled after the human immune system to a wide range of areas including network intrusion detection, job shop scheduling, classification, pattern recognition, and robot control. JPL (Jet Propulsion Laboratory) has developed an integrated pattern recognition/classification system called AISLE (Artificial Immune System for Learning and Exploration) based on biologically inspired models of B-cell dynamics in the immune system. When used for unsupervised or supervised classification, the method scales linearly with the number of dimensions, has performance that is relatively independent of the total size of the dataset, and has been shown to perform as well as traditional clustering methods. When used for pattern recognition, the method efficiently isolates the appropriate matches in the data set. The paper presents the underlying structure of AISLE and the results from a number of experimental studies.

  16. Automated pattern recognition system for noise analysis

    International Nuclear Information System (INIS)

    Sides, W.H. Jr.; Piety, K.R.

    1980-01-01

    A pattern recognition system was developed at ORNL for on-line monitoring of noise signals from sensors in a nuclear power plant. The system continuousy measures the power spectral density (PSD) values of the signals and the statistical characteristics of the PSDs in unattended operation. Through statistical comparison of current with past PSDs (pattern recognition), the system detects changes in the noise signals. Because the noise signals contain information about the current operational condition of the plant, a change in these signals could indicate a change, either normal or abnormal, in the operational condition

  17. Optical Pattern Recognition for Missile Guidance.

    Science.gov (United States)

    1982-11-15

    directed to novel pattern recognition algo- rithms (that allow pattern recognition and object classification in the face of various geometrical and...I wats EF5 = 50) p.j/t’ni 2 (for btith image pat tern recognitio itas a preproicessing oiperatiton. Ini devices). TIhe rt’ad light intensity (0.33t mW...electrodes on its large faces . This Priz light modulator and the motivation for its devel- SLM is known as the Prom (Pockels real-time optical opment. In Sec

  18. Pattern recognition in high energy physics

    International Nuclear Information System (INIS)

    Tenner, A.G.

    1980-01-01

    In high energy physics experiments tracks of elementary particles are recorded by different types of equipment. Coordinates of points of these tracks have to be measured for the geometrical reconstruction and the further analysis of the observed events. Pattern recognition methods may facilitate the detection of tracks or whole events and the separation of relevant from non-relevant information. They may also serve for the automation of measurement. Generally, all work is done by digital computation. In a bubble chamber tracks appear as strings of vapour bubbles that can be recorded photographically. Two methods of pattern recognition are discussed. The flying spot digitizer encodes the pattern on the photograph into point coordinates in the memory of a computer. The computer carries out the pattern recognition procedure entirely on the basis of the stored information. Cathode ray instruments scan the photograph by means of a computer steered optical device. Data acquisition from the film is performed in a feedback loop of the computation. In electronic experimental equipment tracks are defined by the spacial distribution of hits of counters (wire counters, scintillation counters, spark chambers). Pattern recognition is generally performed in various stages both by on-line and off-line equipment. Problems in the data handling arise both from the great abundance of data and from the time limits imposed on the on-line computation by high measuring rates. The on-line computation is carried out by hardwired logic, small computers, and to an increasing extent by microprocessors. (Auth.)

  19. Magnetic Flux Leakage Sensing and Artificial Neural Network Pattern Recognition-Based Automated Damage Detection and Quantification for Wire Rope Non-Destructive Evaluation.

    Science.gov (United States)

    Kim, Ju-Won; Park, Seunghee

    2018-01-02

    In this study, a magnetic flux leakage (MFL) method, known to be a suitable non-destructive evaluation (NDE) method for continuum ferromagnetic structures, was used to detect local damage when inspecting steel wire ropes. To demonstrate the proposed damage detection method through experiments, a multi-channel MFL sensor head was fabricated using a Hall sensor array and magnetic yokes to adapt to the wire rope. To prepare the damaged wire-rope specimens, several different amounts of artificial damages were inflicted on wire ropes. The MFL sensor head was used to scan the damaged specimens to measure the magnetic flux signals. After obtaining the signals, a series of signal processing steps, including the enveloping process based on the Hilbert transform (HT), was performed to better recognize the MFL signals by reducing the unexpected noise. The enveloped signals were then analyzed for objective damage detection by comparing them with a threshold that was established based on the generalized extreme value (GEV) distribution. The detected MFL signals that exceed the threshold were analyzed quantitatively by extracting the magnetic features from the MFL signals. To improve the quantitative analysis, damage indexes based on the relationship between the enveloped MFL signal and the threshold value were also utilized, along with a general damage index for the MFL method. The detected MFL signals for each damage type were quantified by using the proposed damage indexes and the general damage indexes for the MFL method. Finally, an artificial neural network (ANN) based multi-stage pattern recognition method using extracted multi-scale damage indexes was implemented to automatically estimate the severity of the damage. To analyze the reliability of the MFL-based automated wire rope NDE method, the accuracy and reliability were evaluated by comparing the repeatedly estimated damage size and the actual damage size.

  20. Algorithms for adaptive nonlinear pattern recognition

    Science.gov (United States)

    Schmalz, Mark S.; Ritter, Gerhard X.; Hayden, Eric; Key, Gary

    2011-09-01

    In Bayesian pattern recognition research, static classifiers have featured prominently in the literature. A static classifier is essentially based on a static model of input statistics, thereby assuming input ergodicity that is not realistic in practice. Classical Bayesian approaches attempt to circumvent the limitations of static classifiers, which can include brittleness and narrow coverage, by training extensively on a data set that is assumed to cover more than the subtense of expected input. Such assumptions are not realistic for more complex pattern classification tasks, for example, object detection using pattern classification applied to the output of computer vision filters. In contrast, we have developed a two step process, that can render the majority of static classifiers adaptive, such that the tracking of input nonergodicities is supported. Firstly, we developed operations that dynamically insert (or resp. delete) training patterns into (resp. from) the classifier's pattern database, without requiring that the classifier's internal representation of its training database be completely recomputed. Secondly, we developed and applied a pattern replacement algorithm that uses the aforementioned pattern insertion/deletion operations. This algorithm is designed to optimize the pattern database for a given set of performance measures, thereby supporting closed-loop, performance-directed optimization. This paper presents theory and algorithmic approaches for the efficient computation of adaptive linear and nonlinear pattern recognition operators that use our pattern insertion/deletion technology - in particular, tabular nearest-neighbor encoding (TNE) and lattice associative memories (LAMs). Of particular interest is the classification of nonergodic datastreams that have noise corruption with time-varying statistics. The TNE and LAM based classifiers discussed herein have been successfully applied to the computation of object classification in hyperspectral

  1. 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.

  2. Auditory orientation in crickets: Pattern recognition controls reactive steering

    Science.gov (United States)

    Poulet, James F. A.; Hedwig, Berthold

    2005-10-01

    Many groups of insects are specialists in exploiting sensory cues to locate food resources or conspecifics. To achieve orientation, bees and ants analyze the polarization pattern of the sky, male moths orient along the females' odor plume, and cicadas, grasshoppers, and crickets use acoustic signals to locate singing conspecifics. In comparison with olfactory and visual orientation, where learning is involved, auditory processing underlying orientation in insects appears to be more hardwired and genetically determined. In each of these examples, however, orientation requires a recognition process identifying the crucial sensory pattern to interact with a localization process directing the animal's locomotor activity. Here, we characterize this interaction. Using a sensitive trackball system, we show that, during cricket auditory behavior, the recognition process that is tuned toward the species-specific song pattern controls the amplitude of auditory evoked steering responses. Females perform small reactive steering movements toward any sound patterns. Hearing the male's calling song increases the gain of auditory steering within 2-5 s, and the animals even steer toward nonattractive sound patterns inserted into the speciesspecific pattern. This gain control mechanism in the auditory-to-motor pathway allows crickets to pursue species-specific sound patterns temporarily corrupted by environmental factors and may reflect the organization of recognition and localization networks in insects. localization | phonotaxis

  3. Searching for pulsars using image pattern recognition

    Energy Technology Data Exchange (ETDEWEB)

    Zhu, W. W.; Berndsen, A.; Madsen, E. C.; Tan, M.; Stairs, I. H. [Department of Physics and Astronomy, 6224 Agricultural Road, University of British Columbia, Vancouver, BC, V6T 1Z1 (Canada); Brazier, A. [Astronomy Department, Cornell University, Ithaca, NY 14853 (United States); Lazarus, P. [Max-Planck-Institut für Radioastronomie, Auf dem Hügel 69, D-53121 Bonn (Germany); Lynch, R.; Scholz, P. [Department of Physics, McGill University, Montreal, QC H3A 2T8 (Canada); Stovall, K.; Cohen, S.; Dartez, L. P.; Lunsford, G.; Martinez, J. G.; Mata, A. [Center for Advanced Radio Astronomy, University of Texas at Brownsville, Brownsville, TX 78520 (United States); Ransom, S. M. [NRAO, Charlottesville, VA 22903 (United States); Banaszak, S.; Biwer, C. M.; Flanigan, J.; Rohr, M., E-mail: zhuww@phas.ubc.ca, E-mail: berndsen@phas.ubc.ca [Center for Gravitation, Cosmology and Astrophysics. University of Wisconsin Milwaukee, Milwaukee, WI 53211 (United States); and others

    2014-02-01

    In the modern era of big data, many fields of astronomy are generating huge volumes of data, the analysis of which can sometimes be the limiting factor in research. Fortunately, computer scientists have developed powerful data-mining techniques that can be applied to various fields. In this paper, we present a novel artificial intelligence (AI) program that identifies pulsars from recent surveys by using image pattern recognition with deep neural nets—the PICS (Pulsar Image-based Classification System) AI. The AI mimics human experts and distinguishes pulsars from noise and interference by looking for patterns from candidate plots. Different from other pulsar selection programs that search for expected patterns, the PICS AI is taught the salient features of different pulsars from a set of human-labeled candidates through machine learning. The training candidates are collected from the Pulsar Arecibo L-band Feed Array (PALFA) survey. The information from each pulsar candidate is synthesized in four diagnostic plots, which consist of image data with up to thousands of pixels. The AI takes these data from each candidate as its input and uses thousands of such candidates to train its ∼9000 neurons. The deep neural networks in this AI system grant it superior ability to recognize various types of pulsars as well as their harmonic signals. The trained AI's performance has been validated with a large set of candidates from a different pulsar survey, the Green Bank North Celestial Cap survey. In this completely independent test, the PICS ranked 264 out of 277 pulsar-related candidates, including all 56 previously known pulsars and 208 of their harmonics, in the top 961 (1%) of 90,008 test candidates, missing only 13 harmonics. The first non-pulsar candidate appears at rank 187, following 45 pulsars and 141 harmonics. In other words, 100% of the pulsars were ranked in the top 1% of all candidates, while 80% were ranked higher than any noise or interference. The

  4. Searching for pulsars using image pattern recognition

    International Nuclear Information System (INIS)

    Zhu, W. W.; Berndsen, A.; Madsen, E. C.; Tan, M.; Stairs, I. H.; Brazier, A.; Lazarus, P.; Lynch, R.; Scholz, P.; Stovall, K.; Cohen, S.; Dartez, L. P.; Lunsford, G.; Martinez, J. G.; Mata, A.; Ransom, S. M.; Banaszak, S.; Biwer, C. M.; Flanigan, J.; Rohr, M.

    2014-01-01

    In the modern era of big data, many fields of astronomy are generating huge volumes of data, the analysis of which can sometimes be the limiting factor in research. Fortunately, computer scientists have developed powerful data-mining techniques that can be applied to various fields. In this paper, we present a novel artificial intelligence (AI) program that identifies pulsars from recent surveys by using image pattern recognition with deep neural nets—the PICS (Pulsar Image-based Classification System) AI. The AI mimics human experts and distinguishes pulsars from noise and interference by looking for patterns from candidate plots. Different from other pulsar selection programs that search for expected patterns, the PICS AI is taught the salient features of different pulsars from a set of human-labeled candidates through machine learning. The training candidates are collected from the Pulsar Arecibo L-band Feed Array (PALFA) survey. The information from each pulsar candidate is synthesized in four diagnostic plots, which consist of image data with up to thousands of pixels. The AI takes these data from each candidate as its input and uses thousands of such candidates to train its ∼9000 neurons. The deep neural networks in this AI system grant it superior ability to recognize various types of pulsars as well as their harmonic signals. The trained AI's performance has been validated with a large set of candidates from a different pulsar survey, the Green Bank North Celestial Cap survey. In this completely independent test, the PICS ranked 264 out of 277 pulsar-related candidates, including all 56 previously known pulsars and 208 of their harmonics, in the top 961 (1%) of 90,008 test candidates, missing only 13 harmonics. The first non-pulsar candidate appears at rank 187, following 45 pulsars and 141 harmonics. In other words, 100% of the pulsars were ranked in the top 1% of all candidates, while 80% were ranked higher than any noise or interference. The

  5. Searching for Pulsars Using Image Pattern Recognition

    Science.gov (United States)

    Zhu, W. W.; Berndsen, A.; Madsen, E. C.; Tan, M.; Stairs, I. H.; Brazier, A.; Lazarus, P.; Lynch, R.; Scholz, P.; Stovall, K.; Ransom, S. M.; Banaszak, S.; Biwer, C. M.; Cohen, S.; Dartez, L. P.; Flanigan, J.; Lunsford, G.; Martinez, J. G.; Mata, A.; Rohr, M.; Walker, A.; Allen, B.; Bhat, N. D. R.; Bogdanov, S.; Camilo, F.; Chatterjee, S.; Cordes, J. M.; Crawford, F.; Deneva, J. S.; Desvignes, G.; Ferdman, R. D.; Freire, P. C. C.; Hessels, J. W. T.; Jenet, F. A.; Kaplan, D. L.; Kaspi, V. M.; Knispel, B.; Lee, K. J.; van Leeuwen, J.; Lyne, A. G.; McLaughlin, M. A.; Siemens, X.; Spitler, L. G.; Venkataraman, A.

    2014-02-01

    In the modern era of big data, many fields of astronomy are generating huge volumes of data, the analysis of which can sometimes be the limiting factor in research. Fortunately, computer scientists have developed powerful data-mining techniques that can be applied to various fields. In this paper, we present a novel artificial intelligence (AI) program that identifies pulsars from recent surveys by using image pattern recognition with deep neural nets—the PICS (Pulsar Image-based Classification System) AI. The AI mimics human experts and distinguishes pulsars from noise and interference by looking for patterns from candidate plots. Different from other pulsar selection programs that search for expected patterns, the PICS AI is taught the salient features of different pulsars from a set of human-labeled candidates through machine learning. The training candidates are collected from the Pulsar Arecibo L-band Feed Array (PALFA) survey. The information from each pulsar candidate is synthesized in four diagnostic plots, which consist of image data with up to thousands of pixels. The AI takes these data from each candidate as its input and uses thousands of such candidates to train its ~9000 neurons. The deep neural networks in this AI system grant it superior ability to recognize various types of pulsars as well as their harmonic signals. The trained AI's performance has been validated with a large set of candidates from a different pulsar survey, the Green Bank North Celestial Cap survey. In this completely independent test, the PICS ranked 264 out of 277 pulsar-related candidates, including all 56 previously known pulsars and 208 of their harmonics, in the top 961 (1%) of 90,008 test candidates, missing only 13 harmonics. The first non-pulsar candidate appears at rank 187, following 45 pulsars and 141 harmonics. In other words, 100% of the pulsars were ranked in the top 1% of all candidates, while 80% were ranked higher than any noise or interference. The

  6. Pattern recognition applied to uranium prospecting

    Energy Technology Data Exchange (ETDEWEB)

    Briggs, P L; Press, F [Massachusetts Inst. of Tech., Cambridge (USA). Dept. of Earth and Planetary Sciences

    1977-07-14

    It is stated that pattern recognition techniques provide one way of combining quantitative and descriptive geological data for mineral prospecting. A quantified decision process using computer-selected patterns of geological data has the potential for selecting areas with undiscovered deposits of uranium or other minerals. When a natural resource is mined more rapidly than it is discovered, its continued production becomes increasingly difficult, and it has been noted that, although a considerable uranium reserve may remain in the U.S.A., the discovery rate for uranium is decreasing exponentially with cumulative exploration footage drilled. Pattern recognition methods of organising geological information for prospecting may provide new predictive power, as well as insight into the occurrence of uranium ore deposits. Often the task of prospecting consists of three stages of information processing: (1) collection of data on known ore deposits; (2) noting any regularities common to the known examples of an ore; (3) selection of new exploration targets based on the results of the second stage. A logical pattern recognition algorithm is here described that implements this geological procedure to demonstrate the possibility of building a quantified uranium prospecting guide from diverse geologic data.

  7. A pattern recognition account of decision making.

    Science.gov (United States)

    Massaro, D W

    1994-09-01

    In the domain of pattern recognition, experiments have shown that perceivers integrate multiple sources of information in an optimal manner. In contrast, other research has been interpreted to mean that decision making is nonoptimal. As an example, Tversky and Kahneman (1983) have shown that subjects commit a conjunction fallacy because they judge it more likely that a fictitious person named Linda is a bank teller and a feminist than just a bank teller. This judgment supposedly violates probability theory, because the probability of two events can never be greater than the probability of either event alone. The present research tests the hypothesis that subjects interpret this judgment task as a pattern recognition task. If this hypothesis is correct, subjects' judgments should be described accurately by the fuzzy logical model of perception (FLMP)--a successful model of pattern recognition. In the first experiment, the Linda task was extended to an expanded factorial design with five vocations and five avocations. The probability ratings were described well by the FLMP and described poorly by a simple probability model. The second experiment included (1) two fictitious people, Linda and Joan, as response alternatives and (2) both ratings and categorization judgments. Although the ratings were accurately described by both the FLMP and an averaging of the sources of information, the categorization judgments were described better by the FLMP. These results reveal important similarities in recognizing patterns and in decision making. Given that the FLMP is an optimal method for combining multiple sources of information, the probability judgments appear to be optimal in the same manner as pattern-recognition judgments.

  8. DNA pattern recognition using canonical correlation algorithm.

    Science.gov (United States)

    Sarkar, B K; Chakraborty, Chiranjib

    2015-10-01

    We performed canonical correlation analysis as an unsupervised statistical tool to describe related views of the same semantic object for identifying patterns. A pattern recognition technique based on canonical correlation analysis (CCA) was proposed for finding required genetic code in the DNA sequence. Two related but different objects were considered: one was a particular pattern, and other was test DNA sequence. CCA found correlations between two observations of the same semantic pattern and test sequence. It is concluded that the relationship possesses maximum value in the position where the pattern exists. As a case study, the potential of CCA was demonstrated on the sequence found from HIV-1 preferred integration sites. The subsequences on the left and right flanking from the integration site were considered as the two views, and statistically significant relationships were established between these two views to elucidate the viral preference as an important factor for the correlation.

  9. Environmental Sound Recognition Using Time-Frequency Intersection Patterns

    Directory of Open Access Journals (Sweden)

    Xuan Guo

    2012-01-01

    Full Text Available Environmental sound recognition is an important function of robots and intelligent computer systems. In this research, we use a multistage perceptron neural network system for environmental sound recognition. The input data is a combination of time-variance pattern of instantaneous powers and frequency-variance pattern with instantaneous spectrum at the power peak, referred to as a time-frequency intersection pattern. Spectra of many environmental sounds change more slowly than those of speech or voice, so the intersectional time-frequency pattern will preserve the major features of environmental sounds but with drastically reduced data requirements. Two experiments were conducted using an original database and an open database created by the RWCP project. The recognition rate for 20 kinds of environmental sounds was 92%. The recognition rate of the new method was about 12% higher than methods using only an instantaneous spectrum. The results are also comparable with HMM-based methods, although those methods need to treat the time variance of an input vector series with more complicated computations.

  10. Sequential pattern recognition by maximum conditional informativity

    Czech Academy of Sciences Publication Activity Database

    Grim, Jiří

    2014-01-01

    Roč. 45, č. 1 (2014), s. 39-45 ISSN 0167-8655 R&D Projects: GA ČR(CZ) GA14-02652S; GA ČR(CZ) GA14-10911S Keywords : Multivariate statistics * Statistical pattern recognition * Sequential decision making * Product mixtures * EM algorithm * Shannon information Subject RIV: IN - Informatics, Computer Sci ence Impact factor: 1.551, year: 2014 http://library.utia.cas.cz/separaty/2014/RO/grim-0428565.pdf

  11. Pattern recognition of neurotransmitters using multimode sensing.

    Science.gov (United States)

    Stefan-van Staden, Raluca-Ioana; Moldoveanu, Iuliana; van Staden, Jacobus Frederick

    2014-05-30

    Pattern recognition is essential in chemical analysis of biological fluids. Reliable and sensitive methods for neurotransmitters analysis are needed. Therefore, we developed for pattern recognition of neurotransmitters: dopamine, epinephrine, norepinephrine a method based on multimode sensing. Multimode sensing was performed using microsensors based on diamond paste modified with 5,10,15,20-tetraphenyl-21H,23H-porphyrine, hemin and protoporphyrin IX in stochastic and differential pulse voltammetry modes. Optimized working conditions: phosphate buffer solution of pH 3.01 and KCl 0.1mol/L (as electrolyte support), were determined using cyclic voltammetry and used in all measurements. The lowest limits of quantification were: 10(-10)mol/L for dopamine and epinephrine, and 10(-11)mol/L for norepinephrine. The multimode microsensors were selective over ascorbic and uric acids and the method facilitated reliable assay of neurotransmitters in urine samples, and therefore, the pattern recognition showed high reliability (RSDneurotransmitters on biological fluids at a lower determination level than chromatographic methods. The sampling of the biological fluids referees only to the buffering (1:1, v/v) with a phosphate buffer pH 3.01, while for chromatographic methods the sampling is laborious. Accordingly with the statistic evaluation of the results at 99.00% confidence level, both modes can be used for pattern recognition and quantification of neurotransmitters with high reliability. The best multimode microsensor was the one based on diamond paste modified with protoporphyrin IX. Copyright © 2014 Elsevier B.V. All rights reserved.

  12. Pattern recognition methods for acoustic emission analysis

    International Nuclear Information System (INIS)

    Doctor, P.G.; Harrington, T.P.; Hutton, P.H.

    1979-07-01

    Models have been developed that relate the rate of acoustic emissions to structural integrity. The implementation of these techniques in the field has been hindered by the noisy environment in which the data must be taken. Acoustic emissions from noncritical sources are recorded in addition to those produced by critical sources, such as flaws. A technique is discussed for prescreening acoustic events and filtering out those that are produced by noncritical sources. The methodology that was investigated is pattern recognition. Three different pattern recognition techniques were applied to a data set that consisted of acoustic emissions caused by crack growth and acoustic signals caused by extraneous noise sources. Examination of the acoustic emission data presented has uncovered several features of the data that can provide a reasonable filter. Two of the most valuable features are the frequency of maximum response and the autocorrelation coefficient at Lag 13. When these two features and several others were combined with a least squares decision algorithm, 90% of the acoustic emissions in the data set were correctly classified. It appears possible to design filters that eliminate extraneous noise sources from flaw-growth acoustic emissions using pattern recognition techniques

  13. Deep Learning For Sequential Pattern Recognition

    OpenAIRE

    Safari, Pooyan

    2013-01-01

    Projecte realitzat en el marc d’un programa de mobilitat amb la Technische Universität München (TUM) In recent years, deep learning has opened a new research line in pattern recognition tasks. It has been hypothesized that this kind of learning would capture more abstract patterns concealed in data. It is motivated by the new findings both in biological aspects of the brain and hardware developments which have made the parallel processing possible. Deep learning methods come along with ...

  14. Fuzzy tree automata and syntactic pattern recognition.

    Science.gov (United States)

    Lee, E T

    1982-04-01

    An approach of representing patterns by trees and processing these trees by fuzzy tree automata is described. Fuzzy tree automata are defined and investigated. The results include that the class of fuzzy root-to-frontier recognizable ¿-trees is closed under intersection, union, and complementation. Thus, the class of fuzzy root-to-frontier recognizable ¿-trees forms a Boolean algebra. Fuzzy tree automata are applied to processing fuzzy tree representation of patterns based on syntactic pattern recognition. The grade of acceptance is defined and investigated. Quantitative measures of ``approximate isosceles triangle,'' ``approximate elongated isosceles triangle,'' ``approximate rectangle,'' and ``approximate cross'' are defined and used in the illustrative examples of this approach. By using these quantitative measures, a house, a house with high roof, and a church are also presented as illustrative examples. In addition, three fuzzy tree automata are constructed which have the capability of processing the fuzzy tree representations of ``fuzzy houses,'' ``houses with high roofs,'' and ``fuzzy churches,'' respectively. The results may have useful applications in pattern recognition, image processing, artificial intelligence, pattern database design and processing, image science, and pictorial information systems.

  15. 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.

  16. Artificial intelligence tools for pattern recognition

    Science.gov (United States)

    Acevedo, Elena; Acevedo, Antonio; Felipe, Federico; Avilés, Pedro

    2017-06-01

    In this work, we present a system for pattern recognition that combines the power of genetic algorithms for solving problems and the efficiency of the morphological associative memories. We use a set of 48 tire prints divided into 8 brands of tires. The images have dimensions of 200 x 200 pixels. We applied Hough transform to obtain lines as main features. The number of lines obtained is 449. The genetic algorithm reduces the number of features to ten suitable lines that give thus the 100% of recognition. Morphological associative memories were used as evaluation function. The selection algorithms were Tournament and Roulette wheel. For reproduction, we applied one-point, two-point and uniform crossover.

  17. RECOG-ORNL, Pattern Recognition Data Analysis

    International Nuclear Information System (INIS)

    Begovich, C.L.; Larson, N.M.

    2000-01-01

    Description of program or function: RECOG-ORNL, a general-purpose pattern recognition code, is a modification of the RECOG program, written at Lawrence Livermore National Laboratory. RECOG-ORNL contains techniques for preprocessing, analyzing, and displaying data, and for unsupervised and supervised learning. Data preprocessing routines transform the data into useful representations by auto-calling, selecting important variables, and/or adding products or transformations of the variables of the data set. Data analysis routines use correlations to evaluate the data and interrelationships among the data. Display routines plot the multidimensional patterns in two dimensions or plot histograms, patterns, or one variable versus another. Unsupervised learning techniques search for classes contained inherently in the data. Supervised learning techniques use known information about some of the data to generate predicted properties for an unknown set

  18. Target recognition based on convolutional neural network

    Science.gov (United States)

    Wang, Liqiang; Wang, Xin; Xi, Fubiao; Dong, Jian

    2017-11-01

    One of the important part of object target recognition is the feature extraction, which can be classified into feature extraction and automatic feature extraction. The traditional neural network is one of the automatic feature extraction methods, while it causes high possibility of over-fitting due to the global connection. The deep learning algorithm used in this paper is a hierarchical automatic feature extraction method, trained with the layer-by-layer convolutional neural network (CNN), which can extract the features from lower layers to higher layers. The features are more discriminative and it is beneficial to the object target recognition.

  19. Pattern Recognition of the Multiple Sclerosis Syndrome

    Science.gov (United States)

    Stewart, Renee; Healey, Kathleen M.

    2017-01-01

    During recent decades, the autoimmune disease neuromyelitis optica spectrum disorder (NMOSD), once broadly classified under the umbrella of multiple sclerosis (MS), has been extended to include autoimmune inflammatory conditions of the central nervous system (CNS), which are now diagnosable with serum serological tests. These antibody-mediated inflammatory diseases of the CNS share a clinical presentation to MS. A number of practical learning points emerge in this review, which is geared toward the pattern recognition of optic neuritis, transverse myelitis, brainstem/cerebellar and hemispheric tumefactive demyelinating lesion (TDL)-associated MS, aquaporin-4-antibody and myelin oligodendrocyte glycoprotein (MOG)-antibody NMOSD, overlap syndrome, and some yet-to-be-defined/classified demyelinating disease, all unspecifically labeled under MS syndrome. The goal of this review is to increase clinicians’ awareness of the clinical nuances of the autoimmune conditions for MS and NMSOD, and to highlight highly suggestive patterns of clinical, paraclinical or imaging presentations in order to improve differentiation. With overlay in clinical manifestations between MS and NMOSD, magnetic resonance imaging (MRI) of the brain, orbits and spinal cord, serology, and most importantly, high index of suspicion based on pattern recognition, will help lead to the final diagnosis. PMID:29064441

  20. Similarity-based pattern analysis and recognition

    CERN Document Server

    Pelillo, Marcello

    2013-01-01

    This accessible text/reference presents a coherent overview of the emerging field of non-Euclidean similarity learning. The book presents a broad range of perspectives on similarity-based pattern analysis and recognition methods, from purely theoretical challenges to practical, real-world applications. The coverage includes both supervised and unsupervised learning paradigms, as well as generative and discriminative models. Topics and features: explores the origination and causes of non-Euclidean (dis)similarity measures, and how they influence the performance of traditional classification alg

  1. Use of pattern recognition and neural networks for non-metric sex diagnosis from lateral shape of calvarium: an innovative model for computer-aided diagnosis in forensic and physical anthropology.

    Science.gov (United States)

    Cavalli, Fabio; Lusnig, Luca; Trentin, Edmondo

    2017-05-01

    Sex determination on skeletal remains is one of the most important diagnosis in forensic cases and in demographic studies on ancient populations. Our purpose is to realize an automatic operator-independent method to determine the sex from the bone shape and to test an intelligent, automatic pattern recognition system in an anthropological domain. Our multiple-classifier system is based exclusively on the morphological variants of a curve that represents the sagittal profile of the calvarium, modeled via artificial neural networks, and yields an accuracy higher than 80 %. The application of this system to other bone profiles is expected to further improve the sensibility of the methodology.

  2. Discrimination of Li-ion batteries based on Hamming network using discharging-charging voltage pattern recognition for improved state-of-charge estimation

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Jonghoon; Lee, Seongjun; Cho, B.H. [Power Electronics System Laboratory, School of Electrical Engineering and Computer Science, Seoul National University, Seoul 151-744 (Korea, Republic of)

    2011-02-15

    Differences in electrochemical characteristics among Li-ion batteries and factors such as temperature and ageing result in erroneous state-of-charge (SoC) estimation when using the existing extended Kalman filter (EKF) algorithm. This study presents an application of the Hamming neural network to the identification of suitable battery model parameters for improved SoC estimation. The discharging-charging voltage (DCV) patterns of ten fresh Li-ion batteries are measured, together with the battery parameters, as representative patterns. Through statistical analysis, the Hamming network is applied for identification of the representative DCV pattern that matches most closely of the pattern of the arbitrary battery to be measured. Model parameters of the representative battery are then applied to estimate the SoC of the arbitrary battery using the EKF. This avoids the need for repeated parameter measurement. Using model parameters selected by the proposed method, all SoC estimates (off-line and on-line) based on the EKF are within {+-}5% of the values estimated by ampere-hour counting. (author)

  3. An Ultrasonic Pattern Recognition Approach to Welding Defect Classification

    International Nuclear Information System (INIS)

    Song, Sung Jin

    1995-01-01

    Classification of flaws in weldments from their ultrasonic scattering signals is very important in quantitative nondestructive evaluation. This problem is ideally suited to a modern ultrasonic pattern recognition technique. Here brief discussion on systematic approach to this methodology is presented including ultrasonic feature extraction, feature selection and classification. A stronger emphasis is placed on probabilistic neural networks as efficient classifiers for many practical classification problems. In an example probabilistic neural networks are applied to classify flaws in weldments into 3 classes such as cracks, porosity and slag inclusions. Probabilistic nets are shown to be able to exhibit high performance of other classifiers without any training time overhead. In addition, forward selection scheme for sensitive features is addressed to enhance network performance

  4. Extended Target Recognition in Cognitive Radar Networks

    Directory of Open Access Journals (Sweden)

    Xiqin Wang

    2010-11-01

    Full Text Available We address the problem of adaptive waveform design for extended target recognition in cognitive radar networks. A closed-loop active target recognition radar system is extended to the case of a centralized cognitive radar network, in which a generalized likelihood ratio (GLR based sequential hypothesis testing (SHT framework is employed. Using Doppler velocities measured by multiple radars, the target aspect angle for each radar is calculated. The joint probability of each target hypothesis is then updated using observations from different radar line of sights (LOS. Based on these probabilities, a minimum correlation algorithm is proposed to adaptively design the transmit waveform for each radar in an amplitude fluctuation situation. Simulation results demonstrate performance improvements due to the cognitive radar network and adaptive waveform design. Our minimum correlation algorithm outperforms the eigen-waveform solution and other non-cognitive waveform design approaches.

  5. 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.

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

    Science.gov (United States)

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

    1997-03-01

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

  7. Description and recognition of patterns in stochastic signals. [Electroencephalograms

    Energy Technology Data Exchange (ETDEWEB)

    Flik, T [Technische Univ. Berlin (F.R. Germany). Informatik-Forschungsgruppe Rechnerorganisation und Schaltwerke

    1975-10-01

    A method is shown for the description and recognition of patterns in stochastic signals such as electroencephalograms. For pattern extraction the signal is segmented at times of minimum amplitudes. The describing features consist of geometric values of the so defined patterns. The classification algorithm is based on the regression analysis, which is well known in the field of character recognition. For an economic classification a method is proposed which reduces the number of features. The quality of this pattern recognition method is demonstrated by the detection of spike wave complexes in electroencephalograms. The pattern description and recognition are provided for processing on a digital computer. (DE)

  8. 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.

  9. Track recognition with an associative pattern memory

    International Nuclear Information System (INIS)

    Bok, H.W. den; Visschers, J.L.; Borgers, A.J.; Lourens, W.

    1991-01-01

    Using Programmable Gate Arrays (PGAs), a prototype for a fast Associative Pattern Memory module has been realized. The associative memory performs the recognition of tracks within the hadron detector data acquisition system at NIKHEF-K. The memory matches the detector state with a set of 24 predefined tracks to identify the particle tracks that occur during an event. This information enables the trigger hardware to classify and select or discriminate the event. Mounted on a standard size (6U) VME board, several PGAs together form an associative memory. The internal logic architecture of the Gate Array is used in such a way as to minimize signal propagation delay. The memory cells, containing a binary representation of the particle tracks, are dynamically loadable through a VME bus interface, providing a high level of flexibility. The hadron detector and its readout system are briefly described and our track representation method is presented. Results from measurements under experimental conditions are discussed. (orig.)

  10. 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

  11. 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.

  12. Pattern recognition with magnonic holographic memory device

    International Nuclear Information System (INIS)

    Kozhevnikov, A.; Dudko, G.; Filimonov, Y.; Gertz, F.; Khitun, A.

    2015-01-01

    In this work, we present experimental data demonstrating the possibility of using magnonic holographic devices for pattern recognition. The prototype eight-terminal device consists of a magnetic matrix with micro-antennas placed on the periphery of the matrix to excite and detect spin waves. The principle of operation is based on the effect of spin wave interference, which is similar to the operation of optical holographic devices. Input information is encoded in the phases of the spin waves generated on the edges of the magnonic matrix, while the output corresponds to the amplitude of the inductive voltage produced by the interfering spin waves on the other side of the matrix. The level of the output voltage depends on the combination of the input phases as well as on the internal structure of the magnonic matrix. Experimental data collected for several magnonic matrixes show the unique output signatures in which maxima and minima correspond to specific input phase patterns. Potentially, magnonic holographic devices may provide a higher storage density compare to optical counterparts due to a shorter wavelength and compatibility with conventional electronic devices. The challenges and shortcoming of the magnonic holographic devices are also discussed

  13. Pattern recognition for cache management in distributed medical imaging environments.

    Science.gov (United States)

    Viana-Ferreira, Carlos; Ribeiro, Luís; Matos, Sérgio; Costa, Carlos

    2016-02-01

    Traditionally, medical imaging repositories have been supported by indoor infrastructures with huge operational costs. This paradigm is changing thanks to cloud outsourcing which not only brings technological advantages but also facilitates inter-institutional workflows. However, communication latency is one main problem in this kind of approaches, since we are dealing with tremendous volumes of data. To minimize the impact of this issue, cache and prefetching are commonly used. The effectiveness of these mechanisms is highly dependent on their capability of accurately selecting the objects that will be needed soon. This paper describes a pattern recognition system based on artificial neural networks with incremental learning to evaluate, from a set of usage pattern, which one fits the user behavior at a given time. The accuracy of the pattern recognition model in distinct training conditions was also evaluated. The solution was tested with a real-world dataset and a synthesized dataset, showing that incremental learning is advantageous. Even with very immature initial models, trained with just 1 week of data samples, the overall accuracy was very similar to the value obtained when using 75% of the long-term data for training the models. Preliminary results demonstrate an effective reduction in communication latency when using the proposed solution to feed a prefetching mechanism. The proposed approach is very interesting for cache replacement and prefetching policies due to the good results obtained since the first deployment moments.

  14. Star pattern recognition algorithm aided by inertial information

    Science.gov (United States)

    Liu, Bao; Wang, Ke-dong; Zhang, Chao

    2011-08-01

    Star pattern recognition is one of the key problems of the celestial navigation. The traditional star pattern recognition approaches, such as the triangle algorithm and the star angular distance algorithm, are a kind of all-sky matching method whose recognition speed is slow and recognition success rate is not high. Therefore, the real time and reliability of CNS (Celestial Navigation System) is reduced to some extent, especially for the maneuvering spacecraft. However, if the direction of the camera optical axis can be estimated by other navigation systems such as INS (Inertial Navigation System), the star pattern recognition can be fulfilled in the vicinity of the estimated direction of the optical axis. The benefits of the INS-aided star pattern recognition algorithm include at least the improved matching speed and the improved success rate. In this paper, the direction of the camera optical axis, the local matching sky, and the projection of stars on the image plane are estimated by the aiding of INS firstly. Then, the local star catalog for the star pattern recognition is established in real time dynamically. The star images extracted in the camera plane are matched in the local sky. Compared to the traditional all-sky star pattern recognition algorithms, the memory of storing the star catalog is reduced significantly. Finally, the INS-aided star pattern recognition algorithm is validated by simulations. The results of simulations show that the algorithm's computation time is reduced sharply and its matching success rate is improved greatly.

  15. Face recognition based on improved BP neural network

    Directory of Open Access Journals (Sweden)

    Yue Gaili

    2017-01-01

    Full Text Available In order to improve the recognition rate of face recognition, face recognition algorithm based on histogram equalization, PCA and BP neural network is proposed. First, the face image is preprocessed by histogram equalization. Then, the classical PCA algorithm is used to extract the features of the histogram equalization image, and extract the principal component of the image. And then train the BP neural network using the trained training samples. This improved BP neural network weight adjustment method is used to train the network because the conventional BP algorithm has the disadvantages of slow convergence, easy to fall into local minima and training process. Finally, the BP neural network with the test sample input is trained to classify and identify the face images, and the recognition rate is obtained. Through the use of ORL database face image simulation experiment, the analysis results show that the improved BP neural network face recognition method can effectively improve the recognition rate of face recognition.

  16. Online and Offline Pattern Recognition in PANDA

    Science.gov (United States)

    Boca, Gianluigi

    2016-11-01

    PANDA is one of the four experiments that will run at the new facility FAIR that is being built in Darmstadt, Germany. It is a fixed target experiment: a beam of antiprotons collides on a jet proton target (the maximum center of mass energy is 5.46 GeV). The interaction rate at the startup will be 2MHz with the goal of reaching 20MHz at full luminosity. The beam of antiprotons will be essentially continuous. PANDA will have NO hardware trigger but only a software trigger, to allow for maximum flexibility in the physics program. All those characteristics are severe challenges for the reconstruction code that 1) must be fast, since it has to be validated up to 20MHz interaction rate; 2) must be able to reject fake tracks caused by the remnant hits, belonging to previous or later events in some slow detectors, for example the straw tubes in the central region. The Pattern Recognition (PR) of PANDA will have to run both online to achieve a first fast selection, and offline, at lower rate, for a more refined selection. In PANDA the PR code is continuously evolving; this contribution shows the present status. I will give an overview of three examples of PR following different strategies and/or implemented on different hardware (FPGA, GPUs, CPUs) and, when available, I will report the performances.

  17. Online and Offline Pattern Recognition in PANDA

    Directory of Open Access Journals (Sweden)

    Boca Gianluigi

    2016-01-01

    Full Text Available PANDA is one of the four experiments that will run at the new facility FAIR that is being built in Darmstadt, Germany. It is a fixed target experiment: a beam of antiprotons collides on a jet proton target (the maximum center of mass energy is 5.46 GeV. The interaction rate at the startup will be 2MHz with the goal of reaching 20MHz at full luminosity. The beam of antiprotons will be essentially continuous. PANDA will have NO hardware trigger but only a software trigger, to allow for maximum flexibility in the physics program. All those characteristics are severe challenges for the reconstruction code that 1 must be fast, since it has to be validated up to 20MHz interaction rate; 2 must be able to reject fake tracks caused by the remnant hits, belonging to previous or later events in some slow detectors, for example the straw tubes in the central region. The Pattern Recognition (PR of PANDA will have to run both online to achieve a first fast selection, and offline, at lower rate, for a more refined selection. In PANDA the PR code is continuously evolving; this contribution shows the present status. I will give an overview of three examples of PR following different strategies and/or implemented on different hardware (FPGA, GPUs, CPUs and, when available, I will report the performances.

  18. Pattern Recognition by Humans and Machines

    International Nuclear Information System (INIS)

    Versino, C.; )

    2015-01-01

    Data visualization is centred on new ways of processing and displaying large data sets to support pattern recognition by humans rather than by machines. The motivation for approaches based on data visualization is to encourage data exploration and curiosity by analysts. They should help formulating the right question more than addressing specific predefined issues or expectations. Translated into IAEA's terms, they should help verify the completeness of information declared to the IAEA more than their correctness. Data visualization contrasts with traditional information retrieval where one needs first to formulate a query in order to get to a narrow slice of data. Using traditional information retrieval, no one knows what is missed out. The system may fail to recall relevant data due to the way the query was formulated, or the query itself may not be the most relevant one to be asked in the first place. Examples of data visualizations relevant to safeguards will be illustrated, including new approaches for the review of surveillance images and for trade analysis. Common to these examples is the attempt to enlarge the view of the analyst on a universe of data, where context or detailed data is presented on-demand and by levels of abstraction. The paper will make reference to ongoing research and to enabling information technologies. (author)

  19. CNNs flag recognition preprocessing scheme based on gray scale stretching and local binary pattern

    Science.gov (United States)

    Gong, Qian; Qu, Zhiyi; Hao, Kun

    2017-07-01

    Flag is a rather special recognition target in image recognition because of its non-rigid features with the location, scale and rotation characteristics. The location change can be handled well by the depth learning algorithm Convolutional Neural Networks (CNNs), but the scale and rotation changes are quite a challenge for CNNs. Since it has good rotation and gray scale invariance, the local binary pattern (LBP) is combined with grayscale stretching and CNNs to make LBP and grayscale stretching as CNNs pretreatment, which can not only significantly improve the efficiency of flag recognition, but can also evaluate the recognition effect through ROC, accuracy, MSE and quality factor.

  20. Object recognition with hierarchical discriminant saliency networks

    Directory of Open Access Journals (Sweden)

    Sunhyoung eHan

    2014-09-01

    Full Text Available The benefits of integrating attention and object recognition are investigated. While attention is frequently modeled as 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 recognitionmodel, 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. 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 neuralnetwork implementation, all layers are convolutional and implement acombination of filtering, rectification, and pooling. The rectificationis performed with a parametric extension of the now popular rectified linearunits (ReLUs, whose parameters can be tuned for the detection of targetobject classes. This enables a number of functional enhancementsover neural network models that lack a connection to saliency, including optimal feature denoising mechanisms for recognition, modulation ofsaliency 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 totarget object classes and invariance. The resulting performance demonstrates benefits for all the functional enhancements of the HDSN.

  1. Application Of t-Cherry Junction Trees in Pattern Recognition

    Directory of Open Access Journals (Sweden)

    Edith Kovacs

    2010-06-01

    Full Text Available Pattern recognition aims to classify data (patterns based ei-
    ther on a priori knowledge or on statistical information extracted from the data. In this paper we will concentrate on statistical pattern recognition using a new probabilistic approach which makes possible to select the so called 'informative' features. We develop a pattern recognition algorithm which is based on the conditional independence structure underlying the statistical data. Our method was succesfully applied on a real problem of recognizing Parkinson's disease on the basis of voice disorders.

  2. Playing tag with ANN: boosted top identification with pattern recognition

    International Nuclear Information System (INIS)

    Almeida, Leandro G.; Backović, Mihailo; Cliche, Mathieu; Lee, Seung J.; Perelstein, Maxim

    2015-01-01

    Many searches for physics beyond the Standard Model at the Large Hadron Collider (LHC) rely on top tagging algorithms, which discriminate between boosted hadronic top quarks and the much more common jets initiated by light quarks and gluons. We note that the hadronic calorimeter (HCAL) effectively takes a “digital image" of each jet, with pixel intensities given by energy deposits in individual HCAL cells. Viewed in this way, top tagging becomes a canonical pattern recognition problem. With this motivation, we present a novel top tagging algorithm based on an Artificial Neural Network (ANN), one of the most popular approaches to pattern recognition. The ANN is trained on a large sample of boosted tops and light quark/gluon jets, and is then applied to independent test samples. The ANN tagger demonstrated excellent performance in a Monte Carlo study: for example, for jets with p T in the 1100–1200 GeV range, 60% top-tag efficiency can be achieved with a 4% mis-tag rate. We discuss the physical features of the jets identified by the ANN tagger as the most important for classification, as well as correlations between the ANN tagger and some of the familiar top-tagging observables and algorithms.

  3. Playing tag with ANN: boosted top identification with pattern recognition

    Energy Technology Data Exchange (ETDEWEB)

    Almeida, Leandro G. [Institut de Biologie de l’École Normale Supérieure (IBENS), Inserm 1024- CNRS 8197,46 rue d’Ulm, 75005 Paris (France); Backović, Mihailo [Center for Cosmology, Particle Physics and Phenomenology - CP3,Universite Catholique de Louvain,Louvain-la-neuve (Belgium); Cliche, Mathieu [Laboratory for Elementary Particle Physics, Cornell University,Ithaca, NY 14853 (United States); Lee, Seung J. [Department of Physics, Korea Advanced Institute of Science and Technology,335 Gwahak-ro, Yuseong-gu, Daejeon 305-701 (Korea, Republic of); School of Physics, Korea Institute for Advanced Study,Seoul 130-722 (Korea, Republic of); Perelstein, Maxim [Laboratory for Elementary Particle Physics, Cornell University,Ithaca, NY 14853 (United States)

    2015-07-17

    Many searches for physics beyond the Standard Model at the Large Hadron Collider (LHC) rely on top tagging algorithms, which discriminate between boosted hadronic top quarks and the much more common jets initiated by light quarks and gluons. We note that the hadronic calorimeter (HCAL) effectively takes a “digital image' of each jet, with pixel intensities given by energy deposits in individual HCAL cells. Viewed in this way, top tagging becomes a canonical pattern recognition problem. With this motivation, we present a novel top tagging algorithm based on an Artificial Neural Network (ANN), one of the most popular approaches to pattern recognition. The ANN is trained on a large sample of boosted tops and light quark/gluon jets, and is then applied to independent test samples. The ANN tagger demonstrated excellent performance in a Monte Carlo study: for example, for jets with p{sub T} in the 1100–1200 GeV range, 60% top-tag efficiency can be achieved with a 4% mis-tag rate. We discuss the physical features of the jets identified by the ANN tagger as the most important for classification, as well as correlations between the ANN tagger and some of the familiar top-tagging observables and algorithms.

  4. The principles of the pattern recognition of skeletal structures

    International Nuclear Information System (INIS)

    Motto, J.A.

    2006-01-01

    Request of the skeletal system form a lage proportion of plain film radiographic examinations. A sound knowledge of normal radiographic appearances is vital if abnormal patterns are to be recognized.The ABCS, SPACED and SASNOES methods of applying pattern recognition to plain radiographers of bones and joints will be presented in an attempt to make pattern recognition and offer an opinion constitutes role extension of radiographers

  5. 64 x 64 thresholding photodetector array for optical pattern recognition

    Science.gov (United States)

    Langenbacher, Harry; Chao, Tien-Hsin; Shaw, Timothy; Yu, Jeffrey W.

    1993-10-01

    A high performance 32 X 32 peak detector array is introduced. This detector consists of a 32 X 32 array of thresholding photo-transistor cells, manufactured with a standard MOSIS digital 2-micron CMOS process. A built-in thresholding function that is able to perform 1024 thresholding operations in parallel strongly distinguishes this chip from available CCD detectors. This high speed detector offers responses from one to 10 milliseconds that is much higher than the commercially available CCD detectors operating at a TV frame rate. The parallel multiple peaks thresholding detection capability makes it particularly suitable for optical correlator and optoelectronically implemented neural networks. The principle of operation, circuit design and the performance characteristics are described. Experimental demonstration of correlation peak detection is also provided. Recently, we have also designed and built an advanced version of a 64 X 64 thresholding photodetector array chip. Experimental investigation of using this chip for pattern recognition is ongoing.

  6. Fast Traffic Sign Recognition with a Rotation Invariant Binary Pattern Based Feature

    Directory of Open Access Journals (Sweden)

    Shouyi Yin

    2015-01-01

    Full Text Available Robust and fast traffic sign recognition is very important but difficult for safe driving assistance systems. This study addresses fast and robust traffic sign recognition to enhance driving safety. The proposed method includes three stages. First, a typical Hough transformation is adopted to implement coarse-grained location of the candidate regions of traffic signs. Second, a RIBP (Rotation Invariant Binary Pattern based feature in the affine and Gaussian space is proposed to reduce the time of traffic sign detection and achieve robust traffic sign detection in terms of scale, rotation, and illumination. Third, the techniques of ANN (Artificial Neutral Network based feature dimension reduction and classification are designed to reduce the traffic sign recognition time. Compared with the current work, the experimental results in the public datasets show that this work achieves robustness in traffic sign recognition with comparable recognition accuracy and faster processing speed, including training speed and recognition speed.

  7. Macrophage pattern recognition receptors in immunity, homeostasis and self tolerance.

    Science.gov (United States)

    Mukhopadhyay, Subhankar; Plüddemann, Annette; Gordon, Siamon

    2009-01-01

    Macrophages, a major component of innate immune defence, express a large repertoire of different classes of pattern recognition receptors and other surface antigens which determine the immunologic and homeostatic potential of these versatile cells. In the light of present knowledge ofmacrophage surface antigens, we discuss self versus nonself recognition, microbicidal effector functions and self tolerance in the innate immune system.

  8. Applications of evolutionary computation in image processing and pattern recognition

    CERN Document Server

    Cuevas, Erik; Perez-Cisneros, Marco

    2016-01-01

    This book presents the use of efficient Evolutionary Computation (EC) algorithms for solving diverse real-world image processing and pattern recognition problems. It provides an overview of the different aspects of evolutionary methods in order to enable the reader in reaching a global understanding of the field and, in conducting studies on specific evolutionary techniques that are related to applications in image processing and pattern recognition. It explains the basic ideas of the proposed applications in a way that can also be understood by readers outside of the field. Image processing and pattern recognition practitioners who are not evolutionary computation researchers will appreciate the discussed techniques beyond simple theoretical tools since they have been adapted to solve significant problems that commonly arise on such areas. On the other hand, members of the evolutionary computation community can learn the way in which image processing and pattern recognition problems can be translated into an...

  9. The Pandora software development kit for pattern recognition

    Energy Technology Data Exchange (ETDEWEB)

    Marshall, J.S.; Thomson, M.A. [University of Cambridge, Cavendish Laboratory, Cambridge (United Kingdom)

    2015-09-15

    The development of automated solutions to pattern recognition problems is important in many areas of scientific research and human endeavour. This paper describes the implementation of the Pandora software development kit, which aids the process of designing, implementing and running pattern recognition algorithms. The Pandora Application Programming Interfaces ensure simple specification of the building-blocks defining a pattern recognition problem. The logic required to solve the problem is implemented in algorithms. The algorithms request operations to create or modify data structures and the operations are performed by the Pandora framework. This design promotes an approach using many decoupled algorithms, each addressing specific topologies. Details of algorithms addressing two pattern recognition problems in High Energy Physics are presented: reconstruction of events at a high-energy e{sup +}e{sup -} linear collider and reconstruction of cosmic ray or neutrino events in a liquid argon time projection chamber. (orig.)

  10. Data analysis and pattern recognition in multiple databases

    CERN Document Server

    Adhikari, Animesh; Pedrycz, Witold

    2014-01-01

    Pattern recognition in data is a well known classical problem that falls under the ambit of data analysis. As we need to handle different data, the nature of patterns, their recognition and the types of data analyses are bound to change. Since the number of data collection channels increases in the recent time and becomes more diversified, many real-world data mining tasks can easily acquire multiple databases from various sources. In these cases, data mining becomes more challenging for several essential reasons. We may encounter sensitive data originating from different sources - those cannot be amalgamated. Even if we are allowed to place different data together, we are certainly not able to analyse them when local identities of patterns are required to be retained. Thus, pattern recognition in multiple databases gives rise to a suite of new, challenging problems different from those encountered before. Association rule mining, global pattern discovery, and mining patterns of select items provide different...

  11. Digital and optical shape representation and pattern recognition; Proceedings of the Meeting, Orlando, FL, Apr. 4-6, 1988

    Science.gov (United States)

    Juday, Richard D. (Editor)

    1988-01-01

    The present conference discusses topics in pattern-recognition correlator architectures, digital stereo systems, geometric image transformations and their applications, topics in pattern recognition, filter algorithms, object detection and classification, shape representation techniques, and model-based object recognition methods. Attention is given to edge-enhancement preprocessing using liquid crystal TVs, massively-parallel optical data base management, three-dimensional sensing with polar exponential sensor arrays, the optical processing of imaging spectrometer data, hybrid associative memories and metric data models, the representation of shape primitives in neural networks, and the Monte Carlo estimation of moment invariants for pattern recognition.

  12. 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%.

  13. Pattern recognition in molecular dynamics. [FORTRAN

    Energy Technology Data Exchange (ETDEWEB)

    Zurek, W H; Schieve, W C [Texas Univ., Austin (USA)

    1977-07-01

    An algorithm for the recognition of the formation of bound molecular states in the computer simulation of a dilute gas is presented. Applications to various related problems in physics and chemistry are pointed out. Data structure and decision processes are described. Performance of the FORTRAN program based on the algorithm in cooperation with the molecular dynamics program is described and the results are presented.

  14. Emotion recognition a pattern analysis approach

    CERN Document Server

    Konar, Amit

    2014-01-01

    Offers both foundations and advances on emotion recognition in a single volumeProvides a thorough and insightful introduction to the subject by utilizing computational tools of diverse domainsInspires young researchers to prepare themselves for their own researchDemonstrates direction of future research through new technologies, such as Microsoft Kinect, EEG systems etc.

  15. Technical Reviews on Pattern Recognition in Process Analytical Technology

    International Nuclear Information System (INIS)

    Kim, Jong Yun; Choi, Yong Suk; Ji, Sun Kyung; Park, Yong Joon; Song, Kyu Seok; Jung, Sung Hee

    2008-12-01

    Pattern recognition is one of the first and the most widely adopted chemometric tools among many active research area in chemometrics such as design of experiment(DoE), pattern recognition, multivariate calibration, signal processing. Pattern recognition has been used to identify the origin of a wine and the time of year that the vine was grown by using chromatography, cause of fire by using GC/MS chromatography, detection of explosives and land mines, cargo and luggage inspection in seaports and airports by using a prompt gamma-ray activation analysis, and source apportionment of environmental pollutant by using a stable isotope ratio mass spectrometry. Recently, pattern recognition has been taken into account as a major chemometric tool in the so-called 'process analytical technology (PAT)', which is a newly-developed concept in the area of process analytics proposed by US Food and Drug Administration (US FDA). For instance, identification of raw material by using a pattern recognition analysis plays an important role for the effective quality control of the production process. Recently, pattern recognition technique has been used to identify the spatial distribution and uniformity of the active ingredients present in the product such as tablet by transforming the chemical data into the visual information

  16. Face recognition system and method using face pattern words and face pattern bytes

    Science.gov (United States)

    Zheng, Yufeng

    2014-12-23

    The present invention provides a novel system and method for identifying individuals and for face recognition utilizing facial features for face identification. The system and method of the invention comprise creating facial features or face patterns called face pattern words and face pattern bytes for face identification. The invention also provides for pattern recognitions for identification other than face recognition. The invention further provides a means for identifying individuals based on visible and/or thermal images of those individuals by utilizing computer software implemented by instructions on a computer or computer system and a computer readable medium containing instructions on a computer system for face recognition and identification.

  17. Type-2 fuzzy graphical models for pattern recognition

    CERN Document Server

    Zeng, Jia

    2015-01-01

    This book discusses how to combine type-2 fuzzy sets and graphical models to solve a range of real-world pattern recognition problems such as speech recognition, handwritten Chinese character recognition, topic modeling as well as human action recognition. It covers these recent developments while also providing a comprehensive introduction to the fields of type-2 fuzzy sets and graphical models. Though primarily intended for graduate students, researchers and practitioners in fuzzy logic and pattern recognition, the book can also serve as a valuable reference work for researchers without any previous knowledge of these fields. Dr. Jia Zeng is a Professor at the School of Computer Science and Technology, Soochow University, China. Dr. Zhi-Qiang Liu is a Professor at the School of Creative Media, City University of Hong Kong, China.

  18. Threats of Password Pattern Leakage Using Smartwatch Motion Recognition Sensors

    Directory of Open Access Journals (Sweden)

    Jihun Kim

    2017-06-01

    Full Text Available Thanks to the development of Internet of Things (IoT technologies, wearable markets have been growing rapidly. Smartwatches can be said to be the most representative product in wearable markets, and involve various hardware technologies in order to overcome the limitations of small hardware. Motion recognition sensors are a representative example of those hardware technologies. However, smartwatches and motion recognition sensors that can be worn by users may pose security threats of password pattern leakage. In the present paper, passwords are inferred through experiments to obtain password patterns inputted by users using motion recognition sensors, and verification of the results and the accuracy of the results is shown.

  19. 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.

  20. 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.

  1. Traffic sign recognition with deep convolutional neural networks

    OpenAIRE

    Karamatić, Boris

    2016-01-01

    The problem of detection and recognition of traffic signs is becoming an important problem when it comes to the development of self driving cars and advanced driver assistance systems. In this thesis we will develop a system for detection and recognition of traffic signs. For the problem of detection we will use aggregate channel features and for the problem of recognition we will use a deep convolutional neural network. We will describe how convolutional neural networks work, how they are co...

  2. Speech pattern recognition for forensic acoustic purposes

    OpenAIRE

    Herrera Martínez, Marcelo; Aldana Blanco, Andrea Lorena; Guzmán Palacios, Ana María

    2014-01-01

    The present paper describes the development of a software for analysis of acoustic voice parameters (APAVOIX), which can be used for forensic acoustic purposes, based on the speaker recognition and identification. This software enables to observe in a clear manner, the parameters which are sufficient and necessary when performing a comparison between two voice signals, the suspicious and the original one. These parameters are used according to the classic method, generally used by state entit...

  3. Combining Biometric Fractal Pattern and Particle Swarm Optimization-Based Classifier for Fingerprint Recognition

    Directory of Open Access Journals (Sweden)

    Chia-Hung Lin

    2010-01-01

    Full Text Available This paper proposes combining the biometric fractal pattern and particle swarm optimization (PSO-based classifier for fingerprint recognition. Fingerprints have arch, loop, whorl, and accidental morphologies, and embed singular points, resulting in the establishment of fingerprint individuality. An automatic fingerprint identification system consists of two stages: digital image processing (DIP and pattern recognition. DIP is used to convert to binary images, refine out noise, and locate the reference point. For binary images, Katz's algorithm is employed to estimate the fractal dimension (FD from a two-dimensional (2D image. Biometric features are extracted as fractal patterns using different FDs. Probabilistic neural network (PNN as a classifier performs to compare the fractal patterns among the small-scale database. A PSO algorithm is used to tune the optimal parameters and heighten the accuracy. For 30 subjects in the laboratory, the proposed classifier demonstrates greater efficiency and higher accuracy in fingerprint recognition.

  4. 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…

  5. Is having similar eye movement patterns during face learning and recognition beneficial for recognition performance? Evidence from hidden Markov modeling.

    Science.gov (United States)

    Chuk, Tim; Chan, Antoni B; Hsiao, Janet H

    2017-12-01

    The hidden Markov model (HMM)-based approach for eye movement analysis is able to reflect individual differences in both spatial and temporal aspects of eye movements. Here we used this approach to understand the relationship between eye movements during face learning and recognition, and its association with recognition performance. We discovered holistic (i.e., mainly looking at the face center) and analytic (i.e., specifically looking at the two eyes in addition to the face center) patterns during both learning and recognition. Although for both learning and recognition, participants who adopted analytic patterns had better recognition performance than those with holistic patterns, a significant positive correlation between the likelihood of participants' patterns being classified as analytic and their recognition performance was only observed during recognition. Significantly more participants adopted holistic patterns during learning than recognition. Interestingly, about 40% of the participants used different patterns between learning and recognition, and among them 90% switched their patterns from holistic at learning to analytic at recognition. In contrast to the scan path theory, which posits that eye movements during learning have to be recapitulated during recognition for the recognition to be successful, participants who used the same or different patterns during learning and recognition did not differ in recognition performance. The similarity between their learning and recognition eye movement patterns also did not correlate with their recognition performance. These findings suggested that perceptuomotor memory elicited by eye movement patterns during learning does not play an important role in recognition. In contrast, the retrieval of diagnostic information for recognition, such as the eyes for face recognition, is a better predictor for recognition performance. Copyright © 2017 Elsevier Ltd. All rights reserved.

  6. Emergent intelligent properties of progressively structured pattern recognition nets

    Energy Technology Data Exchange (ETDEWEB)

    Aleksander, I

    1983-07-01

    The n-tuple recognition net is seen as a building brick of a progression of network structures. The emergent intelligent properties of such systems are discussed. They include the amplification of confidence for the recognition of images that differ in small detail, a short term memory of the last seen image, sequence sensitivity, sequence sensitivity, sequence acceptance and saccadic inspection as an aid in scene analysis. 12 references.

  7. Grip-pattern recognition: Applied to a smart gun

    NARCIS (Netherlands)

    Shang, X.

    2008-01-01

    In our work the verification performance of a biometric recognition system based on grip patterns, as part of a smart gun for use by the police ocers, has been investigated. The biometric features are extracted from a two-dimensional pattern of the pressure, exerted on the grip of a gun by the hand

  8. Biometric verification based on grip-pattern recognition

    NARCIS (Netherlands)

    Veldhuis, Raymond N.J.; Bazen, A.M.; Kauffman, J.A.; Hartel, Pieter H.; Delp, Edward J.; Wong, Ping W.

    This paper describes the design, implementation and evaluation of a user-verification system for a smart gun, which is based on grip-pattern recognition. An existing pressure sensor consisting of an array of 44 x 44 piezoresistive elements is used to measure the grip pattern. An interface has been

  9. Pattern Recognition as a Human Centered non-Euclidean Problem

    NARCIS (Netherlands)

    Duin, R.P.W.

    2010-01-01

    Regularities in the world are human defined. Patterns in the observed phenomena are there because we define and recognize them as such. Automatic pattern recognition tries to bridge the gap between human judgment and measurements made by artificial sensors. This is done in two steps: representation

  10. A bacterial tyrosine phosphatase inhibits plant pattern recognition receptor activation

    Science.gov (United States)

    Perception of pathogen-associated molecular patterns (PAMPs) by surface-localised pattern-recognition receptors (PRRs) is a key component of plant innate immunity. Most known plant PRRs are receptor kinases and initiation of PAMP-triggered immunity (PTI) signalling requires phosphorylation of the PR...

  11. Biometric verification based on grip-pattern recognition

    NARCIS (Netherlands)

    Veldhuis, Raymond N.J.; Bazen, A.M.; Kauffman, J.A.; Hartel, Pieter H.

    This paper describes the design, implementation and evaluation of a user-verification system for a smart gun, which is based on grip-pattern recognition. An existing pressure sensor consisting of an array of 44 £ 44 piezoresistive elements is used to measure the grip pattern. An interface has been

  12. 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.

  13. IMPROVEMENT OF RECOGNITION QUALITY IN DEEP LEARNING NETWORKS BY SIMULATED ANNEALING METHOD

    Directory of Open Access Journals (Sweden)

    A. S. Potapov

    2014-09-01

    Full Text Available The subject of this research is deep learning methods, in which automatic construction of feature transforms is taken place in tasks of pattern recognition. Multilayer autoencoders have been taken as the considered type of deep learning networks. Autoencoders perform nonlinear feature transform with logistic regression as an upper classification layer. In order to verify the hypothesis of possibility to improve recognition rate by global optimization of parameters for deep learning networks, which are traditionally trained layer-by-layer by gradient descent, a new method has been designed and implemented. The method applies simulated annealing for tuning connection weights of autoencoders while regression layer is simultaneously trained by stochastic gradient descent. Experiments held by means of standard MNIST handwritten digit database have shown the decrease of recognition error rate from 1.1 to 1.5 times in case of the modified method comparing to the traditional method, which is based on local optimization. Thus, overfitting effect doesn’t appear and the possibility to improve learning rate is confirmed in deep learning networks by global optimization methods (in terms of increasing recognition probability. Research results can be applied for improving the probability of pattern recognition in the fields, which require automatic construction of nonlinear feature transforms, in particular, in the image recognition. Keywords: pattern recognition, deep learning, autoencoder, logistic regression, simulated annealing.

  14. Face Recognition Using Local Quantized Patterns and Gabor Filters

    Science.gov (United States)

    Khryashchev, V.; Priorov, A.; Stepanova, O.; Nikitin, A.

    2015-05-01

    The problem of face recognition in a natural or artificial environment has received a great deal of researchers' attention over the last few years. A lot of methods for accurate face recognition have been proposed. Nevertheless, these methods often fail to accurately recognize the person in difficult scenarios, e.g. low resolution, low contrast, pose variations, etc. We therefore propose an approach for accurate and robust face recognition by using local quantized patterns and Gabor filters. The estimation of the eye centers is used as a preprocessing stage. The evaluation of our algorithm on different samples from a standardized FERET database shows that our method is invariant to the general variations of lighting, expression, occlusion and aging. The proposed approach allows about 20% correct recognition accuracy increase compared with the known face recognition algorithms from the OpenCV library. The additional use of Gabor filters can significantly improve the robustness to changes in lighting conditions.

  15. Distinguishing Petroleum (Crude Oil and Fuel) From Smoke Exposure within Populations Based on the Relative Blood Levels of Benzene, Toluene, Ethylbenzene, and Xylenes (BTEX), Styrene and 2,5-Dimethylfuran by Pattern Recognition Using Artificial Neural Networks.

    Science.gov (United States)

    Chambers, D M; Reese, C M; Thornburg, L G; Sanchez, E; Rafson, J P; Blount, B C; Ruhl, J R E; De Jesús, V R

    2018-01-02

    Studies of exposure to petroleum (crude oil/fuel) often involve monitoring benzene, toluene, ethylbenzene, xylenes (BTEX), and styrene (BTEXS) because of their toxicity and gas-phase prevalence, where exposure is typically by inhalation. However, BTEXS levels in the general U.S. population are primarily from exposure to tobacco smoke, where smokers have blood levels on average up to eight times higher than nonsmokers. This work describes a method using partition theory and artificial neural network (ANN) pattern recognition to classify exposure source based on relative BTEXS and 2,5-dimethylfuran blood levels. A method using surrogate signatures to train the ANN was validated by comparing blood levels among cigarette smokers from the National Health and Nutrition Examination Survey (NHANES) with BTEXS and 2,5-dimethylfuran signatures derived from the smoke of machine-smoked cigarettes. Classification agreement for an ANN model trained with relative VOC levels was up to 99.8% for nonsmokers and 100.0% for smokers. As such, because there is limited blood level data on individuals exposed to crude oil/fuel, only surrogate signatures derived from crude oil and fuel were used for training the ANN. For the 2007-2008 NHANES data, the ANN model assigned 7 out of 1998 specimens (0.35%) and for the 2013-2014 NHANES data 12 out of 2906 specimens (0.41%) to the crude oil/fuel signature category.

  16. 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

  17. Subspace methods for pattern recognition in intelligent environment

    CERN Document Server

    Jain, Lakhmi

    2014-01-01

    This research book provides a comprehensive overview of the state-of-the-art subspace learning methods for pattern recognition in intelligent environment. With the fast development of internet and computer technologies, the amount of available data is rapidly increasing in our daily life. How to extract core information or useful features is an important issue. Subspace methods are widely used for dimension reduction and feature extraction in pattern recognition. They transform a high-dimensional data to a lower-dimensional space (subspace), where most information is retained. The book covers a broad spectrum of subspace methods including linear, nonlinear and multilinear subspace learning methods and applications. The applications include face alignment, face recognition, medical image analysis, remote sensing image classification, traffic sign recognition, image clustering, super resolution, edge detection, multi-view facial image synthesis.

  18. Investigation of efficient features for image recognition by neural networks.

    Science.gov (United States)

    Goltsev, Alexander; Gritsenko, Vladimir

    2012-04-01

    In the paper, effective and simple features for image recognition (named LiRA-features) are investigated in the task of handwritten digit recognition. Two neural network classifiers are considered-a modified 3-layer perceptron LiRA and a modular assembly neural network. A method of feature selection is proposed that analyses connection weights formed in the preliminary learning process of a neural network classifier. In the experiments using the MNIST database of handwritten digits, the feature selection procedure allows reduction of feature number (from 60 000 to 7000) preserving comparable recognition capability while accelerating computations. Experimental comparison between the LiRA perceptron and the modular assembly neural network is accomplished, which shows that recognition capability of the modular assembly neural network is somewhat better. Copyright © 2011 Elsevier Ltd. All rights reserved.

  19. Recognition of faults patterns in electric generators using artificial neurons networks; Reconocimiento de patrones de fallas en generadores electricos empleando redes neuronales artificiales

    Energy Technology Data Exchange (ETDEWEB)

    Rocha Sanchez, Martha Alicia

    1999-03-01

    This work present the development of a reprocessing method to reduce the information of the original data and to maintain the essential information of the data that enter the reduction process. The obtaining of these data is performed with the aid of the ICM ++ (ICMsystems), from which vectors or n-uplos of elements are obtained. This investigation allowed to analyze an evaluation of the paradigms of artificial neural networks, with the intention of detecting which of these paradigms would evolve better with the problem of fault diagnosis in electric generators. From this a prototype system was developed called diagnosis of faults in electrical generators, which automatically will recognize faults in electrical generators by means of the interpretation of the recording of partial discharges. [Spanish] El presente trabajo presenta el desarrollo de un metodo de reprocesamiento para reducir informacion de los datos originales y mantener la informacion esencial de los datos que entran al proceso de reduccion. La obtencion de estos datos se realiza con la ayuda del ICM ++ (ICMsystems), de los cuales se obtienen vectores o n-uplos de elementos. Esta investigacion permitio analizar una evaluacion de los paradigmas de redes neuronales artificiales, con el objeto de detectar cual de estos paradigmas se desempenaria mejor con el problema de diagnostico de fallas en generadores electricos. A partir de esto se desarrollo un sistema prototipo llamado diagnostico de fallas en generadores electricos, el cual automaticamente reconocera fallas en los generadores electricos mediante la interpretacion de registro de descargas parciales.

  20. Increased Efficiency of Face Recognition System using Wireless Sensor Network

    Directory of Open Access Journals (Sweden)

    Rajani Muraleedharan

    2006-02-01

    Full Text Available This research was inspired by the need of a flexible and cost effective biometric security system. The flexibility of the wireless sensor network makes it a natural choice for data transmission. Swarm intelligence (SI is used to optimize routing in distributed time varying network. In this paper, SI maintains the required bit error rate (BER for varied channel conditions while consuming minimal energy. A specific biometric, the face recognition system, is discussed as an example. Simulation shows that the wireless sensor network is efficient in energy consumption while keeping the transmission accuracy, and the wireless face recognition system is competitive to the traditional wired face recognition system in classification accuracy.

  1. Using Pattern Classification and Recognition Techniques for Diagnostic and Prediction

    Directory of Open Access Journals (Sweden)

    MORARIU, N.

    2007-04-01

    Full Text Available The paper presents some aspects regarding the joint use of classification and recognition techniques for the activity evolution diagnostication and prediction by means of a set of indexes. Starting from the indexes set there is defined a measure on the patterns set, measure representing a scalar value that characterizes the activity analyzed at each time moment. A pattern is defined by the values of the indexes set at a given time. Over the classes set obtained by means of the classification and recognition techniques is defined a relation that allows the representation of the evolution from negative evolution towards positive evolution. For the diagnostication and prediction the following tools are used: pattern recognition and multilayer perceptron. The data set used in experiments describes the pollution due to CO2 emission from the consumption of fuels in Europe. The paper also presents the REFORME software written by the authors and the results of the experiment obtained with this software.

  2. Diagnosis of Equipment Failures by Pattern Recognition

    DEFF Research Database (Denmark)

    Pau, L. F.

    1974-01-01

    The main problems in relation to automatic fault finding and diagnosis in equipments or production systems are discussed: 1) compression of the syndrome and observation spaces for better discrimination between failure modes; 2) simultaneous display of the failure patterns and the failure instants...

  3. 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

  4. 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-...

  5. Application of pattern recognition techniques to crime analysis

    Energy Technology Data Exchange (ETDEWEB)

    Bender, C.F.; Cox, L.A. Jr.; Chappell, G.A.

    1976-08-15

    The initial goal was to evaluate the capabilities of current pattern recognition techniques when applied to existing computerized crime data. Performance was to be evaluated both in terms of the system's capability to predict crimes and to optimize police manpower allocation. A relation was sought to predict the crime's susceptibility to solution, based on knowledge of the crime type, location, time, etc. The preliminary results of this work are discussed. They indicate that automatic crime analysis involving pattern recognition techniques is feasible, and that efforts to determine optimum variables and techniques are warranted. 47 figures (RWR)

  6. Pattern recognition approach to nondestructive evaluation of materials

    International Nuclear Information System (INIS)

    Chen, C.H.

    1987-01-01

    In this paper, a pattern recognition approach to the ultrasonic nondestructive evaluation of materials is examined. Emphasis is placed on identifying effective features from time and frequency domains, correlation functions and impulse responses to classify aluminum plate specimens into three major defect geometry categories: flat, angular cut and circular hole defects. A multi-stage classification procedure is developed which can further determine the angles and sizes for defect characterization and classification. The research clearly demonstrates that the pattern recognition approach can significantly improve the nondestructive material evaluation capability of the ultrasonic methods without resorting to the solution of highly complex mathematical inverse problems

  7. Instruction of pattern recognition by MATLAB practice 1

    International Nuclear Information System (INIS)

    1999-06-01

    This book describes the pattern recognition by MATLAB practice. It includes possibility and limit of AI, introduction of pattern recognition a vector and matrix, basic status and a probability theory, a random variable and probability distribution, statistical decision theory, data-mining, gaussian mixture model, a nerve cell modeling such as Hebb's learning rule, LMS learning rule, genetic algorithm, dynamic programming and DTW, HMN on Markov model and HMM's three problems and solution, introduction of SVM with KKT condition and margin optimum, kernel trick and MATLAB practice.

  8. TECA: Petascale pattern recognition for climate science

    Energy Technology Data Exchange (ETDEWEB)

    Prabhat, . [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Byna, Surendra [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Vishwanath, Venkatram [Argonne National Lab. (ANL), Argonne, IL (United States); Dart, Eli [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Wehner, Michael [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Collins, William D. [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)

    2015-08-26

    Climate Change is one of the most pressing challenges facing humanity in the 21st century. Climate simulations provide us with a unique opportunity to examine effects of anthropogenic emissions. Highresolution climate simulations produce “Big Data”: contemporary climate archives are ≈ 5PB in size and we expect future archives to measure on the order of Exa-Bytes. In this work, we present the successful application of TECA (Toolkit for Extreme Climate Analysis) framework, for extracting extreme weather patterns such as Tropical Cyclones, Atmospheric Rivers and Extra-Tropical Cyclones from TB-sized simulation datasets. TECA has been run at full-scale on Cray XE6 and IBM BG/Q systems, and has reduced the runtime for pattern detection tasks from years to hours. TECA has been utilized to evaluate the performance of various computational models in reproducing the statistics of extreme weather events, and for characterizing the change in frequency of storm systems in the future.

  9. 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.

  10. 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.

  11. 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 ...

  12. Lexical decoder for continuous speech recognition: sequential neural network approach

    International Nuclear Information System (INIS)

    Iooss, Christine

    1991-01-01

    The work presented in this dissertation concerns the study of a connectionist architecture to treat sequential inputs. In this context, the model proposed by J.L. Elman, a recurrent multilayers network, is used. Its abilities and its limits are evaluated. Modifications are done in order to treat erroneous or noisy sequential inputs and to classify patterns. The application context of this study concerns the realisation of a lexical decoder for analytical multi-speakers continuous speech recognition. Lexical decoding is completed from lattices of phonemes which are obtained after an acoustic-phonetic decoding stage relying on a K Nearest Neighbors search technique. Test are done on sentences formed from a lexicon of 20 words. The results are obtained show the ability of the proposed connectionist model to take into account the sequentiality at the input level, to memorize the context and to treat noisy or erroneous inputs. (author) [fr

  13. Pattern recognition with parallel associative memory

    Science.gov (United States)

    Toth, Charles K.; Schenk, Toni

    1990-01-01

    An examination is conducted of the feasibility of searching targets in aerial photographs by means of a parallel associative memory (PAM) that is based on the nearest-neighbor algorithm; the Hamming distance is used as a measure of closeness, in order to discriminate patterns. Attention has been given to targets typically used for ground-control points. The method developed sorts out approximate target positions where precise localizations are needed, in the course of the data-acquisition process. The majority of control points in different images were correctly identified.

  14. Research of convolutional neural networks for traffic sign recognition

    OpenAIRE

    Stadalnikas, Kasparas

    2017-01-01

    In this thesis the convolutional neural networks application for traffic sign recognition is analyzed. Thesis describes the basic operations, techniques that are commonly used to apply in the image classification using convolutional neural networks. Also, this paper describes the data sets used for traffic sign recognition, their problems affecting the final training results. The paper reviews most popular existing technologies – frameworks for developing the solution for traffic sign recogni...

  15. Reactor noise analysis by statistical pattern recognition methods

    International Nuclear Information System (INIS)

    Howington, L.C.; Gonzalez, R.C.

    1976-01-01

    A multivariate statistical pattern recognition system for reactor noise analysis is presented. The basis of the system is a transformation for decoupling correlated variables and algorithms for inferring probability density functions. The system is adaptable to a variety of statistical properties of the data, and it has learning, tracking, updating, and data compacting capabilities. System design emphasizes control of the false-alarm rate. Its abilities to learn normal patterns, to recognize deviations from these patterns, and to reduce the dimensionality of data with minimum error were evaluated by experiments at the Oak Ridge National Laboratory (ORNL) High-Flux Isotope Reactor. Power perturbations of less than 0.1 percent of the mean value in selected frequency ranges were detected by the pattern recognition system

  16. Two Challenges of Correct Validation in Pattern Recognition

    Directory of Open Access Journals (Sweden)

    Thomas eNowotny

    2014-09-01

    Full Text Available Supervised pattern recognition is the process of mapping patterns to class labelsthat define their meaning. The core methods for pattern recognitionhave been developed by machine learning experts but due to their broadsuccess an increasing number of non-experts are now employing andrefining them. In this perspective I will discuss the challenge ofcorrect validation of supervised pattern recognition systems, in particular whenemployed by non-experts. To illustrate the problem I will give threeexamples of common errors that I have encountered in the lastyear. Much of this challenge can be addressed by strict procedure invalidation but there are remaining problems of correctlyinterpreting comparative work on exemplary data sets, which I willelucidate on the example of the well-used MNIST data set of handwrittendigits.

  17. Hypothesis Support Mechanism for Mid-Level Visual Pattern Recognition

    Science.gov (United States)

    Amador, Jose J (Inventor)

    2007-01-01

    A method of mid-level pattern recognition provides for a pose invariant Hough Transform by parametrizing pairs of points in a pattern with respect to at least two reference points, thereby providing a parameter table that is scale- or rotation-invariant. A corresponding inverse transform may be applied to test hypothesized matches in an image and a distance transform utilized to quantify the level of match.

  18. An inverse problem approach to pattern recognition in industry

    Directory of Open Access Journals (Sweden)

    Ali Sever

    2015-01-01

    Full Text Available Many works have shown strong connections between learning and regularization techniques for ill-posed inverse problems. A careful analysis shows that a rigorous connection between learning and regularization for inverse problem is not straightforward. In this study, pattern recognition will be viewed as an ill-posed inverse problem and applications of methods from the theory of inverse problems to pattern recognition are studied. A new learning algorithm derived from a well-known regularization model is generated and applied to the task of reconstruction of an inhomogeneous object as pattern recognition. Particularly, it is demonstrated that pattern recognition can be reformulated in terms of inverse problems defined by a Riesz-type kernel. This reformulation can be employed to design a learning algorithm based on a numerical solution of a system of linear equations. Finally, numerical experiments have been carried out with synthetic experimental data considering a reasonable level of noise. Good recoveries have been achieved with this methodology, and the results of these simulations are compatible with the existing methods. The comparison results show that the Regularization-based learning algorithm (RBA obtains a promising performance on the majority of the test problems. In prospects, this method can be used for the creation of automated systems for diagnostics, testing, and control in various fields of scientific and applied research, as well as in industry.

  19. Pattern recognition receptors and the inflammasome in kidney disease

    NARCIS (Netherlands)

    Leemans, Jaklien C.; Kors, Lotte; Anders, Hans-Joachim; Florquin, Sandrine

    2014-01-01

    Toll-like receptors (TLRs) and nucleotide-binding oligomerization domain receptors (NLRs) are families of pattern recognition receptors that, together with inflammasomes, sense and respond to highly conserved pathogen motifs and endogenous molecules released upon cell damage or stress. Evidence

  20. Quantitative EEG Applying the Statistical Recognition Pattern Method

    DEFF Research Database (Denmark)

    Engedal, Knut; Snaedal, Jon; Hoegh, Peter

    2015-01-01

    BACKGROUND/AIM: The aim of this study was to examine the discriminatory power of quantitative EEG (qEEG) applying the statistical pattern recognition (SPR) method to separate Alzheimer's disease (AD) patients from elderly individuals without dementia and from other dementia patients. METHODS...

  1. Introduction of pattern recognition by MATLAB practice 2

    International Nuclear Information System (INIS)

    1999-06-01

    The contents of this book starts introduction and examples of pattern recognition. This book describes a vector and matrix, basic statistics and a probability distribution, statistical decision theory and probability density function, liner shunt, vector quantizing and clustering GMM, PCA and KL conversion, LDA, ID 3, a nerve cell modeling, HMM, SVM and Ada boost. It has direction of MATLAB in the appendix.

  2. Ultrasonic pattern recognition study of feedwater nozzle inner radius indication

    International Nuclear Information System (INIS)

    Yoneyama, H.; Takama, S.; Kishigami, M.; Sasahara, T.; Ando, H.

    1983-01-01

    A study was made to distinguish defects on feed-water nozzle inner radius from noise echo caused by stainless steel cladding by using ultrasonic pattern recognition method with frequency analysis technique. Experiment has been successfully performed on flat clad plates and nozzle mock-up containing fatigue cracks and the following results which shows the high capability of frequency analysis technique are obtained

  3. Pattern recognition approach to quantify the atomic structure of graphene

    DEFF Research Database (Denmark)

    Kling, Jens; Vestergaard, Jacob Schack; Dahl, Anders Bjorholm

    2014-01-01

    We report a pattern recognition approach to detect the atomic structure in high-resolution transmission electron microscopy images of graphene. The approach provides quantitative information such as carbon-carbon bond lengths and bond length variations on a global and local scale alike. © 2014...

  4. Statistical pattern recognition for automatic writer identification and verification

    NARCIS (Netherlands)

    Bulacu, Marius Lucian

    2007-01-01

    The thesis addresses the problem of automatic person identification using scanned images of handwriting.Identifying the author of a handwritten sample using automatic image-based methods is an interesting pattern recognition problem with direct applicability in the forensic and historic document

  5. Fringe patterns generated by micro-optical sensors for pattern recognition.

    Science.gov (United States)

    Tamee, Kreangsak; Chaiwong, Khomyuth; Yothapakdee, Kriengsak; Yupapin, Preecha P

    2015-01-01

    We present a new result of pattern recognition generation scheme using a small-scale optical muscle sensing system, which consisted of an optical add-drop filter incorporating two nonlinear optical side ring resonators. When light from laser source enters into the system, the device is stimulated by an external physical parameter that introduces a change in the phase of light propagation within the sensing device, which can be formed by the interference fringe patterns. Results obtained have shown that the fringe patterns can be used to form the relationship between signal patterns and fringe pattern recognitions.

  6. 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.

  7. 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.

  8. 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)

  9. Improvement of the detection response time of gas sensors using the association of artificial neural networks with pattern recognition technique; Amelioration de la reponse temporelle de capteurs de gaz par reconnaissance de forme a l'aide de reseaux de neurones

    Energy Technology Data Exchange (ETDEWEB)

    Bordieu, Ch.; Rebiere, D. [Bordeaux-1 Univ., Lab. IXL, UMR CNRS 5818, 33 (France); Pistre, J.; Planata, R. [Centre d' Etudes du Bouchet, 91 - Vert-le-Petit (France)

    1999-07-01

    The association of artificial neural networks (multilayer perceptrons) with a real time pattern recognition technique (shifting windows) allowed the development of systems for the detection and the quantification of gases. Shifting window technique is presented and offers an interesting way to improve the detection response time. The partial detector characterization with regard to its parameters was realized. Applications dealing with the detection of gas compounds using surface acoustic sensors permit to show the shifting window technique feasibility. (author)

  10. 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...

  11. Network ties in the international opportunity recognition of family SMEs

    OpenAIRE

    Kontinen, Tanja; Ojala, Arto

    2011-01-01

    The importance of network ties is emphasized in the current literature on opportunity recognition. However, it is unclear how firms with limited bridging networks, such as family SMEs, recognize international opportunities through their network ties. In this case study we found that in gaining foreign market entry, those family SMEs that lack existing network ties recognize opportunities through weak ties formed in international exhibitions. The findings also indicate that rather than being p...

  12. The cingulo-opercular network provides word-recognition benefit.

    Science.gov (United States)

    Vaden, Kenneth I; Kuchinsky, Stefanie E; Cute, Stephanie L; Ahlstrom, Jayne B; Dubno, Judy R; Eckert, Mark A

    2013-11-27

    Recognizing speech in difficult listening conditions requires considerable focus of attention that is often demonstrated by elevated activity in putative attention systems, including the cingulo-opercular network. We tested the prediction that elevated cingulo-opercular activity provides word-recognition benefit on a subsequent trial. Eighteen healthy, normal-hearing adults (10 females; aged 20-38 years) performed word recognition (120 trials) in multi-talker babble at +3 and +10 dB signal-to-noise ratios during a sparse sampling functional magnetic resonance imaging (fMRI) experiment. Blood oxygen level-dependent (BOLD) contrast was elevated in the anterior cingulate cortex, anterior insula, and frontal operculum in response to poorer speech intelligibility and response errors. These brain regions exhibited significantly greater correlated activity during word recognition compared with rest, supporting the premise that word-recognition demands increased the coherence of cingulo-opercular network activity. Consistent with an adaptive control network explanation, general linear mixed model analyses demonstrated that increased magnitude and extent of cingulo-opercular network activity was significantly associated with correct word recognition on subsequent trials. These results indicate that elevated cingulo-opercular network activity is not simply a reflection of poor performance or error but also supports word recognition in difficult listening conditions.

  13. A new concept of vertically integrated pattern recognition associative memory

    International Nuclear Information System (INIS)

    Liu, Ted; Hoff, Jim; Deptuch, Grzegorz; Yarema, Ray

    2011-01-01

    Hardware-based pattern recognition for fast triggering on particle tracks has been successfully used in high-energy physics experiments for some time. The CDF Silicon Vertex Trigger (SVT) at the Fermilab Tevatron is an excellent example. The method used there, developed in the 1990's, is based on algorithms that use a massively parallel associative memory architecture to identify patterns efficiently at high speed. However, due to much higher occupancy and event rates at the LHC, and the fact that the LHC detectors have a much larger number of channels in their tracking detectors, there is an enormous challenge in implementing fast pattern recognition for a track trigger, requiring about three orders of magnitude more associative memory patterns than what was used in the original CDF SVT. Scaling of current technologies is unlikely to satisfy the scientific needs of the future, and investments in transformational new technologies need to be made. In this paper, we will discuss a new concept of using the emerging 3D vertical integration technology to significantly advance the state-of-the-art for fast pattern recognition within and outside HEP. A generic R and D proposal based on this new concept, with a few institutions involved, has recently been submitted to DOE with the goal to design and perform the ASIC engineering necessary to realize a prototype device. The progress of this R and D project will be reported in the future. Here we will only focus on the concept of this new approach.

  14. Towards pattern understanding-new technologies beyond pattern recognition

    Energy Technology Data Exchange (ETDEWEB)

    Sakai, T

    1982-04-01

    The techniques employed in understanding-systems for pattern information are classified roughly under top-down and bottom-up techniques. These are outlined in the paper, and intellectual preparation for communications and information processing is briefly described. 1 ref.

  15. 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.

  16. 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.)

  17. New Digital Approach to CNN On-chip Implementation for Pattern Recognition

    OpenAIRE

    Durackova, Daniela

    2008-01-01

    We developed a novel simulator for the CNN using the program tool Visual Basic for Application. Its algorithm is based on the same principle as the planned designed circuit. The network can process the patterns with 400 point recognition. The created universal simulator can change various simulation parameters. We found that the rounding at multiplication is not as important as we previously expected. On the basis of the simulations we designed a novel digital CNN cell implemented on a chip. ...

  18. 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 ...

  19. 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.

  20. 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.

  1. Natural Cytotoxicity Receptors: Pattern Recognition and Involvement of Carbohydrates

    Directory of Open Access Journals (Sweden)

    Angel Porgador

    2005-01-01

    Full Text Available Natural cytotoxicity receptors (NCRs, expressed by natural killer (NK cells, trigger NK lysis of tumor and virus-infected cells on interaction with cell-surface ligands of these target cells. We have determined that viral hemagglutinins expressed on the surface of virus-infected cells are involved in the recognition by the NCRs, NKp44 and NKp46. Recognition of tumor cells by the NCRs NKp30 and NKp46 involves heparan sulfate epitopes expressed on the tumor cell membrane. Our studies provide new evidence for the identity of the ligands for NCRs and indicate that a broader definition should be applied to pathological patterns recognized by innate immune receptors. Since nonmicrobial endogenous carbohydrate structures contribute significantly to this recognition, there is an imperative need to develop appropriate tools for the facile sequencing of carbohydrate moieties.

  2. Running Improves Pattern Separation during Novel Object Recognition.

    Science.gov (United States)

    Bolz, Leoni; Heigele, Stefanie; Bischofberger, Josef

    2015-10-09

    Running increases adult neurogenesis and improves pattern separation in various memory tasks including context fear conditioning or touch-screen based spatial learning. However, it is unknown whether pattern separation is improved in spontaneous behavior, not emotionally biased by positive or negative reinforcement. Here we investigated the effect of voluntary running on pattern separation during novel object recognition in mice using relatively similar or substantially different objects.We show that running increases hippocampal neurogenesis but does not affect object recognition memory with 1.5 h delay after sample phase. By contrast, at 24 h delay, running significantly improves recognition memory for similar objects, whereas highly different objects can be distinguished by both, running and sedentary mice. These data show that physical exercise improves pattern separation, independent of negative or positive reinforcement. In sedentary mice there is a pronounced temporal gradient for remembering object details. In running mice, however, increased neurogenesis improves hippocampal coding and temporally preserves distinction of novel objects from familiar ones.

  3. Do pattern recognition skills transfer across sports? A preliminary analysis.

    Science.gov (United States)

    Smeeton, Nicholas J; Ward, Paul; Williams, A Mark

    2004-02-01

    The ability to recognize patterns of play is fundamental to performance in team sports. While typically assumed to be domain-specific, pattern recognition skills may transfer from one sport to another if similarities exist in the perceptual features and their relations and/or the strategies used to encode and retrieve relevant information. A transfer paradigm was employed to compare skilled and less skilled soccer, field hockey and volleyball players' pattern recognition skills. Participants viewed structured and unstructured action sequences from each sport, half of which were randomly represented with clips not previously seen. The task was to identify previously viewed action sequences quickly and accurately. Transfer of pattern recognition skill was dependent on the participant's skill, sport practised, nature of the task and degree of structure. The skilled soccer and hockey players were quicker than the skilled volleyball players at recognizing structured soccer and hockey action sequences. Performance differences were not observed on the structured volleyball trials between the skilled soccer, field hockey and volleyball players. The skilled field hockey and soccer players were able to transfer perceptual information or strategies between their respective sports. The less skilled participants' results were less clear. Implications for domain-specific expertise, transfer and diversity across domains are discussed.

  4. 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.

  5. Iris double recognition based on modified evolutionary neural network

    Science.gov (United States)

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

    2017-11-01

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

  6. Pattern Recognition-Based Analysis of COPD in CT

    DEFF Research Database (Denmark)

    Sørensen, Lauge Emil Borch Laurs

    recognition part is used to turn the texture measures, measured in a CT image of the lungs, into a quantitative measure of disease. This is done by applying a classifier that is trained on a training set of data examples with known lung tissue patterns. Different classification systems are considered, and we...... will in particular use the pattern recognition concepts of supervised learning, multiple instance learning, and dissimilarity representation-based classification. The proposed texture-based measures are applied to CT data from two different sources, one comprising low dose CT slices from subjects with manually...... annotated regions of emphysema and healthy tissue, and one comprising volumetric low dose CT images from subjects that are either healthy or suffer from COPD. Several experiments demonstrate that it is clearly beneficial to take the lung tissue texture into account when classifying or quantifying emphysema...

  7. 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.

  8. Linear Programming and Its Application to Pattern Recognition Problems

    Science.gov (United States)

    Omalley, M. J.

    1973-01-01

    Linear programming and linear programming like techniques as applied to pattern recognition problems are discussed. Three relatively recent research articles on such applications are summarized. The main results of each paper are described, indicating the theoretical tools needed to obtain them. A synopsis of the author's comments is presented with regard to the applicability or non-applicability of his methods to particular problems, including computational results wherever given.

  9. Pattern recognition as a method of data analysis

    Energy Technology Data Exchange (ETDEWEB)

    Caputo, M.

    1978-11-15

    The method of pattern recognition has been used in biological and social sciences and has been recently introduced for the solution of geological and geophysical problems such as oil and ore prospecting and seismological prediction. The method is briefly illustrated by an application to earthquake prediction in Italy in which topographic and geologic maps are used in conjunction with earthquake catalogs. 3 figures, 1 table.

  10. Neurocomputing methods for pattern recognition in nuclear physics

    Energy Technology Data Exchange (ETDEWEB)

    Gyulassy, M.; Dong, D.; Harlander, M. [Lawrence Berkeley Lab., CA (United States)

    1991-12-31

    We review recent progress on the development and applications of novel neurocomputing techniques for pattern recognition problems of relevance to RHIC experiments. The Elastic Tracking algorithm is shown to achieve sub-pad two track resolution without preprocessing. A high pass neural filter is developed for jet analysis and singular deconvolution methods are shown to recover the primordial jet distribution to a surprising high degree of accuracy.

  11. Spatial pattern recognition of seismic events in South West Colombia

    Science.gov (United States)

    Benítez, Hernán D.; Flórez, Juan F.; Duque, Diana P.; Benavides, Alberto; Lucía Baquero, Olga; Quintero, Jiber

    2013-09-01

    Recognition of seismogenic zones in geographical regions supports seismic hazard studies. This recognition is usually based on visual, qualitative and subjective analysis of data. Spatial pattern recognition provides a well founded means to obtain relevant information from large amounts of data. The purpose of this work is to identify and classify spatial patterns in instrumental data of the South West Colombian seismic database. In this research, clustering tendency analysis validates whether seismic database possesses a clustering structure. A non-supervised fuzzy clustering algorithm creates groups of seismic events. Given the sensitivity of fuzzy clustering algorithms to centroid initial positions, we proposed a methodology to initialize centroids that generates stable partitions with respect to centroid initialization. As a result of this work, a public software tool provides the user with the routines developed for clustering methodology. The analysis of the seismogenic zones obtained reveals meaningful spatial patterns in South-West Colombia. The clustering analysis provides a quantitative location and dispersion of seismogenic zones that facilitates seismological interpretations of seismic activities in South West Colombia.

  12. Conditional Random Fields for Pattern Recognition Applied to Structured Data

    Directory of Open Access Journals (Sweden)

    Tom Burr

    2015-07-01

    Full Text Available Pattern recognition uses measurements from an input domain, X, to predict their labels from an output domain, Y. Image analysis is one setting where one might want to infer whether a pixel patch contains an object that is “manmade” (such as a building or “natural” (such as a tree. Suppose the label for a pixel patch is “manmade”; if the label for a nearby pixel patch is then more likely to be “manmade” there is structure in the output domain that can be exploited to improve pattern recognition performance. Modeling P(X is difficult because features between parts of the model are often correlated. Therefore, conditional random fields (CRFs model structured data using the conditional distribution P(Y|X = x, without specifying a model for P(X, and are well suited for applications with dependent features. This paper has two parts. First, we overview CRFs and their application to pattern recognition in structured problems. Our primary examples are image analysis applications in which there is dependence among samples (pixel patches in the output domain. Second, we identify research topics and present numerical examples.

  13. Face recognition in securing optical telecom network equipment

    International Nuclear Information System (INIS)

    Ali, N.M.

    2015-01-01

    In this paper, face recognition is used with a microcontroller based hardware module to secure the telecommunication equipments like ONU (optical network units) or any other telecommunication equipment. The face recognition classifier value optimization adaption is deployed and in this scheme by increasing or decreasing the number of images in the database will automatically generate and adopt the classifier value for recognition of known and unknown persons. On recognizing and unknown persons. On recognizing an unknown person, the hardware module will send an SMS to the concerned security personnel for security preventive measures. (author)

  14. 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...

  15. 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.

  16. 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

  17. 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.

  18. A study on the extraction of feature variables for the pattern recognition for welding flaws

    International Nuclear Information System (INIS)

    Kim, J. Y.; Kim, C. H.; Kim, B. H.

    1996-01-01

    In this study, the researches classifying the artificial and natural flaws in welding parts are performed using the pattern recognition technology. For this purpose the signal pattern recognition package including the user defined function was developed and the total procedure including the digital signal processing, feature extraction, feature selection and classifier selection is treated by bulk. Specially it is composed with and discussed using the statistical classifier such as the linear discriminant function classifier, the empirical Bayesian classifier. Also, the pattern recognition technology is applied to classification problem of natural flaw(i.e multiple classification problem-crack, lack of penetration, lack of fusion, porosity, and slag inclusion, the planar and volumetric flaw classification problem). According to this results, if appropriately teamed the neural network classifier is better than stastical classifier in the classification problem of natural flaw. And it is possible to acquire the recognition rate of 80% above through it is different a little according to domain extracting the feature and the classifier.

  19. Double-Barrier Memristive Devices for Unsupervised Learning and Pattern Recognition.

    Science.gov (United States)

    Hansen, Mirko; Zahari, Finn; Ziegler, Martin; Kohlstedt, Hermann

    2017-01-01

    The use of interface-based resistive switching devices for neuromorphic computing is investigated. In a combined experimental and numerical study, the important device parameters and their impact on a neuromorphic pattern recognition system are studied. The memristive cells consist of a layer sequence Al/Al 2 O 3 /Nb x O y /Au and are fabricated on a 4-inch wafer. The key functional ingredients of the devices are a 1.3 nm thick Al 2 O 3 tunnel barrier and a 2.5 mm thick Nb x O y memristive layer. Voltage pulse measurements are used to study the electrical conditions for the emulation of synaptic functionality of single cells for later use in a recognition system. The results are evaluated and modeled in the framework of the plasticity model of Ziegler et al. Based on this model, which is matched to experimental data from 84 individual devices, the network performance with regard to yield, reliability, and variability is investigated numerically. As the network model, a computing scheme for pattern recognition and unsupervised learning based on the work of Querlioz et al. (2011), Sheridan et al. (2014), Zahari et al. (2015) is employed. This is a two-layer feedforward network with a crossbar array of memristive devices, leaky integrate-and-fire output neurons including a winner-takes-all strategy, and a stochastic coding scheme for the input pattern. As input pattern, the full data set of digits from the MNIST database is used. The numerical investigation indicates that the experimentally obtained yield, reliability, and variability of the memristive cells are suitable for such a network. Furthermore, evidence is presented that their strong I - V non-linearity might avoid the need for selector devices in crossbar array structures.

  20. Optical pattern recognition III; Proceedings of the Meeting, Orlando, FL, Apr. 21, 22, 1992

    Science.gov (United States)

    Casasent, David P. (Editor); Chao, Tien-Hsin (Editor)

    1992-01-01

    Consideration is given to transitioning of optical processing into systems (TOPS), optical correlator hardware, phase-only optical correlation filters, optical distortion-invariant correlation filters, and optical neural networks. Particular attention is given to a test target for optical correlators, a TOPS electronic warfare channelizer program, a portable video-rate optical correlator, a joint transform correlator employing electron trapping materials, a novelty filtered optical correlator using a photorefractive crystal, a comparison of correlation performance of smart ternary phase-amplitude filters with gray-scale and binary input scenes, real-time distortion-tolerant composite filters for automatic target identification, landscaping the correlation surface, fast designing of a circular harmonic filter using simulated annealing, feature-based correlation filters for distortion invariance, automatic target recognition using a feature-based optical neural network, and a holographic inner-product processor for pattern recognition.

  1. A new pattern associative memory model for image recognition based on Hebb rules and dot product

    Science.gov (United States)

    Gao, Mingyue; Deng, Limiao; Wang, Yanjiang

    2018-04-01

    A great number of associative memory models have been proposed to realize information storage and retrieval inspired by human brain in the last few years. However, there is still much room for improvement for those models. In this paper, we extend a binary pattern associative memory model to accomplish real-world image recognition. The learning process is based on the fundamental Hebb rules and the retrieval is implemented by a normalized dot product operation. Our proposed model can not only fulfill rapid memory storage and retrieval for visual information but also have the ability on incremental learning without destroying the previous learned information. Experimental results demonstrate that our model outperforms the existing Self-Organizing Incremental Neural Network (SOINN) and Back Propagation Neuron Network (BPNN) on recognition accuracy and time efficiency.

  2. Do subitizing deficits in developmental dyscalculia involve pattern recognition weakness?

    Science.gov (United States)

    Ashkenazi, Sarit; Mark-Zigdon, Nitza; Henik, Avishai

    2013-01-01

    The abilities of children diagnosed with developmental dyscalculia (DD) were examined in two types of object enumeration: subitizing, and small estimation (5-9 dots). Subitizing is usually defined as a fast and accurate assessment of a number of small dots (range 1 to 4 dots), and estimation is an imprecise process to assess a large number of items (range 5 dots or more). Based on reaction time (RT) and accuracy analysis, our results indicated a deficit in the subitizing and small estimation range among DD participants in relation to controls. There are indications that subitizing is based on pattern recognition, thus presenting dots in a canonical shape in the estimation range should result in a subitizing-like pattern. In line with this theory, our control group presented a subitizing-like pattern in the small estimation range for canonically arranged dots, whereas the DD participants presented a deficit in the estimation of canonically arranged dots. The present finding indicates that pattern recognition difficulties may play a significant role in both subitizing and subitizing deficits among those with DD. © 2012 Blackwell Publishing Ltd.

  3. 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.

  4. Application of ann-based decision making pattern recognition to fishing operations

    Energy Technology Data Exchange (ETDEWEB)

    Akhlaghinia, M.; Torabi, F.; Wilton, R.R. [University of Regina, Saskatchewan (Canada). Faculty of Engineering. Dept. of Petroleum Engineering], e-mail: Farshid.Torabi@uregina.ca

    2010-10-15

    Decision making is a crucial part of fishing operations. Proper decisions should be made to prevent wasted time and associated costs on unsuccessful operations. This paper presents a novel model to help drilling managers decide when to commence and when to quit a fishing operation. A decision making model based on Artificial Neural Network (ANN) has been developed that utilizes Pattern Recognition based on 181 fishing incidents from one of the most fish-prone fields of the southwest of Iran. All parameters chosen to train the ANN-Based Pattern Recognition Tool are assumed to play a role in the success of the fishing operation and are therefore used to decide whether a fishing operation should be performed or not. If the tool deems the operation suitable for consideration, a cost analysis of the fishing operation can then be performed to justify its overall cost. (author)

  5. Learning-induced pattern classification in a chaotic neural network

    International Nuclear Information System (INIS)

    Li, Yang; Zhu, Ping; Xie, Xiaoping; He, Guoguang; Aihara, Kazuyuki

    2012-01-01

    In this Letter, we propose a Hebbian learning rule with passive forgetting (HLRPF) for use in a chaotic neural network (CNN). We then define the indices based on the Euclidean distance to investigate the evolution of the weights in a simplified way. Numerical simulations demonstrate that, under suitable external stimulations, the CNN with the proposed HLRPF acts as a fuzzy-like pattern classifier that performs much better than an ordinary CNN. The results imply relationship between learning and recognition. -- Highlights: ► Proposing a Hebbian learning rule with passive forgetting (HLRPF). ► Defining indices to investigate the evolution of the weights simply. ► The chaotic neural network with HLRPF acts as a fuzzy-like pattern classifier. ► The pattern classifier ability of the network is improved much.

  6. Multivariate statistical pattern recognition system for reactor noise analysis

    International Nuclear Information System (INIS)

    Gonzalez, R.C.; Howington, L.C.; Sides, W.H. Jr.; Kryter, R.C.

    1976-01-01

    A multivariate statistical pattern recognition system for reactor noise analysis was developed. The basis of the system is a transformation for decoupling correlated variables and algorithms for inferring probability density functions. The system is adaptable to a variety of statistical properties of the data, and it has learning, tracking, and updating capabilities. System design emphasizes control of the false-alarm rate. The ability of the system to learn normal patterns of reactor behavior and to recognize deviations from these patterns was evaluated by experiments at the ORNL High-Flux Isotope Reactor (HFIR). Power perturbations of less than 0.1 percent of the mean value in selected frequency ranges were detected by the system

  7. Multivariate statistical pattern recognition system for reactor noise analysis

    International Nuclear Information System (INIS)

    Gonzalez, R.C.; Howington, L.C.; Sides, W.H. Jr.; Kryter, R.C.

    1975-01-01

    A multivariate statistical pattern recognition system for reactor noise analysis was developed. The basis of the system is a transformation for decoupling correlated variables and algorithms for inferring probability density functions. The system is adaptable to a variety of statistical properties of the data, and it has learning, tracking, and updating capabilities. System design emphasizes control of the false-alarm rate. The ability of the system to learn normal patterns of reactor behavior and to recognize deviations from these patterns was evaluated by experiments at the ORNL High-Flux Isotope Reactor (HFIR). Power perturbations of less than 0.1 percent of the mean value in selected frequency ranges were detected by the system. 19 references

  8. Pattern recognition trigger electronics for an imaging atmospheric Cherenkov telescope

    International Nuclear Information System (INIS)

    Bradbury, S.M.; Rose, H.J.

    2002-01-01

    For imaging atmospheric Cherenkov telescopes, which aim to detect electromagnetic air showers with cameras consisting of several hundred photomultiplier pixels, the single pixel trigger rate is dominated by fluctuations in night sky brightness and by ion feedback in the photomultipliers. Pattern recognition trigger electronics may be used to reject night sky background images, thus reducing the data rate to a manageable level. The trigger system described here detects patterns of 2, 3 or 4 adjacent pixel signals within a 331 pixel camera and gives a positive trigger decision in 65 ns. The candidate pixel pattern is compared with the contents of a pre-programmed memory. With the trigger decision timing controlled by a fixed delay the time-jitter inherent in the use of programmable gate arrays is avoided. This system is now in routine operation at the Whipple 10 m Telescope

  9. Human recognition in a video network

    Science.gov (United States)

    Bhanu, Bir

    2009-10-01

    Video networks is an emerging interdisciplinary field with significant and exciting scientific and technological challenges. It has great promise in solving many real-world problems and enabling a broad range of applications, including smart homes, video surveillance, environment and traffic monitoring, elderly care, intelligent environments, and entertainment in public and private spaces. This paper provides an overview of the design of a wireless video network as an experimental environment, camera selection, hand-off and control, anomaly detection. It addresses challenging questions for individual identification using gait and face at a distance and present new techniques and their comparison for robust identification.

  10. 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.

  11. Stimulated Deep Neural Network for Speech Recognition

    Science.gov (United States)

    2016-09-08

    similarities. As illustrated in Figure 1(b), the network grid behaves as a smooth surface on each layer of a stimulated DNN. The nearby nodes in the...for HTK version 3.5),” 2015. [19] S. Tranter, M. Gales, R. Sinha, S. Umesh, and P. Woodland, “The development of the Cambridge University RT-04

  12. 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

  13. 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.

  14. The DELPHI Silicon Tracker in the global pattern recognition

    CERN Document Server

    Elsing, M

    2000-01-01

    ALEPH and DELPHI were the first experiments operating a silicon vertex detector at LEP. During the past 10 years of data taking the DELPHI Silicon Tracker was upgraded three times to follow the different tracking requirements for LEP 1 and LEP 2 as well as to improve the tracking performance. Several steps in the development of the pattern recognition software were done in order to understand and fully exploit the silicon tracker information. This article gives an overview of the final algorithms and concepts of the track reconstruction using the Silicon Tracker in DELPHI.

  15. 6th International Conference on Pattern Recognition and Machine Intelligence

    CERN Document Server

    Gawrysiak, Piotr; Kryszkiewicz, Marzena; Rybiński, Henryk

    2016-01-01

    This book presents valuable contributions devoted to practical applications of Machine Intelligence and Big Data in various branches of the industry. All the contributions are extended versions of presentations delivered at the Industrial Session the 6th International Conference on Pattern Recognition and Machine Intelligence (PREMI 2015) held in Warsaw, Poland at June 30- July 3, 2015, which passed through a rigorous reviewing process. The contributions address real world problems and show innovative solutions used to solve them. This volume will serve as a bridge between researchers and practitioners, as well as between different industry branches, which can benefit from sharing ideas and results.

  16. Compact holographic memory and its application to optical pattern recognition

    Science.gov (United States)

    Chao, Tien-Hsin; Reyes, George F.; Zhou, Hanying

    2001-03-01

    JPL is developing a high-density, nonvolatile Compact Holographic Data Storage (CHDS) system to enable large- capacity, high-speed, low power consumption, and read/write of data for commercial and space applications. This CHDS system consists of laser diodes, photorefractive crystal, spatial light modulator, photodetector array, and I/O electronic interface. In operation, pages of information would be recorded and retrieved with random access and high- speed. In this paper, recent technology progress in developing this CHDS at JPL will be presented. The recent applications of the CHDS to optical pattern recognition, as a high-density, high transfer rate memory bank will also be discussed.

  17. Infrared target recognition based on improved joint local ternary pattern

    Science.gov (United States)

    Sun, Junding; Wu, Xiaosheng

    2016-05-01

    This paper presents a simple, efficient, yet robust approach, named joint orthogonal combination of local ternary pattern, for automatic forward-looking infrared target recognition. It gives more advantages to describe the macroscopic textures and microscopic textures by fusing variety of scales than the traditional LBP-based methods. In addition, it can effectively reduce the feature dimensionality. Further, the rotation invariant and uniform scheme, the robust LTP, and soft concave-convex partition are introduced to enhance its discriminative power. Experimental results demonstrate that the proposed method can achieve competitive results compared with the state-of-the-art methods.

  18. The DELPHI Silicon Tracker in the global pattern recognition

    International Nuclear Information System (INIS)

    Elsing, M.

    2000-01-01

    ALEPH and DELPHI were the first experiments operating a silicon vertex detector at LEP. During the past 10 years of data taking the DELPHI Silicon Tracker was upgraded three times to follow the different tracking requirements for LEP 1 and LEP 2 as well as to improve the tracking performance. Several steps in the development of the pattern recognition software were done in order to understand and fully exploit the silicon tracker information. This article gives an overview of the final algorithms and concepts of the track reconstruction using the Silicon Tracker in DELPHI

  19. 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.

  20. Artificial intelligence for networks recognition in remote sensing images

    Science.gov (United States)

    Gilliot, Jean-Marc; Amat, Jean-Louis

    1993-12-01

    We describe here a knowledge-based system, NEXSYS (Nextwork EXtraction SYStem) which was designed for the recognition of communication networks in SPOT satellite images. NEXSYS is a frame-based system and uses a co-operative and distributed structure based on a blackboard architecture. Communication networks in SPOT images are composed of thin linear segments. Segments are extracted using mathematical morphology and a Hough transform. An intermediate image representation composed of geometric primitives is obtained. Then an expert module is able to process the segments at the symbolic level trying to recognize networks.

  1. Topology Recognition and Leader Election in Colored Networks

    OpenAIRE

    Dereniowski, Dariusz; Pelc, Andrzej

    2016-01-01

    Topology recognition and leader election are fundamental tasks in distributed computing in networks. The first of them requires each node to find a labeled isomorphic copy of the network, while the result of the second one consists in a single node adopting the label 1 (leader), with all other nodes adopting the label 0 and learning a path to the leader. We consider both these problems in networks whose nodes are equipped with not necessarily distinct labels called colors, and ports at each n...

  2. Automated, high accuracy classification of Parkinsonian disorders: a pattern recognition approach.

    Directory of Open Access Journals (Sweden)

    Andre F Marquand

    Full Text Available Progressive supranuclear palsy (PSP, multiple system atrophy (MSA and idiopathic Parkinson's disease (IPD can be clinically indistinguishable, especially in the early stages, despite distinct patterns of molecular pathology. Structural neuroimaging holds promise for providing objective biomarkers for discriminating these diseases at the single subject level but all studies to date have reported incomplete separation of disease groups. In this study, we employed multi-class pattern recognition to assess the value of anatomical patterns derived from a widely available structural neuroimaging sequence for automated classification of these disorders. To achieve this, 17 patients with PSP, 14 with IPD and 19 with MSA were scanned using structural MRI along with 19 healthy controls (HCs. An advanced probabilistic pattern recognition approach was employed to evaluate the diagnostic value of several pre-defined anatomical patterns for discriminating the disorders, including: (i a subcortical motor network; (ii each of its component regions and (iii the whole brain. All disease groups could be discriminated simultaneously with high accuracy using the subcortical motor network. The region providing the most accurate predictions overall was the midbrain/brainstem, which discriminated all disease groups from one another and from HCs. The subcortical network also produced more accurate predictions than the whole brain and all of its constituent regions. PSP was accurately predicted from the midbrain/brainstem, cerebellum and all basal ganglia compartments; MSA from the midbrain/brainstem and cerebellum and IPD from the midbrain/brainstem only. This study demonstrates that automated analysis of structural MRI can accurately predict diagnosis in individual patients with Parkinsonian disorders, and identifies distinct patterns of regional atrophy particularly useful for this process.

  3. 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.

  4. 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.

  5. Pattern recognition in menstrual bleeding diaries by statistical cluster analysis

    Directory of Open Access Journals (Sweden)

    Wessel Jens

    2009-07-01

    Full Text Available Abstract Background The aim of this paper is to empirically identify a treatment-independent statistical method to describe clinically relevant bleeding patterns by using bleeding diaries of clinical studies on various sex hormone containing drugs. Methods We used the four cluster analysis methods single, average and complete linkage as well as the method of Ward for the pattern recognition in menstrual bleeding diaries. The optimal number of clusters was determined using the semi-partial R2, the cubic cluster criterion, the pseudo-F- and the pseudo-t2-statistic. Finally, the interpretability of the results from a gynecological point of view was assessed. Results The method of Ward yielded distinct clusters of the bleeding diaries. The other methods successively chained the observations into one cluster. The optimal number of distinctive bleeding patterns was six. We found two desirable and four undesirable bleeding patterns. Cyclic and non cyclic bleeding patterns were well separated. Conclusion Using this cluster analysis with the method of Ward medications and devices having an impact on bleeding can be easily compared and categorized.

  6. 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

  7. 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.

  8. Inductive class representation and its central role in pattern recognition

    Energy Technology Data Exchange (ETDEWEB)

    Goldfarb, L. [Univ. of New Brunswick, Fredericton, New Brunswick (Canada)

    1996-12-31

    The definition of inductive learning (IL) based on the new concept of inductive class representation (ICR) is given. The ICR, in addition to the ability to recognize a noise-corrupted object from the class, must also provide the means to generate every element in the resulting approximation of the class, i.e., the emphasis is on the generative capability of the ICR. Thus, the IL problem absorbs the main difficulties associated with a satisfactory formulation of the pattern recognition problem. This formulation of the IL problem appeared gradually as a result of the development of a fundamentally new formal model of IL--evolving transformation system (ETS) model. The model with striking clarity suggests that IL is the basic process which produces all the necessary {open_quotes}structures{close_quotes} for the recognition process, which is built directly on top of it. Based on the training set, the IL process, constructs optimal discriminatory (symbolic) weighted {open_quotes}features{close_quotes} which induce the corresponding optimal (symbolic) distance measure. The distance measure is a generalization of the weighted Levenshtein, or edit, distance defined on strings over a finite alphabet. The ETS model has emerged as a result of an attempt to unify two basic, but inadequate, approaches to pattern recognition: the classical vector space based and the syntactic approaches. ETS also elucidates with remarkable clarity the nature of the interrelationships between the corresponding symbolic and numeric mechanisms, in which the symbolic mechanisms play a more fundamental part. The model, in fact, suggests the first formal definition of the symbolic mathematical structure and also suggests a fundamentally different, more satisfactory, way of introducing the concept of fuzziness. The importance of the ICR concept to semiotics and semantics should become apparent as soon as one fully realizes that it represents the class and specifies the semantics of the class.

  9. Wavelet-based moment invariants for pattern recognition

    Science.gov (United States)

    Chen, Guangyi; Xie, Wenfang

    2011-07-01

    Moment invariants have received a lot of attention as features for identification and inspection of two-dimensional shapes. In this paper, two sets of novel moments are proposed by using the auto-correlation of wavelet functions and the dual-tree complex wavelet functions. It is well known that the wavelet transform lacks the property of shift invariance. A little shift in the input signal will cause very different output wavelet coefficients. The autocorrelation of wavelet functions and the dual-tree complex wavelet functions, on the other hand, are shift-invariant, which is very important in pattern recognition. Rotation invariance is the major concern in this paper, while translation invariance and scale invariance can be achieved by standard normalization techniques. The Gaussian white noise is added to the noise-free images and the noise levels vary with different signal-to-noise ratios. Experimental results conducted in this paper show that the proposed wavelet-based moments outperform Zernike's moments and the Fourier-wavelet descriptor for pattern recognition under different rotation angles and different noise levels. It can be seen that the proposed wavelet-based moments can do an excellent job even when the noise levels are very high.

  10. A pattern recognition approach to transistor array parameter variance

    Science.gov (United States)

    da F. Costa, Luciano; Silva, Filipi N.; Comin, Cesar H.

    2018-06-01

    The properties of semiconductor devices, including bipolar junction transistors (BJTs), are known to vary substantially in terms of their parameters. In this work, an experimental approach, including pattern recognition concepts and methods such as principal component analysis (PCA) and linear discriminant analysis (LDA), was used to experimentally investigate the variation among BJTs belonging to integrated circuits known as transistor arrays. It was shown that a good deal of the devices variance can be captured using only two PCA axes. It was also verified that, though substantially small variation of parameters is observed for BJT from the same array, larger variation arises between BJTs from distinct arrays, suggesting the consideration of device characteristics in more critical analog designs. As a consequence of its supervised nature, LDA was able to provide a substantial separation of the BJT into clusters, corresponding to each transistor array. In addition, the LDA mapping into two dimensions revealed a clear relationship between the considered measurements. Interestingly, a specific mapping suggested by the PCA, involving the total harmonic distortion variation expressed in terms of the average voltage gain, yielded an even better separation between the transistor array clusters. All in all, this work yielded interesting results from both semiconductor engineering and pattern recognition perspectives.

  11. 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.

  12. Recognition of Gestures using Artifical Neural Network

    Directory of Open Access Journals (Sweden)

    Marcel MORE

    2013-12-01

    Full Text Available Sensors for motion measurements are now becoming more widespread. Thanks to their parameters and affordability they are already used not only in the professional sector, but also in devices intended for daily use or entertainment. One of their applications is in control of devices by gestures. Systems that can determine type of gesture from measured motion have many uses. Some are for example in medical practice, but they are still more often used in devices such as cell phones, where they serve as a non-standard form of input. Today there are already several approaches for solving this problem, but building sufficiently reliable system is still a challenging task. In our project we are developing solution based on artificial neural network. In difference to other solutions, this one doesn’t require building model for each measuring system and thus it can be used in combination with various sensors just with minimal changes in his structure.

  13. Computational intelligence in multi-feature visual pattern recognition hand posture and face recognition using biologically inspired approaches

    CERN Document Server

    Pisharady, Pramod Kumar; Poh, Loh Ai

    2014-01-01

    This book presents a collection of computational intelligence algorithms that addresses issues in visual pattern recognition such as high computational complexity, abundance of pattern features, sensitivity to size and shape variations and poor performance against complex backgrounds. The book has 3 parts. Part 1 describes various research issues in the field with a survey of the related literature. Part 2 presents computational intelligence based algorithms for feature selection and classification. The algorithms are discriminative and fast. The main application area considered is hand posture recognition. The book also discusses utility of these algorithms in other visual as well as non-visual pattern recognition tasks including face recognition, general object recognition and cancer / tumor classification. Part 3 presents biologically inspired algorithms for feature extraction. The visual cortex model based features discussed have invariance with respect to appearance and size of the hand, and provide good...

  14. 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.

  15. On the Relevance of Using Bayesian Belief Networks in Wireless Sensor Networks Situation Recognition

    Directory of Open Access Journals (Sweden)

    Marco Zennaro

    2010-12-01

    Full Text Available Achieving situation recognition in ubiquitous sensor networks (USNs is an important issue that has been poorly addressed by both the research and practitioner communities. This paper describes some steps taken to address this issue by effecting USN middleware intelligence using an emerging situation awareness (ESA technology. We propose a situation recognition framework where temporal probabilistic reasoning is used to derive and emerge situation awareness in ubiquitous sensor networks. Using data collected from an outdoor environment monitoring in the city of Cape Town, we illustrate the use of the ESA technology in terms of sensor system operating conditions and environmental situation recognition.

  16. ALBEDO PATTERN RECOGNITION AND TIME-SERIES ANALYSES IN MALAYSIA

    Directory of Open Access Journals (Sweden)

    S. A. Salleh

    2012-07-01

    Full Text Available Pattern recognition and time-series analyses will enable one to evaluate and generate predictions of specific phenomena. The albedo pattern and time-series analyses are very much useful especially in relation to climate condition monitoring. This study is conducted to seek for Malaysia albedo pattern changes. The pattern recognition and changes will be useful for variety of environmental and climate monitoring researches such as carbon budgeting and aerosol mapping. The 10 years (2000–2009 MODIS satellite images were used for the analyses and interpretation. These images were being processed using ERDAS Imagine remote sensing software, ArcGIS 9.3, the 6S code for atmospherical calibration and several MODIS tools (MRT, HDF2GIS, Albedo tools. There are several methods for time-series analyses were explored, this paper demonstrates trends and seasonal time-series analyses using converted HDF format MODIS MCD43A3 albedo land product. The results revealed significance changes of albedo percentages over the past 10 years and the pattern with regards to Malaysia's nebulosity index (NI and aerosol optical depth (AOD. There is noticeable trend can be identified with regards to its maximum and minimum value of the albedo. The rise and fall of the line graph show a similar trend with regards to its daily observation. The different can be identified in term of the value or percentage of rises and falls of albedo. Thus, it can be concludes that the temporal behavior of land surface albedo in Malaysia have a uniform behaviours and effects with regards to the local monsoons. However, although the average albedo shows linear trend with nebulosity index, the pattern changes of albedo with respects to the nebulosity index indicates that there are external factors that implicates the albedo values, as the sky conditions and its diffusion plotted does not have uniform trend over the years, especially when the trend of 5 years interval is examined, 2000 shows high

  17. Implementation theory of distortion-invariant pattern recognition for optical and digital signal processing systems

    Science.gov (United States)

    Lhamon, Michael Earl

    A pattern recognition system which uses complex correlation filter banks requires proportionally more computational effort than single-real valued filters. This introduces increased computation burden but also introduces a higher level of parallelism, that common computing platforms fail to identify. As a result, we consider algorithm mapping to both optical and digital processors. For digital implementation, we develop computationally efficient pattern recognition algorithms, referred to as, vector inner product operators that require less computational effort than traditional fast Fourier methods. These algorithms do not need correlation and they map readily onto parallel digital architectures, which imply new architectures for optical processors. These filters exploit circulant-symmetric matrix structures of the training set data representing a variety of distortions. By using the same mathematical basis as with the vector inner product operations, we are able to extend the capabilities of more traditional correlation filtering to what we refer to as "Super Images". These "Super Images" are used to morphologically transform a complicated input scene into a predetermined dot pattern. The orientation of the dot pattern is related to the rotational distortion of the object of interest. The optical implementation of "Super Images" yields feature reduction necessary for using other techniques, such as artificial neural networks. We propose a parallel digital signal processor architecture based on specific pattern recognition algorithms but general enough to be applicable to other similar problems. Such an architecture is classified as a data flow architecture. Instead of mapping an algorithm to an architecture, we propose mapping the DSP architecture to a class of pattern recognition algorithms. Today's optical processing systems have difficulties implementing full complex filter structures. Typically, optical systems (like the 4f correlators) are limited to phase

  18. 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.

  19. 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.

  20. 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.

  1. Nonlinear dynamics of pattern formation and pattern recognition in the rabbit olfactory bulb

    Science.gov (United States)

    Baird, Bill

    1986-10-01

    A mathematical model of the process of pattern recognition in the first olfactory sensory cortex of the rabbit is presented. It explains the formation and alteration of spatial patterns in neural activity observed experimentally during classical Pavlovian conditioning. On each inspiration of the animal, a surge of receptor input enters the olfactory bulb. EEG activity recorded at the surface of the bulb undergoes a transition from a low amplitude background state of temporal disorder to coherent oscillation. There is a distinctive spatial pattern of rms amplitude in this oscillation which changes reliably to a second pattern during each successful recognition by the animal of a conditioned stimulus odor. When a new odor is paired as conditioned stimulus, these patterns are replaced by new patterns that stabilize as the animal adapts to the new environment. I will argue that a unification of the theories of pattern formation and associative memory is required to account for these observations. This is achieved in a model of the bulb as a discrete excitable medium with spatially inhomogeneous coupling expressed by a connection matrix. The theory of multiple Hopf bifurcations is employed to find coupled equations for the amplitudes of competing unstable oscillatory modes. These may be created in the system by proper coupling and selectively evoked by specific classes of inputs. This allows a view of limit cycle attractors as “stored” fixed points of a gradient vector field and thereby recovers the more familiar dynamical systems picture of associative memory.

  2. 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.

  3. 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

  4. 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.

  5. 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.

  6. Low, slow, small target recognition based on spatial vision network

    Science.gov (United States)

    Cheng, Zhao; Guo, Pei; Qi, Xin

    2018-03-01

    Traditional photoelectric monitoring is monitored using a large number of identical cameras. In order to ensure the full coverage of the monitoring area, this monitoring method uses more cameras, which leads to more monitoring and repetition areas, and higher costs, resulting in more waste. In order to reduce the monitoring cost and solve the difficult problem of finding, identifying and tracking a low altitude, slow speed and small target, this paper presents spatial vision network for low-slow-small targets recognition. Based on camera imaging principle and monitoring model, spatial vision network is modeled and optimized. Simulation experiment results demonstrate that the proposed method has good performance.

  7. 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.

  8. 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.

  9. ISOLATED SPEECH RECOGNITION SYSTEM FOR TAMIL LANGUAGE USING STATISTICAL PATTERN MATCHING AND MACHINE LEARNING TECHNIQUES

    Directory of Open Access Journals (Sweden)

    VIMALA C.

    2015-05-01

    Full Text Available In recent years, speech technology has become a vital part of our daily lives. Various techniques have been proposed for developing Automatic Speech Recognition (ASR system and have achieved great success in many applications. Among them, Template Matching techniques like Dynamic Time Warping (DTW, Statistical Pattern Matching techniques such as Hidden Markov Model (HMM and Gaussian Mixture Models (GMM, Machine Learning techniques such as Neural Networks (NN, Support Vector Machine (SVM, and Decision Trees (DT are most popular. The main objective of this paper is to design and develop a speaker-independent isolated speech recognition system for Tamil language using the above speech recognition techniques. The background of ASR system, the steps involved in ASR, merits and demerits of the conventional and machine learning algorithms and the observations made based on the experiments are presented in this paper. For the above developed system, highest word recognition accuracy is achieved with HMM technique. It offered 100% accuracy during training process and 97.92% for testing process.

  10. Pattern recognition issues on anisotropic smoothed particle hydrodynamics

    Science.gov (United States)

    Pereira Marinho, Eraldo

    2014-03-01

    This is a preliminary theoretical discussion on the computational requirements of the state of the art smoothed particle hydrodynamics (SPH) from the optics of pattern recognition and artificial intelligence. It is pointed out in the present paper that, when including anisotropy detection to improve resolution on shock layer, SPH is a very peculiar case of unsupervised machine learning. On the other hand, the free particle nature of SPH opens an opportunity for artificial intelligence to study particles as agents acting in a collaborative framework in which the timed outcomes of a fluid simulation forms a large knowledge base, which might be very attractive in computational astrophysics phenomenological problems like self-propagating star formation.

  11. Pattern recognition issues on anisotropic smoothed particle hydrodynamics

    International Nuclear Information System (INIS)

    Marinho, Eraldo Pereira

    2014-01-01

    This is a preliminary theoretical discussion on the computational requirements of the state of the art smoothed particle hydrodynamics (SPH) from the optics of pattern recognition and artificial intelligence. It is pointed out in the present paper that, when including anisotropy detection to improve resolution on shock layer, SPH is a very peculiar case of unsupervised machine learning. On the other hand, the free particle nature of SPH opens an opportunity for artificial intelligence to study particles as agents acting in a collaborative framework in which the timed outcomes of a fluid simulation forms a large knowledge base, which might be very attractive in computational astrophysics phenomenological problems like self-propagating star formation

  12. Terahertz Imaging for Biomedical Applications Pattern Recognition and Tomographic Reconstruction

    CERN Document Server

    Yin, Xiaoxia; Abbott, Derek

    2012-01-01

    Terahertz Imaging for Biomedical Applications: Pattern Recognition and Tomographic Reconstruction presents the necessary algorithms needed to assist screening, diagnosis, and treatment, and these algorithms will play a critical role in the accurate detection of abnormalities present in biomedical imaging. Terahertz biomedical imaging has become an area of interest due to its ability to simultaneously acquire both image and spectral information. Terahertz imaging systems are being commercialized with an increasing number of trials performed in a biomedical setting. Terahertz tomographic imaging and detection technology contributes to the ability to identify opaque objects with clear boundaries,and would be useful to both in vivo and ex vivo environments. This book also: Introduces terahertz radiation techniques and provides a number of topical examples of signal and image processing, as well as machine learning Presents the most recent developments in an emerging field, terahertz radiation Utilizes new methods...

  13. Pattern recognition and reconstruction on a FPGA coprocessor board

    CERN Document Server

    Männer, R; Simmler, H

    2000-01-01

    High energy accelerator labs use huge detector systems to track particles. The ATLAS detector at CERN, Geneva (Switzerland), will provide complex three-dimensional images. A trigger system at the detector output is used to reduce the amount of data to a manageable size. Each trigger applies certain filter algorithms to select the very rare physically interesting events. The algorithm presented, processes data from a special detector called TRT, to generate a trigger decision within approximately=10 ms. System supervisors then decide together with other results whether the event will be rejected or passed to the next trigger level. Due to the restricted execution time for calculating the decision, fast pattern recognition algorithms are required. These algorithms require a high I/O bandwidth and high computing power. These reasons and the high degree of parallelism make it best suited for custom computing machines. (3 refs).

  14. Pattern Recognition and Natural Language Processing: State of the Art

    Directory of Open Access Journals (Sweden)

    Mirjana Kocaleva

    2016-05-01

    Full Text Available Development of information technologies is growing steadily. With the latest software technologies development and application of the methods of artificial intelligence and machine learning intelligence embededs in computers, the expectations are that in near future computers will be able to solve problems themselves like people do. Artificial intelligence emulates human behavior on computers. Rather than executing instructions one by one, as theyare programmed, machine learning employs prior experience/data that is used in the process of system’s training. In this state of the art paper, common methods in AI, such as machine learning, pattern recognition and the natural language processing (NLP are discussed. Also are given standard architecture of NLP processing system and the level thatisneeded for understanding NLP. Lastly the statistical NLP processing and multi-word expressions are described.

  15. Distorted Pattern Recognition and Analysis with the Help of IEf Graph Representation

    Directory of Open Access Journals (Sweden)

    Adam Sedziwy

    2002-01-01

    Full Text Available An algorithm for distorted pattern recognition is presented. lt's generalization of M Flasinski results (Pattern Recognition, 27, 1-16, 1992. A new formalism allows to make both qualitative and quantitive distortion analysis. It also enlarges parser flexibility by extending the set of patterns which may be recognized.

  16. Application of PSO for solving problems of pattern recognition

    Directory of Open Access Journals (Sweden)

    S. N. Chukanov

    2016-01-01

    Full Text Available The problem of estimating the norm of the distance between the two closed smooth curves for pattern recognition is considered. Diffeomorphic transformation curves based on the model of large deformation with the transformation of the starting points of domain in required is formed on the basis of which depends on time-dependent vector field of velocity is considered. The action of the translation, rotation and scaling closed curve, the invariants of the action of these groups are considered. The position of curves is normalized by centering, bringing the principal axes of the image to the axes of the coordinate system and bringing the area of a closed curve corresponding to one. For estimating of the norm of the distance between two closed curves is formed the functional corresponding normalized distance between the two curves, and the equation of evolution diffeomorphic transformations. The equation of evolution allows to move objects along trajectories which correspond to diffeomorphic transformations. The diffeomorphisms do not change the topology along the geodesic trajectories. The problem of inexact comparing the minimized functional contains a term that estimates the exactness of shooting points in the required positions. In the equation of evolution is introduced the variance of conversion error. An algorithm for solving the equation of diffeomorphic transformation is proposed, built on the basis of PSO, which can significantly reduce the number of computing operations, compared with gradient methods for solving. The developed algorithms can be used in bioinformatics and biometrics systems, classification of images and objects, machine vision systems, neuroimaging, for pattern recognition and object tracking systems. Algorithm for estimating the norm of distance between the closed curves by diffeomorphic transformation can spread to spatial objects (curves, surfaces, manifolds.

  17. Proposal for the development of 3D Vertically Integrated Pattern Recognition Associative Memory (VIPRAM)

    Energy Technology Data Exchange (ETDEWEB)

    Deptuch, Gregory; Hoff, Jim; Kwan, Simon; Lipton, Ron; Liu, Ted; Ramberg, Erik; Todri, Aida; Yarema, Ray; /Fermilab; Demarteua, Marcel,; Drake, Gary; Weerts, Harry; /Argonne /Chicago U. /Padua U. /INFN, Padua

    2010-10-01

    Future particle physics experiments looking for rare processes will have no choice but to address the demanding challenges of fast pattern recognition in triggering as detector hit density becomes significantly higher due to the high luminosity required to produce the rare process. The authors propose to develop a 3D Vertically Integrated Pattern Recognition Associative Memory (VIPRAM) chip for HEP applications, to advance the state-of-the-art for pattern recognition and track reconstruction for fast triggering.

  18. New pattern recognition system in the e-nose for Chinese spirit identification

    International Nuclear Information System (INIS)

    Zeng Hui; Li Qiang; Gu Yu

    2016-01-01

    This paper presents a new pattern recognition system for Chinese spirit identification by using the polymer quartz piezoelectric crystal sensor based e-nose. The sensors are designed based on quartz crystal microbalance (QCM) principle, and they could capture different vibration frequency signal values for Chinese spirit identification. For each sensor in an 8-channel sensor array, seven characteristic values of the original vibration frequency signal values, i.e., average value (A), root-mean-square value (RMS), shape factor value (S f ), crest factor value (C f ), impulse factor value (I f ), clearance factor value (CL f ), kurtosis factor value (K v ) are first extracted. Then the dimension of the characteristic values is reduced by the principle components analysis (PCA) method. Finally the back propagation (BP) neutral network algorithm is used to recognize Chinese spirits. The experimental results show that the recognition rate of six kinds of Chinese spirits is 93.33% and our proposed new pattern recognition system can identify Chinese spirits effectively. (paper)

  19. A small-world network model of facial emotion recognition.

    Science.gov (United States)

    Takehara, Takuma; Ochiai, Fumio; Suzuki, Naoto

    2016-01-01

    Various models have been proposed to increase understanding of the cognitive basis of facial emotions. Despite those efforts, interactions between facial emotions have received minimal attention. If collective behaviours relating to each facial emotion in the comprehensive cognitive system could be assumed, specific facial emotion relationship patterns might emerge. In this study, we demonstrate that the frameworks of complex networks can effectively capture those patterns. We generate 81 facial emotion images (6 prototypes and 75 morphs) and then ask participants to rate degrees of similarity in 3240 facial emotion pairs in a paired comparison task. A facial emotion network constructed on the basis of similarity clearly forms a small-world network, which features an extremely short average network distance and close connectivity. Further, even if two facial emotions have opposing valences, they are connected within only two steps. In addition, we show that intermediary morphs are crucial for maintaining full network integration, whereas prototypes are not at all important. These results suggest the existence of collective behaviours in the cognitive systems of facial emotions and also describe why people can efficiently recognize facial emotions in terms of information transmission and propagation. For comparison, we construct three simulated networks--one based on the categorical model, one based on the dimensional model, and one random network. The results reveal that small-world connectivity in facial emotion networks is apparently different from those networks, suggesting that a small-world network is the most suitable model for capturing the cognitive basis of facial emotions.

  20. Development of Adaptive AE Signal Pattern Recognition Program and Application to Classification of Defects in Metal Contact Regions of Rotating Component

    International Nuclear Information System (INIS)

    Lee, K. Y.; Lee, C. M.; Kim, J. S.

    1996-01-01

    In this study, the artificial defects in rotary compressor are classified using pattern recognition of acoustic emission signal. For this purpose the computer program is developed. The neural network classifier is compared with the statistical classifier such as the linear discriminant function classifier and empirical Bayesian classifier. It is concluded that the former is better. It is possible to acquire the recognition rate of above 99% by neural network classifier

  1. Deep Belief Networks Based Toponym Recognition for Chinese Text

    Directory of Open Access Journals (Sweden)

    Shu Wang

    2018-06-01

    Full Text Available In Geographical Information Systems, geo-coding is used for the task of mapping from implicitly geo-referenced data to explicitly geo-referenced coordinates. At present, an enormous amount of implicitly geo-referenced information is hidden in unstructured text, e.g., Wikipedia, social data and news. Toponym recognition is the foundation of mining this useful geo-referenced information by identifying words as toponyms in text. In this paper, we propose an adapted toponym recognition approach based on deep belief network (DBN by exploring two key issues: word representation and model interpretation. A Skip-Gram model is used in the word representation process to represent words with contextual information that are ignored by current word representation models. We then determine the core hyper-parameters of the DBN model by illustrating the relationship between the performance and the hyper-parameters, e.g., vector dimensionality, DBN structures and probability thresholds. The experiments evaluate the performance of the Skip-Gram model implemented by the Word2Vec open-source tool, determine stable hyper-parameters and compare our approach with a conditional random field (CRF based approach. The experimental results show that the DBN model outperforms the CRF model with smaller corpus. When the corpus size is large enough, their statistical metrics become approaching. However, their recognition results express differences and complementarity on different kinds of toponyms. More importantly, combining their results can directly improve the performance of toponym recognition relative to their individual performances. It seems that the scale of the corpus has an obvious effect on the performance of toponym recognition. Generally, there is no adequate tagged corpus on specific toponym recognition tasks, especially in the era of Big Data. In conclusion, we believe that the DBN-based approach is a promising and powerful method to extract geo

  2. Differentiation of tea varieties using UV-Vis spectra and pattern recognition techniques

    Science.gov (United States)

    Palacios-Morillo, Ana; Alcázar, Ángela.; de Pablos, Fernando; Jurado, José Marcos

    2013-02-01

    Tea, one of the most consumed beverages all over the world, is of great importance in the economies of a number of countries. Several methods have been developed to classify tea varieties or origins based in pattern recognition techniques applied to chemical data, such as metal profile, amino acids, catechins and volatile compounds. Some of these analytical methods become tedious and expensive to be applied in routine works. The use of UV-Vis spectral data as discriminant variables, highly influenced by the chemical composition, can be an alternative to these methods. UV-Vis spectra of methanol-water extracts of tea have been obtained in the interval 250-800 nm. Absorbances have been used as input variables. Principal component analysis was used to reduce the number of variables and several pattern recognition methods, such as linear discriminant analysis, support vector machines and artificial neural networks, have been applied in order to differentiate the most common tea varieties. A successful classification model was built by combining principal component analysis and multilayer perceptron artificial neural networks, allowing the differentiation between tea varieties. This rapid and simple methodology can be applied to solve classification problems in food industry saving economic resources.

  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.

  4. Identification of strong earthquake ground motion by using pattern recognition

    International Nuclear Information System (INIS)

    Suzuki, Kohei; Tozawa, Shoji; Temmyo, Yoshiharu.

    1983-01-01

    The method of grasping adequately the technological features of complex waveform of earthquake ground motion and utilizing them as the input to structural systems has been proposed by many researchers, and the method of making artificial earthquake waves to be used for the aseismatic design of nuclear facilities has not been established in the unified form. In this research, earthquake ground motion was treated as an irregular process with unsteady amplitude and frequency, and the running power spectral density was expressed as a dark and light image on a plane of the orthogonal coordinate system with both time and frequency axes. The method of classifying this image into a number of technologically important categories by pattern recognition was proposed. This method is based on the concept called compound similarity method in the image technology, entirely different from voice diagnosis, and it has the feature that the result of identification can be quantitatively evaluated by the analysis of correlation of spatial images. Next, the standard pattern model of the simulated running power spectral density corresponding to the representative classification categories was proposed. Finally, the method of making unsteady simulated earthquake motion was shown. (Kako, I.)

  5. Improving Protein Fold Recognition by Deep Learning Networks

    Science.gov (United States)

    Jo, Taeho; Hou, Jie; Eickholt, Jesse; Cheng, Jianlin

    2015-12-01

    For accurate recognition of protein folds, a deep learning network method (DN-Fold) was developed to predict if a given query-template protein pair belongs to the same structural fold. The input used stemmed from the protein sequence and structural features extracted from the protein pair. We evaluated the performance of DN-Fold along with 18 different methods on Lindahl’s benchmark dataset and on a large benchmark set extracted from SCOP 1.75 consisting of about one million protein pairs, at three different levels of fold recognition (i.e., protein family, superfamily, and fold) depending on the evolutionary distance between protein sequences. The correct recognition rate of ensembled DN-Fold for Top 1 predictions is 84.5%, 61.5%, and 33.6% and for Top 5 is 91.2%, 76.5%, and 60.7% at family, superfamily, and fold levels, respectively. We also evaluated the performance of single DN-Fold (DN-FoldS), which showed the comparable results at the level of family and superfamily, compared to ensemble DN-Fold. Finally, we extended the binary classification problem of fold recognition to real-value regression task, which also show a promising performance. DN-Fold is freely available through a web server at http://iris.rnet.missouri.edu/dnfold.

  6. Improving Protein Fold Recognition by Deep Learning Networks.

    Science.gov (United States)

    Jo, Taeho; Hou, Jie; Eickholt, Jesse; Cheng, Jianlin

    2015-12-04

    For accurate recognition of protein folds, a deep learning network method (DN-Fold) was developed to predict if a given query-template protein pair belongs to the same structural fold. The input used stemmed from the protein sequence and structural features extracted from the protein pair. We evaluated the performance of DN-Fold along with 18 different methods on Lindahl's benchmark dataset and on a large benchmark set extracted from SCOP 1.75 consisting of about one million protein pairs, at three different levels of fold recognition (i.e., protein family, superfamily, and fold) depending on the evolutionary distance between protein sequences. The correct recognition rate of ensembled DN-Fold for Top 1 predictions is 84.5%, 61.5%, and 33.6% and for Top 5 is 91.2%, 76.5%, and 60.7% at family, superfamily, and fold levels, respectively. We also evaluated the performance of single DN-Fold (DN-FoldS), which showed the comparable results at the level of family and superfamily, compared to ensemble DN-Fold. Finally, we extended the binary classification problem of fold recognition to real-value regression task, which also show a promising performance. DN-Fold is freely available through a web server at http://iris.rnet.missouri.edu/dnfold.

  7. Modeling urbanization patterns with generative adversarial networks

    OpenAIRE

    Albert, Adrian; Strano, Emanuele; Kaur, Jasleen; Gonzalez, Marta

    2018-01-01

    In this study we propose a new method to simulate hyper-realistic urban patterns using Generative Adversarial Networks trained with a global urban land-use inventory. We generated a synthetic urban "universe" that qualitatively reproduces the complex spatial organization observed in global urban patterns, while being able to quantitatively recover certain key high-level urban spatial metrics.

  8. 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

  9. Fabrication of microstamps and patterned cell network

    International Nuclear Information System (INIS)

    Seong, Nak Seon; Pak, James Jung Ho; Choi, Ju Hee; Ahn, Dong June; Hwang, Seong Min; Lee, Kyung J.

    2002-01-01

    Elastomeric stamps with micrometer-sized grids are fabricated for building biological cell networks by design. Polymerized polydimethyl-siloxane (PDMS) stamps are cast in a variety of different molds prepared by micro-electro mechanical systems (MEMS) technology. Micro square-grid patterns of 3-aminopropyl triethoxy silane (APS) are successfully imprinted on glass plates, and patterned networks of cardiac cells are obtained as designed. The resulting cellular networks clearly demonstrate that cell attachment and growth are greatly favored on APS-treated thin tracks. Here, we report the technical details related to the fabrication of microstamps, to the stamping procedure, and to the culture method. The potential applications of patterned cellular networks are also discussed

  10. User Activity Recognition in Smart Homes Using Pattern Clustering Applied to Temporal ANN Algorithm.

    Science.gov (United States)

    Bourobou, Serge Thomas Mickala; Yoo, Younghwan

    2015-05-21

    This paper discusses the possibility of recognizing and predicting user activities in the IoT (Internet of Things) based smart environment. The activity recognition is usually done through two steps: activity pattern clustering and activity type decision. Although many related works have been suggested, they had some limited performance because they focused only on one part between the two steps. This paper tries to find the best combination of a pattern clustering method and an activity decision algorithm among various existing works. For the first step, in order to classify so varied and complex user activities, we use a relevant and efficient unsupervised learning method called the K-pattern clustering algorithm. In the second step, the training of smart environment for recognizing and predicting user activities inside his/her personal space is done by utilizing the artificial neural network based on the Allen's temporal relations. The experimental results show that our combined method provides the higher recognition accuracy for various activities, as compared with other data mining classification algorithms. Furthermore, it is more appropriate for a dynamic environment like an IoT based smart home.

  11. User Activity Recognition in Smart Homes Using Pattern Clustering Applied to Temporal ANN Algorithm

    Directory of Open Access Journals (Sweden)

    Serge Thomas Mickala Bourobou

    2015-05-01

    Full Text Available This paper discusses the possibility of recognizing and predicting user activities in the IoT (Internet of Things based smart environment. The activity recognition is usually done through two steps: activity pattern clustering and activity type decision. Although many related works have been suggested, they had some limited performance because they focused only on one part between the two steps. This paper tries to find the best combination of a pattern clustering method and an activity decision algorithm among various existing works. For the first step, in order to classify so varied and complex user activities, we use a relevant and efficient unsupervised learning method called the K-pattern clustering algorithm. In the second step, the training of smart environment for recognizing and predicting user activities inside his/her personal space is done by utilizing the artificial neural network based on the Allen’s temporal relations. The experimental results show that our combined method provides the higher recognition accuracy for various activities, as compared with other data mining classification algorithms. Furthermore, it is more appropriate for a dynamic environment like an IoT based smart home.

  12. 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.

  13. 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.

  14. New Directions in Statistical Physics: Econophysics, Bioinformatics, and Pattern Recognition

    International Nuclear Information System (INIS)

    Grassberger, P

    2004-01-01

    This book contains 18 contributions from different authors. Its subtitle 'Econophysics, Bioinformatics, and Pattern Recognition' says more precisely what it is about: not so much about central problems of conventional statistical physics like equilibrium phase transitions and critical phenomena, but about its interdisciplinary applications. After a long period of specialization, physicists have, over the last few decades, found more and more satisfaction in breaking out of the limitations set by the traditional classification of sciences. Indeed, this classification had never been strict, and physicists in particular had always ventured into other fields. Helmholtz, in the middle of the 19th century, had considered himself a physicist when working on physiology, stressing that the physics of animate nature is as much a legitimate field of activity as the physics of inanimate nature. Later, Max Delbrueck and Francis Crick did for experimental biology what Schroedinger did for its theoretical foundation. And many of the experimental techniques used in chemistry, biology, and medicine were developed by a steady stream of talented physicists who left their proper discipline to venture out into the wider world of science. The development we have witnessed over the last thirty years or so is different. It started with neural networks where methods could be applied which had been developed for spin glasses, but todays list includes vehicular traffic (driven lattice gases), geology (self-organized criticality), economy (fractal stochastic processes and large scale simulations), engineering (dynamical chaos), and many others. By staying in the physics departments, these activities have transformed the physics curriculum and the view physicists have of themselves. In many departments there are now courses on econophysics or on biological physics, and some universities offer degrees in the physics of traffic or in econophysics. In order to document this change of attitude

  15. 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....

  16. The effect of network degradation on speech recognition

    CSIR Research Space (South Africa)

    Joubert, G

    2005-11-01

    Full Text Available become increasingly popular, VoIP (Voice over Internet Protocol) is predicted to become the standard means of spoken telecommunication. As a consequence, a significant amount of research has been undertaken on the effect of various packet... to measure the effect of network traffic degeneration during a VoIP transmission, on speech-recognition accuracy. Sentences from the TIMIT database [2] were selected as basis for comparison. The open-source toolkit SOX [3] was used to code the samples...

  17. Applications of pattern recognition techniques to online fault detection

    International Nuclear Information System (INIS)

    Singer, R.M.; Gross, K.C.; King, R.W.

    1993-01-01

    A common problem to operators of complex industrial systems is the early detection of incipient degradation of sensors and components in order to avoid unplanned outages, to orderly plan for anticipated maintenance activities and to assure continued safe operation. In such systems, there usually are a large number of sensors (upwards of several thousand is not uncommon) serving many functions, ranging from input to control systems, monitoring of safety parameters and component performance limits, system environmental conditions, etc. Although sensors deemed to measure important process conditions are generally alarmed, the alarm set points usually are just high-low limits and the operator's response to such alarms is based on written procedures and his or her experience and training. In many systems this approach has been successful, but in situations where the cost of a forced outage is high an improved method is needed. In such cases it is desirable, if not necessary, to detect disturbances in either sensors or the process prior to any actual failure that could either shut down the process or challenge any safety system that is present. Recent advances in various artificial intelligence techniques have provided the opportunity to perform such functions of early detection and diagnosis. In this paper, the experience gained through the application of several pattern-recognition techniques to the on-line monitoring and incipient disturbance detection of several coolant pumps and numerous sensors at the Experimental Breeder Reactor-II (EBR-II) which is located at the Idaho National Engineering Laboratory is presented

  18. Cerebellar involvement in metabolic disorders: a pattern-recognition approach

    International Nuclear Information System (INIS)

    Steinlin, M.; Boltshauser, E.; Blaser, S.

    1998-01-01

    Inborn errors of metabolism can affect the cerebellum during development, maturation and later during life. We have established criteria for pattern recognition of cerebellar abnormalities in metabolic disorders. The abnormalities can be divided into four major groups: cerebellar hypoplasia (CH), hyperplasia, cerebellar atrophy (CA), cerebellar white matter abnormalities (WMA) or swelling, and involvement of the dentate nuclei (DN) or cerebellar cortex. CH can be an isolated typical finding, as in adenylsuccinase deficiency, but is also occasionally seen in many other disorders. Differentiation from CH and CA is often difficult, as in carbohydrate deficient glycoprotein syndrome or 2-l-hydroxyglutaric acidaemia. In cases of atrophy the relationship of cerebellar to cerebral atrophy is important. WMA may be diffuse or patchy, frequently predominantly around the DN. Severe swelling of white matter is present during metabolic crisis in maple syrup urine disease. The DN can be affected by metabolite deposition, necrosis, calcification or demyelination. Involvement of cerebellar cortex is seen in infantile neuroaxonal dystrophy. Changes in DN and cerebellar cortex are rather typical and therefore most helpful; additional features should be sought as they are useful in narrowing down the differential diagnosis. (orig.)

  19. Session Introduction: Challenges of Pattern Recognition in Biomedical Data.

    Science.gov (United States)

    Verma, Shefali Setia; Verma, Anurag; Basile, Anna Okula; Bishop, Marta-Byrska; Darabos, Christian

    2018-01-01

    The analysis of large biomedical data often presents with various challenges related to not just the size of the data, but also to data quality issues such as heterogeneity, multidimensionality, noisiness, and incompleteness of the data. The data-intensive nature of computational genomics problems in biomedical informatics warrants the development and use of massive computer infrastructure and advanced software tools and platforms, including but not limited to the use of cloud computing. Our session aims to address these challenges in handling big data for designing a study, performing analysis, and interpreting outcomes of these analyses. These challenges have been prevalent in many studies including those which focus on the identification of novel genetic variant-phenotype associations using data from sources like Electronic Health Records (EHRs) or multi-omic data. One of the biggest challenges to focus on is the imperfect nature of the biomedical data where a lot of noise and sparseness is observed. In our session, we will present research articles that can help in identifying innovative ways to recognize and overcome newly arising challenges associated with pattern recognition in biomedical data.

  20. 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.

  1. Virtualized Network Function Orchestration System and Experimental Network Based QR Recognition for a 5G Mobile Access Network

    Directory of Open Access Journals (Sweden)

    Misun Ahn

    2017-12-01

    Full Text Available This paper proposes a virtualized network function orchestration system based on Network Function Virtualization (NFV, one of the main technologies in 5G mobile networks. This system should provide connectivity between network devices and be able to create flexible network function and distribution. This system focuses more on access networks. By experimenting with various scenarios of user service established and activated in a network, we examine whether rapid adoption of new service is possible and whether network resources can be managed efficiently. The proposed method is based on Bluetooth transfer technology and mesh networking to provide automatic connections between network machines and on a Docker flat form, which is a container virtualization technology for setting and managing key functions. Additionally, the system includes a clustering and recovery measure regarding network function based on the Docker platform. We will briefly introduce the QR code perceived service as a user service to examine the proposal and based on this given service, we evaluate the function of the proposal and present analysis. Through the proposed approach, container relocation has been implemented according to a network device’s CPU usage and we confirm successful service through function evaluation on a real test bed. We estimate QR code recognition speed as the amount of network equipment is gradually increased, improving user service and confirm that the speed of recognition is increased as the assigned number of network devices is increased by the user service.

  2. Surveillance of a nuclear reactor core by use of a pattern recognition method

    International Nuclear Information System (INIS)

    Invernizzi, Michel.

    1982-07-01

    A pattern recognition system is described for the surveillance of a PWR reactor. This report contains four chapters. The first one succinctly deals with statistical pattern recognition principles. In the second chapter we show how a surveillance problem may be treated by pattern recognition and we present methods for surveillances (detection of abnormalities), controls (kind of running recognition) and diagnotics (kind of abnormality recognition). The third chapter shows a surveillance method of a nuclear plant. The signals used are the neutron noise observations made by the ionization chambers inserted in the reactor. Abnormality is defined in opposition with the training set witch is supposed to be an exhaustive summary of normality. In the fourth chapter we propose a scheme for an adaptative recognition and a method based on classes modelisations by hyper-spheres. This method has been tested on simulated training sets in two-dimensional feature spaces. It gives solutions to problems of non-linear separability [fr

  3. 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

  4. Recent developments in pattern recognition with applications in high-energy physics

    International Nuclear Information System (INIS)

    Bischof, H.; Fruehwirth, R.

    1998-01-01

    In this contribution we consider the track finding and fitting problem from the pattern recognition and computer vision point of view. In particular, we consider it as a problem of recovering parametric models from noisy measurements. We review major approaches like neural networks, Hough transforms, Kalman filtering techniques, etc, which have been previously used in that area, and point out the problems of these approaches. Then we present an algorithm, originally developed in the area of computer vision, to fit different types of curves to noisy edge data, and demonstrate how it can be used for track finding and fitting. The algorithm is based on two principles: (a) a data driven exploration produces many hypotheses of possible tracks; (b) a selection procedure based on the Minimum Description Length Principle (MDL), selects those hypotheses which are needed to explain the data. The results of the algorithm are a number of tracks, and a set of outlier points (which cannot be explained by tracks according to the MDL-principle). We discuss how knowledge about the detectors and the underlying processes can be incorporated in the algorithm. Finally, we demonstrate the algorithm on 2D and 3D pattern recognition tasks. (author)

  5. 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.

  6. Weighted Local Active Pixel Pattern (WLAPP for Face Recognition in Parallel Computation Environment

    Directory of Open Access Journals (Sweden)

    Gundavarapu Mallikarjuna Rao

    2013-10-01

    Full Text Available Abstract  - The availability of multi-core technology resulted totally new computational era. Researchers are keen to explore available potential in state of art-machines for breaking the bearer imposed by serial computation. Face Recognition is one of the challenging applications on so ever computational environment. The main difficulty of traditional Face Recognition algorithms is lack of the scalability. In this paper Weighted Local Active Pixel Pattern (WLAPP, a new scalable Face Recognition Algorithm suitable for parallel environment is proposed.  Local Active Pixel Pattern (LAPP is found to be simple and computational inexpensive compare to Local Binary Patterns (LBP. WLAPP is developed based on concept of LAPP. The experimentation is performed on FG-Net Aging Database with deliberately introduced 20% distortion and the results are encouraging. Keywords — Active pixels, Face Recognition, Local Binary Pattern (LBP, Local Active Pixel Pattern (LAPP, Pattern computing, parallel workers, template, weight computation.  

  7. Applications of pattern recognition theory in diagnostics of nuclear power plants

    International Nuclear Information System (INIS)

    Cech, J.

    1982-01-01

    The questions are discussed of the application of the theory of pattern recognition in the diagnostics of nuclear power plants. For the future use of recognition systems in the diagnostics of nuclear power plants it is obvious that like with other complex systems, optimal models will have to be used which will organize the optimal recognition algorithm. The conclusion is presented that for the needs of nuclear power plants special systems will be more suitable for pattern recognition than digital computers which are flexible and adaptible but have a lower decision rate, an insufficient working memory, complicated programs, etc. (Z.M.)

  8. Multiresolution pattern recognition of small volcanos in Magellan data

    Science.gov (United States)

    Smyth, P.; Anderson, C. H.; Aubele, J. C.; Crumpler, L. S.

    1992-01-01

    The Magellan data is a treasure-trove for scientific analysis of venusian geology, providing far more detail than was previously available from Pioneer Venus, Venera 15/16, or ground-based radar observations. However, at this point, planetary scientists are being overwhelmed by the sheer quantities of data collected--data analysis technology has not kept pace with our ability to collect and store it. In particular, 'small-shield' volcanos (less than 20 km in diameter) are the most abundant visible geologic feature on the planet. It is estimated, based on extrapolating from previous studies and knowledge of the underlying geologic processes, that there should be on the order of 10(exp 5) to 10(exp 6) of these volcanos visible in the Magellan data. Identifying and studying these volcanos is fundamental to a proper understanding of the geologic evolution of Venus. However, locating and parameterizing them in a manual manner is very time-consuming. Hence, we have undertaken the development of techniques to partially automate this task. The goal is not the unrealistic one of total automation, but rather the development of a useful tool to aid the project scientists. The primary constraints for this particular problem are as follows: (1) the method must be reasonably robust; and (2) the method must be reasonably fast. Unlike most geological features, the small volcanos of Venus can be ascribed to a basic process that produces features with a short list of readily defined characteristics differing significantly from other surface features on Venus. For pattern recognition purposes the relevant criteria include the following: (1) a circular planimetric outline; (2) known diameter frequency distribution from preliminary studies; (3) a limited number of basic morphological shapes; and (4) the common occurrence of a single, circular summit pit at the center of the edifice.

  9. Motor Oil Classification using Color Histograms and Pattern Recognition Techniques.

    Science.gov (United States)

    Ahmadi, Shiva; Mani-Varnosfaderani, Ahmad; Habibi, Biuck

    2018-04-20

    Motor oil classification is important for quality control and the identification of oil adulteration. In thiswork, we propose a simple, rapid, inexpensive and nondestructive approach based on image analysis and pattern recognition techniques for the classification of nine different types of motor oils according to their corresponding color histograms. For this, we applied color histogram in different color spaces such as red green blue (RGB), grayscale, and hue saturation intensity (HSI) in order to extract features that can help with the classification procedure. These color histograms and their combinations were used as input for model development and then were statistically evaluated by using linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and support vector machine (SVM) techniques. Here, two common solutions for solving a multiclass classification problem were applied: (1) transformation to binary classification problem using a one-against-all (OAA) approach and (2) extension from binary classifiers to a single globally optimized multilabel classification model. In the OAA strategy, LDA, QDA, and SVM reached up to 97% in terms of accuracy, sensitivity, and specificity for both the training and test sets. In extension from binary case, despite good performances by the SVM classification model, QDA and LDA provided better results up to 92% for RGB-grayscale-HSI color histograms and up to 93% for the HSI color map, respectively. In order to reduce the numbers of independent variables for modeling, a principle component analysis algorithm was used. Our results suggest that the proposed method is promising for the identification and classification of different types of motor oils.

  10. Pattern Recognition in Optical Remote Sensing Data Processing

    Science.gov (United States)

    Kozoderov, Vladimir; Kondranin, Timofei; Dmitriev, Egor; Kamentsev, Vladimir

    Computational procedures of the land surface biophysical parameters retrieval imply that modeling techniques are available of the outgoing radiation description together with monitoring techniques of remote sensing data processing using registered radiances between the related optical sensors and the land surface objects called “patterns”. Pattern recognition techniques are a valuable approach to the processing of remote sensing data for images of the land surface - atmosphere system. Many simplified codes of the direct and inverse problems of atmospheric optics are considered applicable for the imagery processing of low and middle spatial resolution. Unless the authors are not interested in the accuracy of the final information products, they utilize these standard procedures. The emerging necessity of processing data of high spectral and spatial resolution given by imaging spectrometers puts forward the newly defined pattern recognition techniques. The proposed tools of using different types of classifiers combined with the parameter retrieval procedures for the forested environment are maintained to have much wider applications as compared with the image features and object shapes extraction, which relates to photometry and geometry in pixel-level reflectance representation of the forested land cover. The pixel fraction and reflectance of “end-members” (sunlit forest canopy, sunlit background and shaded background for a particular view and solar illumination angle) are only a part in the listed techniques. It is assumed that each pixel views collections of the individual forest trees and the pixel-level reflectance can thus be computed as a linear mixture of sunlit tree tops, sunlit background (or understory) and shadows. Instead of these photometry and geometry constraints, the improved models are developed of the functional description of outgoing spectral radiation, in which such parameters of the forest canopy like the vegetation biomass density for

  11. 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.

  12. Network approach to patterns in stratocumulus clouds

    Science.gov (United States)

    Glassmeier, Franziska; Feingold, Graham

    2017-10-01

    Stratocumulus clouds (Sc) have a significant impact on the amount of sunlight reflected back to space, with important implications for Earth’s climate. Representing Sc and their radiative impact is one of the largest challenges for global climate models. Sc fields self-organize into cellular patterns and thus lend themselves to analysis and quantification in terms of natural cellular networks. Based on large-eddy simulations of Sc fields, we present a first analysis of the geometric structure and self-organization of Sc patterns from this network perspective. Our network analysis shows that the Sc pattern is scale-invariant as a consequence of entropy maximization that is known as Lewis’s Law (scaling parameter: 0.16) and is largely independent of the Sc regime (cloud-free vs. cloudy cell centers). Cells are, on average, hexagonal with a neighbor number variance of about 2, and larger cells tend to be surrounded by smaller cells, as described by an Aboav-Weaire parameter of 0.9. The network structure is neither completely random nor characteristic of natural convection. Instead, it emerges from Sc-specific versions of cell division and cell merging that are shaped by cell expansion. This is shown with a heuristic model of network dynamics that incorporates our physical understanding of cloud processes.

  13. Spatial and temporal air quality pattern recognition using environmetric techniques: a case study in Malaysia.

    Science.gov (United States)

    Syed Abdul Mutalib, Sharifah Norsukhairin; Juahir, Hafizan; Azid, Azman; Mohd Sharif, Sharifah; Latif, Mohd Talib; Aris, Ahmad Zaharin; Zain, Sharifuddin M; Dominick, Doreena

    2013-09-01

    The objective of this study is to identify spatial and temporal patterns in the air quality at three selected Malaysian air monitoring stations based on an eleven-year database (January 2000-December 2010). Four statistical methods, Discriminant Analysis (DA), Hierarchical Agglomerative Cluster Analysis (HACA), Principal Component Analysis (PCA) and Artificial Neural Networks (ANNs), were selected to analyze the datasets of five air quality parameters, namely: SO2, NO2, O3, CO and particulate matter with a diameter size of below 10 μm (PM10). The three selected air monitoring stations share the characteristic of being located in highly urbanized areas and are surrounded by a number of industries. The DA results show that spatial characterizations allow successful discrimination between the three stations, while HACA shows the temporal pattern from the monthly and yearly factor analysis which correlates with severe haze episodes that have happened in this country at certain periods of time. The PCA results show that the major source of air pollution is mostly due to the combustion of fossil fuel in motor vehicles and industrial activities. The spatial pattern recognition (S-ANN) results show a better prediction performance in discriminating between the regions, with an excellent percentage of correct classification compared to DA. This study presents the necessity and usefulness of environmetric techniques for the interpretation of large datasets aiming to obtain better information about air quality patterns based on spatial and temporal characterizations at the selected air monitoring stations.

  14. Chemical Vapor Identification by Plasma Treated Thick Film Tin Oxide Gas Sensor Array and Pattern Recognition

    Directory of Open Access Journals (Sweden)

    J. K. Srivastava

    2011-02-01

    Full Text Available Present study deals the class recognition potential of a four element plasma treated thick film tin oxide gas sensor array exposed with volatile organic compounds (VOCs. Methanol, Ethanol and Acetone are selected as target VOCs and exposed on sensor array at different concentration in range from 100-1000 ppm. Sensor array consist of four tin oxide sensors doped with 1-4 % PbO concentrations were fabricated by thick film technology and then treated with oxygen plasma for 5-10 minute durations. Sensor signal is analyzed by principal component analysis (PCA for visual classification of VOCs. Further output of PCA is used as input for classification of VOCs by four pattern classification techniques as: linear discriminant analysis (LDA, k-nearest neighbor (KNN, back propagation neural network (BPNN and support vector machine (SVM. All the four classifier results 100 % correct classification rate of VOCs by response analysis of sensor array treated with plasma for 5 minute.

  15. Peeking Network States with Clustered Patterns

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Jinoh [Texas A & M Univ., Commerce, TX (United States); Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Sim, Alex [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)

    2015-10-20

    Network traffic monitoring has long been a core element for effec- tive network management and security. However, it is still a chal- lenging task with a high degree of complexity for comprehensive analysis when considering multiple variables and ever-increasing traffic volumes to monitor. For example, one of the widely con- sidered approaches is to scrutinize probabilistic distributions, but it poses a scalability concern and multivariate analysis is not gen- erally supported due to the exponential increase of the complexity. In this work, we propose a novel method for network traffic moni- toring based on clustering, one of the powerful deep-learning tech- niques. We show that the new approach enables us to recognize clustered results as patterns representing the network states, which can then be utilized to evaluate “similarity” of network states over time. In addition, we define a new quantitative measure for the similarity between two compared network states observed in dif- ferent time windows, as a supportive means for intuitive analysis. Finally, we demonstrate the clustering-based network monitoring with public traffic traces, and show that the proposed approach us- ing the clustering method has a great opportunity for feasible, cost- effective network monitoring.

  16. Kernel Learning of Histogram of Local Gabor Phase Patterns for Face Recognition

    Directory of Open Access Journals (Sweden)

    Bineng Zhong

    2008-06-01

    Full Text Available This paper proposes a new face recognition method, named kernel learning of histogram of local Gabor phase pattern (K-HLGPP, which is based on Daugman’s method for iris recognition and the local XOR pattern (LXP operator. Unlike traditional Gabor usage exploiting the magnitude part in face recognition, we encode the Gabor phase information for face classification by the quadrant bit coding (QBC method. Two schemes are proposed for face recognition. One is based on the nearest-neighbor classifier with chi-square as the similarity measurement, and the other makes kernel discriminant analysis for HLGPP (K-HLGPP using histogram intersection and Gaussian-weighted chi-square kernels. The comparative experiments show that K-HLGPP achieves a higher recognition rate than other well-known face recognition systems on the large-scale standard FERET, FERET200, and CAS-PEAL-R1 databases.

  17. On Assisting a Visual-Facial Affect Recognition System with Keyboard-Stroke Pattern Information

    Science.gov (United States)

    Stathopoulou, I.-O.; Alepis, E.; Tsihrintzis, G. A.; Virvou, M.

    Towards realizing a multimodal affect recognition system, we are considering the advantages of assisting a visual-facial expression recognition system with keyboard-stroke pattern information. Our work is based on the assumption that the visual-facial and keyboard modalities are complementary to each other and that their combination can significantly improve the accuracy in affective user models. Specifically, we present and discuss the development and evaluation process of two corresponding affect recognition subsystems, with emphasis on the recognition of 6 basic emotional states, namely happiness, sadness, surprise, anger and disgust as well as the emotion-less state which we refer to as neutral. We find that emotion recognition by the visual-facial modality can be aided greatly by keyboard-stroke pattern information and the combination of the two modalities can lead to better results towards building a multimodal affect recognition system.

  18. Optimal pattern synthesis for speech recognition based on principal component analysis

    Science.gov (United States)

    Korsun, O. N.; Poliyev, A. V.

    2018-02-01

    The algorithm for building an optimal pattern for the purpose of automatic speech recognition, which increases the probability of correct recognition, is developed and presented in this work. The optimal pattern forming is based on the decomposition of an initial pattern to principal components, which enables to reduce the dimension of multi-parameter optimization problem. At the next step the training samples are introduced and the optimal estimates for principal components decomposition coefficients are obtained by a numeric parameter optimization algorithm. Finally, we consider the experiment results that show the improvement in speech recognition introduced by the proposed optimization algorithm.

  19. 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.

  20. 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

  1. The Role of Binocular Disparity in Rapid Scene and Pattern Recognition

    Directory of Open Access Journals (Sweden)

    Matteo Valsecchi

    2013-04-01

    Full Text Available We investigated the contribution of binocular disparity to the rapid recognition of scenes and simpler spatial patterns using a paradigm combining backward masked stimulus presentation and short-term match-to-sample recognition. First, we showed that binocular disparity did not contribute significantly to the recognition of briefly presented natural and artificial scenes, even when the availability of monocular cues was reduced. Subsequently, using dense random dot stereograms as stimuli, we showed that observers were in principle able to extract spatial patterns defined only by disparity under brief, masked presentations. Comparing our results with the predictions from a cue-summation model, we showed that combining disparity with luminance did not per se disrupt the processing of disparity. Our results suggest that the rapid recognition of scenes is mediated mostly by a monocular comparison of the images, although we can rely on stereo in fast pattern recognition.

  2. 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.

  3. Characterizing synchrony patterns across cognitive task stages of associative recognition memory.

    Science.gov (United States)

    Portoles, Oscar; Borst, Jelmer P; van Vugt, Marieke K

    2017-12-28

    Numerous studies seek to understand the role of oscillatory synchronization in cognition. This problem is particularly challenging in the context of complex cognitive behavior, which consists of a sequence of processing steps with uncertain duration. In this study, we analyzed oscillatory connectivity measures in time windows that previous computational models had associated with a specific sequence of processing steps in an associative memory recognition task (visual encoding, familiarity, memory retrieval, decision making, and motor response). The timing of these processing steps was estimated on a single-trial basis with a novel hidden semi-Markov model multivariate pattern analysis (HSMM-MVPA) method. We show that different processing stages are associated with specific patterns of oscillatory connectivity. Visual encoding is characterized by a dense network connecting frontal, posterior, and temporal areas as well as frontal and occipital phase locking in the 4-9 Hz theta band. Familiarity is associated with frontal phase locking in the 9-14 Hz alpha band. Decision making is associated with frontal and temporo-central interhemispheric connections in the alpha band. During decision making, a second network in the theta band that connects left-temporal, central, and occipital areas bears similarity to the neural signature for preparing a motor response. A similar theta band network is also present during the motor response, with additionally alpha band connectivity between right-temporal and posterior areas. This demonstrates that the processing stages discovered with the HSMM-MVPA method are indeed linked to distinct synchronization patterns, leading to a closer understanding of the functional role of oscillations in cognition. © 2017 The Authors. European Journal of Neuroscience published by Federation of European Neuroscience Societies and John Wiley & Sons Ltd.

  4. A Novel Wearable Sensor-Based Human Activity Recognition Approach Using Artificial Hydrocarbon Networks.

    Science.gov (United States)

    Ponce, Hiram; Martínez-Villaseñor, María de Lourdes; Miralles-Pechuán, Luis

    2016-07-05

    Human activity recognition has gained more interest in several research communities given that understanding user activities and behavior helps to deliver proactive and personalized services. There are many examples of health systems improved by human activity recognition. Nevertheless, the human activity recognition classification process is not an easy task. Different types of noise in wearable sensors data frequently hamper the human activity recognition classification process. In order to develop a successful activity recognition system, it is necessary to use stable and robust machine learning techniques capable of dealing with noisy data. In this paper, we presented the artificial hydrocarbon networks (AHN) technique to the human activity recognition community. Our artificial hydrocarbon networks novel approach is suitable for physical activity recognition, noise tolerance of corrupted data sensors and robust in terms of different issues on data sensors. We proved that the AHN classifier is very competitive for physical activity recognition and is very robust in comparison with other well-known machine learning methods.

  5. Pattern recognition and modelling of earthquake registrations with interactive computer support

    International Nuclear Information System (INIS)

    Manova, Katarina S.

    2004-01-01

    The object of the thesis is Pattern Recognition. Pattern recognition i.e. classification, is applied in many fields: speech recognition, hand printed character recognition, medical analysis, satellite and aerial-photo interpretations, biology, computer vision, information retrieval and so on. In this thesis is studied its applicability in seismology. Signal classification is an area of great importance in a wide variety of applications. This thesis deals with the problem of (automatic) classification of earthquake signals, which are non-stationary signals. Non-stationary signal classification is an area of active research in the signal and image processing community. The goal of the thesis is recognition of earthquake signals according to their epicentral zone. Source classification i.e. recognition is based on transformation of seismograms (earthquake registrations) to images, via time-frequency transformations, and applying image processing and pattern recognition techniques for feature extraction, classification and recognition. The tested data include local earthquakes from seismic regions in Macedonia. By using actual seismic data it is shown that proposed methods provide satisfactory results for classification and recognition.(Author)

  6. On damage diagnosis for a wind turbine blade using pattern recognition

    Science.gov (United States)

    Dervilis, N.; Choi, M.; Taylor, S. G.; Barthorpe, R. J.; Park, G.; Farrar, C. R.; Worden, K.

    2014-03-01

    With the increased interest in implementation of wind turbine power plants in remote areas, structural health monitoring (SHM) will be one of the key cards in the efficient establishment of wind turbines in the energy arena. Detection of blade damage at an early stage is a critical problem, as blade failure can lead to a catastrophic outcome for the entire wind turbine system. Experimental measurements from vibration analysis were extracted from a 9 m CX-100 blade by researchers at Los Alamos National Laboratory (LANL) throughout a full-scale fatigue test conducted at the National Renewable Energy Laboratory (NREL) and National Wind Technology Center (NWTC). The blade was harmonically excited at its first natural frequency using a Universal Resonant EXcitation (UREX) system. In the current study, machine learning algorithms based on Artificial Neural Networks (ANNs), including an Auto-Associative Neural Network (AANN) based on a standard ANN form and a novel approach to auto-association with Radial Basis Functions (RBFs) networks are used, which are optimised for fast and efficient runs. This paper introduces such pattern recognition methods into the wind energy field and attempts to address the effectiveness of such methods by combining vibration response data with novelty detection techniques.

  7. Hardware processors for pattern recognition tasks in experiments with wire chambers

    International Nuclear Information System (INIS)

    Verkerk, C.

    1975-01-01

    Hardware processors for pattern recognition tasks in experiments with multiwire proportional chambers or drift chambers are described. They vary from simple ones used for deciding in real time if particle trajectories are straight to complex ones for recognition of curved tracks. Schematics and block-diagrams of different processors are shown

  8. Discovering Preferential Patterns in Sectoral Trade Networks.

    Science.gov (United States)

    Cingolani, Isabella; Piccardi, Carlo; Tajoli, Lucia

    2015-01-01

    We analyze the patterns of import/export bilateral relations, with the aim of assessing the relevance and shape of "preferentiality" in countries' trade decisions. Preferentiality here is defined as the tendency to concentrate trade on one or few partners. With this purpose, we adopt a systemic approach through the use of the tools of complex network analysis. In particular, we apply a pattern detection approach based on community and pseudocommunity analysis, in order to highlight the groups of countries within which most of members' trade occur. The method is applied to two intra-industry trade networks consisting of 221 countries, relative to the low-tech "Textiles and Textile Articles" and the high-tech "Electronics" sectors for the year 2006, to look at the structure of world trade before the start of the international financial crisis. It turns out that the two networks display some similarities and some differences in preferential trade patterns: they both include few significant communities that define narrow sets of countries trading with each other as preferential destinations markets or supply sources, and they are characterized by the presence of similar hierarchical structures, led by the largest economies. But there are also distinctive features due to the characteristics of the industries examined, in which the organization of production and the destination markets are different. Overall, the extent of preferentiality and partner selection at the sector level confirm the relevance of international trade costs still today, inducing countries to seek the highest efficiency in their trade patterns.

  9. Exploring How User Routine Affects the Recognition Performance of a Lock Pattern

    NARCIS (Netherlands)

    de Wide, Lisa; Spreeuwers, Lieuwe Jan; Veldhuis, Raymond N.J.

    2015-01-01

    To protect an Android smartphone against attackers, a lock pattern can be used. Nevertheless, shoulder-surfing and smudge attacks can be used to get access despite of this protection. To combat these attacks, biometric recognition can be added to the lock pattern, such that the lock-pattern

  10. Transfer Learning for Video Recognition with Scarce Training Data for Deep Convolutional Neural Network

    OpenAIRE

    Su, Yu-Chuan; Chiu, Tzu-Hsuan; Yeh, Chun-Yen; Huang, Hsin-Fu; Hsu, Winston H.

    2014-01-01

    Unconstrained video recognition and Deep Convolution Network (DCN) are two active topics in computer vision recently. In this work, we apply DCNs as frame-based recognizers for video recognition. Our preliminary studies, however, show that video corpora with complete ground truth are usually not large and diverse enough to learn a robust model. The networks trained directly on the video data set suffer from significant overfitting and have poor recognition rate on the test set. The same lack-...

  11. Real-time intelligent pattern recognition algorithm for surface EMG signals

    Directory of Open Access Journals (Sweden)

    Jahed Mehran

    2007-12-01

    are time and time-frequency domain. In this work we demonstrate the capability of an EMG pattern recognition system using ANFIS as classifier with a real-time learning method. Our results reveal that the utilized real-time ANFIS approach along with the user evaluation provides a 96.7% average accuracy. This rate is superior to the previously reported result utilizing artificial neural networks (ANN real-time method 1. Conclusion This study shows that ANFIS real-time learning method coupled with mixed time and time-frequency features as EMG features can provide acceptable results for designing sEMG pattern recognition system suitable for hand prosthesis control.

  12. Segmentation of turbo generator and reactor coolant pump vibratory patterns: a syntactic pattern recognition approach

    International Nuclear Information System (INIS)

    Tira, Z.

    1993-02-01

    This study was undertaken in the context of turbogenerator and reactor coolant pump vibration surveillance. Vibration meters are used to monitor equipment condition. An anomaly will modify the signal mean. At the present time, the expert system DIVA, developed to automate diagnosis, requests the operator to identify the nature of the pattern change thus indicated. In order to minimize operator intervention, we have to automate on the one hand classification and on the other hand, detection and segmentation of the patterns. The purpose of this study is to develop a new automatic system for the segmentation and classification of signals. The segmentation is based on syntactic pattern recognition. For the classification, a decision tree is used. The signals to process are the rms values of the vibrations measured on rotating machines. These signals are randomly sampled. All processing is automatic and no a priori statistical knowledge on the signals is required. The segmentation performances are assessed by tests on vibratory signals. (author). 31 figs

  13. Utility and recognition of lines and linear patterns on electronic displays depicting aeronautical charting information

    Science.gov (United States)

    2009-01-01

    This report describes a study conducted to explore the utility and recognition of lines and linear patterns on electronic displays depicting aeronautical charting information. The study gathered data from a large number of pilots who conduct all type...

  14. Peptide Pattern Recognition for high-throughput protein sequence analysis and clustering

    DEFF Research Database (Denmark)

    Busk, Peter Kamp

    2017-01-01

    Large collections of protein sequences with divergent sequences are tedious to analyze for understanding their phylogenetic or structure-function relation. Peptide Pattern Recognition is an algorithm that was developed to facilitate this task but the previous version does only allow a limited...... number of sequences as input. I implemented Peptide Pattern Recognition as a multithread software designed to handle large numbers of sequences and perform analysis in a reasonable time frame. Benchmarking showed that the new implementation of Peptide Pattern Recognition is twenty times faster than...... the previous implementation on a small protein collection with 673 MAP kinase sequences. In addition, the new implementation could analyze a large protein collection with 48,570 Glycosyl Transferase family 20 sequences without reaching its upper limit on a desktop computer. Peptide Pattern Recognition...

  15. Data Mining and Pattern Recognition Models for Identifying Inherited Diseases: Challenges and Implications

    OpenAIRE

    Iddamalgoda, Lahiru; Das, Partha S.; Aponso, Achala; Sundararajan, Vijayaraghava S.; Suravajhala, Prashanth; Valadi, Jayaraman K.

    2016-01-01

    Data mining and pattern recognition methods reveal interesting findings in genetic studies, especially on how the genetic makeup is associated with inherited diseases. Although researchers have proposed various data mining models for biomedical approaches, there remains a challenge in accurately prioritizing the single nucleotide polymorphisms (SNP) associated with the disease. In this commentary, we review the state-of-art data mining and pattern recognition models for identifying inherited ...

  16. 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%.

  17. New neural-networks-based 3D object recognition system

    Science.gov (United States)

    Abolmaesumi, Purang; Jahed, M.

    1997-09-01

    Three-dimensional object recognition has always been one of the challenging fields in computer vision. In recent years, Ulman and Basri (1991) have proposed that this task can be done by using a database of 2-D views of the objects. The main problem in their proposed system is that the correspondent points should be known to interpolate the views. On the other hand, their system should have a supervisor to decide which class does the represented view belong to. In this paper, we propose a new momentum-Fourier descriptor that is invariant to scale, translation, and rotation. This descriptor provides the input feature vectors to our proposed system. By using the Dystal network, we show that the objects can be classified with over 95% precision. We have used this system to classify the objects like cube, cone, sphere, torus, and cylinder. Because of the nature of the Dystal network, this system reaches to its stable point by a single representation of the view to the system. This system can also classify the similar views to a single class (e.g., for the cube, the system generated 9 different classes for 50 different input views), which can be used to select an optimum database of training views. The system is also very flexible to the noise and deformed views.

  18. 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.

  19. Gender recognition using local binary pattern and Naive Bayes ...

    African Journals Online (AJOL)

    Automatic gender classification has many important applications, for example, intelligent user interface, surveillance, identity authentication, access control and human-computer interaction amongst others. Gender ... The system can be employed for use in scenarios where real time gender recognition is required.

  20. DETECTION OF TOPOLOGICAL PATTERNS IN PROTEIN NETWORKS.

    Energy Technology Data Exchange (ETDEWEB)

    MASLOV,S.SNEPPEN,K.

    2003-11-17

    interesting property of many biological networks that was recently brought to attention of the scientific community [3, 4, 5] is an extremely broad distribution of node connectivities defined as the number of immediate neighbors of a given node in the network. While the majority of nodes have just a few edges connecting them to other nodes in the network, there exist some nodes, that we will refer to as ''hubs'', with an unusually large number of neighbors. The connectivity of the most connected hub in such a network is typically several orders of magnitude larger than the average connectivity in the network. Often the distribution of connectivities of individual nodes can be approximated by a scale-free power law form [3] in which case the network is referred to as scale-free. Among biological networks distributions of node connectivities in metabolic [4], protein interaction [5], and brain functional [6] networks can be reasonably approximated by a power law extending for several orders of magnitude. The set of connectivities of individual nodes is an example of a low-level (single-node) topological property of a network. While it answers the question about how many neighbors a given node has, it gives no information about the identity of those neighbors. It is clear that most functional properties of networks are defined at a higher topological level in the exact pattern of connections of nodes to each other. However, such multi-node connectivity patterns are rather difficult to quantify and compare between networks. In this work we concentrate on multi-node topological properties of protein networks. These networks (as any other biological networks) lack the top-down design. Instead, selective forces of biological evolution shape them from raw material provided by random events such as mutations within individual genes, and gene duplications. As a result their connections are characterized by a large degree of randomness. One may wonder which

  1. A modified artificial immune system based pattern recognition approach -- an application to clinic diagnostics

    Science.gov (United States)

    Zhao, Weixiang; Davis, Cristina E.

    2011-01-01

    Objective This paper introduces a modified artificial immune system (AIS)-based pattern recognition method to enhance the recognition ability of the existing conventional AIS-based classification approach and demonstrates the superiority of the proposed new AIS-based method via two case studies of breast cancer diagnosis. Methods and materials Conventionally, the AIS approach is often coupled with the k nearest neighbor (k-NN) algorithm to form a classification method called AIS-kNN. In this paper we discuss the basic principle and possible problems of this conventional approach, and propose a new approach where AIS is integrated with the radial basis function – partial least square regression (AIS-RBFPLS). Additionally, both the two AIS-based approaches are compared with two classical and powerful machine learning methods, back-propagation neural network (BPNN) and orthogonal radial basis function network (Ortho-RBF network). Results The diagnosis results show that: (1) both the AIS-kNN and the AIS-RBFPLS proved to be a good machine leaning method for clinical diagnosis, but the proposed AIS-RBFPLS generated an even lower misclassification ratio, especially in the cases where the conventional AIS-kNN approach generated poor classification results because of possible improper AIS parameters. For example, based upon the AIS memory cells of “replacement threshold = 0.3”, the average misclassification ratios of two approaches for study 1 are 3.36% (AIS-RBFPLS) and 9.07% (AIS-kNN), and the misclassification ratios for study 2 are 19.18% (AIS-RBFPLS) and 28.36% (AIS-kNN); (2) the proposed AIS-RBFPLS presented its robustness in terms of the AIS-created memory cells, showing a smaller standard deviation of the results from the multiple trials than AIS-kNN. For example, using the result from the first set of AIS memory cells as an example, the standard deviations of the misclassification ratios for study 1 are 0.45% (AIS-RBFPLS) and 8.71% (AIS-kNN) and those for

  2. Distributed open environment for data retrieval based on pattern recognition techniques

    International Nuclear Information System (INIS)

    Pereira, A.; Vega, J.; Castro, R.; Portas, A.

    2010-01-01

    Pattern recognition methods for data retrieval have been applied to fusion databases for the localization and extraction of similar waveforms within temporal evolution signals. In order to standardize the use of these methods, a distributed open environment has been designed. It is based on a client/server architecture that supports distribution, interoperability and portability between heterogeneous platforms. The server part is a single desktop application based on J2EE (Java 2 Enterprise Edition), which provides a mature standard framework and a modular architecture. It can handle transactions and concurrency of components that are deployed on JETTY, an embedded web container within the Java server application for providing HTTP services. The data management is based on Apache DERBY, a relational database engine also embedded on the same Java based solution. This encapsulation allows hiding of unnecessary details about the installation, distribution, and configuration of all these components but with the flexibility to create and allocate many databases on different servers. The DERBY network module increases the scope of the installed database engine by providing traditional Java database network connections (JDBC-TCP/IP). This avoids scattering several database engines (a unique embedded engine defines the rules for accessing the distributed data). Java thin clients (Java 5 or above is the unique requirement) can be executed in the same computer than the server program (for example a desktop computer) but also server and client software can be distributed in a remote participation environment (wide area networks). The thin client provides graphic user interface to look for patterns (entire waveforms or specific structural forms) and display the most similar ones. This is obtained with HTTP requests and by generating dynamic content (servlets) in response to these client requests.

  3. Distributed Open Environment for Data Retrieval based on Pattern Recognition Techniques

    Energy Technology Data Exchange (ETDEWEB)

    Pereira, A.; Vega, J.; Castro, R.; Portas, A. [Association EuratomCIEMAT para Fusion, Madrid (Spain)

    2009-07-01

    Full text of publication follows: Pattern recognition methods for data retrieval have been applied to fusion databases for the localization and extraction of similar waveforms within temporal evolution signals. In order to standardize the use of these methods, a distributed open environment has been designed. It is based on a client/server architecture that supports distribution, inter-operability and portability between heterogeneous platforms. The server part is a single desktop application based on J2EE, which provides a mature standard framework and a modular architecture. It can handle transactions and competition of components that are deployed on JETTY, an embedded web container within the Java server application for providing HTTP services. The data management is based on Apache DERBY, a relational database engine also embedded on the same Java based solution. This encapsulation allows concealment of unnecessary details about the installation, distribution, and configuration of all these components but with the flexibility to create and allocate many databases on different servers. The DERBY network module increases the scope of the installed database engine by providing traditional Java database network connections (JDBC-TCP/IP). This avoids scattering several database engines (a unique embedded engine defines the rules for accessing the distributed data). Java thin clients (Java 5 or above is the unique requirement) can be executed in the same computer than the server program (for example a desktop computer) but also server and client software can be distributed in a remote participation environment (wide area networks). The thin client provides graphic user interface to look for patterns (entire waveforms or specific structural forms) and display the most similar ones. This is obtained with HTTP requests and by generating dynamic content (servlets) in response to these client requests. (authors)

  4. Distributed open environment for data retrieval based on pattern recognition techniques

    Energy Technology Data Exchange (ETDEWEB)

    Pereira, A., E-mail: augusto.pereira@ciemat.e [Asociacion EURATOM/CIEMAT para Fusion, CIEMAT, Edificio 66, Avda. Complutense, 22, 28040 Madrid (Spain); Vega, J.; Castro, R.; Portas, A. [Asociacion EURATOM/CIEMAT para Fusion, CIEMAT, Edificio 66, Avda. Complutense, 22, 28040 Madrid (Spain)

    2010-07-15

    Pattern recognition methods for data retrieval have been applied to fusion databases for the localization and extraction of similar waveforms within temporal evolution signals. In order to standardize the use of these methods, a distributed open environment has been designed. It is based on a client/server architecture that supports distribution, interoperability and portability between heterogeneous platforms. The server part is a single desktop application based on J2EE (Java 2 Enterprise Edition), which provides a mature standard framework and a modular architecture. It can handle transactions and concurrency of components that are deployed on JETTY, an embedded web container within the Java server application for providing HTTP services. The data management is based on Apache DERBY, a relational database engine also embedded on the same Java based solution. This encapsulation allows hiding of unnecessary details about the installation, distribution, and configuration of all these components but with the flexibility to create and allocate many databases on different servers. The DERBY network module increases the scope of the installed database engine by providing traditional Java database network connections (JDBC-TCP/IP). This avoids scattering several database engines (a unique embedded engine defines the rules for accessing the distributed data). Java thin clients (Java 5 or above is the unique requirement) can be executed in the same computer than the server program (for example a desktop computer) but also server and client software can be distributed in a remote participation environment (wide area networks). The thin client provides graphic user interface to look for patterns (entire waveforms or specific structural forms) and display the most similar ones. This is obtained with HTTP requests and by generating dynamic content (servlets) in response to these client requests.

  5. 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.

  6. Container-code recognition system based on computer vision and deep neural networks

    Science.gov (United States)

    Liu, Yi; Li, Tianjian; Jiang, Li; Liang, Xiaoyao

    2018-04-01

    Automatic container-code recognition system becomes a crucial requirement for ship transportation industry in recent years. In this paper, an automatic container-code recognition system based on computer vision and deep neural networks is proposed. The system consists of two modules, detection module and recognition module. The detection module applies both algorithms based on computer vision and neural networks, and generates a better detection result through combination to avoid the drawbacks of the two methods. The combined detection results are also collected for online training of the neural networks. The recognition module exploits both character segmentation and end-to-end recognition, and outputs the recognition result which passes the verification. When the recognition module generates false recognition, the result will be corrected and collected for online training of the end-to-end recognition sub-module. By combining several algorithms, the system is able to deal with more situations, and the online training mechanism can improve the performance of the neural networks at runtime. The proposed system is able to achieve 93% of overall recognition accuracy.

  7. 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.

  8. Automated Detection of Selective Logging in Amazon Forests Using Airborne Lidar Data and Pattern Recognition Algorithms

    Science.gov (United States)

    Keller, M. M.; d'Oliveira, M. N.; Takemura, C. M.; Vitoria, D.; Araujo, L. S.; Morton, D. C.

    2012-12-01

    Selective logging, the removal of several valuable timber trees per hectare, is an important land use in the Brazilian Amazon and may degrade forests through long term changes in structure, loss of forest carbon and species diversity. Similar to deforestation, the annual area affected by selected logging has declined significantly in the past decade. Nonetheless, this land use affects several thousand km2 per year in Brazil. We studied a 1000 ha area of the Antimary State Forest (FEA) in the State of Acre, Brazil (9.304 ○S, 68.281 ○W) that has a basal area of 22.5 m2 ha-1 and an above-ground biomass of 231 Mg ha-1. Logging intensity was low, approximately 10 to 15 m3 ha-1. We collected small-footprint airborne lidar data using an Optech ALTM 3100EA over the study area once each in 2010 and 2011. The study area contained both recent and older logging that used both conventional and technologically advanced logging techniques. Lidar return density averaged over 20 m-2 for both collection periods with estimated horizontal and vertical precision of 0.30 and 0.15 m. A relative density model comparing returns from 0 to 1 m elevation to returns in 1-5 m elevation range revealed the pattern of roads and skid trails. These patterns were confirmed by ground-based GPS survey. A GIS model of the road and skid network was built using lidar and ground data. We tested and compared two pattern recognition approaches used to automate logging detection. Both segmentation using commercial eCognition segmentation and a Frangi filter algorithm identified the road and skid trail network compared to the GIS model. We report on the effectiveness of these two techniques.

  9. Dentate gyrus supports slope recognition memory, shades of grey-context pattern separation and recognition memory, and CA3 supports pattern completion for object memory.

    Science.gov (United States)

    Kesner, Raymond P; Kirk, Ryan A; Yu, Zhenghui; Polansky, Caitlin; Musso, Nick D

    2016-03-01

    In order to examine the role of the dorsal dentate gyrus (dDG) in slope (vertical space) recognition and possible pattern separation, various slope (vertical space) degrees were used in a novel exploratory paradigm to measure novelty detection for changes in slope (vertical space) recognition memory and slope memory pattern separation in Experiment 1. The results of the experiment indicate that control rats displayed a slope recognition memory function with a pattern separation process for slope memory that is dependent upon the magnitude of change in slope between study and test phases. In contrast, the dDG lesioned rats displayed an impairment in slope recognition memory, though because there was no significant interaction between the two groups and slope memory, a reliable pattern separation impairment for slope could not be firmly established in the DG lesioned rats. In Experiment 2, in order to determine whether, the dDG plays a role in shades of grey spatial context recognition and possible pattern separation, shades of grey were used in a novel exploratory paradigm to measure novelty detection for changes in the shades of grey context environment. The results of the experiment indicate that control rats displayed a shades of grey-context pattern separation effect across levels of separation of context (shades of grey). In contrast, the DG lesioned rats displayed a significant interaction between the two groups and levels of shades of grey suggesting impairment in a pattern separation function for levels of shades of grey. In Experiment 3 in order to determine whether the dorsal CA3 (dCA3) plays a role in object pattern completion, a new task requiring less training and using a choice that was based on choosing the correct set of objects on a two-choice discrimination task was used. The results indicated that control rats displayed a pattern completion function based on the availability of one, two, three or four cues. In contrast, the dCA3 lesioned rats

  10. Automatic recognition of cardiac arrhythmias based on the geometric patterns of Poincaré plots

    International Nuclear Information System (INIS)

    Zhang, Lijuan; Guo, Tianci; Xi, Bin; Fan, Yang; Wang, Kun; Bi, Jiacheng; Wang, Ying

    2015-01-01

    The Poincaré plot emerges as an effective tool for assessing cardiovascular autonomic regulation. It displays nonlinear characteristics of heart rate variability (HRV) from electrocardiographic (ECG) recordings and gives a global view of the long range of ECG signals. In the telemedicine or computer-aided diagnosis system, it would offer significant auxiliary information for diagnosis if the patterns of the Poincaré plots can be automatically classified. Therefore, we developed an automatic classification system to distinguish five geometric patterns of the Poincaré plots from four types of cardiac arrhythmias. The statistics features are designed on measurements and an ensemble classifier of three types of neural networks is proposed. Aiming at the difficulty to set a proper threshold for classifying the multiple categories, the threshold selection strategy is analyzed. 24 h ECG monitoring recordings from 674 patients, which have four types of cardiac arrhythmias, are adopted for recognition. For comparison, Support Vector Machine (SVM) classifiers with linear and Gaussian kernels are also applied. The experiment results demonstrate the effectiveness of the extracted features and the better performance of the designed classifier. Our study can be applied to diagnose the corresponding sinus rhythm and arrhythmia substrates disease automatically in the telemedicine and computer-aided diagnosis system. (paper)

  11. Investigation of Time Series Representations and Similarity Measures for Structural Damage Pattern Recognition

    Directory of Open Access Journals (Sweden)

    Wenjia Liu

    2013-01-01

    Full Text Available This paper investigates the time series representation methods and similarity measures for sensor data feature extraction and structural damage pattern recognition. Both model-based time series representation and dimensionality reduction methods are studied to compare the effectiveness of feature extraction for damage pattern recognition. The evaluation of feature extraction methods is performed by examining the separation of feature vectors among different damage patterns and the pattern recognition success rate. In addition, the impact of similarity measures on the pattern recognition success rate and the metrics for damage localization are also investigated. The test data used in this study are from the System Identification to Monitor Civil Engineering Structures (SIMCES Z24 Bridge damage detection tests, a rigorous instrumentation campaign that recorded the dynamic performance of a concrete box-girder bridge under progressively increasing damage scenarios. A number of progressive damage test case datasets and damage test data with different damage modalities are used. The simulation results show that both time series representation methods and similarity measures have significant impact on the pattern recognition success rate.

  12. Investigation of Time Series Representations and Similarity Measures for Structural Damage Pattern Recognition

    Science.gov (United States)

    Swartz, R. Andrew

    2013-01-01

    This paper investigates the time series representation methods and similarity measures for sensor data feature extraction and structural damage pattern recognition. Both model-based time series representation and dimensionality reduction methods are studied to compare the effectiveness of feature extraction for damage pattern recognition. The evaluation of feature extraction methods is performed by examining the separation of feature vectors among different damage patterns and the pattern recognition success rate. In addition, the impact of similarity measures on the pattern recognition success rate and the metrics for damage localization are also investigated. The test data used in this study are from the System Identification to Monitor Civil Engineering Structures (SIMCES) Z24 Bridge damage detection tests, a rigorous instrumentation campaign that recorded the dynamic performance of a concrete box-girder bridge under progressively increasing damage scenarios. A number of progressive damage test case datasets and damage test data with different damage modalities are used. The simulation results show that both time series representation methods and similarity measures have significant impact on the pattern recognition success rate. PMID:24191136

  13. Fingerprint Recognition using Fuzzy Logic with Triangular Pattern Template

    DEFF Research Database (Denmark)

    Hussain, Dil Muhammad Akbar

    2006-01-01

    A fingerprint is a pattern of ridges and valleys that exist on the surface of the finger. The uniqueness of a fingerprint is typically determined by the overall pattern of ridges and valleys as well as the local ridge structures e.g., a ridge bifurcation or a ridge ending, which are called minutiae...

  14. Application of data clustering to railway delay pattern recognition

    DEFF Research Database (Denmark)

    Cerreto, Fabrizio; Nielsen, Bo Friis; Nielsen, Otto Anker

    2018-01-01

    K-means clustering is employed to identify recurrent delay patterns on a high traffic railway line north of Copenhagen, Denmark. The clusters identify behavioral patterns in the very large (“big data”) data sets generated automatically and continuously by the railway signal system. The results re...

  15. A Global Online Handwriting Recognition Approach Based on Frequent Patterns

    Directory of Open Access Journals (Sweden)

    C. Gmati

    2018-06-01

    Full Text Available In this article, the handwriting signals are represented based on geometric and spatio-temporal characteristics to increase the feature vectors relevance of each object. The main goal was to extract features in the form of a numeric vector based on the extraction of frequent patterns. We used two types of frequent motifs (closed frequent patterns and maximal frequent patterns that can represent handwritten characters pertinently. These common features patterns are generated from a raw data transformation method to achieve high relevance. A database of words consisting of two different letters was created. The proposed application gives promising results and highlights the advantages that frequent pattern extraction algorithms can achieve, as well as the central role played by the “minimum threshold” parameter in the overall description of the characters.

  16. Innate pattern recognition and categorization in a jumping spider.

    Directory of Open Access Journals (Sweden)

    Yinnon Dolev

    Full Text Available The East African jumping spider Evarcha culicivora feeds indirectly on vertebrate blood by preferentially preying upon blood-fed Anopheles mosquitoes, the vectors of human malaria1, using the distinct resting posture and engorged abdomen characteristic of these specific prey as key elements for their recognition. To understand perceptual categorization of objects by these spiders, we investigated their predatory behavior toward different digital stimuli--abstract 'stick figure' representations of Anopheles constructed solely by known key identification elements, disarranged versions of these, as well as non-prey items and detailed images of alternative prey. We hypothesized that the abstract images representing Anopheles would be perceived as potential prey, and would be preferred to those of non-preferred prey. Spiders perceived the abstract stick figures of Anopheles specifically as their preferred prey, attacking them significantly more often than non-preferred prey, even when the comprising elements of the Anopheles stick figures were disarranged and disconnected from each other. However, if the relative angles between the elements of the disconnected stick figures of Anopheles were altered, the otherwise identical set of elements was no longer perceived as prey. These data show that E. culicivora is capable of making discriminations based on abstract concepts, such as the hypothetical angle formed by discontinuous elements. It is this inter-element angle rather than resting posture that is important for correct identification of Anopheles. Our results provide a glimpse of the underlying processes of object recognition in animals with minute brains, and suggest that these spiders use a local processing approach for object recognition, rather than a holistic or global approach. This study provides an excellent basis for a comparative analysis on feature extraction and detection by animals as diverse as bees and mammals.

  17. Innate Pattern Recognition and Categorization in a Jumping Spider

    Science.gov (United States)

    Dolev, Yinnon; Nelson, Ximena J.

    2014-01-01

    The East African jumping spider Evarcha culicivora feeds indirectly on vertebrate blood by preferentially preying upon blood-fed Anopheles mosquitoes, the vectors of human malaria1, using the distinct resting posture and engorged abdomen characteristic of these specific prey as key elements for their recognition. To understand perceptual categorization of objects by these spiders, we investigated their predatory behavior toward different digital stimuli - abstract ‘stick figure’ representations of Anopheles constructed solely by known key identification elements, disarranged versions of these, as well as non-prey items and detailed images of alternative prey. We hypothesized that the abstract images representing Anopheles would be perceived as potential prey, and would be preferred to those of non-preferred prey. Spiders perceived the abstract stick figures of Anopheles specifically as their preferred prey, attacking them significantly more often than non-preferred prey, even when the comprising elements of the Anopheles stick figures were disarranged and disconnected from each other. However, if the relative angles between the elements of the disconnected stick figures of Anopheles were altered, the otherwise identical set of elements was no longer perceived as prey. These data show that E. culicivora is capable of making discriminations based on abstract concepts, such as the hypothetical angle formed by discontinuous elements. It is this inter-element angle rather than resting posture that is important for correct identification of Anopheles. Our results provide a glimpse of the underlying processes of object recognition in animals with minute brains, and suggest that these spiders use a local processing approach for object recognition, rather than a holistic or global approach. This study provides an excellent basis for a comparative analysis on feature extraction and detection by animals as diverse as bees and mammals. PMID:24893306

  18. Structural pattern recognition methods based on string comparison for fusion databases

    International Nuclear Information System (INIS)

    Dormido-Canto, S.; Farias, G.; Dormido, R.; Vega, J.; Sanchez, J.; Duro, N.; Vargas, H.; Ratta, G.; Pereira, A.; Portas, A.

    2008-01-01

    Databases for fusion experiments are designed to store several million waveforms. Temporal evolution signals show the same patterns under the same plasma conditions and, therefore, pattern recognition techniques allow the identification of similar plasma behaviours. This article is focused on the comparison of structural pattern recognition methods. A pattern can be composed of simpler sub-patterns, where the most elementary sub-patterns are known as primitives. Selection of primitives is an essential issue in structural pattern recognition methods, because they determine what types of structural components can be constructed. However, it should be noted that there is not a general solution to extract structural features (primitives) from data. So, four different ways to compute the primitives of plasma waveforms are compared: (1) constant length primitives, (2) adaptive length primitives, (3) concavity method and (4) concavity method for noisy signals. Each method defines a code alphabet and, in this way, the pattern recognition problem is carried out via string comparisons. Results of the four methods with the TJ-II stellarator databases will be discussed

  19. Interfamily transfer of a plant pattern-recognition receptor confers broad-spectrum bacterial resistance

    NARCIS (Netherlands)

    Lacombe, S.; Rougon-Cardoso, A.; Sherwood, E.; Peeters, N.; Dahlbeck, D.; Esse, van H.P.; Smoker, M.; Rallapalli, G.; Thomma, B.P.H.J.; Staskawicz, B.; Jones, J.D.G.; Zipfel, C.

    2010-01-01

    Plant diseases cause massive losses in agriculture. Increasing the natural defenses of plants may reduce the impact of phytopathogens on agricultural productivity. Pattern-recognition receptors (PRRs) detect microbes by recognizing conserved pathogen-associated molecular patterns (PAMPs)1, 2, 3.

  20. Structural pattern recognition methods based on string comparison for fusion databases

    Energy Technology Data Exchange (ETDEWEB)

    Dormido-Canto, S. [Dpto. Informatica y Automatica - UNED 28040, Madrid (Spain)], E-mail: sebas@dia.uned.es; Farias, G.; Dormido, R. [Dpto. Informatica y Automatica - UNED 28040, Madrid (Spain); Vega, J. [Asociacion EURATOM/CIEMAT para Fusion, 28040, Madrid (Spain); Sanchez, J.; Duro, N.; Vargas, H. [Dpto. Informatica y Automatica - UNED 28040, Madrid (Spain); Ratta, G.; Pereira, A.; Portas, A. [Asociacion EURATOM/CIEMAT para Fusion, 28040, Madrid (Spain)

    2008-04-15

    Databases for fusion experiments are designed to store several million waveforms. Temporal evolution signals show the same patterns under the same plasma conditions and, therefore, pattern recognition techniques allow the identification of similar plasma behaviours. This article is focused on the comparison of structural pattern recognition methods. A pattern can be composed of simpler sub-patterns, where the most elementary sub-patterns are known as primitives. Selection of primitives is an essential issue in structural pattern recognition methods, because they determine what types of structural components can be constructed. However, it should be noted that there is not a general solution to extract structural features (primitives) from data. So, four different ways to compute the primitives of plasma waveforms are compared: (1) constant length primitives, (2) adaptive length primitives, (3) concavity method and (4) concavity method for noisy signals. Each method defines a code alphabet and, in this way, the pattern recognition problem is carried out via string comparisons. Results of the four methods with the TJ-II stellarator databases will be discussed.

  1. Finger Vein Recognition Using Local Line Binary Pattern

    Directory of Open Access Journals (Sweden)

    Bakhtiar Affendi Rosdi

    2011-11-01

    Full Text Available In this paper, a personal verification method using finger vein is presented. Finger vein can be considered more secured compared to other hands based biometric traits such as fingerprint and palm print because the features are inside the human body. In the proposed method, a new texture descriptor called local line binary pattern (LLBP is utilized as feature extraction technique. The neighbourhood shape in LLBP is a straight line, unlike in local binary pattern (LBP which is a square shape. Experimental results show that the proposed method using LLBP has better performance than the previous methods using LBP and local derivative pattern (LDP.

  2. Finger vein recognition using local line binary pattern.

    Science.gov (United States)

    Rosdi, Bakhtiar Affendi; Shing, Chai Wuh; Suandi, Shahrel Azmin

    2011-01-01

    In this paper, a personal verification method using finger vein is presented. Finger vein can be considered more secured compared to other hands based biometric traits such as fingerprint and palm print because the features are inside the human body. In the proposed method, a new texture descriptor called local line binary pattern (LLBP) is utilized as feature extraction technique. The neighbourhood shape in LLBP is a straight line, unlike in local binary pattern (LBP) which is a square shape. Experimental results show that the proposed method using LLBP has better performance than the previous methods using LBP and local derivative pattern (LDP).

  3. Finger Vein Recognition Using Local Line Binary Pattern

    Science.gov (United States)

    Rosdi, Bakhtiar Affendi; Shing, Chai Wuh; Suandi, Shahrel Azmin

    2011-01-01

    In this paper, a personal verification method using finger vein is presented. Finger vein can be considered more secured compared to other hands based biometric traits such as fingerprint and palm print because the features are inside the human body. In the proposed method, a new texture descriptor called local line binary pattern (LLBP) is utilized as feature extraction technique. The neighbourhood shape in LLBP is a straight line, unlike in local binary pattern (LBP) which is a square shape. Experimental results show that the proposed method using LLBP has better performance than the previous methods using LBP and local derivative pattern (LDP). PMID:22247670

  4. Supervised and Unsupervised Classification for Pattern Recognition Purposes

    Directory of Open Access Journals (Sweden)

    Catalina COCIANU

    2006-01-01

    Full Text Available A cluster analysis task has to identify the grouping trends of data, to decide on the sound clusters as well as to validate somehow the resulted structure. The identification of the grouping tendency existing in a data collection assumes the selection of a framework stated in terms of a mathematical model allowing to express the similarity degree between couples of particular objects, quasi-metrics expressing the similarity between an object an a cluster and between clusters, respectively. In supervised classification, we are provided with a collection of preclassified patterns, and the problem is to label a newly encountered pattern. Typically, the given training patterns are used to learn the descriptions of classes which in turn are used to label a new pattern. The final section of the paper presents a new methodology for supervised learning based on PCA. The classes are represented in the measurement/feature space by a continuous repartitions

  5. Recognition of distinctive patterns of gallium-67 distribution in sarcoidosis

    International Nuclear Information System (INIS)

    Sulavik, S.B.; Spencer, R.P.; Weed, D.A.; Shapiro, H.R.; Shiue, S.T.; Castriotta, R.J.

    1990-01-01

    Assessment of gallium-67 ( 67 Ga) uptake in the salivary and lacrimal glands and intrathoracic lymph nodes was made in 605 consecutive patients including 65 with sarcoidosis. A distinctive intrathoracic lymph node 67 Ga uptake pattern, resembling the Greek letter lambda, was observed only in sarcoidosis (72%). Symmetrical lacrimal gland and parotid gland 67 Ga uptake (panda appearance) was noted in 79% of sarcoidosis patients. A simultaneous lambda and panda pattern (62%) or a panda appearance with radiographic bilateral, symmetrical, hilar lymphadenopathy (6%) was present only in sarcoidosis patients. The presence of either of these patterns was particularly prevalent in roentgen Stages I (80%) or II (74%). We conclude that simultaneous (a) lambda and panda images, or (b) a panda image with bilateral symmetrical hilar lymphadenopathy on chest X-ray represent distinctive patterns which are highly specific for sarcoidosis, and may obviate the need for invasive diagnostic procedures

  6. Sub-pattern based multi-manifold discriminant analysis for face recognition

    Science.gov (United States)

    Dai, Jiangyan; Guo, Changlu; Zhou, Wei; Shi, Yanjiao; Cong, Lin; Yi, Yugen

    2018-04-01

    In this paper, we present a Sub-pattern based Multi-manifold Discriminant Analysis (SpMMDA) algorithm for face recognition. Unlike existing Multi-manifold Discriminant Analysis (MMDA) approach which is based on holistic information of face image for recognition, SpMMDA operates on sub-images partitioned from the original face image and then extracts the discriminative local feature from the sub-images separately. Moreover, the structure information of different sub-images from the same face image is considered in the proposed method with the aim of further improve the recognition performance. Extensive experiments on three standard face databases (Extended YaleB, CMU PIE and AR) demonstrate that the proposed method is effective and outperforms some other sub-pattern based face recognition methods.

  7. 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.

  8. Sonographic Diagnosis of Tubal Cancer with IOTA Simple Rules Plus Pattern Recognition

    Science.gov (United States)

    Tongsong, Theera; Wanapirak, Chanane; Tantipalakorn, Charuwan; Tinnangwattana, Dangcheewan

    2017-11-26

    Objective: To evaluate diagnostic performance of IOTA simple rules plus pattern recognition in predicting tubal cancer. Methods: Secondary analysis was performed on prospective database of our IOTA project. The patients recruited in the project were those who were scheduled for pelvic surgery due to adnexal masses. The patients underwent ultrasound examinations within 24 hours before surgery. On ultrasound examination, the masses were evaluated using the well-established IOTA simple rules plus pattern recognition (sausage-shaped appearance, incomplete septum, visible ipsilateral ovaries) to predict tubal cancer. The gold standard diagnosis was based on histological findings or operative findings. Results: A total of 482 patients, including 15 cases of tubal cancer, were evaluated by ultrasound preoperatively. The IOTA simple rules plus pattern recognition gave a sensitivity of 86.7% (13 in 15) and specificity of 97.4%. Sausage-shaped appearance was identified in nearly all cases (14 in 15). Incomplete septa and normal ovaries could be identified in 33.3% and 40%, respectively. Conclusion: IOTA simple rules plus pattern recognition is relatively effective in predicting tubal cancer. Thus, we propose the simple scheme in diagnosis of tubal cancer as follows. First of all, the adnexal masses are evaluated with IOTA simple rules. If the B-rules could be applied, tubal cancer is reliably excluded. If the M-rules could be applied or the result is inconclusive, careful delineation of the mass with pattern recognition should be performed. Creative Commons Attribution License

  9. Automatic micropropagation of plants--the vision-system: graph rewriting as pattern recognition

    Science.gov (United States)

    Schwanke, Joerg; Megnet, Roland; Jensch, Peter F.

    1993-03-01

    The automation of plant-micropropagation is necessary to produce high amounts of biomass. Plants have to be dissected on particular cutting-points. A vision-system is needed for the recognition of the cutting-points on the plants. With this background, this contribution is directed to the underlying formalism to determine cutting-points on abstract-plant models. We show the usefulness of pattern recognition by graph-rewriting along with some examples in this context.

  10. 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...

  11. Dysphonia Detected by Pattern Recognition of Spectral Composition.

    Science.gov (United States)

    Leinonen, Lea; And Others

    1992-01-01

    This study analyzed production of a long vowel sound within Finnish words by normal or dysphonic voices, using the Self-Organizing Map, the artificial neural network algorithm of T. Kohonen which produces two-dimensional representations of speech. The method was found to be both sensitive and specific in the detection of dysphonia. (Author/JDD)

  12. 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

  13. Extracting Association Patterns in Network Communications

    Science.gov (United States)

    Portela, Javier; Villalba, Luis Javier García; Trujillo, Alejandra Guadalupe Silva; Orozco, Ana Lucila Sandoval; Kim, Tai-hoon

    2015-01-01

    In network communications, mixes provide protection against observers hiding the appearance of messages, patterns, length and links between senders and receivers. Statistical disclosure attacks aim to reveal the identity of senders and receivers in a communication network setting when it is protected by standard techniques based on mixes. This work aims to develop a global statistical disclosure attack to detect relationships between users. The only information used by the attacker is the number of messages sent and received by each user for each round, the batch of messages grouped by the anonymity system. A new modeling framework based on contingency tables is used. The assumptions are more flexible than those used in the literature, allowing to apply the method to multiple situations automatically, such as email data or social networks data. A classification scheme based on combinatoric solutions of the space of rounds retrieved is developed. Solutions about relationships between users are provided for all pairs of users simultaneously, since the dependence of the data retrieved needs to be addressed in a global sense. PMID:25679311

  14. Extracting Association Patterns in Network Communications

    Directory of Open Access Journals (Sweden)

    Javier Portela

    2015-02-01

    Full Text Available In network communications, mixes provide protection against observers hiding the appearance of messages, patterns, length and links between senders and receivers. Statistical disclosure attacks aim to reveal the identity of senders and receivers in a communication network setting when it is protected by standard techniques based on mixes. This work aims to develop a global statistical disclosure attack to detect relationships between users. The only information used by the attacker is the number of messages sent and received by each user for each round, the batch of messages grouped by the anonymity system. A new modeling framework based on contingency tables is used. The assumptions are more flexible than those used in the literature, allowing to apply the method to multiple situations automatically, such as email data or social networks data. A classification scheme based on combinatoric solutions of the space of rounds retrieved is developed. Solutions about relationships between users are provided for all pairs of users simultaneously, since the dependence of the data retrieved needs to be addressed in a global sense.

  15. Dialogue act recognition under uncertainty using Bayesian networks

    NARCIS (Netherlands)

    Keizer, S.; op den Akker, Hendrikus J.A.

    2007-01-01

    In this paper we discuss the task of dialogue act recognition as a part of interpreting user utterances in context. To deal with the uncertainty that is inherent in natural language processing in general and dialogue act recognition in particular we use machine learning techniques to train

  16. Human Walking Pattern Recognition Based on KPCA and SVM with Ground Reflex Pressure Signal

    Directory of Open Access Journals (Sweden)

    Zhaoqin Peng

    2013-01-01

    Full Text Available Algorithms based on the ground reflex pressure (GRF signal obtained from a pair of sensing shoes for human walking pattern recognition were investigated. The dimensionality reduction algorithms based on principal component analysis (PCA and kernel principal component analysis (KPCA for walking pattern data compression were studied in order to obtain higher recognition speed. Classifiers based on support vector machine (SVM, SVM-PCA, and SVM-KPCA were designed, and the classification performances of these three kinds of algorithms were compared using data collected from a person who was wearing the sensing shoes. Experimental results showed that the algorithm fusing SVM and KPCA had better recognition performance than the other two methods. Experimental outcomes also confirmed that the sensing shoes developed in this paper can be employed for automatically recognizing human walking pattern in unlimited environments which demonstrated the potential application in the control of exoskeleton robots.

  17. The Role of Verbal Instruction and Visual Guidance in Training Pattern Recognition

    Directory of Open Access Journals (Sweden)

    Jamie S. North

    2017-09-01

    Full Text Available We used a novel approach to examine whether it is possible to improve the perceptual–cognitive skill of pattern recognition using a video-based training intervention. Moreover, we investigated whether any improvements in pattern recognition transfer to an improved ability to make anticipation judgments. Finally, we compared the relative effectiveness of verbal and visual guidance interventions compared to a group that merely viewed the same sequences without any intervention and a control group that only completed pre- and post-tests. We found a significant effect for time of testing. Participants were more sensitive in their ability to perceive patterns and distinguish between novel and familiar sequences at post- compared to pre-test. However, this improvement was not influenced by the nature of the intervention, despite some trends in the data. An analysis of anticipation accuracy showed no change from pre- to post-test following the pattern recognition training intervention, suggesting that the link between pattern perception and anticipation may not be strong. We present a series of recommendations for scientists and practitioners when employing training methods to improve pattern recognition and anticipation.

  18. Landscape metrics for three-dimension urban pattern recognition

    Science.gov (United States)

    Liu, M.; Hu, Y.; Zhang, W.; Li, C.

    2017-12-01

    Understanding how landscape pattern determines population or ecosystem dynamics is crucial for managing our landscapes. Urban areas are becoming increasingly dominant social-ecological systems, so it is important to understand patterns of urbanization. Most studies of urban landscape pattern examine land-use maps in two dimensions because the acquisition of 3-dimensional information is difficult. We used Brista software based on Quickbird images and aerial photos to interpret the height of buildings, thus incorporating a 3-dimensional approach. We estimated the feasibility and accuracy of this approach. A total of 164,345 buildings in the Liaoning central urban agglomeration of China, which included seven cities, were measured. Twelve landscape metrics were proposed or chosen to describe the urban landscape patterns in 2- and 3-dimensional scales. The ecological and social meaning of landscape metrics were analyzed with multiple correlation analysis. The results showed that classification accuracy compared with field surveys was 87.6%, which means this method for interpreting building height was acceptable. The metrics effectively reflected the urban architecture in relation to number of buildings, area, height, 3-D shape and diversity aspects. We were able to describe the urban characteristics of each city with these metrics. The metrics also captured ecological and social meanings. The proposed landscape metrics provided a new method for urban landscape analysis in three dimensions.

  19. Automatic SIMD parallelization of embedded applications based on pattern recognition

    NARCIS (Netherlands)

    Manniesing, R.; Karkowski, I.P.; Corporaal, H.

    2000-01-01

    This paper investigates the potential for automatic mapping of typical embedded applications to architectures with multimedia instruction set extensions. For this purpose a (pattern matching based) code transformation engine is used, which involves a three-step process of matching, condition

  20. Recognition of periodic behavioral patterns from streaming mobility data

    NARCIS (Netherlands)

    Baratchi, Mitra; Meratnia, Nirvana; Havinga, Paul J.M.; Stojmenovic, Ivan; Cheng, Zixue; Guo, Song

    2014-01-01

    Ubiquitous location-aware sensing devices have facilitated collection of large volumes of mobility data streams from moving entities such as people and animals, among others. Extraction of various types of periodic behavioral patterns hidden in such large volume of mobility data helps in

  1. Determination of ocular torsion by means of automatic pattern recognition

    NARCIS (Netherlands)

    Groen, E.L.; Bos, J.E.; Nacken, P.F.M.; Graaf, B. de

    1996-01-01

    A new, automatic method for determination of human ocular torsion (OT) was devel-oped based on the tracking of iris patterns in digitized video images. Instead of quanti-fying OT by means of cross-correlation of circular iris samples, a procedure commonly applied, this new method automatically

  2. Determination of ocular torsion by means of automatic pattern recognition

    NARCIS (Netherlands)

    Groen, Eric; Bos, Jelte E.; Nacken, Peter F M; De Graaf, Bernd

    A new, automatic method for determination of human ocular torsion (OT) was developed based on the tracking of iris patterns in digitized video images. Instead of quantifying OT by means of cross-correlation of circular iris samples, a procedure commonly applied, this new method automatically selects

  3. Increased neutrophil expression of pattern recognition receptors during COPD exacerbations

    NARCIS (Netherlands)

    Pouwels, Simon D.; Van Geffen, Wouter H.; Jonker, Marnix R.; Kerstjens, Huib A. M.; Nawijn, Martijn C.; Heijink, Irene H.

    Previously, we observed increased serum levels of damage-associated molecular patterns (DAMPs) during COPD exacerbations. Here, gene expression of DAMP receptors was measured in peripheral blood neutrophils of COPD patients during stable disease and severe acute exacerbation. The expression of

  4. SAR Target Recognition Using the Multi-aspect-aware Bidirectional LSTM Recurrent Neural Networks

    OpenAIRE

    Zhang, Fan; Hu, Chen; Yin, Qiang; Li, Wei; Li, Hengchao; Hong, Wen

    2017-01-01

    The outstanding pattern recognition performance of deep learning brings new vitality to the synthetic aperture radar (SAR) automatic target recognition (ATR). However, there is a limitation in current deep learning based ATR solution that each learning process only handle one SAR image, namely learning the static scattering information, while missing the space-varying information. It is obvious that multi-aspect joint recognition introduced space-varying scattering information should improve ...

  5. Rough-fuzzy pattern recognition applications in bioinformatics and medical imaging

    CERN Document Server

    Maji, Pradipta

    2012-01-01

    Learn how to apply rough-fuzzy computing techniques to solve problems in bioinformatics and medical image processing Emphasizing applications in bioinformatics and medical image processing, this text offers a clear framework that enables readers to take advantage of the latest rough-fuzzy computing techniques to build working pattern recognition models. The authors explain step by step how to integrate rough sets with fuzzy sets in order to best manage the uncertainties in mining large data sets. Chapters are logically organized according to the major phases of pattern recognition systems dev

  6. Recognition of higher order patterns in proteins: immunologic kernels.

    Directory of Open Access Journals (Sweden)

    Robert D Bremel

    Full Text Available By applying analysis of the principal components of amino acid physical properties we predicted cathepsin cleavage sites, MHC binding affinity, and probability of B-cell epitope binding of peptides in tetanus toxin and in ten diverse additional proteins. Cross-correlation of these metrics, for peptides of all possible amino acid index positions, each evaluated in the context of a ±25 amino acid flanking region, indicated that there is a strongly repetitive pattern of short peptides of approximately thirty amino acids each bounded by cathepsin cleavage sites and each comprising B-cell linear epitopes, MHC-I and MHC-II binding peptides. Such "immunologic kernel" peptides comprise all signals necessary for adaptive immunologic cognition, response and recall. The patterns described indicate a higher order spatial integration that forms a symbolic logic coordinating the adaptive immune system.

  7. Pattern recognition invariant under changes of scale and orientation

    Science.gov (United States)

    Arsenault, Henri H.; Parent, Sebastien; Moisan, Sylvain

    1997-08-01

    We have used a modified method proposed by neiberg and Casasent to successfully classify five kinds of military vehicles. The method uses a wedge filter to achieve scale invariance, and lines in a multi-dimensional feature space correspond to each target with out-of-plane orientations over 360 degrees around a vertical axis. The images were not binarized, but were filtered in a preprocessing step to reduce aliasing. The feature vectors were normalized and orthogonalized by means of a neural network. Out-of-plane rotations of 360 degrees and scale changes of a factor of four were considered. Error-free classification was achieved.

  8. Study on Analysis and Pattern Recognition of the Manifestation of the Pulse Detection of Cerebrovascular Disease

    Energy Technology Data Exchange (ETDEWEB)

    Jing, J; Wang, Y C; Hong, W X; Zhang, W P [Department of Biomedical Engineering, University of Yanshan, Qinhuangdao, Hebei Province, 066004 (China)

    2006-10-15

    Cerebrovascular Disease (CVD) is also called stroke in Traditional Chinese Medicine (TCM). CVD is a kind of frequent diseases with high incidence, high death rate, high deformity rate and high relapse rate. The pathogenesis of CVD has relation to many factors. In modern medicine, we can make use of various instruments to check many biochemical parameters. However, at present, the early detection of CVD can mostly be done artificially by specialists. In TCM the salted expert can detect the state of a CVD patient by felling his (or her) pulse. It is significant to apply the modern information and engineering techniques to the early discovery of CVD. It is also a challenge to do this in fact. In this paper, the authors presented a detection method of CVD basing on analysis and pattern recognition of Manifestation of the Pulse of TCM using wavelet technology and Neural Networks. Pulse signals from normal health persons and CVD patients were studied comparatively. This research method is flexible to deal with other physiological signals.

  9. Development of pattern recognition algorithms for particles detection from atmospheric images

    International Nuclear Information System (INIS)

    Khatchadourian, S.

    2010-01-01

    The HESS experiment consists of a system of telescopes destined to observe cosmic rays. Since the project has achieved a high level of performances, a second phase of the project has been initiated. This implies the addition of a new telescope which is more sensitive than its predecessors and which is capable of collecting a huge amount of images. In this context, all data collected by the telescope can not be retained because of storage limitations. Therefore, a new real-time system trigger must be designed in order to select interesting events on the fly. The purpose of this thesis was to propose a trigger solution to efficiently discriminate events (images) which are captured by the telescope. The first part of this thesis was to develop pattern recognition algorithms to be implemented within the trigger. A processing chain based on neural networks and Zernike moments has been validated. The second part of the thesis has focused on the implementation of the proposed algorithms onto an FPGA target, taking into account the application constraints in terms of resources and execution time. (author)

  10. Application of the new pattern recognition system in the new e-nose to detecting Chinese spirits

    International Nuclear Information System (INIS)

    Gu Yu; Li Qiang

    2014-01-01

    We present a new pattern recognition system based on moving average and linear discriminant analysis (LDA), which can be used to process the original signal of the new polymer quartz piezoelectric crystal air-sensitive sensor system we designed, called the new e-nose. Using the new e-nose, we obtain the template datum of Chinese spirits via a new pattern recognition system. To verify the effectiveness of the new pattern recognition system, we select three kinds of Chinese spirits to test, our results confirm that the new pattern recognition system can perfectly identify and distinguish between the Chinese spirits. (electromagnetism, optics, acoustics, heat transfer, classical mechanics, and fluid dynamics)

  11. 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.

  12. 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.

  13. Oxidation-specific epitopes are danger-associated molecular patterns recognized by pattern recognition receptors of innate immunity

    DEFF Research Database (Denmark)

    Miller, Yury I; Choi, Soo-Ho; Wiesner, Philipp

    2011-01-01

    are a major target of innate immunity, recognized by a variety of "pattern recognition receptors" (PRRs). By analogy with microbial "pathogen-associated molecular patterns" (PAMPs), we postulate that host-derived, oxidation-specific epitopes can be considered to represent "danger (or damage......)-associated molecular patterns" (DAMPs). We also argue that oxidation-specific epitopes present on apoptotic cells and their cellular debris provided the primary evolutionary pressure for the selection of such PRRs. Furthermore, because many PAMPs on microbes share molecular identity and/or mimicry with oxidation...

  14. Energy prediction using spatiotemporal pattern networks

    Energy Technology Data Exchange (ETDEWEB)

    Jiang, Zhanhong; Liu, Chao; Akintayo, Adedotun; Henze, Gregor P.; Sarkar, Soumik

    2017-11-01

    This paper presents a novel data-driven technique based on the spatiotemporal pattern network (STPN) for energy/power prediction for complex dynamical systems. Built on symbolic dynamical filtering, the STPN framework is used to capture not only the individual system characteristics but also the pair-wise causal dependencies among different sub-systems. To quantify causal dependencies, a mutual information based metric is presented and an energy prediction approach is subsequently proposed based on the STPN framework. To validate the proposed scheme, two case studies are presented, one involving wind turbine power prediction (supply side energy) using the Western Wind Integration data set generated by the National Renewable Energy Laboratory (NREL) for identifying spatiotemporal characteristics, and the other, residential electric energy disaggregation (demand side energy) using the Building America 2010 data set from NREL for exploring temporal features. In the energy disaggregation context, convex programming techniques beyond the STPN framework are developed and applied to achieve improved disaggregation performance.

  15. Page Oriented Holographic Memories And Optical Pattern Recognition

    Science.gov (United States)

    Caulfield, H. J.

    1987-08-01

    In the twenty-two years since VanderLugt's introduction of holographic matched filtering, the intensive research carried out throughout the world has led to no applications in complex environment. This leads one to the suspicion that the VanderLugt filter technique is insufficiently complex to handle truly complex problems. Therefore, it is of great interest to increase the complexity of the VanderLugt filtering operation. We introduce here an approach to the real time filter assembly: use of page oriented holographic memories and optically addressed SLMs to achieve intelligent and fast reprogramming of the filters using a 10 4 to 10 6 stored pattern base.

  16. 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.

  17. Social networking patterns/hazards among teenagers.

    Science.gov (United States)

    Machold, C; Judge, G; Mavrinac, A; Elliott, J; Murphy, A M; Roche, E

    2012-05-01

    Social Networking Sites (SNSs) have grown substantially, posing new hazards to teenagers. This study aimed to determine general patterns of Internet usage among Irish teenagers aged 11-16 years, and to identify potential hazards, including; bullying, inappropriate contact, overuse, addiction and invasion of users' privacy. A cross-sectional study design was employed to survey students at three Irish secondary schools, with a sample of 474 completing a questionnaire. 202 (44%) (n = 460) accessed the Internet using a shared home computer. Two hours or less were spent online daily by 285(62%), of whom 450 (98%) were unsupervised. 306 (72%) (n = 425) reported frequent usage of SNSs, 403 (95%) of whom were Facebook users. 42 (10%) males and 51 (12%) females experienced bullying online, while 114 (27%) reported inappropriate contact from others. Concerning overuse and the risk of addiction, 140 (33%) felt they accessed SNSs too often. These patterns among Irish teenagers suggest that SNS usage poses significant dangers, which are going largely unaddressed.

  18. Social networking patterns/hazards among teenagers.

    LENUS (Irish Health Repository)

    Machold, C

    2012-05-01

    Social Networking Sites (SNSs) have grown substantially, posing new hazards to teenagers. This study aimed to determine general patterns of Internet usage among Irish teenagers aged 11-16 years, and to identify potential hazards, including; bullying, inappropriate contact, overuse, addiction and invasion of users\\' privacy. A cross-sectional study design was employed to survey students at three Irish secondary schools, with a sample of 474 completing a questionnaire. 202 (44%) (n = 460) accessed the Internet using a shared home computer. Two hours or less were spent online daily by 285(62%), of whom 450 (98%) were unsupervised. 306 (72%) (n = 425) reported frequent usage of SNSs, 403 (95%) of whom were Facebook users. 42 (10%) males and 51 (12%) females experienced bullying online, while 114 (27%) reported inappropriate contact from others. Concerning overuse and the risk of addiction, 140 (33%) felt they accessed SNSs too often. These patterns among Irish teenagers suggest that SNS usage poses significant dangers, which are going largely unaddressed.

  19. Protein recognition by a pattern-generating fluorescent molecular probe

    Science.gov (United States)

    Pode, Zohar; Peri-Naor, Ronny; Georgeson, Joseph M.; Ilani, Tal; Kiss, Vladimir; Unger, Tamar; Markus, Barak; Barr, Haim M.; Motiei, Leila; Margulies, David

    2017-12-01

    Fluorescent molecular probes have become valuable tools in protein research; however, the current methods for using these probes are less suitable for analysing specific populations of proteins in their native environment. In this study, we address this gap by developing a unimolecular fluorescent probe that combines the properties of small-molecule-based probes and cross-reactive sensor arrays (the so-called chemical 'noses/tongues'). On the one hand, the probe can detect different proteins by generating unique identification (ID) patterns, akin to cross-reactive arrays. On the other hand, its unimolecular scaffold and selective binding enable this ID-generating probe to identify combinations of specific protein families within complex mixtures and to discriminate among isoforms in living cells, where macroscopic arrays cannot access. The ability to recycle the molecular device and use it to track several binding interactions simultaneously further demonstrates how this approach could expand the fluorescent toolbox currently used to detect and image proteins.

  20. Pattern Recognition of Gene Expression with Singular Spectrum Analysis

    Directory of Open Access Journals (Sweden)

    Hossein Hassani

    2014-07-01

    Full Text Available Drosophila segmentation as a model organism is one of the most highly studied. Among many maternal segmentation coordinate genes, bicoid protein pattern plays a significant role during Drosophila embryogenesis, since this gradient determines most aspects of head and thorax development. Despite the fact that several models have been proposed to describe the bicoid gradient, due to its association with considerable error, each can only partially explain bicoid characteristics. In this paper, a modified version of singular spectrum analysis is examined for filtering and extracting the bicoid gene expression signal. The results with strong evidence indicate that the proposed technique is able to remove noise more effectively and can be considered as a promising method for filtering gene expression measurements for other applications.

  1. Pattern recognition methodologies and deterministic evaluation of seismic hazard: A strategy to increase earthquake preparedness

    International Nuclear Information System (INIS)

    Peresan, Antonella; Panza, Giuliano F.; Gorshkov, Alexander I.; Aoudia, Abdelkrim

    2001-05-01

    Several algorithms, structured according to a general pattern-recognition scheme, have been developed for the space-time identification of strong events. Currently, two of such algorithms are applied to the Italian territory, one for the recognition of earthquake-prone areas and the other, namely CN algorithm, for earthquake prediction purposes. These procedures can be viewed as independent experts, hence they can be combined to better constrain the alerted seismogenic area. We examine here the possibility to integrate CN intermediate-term medium-range earthquake predictions, pattern recognition of earthquake-prone areas and deterministic hazard maps, in order to associate CN Times of Increased Probability (TIPs) to a set of appropriate scenarios of ground motion. The advantage of this procedure mainly consists in the time information provided by predictions, useful to increase preparedness of safety measures and to indicate a priority for detailed seismic risk studies to be performed at a local scale. (author)

  2. A Dynamic Interval-Valued Intuitionistic Fuzzy Sets Applied to Pattern Recognition

    Directory of Open Access Journals (Sweden)

    Zhenhua Zhang

    2013-01-01

    Full Text Available We present dynamic interval-valued intuitionistic fuzzy sets (DIVIFS, which can improve the recognition accuracy when they are applied to pattern recognition. By analyzing the degree of hesitancy, we propose some DIVIFS models from intuitionistic fuzzy sets (IFS and interval-valued IFS (IVIFS. And then we present a novel ranking condition on the distance of IFS and IVIFS and introduce some distance measures of DIVIFS satisfying the ranking condition. Finally, a pattern recognition example applied to medical diagnosis decision making is given to demonstrate the application of DIVIFS and its distances. The simulation results show that the DIVIFS method is more comprehensive and flexible than the IFS method and the IVIFS method.

  3. Foundations for a syntatic pattern recognition system for genomic DNA sequences

    Energy Technology Data Exchange (ETDEWEB)

    Searles, D.B.

    1993-03-01

    The goal of the proposed work is the creation of a software system that will perform sophisticated pattern recognition and related functions at a level of abstraction and with expressive power beyond current general-purpose pattern-matching systems for biological sequences; and with a more uniform language, environment, and graphical user interface, and with greater flexibility, extensibility, embeddability, and ability to incorporate other algorithms, than current special-purpose analytic software.

  4. Machine learning and pattern recognition from surface molecular architectures.

    Science.gov (United States)

    Maksov, Artem; Ziatdinov, Maxim; Fujii, Shintaro; Sumpter, Bobby; Kalinin, Sergei

    The ability to utilize molecular assemblies as data storage devices requires capability to identify individual molecular states on a scale of thousands of molecules. We present a novel method of applying machine learning techniques for extraction of positional and rotational information from ultra-high vacuum scanning tunneling microscopy (STM) images and apply it to self-assembled monolayer of π-bowl sumanene molecules on gold. From density functional theory (DFT) simulations, we assume existence of distinct polar and multiple azimuthal rotational states. We use DFT-generated templates in conjunction with Markov Chain Monte Carlo (MCMC) sampler and noise modeling to create synthetic images representative of our model. We extract positional information of each molecule and use nearest neighbor criteria to construct a graph input to Markov Random Field (MRF) model to identify polar rotational states. We train a convolutional Neural Network (cNN) on a synthetic dataset and combine it with MRF model to classify molecules based on their azimuthal rotational state. We demonstrate effectiveness of such approach compared to other methods. Finally, we apply our approach to experimental images and achieve complete rotational class information extraction. This research was sponsored by the Division of Materials Sciences and Engineering, Office of Science, Basic Energy Sciences, US DOE.

  5. Binary pattern flavored feature extractors for Facial Expression Recognition: An overview

    DEFF Research Database (Denmark)

    Kristensen, Rasmus Lyngby; Tan, Zheng-Hua; Ma, Zhanyu

    2015-01-01

    This paper conducts a survey of modern binary pattern flavored feature extractors applied to the Facial Expression Recognition (FER) problem. In total, 26 different feature extractors are included, of which six are selected for in depth description. In addition, the paper unifies important FER...

  6. 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…

  7. An Application of Discriminant Analysis to Pattern Recognition of Selected Contaminated Soil Features in Thin Sections

    DEFF Research Database (Denmark)

    Ribeiro, Alexandra B.; Nielsen, Allan Aasbjerg

    1997-01-01

    qualitative microprobe results: present elements Al, Si, Cr, Fe, As (associated with others). Selected groups of calibrated images (same light conditions and magnification) submitted to discriminant analysis, in order to find a pattern of recognition in the soil features corresponding to contamination already...

  8. A New Functional Classification of Glucuronoyl Esterases by Peptide Pattern Recognition

    DEFF Research Database (Denmark)

    Wittrup Agger, Jane; Busk, Peter Kamp; Pilgaard, Bo

    2017-01-01

    of characterized enzymes exist and the exact activity is still uncertain. Here peptide pattern recognition is used as a bioinformatic tool to identify and group new CE15 proteins that are likely to have glucuronoyl esterase activity. 1024 CE15-like sequences were drawn from GenBank and grouped into 24 groups...

  9. Identification of a β-glucosidase from the Mucor circinelloides genome by peptide pattern recognition

    DEFF Research Database (Denmark)

    Yuhong, Huang; Busk, Peter Kamp; Grell, Morten Nedergaard

    2014-01-01

    Mucor circinelloides produces plant cell wall degrading enzymes that allow it to grow on complex polysaccharides. Although the genome of M. circinelloides has been sequenced, only few plant cell wall degrading enzymes are annotated in this species. We applied peptide pattern recognition, which...

  10. Pattern recognition in cyclic and discrete skills performance from inertial measurement units

    NARCIS (Netherlands)

    Seifert, Ludovic; L'Hermette, Maxime; Komar, John; Orth, Dominic; Mell, Florian; Merriaux, Pierre; Grenet, Pierre; Caritu, Yanis; Hérault, Romain; Dovgalecs, Vladislavs; Davids, Keith

    2014-01-01

    The aim of this study is to compare and validate an Inertial Measurement Unit (IMU) relative to an optic system, and to propose methods for pattern recognition to capture behavioural dynamics during sport performance. IMU validation was conducted by comparing the motions of the two arms of a

  11. 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)

  12. A Hierarchical Approach to Real-time Activity Recognition in Body Sensor Networks

    DEFF Research Database (Denmark)

    Wang, Liang; Gu, Tao; Tao, Xianping

    2012-01-01

    Real-time activity recognition in body sensor networks is an important and challenging task. In this paper, we propose a real-time, hierarchical model to recognize both simple gestures and complex activities using a wireless body sensor network. In this model, we rst use a fast and lightweight al...

  13. Real-time Human Activity Recognition using a Body Sensor Network

    DEFF Research Database (Denmark)

    Wang, Liang; Gu, Tao; Chen, Hanhua

    2010-01-01

    Real-time activity recognition using body sensor networks is an important and challenging task and it has many potential applications. In this paper, we propose a realtime, hierarchical model to recognize both simple gestures and complex activities using a wireless body sensor network. In this mo...

  14. Three dimensional pattern recognition using feature-based indexing and rule-based search

    Science.gov (United States)

    Lee, Jae-Kyu

    In flexible automated manufacturing, robots can perform routine operations as well as recover from atypical events, provided that process-relevant information is available to the robot controller. Real time vision is among the most versatile sensing tools, yet the reliability of machine-based scene interpretation can be questionable. The effort described here is focused on the development of machine-based vision methods to support autonomous nuclear fuel manufacturing operations in hot cells. This thesis presents a method to efficiently recognize 3D objects from 2D images based on feature-based indexing. Object recognition is the identification of correspondences between parts of a current scene and stored views of known objects, using chains of segments or indexing vectors. To create indexed object models, characteristic model image features are extracted during preprocessing. Feature vectors representing model object contours are acquired from several points of view around each object and stored. Recognition is the process of matching stored views with features or patterns detected in a test scene. Two sets of algorithms were developed, one for preprocessing and indexed database creation, and one for pattern searching and matching during recognition. At recognition time, those indexing vectors with the highest match probability are retrieved from the model image database, using a nearest neighbor search algorithm. The nearest neighbor search predicts the best possible match candidates. Extended searches are guided by a search strategy that employs knowledge-base (KB) selection criteria. The knowledge-based system simplifies the recognition process and minimizes the number of iterations and memory usage. Novel contributions include the use of a feature-based indexing data structure together with a knowledge base. Both components improve the efficiency of the recognition process by improved structuring of the database of object features and reducing data base size

  15. Recognition of building group patterns in topographic maps based on graph partitioning and random forest

    Science.gov (United States)

    He, Xianjin; Zhang, Xinchang; Xin, Qinchuan

    2018-02-01

    Recognition of building group patterns (i.e., the arrangement and form exhibited by a collection of buildings at a given mapping scale) is important to the understanding and modeling of geographic space and is hence essential to a wide range of downstream applications such as map generalization. Most of the existing methods develop rigid rules based on the topographic relationships between building pairs to identify building group patterns and thus their applications are often limited. This study proposes a method to identify a variety of building group patterns that allow for map generalization. The method first identifies building group patterns from potential building clusters based on a machine-learning algorithm and further partitions the building clusters with no recognized patterns based on the graph partitioning method. The proposed method is applied to the datasets of three cities that are representative of the complex urban environment in Southern China. Assessment of the results based on the reference data suggests that the proposed method is able to recognize both regular (e.g., the collinear, curvilinear, and rectangular patterns) and irregular (e.g., the L-shaped, H-shaped, and high-density patterns) building group patterns well, given that the correctness values are consistently nearly 90% and the completeness values are all above 91% for three study areas. The proposed method shows promises in automated recognition of building group patterns that allows for map generalization.

  16. 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.

  17. 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)

  18. 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.

  19. Listening for recollection: a multi-voxel pattern analysis of recognition memory retrieval strategies

    Directory of Open Access Journals (Sweden)

    Joel R Quamme

    2010-08-01

    Full Text Available Recent studies of recognition memory indicate that subjects can strategically vary how much they rely on recollection of specific details vs. feelings of familiarity when making recognition judgments. One possible explanation of these results is that subjects can establish an internally-directed attentional state (listening for recollection that enhances retrieval of studied details; fluctuations in this attentional state over time should be associated with fluctuations in subjects' recognition behavior. In this study, we used multi-voxel pattern analysis of fMRI data to identify brain regions that are involved in listening for recollection. Specifically, we looked for brain regions that met the following criteria: 1 Distinct neural patterns should be present when subjects are instructed to rely on recollection vs. familiarity, and 2 fluctuations in these neural patterns should be related to recognition behavior in the manner predicted by dual-process theories of recognition: Specifically, the presence of the recollection pattern during the pre-stimulus interval (indicating that subjects are listening for recollection at that moment should be associated with a selective decrease in false alarms to related lures. We found that pre-stimulus activity in the right supramarginal gyrus met all of these criteria, suggesting that this region proactively establishes an internally-directed attentional state that fosters recollection. We also found other regions (e.g., left middle temporal gyrus where the pattern of neural activity was related to subjects’ responding to related lures after stimulus onset (but not before, suggesting that these regions implement processes that are engaged in a reactive fashion to boost recollection.

  20. Emotional Faces in Context: Age Differences in Recognition Accuracy and Scanning Patterns

    Science.gov (United States)

    Noh, Soo Rim; Isaacowitz, Derek M.

    2014-01-01

    While age-related declines in facial expression recognition are well documented, previous research relied mostly on isolated faces devoid of context. We investigated the effects of context on age differences in recognition of facial emotions and in visual scanning patterns of emotional faces. While their eye movements were monitored, younger and older participants viewed facial expressions (i.e., anger, disgust) in contexts that were emotionally congruent, incongruent, or neutral to the facial expression to be identified. Both age groups had highest recognition rates of facial expressions in the congruent context, followed by the neutral context, and recognition rates in the incongruent context were worst. These context effects were more pronounced for older adults. Compared to younger adults, older adults exhibited a greater benefit from congruent contextual information, regardless of facial expression. Context also influenced the pattern of visual scanning characteristics of emotional faces in a similar manner across age groups. In addition, older adults initially attended more to context overall. Our data highlight the importance of considering the role of context in understanding emotion recognition in adulthood. PMID:23163713

  1. Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks

    Science.gov (United States)

    Liu, Jun; Wang, Gang; Duan, Ling-Yu; Abdiyeva, Kamila; Kot, Alex C.

    2018-04-01

    Human action recognition in 3D skeleton sequences has attracted a lot of research attention. Recently, Long Short-Term Memory (LSTM) networks have shown promising performance in this task due to their strengths in modeling the dependencies and dynamics in sequential data. As not all skeletal joints are informative for action recognition, and the irrelevant joints often bring noise which can degrade the performance, we need to pay more attention to the informative ones. However, the original LSTM network does not have explicit attention ability. In this paper, we propose a new class of LSTM network, Global Context-Aware Attention LSTM (GCA-LSTM), for skeleton based action recognition. This network is capable of selectively focusing on the informative joints in each frame of each skeleton sequence by using a global context memory cell. To further improve the attention capability of our network, we also introduce a recurrent attention mechanism, with which the attention performance of the network can be enhanced progressively. Moreover, we propose a stepwise training scheme in order to train our network effectively. Our approach achieves state-of-the-art performance on five challenging benchmark datasets for skeleton based action recognition.

  2. Visual Scanning Patterns and Executive Function in Relation to Facial Emotion Recognition in Aging

    Science.gov (United States)

    Circelli, Karishma S.; Clark, Uraina S.; Cronin-Golomb, Alice

    2012-01-01

    Objective The ability to perceive facial emotion varies with age. Relative to younger adults (YA), older adults (OA) are less accurate at identifying fear, anger, and sadness, and more accurate at identifying disgust. Because different emotions are conveyed by different parts of the face, changes in visual scanning patterns may account for age-related variability. We investigated the relation between scanning patterns and recognition of facial emotions. Additionally, as frontal-lobe changes with age may affect scanning patterns and emotion recognition, we examined correlations between scanning parameters and performance on executive function tests. Methods We recorded eye movements from 16 OA (mean age 68.9) and 16 YA (mean age 19.2) while they categorized facial expressions and non-face control images (landscapes), and administered standard tests of executive function. Results OA were less accurate than YA at identifying fear (precognition of sad expressions and with scanning patterns for fearful, sad, and surprised expressions. Conclusion We report significant age-related differences in visual scanning that are specific to faces. The observed relation between scanning patterns and executive function supports the hypothesis that frontal-lobe changes with age may underlie some changes in emotion recognition. PMID:22616800

  3. Performance Study of the First 2D Prototype of Vertically Integrated Pattern Recognition Associative Memory (VIPRAM)

    Energy Technology Data Exchange (ETDEWEB)

    Deptuch, Gregory [Fermilab; Hoff, James [Fermilab; Jindariani, Sergo [Fermilab; Liu, Tiehui [Fermilab; Olsen, Jamieson [Fermilab; Tran, Nhan [Fermilab; Joshi, Siddhartha [Northwestern U.; Li, Dawei [Northwestern U.; Ogrenci-Memik, Seda [Northwestern U.

    2017-09-24

    Extremely fast pattern recognition capabilities are necessary to find and fit billions of tracks at the hardware trigger level produced every second anticipated at high luminosity LHC (HL-LHC) running conditions. Associative Memory (AM) based approaches for fast pattern recognition have been proposed as a potential solution to the tracking trigger. However, at the HL-LHC, there is much less time available and speed performance must be improved over previous systems while maintaining a comparable number of patterns. The Vertically Integrated Pattern Recognition Associative Memory (VIPRAM) Project aims to achieve the target pattern density and performance goal using 3DIC technology. The first step taken in the VIPRAM work was the development of a 2D prototype (protoVIPRAM00) in which the associative memory building blocks were designed to be compatible with the 3D integration. In this paper, we present the results from extensive performance studies of the protoVIPRAM00 chip in both realistic HL-LHC and extreme conditions. Results indicate that the chip operates at the design frequency of 100 MHz with perfect correctness in realistic conditions and conclude that the building blocks are ready for 3D stacking. We also present performance boundary characterization of the chip under extreme conditions.

  4. Speed sign detection and recognition by convolutional neural networks

    NARCIS (Netherlands)

    Peemen, M.C.J.; Mesman, B.; Corporaal, H.

    2011-01-01

    From the desire to update the maximum road speed data for navigation devices, a speed sign recognition and detection system is proposed. This system should prevent accidental speeding at roads where the map data is incorrect for example due to construction work. Multiple examples of road sign

  5. 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

  6. 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

  7. 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...

  8. 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.

  9. Improving subjective pattern recognition in chemical senses through reduction of nonlinear effects in evaluation of sparse data

    Science.gov (United States)

    Assadi, Amir H.; Rasouli, Firooz; Wrenn, Susan E.; Subbiah, M.

    2002-11-01

    Artificial neural network models are typically useful in pattern recognition and extraction of important features in large data sets. These models are implemented in a wide variety of contexts and with diverse type of input-output data. The underlying mathematics of supervised training of neural networks is ultimately tied to the ability to approximate the nonlinearities that are inherent in network"s generalization ability. The quality and availability of sufficient data points for training and validation play a key role in the generalization ability of the network. A potential domain of applications of neural networks is in analysis of subjective data, such as in consumer science, affective neuroscience and perception of chemical senses. In applications of ANN to subjective data, it is common to rely on knowledge of the science and context for data acquisition, for instance as a priori probabilities in the Bayesian framework. In this paper, we discuss the circumstances that create challenges for success of neural network models for subjective data analysis, such as sparseness of data and cost of acquisition of additional samples. In particular, in the case of affect and perception of chemical senses, we suggest that inherent ambiguity of subjective responses could be offset by a combination of human-machine expert. We propose a method of pre- and post-processing for blind analysis of data that that relies on heuristics from human performance in interpretation of data. In particular, we offer an information-theoretic smoothing (ITS) algorithm that optimizes that geometric visualization of multi-dimensional data and improves human interpretation of the input-output view of neural network implementations. The pre- and post-processing algorithms and ITS are unsupervised. Finally, we discuss the details of an example of blind data analysis from actual taste-smell subjective data, and demonstrate the usefulness of PCA in reduction of dimensionality, as well as ITS.

  10. The time course of individual face recognition: A pattern analysis of ERP signals.

    Science.gov (United States)

    Nemrodov, Dan; Niemeier, Matthias; Mok, Jenkin Ngo Yin; Nestor, Adrian

    2016-05-15

    An extensive body of work documents the time course of neural face processing in the human visual cortex. However, the majority of this work has focused on specific temporal landmarks, such as N170 and N250 components, derived through univariate analyses of EEG data. Here, we take on a broader evaluation of ERP signals related to individual face recognition as we attempt to move beyond the leading theoretical and methodological framework through the application of pattern analysis to ERP data. Specifically, we investigate the spatiotemporal profile of identity recognition across variation in emotional expression. To this end, we apply pattern classification to ERP signals both in time, for any single electrode, and in space, across multiple electrodes. Our results confirm the significance of traditional ERP components in face processing. At the same time though, they support the idea that the temporal profile of face recognition is incompletely described by such components. First, we show that signals associated with different facial identities can be discriminated from each other outside the scope of these components, as early as 70ms following stimulus presentation. Next, electrodes associated with traditional ERP components as well as, critically, those not associated with such components are shown to contribute information to stimulus discriminability. And last, the levels of ERP-based pattern discrimination are found to correlate with recognition accuracy across subjects confirming the relevance of these methods for bridging brain and behavior data. Altogether, the current results shed new light on the fine-grained time course of neural face processing and showcase the value of novel methods for pattern analysis to investigating fundamental aspects of visual recognition. Copyright © 2016 Elsevier Inc. All rights reserved.

  11. Deep learning architecture for iris recognition based on optimal Gabor filters and deep belief network

    Science.gov (United States)

    He, Fei; Han, Ye; Wang, Han; Ji, Jinchao; Liu, Yuanning; Ma, Zhiqiang

    2017-03-01

    Gabor filters are widely utilized to detect iris texture information in several state-of-the-art iris recognition systems. However, the proper Gabor kernels and the generative pattern of iris Gabor features need to be predetermined in application. The traditional empirical Gabor filters and shallow iris encoding ways are incapable of dealing with such complex variations in iris imaging including illumination, aging, deformation, and device variations. Thereby, an adaptive Gabor filter selection strategy and deep learning architecture are presented. We first employ particle swarm optimization approach and its binary version to define a set of data-driven Gabor kernels for fitting the most informative filtering bands, and then capture complex pattern from the optimal Gabor filtered coefficients by a trained deep belief network. A succession of comparative experiments validate that our optimal Gabor filters may produce more distinctive Gabor coefficients and our iris deep representations be more robust and stable than traditional iris Gabor codes. Furthermore, the depth and scales of the deep learning architecture are also discussed.

  12. 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.

  13. Recognition

    DEFF Research Database (Denmark)

    Gimmler, Antje

    2017-01-01

    In this article, I shall examine the cognitive, heuristic and theoretical functions of the concept of recognition. To evaluate both the explanatory power and the limitations of a sociological concept, the theory construction must be analysed and its actual productivity for sociological theory mus...

  14. 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.

  15. Memristive Computational Architecture of an Echo State Network for Real-Time Speech Emotion Recognition

    Science.gov (United States)

    2015-05-28

    recognition is simpler and requires less computational resources compared to other inputs such as facial expressions . The Berlin database of Emotional ...Processing Magazine, IEEE, vol. 18, no. 1, pp. 32– 80, 2001. [15] K. R. Scherer, T. Johnstone, and G. Klasmeyer, “Vocal expression of emotion ...Network for Real-Time Speech- Emotion Recognition 5a. CONTRACT NUMBER IN-HOUSE 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 62788F 6. AUTHOR(S) Q

  16. Adaptive pattern recognition in real-time video-based soccer analysis

    DEFF Research Database (Denmark)

    Schlipsing, Marc; Salmen, Jan; Tschentscher, Marc

    2017-01-01

    are taken into account. Our contribution is twofold: (1) the deliberate use of machine learning and pattern recognition techniques allows us to achieve high classification accuracy in varying environments. We systematically evaluate combinations of image features and learning machines in the given online......Computer-aided sports analysis is demanded by coaches and the media. Image processing and machine learning techniques that allow for "live" recognition and tracking of players exist. But these methods are far from collecting and analyzing event data fully autonomously. To generate accurate results......, human interaction is required at different stages including system setup, calibration, supervision of classifier training, and resolution of tracking conflicts. Furthermore, the real-time constraints are challenging: in contrast to other object recognition and tracking applications, we cannot treat data...

  17. 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.

  18. 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.

  19. Type I interferon and pattern recognition receptor signaling following particulate matter inhalation

    Directory of Open Access Journals (Sweden)

    Erdely Aaron

    2012-07-01

    Full Text Available Abstract Background Welding, a process that generates an aerosol containing gases and metal-rich particulates, induces adverse physiological effects including inflammation, immunosuppression and cardiovascular dysfunction. This study utilized microarray technology and subsequent pathway analysis as an exploratory search for markers/mechanisms of in vivo systemic effects following inhalation. Mice were exposed by inhalation to gas metal arc – stainless steel (GMA-SS welding fume at 40 mg/m3 for 3 hr/d for 10 d and sacrificed 4 hr, 14 d and 28 d post-exposure. Whole blood cells, aorta and lung were harvested for global gene expression analysis with subsequent Ingenuity Pathway Analysis and confirmatory qRT-PCR. Serum was collected for protein profiling. Results The novel finding was a dominant type I interferon signaling network with the transcription factor Irf7 as a central component maintained through 28 d. Remarkably, these effects showed consistency across all tissues indicating a systemic type I interferon response that was complemented by changes in serum proteins (decreased MMP-9, CRP and increased VCAM1, oncostatin M, IP-10. In addition, pulmonary expression of interferon α and β and Irf7 specific pattern recognition receptors (PRR and signaling molecules (Ddx58, Ifih1, Dhx58, ISGF3 were induced, an effect that showed specificity when compared to other inflammatory exposures. Also, a canonical pathway indicated a coordinated response of multiple PRR and associated signaling molecules (Tlr7, Tlr2, Clec7a, Nlrp3, Myd88 to inhalation of GMA-SS. Conclusion This methodological approach has the potential to identify consistent, prominent and/or novel pathways and provides insight into mechanisms that contribute to pulmonary and systemic effects following toxicant exposure.

  20. 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.

  1. 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

  2. A Motion-Adaptive Deinterlacer via Hybrid Motion Detection and Edge-Pattern Recognition

    Directory of Open Access Journals (Sweden)

    He-Yuan Lin

    2008-03-01

    Full Text Available A novel motion-adaptive deinterlacing algorithm with edge-pattern recognition and hybrid motion detection is introduced. The great variety of video contents makes the processing of assorted motion, edges, textures, and the combination of them very difficult with a single algorithm. The edge-pattern recognition algorithm introduced in this paper exhibits the flexibility in processing both textures and edges which need to be separately accomplished by line average and edge-based line average before. Moreover, predicting the neighboring pixels for pattern analysis and interpolation further enhances the adaptability of the edge-pattern recognition unit when motion detection is incorporated. Our hybrid motion detection features accurate detection of fast and slow motion in interlaced video and also the motion with edges. Using only three fields for detection also renders higher temporal correlation for interpolation. The better performance of our deinterlacing algorithm with higher content-adaptability and less memory cost than the state-of-the-art 4-field motion detection algorithms can be seen from the subjective and objective experimental results of the CIF and PAL video sequences.

  3. A Motion-Adaptive Deinterlacer via Hybrid Motion Detection and Edge-Pattern Recognition

    Directory of Open Access Journals (Sweden)

    Li Hsin-Te

    2008-01-01

    Full Text Available Abstract A novel motion-adaptive deinterlacing algorithm with edge-pattern recognition and hybrid motion detection is introduced. The great variety of video contents makes the processing of assorted motion, edges, textures, and the combination of them very difficult with a single algorithm. The edge-pattern recognition algorithm introduced in this paper exhibits the flexibility in processing both textures and edges which need to be separately accomplished by line average and edge-based line average before. Moreover, predicting the neighboring pixels for pattern analysis and interpolation further enhances the adaptability of the edge-pattern recognition unit when motion detection is incorporated. Our hybrid motion detection features accurate detection of fast and slow motion in interlaced video and also the motion with edges. Using only three fields for detection also renders higher temporal correlation for interpolation. The better performance of our deinterlacing algorithm with higher content-adaptability and less memory cost than the state-of-the-art 4-field motion detection algorithms can be seen from the subjective and objective experimental results of the CIF and PAL video sequences.

  4. Pedestrian Movement Direction Recognition Using Convolutional Neural Networks

    OpenAIRE

    Dominguez-Sanchez, Alex; Cazorla, Miguel; Orts-Escolano, Sergio

    2017-01-01

    Pedestrian movement direction recognition is an important factor in autonomous driver assistance and security surveillance systems. Pedestrians are the most crucial and fragile moving objects in streets, roads, and events, where thousands of people may gather on a regular basis. People flow analysis on zebra crossings and in shopping centers or events such as demonstrations are a key element to improve safety and to enable autonomous cars to drive in real life environments. This paper focuses...

  5. 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.

  6. Activation and Regulation of the Pattern Recognition Receptors in Obesity-Induced Adipose Tissue Inflammation and Insulin Resistance

    Directory of Open Access Journals (Sweden)

    Kiyoshi Takatsu

    2013-09-01

    Full Text Available Obesity-associated chronic tissue inflammation is a key contributing factor to type 2 diabetes mellitus, and a number of studies have clearly demonstrated that the immune system and metabolism are highly integrated. Recent advances in deciphering the various immune cells and signaling networks that link the immune and metabolic systems have contributed to our understanding of the pathogenesis of obesity-associated inflammation. Other recent studies have suggested that pattern recognition receptors in the innate immune system recognize various kinds of endogenous and exogenous ligands, and have a crucial role in initiating or promoting obesity-associated chronic inflammation. Importantly, these mediators act on insulin target cells or on insulin-producing cells impairing insulin sensitivity and its secretion. Here, we discuss how various pattern recognition receptors in the immune system underlie the etiology of obesity-associated inflammation and insulin resistance, with a particular focus on the TLR (Toll-like receptor family protein Radioprotective 105 (RP105/myeloid differentiation protein-1 (MD-1.

  7. Activation and regulation of the pattern recognition receptors in obesity-induced adipose tissue inflammation and insulin resistance.

    Science.gov (United States)

    Watanabe, Yasuharu; Nagai, Yoshinori; Takatsu, Kiyoshi

    2013-09-23

    Obesity-associated chronic tissue inflammation is a key contributing factor to type 2 diabetes mellitus, and a number of studies have clearly demonstrated that the immune system and metabolism are highly integrated. Recent advances in deciphering the various immune cells and signaling networks that link the immune and metabolic systems have contributed to our understanding of the pathogenesis of obesity-associated inflammation. Other recent studies have suggested that pattern recognition receptors in the innate immune system recognize various kinds of endogenous and exogenous ligands, and have a crucial role in initiating or promoting obesity-associated chronic inflammation. Importantly, these mediators act on insulin target cells or on insulin-producing cells impairing insulin sensitivity and its secretion. Here, we discuss how various pattern recognition receptors in the immune system underlie the etiology of obesity-associated inflammation and insulin resistance, with a particular focus on the TLR (Toll-like receptor) family protein Radioprotective 105 (RP105)/myeloid differentiation protein-1 (MD-1).

  8. Compression of a Deep Competitive Network Based on Mutual Information for Underwater Acoustic Targets Recognition

    Directory of Open Access Journals (Sweden)

    Sheng Shen

    2018-04-01

    Full Text Available The accuracy of underwater acoustic targets recognition via limited ship radiated noise can be improved by a deep neural network trained with a large number of unlabeled samples. However, redundant features learned by deep neural network have negative effects on recognition accuracy and efficiency. A compressed deep competitive network is proposed to learn and extract features from ship radiated noise. The core idea of the algorithm includes: (1 Competitive learning: By integrating competitive learning into the restricted Boltzmann machine learning algorithm, the hidden units could share the weights in each predefined group; (2 Network pruning: The pruning based on mutual information is deployed to remove the redundant parameters and further compress the network. Experiments based on real ship radiated noise show that the network can increase recognition accuracy with fewer informative features. The compressed deep competitive network can achieve a classification accuracy of 89.1 % , which is 5.3 % higher than deep competitive network and 13.1 % higher than the state-of-the-art signal processing feature extraction methods.

  9. 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.

  10. LOCAL LINE BINARY PATTERN FOR FEATURE EXTRACTION ON PALM VEIN RECOGNITION

    Directory of Open Access Journals (Sweden)

    Jayanti Yusmah Sari

    2015-08-01

    Full Text Available In recent years, palm vein recognition has been studied to overcome problems in conventional systems in biometrics technology (finger print, face, and iris. Those problems in biometrics includes convenience and performance. However, due to the clarity of the palm vein image, the veins could not be segmented properly. To overcome this problem, we propose a palm vein recognition system using Local Line Binary Pattern (LLBP method that can extract robust features from the palm vein images that has unclear veins. LLBP is an advanced method of Local Binary Pattern (LBP, a texture descriptor based on the gray level comparison of a neighborhood of pixels. There are four major steps in this paper, Region of Interest (ROI detection, image preprocessing, features extraction using LLBP method, and matching using Fuzzy k-NN classifier. The proposed method was applied on the CASIA Multi-Spectral Image Database. Experimental results showed that the proposed method using LLBP has a good performance with recognition accuracy of 97.3%. In the future, experiments will be conducted to observe which parameter that could affect processing time and recognition accuracy of LLBP is needed

  11. Stage-specific sampling by pattern recognition receptors during Candida albicans phagocytosis.

    Directory of Open Access Journals (Sweden)

    Sigrid E M Heinsbroek

    2008-11-01

    Full Text Available Candida albicans is a medically important pathogen, and recognition by innate immune cells is critical for its clearance. Although a number of pattern recognition receptors have been shown to be involved in recognition and phagocytosis of this fungus, the relative role of these receptors has not been formally examined. In this paper, we have investigated the contribution of the mannose receptor, Dectin-1, and complement receptor 3; and we have demonstrated that Dectin-1 is the main non-opsonic receptor involved in fungal uptake. However, both Dectin-1 and complement receptor 3 were found to accumulate at the site of uptake, while mannose receptor accumulated on C. albicans phagosomes at later stages. These results suggest a potential role for MR in phagosome sampling; and, accordingly, MR deficiency led to a reduction in TNF-alpha and MCP-1 production in response to C. albicans uptake. Our data suggest that pattern recognition receptors sample the fungal phagosome in a sequential fashion.

  12. Face recognition via Gabor and convolutional neural network

    Science.gov (United States)

    Lu, Tongwei; Wu, Menglu; Lu, Tao

    2018-04-01

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

  13. 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

  14. Application of pattern recognition techniques to the detection of the Phenix reactor control rods vibrations

    International Nuclear Information System (INIS)

    Zwingelstein, G.; Deat, M.; Le Guillou, G.

    1979-01-01

    The incipient detection of control rods vibrations is very important for the safety of the operating plants. This detection can be achieved by an analysis of the peaks of the power spectrum density of the neutron noise. Pattern Recognition techniques were applied to detect the rod vibrations which occured at the fast breeder Phenix (250MWe). In the first part we give a description of the basic pattern which is used to characterize the behavior of the plant. The pattern is considered as column vector in n dimensional Euclidian space where the components are the samples of the power spectral density of the neutron noise. In the second part, a recursive learning procedure of the normal patterns which provides the mean and the variance of the estimates is described. In the third part the classification problem has been framed in terms of a partitioning procedure in n dimensional space which encloses regions corresponding to normal operations. This pattern recognition scheme was applied to the detection of rod vibrations with neutron data collected at the Phenix site before and after occurence of the vibrations. The analysis was carried out with a 42-dimensional measurement space. The learned pattern was estimated with 150 measurement vectors which correspond to the period without vibrations. The efficiency of the surveillance scheme is then demonstrated by processing separately 119 measurement vectors recorded during the rod vibration period

  15. Extended pattern recognition scheme for self-learning kinetic Monte Carlo simulations

    International Nuclear Information System (INIS)

    Shah, Syed Islamuddin; Nandipati, Giridhar; Kara, Abdelkader; Rahman, Talat S

    2012-01-01

    We report the development of a pattern recognition scheme that takes into account both fcc and hcp adsorption sites in performing self-learning kinetic Monte Carlo (SLKMC-II) simulations on the fcc(111) surface. In this scheme, the local environment of every under-coordinated atom in an island is uniquely identified by grouping fcc sites, hcp sites and top-layer substrate atoms around it into hexagonal rings. As the simulation progresses, all possible processes, including those such as shearing, reptation and concerted gliding, which may involve fcc-fcc, hcp-hcp and fcc-hcp moves are automatically found, and their energetics calculated on the fly. In this article we present the results of applying this new pattern recognition scheme to the self-diffusion of 9-atom islands (M 9 ) on M(111), where M = Cu, Ag or Ni.

  16. Pattern recognition algorithms for data mining scalability, knowledge discovery and soft granular computing

    CERN Document Server

    Pal, Sankar K

    2004-01-01

    Pattern Recognition Algorithms for Data Mining addresses different pattern recognition (PR) tasks in a unified framework with both theoretical and experimental results. Tasks covered include data condensation, feature selection, case generation, clustering/classification, and rule generation and evaluation. This volume presents various theories, methodologies, and algorithms, using both classical approaches and hybrid paradigms. The authors emphasize large datasets with overlapping, intractable, or nonlinear boundary classes, and datasets that demonstrate granular computing in soft frameworks.Organized into eight chapters, the book begins with an introduction to PR, data mining, and knowledge discovery concepts. The authors analyze the tasks of multi-scale data condensation and dimensionality reduction, then explore the problem of learning with support vector machine (SVM). They conclude by highlighting the significance of granular computing for different mining tasks in a soft paradigm.

  17. Pattern-recognition software detecting the onset of failures in complex systems

    International Nuclear Information System (INIS)

    Mott, J.; King, R.

    1987-01-01

    A very general mathematical framework for embodying learned data from a complex system and combining it with a current observation to estimate the true current state of the system has been implemented using nearly universal pattern-recognition algorithms and applied to surveillance of the EBR-II power plant. In this application the methodology can provide signal validation and replacement of faulty signals on a near-real-time basis for hundreds of plant parameters. The mathematical framework, the pattern-recognition algorithms, examples of the learning and estimating process, and plant operating decisions made using this methodology are discussed. The entire methodology has been reduced to a set of FORTRAN subroutines which are small, fast, robust and executable on a personal computer with a serial link to the system's data acquisition computer, or on the data acquisition computer itself

  18. Authentication and distinction of Shenmai injection with HPLC fingerprint analysis assisted by pattern recognition techniques

    Directory of Open Access Journals (Sweden)

    Xue-Feng Lu

    2012-10-01

    Full Text Available In this paper, the feasibility and advantages of employing high performance liquid chromatographic (HPLC fingerprints combined with pattern recognition techniques for quality control of Shenmai injection were investigated and demonstrated. The Similarity Evaluation System was employed to evaluate the similarities of samples of Shenmai injection, and the HPLC generated chromatographic data were analyzed using hierarchical clustering analysis (HCA and soft independent modeling of class analogy (SIMCA. Consistent results were obtained to show that the authentic samples and the blended samples were successfully classified by SIMCA, which could be applied to accurate discrimination and quality control of Shenmai injection. Furthermore, samples could also be grouped in accordance with manufacturers. Our results revealed that the developed method has potential perspective for the original discrimination and quality control of Shenmai injection. Keywords: Shenmai injection, High performance liquid chromatography, Fingerprint, Pattern recognition

  19. Simultaneous pattern recognition and track fitting by the Kalman filtering method

    International Nuclear Information System (INIS)

    Billoir, P.

    1990-01-01

    A progressive pattern recognition algorithm based on the Kalman filtering method has been tested. The algorithm starts from a small track segment or from a fitted track of a neighbouring detector, then extends the candidate tracks by adding measured points one by one. The fitted parameters and weight matrix of the candidate track are updated when adding a point, and give an increasing precision on prediction of the next point. Thus, pattern recognition and track fitting can be accomplished simultaneously. The method has been implemented and tested for track reconstruction for the vertex detector of the ZEUS experiment at DESY. Detailed procedures of the method and its performance are presented. Its flexibility is described as well. (orig.)

  20. EBR-II [Experimental Breeder Reactor-II] system surveillance using pattern recognition software

    International Nuclear Information System (INIS)

    Mott, J.E.; Radtke, W.H.; King, R.W.

    1986-02-01

    The problem of most accurately determining the Experimental Breeder Reactor-II (EBR-II) reactor outlet temperature from currently available plant signals is investigated. Historically, the reactor outlet pipe was originally instrumented with 8 temperature sensors but, during 22 years of operation, all these instruments have failed except for one remaining thermocouple, and its output had recently become suspect. Using pattern recognition methods to compare values of 129 plant signals for similarities over a 7 month period spanning reconfiguration of the core and recalibration of many plant signals, it was determined that the remaining reactor outlet pipe thermocouple is still useful as an indicator of true mixed mean reactor outlet temperature. Application of this methodology to investigate one specific signal has automatically validated the vast majority of the 129 signals used for pattern recognition and also highlighted a few inconsistent signals for further investigation

  1. Data Mining and Pattern Recognition Models for Identifying Inherited Diseases: Challenges and Implications.

    Science.gov (United States)

    Iddamalgoda, Lahiru; Das, Partha S; Aponso, Achala; Sundararajan, Vijayaraghava S; Suravajhala, Prashanth; Valadi, Jayaraman K

    2016-01-01

    Data mining and pattern recognition methods reveal interesting findings in genetic studies, especially on how the genetic makeup is associated with inherited diseases. Although researchers have proposed various data mining models for biomedical approaches, there remains a challenge in accurately prioritizing the single nucleotide polymorphisms (SNP) associated with the disease. In this commentary, we review the state-of-art data mining and pattern recognition models for identifying inherited diseases and deliberate the need of binary classification- and scoring-based prioritization methods in determining causal variants. While we discuss the pros and cons associated with these methods known, we argue that the gene prioritization methods and the protein interaction (PPI) methods in conjunction with the K nearest neighbors' could be used in accurately categorizing the genetic factors in disease causation.

  2. Fault diagnosis and performance monitoring for pumps by means of vibration measurement and pattern recognition

    International Nuclear Information System (INIS)

    Grabner, A.; Weiss, F.P.

    1984-12-01

    In recent years the early detection of malfunctions with noise and vibration analysis techniques has become a more and more important method for increasing availability and safety of various components in technical plants. The possibility of pattern recognition assisted vibration monitoring and its practical realization are demonstrated by failure diagnosis and trend analysis of the condition of large centrifugal pumps in hydraulic circuits. Some problems as, e.g., the finding of dynamic failure models, signal analysis, feature extraction and statistical pattern recognition, which helps automatically to decide whether the pump works normally or not, are discussed in more detail. In the paper it is shown that for various types of machines the chance of success of condition based maintenance can be enhanced by such an automatic vibration monitoring. (author)

  3. A pattern recognition methodology for evaluation of load profiles and typical days of large electricity customers

    International Nuclear Information System (INIS)

    Tsekouras, G.J.; Kotoulas, P.B.; Tsirekis, C.D.; Dialynas, E.N.; Hatziargyriou, N.D.

    2008-01-01

    This paper describes a pattern recognition methodology for the classification of the daily chronological load curves of each large electricity customer, in order to estimate his typical days and his respective representative daily load profiles. It is based on pattern recognition methods, such as k-means, self-organized maps (SOM), fuzzy k-means and hierarchical clustering, which are theoretically described and properly adapted. The parameters of each clustering method are properly selected by an optimization process, which is separately applied for each one of six adequacy measures. The results can be used for the short-term and mid-term load forecasting of each consumer, for the choice of the proper tariffs and the feasibility studies of demand side management programs. This methodology is analytically applied for one medium voltage industrial customer and synoptically for a set of medium voltage customers of the Greek power system. The results of the clustering methods are presented and discussed. (author)

  4. 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.

  5. Bayesian network modeling of operator's state recognition process

    International Nuclear Information System (INIS)

    Hatakeyama, Naoki; Furuta, Kazuo

    2000-01-01

    Nowadays we are facing a difficult problem of establishing a good relation between humans and machines. To solve this problem, we suppose that machine system need to have a model of human behavior. In this study we model the state cognition process of a PWR plant operator as an example. We use a Bayesian network as an inference engine. We incorporate the knowledge hierarchy in the Bayesian network and confirm its validity using the example of PWR plant operator. (author)

  6. An object recognition using structured light and neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Byeong Gab; Kim, Dong Gi; Kang, E Sok [Chungnam National Univ., Taejon (Korea, Republic of); Yoon, Ji Sup [Korea Atomic Energy Research Institute, Taejon (Korea, Republic of)

    1998-12-31

    This paper presents a 3D image processing which uses neural networks to combine a 2D vision camera and a laser slit beam. A laser slit beam from laser source is slitted by a set of cylindrical lenses and the line image of the networks allow to get the 3D image parameters such as the size, the position and the orientation from the line image without knowing the camera intrinsic parameters. (author). 7 refs., 3 tabs., 5 figs.

  7. An object recognition using structured light and neural networks

    International Nuclear Information System (INIS)

    Kim, Byeong Gab; Kim, Dong Gi; Kang, E Sok; Yoon, Ji Sup

    1997-01-01

    This paper presents a 3D image processing which uses neural networks to combine a 2D vision camera and a laser slit beam. A laser slit beam from laser source is slitted by a set of cylindrical lenses and the line image of the networks allow to get the 3D image parameters such as the size, the position and the orientation from the line image without knowing the camera intrinsic parameters. (author). 7 refs., 3 tabs., 5 figs

  8. An object recognition using structured light and neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Byeong Gab; Kim, Dong Gi; Kang, E Sok [Chungnam National Univ., Taejon (Korea, Republic of); Yoon, Ji Sup [Korea Atomic Energy Research Institute, Taejon (Korea, Republic of)

    1997-12-31

    This paper presents a 3D image processing which uses neural networks to combine a 2D vision camera and a laser slit beam. A laser slit beam from laser source is slitted by a set of cylindrical lenses and the line image of the networks allow to get the 3D image parameters such as the size, the position and the orientation from the line image without knowing the camera intrinsic parameters. (author). 7 refs., 3 tabs., 5 figs.

  9. Investigation of CoPd alloys by XPS and EPES using the pattern recognition method

    Czech Academy of Sciences Publication Activity Database

    Lesiak, B.; Zemek, Josef; Jiříček, Petr; Jozwik, A.

    2007-01-01

    Roč. 428, - (2007), s. 190-196 ISSN 0925-8388 R&D Projects: GA ČR GA202/06/0459 Institutional research plan: CEZ:AV0Z10100521 Keywords : CoPd alloys * x-ray photoelectron spectroscopy (XPS) * elastic peak electron spectroscopy (EPES) * pattern recognition method * fuzzy k-nearest neighbour rule (fkNN) * quantitative analysis * surface segregation Subject RIV: BM - Solid Matter Physics ; Magnetism Impact factor: 1.455, year: 2007

  10. Development of a Pattern Recognition Methodology for Determining Operationally Optimal Heat Balance Instrumentation Calibration Schedules

    Energy Technology Data Exchange (ETDEWEB)

    Kurt Beran; John Christenson; Dragos Nica; Kenny Gross

    2002-12-15

    The goal of the project is to enable plant operators to detect with high sensitivity and reliability the onset of decalibration drifts in all of the instrumentation used as input to the reactor heat balance calculations. To achieve this objective, the collaborators developed and implemented at DBNPS an extension of the Multivariate State Estimation Technique (MSET) pattern recognition methodology pioneered by ANAL. The extension was implemented during the second phase of the project and fully achieved the project goal.

  11. Application of pattern recognition methods for evaluating the immune status in patients

    International Nuclear Information System (INIS)

    Stavitsky, R.B.; Guslistyj, I.V.; Miroshnichenko, I.V.; Karklinskaya, O.N.; Ryabinina, I.D.; Kosova, I.P.; Stolpnikova, V.N.; Malaeva, N.S.; Latypova, I.I.; Lebedev, L.A.

    2001-01-01

    The effectiveness of mathematical tools for pattern recognition as applied to numerical assessments of the immune status of patients exposed to ecological hazards is evaluated by experimentation. The immune status is estimated according to a two-class scheme (norm/abnormality) based on blood indicators of immunity for the patients examined. The task of categorizing patients by immunological parameters of blood is shown to be resolved with high effectiveness for determining the immune status [ru

  12. Pattern recognition application for surveillance of abnormal conditions in a nuclear reactor

    International Nuclear Information System (INIS)

    Pepelyshev, Yu.N.; Dzwinel, W.

    1990-01-01

    The system to monitor abnormal conditions in a nuclear reactor, based on the noise analysis of the reactor basic parameters such as power, temperature and coolant flow rate, has been developed. The pattern recognition techniques such as clustering, cluster analysis, feature selection and clusters visualization methods form the basis of the software. Apart from non-hierarchical clustering procedures applied earlier, the hierarchical one is recommended. The system application for IBR-2 Dubna reactor diagnostics is shown. 10 refs.; 6 figs

  13. Development of pattern recognition algorithms for the central drift chamber of the Belle II detector

    Energy Technology Data Exchange (ETDEWEB)

    Trusov, Viktor

    2016-11-04

    In this thesis, the development of one of the pattern recognition algorithms for the Belle II experiment based on conformal and Legendre transformations is presented. In order to optimize the performance of the algorithm (CPU time and efficiency) specialized processing steps have been introduced. To show achieved results, Monte-Carlo based efficiency measurements of the tracking algorithms in the Central Drift Chamber (CDC) has been done.

  14. 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.

  15. 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

  16. 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.

  17. 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.

  18. 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.

  19. 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

  20. Speaker emotion recognition: from classical classifiers to deep neural networks

    Science.gov (United States)

    Mezghani, Eya; Charfeddine, Maha; Nicolas, Henri; Ben Amar, Chokri

    2018-04-01

    Speaker emotion recognition is considered among the most challenging tasks in recent years. In fact, automatic systems for security, medicine or education can be improved when considering the speech affective state. In this paper, a twofold approach for speech emotion classification is proposed. At the first side, a relevant set of features is adopted, and then at the second one, numerous supervised training techniques, involving classic methods as well as deep learning, are experimented. Experimental results indicate that deep architecture can improve classification performance on two affective databases, the Berlin Dataset of Emotional Speech and the SAVEE Dataset Surrey Audio-Visual Expressed Emotion.