Constructive neural network learning algorithms
Parekh, R.; Yang, Jihoon; Honavar, V.
1996-12-31
Constructive Algorithms offer an approach for incremental construction of potentially minimal neural network architectures for pattern classification tasks. These algorithms obviate the need for an ad-hoc a-priori choice of the network topology. The constructive algorithm design involves alternately augmenting the existing network topology by adding one or more threshold logic units and training the newly added threshold neuron(s) using a stable variant of the perception learning algorithm (e.g., pocket algorithm, thermal perception, and barycentric correction procedure). Several constructive algorithms including tower, pyramid, tiling, upstart, and perception cascade have been proposed for 2-category pattern classification. These algorithms differ in terms of their topological and connectivity constraints as well as the training strategies used for individual neurons.
Neural Network Algorithm for Particle Loading
J. L. V. Lewandowski
2003-04-25
An artificial neural network algorithm for continuous minimization is developed and applied to the case of numerical particle loading. It is shown that higher-order moments of the probability distribution function can be efficiently renormalized using this technique. A general neural network for the renormalization of an arbitrary number of moments is given.
Parameter incremental learning algorithm for neural networks.
Wan, Sheng; Banta, Larry E
2006-11-01
In this paper, a novel stochastic (or online) training algorithm for neural networks, named parameter incremental learning (PIL) algorithm, is proposed and developed. The main idea of the PIL strategy is that the learning algorithm should not only adapt to the newly presented input-output training pattern by adjusting parameters, but also preserve the prior results. A general PIL algorithm for feedforward neural networks is accordingly presented as the first-order approximate solution to an optimization problem, where the performance index is the combination of proper measures of preservation and adaptation. The PIL algorithms for the multilayer perceptron (MLP) are subsequently derived. Numerical studies show that for all the three benchmark problems used in this paper the PIL algorithm for MLP is measurably superior to the standard online backpropagation (BP) algorithm and the stochastic diagonal Levenberg-Marquardt (SDLM) algorithm in terms of the convergence speed and accuracy. Other appealing features of the PIL algorithm are that it is computationally as simple as the BP algorithm, and as easy to use as the BP algorithm. It, therefore, can be applied, with better performance, to any situations where the standard online BP algorithm is applicable. PMID:17131658
Pruning Neural Networks with Distribution Estimation Algorithms
Cantu-Paz, E
2003-01-15
This paper describes the application of four evolutionary algorithms to the pruning of neural networks used in classification problems. Besides of a simple genetic algorithm (GA), the paper considers three distribution estimation algorithms (DEAs): a compact GA, an extended compact GA, and the Bayesian Optimization Algorithm. The objective is to determine if the DEAs present advantages over the simple GA in terms of accuracy or speed in this problem. The experiments used a feed forward neural network trained with standard back propagation and public-domain and artificial data sets. The pruned networks seemed to have better or equal accuracy than the original fully-connected networks. Only in a few cases, pruning resulted in less accurate networks. We found few differences in the accuracy of the networks pruned by the four EAs, but found important differences in the execution time. The results suggest that a simple GA with a small population might be the best algorithm for pruning networks on the data sets we tested.
Algorithm For A Self-Growing Neural Network
NASA Technical Reports Server (NTRS)
Cios, Krzysztof J.
1996-01-01
CID3 algorithm simulates self-growing neural network. Constructs decision trees equivalent to hidden layers of neural network. Based on ID3 algorithm, which dynamically generates decision tree while minimizing entropy of information. CID3 algorithm generates feedforward neural network by use of either crisp or fuzzy measure of entropy.
Training product unit neural networks with genetic algorithms
NASA Technical Reports Server (NTRS)
Janson, D. J.; Frenzel, J. F.; Thelen, D. C.
1991-01-01
The training of product neural networks using genetic algorithms is discussed. Two unusual neural network techniques are combined; product units are employed instead of the traditional summing units and genetic algorithms train the network rather than backpropagation. As an example, a neural netork is trained to calculate the optimum width of transistors in a CMOS switch. It is shown how local minima affect the performance of a genetic algorithm, and one method of overcoming this is presented.
Learning evasive maneuvers using evolutionary algorithms and neural networks
NASA Astrophysics Data System (ADS)
Kang, Moung Hung
In this research, evolutionary algorithms and recurrent neural networks are combined to evolve control knowledge to help pilots avoid being struck by a missile, based on a two-dimensional air combat simulation model. The recurrent neural network is used for representing the pilot's control knowledge and evolutionary algorithms (i.e., Genetic Algorithms, Evolution Strategies, and Evolutionary Programming) are used for optimizing the weights and/or topology of the recurrent neural network. The simulation model of the two-dimensional evasive maneuver problem evolved is used for evaluating the performance of the recurrent neural network. Five typical air combat conditions were selected to evaluate the performance of the recurrent neural networks evolved by the evolutionary algorithms. Analysis of Variance (ANOVA) tests and response graphs were used to analyze the results. Overall, there was little difference in the performance of the three evolutionary algorithms used to evolve the control knowledge. However, the number of generations of each algorithm required to obtain the best performance was significantly different. ES converges the fastest, followed by EP and then by GA. The recurrent neural networks evolved by the evolutionary algorithms provided better performance than the traditional recommendations for evasive maneuvers, maximum gravitational turn, for each air combat condition. Furthermore, the recommended actions of the recurrent neural networks are reasonable and can be used for pilot training.
Genetic Algorithm Based Neural Networks for Nonlinear Optimization
1994-09-28
This software develops a novel approach to nonlinear optimization using genetic algorithm based neural networks. To our best knowledge, this approach represents the first attempt at applying both neural network and genetic algorithm techniques to solve a nonlinear optimization problem. The approach constructs a neural network structure and an appropriately shaped energy surface whose minima correspond to optimal solutions of the problem. A genetic algorithm is employed to perform a parallel and powerful search ofmore » the energy surface.« less
Training Feedforward Neural Networks: An Algorithm Giving Improved Generalization.
Lee, Charles W.
1997-01-01
An algorithm is derived for supervised training in multilayer feedforward neural networks. Relative to the gradient descent backpropagation algorithm it appears to give both faster convergence and improved generalization, whilst preserving the system of backpropagating errors through the network. Copyright 1996 Elsevier Science Ltd. PMID:12662887
A TLD dose algorithm using artificial neural networks
Moscovitch, M.; Rotunda, J.E.; Tawil, R.A.; Rathbone, B.A.
1995-12-31
An artificial neural network was designed and used to develop a dose algorithm for a multi-element thermoluminescence dosimeter (TLD). The neural network architecture is based on the concept of functional links network (FLN). Neural network is an information processing method inspired by the biological nervous system. A dose algorithm based on neural networks is fundamentally different as compared to conventional algorithms, as it has the capability to learn from its own experience. The neural network algorithm is shown the expected dose values (output) associated with given responses of a multi-element dosimeter (input) many times. The algorithm, being trained that way, eventually is capable to produce its own unique solution to similar (but not exactly the same) dose calculation problems. For personal dosimetry, the output consists of the desired dose components: deep dose, shallow dose and eye dose. The input consists of the TL data obtained from the readout of a multi-element dosimeter. The neural network approach was applied to the Harshaw Type 8825 TLD, and was shown to significantly improve the performance of this dosimeter, well within the U.S. accreditation requirements for personnel dosimeters.
Neural-network algorithms and architectures for pattern classification
Mao, Weidong.
1991-01-01
The study of the artificial neural networks is an integrated research field that involves the disciplines of applied mathematics, physics, neurobiology, computer science, information, control, parallel processing and VLSI. This dissertation deals with a number of topics from a broad spectrum of neural network research in models, algorithms, applications and VLSI architectures. Specifically, this dissertation is aimed at studying neural network algorithms and architectures for pattern classification tasks. The work presented in this dissertation has a wide range of applications including speech recognition, image recognition, and high level knowledge processing. Supervised neural networks, such as the back-propagation network, can be used for classification tasks as the result of approximating an input/output mapping. They are the approximation-based classifiers. The original gradient descent back propagation learning algorithm exhibits slow convergence speed. Fast algorithms such as the conjugate gradient and quasi-Newton algorithms can be adopted. The main emphasis on neural network classifiers in this dissertation is the competition-based classifiers. Due to the rapid advance in VLSI technology, parallel processing, and computer aided design (CAD), application-specific VLSI systems are becoming more and more powerful and feasible. In particular, VLSI array processors offer high speed and efficiency through their massive parallelism and pipelining, regularity, modularity, and local communication. A unified VLSI array architecture can be used for implementing neural networks and Hidden Markov Models. He also proposes a pipeline interleaving approach to design VLSI array architectures for real-time image and video signal processing.
Genetic-algorithm-based tri-state neural networks
NASA Astrophysics Data System (ADS)
Uang, Chii-Maw; Chen, Wen-Gong; Horng, Ji-Bin
2002-09-01
A new method, using genetic algorithms, for constructing a tri-state neural network is presented. The global searching features of the genetic algorithms are adopted to help us easily find the interconnection weight matrix of a bipolar neural network. The construction method is based on the biological nervous systems, which evolve the parameters encoded in genes. Taking the advantages of conventional (binary) genetic algorithms, a two-level chromosome structure is proposed for training the tri-state neural network. A Matlab program is developed for simulating the network performances. The results show that the proposed genetic algorithms method not only has the features of accurate of constructing the interconnection weight matrix, but also has better network performance.
An Improved Back Propagation Neural Network Algorithm on Classification Problems
NASA Astrophysics Data System (ADS)
Nawi, Nazri Mohd; Ransing, R. S.; Salleh, Mohd Najib Mohd; Ghazali, Rozaida; Hamid, Norhamreeza Abdul
The back propagation algorithm is one the most popular algorithms to train feed forward neural networks. However, the convergence of this algorithm is slow, it is mainly because of gradient descent algorithm. Previous research demonstrated that in 'feed forward' algorithm, the slope of the activation function is directly influenced by a parameter referred to as 'gain'. This research proposed an algorithm for improving the performance of the back propagation algorithm by introducing the adaptive gain of the activation function. The gain values change adaptively for each node. The influence of the adaptive gain on the learning ability of a neural network is analysed. Multi layer feed forward neural networks have been assessed. Physical interpretation of the relationship between the gain value and the learning rate and weight values is given. The efficiency of the proposed algorithm is compared with conventional Gradient Descent Method and verified by means of simulation on four classification problems. In learning the patterns, the simulations result demonstrate that the proposed method converged faster on Wisconsin breast cancer with an improvement ratio of nearly 2.8, 1.76 on diabetes problem, 65% better on thyroid data sets and 97% faster on IRIS classification problem. The results clearly show that the proposed algorithm significantly improves the learning speed of the conventional back-propagation algorithm.
A training algorithm for binary feedforward neural networks.
Gray, D L; Michel, A N
1992-01-01
The authors present a new training algorithm to be used on a four-layer perceptron-type feedforward neural network for the generation of binary-to-binary mappings. This algorithm is called the Boolean-like training algorithm (BLTA) and is derived from original principles of Boolean algebra followed by selected extensions. The algorithm can be implemented on analog hardware, using a four-layer binary feedforward neural network (BFNN). The BLTA does not constitute a traditional circuit building technique. Indeed, the rules which govern the BLTA allow for generalization of data in the face of incompletely specified Boolean functions. When compared with techniques which employ descent methods, training times are greatly reduced in the case of the BLTA. Also, when the BFNN is used in conjunction with A/D converters, the applicability of the present algorithm can be extended to accept real-valued inputs. PMID:18276419
Metaheuristic Algorithms for Convolution Neural Network.
Rere, L M Rasdi; Fanany, Mohamad Ivan; Arymurthy, Aniati Murni
2016-01-01
A typical modern optimization technique is usually either heuristic or metaheuristic. This technique has managed to solve some optimization problems in the research area of science, engineering, and industry. However, implementation strategy of metaheuristic for accuracy improvement on convolution neural networks (CNN), a famous deep learning method, is still rarely investigated. Deep learning relates to a type of machine learning technique, where its aim is to move closer to the goal of artificial intelligence of creating a machine that could successfully perform any intellectual tasks that can be carried out by a human. In this paper, we propose the implementation strategy of three popular metaheuristic approaches, that is, simulated annealing, differential evolution, and harmony search, to optimize CNN. The performances of these metaheuristic methods in optimizing CNN on classifying MNIST and CIFAR dataset were evaluated and compared. Furthermore, the proposed methods are also compared with the original CNN. Although the proposed methods show an increase in the computation time, their accuracy has also been improved (up to 7.14 percent). PMID:27375738
Metaheuristic Algorithms for Convolution Neural Network
Fanany, Mohamad Ivan; Arymurthy, Aniati Murni
2016-01-01
A typical modern optimization technique is usually either heuristic or metaheuristic. This technique has managed to solve some optimization problems in the research area of science, engineering, and industry. However, implementation strategy of metaheuristic for accuracy improvement on convolution neural networks (CNN), a famous deep learning method, is still rarely investigated. Deep learning relates to a type of machine learning technique, where its aim is to move closer to the goal of artificial intelligence of creating a machine that could successfully perform any intellectual tasks that can be carried out by a human. In this paper, we propose the implementation strategy of three popular metaheuristic approaches, that is, simulated annealing, differential evolution, and harmony search, to optimize CNN. The performances of these metaheuristic methods in optimizing CNN on classifying MNIST and CIFAR dataset were evaluated and compared. Furthermore, the proposed methods are also compared with the original CNN. Although the proposed methods show an increase in the computation time, their accuracy has also been improved (up to 7.14 percent). PMID:27375738
Simulating and Synthesizing Substructures Using Neural Network and Genetic Algorithms
NASA Technical Reports Server (NTRS)
Liu, Youhua; Kapania, Rakesh K.; VanLandingham, Hugh F.
1997-01-01
The feasibility of simulating and synthesizing substructures by computational neural network models is illustrated by investigating a statically indeterminate beam, using both a 1-D and a 2-D plane stress modelling. The beam can be decomposed into two cantilevers with free-end loads. By training neural networks to simulate the cantilever responses to different loads, the original beam problem can be solved as a match-up between two subsystems under compatible interface conditions. The genetic algorithms are successfully used to solve the match-up problem. Simulated results are found in good agreement with the analytical or FEM solutions.
A neural network algorithm for sea ice edge classification
Alhumaidi, S.M.; Ferguson, S.M.; Jones, W.L.; Park, J.D.
1997-07-01
The NASA Scatterometer (NSCAT), launched in August 1996, is designed to measure wind vectors over ice-free oceans. To prevent contamination f the wind measurements, by the presence of sea ice, algorithms based on neural network technology have been developed to classify ice-free ocean surfaces. Neural networks trained using polarized alone and polarized plus multi-azimuth look Ku-band backscatter are described. Algorithm skill in locating the sea ice edge around Antarctica is experimentally evaluated using backscatter data from the Seasat-A Satellite Scatterometer that operated in 1978. Comparisons between the algorithms demonstrate a slight advantage of combined polarization and multi-look over using co-polarized backscatter alone. Classification skill is evaluated by comparisons with surface truth (sea ice maps), subjective ice classification, and independent over lapping scatterometer measurements (consecutive revolutions).
Adaptive NUC algorithm for uncooled IRFPA based on neural networks
NASA Astrophysics Data System (ADS)
Liu, Ziji; Jiang, Yadong; Lv, Jian; Zhu, Hongbin
2010-10-01
With developments in uncooled infrared plane array (UFPA) technology, many new advanced uncooled infrared sensors are used in defensive weapons, scientific research, industry and commercial applications. A major difference in imaging techniques between infrared IRFPA imaging system and a visible CCD camera is that, IRFPA need nonuniformity correction and dead pixel compensation, we usually called it infrared image pre-processing. Two-point or multi-point correction algorithms based on calibration commonly used may correct the non-uniformity of IRFPAs, but they are limited by pixel linearity and instability. Therefore, adaptive non-uniformity correction techniques are developed. Two of these adaptive non-uniformity correction algorithms are mostly discussed, one is based on temporal high-pass filter, and another is based on neural network. In this paper, a new NUC algorithm based on improved neural networks is introduced, and involves the compare result between improved neural networks and other adaptive correction techniques. A lot of different will discussed in different angle, like correction effects, calculation efficiency, hardware implementation and so on. According to the result and discussion, it could be concluding that the adaptive algorithm offers improved performance compared to traditional calibration mode techniques. This new algorithm not only provides better sensitivity, but also increases the system dynamic range. As the sensor application expended, it will be very useful in future infrared imaging systems.
An Efficient Supervised Training Algorithm for Multilayer Spiking Neural Networks
Xie, Xiurui; Qu, Hong; Liu, Guisong; Zhang, Malu; Kurths, Jürgen
2016-01-01
The spiking neural networks (SNNs) are the third generation of neural networks and perform remarkably well in cognitive tasks such as pattern recognition. The spike emitting and information processing mechanisms found in biological cognitive systems motivate the application of the hierarchical structure and temporal encoding mechanism in spiking neural networks, which have exhibited strong computational capability. However, the hierarchical structure and temporal encoding approach require neurons to process information serially in space and time respectively, which reduce the training efficiency significantly. For training the hierarchical SNNs, most existing methods are based on the traditional back-propagation algorithm, inheriting its drawbacks of the gradient diffusion and the sensitivity on parameters. To keep the powerful computation capability of the hierarchical structure and temporal encoding mechanism, but to overcome the low efficiency of the existing algorithms, a new training algorithm, the Normalized Spiking Error Back Propagation (NSEBP) is proposed in this paper. In the feedforward calculation, the output spike times are calculated by solving the quadratic function in the spike response model instead of detecting postsynaptic voltage states at all time points in traditional algorithms. Besides, in the feedback weight modification, the computational error is propagated to previous layers by the presynaptic spike jitter instead of the gradient decent rule, which realizes the layer-wised training. Furthermore, our algorithm investigates the mathematical relation between the weight variation and voltage error change, which makes the normalization in the weight modification applicable. Adopting these strategies, our algorithm outperforms the traditional SNN multi-layer algorithms in terms of learning efficiency and parameter sensitivity, that are also demonstrated by the comprehensive experimental results in this paper. PMID:27044001
An Efficient Supervised Training Algorithm for Multilayer Spiking Neural Networks.
Xie, Xiurui; Qu, Hong; Liu, Guisong; Zhang, Malu; Kurths, Jürgen
2016-01-01
The spiking neural networks (SNNs) are the third generation of neural networks and perform remarkably well in cognitive tasks such as pattern recognition. The spike emitting and information processing mechanisms found in biological cognitive systems motivate the application of the hierarchical structure and temporal encoding mechanism in spiking neural networks, which have exhibited strong computational capability. However, the hierarchical structure and temporal encoding approach require neurons to process information serially in space and time respectively, which reduce the training efficiency significantly. For training the hierarchical SNNs, most existing methods are based on the traditional back-propagation algorithm, inheriting its drawbacks of the gradient diffusion and the sensitivity on parameters. To keep the powerful computation capability of the hierarchical structure and temporal encoding mechanism, but to overcome the low efficiency of the existing algorithms, a new training algorithm, the Normalized Spiking Error Back Propagation (NSEBP) is proposed in this paper. In the feedforward calculation, the output spike times are calculated by solving the quadratic function in the spike response model instead of detecting postsynaptic voltage states at all time points in traditional algorithms. Besides, in the feedback weight modification, the computational error is propagated to previous layers by the presynaptic spike jitter instead of the gradient decent rule, which realizes the layer-wised training. Furthermore, our algorithm investigates the mathematical relation between the weight variation and voltage error change, which makes the normalization in the weight modification applicable. Adopting these strategies, our algorithm outperforms the traditional SNN multi-layer algorithms in terms of learning efficiency and parameter sensitivity, that are also demonstrated by the comprehensive experimental results in this paper. PMID:27044001
Neural network fusion capabilities for efficient implementation of tracking algorithms
NASA Astrophysics Data System (ADS)
Sundareshan, Malur K.; Amoozegar, Farid
1996-05-01
The ability to efficiently fuse information of different forms for facilitating intelligent decision-making is one of the major capabilities of trained multilayer neural networks that is being recognized int eh recent times. While development of innovative adaptive control algorithms for nonlinear dynamical plants which attempt to exploit these capabilities seems to be more popular, a corresponding development of nonlinear estimation algorithms using these approaches, particularly for application in target surveillance and guidance operations, has not received similar attention. In this paper we describe the capabilities and functionality of neural network algorithms for data fusion and implementation of nonlinear tracking filters. For a discussion of details and for serving as a vehicle for quantitative performance evaluations, the illustrative case of estimating the position and velocity of surveillance targets is considered. Efficient target tracking algorithms that can utilize data from a host of sensing modalities and are capable of reliably tracking even uncooperative targets executing fast and complex maneuvers are of interest in a number of applications. The primary motivation for employing neural networks in these applications comes form the efficiency with which more features extracted from different sensor measurements can be utilized as inputs for estimating target maneuvers. Such an approach results in an overall nonlinear tracking filter which has several advantages over the popular efforts at designing nonlinear estimation algorithms for tracking applications, the principle one being the reduction of mathematical and computational complexities. A system architecture that efficiently integrates the processing capabilities of a trained multilayer neural net with the tracking performance of a Kalman filter is described in this paper.
Recursive least-squares learning algorithms for neural networks
Lewis, P.S. ); Hwang, Jenq-Neng . Dept. of Electrical Engineering)
1990-01-01
This paper presents the development of a pair of recursive least squares (RLS) algorithms for online training of multilayer perceptrons, which are a class of feedforward artificial neural networks. These algorithms incorporate second order information about the training error surface in order to achieve faster learning rates than are possible using first order gradient descent algorithms such as the generalized delta rule. A least squares formulation is derived from a linearization of the training error function. Individual training pattern errors are linearized about the network parameters that were in effect when the pattern was presented. This permits the recursive solution of the least squares approximation, either via conventional RLS recursions or by recursive QR decomposition-based techniques. The computational complexity of the update is in the order of (N{sup 2}), where N is the number of network parameters. This is due to the estimation of the N {times} N inverse Hessian matrix. Less computationally intensive approximations of the RLS algorithms can be easily derived by using only block diagonal elements of this matrix, thereby partitioning the learning into independent sets. A simulation example is presented in which a neural network is trained to approximate a two dimensional Gaussian bump. In this example, RLS training required an order of magnitude fewer iterations on average (527) than did training with the generalized delta rule (6331). 14 refs., 3 figs.
Constructive neural-network learning algorithms for pattern classification.
Parekh, R; Yang, J; Honavar, V
2000-01-01
Constructive learning algorithms offer an attractive approach for the incremental construction of near-minimal neural-network architectures for pattern classification. They help overcome the need for ad hoc and often inappropriate choices of network topology in algorithms that search for suitable weights in a priori fixed network architectures. Several such algorithms are proposed in the literature and shown to converge to zero classification errors (under certain assumptions) on tasks that involve learning a binary to binary mapping (i.e., classification problems involving binary-valued input attributes and two output categories). We present two constructive learning algorithms MPyramid-real and MTiling-real that extend the pyramid and tiling algorithms, respectively, for learning real to M-ary mappings (i.e., classification problems involving real-valued input attributes and multiple output classes). We prove the convergence of these algorithms and empirically demonstrate their applicability to practical pattern classification problems. Additionally, we show how the incorporation of a local pruning step can eliminate several redundant neurons from MTiling-real networks. PMID:18249773
NASA Astrophysics Data System (ADS)
Timofeew, Sergey; Eliseev, Vladimir; Tcherkassov, Oleg; Birukow, Valentin; Orbachevskyi, Leonid; Shamsutdinov, Uriy
1998-04-01
Some problems of creation of medical expert systems and the ways of their overcoming using artificial neural networks are discussed. The instrumental system for projecting neural network algorithms `Neural Architector', developed by the authors, is described. It allows to perform effective modeling of artificial neural networks and to analyze their work. The example of the application of the `Neural Architector' system in composing an expert system for diagnostics of pulmonological diseases is shown.
On-line learning algorithms for locally recurrent neural networks.
Campolucci, P; Uncini, A; Piazza, F; Rao, B D
1999-01-01
This paper focuses on on-line learning procedures for locally recurrent neural networks with emphasis on multilayer perceptron (MLP) with infinite impulse response (IIR) synapses and its variations which include generalized output and activation feedback multilayer networks (MLN's). We propose a new gradient-based procedure called recursive backpropagation (RBP) whose on-line version, causal recursive backpropagation (CRBP), presents some advantages with respect to the other on-line training methods. The new CRBP algorithm includes as particular cases backpropagation (BP), temporal backpropagation (TBP), backpropagation for sequences (BPS), Back-Tsoi algorithm among others, thereby providing a unifying view on gradient calculation techniques for recurrent networks with local feedback. The only learning method that has been proposed for locally recurrent networks with no architectural restriction is the one by Back and Tsoi. The proposed algorithm has better stability and higher speed of convergence with respect to the Back-Tsoi algorithm, which is supported by the theoretical development and confirmed by simulations. The computational complexity of the CRBP is comparable with that of the Back-Tsoi algorithm, e.g., less that a factor of 1.5 for usual architectures and parameter settings. The superior performance of the new algorithm, however, easily justifies this small increase in computational burden. In addition, the general paradigms of truncated BPTT and RTRL are applied to networks with local feedback and compared with the new CRBP method. The simulations show that CRBP exhibits similar performances and the detailed analysis of complexity reveals that CRBP is much simpler and easier to implement, e.g., CRBP is local in space and in time while RTRL is not local in space. PMID:18252525
Combining neural networks and genetic algorithms for hydrological flow forecasting
NASA Astrophysics Data System (ADS)
Neruda, Roman; Srejber, Jan; Neruda, Martin; Pascenko, Petr
2010-05-01
We present a neural network approach to rainfall-runoff modeling for small size river basins based on several time series of hourly measured data. Different neural networks are considered for short time runoff predictions (from one to six hours lead time) based on runoff and rainfall data observed in previous time steps. Correlation analysis shows that runoff data, short time rainfall history, and aggregated API values are the most significant data for the prediction. Neural models of multilayer perceptron and radial basis function networks with different numbers of units are used and compared with more traditional linear time series predictors. Out of possible 48 hours of relevant history of all the input variables, the most important ones are selected by means of input filters created by a genetic algorithm. The genetic algorithm works with population of binary encoded vectors defining input selection patterns. Standard genetic operators of two-point crossover, random bit-flipping mutation, and tournament selection were used. The evaluation of objective function of each individual consists of several rounds of building and testing a particular neural network model. The whole procedure is rather computational exacting (taking hours to days on a desktop PC), thus a high-performance mainframe computer has been used for our experiments. Results based on two years worth data from the Ploucnice river in Northern Bohemia suggest that main problems connected with this approach to modeling are ovetraining that can lead to poor generalization, and relatively small number of extreme events which makes it difficult for a model to predict the amplitude of the event. Thus, experiments with both absolute and relative runoff predictions were carried out. In general it can be concluded that the neural models show about 5 per cent improvement in terms of efficiency coefficient over liner models. Multilayer perceptrons with one hidden layer trained by back propagation algorithm and
A constructive algorithm for training cooperative neural network ensembles.
Islam, Md M; Yao, Xin; Murase, K
2003-01-01
Presents a constructive algorithm for training cooperative neural-network ensembles (CNNEs). CNNE combines ensemble architecture design with cooperative training for individual neural networks (NNs) in ensembles. Unlike most previous studies on training ensembles, CNNE puts emphasis on both accuracy and diversity among individual NNs in an ensemble. In order to maintain accuracy among individual NNs, the number of hidden nodes in individual NNs are also determined by a constructive approach. Incremental training based on negative correlation is used in CNNE to train individual NNs for different numbers of training epochs. The use of negative correlation learning and different training epochs for training individual NNs reflect CNNEs emphasis on diversity among individual NNs in an ensemble. CNNE has been tested extensively on a number of benchmark problems in machine learning and neural networks, including Australian credit card assessment, breast cancer, diabetes, glass, heart disease, letter recognition, soybean, and Mackey-Glass time series prediction problems. The experimental results show that CNNE can produce NN ensembles with good generalization ability. PMID:18238062
Applications of genetic algorithms and neural networks to interatomic potentials
NASA Astrophysics Data System (ADS)
Hobday, Steven; Smith, Roger; BelBruno, Joe
1999-06-01
Applications of two modern artificial intelligence (AI) techniques, genetic algorithms (GA) and neural networks (NN) to computer simulations are reported. It is shown that the GA are very useful tools for determining the minimum energy structures of clusters of atoms described by interatomic potential functions and generally outperform other optimisation methods for this task. A number of applications are given including covalent, and close packed structures of single or multi-component atomic species. It is also shown that (many body) interatomic potential functions for multi-component systems can be derived by training a specially constructed NN on a variety of structural data.
Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks.
Walter, Florian; Röhrbein, Florian; Knoll, Alois
2015-12-01
The application of biologically inspired methods in design and control has a long tradition in robotics. Unlike previous approaches in this direction, the emerging field of neurorobotics not only mimics biological mechanisms at a relatively high level of abstraction but employs highly realistic simulations of actual biological nervous systems. Even today, carrying out these simulations efficiently at appropriate timescales is challenging. Neuromorphic chip designs specially tailored to this task therefore offer an interesting perspective for neurorobotics. Unlike Von Neumann CPUs, these chips cannot be simply programmed with a standard programming language. Like real brains, their functionality is determined by the structure of neural connectivity and synaptic efficacies. Enabling higher cognitive functions for neurorobotics consequently requires the application of neurobiological learning algorithms to adjust synaptic weights in a biologically plausible way. In this paper, we therefore investigate how to program neuromorphic chips by means of learning. First, we provide an overview over selected neuromorphic chip designs and analyze them in terms of neural computation, communication systems and software infrastructure. On the theoretical side, we review neurobiological learning techniques. Based on this overview, we then examine on-die implementations of these learning algorithms on the considered neuromorphic chips. A final discussion puts the findings of this work into context and highlights how neuromorphic hardware can potentially advance the field of autonomous robot systems. The paper thus gives an in-depth overview of neuromorphic implementations of basic mechanisms of synaptic plasticity which are required to realize advanced cognitive capabilities with spiking neural networks. PMID:26422422
A fast neural-network algorithm for VLSI cell placement.
Aykanat, Cevdet; Bultan, Tevfik; Haritaoğlu, Ismail
1998-12-01
Cell placement is an important phase of current VLSI circuit design styles such as standard cell, gate array, and Field Programmable Gate Array (FPGA). Although nondeterministic algorithms such as Simulated Annealing (SA) were successful in solving this problem, they are known to be slow. In this paper, a neural network algorithm is proposed that produces solutions as good as SA in substantially less time. This algorithm is based on Mean Field Annealing (MFA) technique, which was successfully applied to various combinatorial optimization problems. A MFA formulation for the cell placement problem is derived which can easily be applied to all VLSI design styles. To demonstrate that the proposed algorithm is applicable in practice, a detailed formulation for the FPGA design style is derived, and the layouts of several benchmark circuits are generated. The performance of the proposed cell placement algorithm is evaluated in comparison with commercial automated circuit design software Xilinx Automatic Place and Route (APR) which uses SA technique. Performance evaluation is conducted using ACM/SIGDA Design Automation benchmark circuits. Experimental results indicate that the proposed MFA algorithm produces comparable results with APR. However, MFA is almost 20 times faster than APR on the average. PMID:12662737
Neural Networks Art: Solving Problems with Multiple Solutions and New Teaching Algorithm
Dmitrienko, V. D; Zakovorotnyi, A. Yu.; Leonov, S. Yu.; Khavina, I. P
2014-01-01
A new discrete neural networks adaptive resonance theory (ART), which allows solving problems with multiple solutions, is developed. New algorithms neural networks teaching ART to prevent degradation and reproduction classes at training noisy input data is developed. Proposed learning algorithms discrete ART networks, allowing obtaining different classification methods of input. PMID:25246988
APPLICATION OF NEURAL NETWORK ALGORITHMS FOR BPM LINEARIZATION
Musson, John C.; Seaton, Chad; Spata, Mike F.; Yan, Jianxun
2012-11-01
Stripline BPM sensors contain inherent non-linearities, as a result of field distortions from the pickup elements. Many methods have been devised to facilitate corrections, often employing polynomial fitting. The cost of computation makes real-time correction difficult, particulalry when integer math is utilized. The application of neural-network technology, particularly the multi-layer perceptron algorithm, is proposed as an efficient alternative for electrode linearization. A process of supervised learning is initially used to determine the weighting coefficients, which are subsequently applied to the incoming electrode data. A non-linear layer, known as an activation layer, is responsible for the removal of saturation effects. Implementation of a perceptron in an FPGA-based software-defined radio (SDR) is presented, along with performance comparisons. In addition, efficient calculation of the sigmoidal activation function via the CORDIC algorithm is presented.
Neural network implementations of data association algorithms for sensor fusion
NASA Technical Reports Server (NTRS)
Brown, Donald E.; Pittard, Clarence L.; Martin, Worthy N.
1989-01-01
The paper is concerned with locating a time varying set of entities in a fixed field when the entities are sensed at discrete time instances. At a given time instant a collection of bivariate Gaussian sensor reports is produced, and these reports estimate the location of a subset of the entities present in the field. A database of reports is maintained, which ideally should contain one report for each entity sensed. Whenever a collection of sensor reports is received, the database must be updated to reflect the new information. This updating requires association processing between the database reports and the new sensor reports to determine which pairs of sensor and database reports correspond to the same entity. Algorithms for performing this association processing are presented. Neural network implementation of the algorithms, along with simulation results comparing the approaches are provided.
Novel maximum-margin training algorithms for supervised neural networks.
Ludwig, Oswaldo; Nunes, Urbano
2010-06-01
This paper proposes three novel training methods, two of them based on the backpropagation approach and a third one based on information theory for multilayer perceptron (MLP) binary classifiers. Both backpropagation methods are based on the maximal-margin (MM) principle. The first one, based on the gradient descent with adaptive learning rate algorithm (GDX) and named maximum-margin GDX (MMGDX), directly increases the margin of the MLP output-layer hyperplane. The proposed method jointly optimizes both MLP layers in a single process, backpropagating the gradient of an MM-based objective function, through the output and hidden layers, in order to create a hidden-layer space that enables a higher margin for the output-layer hyperplane, avoiding the testing of many arbitrary kernels, as occurs in case of support vector machine (SVM) training. The proposed MM-based objective function aims to stretch out the margin to its limit. An objective function based on Lp-norm is also proposed in order to take into account the idea of support vectors, however, overcoming the complexity involved in solving a constrained optimization problem, usually in SVM training. In fact, all the training methods proposed in this paper have time and space complexities O(N) while usual SVM training methods have time complexity O(N (3)) and space complexity O(N (2)) , where N is the training-data-set size. The second approach, named minimization of interclass interference (MICI), has an objective function inspired on the Fisher discriminant analysis. Such algorithm aims to create an MLP hidden output where the patterns have a desirable statistical distribution. In both training methods, the maximum area under ROC curve (AUC) is applied as stop criterion. The third approach offers a robust training framework able to take the best of each proposed training method. The main idea is to compose a neural model by using neurons extracted from three other neural networks, each one previously trained by
Designing Artificial Neural Networks Using Particle Swarm Optimization Algorithms
Garro, Beatriz A.; Vázquez, Roberto A.
2015-01-01
Artificial Neural Network (ANN) design is a complex task because its performance depends on the architecture, the selected transfer function, and the learning algorithm used to train the set of synaptic weights. In this paper we present a methodology that automatically designs an ANN using particle swarm optimization algorithms such as Basic Particle Swarm Optimization (PSO), Second Generation of Particle Swarm Optimization (SGPSO), and a New Model of PSO called NMPSO. The aim of these algorithms is to evolve, at the same time, the three principal components of an ANN: the set of synaptic weights, the connections or architecture, and the transfer functions for each neuron. Eight different fitness functions were proposed to evaluate the fitness of each solution and find the best design. These functions are based on the mean square error (MSE) and the classification error (CER) and implement a strategy to avoid overtraining and to reduce the number of connections in the ANN. In addition, the ANN designed with the proposed methodology is compared with those designed manually using the well-known Back-Propagation and Levenberg-Marquardt Learning Algorithms. Finally, the accuracy of the method is tested with different nonlinear pattern classification problems. PMID:26221132
Designing Artificial Neural Networks Using Particle Swarm Optimization Algorithms.
Garro, Beatriz A; Vázquez, Roberto A
2015-01-01
Artificial Neural Network (ANN) design is a complex task because its performance depends on the architecture, the selected transfer function, and the learning algorithm used to train the set of synaptic weights. In this paper we present a methodology that automatically designs an ANN using particle swarm optimization algorithms such as Basic Particle Swarm Optimization (PSO), Second Generation of Particle Swarm Optimization (SGPSO), and a New Model of PSO called NMPSO. The aim of these algorithms is to evolve, at the same time, the three principal components of an ANN: the set of synaptic weights, the connections or architecture, and the transfer functions for each neuron. Eight different fitness functions were proposed to evaluate the fitness of each solution and find the best design. These functions are based on the mean square error (MSE) and the classification error (CER) and implement a strategy to avoid overtraining and to reduce the number of connections in the ANN. In addition, the ANN designed with the proposed methodology is compared with those designed manually using the well-known Back-Propagation and Levenberg-Marquardt Learning Algorithms. Finally, the accuracy of the method is tested with different nonlinear pattern classification problems. PMID:26221132
Optimized approximation algorithm in neural networks without overfitting.
Liu, Yinyin; Starzyk, Janusz A; Zhu, Zhen
2008-06-01
In this paper, an optimized approximation algorithm (OAA) is proposed to address the overfitting problem in function approximation using neural networks (NNs). The optimized approximation algorithm avoids overfitting by means of a novel and effective stopping criterion based on the estimation of the signal-to-noise-ratio figure (SNRF). Using SNRF, which checks the goodness-of-fit in the approximation, overfitting can be automatically detected from the training error only without use of a separate validation set. The algorithm has been applied to problems of optimizing the number of hidden neurons in a multilayer perceptron (MLP) and optimizing the number of learning epochs in MLP's backpropagation training using both synthetic and benchmark data sets. The OAA algorithm can also be utilized in the optimization of other parameters of NNs. In addition, it can be applied to the problem of function approximation using any kind of basis functions, or to the problem of learning model selection when overfitting needs to be considered. PMID:18541499
A synergisitic Neural Network Soil Moisture Retrieval Algorithm for SMAP
NASA Astrophysics Data System (ADS)
Kolassa, J.; Reichle, R. H.; Gentine, P.; Prigent, C.; Aires, F.; Fang, B.
2015-12-01
A Neural Network (NN)-based algorithm is developed to retrieve surface soil moisture from Soil Moisture Active/Passive (SMAP) microwave observations. This statistical approach serves as an alternative to the official Radiative Transfer (RT) based SMAP retrieval algorithm, since it avoids an explicit formulation of the RT processes as well as the use of often uncertain or unavailable a priori knowledge for additional surface parameters. The NN algorithm is calibrated on observations from the SMAP radiometer and radar as well as surface soil moisture fields from the MERRA-2 reanalysis. To highlight different physical aspects of the satellite signals and to maximize the soil moisture information, different preprocessing techniques of the SMAP data are investigated. These include an analysis of radiometer polarization and diurnal indices to isolate the surface temperature contribution, as well as the radar co- and cross-polarized channels to account for vegetation effects. A major difference with respect to the official retrieval is the increased importance given to the information provided by the SMAP radar or other active sensors, utilizing not only the relative spatial structures, but also the absolute soil moisture information provided. The NN methodology combines multiple sensor observations in a data fusion approach and is thus able to fully exploit the complementarity of the information provided by the different instruments. The algorithm is used to compute global estimates of surface soil moisture and evaluated against retrieved soil moisture from SMOS as well as in situ observations from the International Soil Moisture Network (ISMN). The calibration on MERRA-2 data means that the NN retrieval algorithm functions as the model operator in a data assimilation framework yielding soil moisture estimates that are very compatible with the model. This could facilitate the assimilation of SMAP observations into land surface and numerical weather prediction models.
Quantum Associative Neural Network with Nonlinear Search Algorithm
NASA Astrophysics Data System (ADS)
Zhou, Rigui; Wang, Huian; Wu, Qian; Shi, Yang
2012-03-01
Based on analysis on properties of quantum linear superposition, to overcome the complexity of existing quantum associative memory which was proposed by Ventura, a new storage method for multiply patterns is proposed in this paper by constructing the quantum array with the binary decision diagrams. Also, the adoption of the nonlinear search algorithm increases the pattern recalling speed of this model which has multiply patterns to O( {log2}^{2^{n -t}} ) = O( n - t ) time complexity, where n is the number of quantum bit and t is the quantum information of the t quantum bit. Results of case analysis show that the associative neural network model proposed in this paper based on quantum learning is much better and optimized than other researchers' counterparts both in terms of avoiding the additional qubits or extraordinary initial operators, storing pattern and improving the recalling speed.
Strawberry Maturity Neural Network Detectng System Based on Genetic Algorithm
NASA Astrophysics Data System (ADS)
Xu, Liming
The quick and non-detective detection of agriculture product is one of the measures to increase the precision and productivity of harvesting and grading. Having analyzed H frequency of different maturities in different light intensities, the results show that H frequency for the same maturity has little influence in different light intensities; Under the same light intensity, three strawberry maturities are changing in order. After having confirmed the H frequency section to distinguish the different strawberry maturity, the triplelayer feed-forward neural network system to detect strawberry maturity was designed by using genetic algorithm. The test results show that the detecting precision ratio is 91.7%, it takes 160ms to distinguish one strawberry. Therefore, the online non-detective detecting the strawberry maturity could be realized.
Neural-network-biased genetic algorithms for materials design
NASA Astrophysics Data System (ADS)
Patra, Tarak; Meenakshisundaram, Venkatesh; Simmons, David
Machine learning tools have been progressively adopted by the materials science community to accelerate design of materials with targeted properties. However, in the search for new materials exhibiting properties and performance beyond that previously achieved, machine learning approaches are frequently limited by two major shortcomings. First, they are intrinsically interpolative. They are therefore better suited to the optimization of properties within the known range of accessible behavior than to the discovery of new materials with extremal behavior. Second, they require the availability of large datasets, which in some fields are not available and would be prohibitively expensive to produce. Here we describe a new strategy for combining genetic algorithms, neural networks and other machine learning tools, and molecular simulation to discover materials with extremal properties in the absence of pre-existing data. Predictions from progressively constructed machine learning tools are employed to bias the evolution of a genetic algorithm, with fitness evaluations performed via direct molecular dynamics simulation. We survey several initial materials design problems we have addressed with this framework and compare its performance to that of standard genetic algorithm approaches. We acknowledge the W. M. Keck Foundation for support of this work.
NASA Astrophysics Data System (ADS)
Li, Xiaofeng; Xiang, Suying; Zhu, Pengfei; Wu, Min
2015-12-01
In order to avoid the inherent deficiencies of the traditional BP neural network, such as slow convergence speed, that easily leading to local minima, poor generalization ability and difficulty in determining the network structure, the dynamic self-adaptive learning algorithm of the BP neural network is put forward to improve the function of the BP neural network. The new algorithm combines the merit of principal component analysis, particle swarm optimization, correlation analysis and self-adaptive model, hence can effectively solve the problems of selecting structural parameters, initial connection weights and thresholds and learning rates of the BP neural network. This new algorithm not only reduces the human intervention, optimizes the topological structures of BP neural networks and improves the network generalization ability, but also accelerates the convergence speed of a network, avoids trapping into local minima, and enhances network adaptation ability and prediction ability. The dynamic self-adaptive learning algorithm of the BP neural network is used to forecast the total retail sale of consumer goods of Sichuan Province, China. Empirical results indicate that the new algorithm is superior to the traditional BP network algorithm in predicting accuracy and time consumption, which shows the feasibility and effectiveness of the new algorithm.
Digit and command interpretation for electronic book using neural network and genetic algorithm.
Lam, H K; Leung, Frank H F
2004-12-01
This paper presents the interpretation of digits and commands using a modified neural network and the genetic algorithm. The modified neural network exhibits a node-to-node relationship which enhances its learning and generalization abilities. A digit-and-command interpreter constructed by the modified neural networks is proposed to recognize handwritten digits and commands. A genetic algorithm is employed to train the parameters of the modified neural networks of the digit-and-command interpreter. The proposed digit-and-command interpreter is successfully realized in an electronic book. Simulation and experimental results will be presented to show the applicability and merits of the proposed approach. PMID:15619928
Echoed time series predictions, neural networks and genetic algorithms
NASA Astrophysics Data System (ADS)
Conway, A.
This work aims to illustrate a potentially serious and previously unrecognised problem in using Neural Networks (NNs), and possibly other techniques, to predict Time Series (TS). It also demonstrates how a new training scheme using a genetic algorithm can alleviate this problem. Although it is already established that NNs can predict TS such as Sunspot Number (SSN) with reasonable success, the accuracy of these predictions is often judged solely by an RMS or related error. The use of this type of error overlooks the presence of what we have termed echoing, where the NN outputs its most recent input as its prediction. Therefore, a method of detecting echoed predictions is introduced, called time-shifting. Reasons for the presence of echo are discussed and then related to the choice of TS sampling. Finally, a new specially designed training scheme is described, which is a hybrid of a genetic algorithm search and back propagation. With this method we have successfully trained NNs to predict without any echo.
NASA Astrophysics Data System (ADS)
Zhang, Xiuping
In this paper, the weights of a Neural Network using Chaotic Imperialist Competitive Algorithm are updated. A three-layered Perseptron Neural Network applied for prediction of the maximum worth of the stocks changed in TEHRAN's bourse market. We trained this neural network with CICA, ICA, PSO and GA algorithms and compared the results with each other. The consideration of the results showed that the training and test error of the network trained by the CICA algorithm has been reduced in comparison to the other three methods.
NASA Technical Reports Server (NTRS)
Boussalis, Dhemetrios; Wang, Shyh J.
1992-01-01
This paper presents a method for utilizing artificial neural networks for direct adaptive control of dynamic systems with poorly known dynamics. The neural network weights (controller gains) are adapted in real time using state measurements and a random search optimization algorithm. The results are demonstrated via simulation using two highly nonlinear systems.
Performance evaluation of a routing algorithm based on Hopfield Neural Network for network-on-chip
NASA Astrophysics Data System (ADS)
Esmaelpoor, Jamal; Ghafouri, Abdollah
2015-12-01
Network on chip (NoC) has emerged as a solution to overcome the system on chip growing complexity and design challenges. A proper routing algorithm is a key issue of an NoC design. An appropriate routing method balances load across the network channels and keeps path length as short as possible. This survey investigates the performance of a routing algorithm based on Hopfield Neural Network. It is a dynamic programming to provide optimal path and network monitoring in real time. The aim of this article is to analyse the possibility of using a neural network as a router. The algorithm takes into account the path with the lowest delay (cost) form source to destination. In other words, the path a message takes from source to destination depends on network traffic situation at the time and it is the fastest one. The simulation results show that the proposed approach improves average delay, throughput and network congestion efficiently. At the same time, the increase in power consumption is almost negligible.
A Speech Endpoint Detection Algorithm Based on BP Neural Network and Multiple Features
NASA Astrophysics Data System (ADS)
Shi, Yong-Qiang; Li, Ru-Wei; Zhang, Shuang; Wang, Shuai; Yi, Xiao-Qun
Focusing on a sharp decline in the performance of endpoint detection algorithm in a complicated noise environment, a new speech endpoint detection method based on BPNN (back propagation neural network) and multiple features is presented. Firstly, maximum of short-time autocorrelation function and spectrum variance of speech signals are extracted respectively. Secondly, these feature vectors as the input of BP neural network are trained and modeled and then the Genetic Algorithm is used to optimize the BP Neural Network. Finally, the signal's type is determined according to the output of Neural Network. The experiments show that the correct rate of this proposed algorithm is improved, because this method has better robustness and adaptability than algorithm based on maximum of short-time autocorrelation function or spectrum variance.
Application of BP Neural Network Based on Genetic Algorithm in Quantitative Analysis of Mixed GAS
NASA Astrophysics Data System (ADS)
Chen, Hongyan; Liu, Wenzhen; Qu, Jian; Zhang, Bing; Li, Zhibin
Aiming at the problem of mixed gas detection in neural network and analysis on the principle of gas detection. Combining BP algorithm of genetic algorithm with hybrid gas sensors, a kind of quantitative analysis system of mixed gas is designed. The local minimum of network learning is the main reason which affects the precision of gas analysis. On the basis of the network study to improve the learning algorithms, the analyses and tests for CO, CO2 and HC compounds were tested. The results showed that the above measures effectively improve and enhance the accuracy of the neural network for gas analysis.
Training the Recurrent neural network by the Fuzzy Min-Max algorithm for fault prediction
Zemouri, Ryad; Racoceanu, Daniel; Minca, Eugenia; Filip, Florin
2009-03-05
In this paper, we present a training technique of a Recurrent Radial Basis Function neural network for fault prediction. We use the Fuzzy Min-Max technique to initialize the k-center of the RRBF neural network. The k-means algorithm is then applied to calculate the centers that minimize the mean square error of the prediction task. The performances of the k-means algorithm are then boosted by the Fuzzy Min-Max technique.
A stochastic learning algorithm for layered neural networks
Bartlett, E.B.; Uhrig, R.E.
1992-12-31
The random optimization method typically uses a Gaussian probability density function (PDF) to generate a random search vector. In this paper the random search technique is applied to the neural network training problem and is modified to dynamically seek out the optimal probability density function (OPDF) from which to select the search vector. The dynamic OPDF search process, combined with an auto-adaptive stratified sampling technique and a dynamic node architecture (DNA) learning scheme, completes the modifications of the basic method. The DNA technique determines the appropriate number of hidden nodes needed for a given training problem. By using DNA, researchers do not have to set the neural network architectures before training is initiated. The approach is applied to networks of generalized, fully interconnected, continuous perceptions. Computer simulation results are given.
A stochastic learning algorithm for layered neural networks
Bartlett, E.B. . Dept. of Mechanical Engineering); Uhrig, R.E. . Dept. of Nuclear Engineering)
1992-01-01
The random optimization method typically uses a Gaussian probability density function (PDF) to generate a random search vector. In this paper the random search technique is applied to the neural network training problem and is modified to dynamically seek out the optimal probability density function (OPDF) from which to select the search vector. The dynamic OPDF search process, combined with an auto-adaptive stratified sampling technique and a dynamic node architecture (DNA) learning scheme, completes the modifications of the basic method. The DNA technique determines the appropriate number of hidden nodes needed for a given training problem. By using DNA, researchers do not have to set the neural network architectures before training is initiated. The approach is applied to networks of generalized, fully interconnected, continuous perceptions. Computer simulation results are given.
The No-Prop algorithm: a new learning algorithm for multilayer neural networks.
Widrow, Bernard; Greenblatt, Aaron; Kim, Youngsik; Park, Dookun
2013-01-01
A new learning algorithm for multilayer neural networks that we have named No-Propagation (No-Prop) is hereby introduced. With this algorithm, the weights of the hidden-layer neurons are set and fixed with random values. Only the weights of the output-layer neurons are trained, using steepest descent to minimize mean square error, with the LMS algorithm of Widrow and Hoff. The purpose of introducing nonlinearity with the hidden layers is examined from the point of view of Least Mean Square Error Capacity (LMS Capacity), which is defined as the maximum number of distinct patterns that can be trained into the network with zero error. This is shown to be equal to the number of weights of each of the output-layer neurons. The No-Prop algorithm and the Back-Prop algorithm are compared. Our experience with No-Prop is limited, but from the several examples presented here, it seems that the performance regarding training and generalization of both algorithms is essentially the same when the number of training patterns is less than or equal to LMS Capacity. When the number of training patterns exceeds Capacity, Back-Prop is generally the better performer. But equivalent performance can be obtained with No-Prop by increasing the network Capacity by increasing the number of neurons in the hidden layer that drives the output layer. The No-Prop algorithm is much simpler and easier to implement than Back-Prop. Also, it converges much faster. It is too early to definitively say where to use one or the other of these algorithms. This is still a work in progress. PMID:23140797
Study on Optimized Elman Neural Network Classification Algorithm Based on PLS and CA
Zhao, Dean; Shen, Tian; Zhao, Yuyan
2014-01-01
High-dimensional large sample data sets, between feature variables and between samples, may cause some correlative or repetitive factors, occupy lots of storage space, and consume much computing time. Using the Elman neural network to deal with them, too many inputs will influence the operating efficiency and recognition accuracy; too many simultaneous training samples, as well as being not able to get precise neural network model, also restrict the recognition accuracy. Aiming at these series of problems, we introduce the partial least squares (PLS) and cluster analysis (CA) into Elman neural network algorithm, by the PLS for dimension reduction which can eliminate the correlative and repetitive factors of the features. Using CA eliminates the correlative and repetitive factors of the sample. If some subclass becomes small sample, with high-dimensional feature and fewer numbers, PLS shows a unique advantage. Each subclass is regarded as one training sample to train the different precise neural network models. Then simulation samples are discriminated and classified into different subclasses, using the corresponding neural network to recognize it. An optimized Elman neural network classification algorithm based on PLS and CA (PLS-CA-Elman algorithm) is established. The new algorithm aims at improving the operating efficiency and recognition accuracy. By the case analysis, the new algorithm has unique superiority, worthy of further promotion. PMID:25165470
NASA Technical Reports Server (NTRS)
Thakoor, Anil
1990-01-01
Viewgraphs on electronic neural networks for space station are presented. Topics covered include: electronic neural networks; electronic implementations; VLSI/thin film hybrid hardware for neurocomputing; computations with analog parallel processing; features of neuroprocessors; applications of neuroprocessors; neural network hardware for terrain trafficability determination; a dedicated processor for path planning; neural network system interface; neural network for robotic control; error backpropagation algorithm for learning; resource allocation matrix; global optimization neuroprocessor; and electrically programmable read only thin-film synaptic array.
NASA Astrophysics Data System (ADS)
Cheng, Xinmin; Zhang, Xiaodan; Zhao, Li; Deng, Aideng; Bao, Yongqiang; Liu, Yong; Jiang, Yunliang
2014-04-01
When using acoustic emission to locate the friction fault source of rotating machinery, the effects of strong noise and waveform distortion make accurate locating difficult. Applying neural network for acoustic emission source location could be helpful. In the BP Wavelet Neural Network, BP is a local search algorithm, which falls into local minimum easily. The probability of successful search is low. We used Shuffled Frog Leaping Algorithm (SFLA) to optimize the parameters of the Wavelet Neural Network, and the optimized Wavelet Neural Network to locate the source. After having performed the experiments of friction acoustic emission's source location on the rotor friction test machine, the results show that the calculation of SFLA is simple and effective, and that locating is accurate with proper structure of the network and input parameters.
Farber, R.M.; Lapedes, A.S.; Rico-Martinez, R.; Kevrekidis, I.G.
1993-06-01
Time-delay mappings constructed using neural networks have proven successful performing nonlinear system identification; however, because of their discrete nature, their use in bifurcation analysis of continuous-tune systems is limited. This shortcoming can be avoided by embedding the neural networks in a training algorithm that mimics a numerical integrator. Both explicit and implicit integrators can be used. The former case is based on repeated evaluations of the network in a feedforward implementation; the latter relies on a recurrent network implementation. Here the algorithms and their implementation on parallel machines (SIMD and MIMD architectures) are discussed.
Farber, R.M.; Lapedes, A.S. ); Rico-Martinez, R.; Kevrekidis, I.G. . Dept. of Chemical Engineering)
1993-01-01
Time-delay mappings constructed using neural networks have proven successful performing nonlinear system identification; however, because of their discrete nature, their use in bifurcation analysis of continuous-tune systems is limited. This shortcoming can be avoided by embedding the neural networks in a training algorithm that mimics a numerical integrator. Both explicit and implicit integrators can be used. The former case is based on repeated evaluations of the network in a feedforward implementation; the latter relies on a recurrent network implementation. Here the algorithms and their implementation on parallel machines (SIMD and MIMD architectures) are discussed.
Computational-complexity reduction for neural network algorithms
Guez, A.; Kam, M. . Dept. of Electrical and Computer Engineering); Eilbert, J.L. )
1989-03-01
An important class of neural models is described as a set of coupled nonlinear differential equations with state variables corresponding to the axon hillock potential of neurons. Through a nonlinear transformation, these models can be converted to an equivalent system of differential equations whose state variables correspond to firing rates. The new firing rate formulation has certain computational advantages over the potential formulation of the model. The computational and storage burdens per cycle in simulations are reduced, and the resulting equations become quasi-linear in a large significant subset of the state space. Moreover, the dynamic range of the state space is bounded, alleviating the numerical stability problems in network simulation. These advantages are demonstrated through an example, using their model for the neural solution to the traveling salesman proposed by Hopfield and Tank.
NASA Technical Reports Server (NTRS)
Kobayashi, Takahisa; Simon, Donald L.
2002-01-01
As part of the NASA Aviation Safety Program, a unique model-based diagnostics method that employs neural networks and genetic algorithms for aircraft engine performance diagnostics has been developed and demonstrated at the NASA Glenn Research Center against a nonlinear gas turbine engine model. Neural networks are applied to estimate the internal health condition of the engine, and genetic algorithms are used for sensor fault detection, isolation, and quantification. This hybrid architecture combines the excellent nonlinear estimation capabilities of neural networks with the capability to rank the likelihood of various faults given a specific sensor suite signature. The method requires a significantly smaller data training set than a neural network approach alone does, and it performs the combined engine health monitoring objectives of performance diagnostics and sensor fault detection and isolation in the presence of nominal and degraded engine health conditions.
Xue, Y.; Liu, S.; Hu, Y.; Yang, J.; Chen, Q.
2007-01-01
To improve the accuracy in prediction, Genetic Algorithm based Adaptive Neural Network Ensemble (GA-ANNE) is presented. Intersections are allowed between different training sets based on the fuzzy clustering analysis, which ensures the diversity as well as the accuracy of individual Neural Networks (NNs). Moreover, to improve the accuracy of the adaptive weights of individual NNs, GA is used to optimize the cluster centers. Empirical results in predicting carbon flux of Duke Forest reveal that GA-ANNE can predict the carbon flux more accurately than Radial Basis Function Neural Network (RBFNN), Bagging NN ensemble, and ANNE. ?? 2007 IEEE.
Elements of an algorithm for optimizing a parameter-structural neural network
NASA Astrophysics Data System (ADS)
Mrówczyńska, Maria
2016-06-01
The field of processing information provided by measurement results is one of the most important components of geodetic technologies. The dynamic development of this field improves classic algorithms for numerical calculations in the aspect of analytical solutions that are difficult to achieve. Algorithms based on artificial intelligence in the form of artificial neural networks, including the topology of connections between neurons have become an important instrument connected to the problem of processing and modelling processes. This concept results from the integration of neural networks and parameter optimization methods and makes it possible to avoid the necessity to arbitrarily define the structure of a network. This kind of extension of the training process is exemplified by the algorithm called the Group Method of Data Handling (GMDH), which belongs to the class of evolutionary algorithms. The article presents a GMDH type network, used for modelling deformations of the geometrical axis of a steel chimney during its operation.
A Hybrid Neural Network-Genetic Algorithm Technique for Aircraft Engine Performance Diagnostics
NASA Technical Reports Server (NTRS)
Kobayashi, Takahisa; Simon, Donald L.
2001-01-01
In this paper, a model-based diagnostic method, which utilizes Neural Networks and Genetic Algorithms, is investigated. Neural networks are applied to estimate the engine internal health, and Genetic Algorithms are applied for sensor bias detection and estimation. This hybrid approach takes advantage of the nonlinear estimation capability provided by neural networks while improving the robustness to measurement uncertainty through the application of Genetic Algorithms. The hybrid diagnostic technique also has the ability to rank multiple potential solutions for a given set of anomalous sensor measurements in order to reduce false alarms and missed detections. The performance of the hybrid diagnostic technique is evaluated through some case studies derived from a turbofan engine simulation. The results show this approach is promising for reliable diagnostics of aircraft engines.
Neural network based algorithm for automatic identification of cough sounds.
Swarnkar, V; Abeyratne, U R; Amrulloh, Yusuf; Hukins, Craig; Triasih, Rina; Setyati, Amalia
2013-01-01
Cough is the most common symptom of the several respiratory diseases containing diagnostic information. It is the best suitable candidate to develop a simplified screening technique for the management of respiratory diseases in timely manner, both in developing and developed countries, particularly in remote areas where medical facilities are limited. However, major issue hindering the development is the non-availability of reliable technique to automatically identify cough events. Medical practitioners still rely on manual counting, which is laborious and time consuming. In this paper we propose a novel method, based on the neural network to automatically identify cough segments, discarding other sounds such a speech, ambient noise etc. We achieved the accuracy of 98% in classifying 13395 segments into two classes, 'cough' and 'other sounds', with the sensitivity of 93.44% and specificity of 94.52%. Our preliminary results indicate that method can develop into a real-time cough identification technique in continuous cough monitoring systems. PMID:24110049
NASA Technical Reports Server (NTRS)
Rajkumar, T.; Aragon, Cecilia; Bardina, Jorge; Britten, Roy
2002-01-01
A fast, reliable way of predicting aerodynamic coefficients is produced using a neural network optimized by a genetic algorithm. Basic aerodynamic coefficients (e.g. lift, drag, pitching moment) are modelled as functions of angle of attack and Mach number. The neural network is first trained on a relatively rich set of data from wind tunnel tests of numerical simulations to learn an overall model. Most of the aerodynamic parameters can be well-fitted using polynomial functions. A new set of data, which can be relatively sparse, is then supplied to the network to produce a new model consistent with the previous model and the new data. Because the new model interpolates realistically between the sparse test data points, it is suitable for use in piloted simulations. The genetic algorithm is used to choose a neural network architecture to give best results, avoiding over-and under-fitting of the test data.
Zhang, Mei; Hu, Yueming; Wang, Tao; Zhu, Jinhui
2009-12-01
This paper addresses the predicting problem of peritoneal fluid absorption rate(PFAR). An innovative predicting model was developed, which employed the improved genetic algorithm embedded in neural network for predicting the important PFAR index in the peritoneal dialysis treatment process of renal failure. The significance of PFAR and the complexity of dialysis process were analyzed. The improved genetic algorithm was used for defining the initial weight and bias of neural network, and then the neural network was used for finding out the optimal predicting model of PFAR. This method utilizes the global search capability of genetic algorithm and the local search advantage of neural network completely. For the purpose of showing the validity of the model, the improved optimal predicting model is compared with the standard hybrid method of genetic algorithm and neural network. The simulation results show that the predicting accuracy of the improved optimal neural network is greatly improved and the learning process needs less time. PMID:20095466
Volume learning algorithm artificial neural networks for 3D QSAR studies.
Tetko, I V; Kovalishyn, V V; Livingstone, D J
2001-07-19
The current study introduces a new method, the volume learning algorithm (VLA), for the investigation of three-dimensional quantitative structure-activity relationships (QSAR) of chemical compounds. This method incorporates the advantages of comparative molecular field analysis (CoMFA) and artificial neural network approaches. VLA is a combination of supervised and unsupervised neural networks applied to solve the same problem. The supervised algorithm is a feed-forward neural network trained with a back-propagation algorithm while the unsupervised network is a self-organizing map of Kohonen. The use of both of these algorithms makes it possible to cluster the input CoMFA field variables and to use only a small number of the most relevant parameters to correlate spatial properties of the molecules with their activity. The statistical coefficients calculated by the proposed algorithm for cannabimimetic aminoalkyl indoles were comparable to, or improved, in comparison to the original study using the partial least squares algorithm. The results of the algorithm can be visualized and easily interpreted. Thus, VLA is a new convenient tool for three-dimensional QSAR studies. PMID:11448223
Combining neural network and genetic algorithm for prediction of lung sounds.
Güler, Inan; Polat, Hüseyin; Ergün, Uçman
2005-06-01
Recognition of lung sounds is an important goal in pulmonary medicine. In this work, we present a study for neural networks-genetic algorithm approach intended to aid in lung sound classification. Lung sound was captured from the chest wall of The subjects with different pulmonary diseases and also from the healthy subjects. Sound intervals with duration of 15-20 s were sampled from subjects. From each interval, full breath cycles were selected. Of each selected breath cycle, a 256-point Fourier Power Spectrum Density (PSD) was calculated. Total of 129 data values calculated by the spectral analysis are selected by genetic algorithm and applied to neural network. Multilayer perceptron (MLP) neural network employing backpropagation training algorithm was used to predict the presence or absence of adventitious sounds (wheeze and crackle). We used genetic algorithms to search for optimal structure and training parameters of neural network for a better predicting of lung sounds. This application resulted in designing of optimum network structure and, hence reducing the processing load and time. PMID:16050077
Genetic algorithm-based neural fuzzy decision tree for mixed scheduling in ATM networks.
Lin, Chin-Teng; Chung, I-Fang; Pu, Her-Chang; Lee', Tsern-Huei; Chang, Jyh-Yeong
2002-01-01
Future broadband integrated services networks based on asynchronous transfer mode (ATM) technology are expected to support multiple types of multimedia information with diverse statistical characteristics and quality of service (QoS) requirements. To meet these requirements, efficient scheduling methods are important for traffic control in ATM networks. Among general scheduling schemes, the rate monotonic algorithm is simple enough to be used in high-speed networks, but does not attain the high system utilization of the deadline driven algorithm. However, the deadline driven scheme is computationally complex and hard to implement in hardware. The mixed scheduling algorithm is a combination of the rate monotonic algorithm and the deadline driven algorithm; thus it can provide most of the benefits of these two algorithms. In this paper, we use the mixed scheduling algorithm to achieve high system utilization under the hardware constraint. Because there is no analytic method for schedulability testing of mixed scheduling, we propose a genetic algorithm-based neural fuzzy decision tree (GANFDT) to realize it in a real-time environment. The GANFDT combines a GA and a neural fuzzy network into a binary classification tree. This approach also exploits the power of the classification tree. Simulation results show that the GANFDT provides an efficient way of carrying out mixed scheduling in ATM networks. PMID:18244889
Predicting recurrent aphthous ulceration using genetic algorithms-optimized neural networks
Dar-Odeh, Najla S; Alsmadi, Othman M; Bakri, Faris; Abu-Hammour, Zaer; Shehabi, Asem A; Al-Omiri, Mahmoud K; Abu-Hammad, Shatha M K; Al-Mashni, Hamzeh; Saeed, Mohammad B; Muqbil, Wael; Abu-Hammad, Osama A
2010-01-01
Objective To construct and optimize a neural network that is capable of predicting the occurrence of recurrent aphthous ulceration (RAU) based on a set of appropriate input data. Participants and methods Artificial neural networks (ANN) software employing genetic algorithms to optimize the architecture neural networks was used. Input and output data of 86 participants (predisposing factors and status of the participants with regards to recurrent aphthous ulceration) were used to construct and train the neural networks. The optimized neural networks were then tested using untrained data of a further 10 participants. Results The optimized neural network, which produced the most accurate predictions for the presence or absence of recurrent aphthous ulceration was found to employ: gender, hematological (with or without ferritin) and mycological data of the participants, frequency of tooth brushing, and consumption of vegetables and fruits. Conclusions Factors appearing to be related to recurrent aphthous ulceration and appropriate for use as input data to construct ANNs that predict recurrent aphthous ulceration were found to include the following: gender, hemoglobin, serum vitamin B12, serum ferritin, red cell folate, salivary candidal colony count, frequency of tooth brushing, and the number of fruits or vegetables consumed daily. PMID:21918622
A model selection algorithm for a posteriori probability estimation with neural networks.
Arribas, Juan Ignacio; Cid-Sueiro, Jesús
2005-07-01
This paper proposes a novel algorithm to jointly determine the structure and the parameters of a posteriori probability model based on neural networks (NNs). It makes use of well-known ideas of pruning, splitting, and merging neural components and takes advantage of the probabilistic interpretation of these components. The algorithm, so called a posteriori probability model selection (PPMS), is applied to an NN architecture called the generalized softmax perceptron (GSP) whose outputs can be understood as probabilities although results shown can be extended to more general network architectures. Learning rules are derived from the application of the expectation-maximization algorithm to the GSP-PPMS structure. Simulation results show the advantages of the proposed algorithm with respect to other schemes. PMID:16121722
An Efficient Algorithm for Maximum Clique Problem Using Improved Hopfield Neural Network
NASA Astrophysics Data System (ADS)
Wang, Rong Long; Tang, Zheng; Cao, Qi Ping
The maximum clique problem is a classic graph optimization problem that is NP-hard even to approximate. For this and related reasons, it is a problem of considerable interest in theoretical computer science. The maximum clique also has several real-world applications. In this paper, an efficient algorithm for the maximum clique problem using improved Hopfield neural network is presented. In this algorithm, the internal dynamics of the Hopfield neural network is modified to efficiently increase exchange of information between neurons and permit temporary increases in the energy function in order to avoid local minima. The proposed algorithm is tested on two types of random graphs and DIMACS benchmark graphs. The simulation results show that the proposed algorithm is better than previous works for solving the maximum clique problem in terms of the computation time and the solution quality.
A generalized LSTM-like training algorithm for second-order recurrent neural networks
Monner, Derek; Reggia, James A.
2011-01-01
The Long Short Term Memory (LSTM) is a second-order recurrent neural network architecture that excels at storing sequential short-term memories and retrieving them many time-steps later. LSTM’s original training algorithm provides the important properties of spatial and temporal locality, which are missing from other training approaches, at the cost of limiting it’s applicability to a small set of network architectures. Here we introduce the Generalized Long Short-Term Memory (LSTM-g) training algorithm, which provides LSTM-like locality while being applicable without modification to a much wider range of second-order network architectures. With LSTM-g, all units have an identical set of operating instructions for both activation and learning, subject only to the configuration of their local environment in the network; this is in contrast to the original LSTM training algorithm, where each type of unit has its own activation and training instructions. When applied to LSTM architectures with peephole connections, LSTM-g takes advantage of an additional source of back-propagated error which can enable better performance than the original algorithm. Enabled by the broad architectural applicability of LSTM-g, we demonstrate that training recurrent networks engineered for specific tasks can produce better results than single-layer networks. We conclude that LSTM-g has the potential to both improve the performance and broaden the applicability of spatially and temporally local gradient-based training algorithms for recurrent neural networks. PMID:21803542
Orozco-Monteagudo, Maykel; Taboada-Crispi, Alberto; Gutierrez-Hernandez, Liliana
2008-11-06
This paper deals with the controversial topic of the selection of the parameters of a genetic algorithm, in this case hierarchical, used for training of multilayer perceptron neural networks for the binary classification. The parameters to select are the crossover and mutation probabilities of the control and parametric genes and the permanency percent. The results can be considered as a guide for using this kind of algorithm.
NASA Technical Reports Server (NTRS)
Rajkumar, T.; Bardina, Jorge; Clancy, Daniel (Technical Monitor)
2002-01-01
Wind tunnels use scale models to characterize aerodynamic coefficients, Wind tunnel testing can be slow and costly due to high personnel overhead and intensive power utilization. Although manual curve fitting can be done, it is highly efficient to use a neural network to define the complex relationship between variables. Numerical simulation of complex vehicles on the wide range of conditions required for flight simulation requires static and dynamic data. Static data at low Mach numbers and angles of attack may be obtained with simpler Euler codes. Static data of stalled vehicles where zones of flow separation are usually present at higher angles of attack require Navier-Stokes simulations which are costly due to the large processing time required to attain convergence. Preliminary dynamic data may be obtained with simpler methods based on correlations and vortex methods; however, accurate prediction of the dynamic coefficients requires complex and costly numerical simulations. A reliable and fast method of predicting complex aerodynamic coefficients for flight simulation I'S presented using a neural network. The training data for the neural network are derived from numerical simulations and wind-tunnel experiments. The aerodynamic coefficients are modeled as functions of the flow characteristics and the control surfaces of the vehicle. The basic coefficients of lift, drag and pitching moment are expressed as functions of angles of attack and Mach number. The modeled and training aerodynamic coefficients show good agreement. This method shows excellent potential for rapid development of aerodynamic models for flight simulation. Genetic Algorithms (GA) are used to optimize a previously built Artificial Neural Network (ANN) that reliably predicts aerodynamic coefficients. Results indicate that the GA provided an efficient method of optimizing the ANN model to predict aerodynamic coefficients. The reliability of the ANN using the GA includes prediction of aerodynamic
Optimization of cocoa butter analog synthesis variables using neural networks and genetic algorithm.
Shekarchizadeh, Hajar; Tikani, Reza; Kadivar, Mahdi
2014-09-01
Cocoa butter analog was prepared from camel hump fat and tristearin by enzymatic interesterification in supercritical carbon dioxide (SC-CO2) using immobilized Thermomyces lanuginosus lipase (Lipozyme TL IM) as a biocatalyst. Optimal process conditions were determined using neural networks and genetic algorithm optimization. Response surfaces methodology was used to design the experiments to collect data for the neural network modelling. A general regression neural network model was developed to predict the response of triacylglycerol (TAG) distribution of cocoa butter analog from the process pressure, temperature, tristearin/camel hump fat ratio, water content, and incubation time. A genetic algorithm was used to search for a combination of the process variables for production of most similar cocoa butter analog to the corresponding cocoa butter. The combinations of the process variables during genetic algorithm optimization were evaluated using the neural network model. The pressure of 10 MPa; temperature of 40 °C; SSS/CHF ratio of 0.6:1; water content of 13 % (w/w); and incubation time of 4.5 h were found to be the optimum conditions to achieve the most similar cocoa butter analog to the corresponding cocoa butter. PMID:25190869
Cao, Jianfang; Cui, Hongyan; Shi, Hao; Jiao, Lijuan
2016-01-01
A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network's initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data. PMID:27304987
Two neural network algorithms for designing optimal terminal controllers with open final time
NASA Technical Reports Server (NTRS)
Plumer, Edward S.
1992-01-01
Multilayer neural networks, trained by the backpropagation through time algorithm (BPTT), have been used successfully as state-feedback controllers for nonlinear terminal control problems. Current BPTT techniques, however, are not able to deal systematically with open final-time situations such as minimum-time problems. Two approaches which extend BPTT to open final-time problems are presented. In the first, a neural network learns a mapping from initial-state to time-to-go. In the second, the optimal number of steps for each trial run is found using a line-search. Both methods are derived using Lagrange multiplier techniques. This theoretical framework is used to demonstrate that the derived algorithms are direct extensions of forward/backward sweep methods used in N-stage optimal control. The two algorithms are tested on a Zermelo problem and the resulting trajectories compare favorably to optimal control results.
The backpropagation algorithm in J, a fast prototyping tool for researching neural networks.
Brouwer, R K
1999-08-01
This paper illustrates the use of a powerful language, called J, that is ideal for simulating neural networks. The use of J is demonstrated by its application to a gradient descent method for training a multilayer perceptron. It is also shown how the back-propagation algorithm can be easily generalized to multilayer networks without any increase in complexity and that the algorithm can be completely expressed in an array notation which is directly executable through J. J is a general purpose language, which means that its user is given a flexibility not available in neural network simulators or in software packages such as MATLAB. Yet, because of its numerous operators, J allows a very succinct code to be used, leading to a tremendous decrease in development time. PMID:10586987
Cao, Jianfang; Cui, Hongyan; Shi, Hao; Jiao, Lijuan
2016-01-01
A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network’s initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data. PMID:27304987
On the use of harmony search algorithm in the training of wavelet neural networks
NASA Astrophysics Data System (ADS)
Lai, Kee Huong; Zainuddin, Zarita; Ong, Pauline
2015-10-01
Wavelet neural networks (WNNs) are a class of feedforward neural networks that have been used in a wide range of industrial and engineering applications to model the complex relationships between the given inputs and outputs. The training of WNNs involves the configuration of the weight values between neurons. The backpropagation training algorithm, which is a gradient-descent method, can be used for this training purpose. Nonetheless, the solutions found by this algorithm often get trapped at local minima. In this paper, a harmony search-based algorithm is proposed for the training of WNNs. The training of WNNs, thus can be formulated as a continuous optimization problem, where the objective is to maximize the overall classification accuracy. Each candidate solution proposed by the harmony search algorithm represents a specific WNN architecture. In order to speed up the training process, the solution space is divided into disjoint partitions during the random initialization step of harmony search algorithm. The proposed training algorithm is tested onthree benchmark problems from the UCI machine learning repository, as well as one real life application, namely, the classification of electroencephalography signals in the task of epileptic seizure detection. The results obtained show that the proposed algorithm outperforms the traditional harmony search algorithm in terms of overall classification accuracy.
Negri, Lucas; Nied, Ademir; Kalinowski, Hypolito; Paterno, Aleksander
2011-01-01
This paper presents a benchmark for peak detection algorithms employed in fiber Bragg grating spectrometric interrogation systems. The accuracy, precision, and computational performance of currently used algorithms and those of a new proposed artificial neural network algorithm are compared. Centroid and gaussian fitting algorithms are shown to have the highest precision but produce systematic errors that depend on the FBG refractive index modulation profile. The proposed neural network displays relatively good precision with reduced systematic errors and improved computational performance when compared to other networks. Additionally, suitable algorithms may be chosen with the general guidelines presented. PMID:22163806
Lu, Y; Sundararajan, N; Saratchandran, P
1998-01-01
This paper presents a detailed performance analysis of the minimal resource allocation network (M-RAN) learning algorithm, M-RAN is a sequential learning radial basis function neural network which combines the growth criterion of the resource allocating network (RAN) of Platt (1991) with a pruning strategy based on the relative contribution of each hidden unit to the overall network output. The resulting network leads toward a minimal topology for the RAN. The performance of this algorithm is compared with the multilayer feedforward networks (MFNs) trained with 1) a variant of the standard backpropagation algorithm, known as RPROP and 2) the dependence identification (DI) algorithm of Moody and Antsaklis on several benchmark problems in the function approximation and pattern classification areas. For all these problems, the M-RAN algorithm is shown to realize networks with far fewer hidden neurons with better or same approximation/classification accuracy. Further, the time taken for learning (training) is also considerably shorter as M-RAN does not require repeated presentation of the training data. PMID:18252454
NASA Astrophysics Data System (ADS)
Zainuddin, Zarita; Lai, Kee Huong; Ong, Pauline
2013-04-01
Artificial neural networks (ANNs) are powerful mathematical models that are used to solve complex real world problems. Wavelet neural networks (WNNs), which were developed based on the wavelet theory, are a variant of ANNs. During the training phase of WNNs, several parameters need to be initialized; including the type of wavelet activation functions, translation vectors, and dilation parameter. The conventional k-means and fuzzy c-means clustering algorithms have been used to select the translation vectors. However, the solution vectors might get trapped at local minima. In this regard, the evolutionary harmony search algorithm, which is capable of searching for near-optimum solution vectors, both locally and globally, is introduced to circumvent this problem. In this paper, the conventional k-means and fuzzy c-means clustering algorithms were hybridized with the metaheuristic harmony search algorithm. In addition to obtaining the estimation of the global minima accurately, these hybridized algorithms also offer more than one solution to a particular problem, since many possible solution vectors can be generated and stored in the harmony memory. To validate the robustness of the proposed WNNs, the real world problem of epileptic seizure detection was presented. The overall classification accuracy from the simulation showed that the hybridized metaheuristic algorithms outperformed the standard k-means and fuzzy c-means clustering algorithms.
NASA Astrophysics Data System (ADS)
Huan, Yanfu; Feng, Guodong; Wang, Bin; Ren, Yulin; Fei, Qiang
2013-05-01
In this paper, a novel chemometric method was developed for rapid, accurate, and quantitative analysis of cefalexin in samples. The experiments were carried out by using the short near-infrared spectroscopy coupled with artificial neural networks. In order to enhancing the predictive ability of artificial neural networks model, a modified genetic algorithm was used to select fixed number of wavelength.
Mandal, Sudip; Khan, Abhinandan; Saha, Goutam; Pal, Rajat K.
2016-01-01
The accurate prediction of genetic networks using computational tools is one of the greatest challenges in the postgenomic era. Recurrent Neural Network is one of the most popular but simple approaches to model the network dynamics from time-series microarray data. To date, it has been successfully applied to computationally derive small-scale artificial and real-world genetic networks with high accuracy. However, they underperformed for large-scale genetic networks. Here, a new methodology has been proposed where a hybrid Cuckoo Search-Flower Pollination Algorithm has been implemented with Recurrent Neural Network. Cuckoo Search is used to search the best combination of regulators. Moreover, Flower Pollination Algorithm is applied to optimize the model parameters of the Recurrent Neural Network formalism. Initially, the proposed method is tested on a benchmark large-scale artificial network for both noiseless and noisy data. The results obtained show that the proposed methodology is capable of increasing the inference of correct regulations and decreasing false regulations to a high degree. Secondly, the proposed methodology has been validated against the real-world dataset of the DNA SOS repair network of Escherichia coli. However, the proposed method sacrifices computational time complexity in both cases due to the hybrid optimization process. PMID:26989410
Mandal, Sudip; Khan, Abhinandan; Saha, Goutam; Pal, Rajat K
2016-01-01
The accurate prediction of genetic networks using computational tools is one of the greatest challenges in the postgenomic era. Recurrent Neural Network is one of the most popular but simple approaches to model the network dynamics from time-series microarray data. To date, it has been successfully applied to computationally derive small-scale artificial and real-world genetic networks with high accuracy. However, they underperformed for large-scale genetic networks. Here, a new methodology has been proposed where a hybrid Cuckoo Search-Flower Pollination Algorithm has been implemented with Recurrent Neural Network. Cuckoo Search is used to search the best combination of regulators. Moreover, Flower Pollination Algorithm is applied to optimize the model parameters of the Recurrent Neural Network formalism. Initially, the proposed method is tested on a benchmark large-scale artificial network for both noiseless and noisy data. The results obtained show that the proposed methodology is capable of increasing the inference of correct regulations and decreasing false regulations to a high degree. Secondly, the proposed methodology has been validated against the real-world dataset of the DNA SOS repair network of Escherichia coli. However, the proposed method sacrifices computational time complexity in both cases due to the hybrid optimization process. PMID:26989410
Modeling discharge-sediment relationship using neural networks with artificial bee colony algorithm
NASA Astrophysics Data System (ADS)
Kisi, Ozgur; Ozkan, Coskun; Akay, Bahriye
2012-03-01
SummaryEstimation of suspended sediment concentration carried by a river is very important for many water resources projects. The accuracy of artificial neural networks (ANN) with artificial bee colony (ABC) algorithm is investigated in this paper for modeling discharge-suspended sediment relationship. The ANN-ABC was compared with those of the neural differential evolution, adaptive neuro-fuzzy, neural networks and rating curve models. The daily stream flow and suspended sediment concentration data from two stations, Rio Valenciano Station and Quebrada Blanca Station, were used as case studies. For evaluating the ability of the models, mean square error and determination coefficient criteria were used. Comparison results showed that the ANN-ABC was able to produce better results than the neural differential evolution, neuro-fuzzy, neural networks and rating curve models. The logarithm transformed data were also used as input to the proposed ANN-ABC models. It was found that the logarithm transform significantly increased accuracy of the models in suspended sediment estimation.
A new backpropagation learning algorithm for layered neural networks with nondifferentiable units.
Oohori, Takahumi; Naganuma, Hidenori; Watanabe, Kazuhisa
2007-05-01
We propose a digital version of the backpropagation algorithm (DBP) for three-layered neural networks with nondifferentiable binary units. This approach feeds teacher signals to both the middle and output layers, whereas with a simple perceptron, they are given only to the output layer. The additional teacher signals enable the DBP to update the coupling weights not only between the middle and output layers but also between the input and middle layers. A neural network based on DBP learning is fast and easy to implement in hardware. Simulation results for several linearly nonseparable problems such as XOR demonstrate that the DBP performs favorably when compared to the conventional approaches. Furthermore, in large-scale networks, simulation results indicate that the DBP provides high performance. PMID:17381272
Efficient training algorithms for a class of shunting inhibitory convolutional neural networks.
Tivive, Fok Hing Chi; Bouzerdoum, Abdesselam
2005-05-01
This article presents some efficient training algorithms, based on first-order, second-order, and conjugate gradient optimization methods, for a class of convolutional neural networks (CoNNs), known as shunting inhibitory convolution neural networks. Furthermore, a new hybrid method is proposed, which is derived from the principles of Quickprop, Rprop, SuperSAB, and least squares (LS). Experimental results show that the new hybrid method can perform as well as the Levenberg-Marquardt (LM) algorithm, but at a much lower computational cost and less memory storage. For comparison sake, the visual pattern recognition task of face/nonface discrimination is chosen as a classification problem to evaluate the performance of the training algorithms. Sixteen training algorithms are implemented for the three different variants of the proposed CoNN architecture: binary-, Toeplitz- and fully connected architectures. All implemented algorithms can train the three network architectures successfully, but their convergence speed vary markedly. In particular, the combination of LS with the new hybrid method and LS with the LM method achieve the best convergence rates in terms of number of training epochs. In addition, the classification accuracies of all three architectures are assessed using ten-fold cross validation. The results show that the binary- and Toeplitz-connected architectures outperform slightly the fully connected architecture: the lowest error rates across all training algorithms are 1.95% for Toeplitz-connected, 2.10% for the binary-connected, and 2.20% for the fully connected network. In general, the modified Broyden-Fletcher-Goldfarb-Shanno (BFGS) methods, the three variants of LM algorithm, and the new hybrid/LS method perform consistently well, achieving error rates of less than 3% averaged across all three architectures. PMID:15940985
Neural network and genetic algorithm technology in data mining of manufacturing quality information
NASA Astrophysics Data System (ADS)
Song, Limei; Qu, Xing-Hua; Ye, Shenghua
2002-03-01
Data Mining of Manufacturing Quality Information (MQI) is the key technology in Quality Lead Control. Of all the data mining methods, Neural Network and Genetic Algorithm is widely used for their strong advantages, such as non-linear, collateral, veracity etc. But if you singly use them, there will be some limitations preventing your research, such as convergence slowly, searching blindness etc. This paper combines their merits and use Genetic BP Algorithm in Data Mining of MQI. It has been successfully used in the key project of Natural Science Foundation of China (NSFC) - Quality Control and Zero-defect Engineering (Project No. 59735120).
Modeling of CMM dynamic error based on optimization of neural network using genetic algorithm
NASA Astrophysics Data System (ADS)
Ying, Qu; Zai, Luo; Yi, Lu
2010-08-01
By analyzing the dynamic error of CMM, a model is established using BP neural network for CMM .The most important 5 input parameters which affect the dynamic error of CMM are approximate rate, length of rod, diameter of probe, coordinate values of X and coordinate values of Y. But the training of BP neural network can be easily trapped in local minimums and its training speed is slow. In order to overcome these disadvantages, genetic algorithm (GA) is introduced for optimization. So the model of GA-BP network is built up. In order to verify the model, experiments are done on the CMM of type 9158. Experimental results indicate that the entire optimizing capability of genetic algorithm is perfect. Compared with traditional BP network, the GA-BP network has better accuracy and adaptability and the training time is halved using GA-BP network. The average dynamic error can be reduced from 3.5μm to 0.7μm. So the precision is improved by 76%.
Chiang, Kai-Wei; Chang, Hsiu-Wen
2010-01-01
Mobile mapping systems have been widely applied for acquiring spatial information in applications such as spatial information systems and 3D city models. Nowadays the most common technologies used for positioning and orientation of a mobile mapping system include a Global Positioning System (GPS) as the major positioning sensor and an Inertial Navigation System (INS) as the major orientation sensor. In the classical approach, the limitations of the Kalman Filter (KF) method and the overall price of multi-sensor systems have limited the popularization of most land-based mobile mapping applications. Although intelligent sensor positioning and orientation schemes consisting of Multi-layer Feed-forward Neural Networks (MFNNs), one of the most famous Artificial Neural Networks (ANNs), and KF/smoothers, have been proposed in order to enhance the performance of low cost Micro Electro Mechanical System (MEMS) INS/GPS integrated systems, the automation of the MFNN applied has not proven as easy as initially expected. Therefore, this study not only addresses the problems of insufficient automation in the conventional methodology that has been applied in MFNN-KF/smoother algorithms for INS/GPS integrated systems proposed in previous studies, but also exploits and analyzes the idea of developing alternative intelligent sensor positioning and orientation schemes that integrate various sensors in more automatic ways. The proposed schemes are implemented using one of the most famous constructive neural networks--the Cascade Correlation Neural Network (CCNNs)--to overcome the limitations of conventional techniques based on KF/smoother algorithms as well as previously developed MFNN-smoother schemes. The CCNNs applied also have the advantage of a more flexible topology compared to MFNNs. Based on the experimental data utilized the preliminary results presented in this article illustrate the effectiveness of the proposed schemes compared to smoother algorithms as well as the MFNN
NASA Astrophysics Data System (ADS)
Wang, H. B.; Li, J. W.; Zhou, B.; Yuan, Z. Q.; Chen, Y. P.
2013-03-01
In the last few decades, the development of Geographical Information Systems (GIS) technology has provided a method for the evaluation of landslide susceptibility and hazard. Slope units were found to be appropriate for the fundamental morphological elements in landslide susceptibility evaluation. Following the DEM construction in a loess area susceptible to landslides, the direct-reverse DEM technology was employed to generate 216 slope units in the studied area. After a detailed investigation, the landslide inventory was mapped in which 39 landslides, including paleo-landslides, old landslides and recent landslides, were present. Of the 216 slope units, 123 involved landslides. To analyze the mechanism of these landslides, six environmental factors were selected to evaluate landslide occurrence: slope angle, aspect, the height and shape of the slope, distance to river and human activities. These factors were extracted in terms of the slope unit within the ArcGIS software. The spatial analysis demonstrates that most of the landslides are located on convex slopes at an elevation of 100-150 m with slope angles from 135°-225° and 40°-60°. Landslide occurrence was then checked according to these environmental factors using an artificial neural network with back propagation, optimized by genetic algorithms. A dataset of 120 slope units was chosen for training the neural network model, i.e., 80 units with landslide presence and 40 units without landslide presence. The parameters of genetic algorithms and neural networks were then set: population size of 100, crossover probability of 0.65, mutation probability of 0.01, momentum factor of 0.60, learning rate of 0.7, max learning number of 10 000, and target error of 0.000001. After training on the datasets, the susceptibility of landslides was mapped for the land-use plan and hazard mitigation. Comparing the susceptibility map with landslide inventory, it was noted that the prediction accuracy of landslide occurrence
Comparison of neuron selection algorithms of wavelet-based neural network
NASA Astrophysics Data System (ADS)
Mei, Xiaodan; Sun, Sheng-He
2001-09-01
Wavelet networks have increasingly received considerable attention in various fields such as signal processing, pattern recognition, robotics and automatic control. Recently people are interested in employing wavelet functions as activation functions and have obtained some satisfying results in approximating and localizing signals. However, the function estimation will become more and more complex with the growth of the input dimension. The hidden neurons contribute to minimize the approximation error, so it is important to study suitable algorithms for neuron selection. It is obvious that exhaustive search procedure is not satisfying when the number of neurons is large. The study in this paper focus on what type of selection algorithm has faster convergence speed and less error for signal approximation. Therefore, the Genetic algorithm and the Tabu Search algorithm are studied and compared by some experiments. This paper first presents the structure of the wavelet-based neural network, then introduces these two selection algorithms and discusses their properties and learning processes, and analyzes the experiments and results. We used two wavelet functions to test these two algorithms. The experiments show that the Tabu Search selection algorithm's performance is better than the Genetic selection algorithm, TSA has faster convergence rate than GA under the same stopping criterion.
Ahmed, Afaz Uddin; Islam, Mohammad Tariqul; Ismail, Mahamod; Kibria, Salehin; Arshad, Haslina
2014-01-01
An artificial neural network (ANN) and affinity propagation (AP) algorithm based user categorization technique is presented. The proposed algorithm is designed for closed access femtocell network. ANN is used for user classification process and AP algorithm is used to optimize the ANN training process. AP selects the best possible training samples for faster ANN training cycle. The users are distinguished by using the difference of received signal strength in a multielement femtocell device. A previously developed directive microstrip antenna is used to configure the femtocell device. Simulation results show that, for a particular house pattern, the categorization technique without AP algorithm takes 5 indoor users and 10 outdoor users to attain an error-free operation. While integrating AP algorithm with ANN, the system takes 60% less training samples reducing the training time up to 50%. This procedure makes the femtocell more effective for closed access operation. PMID:25133214
Study on recognition algorithm for paper currency numbers based on neural network
NASA Astrophysics Data System (ADS)
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.
Evolving spiking neural networks: a novel growth algorithm exhibits unintelligent design
NASA Astrophysics Data System (ADS)
Schaffer, J. David
2015-06-01
Spiking neural networks (SNNs) have drawn considerable excitement because of their computational properties, believed to be superior to conventional von Neumann machines, and sharing properties with living brains. Yet progress building these systems has been limited because we lack a design methodology. We present a gene-driven network growth algorithm that enables a genetic algorithm (evolutionary computation) to generate and test SNNs. The genome for this algorithm grows O(n) where n is the number of neurons; n is also evolved. The genome not only specifies the network topology, but all its parameters as well. Experiments show the algorithm producing SNNs that effectively produce a robust spike bursting behavior given tonic inputs, an application suitable for central pattern generators. Even though evolution did not include perturbations of the input spike trains, the evolved networks showed remarkable robustness to such perturbations. In addition, the output spike patterns retain evidence of the specific perturbation of the inputs, a feature that could be exploited by network additions that could use this information for refined decision making if required. On a second task, a sequence detector, a discriminating design was found that might be considered an example of "unintelligent design"; extra non-functional neurons were included that, while inefficient, did not hamper its proper functioning.
Single-Iteration Learning Algorithm for Feed-Forward Neural Networks
Barhen, J.; Cogswell, R.; Protopopescu, V.
1999-07-31
A new methodology for neural learning is presented, whereby only a single iteration is required to train a feed-forward network with near-optimal results. To this aim, a virtual input layer is added to the multi-layer architecture. The virtual input layer is connected to the nominal input layer by a specird nonlinear transfer function, and to the fwst hidden layer by regular (linear) synapses. A sequence of alternating direction singular vrdue decompositions is then used to determine precisely the inter-layer synaptic weights. This algorithm exploits the known separability of the linear (inter-layer propagation) and nonlinear (neuron activation) aspects of information &ansfer within a neural network.
Hybrid neural network and statistical classification algorithms in computer-assisted diagnosis
NASA Astrophysics Data System (ADS)
Stotzka, Rainer
2000-06-01
The development of computer assisted diagnosis systems for image-patterns is still in the early stages compared to the powerful image and object recognition capabilities of the human eye and visual cortex. Rules have to be defined and features have to be found manually in digital images to come to an automatic classification. The extraction of discriminating features is especially in medical applications a very time consuming process. The quality of the defined features influences directly the classification success. Artificial neural networks are in principle able to solve complex recognition and classification tasks, but their computational expenses restrict their use to small images. A new improved image object classification scheme consists of neural networks as feature extractors and common statistical discrimination algorithms. Applied to the recognition of different types of tumor nuclei images this system is able to find differences which are barely discernible by human eyes.
Wang, Jie-sheng; Li, Shu-xia; Gao, Jie
2014-01-01
For meeting the real-time fault diagnosis and the optimization monitoring requirements of the polymerization kettle in the polyvinyl chloride resin (PVC) production process, a fault diagnosis strategy based on the self-organizing map (SOM) neural network is proposed. Firstly, a mapping between the polymerization process data and the fault pattern is established by analyzing the production technology of polymerization kettle equipment. The particle swarm optimization (PSO) algorithm with a new dynamical adjustment method of inertial weights is adopted to optimize the structural parameters of SOM neural network. The fault pattern classification of the polymerization kettle equipment is to realize the nonlinear mapping from symptom set to fault set according to the given symptom set. Finally, the simulation experiments of fault diagnosis are conducted by combining with the industrial on-site historical data of the polymerization kettle and the simulation results show that the proposed PSO-SOM fault diagnosis strategy is effective. PMID:25152929
Wang, Jie-sheng; Li, Shu-xia; Gao, Jie
2014-01-01
For meeting the real-time fault diagnosis and the optimization monitoring requirements of the polymerization kettle in the polyvinyl chloride resin (PVC) production process, a fault diagnosis strategy based on the self-organizing map (SOM) neural network is proposed. Firstly, a mapping between the polymerization process data and the fault pattern is established by analyzing the production technology of polymerization kettle equipment. The particle swarm optimization (PSO) algorithm with a new dynamical adjustment method of inertial weights is adopted to optimize the structural parameters of SOM neural network. The fault pattern classification of the polymerization kettle equipment is to realize the nonlinear mapping from symptom set to fault set according to the given symptom set. Finally, the simulation experiments of fault diagnosis are conducted by combining with the industrial on-site historical data of the polymerization kettle and the simulation results show that the proposed PSO-SOM fault diagnosis strategy is effective. PMID:25152929
Smith, Patrick I.
2003-09-23
Physicists use large detectors to measure particles created in high-energy collisions at particle accelerators. These detectors typically produce signals indicating either where ionization occurs along the path of the particle, or where energy is deposited by the particle. The data produced by these signals is fed into pattern recognition programs to try to identify what particles were produced, and to measure the energy and direction of these particles. Ideally, there are many techniques used in this pattern recognition software. One technique, neural networks, is particularly suitable for identifying what type of particle caused by a set of energy deposits. Neural networks can derive meaning from complicated or imprecise data, extract patterns, and detect trends that are too complex to be noticed by either humans or other computer related processes. To assist in the advancement of this technology, Physicists use a tool kit to experiment with several neural network techniques. The goal of this research is interface a neural network tool kit into Java Analysis Studio (JAS3), an application that allows data to be analyzed from any experiment. As the final result, a physicist will have the ability to train, test, and implement a neural network with the desired output while using JAS3 to analyze the results or output. Before an implementation of a neural network can take place, a firm understanding of what a neural network is and how it works is beneficial. A neural network is an artificial representation of the human brain that tries to simulate the learning process [5]. It is also important to think of the word artificial in that definition as computer programs that use calculations during the learning process. In short, a neural network learns by representative examples. Perhaps the easiest way to describe the way neural networks learn is to explain how the human brain functions. The human brain contains billions of neural cells that are responsible for processing
Vyas, Bhargav Y; Das, Biswarup; Maheshwari, Rudra Prakash
2016-08-01
This paper presents the Chebyshev neural network (ChNN) as an improved artificial intelligence technique for power system protection studies and examines the performances of two ChNN learning algorithms for fault classification of series compensated transmission line. The training algorithms are least-square Levenberg-Marquardt (LSLM) and recursive least-square algorithm with forgetting factor (RLSFF). The performances of these algorithms are assessed based on their generalization capability in relating the fault current parameters with an event of fault in the transmission line. The proposed algorithm is fast in response as it utilizes postfault samples of three phase currents measured at the relaying end corresponding to half-cycle duration only. After being trained with only a small part of the generated fault data, the algorithms have been tested over a large number of fault cases with wide variation of system and fault parameters. Based on the studies carried out in this paper, it has been found that although the RLSFF algorithm is faster for training the ChNN in the fault classification application for series compensated transmission lines, the LSLM algorithm has the best accuracy in testing. The results prove that the proposed ChNN-based method is accurate, fast, easy to design, and immune to the level of compensations. Thus, it is suitable for digital relaying applications. PMID:25314714
A neural network-based optimization algorithm for the weapon-target assignment problem
Wacholder, E.
1989-02-01
A neural network-based algorithm was developed for the Weapon-Target Assignment Problem (WTAP) in Ballistic Missile Defense (BMD). An optimal assignment policy is one which allocates targets to weapon platforms such that the total expected leakage value of targets surviving the defense is minimized. This involves the minimization of a non-linear objective function subject to inequality constraints specifying the maximum number of interceptors available to each platform and the maximum number of interceptors allowed to be fired at each target as imposed by the Battle Management/Command Control and Communications (BM/C/sup 3/) system. The algorithm consists of solving a system of ODEs trajectories and variables. Simulations of the algorithm on PC and VAX computers were carried out using a simple numerical scheme. In all the battle instances tested, the algorithm has proven to be stable and to converge to solutions very close to global optima. The time to achieve convergence was consistently less than the time constant of the network's processing elements (neurons). This implies that fast solutions can be realized if the algorithm is implemented in hardware circuits. Three series of battle scenarios are analyzed and discussed in this report. Input data and results are presented in detail. The main advantage of this algorithm is that it can be adapted to either a special-purpose hardware circuit or a general-purpose concurrent machine to yield fast and accurate solutions to difficult decision problems. 40 refs., 8 figs., 8 tabs.
Prediction of road traffic death rate using neural networks optimised by genetic algorithm.
Jafari, Seyed Ali; Jahandideh, Sepideh; Jahandideh, Mina; Asadabadi, Ebrahim Barzegari
2015-01-01
Road traffic injuries (RTIs) are realised as a main cause of public health problems at global, regional and national levels. Therefore, prediction of road traffic death rate will be helpful in its management. Based on this fact, we used an artificial neural network model optimised through Genetic algorithm to predict mortality. In this study, a five-fold cross-validation procedure on a data set containing total of 178 countries was used to verify the performance of models. The best-fit model was selected according to the root mean square errors (RMSE). Genetic algorithm, as a powerful model which has not been introduced in prediction of mortality to this extent in previous studies, showed high performance. The lowest RMSE obtained was 0.0808. Such satisfactory results could be attributed to the use of Genetic algorithm as a powerful optimiser which selects the best input feature set to be fed into the neural networks. Seven factors have been known as the most effective factors on the road traffic mortality rate by high accuracy. The gained results displayed that our model is very promising and may play a useful role in developing a better method for assessing the influence of road traffic mortality risk factors. PMID:24304230
Anisotropic optical flow algorithm based on self-adaptive cellular neural network
NASA Astrophysics Data System (ADS)
Zhang, Congxuan; Chen, Zhen; Li, Ming; Sun, Kaiqiong
2013-01-01
An anisotropic optical flow estimation method based on self-adaptive cellular neural networks (CNN) is proposed. First, a novel optical flow energy function which contains a robust data term and an anisotropic smoothing term is projected. Next, the CNN model which has the self-adaptive feedback operator and threshold is presented according to the Euler-Lagrange partial differential equations of the proposed optical flow energy function. Finally, the elaborate evaluation experiments indicate the significant effects of the various proposed strategies for optical flow estimation, and the comparison results with the other methods show that the proposed algorithm has better performance in computing accuracy and efficiency.
Supervised feature ranking using a genetic algorithm optimized artificial neural network.
Lin, Thy-Hou; Chiu, Shih-Hau; Tsai, Keng-Chang
2006-01-01
A genetic algorithm optimized artificial neural network GNW has been designed to rank features for two diversified multivariate data sets. The dimensions of these data sets are 85x24 and 62x25 for 24 or 25 molecular descriptors being computed for 85 matrix metalloproteinase-1 inhibitors or 62 hepatitis C virus NS3 protease inhibitors, respectively. Each molecular descriptor computed is treated as a feature and input into an input layer node of the artificial neural network. To optimize the artificial neural network by the genetic algorithm, each interconnected weight between input and hidden or between hidden and output layer nodes is binary encoded as a 16 bits string in a chromosome, and the chromosome is evolved by crossover and mutation operations. Each input layer node and its associated weights of the trained GNW are systematically omitted once (the self-depleted weights), and the corresponding weight adjustments due to the omission are computed to keep the overall network behavior unchanged. The primary feature ranking index defined as the sum of self-depleted weights and the corresponding weight adjustments computed is found capable of separating good from bad features for some artificial data sets of known feature rankings tested. The final feature indexes used to rank the data sets are computed as a sum of the weighted frequency of each feature being ranked in a particular rank for each data set being partitioned into numerous clusters. The two data sets are also clustered by a standard K-means method and trained by a support vector machine (SVM) for feature ranking using the computed F-scores as feature ranking index. It is found that GNW outperforms the SVM method on three artificial as well as the matrix metalloproteinase-1 inhibitor data sets studied. A clear-cut separation of good from bad features is offered by the GNW but not by the SVM method for a feature pool of known feature ranking. PMID:16859292
Nguyen, Lien B; Nguyen, Anh V; Ling, Sai Ho; Nguyen, Hung T
2013-01-01
Hypoglycemia is the most common but highly feared complication induced by the intensive insulin therapy in patients with type 1 diabetes mellitus (T1DM). Nocturnal hypoglycemia is dangerous because sleep obscures early symptoms and potentially leads to severe episodes which can cause seizure, coma, or even death. It is shown that the hypoglycemia onset induces early changes in electroencephalography (EEG) signals which can be detected non-invasively. In our research, EEG signals from five T1DM patients during an overnight clamp study were measured and analyzed. By applying a method of feature extraction using Fast Fourier Transform (FFT) and classification using neural networks, we establish that hypoglycemia can be detected efficiently using EEG signals from only two channels. This paper demonstrates that by implementing a training process of combining genetic algorithm and Levenberg-Marquardt algorithm, the classification results are improved markedly up to 75% sensitivity and 60% specificity on a separate testing set. PMID:24110953
NASA Astrophysics Data System (ADS)
Jokar, Ali; Godarzi, Ali Abbasi; Saber, Mohammad; Shafii, Mohammad Behshad
2016-01-01
In this paper, a novel approach has been presented to simulate and optimize the pulsating heat pipes (PHPs). The used pulsating heat pipe setup was designed and constructed for this study. Due to the lack of a general mathematical model for exact analysis of the PHPs, a method has been applied for simulation and optimization using the natural algorithms. In this way, the simulator consists of a kind of multilayer perceptron neural network, which is trained by experimental results obtained from our PHP setup. The results show that the complex behavior of PHPs can be successfully described by the non-linear structure of this simulator. The input variables of the neural network are input heat flux to evaporator (q″), filling ratio (FR) and inclined angle (IA) and its output is thermal resistance of PHP. Finally, based upon the simulation results and considering the heat pipe's operating constraints, the optimum operating point of the system is obtained by using genetic algorithm (GA). The experimental results show that the optimum FR (38.25 %), input heat flux to evaporator (39.93 W) and IA (55°) that obtained from GA are acceptable.
Malik, Bilal H.; Jabbour, Joey M.; Maitland, Kristen C.
2015-01-01
Automatic segmentation of nuclei in reflectance confocal microscopy images is critical for visualization and rapid quantification of nuclear-to-cytoplasmic ratio, a useful indicator of epithelial precancer. Reflectance confocal microscopy can provide three-dimensional imaging of epithelial tissue in vivo with sub-cellular resolution. Changes in nuclear density or nuclear-to-cytoplasmic ratio as a function of depth obtained from confocal images can be used to determine the presence or stage of epithelial cancers. However, low nuclear to background contrast, low resolution at greater imaging depths, and significant variation in reflectance signal of nuclei complicate segmentation required for quantification of nuclear-to-cytoplasmic ratio. Here, we present an automated segmentation method to segment nuclei in reflectance confocal images using a pulse coupled neural network algorithm, specifically a spiking cortical model, and an artificial neural network classifier. The segmentation algorithm was applied to an image model of nuclei with varying nuclear to background contrast. Greater than 90% of simulated nuclei were detected for contrast of 2.0 or greater. Confocal images of porcine and human oral mucosa were used to evaluate application to epithelial tissue. Segmentation accuracy was assessed using manual segmentation of nuclei as the gold standard. PMID:25816131
A novel learning algorithm which improves the partial fault tolerance of multilayer neural networks.
Cavalieri, Salvatore; Mirabella, Orazio
1999-01-01
The paper deals with the problem of fault tolerance in a multilayer perceptron network. Although it already possesses a reasonable fault tolerance capability, it may be insufficient in particularly critical applications. Studies carried out by the authors have shown that the traditional backpropagation learning algorithm may entail the presence of a certain number of weights with a much higher absolute value than the others. Further studies have shown that faults in these weights is the main cause of deterioration in the performance of the neural network. In other words, the main cause of incorrect network functioning on the occurrence of a fault is the non-uniform distribution of absolute values of weights in each layer. The paper proposes a learning algorithm which updates the weights, distributing their absolute values as uniformly as possible in each layer. Tests performed on benchmark test sets have shown the considerable increase in fault tolerance obtainable with the proposed approach as compared with the traditional backpropagation algorithm and with some of the most efficient fault tolerance approaches to be found in literature. PMID:12662719
NASA Astrophysics Data System (ADS)
Karabiber, Fethullah; Vecchio, Pietro; Grassi, Giuseppe
2011-12-01
The Bio-inspired (Bi-i) Cellular Vision System is a computing platform consisting of sensing, array sensing-processing, and digital signal processing. The platform is based on the Cellular Neural/Nonlinear Network (CNN) paradigm. This article presents the implementation of a novel CNN-based segmentation algorithm onto the Bi-i system. Each part of the algorithm, along with the corresponding implementation on the hardware platform, is carefully described through the article. The experimental results, carried out for Foreman and Car-phone video sequences, highlight the feasibility of the approach, which provides a frame rate of about 26 frames/s. Comparisons with existing CNN-based methods show that the conceived approach is more accurate, thus representing a good trade-off between real-time requirements and accuracy.
Performance comparison of neural network training algorithms in modeling of bimodal drug delivery.
Ghaffari, A; Abdollahi, H; Khoshayand, M R; Bozchalooi, I Soltani; Dadgar, A; Rafiee-Tehrani, M
2006-12-11
The major aim of this study was to model the effect of two causal factors, i.e. coating weight gain and amount of pectin-chitosan in the coating solution on the in vitro release profile of theophylline for bimodal drug delivery. Artificial neural network (ANN) as a multilayer perceptron feedforward network was incorporated for developing a predictive model of the formulations. Five different training algorithms belonging to three classes: gradient descent, quasi-Newton (Levenberg-Marquardt, LM) and genetic algorithm (GA) were used to train ANN containing a single hidden layer of four nodes. The next objective of the current study was to compare the performance of aforementioned algorithms with regard to predicting ability. The ANNs were trained with those algorithms using the available experimental data as the training set. The divergence of the RMSE between the output and target values of test set was monitored and used as a criterion to stop training. Two versions of gradient descent backpropagation algorithms, i.e. incremental backpropagation (IBP) and batch backpropagation (BBP) outperformed the others. No significant differences were found between the predictive abilities of IBP and BBP, although, the convergence speed of BBP is three- to four-fold higher than IBP. Although, both gradient descent backpropagation and LM methodologies gave comparable results for the data modeling, training of ANNs with genetic algorithm was erratic. The precision of predictive ability was measured for each training algorithm and their performances were in the order of: IBP, BBP>LM>QP (quick propagation)>GA. According to BBP-ANN implementation, an increase in coating levels and a decrease in the amount of pectin-chitosan generally retarded the drug release. Moreover, the latter causal factor namely the amount of pectin-chitosan played slightly more dominant role in determination of the dissolution profiles. PMID:16959449
Optimal groundwater remediation using artificial neural networks and the genetic algorithm
Rogers, L.L.
1992-08-01
An innovative computational approach for the optimization of groundwater remediation is presented which uses artificial neural networks (ANNs) and the genetic algorithm (GA). In this approach, the ANN is trained to predict an aspect of the outcome of a flow and transport simulation. Then the GA searches through realizations or patterns of pumping and uses the trained network to predict the outcome of the realizations. This approach has advantages of parallel processing of the groundwater simulations and the ability to ``recycle`` or reuse the base of knowledge formed by these simulations. These advantages offer reduction of computational burden of the groundwater simulations relative to a more conventional approach which uses nonlinear programming (NLP) with a quasi-newtonian search. Also the modular nature of this approach facilitates substitution of different groundwater simulation models.
NASA Astrophysics Data System (ADS)
Sahoo, G. B.
2007-12-01
In recent years, artificial neural networks (ANNs) appear to be viable alternative to models that use phenomenological hypotheses (i.e. knowledge based models) for cases (1) the available data are not detailed and sufficient for using a process based model and (2) the detailed complex physics of the system is partially understood. ANNs have been widely used in many fields such as chemical and environmental engineering, hydrology, and water resources applications for optimum prediction of system parameters and variables. However, in most cases, parameters and system variables were forecasted employing suboptimal ANNs. The geometry and modeling parameters of an artificial neural network (ANN) and the training dataset have significant effects on its predictive performance efficiency. The combination of ANN modeling parameter and geometry arranged in the modeling domain (i.e. lower and upper bounds of each modeling parameter and geometry) is large enough (i.e. greater than 100000) that it is difficult to examine all cases using trial and error approach for the selection of an optimum set. Thus, one could easily end up with finding a set of suboptimal values. This study presents the use of genetic algorithms (GAs) to search for the optimal geometry and values of modeling parameters of a multilayer feedforward backpropagation neural network (BPNN) and a radial basis function network (RBFN). The predictive performance efficiency of the GA and ANN combination is examined using two datasets derived from the same population for training. It is illustrated that (1) the GA optimized ANN outperforms to the ANN using a trial and error approach, and (2) ANN predictive performance and geometry depend on the number of samples and the characteristics of samples included in the training dataset.
An Imperialist Competitive Algorithm Artificial Neural Network Method to Predict Runoff
NASA Astrophysics Data System (ADS)
Ashraf Vaghefi, S.; Mousavi, S. J.; Abbaspour, K. C.; Yang, H.
2012-04-01
Modeling of rainfall-runoff relationship is important in view of many uses of water resources. Artificial Neural Networks (ANNs) are able to extract the relation between the rainfall and runoff without addressing the physics behind the process. Using back propagation (BP) method to train weights of ANNs may lead to problems in predicting low flows. This paper provides a procedure for application of artificial neural networks trained by Imperialist Competitive Algorithm (ICA) to flow forecasting in Karkheh watershed in southwest of Iran. The monthly hydrometric and climatic data in ANN existed for the period of 1982 to 2002. The results of this study indicated that ANNs rainfall-runoff models trained by ICA predicted daily flow more accurately than those trained by BP. Coefficient of determination for predicted runoffs in training and validating phases in ICA method were 0.97 and 0.93, respectively, while 0.93 and 0.91 were obtained in BP method. The mean squared error of the networks (MSE) for both ICA and BP methods were measured for training and testing data. The accuracy of the model performance was acceptable in both methods, although ICA's results were slightly more accurate.
Application of neural networks and other machine learning algorithms to DNA sequence analysis
Lapedes, A.; Barnes, C.; Burks, C.; Farber, R.; Sirotkin, K.
1988-01-01
In this article we report initial, quantitative results on application of simple neutral networks, and simple machine learning methods, to two problems in DNA sequence analysis. The two problems we consider are: (1) determination of whether procaryotic and eucaryotic DNA sequences segments are translated to protein. An accuracy of 99.4% is reported for procaryotic DNA (E. coli) and 98.4% for eucaryotic DNA (H. Sapiens genes known to be expressed in liver); (2) determination of whether eucaryotic DNA sequence segments containing the dinucleotides ''AG'' or ''GT'' are transcribed to RNA splice junctions. Accuracy of 91.2% was achieved on intron/exon splice junctions (acceptor sites) and 92.8% on exon/intron splice junctions (donor sites). The solution of these two problems, by use of information processing algorithms operating on unannotated base sequences and without recourse to biological laboratory work, is relevant to the Human Genome Project. A variety of neural network, machine learning, and information theoretic algorithms are used. The accuracies obtained exceed those of previous investigations for which quantitative results are available in the literature. They result from an ongoing program of research that applies machine learning algorithms to the problem of determining biological function of DNA sequences. Some predictions of possible new genes using these methods are listed -- although a complete survey of the H. sapiens and E. coli sections of GenBank will be given elsewhere. 36 refs., 6 figs., 6 tabs.
NASA Astrophysics Data System (ADS)
Tang, Shihua; Li, Feida; Liu, Yintao; Lan, Lan; Zhou, Conglin; Huang, Qing
2015-12-01
With the advantage of high speed, big transport capacity, low energy consumption, good economic benefits and so on, high-speed railway is becoming more and more popular all over the world. It can reach 350 kilometers per hour, which requires high security performances. So research on the prediction of high-speed railway settlement that as one of the important factors affecting the safety of high-speed railway becomes particularly important. This paper takes advantage of genetic algorithms to seek all the data in order to calculate the best result and combines the advantage of strong learning ability and high accuracy of wavelet neural network, then build the model of genetic wavelet neural network for the prediction of high-speed railway settlement. By the experiment of back propagation neural network, wavelet neural network and genetic wavelet neural network, it shows that the absolute value of residual errors in the prediction of high-speed railway settlement based on genetic algorithm is the smallest, which proves that genetic wavelet neural network is better than the other two methods. The correlation coefficient of predicted and observed value is 99.9%. Furthermore, the maximum absolute value of residual error, minimum absolute value of residual error-mean value of relative error and value of root mean squared error(RMSE) that predicted by genetic wavelet neural network are all smaller than the other two methods'. The genetic wavelet neural network in the prediction of high-speed railway settlement is more stable in terms of stability and more accurate in the perspective of accuracy.
A new adaptive merging and growing algorithm for designing artificial neural networks.
Islam, Md Monirul; Sattar, Md Abdus; Amin, Md Faijul; Yao, Xin; Murase, Kazuyuki
2009-06-01
This paper presents a new algorithm, called adaptive merging and growing algorithm (AMGA), in designing artificial neural networks (ANNs). This algorithm merges and adds hidden neurons during the training process of ANNs. The merge operation introduced in AMGA is a kind of a mixed mode operation, which is equivalent to pruning two neurons and adding one neuron. Unlike most previous studies, AMGA puts emphasis on autonomous functioning in the design process of ANNs. This is the main reason why AMGA uses an adaptive not a predefined fixed strategy in designing ANNs. The adaptive strategy merges or adds hidden neurons based on the learning ability of hidden neurons or the training progress of ANNs. In order to reduce the amount of retraining after modifying ANN architectures, AMGA prunes hidden neurons by merging correlated hidden neurons and adds hidden neurons by splitting existing hidden neurons. The proposed AMGA has been tested on a number of benchmark problems in machine learning and ANNs, including breast cancer, Australian credit card assessment, and diabetes, gene, glass, heart, iris, and thyroid problems. The experimental results show that AMGA can design compact ANN architectures with good generalization ability compared to other algorithms. PMID:19203888
NASA Astrophysics Data System (ADS)
Srivatsan, V.; Balasubramaniam, Krishnan; Nair, N. V.
2003-03-01
Damages like cracks, delaminations, etc., in composite parts have traditionally been evaluated using manual methods like acoustic impact (using measurements in the audio frequencies). This technique is currently used during manufacturing for product quality testing and later for maintenance and assurance of structural integrity. The automation of this technique will significantly improve the reliability of inspection. The signals obtained from the composites are analyzed using signal-processing techniques in the time-frequency domain to build a robust algorithm for detection and identification of defects. A feature vector is constructed using these techniques and then applied to a neural network for defect identification. Comparative studies are conducted to search for the best and most comprehensive feature vector. Results using different signal processing techniques are presented. Similarly comparative results are presented between two different kinds of neural networks (namely Radial Basis functions and MLP) and various architectures in each kind. A low cost data acquisition system has also been developed for acquiring audio signals using the sound card and the microphone in a multi-media PC.
Program Helps Simulate Neural Networks
NASA Technical Reports Server (NTRS)
Villarreal, James; Mcintire, Gary
1993-01-01
Neural Network Environment on Transputer System (NNETS) computer program provides users high degree of flexibility in creating and manipulating wide variety of neural-network topologies at processing speeds not found in conventional computing environments. Supports back-propagation and back-propagation-related algorithms. Back-propagation algorithm used is implementation of Rumelhart's generalized delta rule. NNETS developed on INMOS Transputer(R). Predefines back-propagation network, Jordan network, and reinforcement network to assist users in learning and defining own networks. Also enables users to configure other neural-network paradigms from NNETS basic architecture. Small portion of software written in OCCAM(R) language.
Poultangari, Iman; Shahnazi, Reza; Sheikhan, Mansour
2012-09-01
In order to control the pitch angle of blades in wind turbines, commonly the proportional and integral (PI) controller due to its simplicity and industrial usability is employed. The neural networks and evolutionary algorithms are tools that provide a suitable ground to determine the optimal PI gains. In this paper, a radial basis function (RBF) neural network based PI controller is proposed for collective pitch control (CPC) of a 5-MW wind turbine. In order to provide an optimal dataset to train the RBF neural network, particle swarm optimization (PSO) evolutionary algorithm is used. The proposed method does not need the complexities, nonlinearities and uncertainties of the system under control. The simulation results show that the proposed controller has satisfactory performance. PMID:22738782
Cold header machine process monitoring using a genetic algorithm designed neural network approach
NASA Astrophysics Data System (ADS)
dos Reis, Henrique L. M.; Voegele, Aaron C.; Cook, David B.
1999-12-01
In cold heading manufacturing processes, complete or partial fracture of the punch-pin leads to production of out-of-tolerance parts. A process monitoring system has been developed to assure that out-of-tolerance parts do not contaminate the batch of acceptable parts. A four-channel data acquisition system was assembled to collect and store the acoustic signal generated during the manufacturing process. A genetic algorithm was designed to select the smallest subset of waveform features necessary to develop a robust artificial neural network that could differentiate among the various cold head machine conditions, including complete or partial failure of the punch pin. The developed monitoring system is able to terminate production within seconds of punch pin failure using only four waveform features.
NASA Astrophysics Data System (ADS)
Dwivedi, Suneet; Pandey, Avinash C.
2011-08-01
The correct and timely forecast of the Indian summer monsoon Intraseasonal Oscillations (ISOs) is very important. It has great impact on the agriculture and economy of the Indian subcontinent region. The applicability of Genetic Algorithm (GA) is demonstrated for nonlinear curve fitting of the inherently chaotic and noisy Lorenz time series and the ISO data. A robust method is developed for the very long-range prediction of the ISO using a feed-forward time delay backpropagation Artificial Neural Network (ANN). Using an iterative one-step-ahead prediction strategy, five years (120 pentads) of advanced prediction is made for the ISO data with good forecast skill. It is shown that a hybrid GA-ANN model may be used as an early forecast model followed by ANN only model as a more reliable model.
Calibration of neural networks using genetic algorithms, with application to optimal path planning
NASA Technical Reports Server (NTRS)
Smith, Terence R.; Pitney, Gilbert A.; Greenwood, Daniel
1987-01-01
Genetic algorithms (GA) are used to search the synaptic weight space of artificial neural systems (ANS) for weight vectors that optimize some network performance function. GAs do not suffer from some of the architectural constraints involved with other techniques and it is straightforward to incorporate terms into the performance function concerning the metastructure of the ANS. Hence GAs offer a remarkably general approach to calibrating ANS. GAs are applied to the problem of calibrating an ANS that finds optimal paths over a given surface. This problem involves training an ANS on a relatively small set of paths and then examining whether the calibrated ANS is able to find good paths between arbitrary start and end points on the surface.
NASA Astrophysics Data System (ADS)
Quintanilla-Domínguez, Joel; Ojeda-Magaña, Benjamín; Marcano-Cedeño, Alexis; Cortina-Januchs, María G.; Vega-Corona, Antonio; Andina, Diego
2011-12-01
A new method for detecting microcalcifications in regions of interest (ROIs) extracted from digitized mammograms is proposed. The top-hat transform is a technique based on mathematical morphology operations and, in this paper, is used to perform contrast enhancement of the mi-crocalcifications. To improve microcalcification detection, a novel image sub-segmentation approach based on the possibilistic fuzzy c-means algorithm is used. From the original ROIs, window-based features, such as the mean and standard deviation, were extracted; these features were used as an input vector in a classifier. The classifier is based on an artificial neural network to identify patterns belonging to microcalcifications and healthy tissue. Our results show that the proposed method is a good alternative for automatically detecting microcalcifications, because this stage is an important part of early breast cancer detection.
Architecture for High Speed Learning of Neural Network using Genetic Algorithm
NASA Astrophysics Data System (ADS)
Yoshikawa, Masaya; Terai, Hidekazu
This paper discusses the architecture for high speed learning of Neural Network (NN) using Genetic Algorithm (GA). The proposed architecture prevents local minimum by using the GA characteristic of holding several individual populations for a population-based search and achieves high speed processing adopting dedicated hardware. To keep general purpose equal software processing, the proposed architecture can be flexible genetic operations on GA and is introduced both Sigmoid function and Heaviside function on NN. Furthermore, the proposed architecture is not optimized only the pipeline at evaluation phase on NN, but also optimized hierarchic pipelines on the whole at evolutionary phase. We have done the simulation, verification and logic synthesis using library of 0.35μm CMOS standard cell. Simulation results evaluating the proposed architecture show to achieve 22 times speed on average compared with software processing.
A Modified Hopfield Neural Network Algorithm (MHNNA) Using ALOS Image for Water Quality Mapping
Kzar, Ahmed Asal; Mat Jafri, Mohd Zubir; Mutter, Kussay N.; Syahreza, Saumi
2015-01-01
Decreasing water pollution is a big problem in coastal waters. Coastal health of ecosystems can be affected by high concentrations of suspended sediment. In this work, a Modified Hopfield Neural Network Algorithm (MHNNA) was used with remote sensing imagery to classify the total suspended solids (TSS) concentrations in the waters of coastal Langkawi Island, Malaysia. The adopted remote sensing image is the Advanced Land Observation Satellite (ALOS) image acquired on 18 January 2010. Our modification allows the Hopfield neural network to convert and classify color satellite images. The samples were collected from the study area simultaneously with the acquiring of satellite imagery. The sample locations were determined using a handheld global positioning system (GPS). The TSS concentration measurements were conducted in a lab and used for validation (real data), classification, and accuracy assessments. Mapping was achieved by using the MHNNA to classify the concentrations according to their reflectance values in band 1, band 2, and band 3. The TSS map was color-coded for visual interpretation. The efficiency of the proposed algorithm was investigated by dividing the validation data into two groups. The first group was used as source samples for supervisor classification via the MHNNA. The second group was used to test the MHNNA efficiency. After mapping, the locations of the second group in the produced classes were detected. Next, the correlation coefficient (R) and root mean square error (RMSE) were calculated between the two groups, according to their corresponding locations in the classes. The MHNNA exhibited a higher R (0.977) and lower RMSE (2.887). In addition, we test the MHNNA with noise, where it proves its accuracy with noisy images over a range of noise levels. All results have been compared with a minimum distance classifier (Min-Dis). Therefore, TSS mapping of polluted water in the coastal Langkawi Island, Malaysia can be performed using the adopted
A Modified Hopfield Neural Network Algorithm (MHNNA) Using ALOS Image for Water Quality Mapping.
Kzar, Ahmed Asal; Mat Jafri, Mohd Zubir; Mutter, Kussay N; Syahreza, Saumi
2016-01-01
Decreasing water pollution is a big problem in coastal waters. Coastal health of ecosystems can be affected by high concentrations of suspended sediment. In this work, a Modified Hopfield Neural Network Algorithm (MHNNA) was used with remote sensing imagery to classify the total suspended solids (TSS) concentrations in the waters of coastal Langkawi Island, Malaysia. The adopted remote sensing image is the Advanced Land Observation Satellite (ALOS) image acquired on 18 January 2010. Our modification allows the Hopfield neural network to convert and classify color satellite images. The samples were collected from the study area simultaneously with the acquiring of satellite imagery. The sample locations were determined using a handheld global positioning system (GPS). The TSS concentration measurements were conducted in a lab and used for validation (real data), classification, and accuracy assessments. Mapping was achieved by using the MHNNA to classify the concentrations according to their reflectance values in band 1, band 2, and band 3. The TSS map was color-coded for visual interpretation. The efficiency of the proposed algorithm was investigated by dividing the validation data into two groups. The first group was used as source samples for supervisor classification via the MHNNA. The second group was used to test the MHNNA efficiency. After mapping, the locations of the second group in the produced classes were detected. Next, the correlation coefficient (R) and root mean square error (RMSE) were calculated between the two groups, according to their corresponding locations in the classes. The MHNNA exhibited a higher R (0.977) and lower RMSE (2.887). In addition, we test the MHNNA with noise, where it proves its accuracy with noisy images over a range of noise levels. All results have been compared with a minimum distance classifier (Min-Dis). Therefore, TSS mapping of polluted water in the coastal Langkawi Island, Malaysia can be performed using the adopted
NASA Astrophysics Data System (ADS)
Zhang, Liqiang; Li, Luoxing; Wang, Shiuping; Zhu, Biwu
2012-04-01
In this article, the low-pressure die-cast (LPDC) process parameters of aluminum alloy thin-walled component with permanent mold are optimized using a combining artificial neural network and genetic algorithm (ANN/GA) method. In this method, an ANN model combining learning vector quantization (LVQ) and back-propagation (BP) algorithm is proposed to map the complex relationship between process conditions and quality indexes of LPDC. The genetic algorithm is employed to optimize the process parameters with the fitness function based on the trained ANN model. Then, by applying the optimized parameters, a thin-walled component with 300 mm in length, 100 mm in width, and 1.5 mm in thickness is successfully prepared and no obvious defects such as shrinkage, gas porosity, distortion, and crack were found in the component. The results indicate that the combining ANN/GA method is an effective tool for the process optimization of LPDC, and they also provide valuable reference on choosing the right process parameters for LPDC thin-walled aluminum alloy casting.
Using neural networks and Dyna algorithm for integrated planning, reacting and learning in systems
NASA Technical Reports Server (NTRS)
Lima, Pedro; Beard, Randal
1992-01-01
The traditional AI answer to the decision making problem for a robot is planning. However, planning is usually CPU-time consuming, depending on the availability and accuracy of a world model. The Dyna system generally described in earlier work, uses trial and error to learn a world model which is simultaneously used to plan reactions resulting in optimal action sequences. It is an attempt to integrate planning, reactive, and learning systems. The architecture of Dyna is presented. The different blocks are described. There are three main components of the system. The first is the world model used by the robot for internal world representation. The input of the world model is the current state and the action taken in the current state. The output is the corresponding reward and resulting state. The second module in the system is the policy. The policy observes the current state and outputs the action to be executed by the robot. At the beginning of program execution, the policy is stochastic and through learning progressively becomes deterministic. The policy decides upon an action according to the output of an evaluation function, which is the third module of the system. The evaluation function takes the following as input: the current state of the system, the action taken in that state, the resulting state, and a reward generated by the world which is proportional to the current distance from the goal state. Originally, the work proposed was as follows: (1) to implement a simple 2-D world where a 'robot' is navigating around obstacles, to learn the path to a goal, by using lookup tables; (2) to substitute the world model and Q estimate function Q by neural networks; and (3) to apply the algorithm to a more complex world where the use of a neural network would be fully justified. In this paper, the system design and achieved results will be described. First we implement the world model with a neural network and leave Q implemented as a look up table. Next, we use a
NASA Technical Reports Server (NTRS)
Lary, David J.; Mussa, Yussuf
2004-01-01
In this study a new extended Kalman filter (EKF) learning algorithm for feed-forward neural networks (FFN) is used. With the EKF approach, the training of the FFN can be seen as state estimation for a non-linear stationary process. The EKF method gives excellent convergence performances provided that there is enough computer core memory and that the machine precision is high. Neural networks are ideally suited to describe the spatial and temporal dependence of tracer-tracer correlations. The neural network performs well even in regions where the correlations are less compact and normally a family of correlation curves would be required. For example, the CH4-N2O correlation can be well described using a neural network trained with the latitude, pressure, time of year, and CH4 volume mixing ratio (v.m.r.). The neural network was able to reproduce the CH4-N2O correlation with a correlation coefficient between simulated and training values of 0.9997. The neural network Fortran code used is available for download.
ERIC Educational Resources Information Center
Sunal, Cynthia Szymanski; Karr, Charles L.; Sunal, Dennis W.
2003-01-01
Students' conceptions of three major artificial intelligence concepts used in the modeling of systems in science, fuzzy logic, neural networks, and genetic algorithms were investigated before and after a higher education science course. Students initially explored their prior ideas related to the three concepts through active tasks. Then,…
Using Hybrid Algorithm to Improve Intrusion Detection in Multi Layer Feed Forward Neural Networks
ERIC Educational Resources Information Center
Ray, Loye Lynn
2014-01-01
The need for detecting malicious behavior on a computer networks continued to be important to maintaining a safe and secure environment. The purpose of this study was to determine the relationship of multilayer feed forward neural network architecture to the ability of detecting abnormal behavior in networks. This involved building, training, and…
Xu, Lei; Jeavons, Peter
2015-11-01
Leader election in anonymous rings and complete networks is a very practical problem in distributed computing. Previous algorithms for this problem are generally designed for a classical message passing model where complex messages are exchanged. However, the need to send and receive complex messages makes such algorithms less practical for some real applications. We present some simple synchronous algorithms for distributed leader election in anonymous rings and complete networks that are inspired by the development of the neural system of the fruit fly. Our leader election algorithms all assume that only one-bit messages are broadcast by nodes in the network and processors are only able to distinguish between silence and the arrival of one or more messages. These restrictions allow implementations to use a simpler message-passing architecture. Even with these harsh restrictions our algorithms are shown to achieve good time and message complexity both analytically and experimentally. PMID:26173905
Optimal groundwater remediation using artificial neural networks and the genetic algorithm
Rogers, L.L.
1992-01-01
An innovative computational approach for the optimization of groundwater remediation is presented which uses artificial neural networks (ANNs) and the genetic algorithm (GA). In this approach, the ANN is trained to predict an aspect of the outcome of a flow and transport simulation. Then the trained network searches through realizations or patterns of pumping selected by the GA, predicting the outcome. This approach has advantages of parallel processing of the groundwater simulations and the ability to [open quotes]recycle[close quotes] or reuse the base of knowledge formed by these simulations. These advantages offer reduction of computational burden of the groundwater simulations relative to a more conventional approach which uses nonlinear programming (NLP) with a quasi-newtonian search. Also the modular nature of this approach facilitates substitution of different groundwater simulation models. The ANN technology, inspired by neurobiological theories of massive interconnection and parallelism, has been applied to a variety of optimization problems. In the ANN groundwater management approach presented here, the behavior of complex groundwater scenarios with spatially-variable transport parameters and multiple contaminant plumes are simulated with 2-D flow and transport codes. An ANN is trained upon a set of examples developed from groundwater simulations. The input of the ANN characterizes the different realizations of pumping. The output characterizes the objectives and constraints of the optimization, such as whether regulatory goals have been met, value of cost functions or cleanup time, and mass of contaminant removal. The supervised learning algorithm of backpropagation is used to train the network. The conjugate gradient method and weight-elimination procedures are used to speed convergence and improve performance, respectively. Then a search is made through possible pumping realizations to find optimal realizations.
Pile-up correction by Genetic Algorithm and Artificial Neural Network
NASA Astrophysics Data System (ADS)
Kafaee, M.; Saramad, S.
2009-08-01
Pile-up distortion is a common problem for high counting rates radiation spectroscopy in many fields such as industrial, nuclear and medical applications. It is possible to reduce pulse pile-up using hardware-based pile-up rejections. However, this phenomenon may not be eliminated completely by this approach and the spectrum distortion caused by pile-up rejection can be increased as well. In addition, inaccurate correction or rejection of pile-up artifacts in applications such as energy dispersive X-ray (EDX) spectrometers can lead to losses of counts, will give poor quantitative results and even false element identification. Therefore, it is highly desirable to use software-based models to predict and correct any recognized pile-up signals in data acquisition systems. The present paper describes two new intelligent approaches for pile-up correction; the Genetic Algorithm (GA) and Artificial Neural Networks (ANNs). The validation and testing results of these new methods have been compared, which shows excellent agreement with the measured data with 60Co source and NaI detector. The Monte Carlo simulation of these new intelligent algorithms also shows their advantages over hardware-based pulse pile-up rejection methods.
Johnson, V.M.; Rogers, L.L.
1994-09-01
A goal common to both the environmental and petroleum industries is the reduction of costs and/or enhancement of profits by the optimal placement of extraction/production and injection wells. Formal optimization techniques facilitate this goal by searching among the potentially infinite number of possible well patterns for ones that best meet engineering and economic objectives. However, if a flow and transport model or reservoir simulator is being used to evaluate the effectiveness of each network of wells, the computational resources required to apply most optimization techniques to real field problems become prohibitively expensive. This paper describes a new approach to field-scale, nonlinear optimization of well patterns that is intended to make such searches tractable on conventional computer equipment. Artificial neural networks (ANNs) are trained to predict selected information that would normally be calculated by the simulator. The ANNs are then embedded in a variant of the genetic algorithm (GA), which drives the search for increasingly effective well patterns and uses the ANNs, rather than the original simulator, to evaluate the effectiveness of each pattern. Once the search is complete, the ANNs are reused in sensitivity studies to give additional information on the performance of individual or clusters of wells.
Wu, Jianfa; Peng, Dahao; Li, Zhuping; Zhao, Li; Ling, Huanzhang
2015-01-01
To effectively and accurately detect and classify network intrusion data, this paper introduces a general regression neural network (GRNN) based on the artificial immune algorithm with elitist strategies (AIAE). The elitist archive and elitist crossover were combined with the artificial immune algorithm (AIA) to produce the AIAE-GRNN algorithm, with the aim of improving its adaptivity and accuracy. In this paper, the mean square errors (MSEs) were considered the affinity function. The AIAE was used to optimize the smooth factors of the GRNN; then, the optimal smooth factor was solved and substituted into the trained GRNN. Thus, the intrusive data were classified. The paper selected a GRNN that was separately optimized using a genetic algorithm (GA), particle swarm optimization (PSO), and fuzzy C-mean clustering (FCM) to enable a comparison of these approaches. As shown in the results, the AIAE-GRNN achieves a higher classification accuracy than PSO-GRNN, but the running time of AIAE-GRNN is long, which was proved first. FCM and GA-GRNN were eliminated because of their deficiencies in terms of accuracy and convergence. To improve the running speed, the paper adopted principal component analysis (PCA) to reduce the dimensions of the intrusive data. With the reduction in dimensionality, the PCA-AIAE-GRNN decreases in accuracy less and has better convergence than the PCA-PSO-GRNN, and the running speed of the PCA-AIAE-GRNN was relatively improved. The experimental results show that the AIAE-GRNN has a higher robustness and accuracy than the other algorithms considered and can thus be used to classify the intrusive data. PMID:25807466
NASA Astrophysics Data System (ADS)
Asal Kzar, Ahmed; Mat Jafri, M. Z.; Hwee San, Lim; Al-Zuky, Ali A.; Mutter, Kussay N.; Hassan Al-Saleh, Anwar
2016-06-01
There are many techniques that have been given for water quality problem, but the remote sensing techniques have proven their success, especially when the artificial neural networks are used as mathematical models with these techniques. Hopfield neural network is one type of artificial neural networks which is common, fast, simple, and efficient, but it when it deals with images that have more than two colours such as remote sensing images. This work has attempted to solve this problem via modifying the network that deals with colour remote sensing images for water quality mapping. A Feed-forward Hopfield Neural Network Algorithm (FHNNA) was modified and used with a satellite colour image from type of Thailand earth observation system (THEOS) for TSS mapping in the Penang strait, Malaysia, through the classification of TSS concentrations. The new algorithm is based essentially on three modifications: using HNN as feed-forward network, considering the weights of bitplanes, and non-self-architecture or zero diagonal of weight matrix, in addition, it depends on a validation data. The achieved map was colour-coded for visual interpretation. The efficiency of the new algorithm has found out by the higher correlation coefficient (R=0.979) and the lower root mean square error (RMSE=4.301) between the validation data that were divided into two groups. One used for the algorithm and the other used for validating the results. The comparison was with the minimum distance classifier. Therefore, TSS mapping of polluted water in Penang strait, Malaysia, can be performed using FHNNA with remote sensing technique (THEOS). It is a new and useful application of HNN, so it is a new model with remote sensing techniques for water quality mapping which is considered important environmental problem.
2014-01-01
Background Extracting relevant information from microarray data is a very complex task due to the characteristics of the data sets, as they comprise a large number of features while few samples are generally available. In this sense, feature selection is a very important aspect of the analysis helping in the tasks of identifying relevant genes and also for maximizing predictive information. Methods Due to its simplicity and speed, Stepwise Forward Selection (SFS) is a widely used feature selection technique. In this work, we carry a comparative study of SFS and Genetic Algorithms (GA) as general frameworks for the analysis of microarray data with the aim of identifying group of genes with high predictive capability and biological relevance. Six standard and machine learning-based techniques (Linear Discriminant Analysis (LDA), Support Vector Machines (SVM), Naive Bayes (NB), C-MANTEC Constructive Neural Network, K-Nearest Neighbors (kNN) and Multilayer perceptron (MLP)) are used within both frameworks using six free-public datasets for the task of predicting cancer outcome. Results Better cancer outcome prediction results were obtained using the GA framework noting that this approach, in comparison to the SFS one, leads to a larger selection set, uses a large number of comparison between genetic profiles and thus it is computationally more intensive. Also the GA framework permitted to obtain a set of genes that can be considered to be more biologically relevant. Regarding the different classifiers used standard feedforward neural networks (MLP), LDA and SVM lead to similar and best results, while C-MANTEC and k-NN followed closely but with a lower accuracy. Further, C-MANTEC, MLP and LDA permitted to obtain a more limited set of genes in comparison to SVM, NB and kNN, and in particular C-MANTEC resulted in the most robust classifier in terms of changes in the parameter settings. Conclusions This study shows that if prediction accuracy is the objective, the GA
Hunting for seamounts using neural networks: learning algorithms for geomorphic studies
NASA Astrophysics Data System (ADS)
Valentine, A. P.; Kalnins, L. M.; Trampert, J.
2012-04-01
Many geophysical studies rely on finding and analysing particular topographic features: the various landforms associated with glaciation, for example, or those that characterise regional tectonics. Typically, these can readily be identified from visual inspection of datasets, but this is a tedious and time-consuming process. However, the development of techniques to perform this assessment automatically is often difficult, since a mathematical description of the feature of interest is required. To identify characteristics of a feature, such as its spatial extent, each characteristic must also have a mathematical description. Where features exhibit significant natural variations, or where their signature in data is marred by noise, performance of conventional algorithms may be poor. One potential avenue lies in the use of neural networks, or other learning algorithms, ideal for complex pattern recognition tasks. Rather than formulating a description of the feature, the user simply provides the algorithm with a training set of hand-classified examples: the problem then becomes one of assessing whether some new example shares the characteristics of this training data. In seismology, this approach is being developed for the identification of high-quality seismic waveforms amidst noisy datasets (e.g. Valentine & Woodhouse, 2010; Valentine & Trampert, in review): can it also be applied to topographic data? To explore this, we attempt to identify the locations of seamounts from gridded bathymetric data (e.g. Smith & Sandwell, 1997). Our approach involves assessing small 'patches' of ocean floor to determine whether they might plausibly contain a seamount, and if so, its location. Since seamounts have been extensively studied, this problem provides an ideal testing ground: in particular, various catalogues exist, compiled using 'traditional' approaches (e.g. Kim & Wessel, 2011). This allows us to straightforwardly generate training datasets, and compare algorithmic
A hybrid neural networks-fuzzy logic-genetic algorithm for grade estimation
Tahmasebi, Pejman; Hezarkhani, Ardeshir
2012-01-01
The grade estimation is a quite important and money/time-consuming stage in a mine project, which is considered as a challenge for the geologists and mining engineers due to the structural complexities in mineral ore deposits. To overcome this problem, several artificial intelligence techniques such as Artificial Neural Networks (ANN) and Fuzzy Logic (FL) have recently been employed with various architectures and properties. However, due to the constraints of both methods, they yield the desired results only under the specific circumstances. As an example, one major problem in FL is the difficulty of constructing the membership functions (MFs).Other problems such as architecture and local minima could also be located in ANN designing. Therefore, a new methodology is presented in this paper for grade estimation. This method which is based on ANN and FL is called “Coactive Neuro-Fuzzy Inference System” (CANFIS) which combines two approaches, ANN and FL. The combination of these two artificial intelligence approaches is achieved via the verbal and numerical power of intelligent systems. To improve the performance of this system, a Genetic Algorithm (GA) – as a well-known technique to solve the complex optimization problems – is also employed to optimize the network parameters including learning rate, momentum of the network and the number of MFs for each input. A comparison of these techniques (ANN, Adaptive Neuro-Fuzzy Inference System or ANFIS) with this new method (CANFIS–GA) is also carried out through a case study in Sungun copper deposit, located in East-Azerbaijan, Iran. The results show that CANFIS–GA could be a faster and more accurate alternative to the existing time-consuming methodologies for ore grade estimation and that is, therefore, suggested to be applied for grade estimation in similar problems. PMID:25540468
A hybrid neural networks-fuzzy logic-genetic algorithm for grade estimation
NASA Astrophysics Data System (ADS)
Tahmasebi, Pejman; Hezarkhani, Ardeshir
2012-05-01
The grade estimation is a quite important and money/time-consuming stage in a mine project, which is considered as a challenge for the geologists and mining engineers due to the structural complexities in mineral ore deposits. To overcome this problem, several artificial intelligence techniques such as Artificial Neural Networks (ANN) and Fuzzy Logic (FL) have recently been employed with various architectures and properties. However, due to the constraints of both methods, they yield the desired results only under the specific circumstances. As an example, one major problem in FL is the difficulty of constructing the membership functions (MFs).Other problems such as architecture and local minima could also be located in ANN designing. Therefore, a new methodology is presented in this paper for grade estimation. This method which is based on ANN and FL is called "Coactive Neuro-Fuzzy Inference System" (CANFIS) which combines two approaches, ANN and FL. The combination of these two artificial intelligence approaches is achieved via the verbal and numerical power of intelligent systems. To improve the performance of this system, a Genetic Algorithm (GA) - as a well-known technique to solve the complex optimization problems - is also employed to optimize the network parameters including learning rate, momentum of the network and the number of MFs for each input. A comparison of these techniques (ANN, Adaptive Neuro-Fuzzy Inference System or ANFIS) with this new method (CANFIS-GA) is also carried out through a case study in Sungun copper deposit, located in East-Azerbaijan, Iran. The results show that CANFIS-GA could be a faster and more accurate alternative to the existing time-consuming methodologies for ore grade estimation and that is, therefore, suggested to be applied for grade estimation in similar problems.
García-Pedrajas, Nicolás; Ortiz-Boyer, Domingo; Hervás-Martínez, César
2006-05-01
In this work we present a new approach to crossover operator in the genetic evolution of neural networks. The most widely used evolutionary computation paradigm for neural network evolution is evolutionary programming. This paradigm is usually preferred due to the problems caused by the application of crossover to neural network evolution. However, crossover is the most innovative operator within the field of evolutionary computation. One of the most notorious problems with the application of crossover to neural networks is known as the permutation problem. This problem occurs due to the fact that the same network can be represented in a genetic coding by many different codifications. Our approach modifies the standard crossover operator taking into account the special features of the individuals to be mated. We present a new model for mating individuals that considers the structure of the hidden layer and redefines the crossover operator. As each hidden node represents a non-linear projection of the input variables, we approach the crossover as a problem on combinatorial optimization. We can formulate the problem as the extraction of a subset of near-optimal projections to create the hidden layer of the new network. This new approach is compared to a classical crossover in 25 real-world problems with an excellent performance. Moreover, the networks obtained are much smaller than those obtained with classical crossover operator. PMID:16343847
Zhang, Yan-jun; Liu, Wen-zhe; Fu, Xing-hu; Bi, Wei-hong
2015-10-01
According to the high precision extracting characteristics of scattering spectrum in Brillouin optical time domain reflection optical fiber sensing system, this paper proposes a new algorithm based on flies optimization algorithm with adaptive mutation and generalized regression neural network. The method takes advantages of the generalized regression neural network which has the ability of the approximation ability, learning speed and generalization of the model. Moreover, by using the strong search ability of flies optimization algorithm with adaptive mutation, it can enhance the learning ability of the neural network. Thus the fitting degree of Brillouin scattering spectrum and the extraction accuracy of frequency shift is improved. Model of actual Brillouin spectrum are constructed by Gaussian white noise on theoretical spectrum, whose center frequency is 11.213 GHz and the linewidths are 40-50, 30-60 and 20-70 MHz, respectively. Comparing the algorithm with the Levenberg-Marquardt fitting method based on finite element analysis, hybrid algorithm particle swarm optimization, Levenberg-Marquardt and the least square method, the maximum frequency shift error of the new algorithm is 0.4 MHz, the fitting degree is 0.991 2 and the root mean square error is 0.024 1. The simulation results show that the proposed algorithm has good fitting degree and minimum absolute error. Therefore, the algorithm can be used on distributed optical fiber sensing system based on Brillouin optical time domain reflection, which can improve the fitting of Brillouin scattering spectrum and the precision of frequency shift extraction effectively. PMID:26904844
Moghri, Mehdi; Omidi, Mostafa; Farahnakian, Masoud
2014-01-01
During the past decade, polymer nanocomposites attracted considerable investment in research and development worldwide. One of the key factors that affect the quality of polymer nanocomposite products in machining is surface roughness. To obtain high quality products and reduce machining costs it is very important to determine the optimal machining conditions so as to achieve enhanced machining performance. The objective of this paper is to develop a predictive model using a combined design of experiments and artificial intelligence approach for optimization of surface roughness in milling of polyamide-6 (PA-6) nanocomposites. A surface roughness predictive model was developed in terms of milling parameters (spindle speed and feed rate) and nanoclay (NC) content using artificial neural network (ANN). As the present study deals with relatively small number of data obtained from full factorial design, application of genetic algorithm (GA) for ANN training is thought to be an appropriate approach for the purpose of developing accurate and robust ANN model. In the optimization phase, a GA is considered in conjunction with the explicit nonlinear function derived from the ANN to determine the optimal milling parameters for minimization of surface roughness for each PA-6 nanocomposite. PMID:24578636
Production of Engineered Fabrics Using Artificial Neural Network-Genetic Algorithm Hybrid Model
NASA Astrophysics Data System (ADS)
Mitra, Ashis; Majumdar, Prabal Kumar; Banerjee, Debamalya
2015-10-01
The process of fabric engineering which is generally practised in most of the textile mills is very complicated, repetitive, tedious and time consuming. To eliminate this trial and error approach, a new approach of fabric engineering has been attempted in this work. Data sets of construction parameters [comprising of ends per inch, picks per inch, warp count and weft count] and three fabric properties (namely drape coefficient, air permeability and thermal resistance) of 25 handloom cotton fabrics have been used. The weights and biases of three artificial neural network (ANN) models developed for the prediction of drape coefficient, air permeability and thermal resistance were used to formulate the fitness or objective function and constraints of the optimization problem. The optimization problem was solved using genetic algorithm (GA). In both the fabrics which were attempted for engineering, the target and simulated fabric properties were very close. The GA was able to search the optimum set of fabric construction parameters with reasonably good accuracy except in case of EPI. However, the overall result is encouraging and can be improved further by using larger data sets of handloom fabrics by hybrid ANN-GA model.
Neural network-based inversion algorithms in magnetic flux leakage nondestructive evaluation
NASA Astrophysics Data System (ADS)
Ramuhalli, Pradeep; Udpa, Lalita; Udpa, Satish S.
2003-05-01
Magnetic flux leakage (MFL) methods are commonly used in the nondestructive evaluation (NDE) of ferromagnetic materials. An important problem in MFL NDE is the determination of flaw parameters such as the flaw length, depth, and shape (profile) from the measured values of the flux density B. Commonly used methods use a forward model in a loop to determine B for a given set of flaw parameters. This approach iteratively adjusts the flaw parameters to minimize the error between the measured and predicted values of B. This article proposes the use of neural networks as forward models. The proposed approach uses two neural networks in feedback configuration—a forward network and an inverse network. The second network is used to predict the profile given the measured value of B, and acts to constrain the solution space. Results of applying these methods to MFL data obtained from a two-dimensional finite-element model, with rectangular flaws of various dimensions, are presented.
Neural network temperature and moisture retrieval algorithm validation for AIRS/AMSU and CrIS/ATMS
NASA Astrophysics Data System (ADS)
Milstein, Adam B.; Blackwell, William J.
2016-02-01
We present comprehensive validation results for the recently introduced neural network technique for retrieving vertical profiles of atmospheric temperature and water vapor from spaceborne microwave and hyperspectral infrared sounding instruments. This technique is currently in operational use as the first guess for the NASA Atmospheric Infrared Sounder (AIRS) Science Team Version 6 retrieval algorithm. The validation incorporates a variety of data sources, independent from the algorithm training set, as ground truth, including global numerical weather analyses generated by the European Center for Medium-Range Weather Forecasts, synoptic radiosonde measurements, and radiosondes dedicated for validation. The results demonstrate significant performance improvements over the previous AIRS/advanced microwave sounding unit (AMSU) operational sounding retrievals in both retrieval error and also show comparable vertical resolution. We also present initial neural network retrieval results using measurements from the Cross-Track Infrared Sounder (CrIS) and Advanced Technology Microwave Sounder (ATMS) currently flying on the Suomi National Polar-orbiting Partnership satellite.
Yoo, Sung-Hoon; Oh, Sung-Kwun; Pedrycz, Witold
2015-09-01
In this study, we propose a hybrid method of face recognition by using face region information extracted from the detected face region. In the preprocessing part, we develop a hybrid approach based on the Active Shape Model (ASM) and the Principal Component Analysis (PCA) algorithm. At this step, we use a CCD (Charge Coupled Device) camera to acquire a facial image by using AdaBoost and then Histogram Equalization (HE) is employed to improve the quality of the image. ASM extracts the face contour and image shape to produce a personal profile. Then we use a PCA method to reduce dimensionality of face images. In the recognition part, we consider the improved Radial Basis Function Neural Networks (RBF NNs) to identify a unique pattern associated with each person. The proposed RBF NN architecture consists of three functional modules realizing the condition phase, the conclusion phase, and the inference phase completed with the help of fuzzy rules coming in the standard 'if-then' format. In the formation of the condition part of the fuzzy rules, the input space is partitioned with the use of Fuzzy C-Means (FCM) clustering. In the conclusion part of the fuzzy rules, the connections (weights) of the RBF NNs are represented by four kinds of polynomials such as constant, linear, quadratic, and reduced quadratic. The values of the coefficients are determined by running a gradient descent method. The output of the RBF NNs model is obtained by running a fuzzy inference method. The essential design parameters of the network (including learning rate, momentum coefficient and fuzzification coefficient used by the FCM) are optimized by means of Differential Evolution (DE). The proposed P-RBF NNs (Polynomial based RBF NNs) are applied to facial recognition and its performance is quantified from the viewpoint of the output performance and recognition rate. PMID:26163042
NASA Astrophysics Data System (ADS)
Wu, Zhishen; Xu, Bin
2003-07-01
A structural parametric identification strategy based on neural networks algorithms using dynamic macro-strain measurements in time domain from a long-gage strain sensor by fiber optic sensing technique such as Fiber Bragg Grating (FBG) sensor is developed. An array of long-gage sensors is bounded on the structure to measure reliably and accurately macro-strains. By the proposed methodology, the structural parameter of stiffness can be identified. A beam model with known mass distribution is considered as an object structure. Without any eigenvalue analysis or optimization computation, the structural parameter of stiffness can be identified. First an emulator neural network is presented to identify the beam structure in current state. Free vibration macro-strain responses of the beam structure are used to train the emulator neural network. The trained emulator neural network can be used to forecast the free vibration macro-strain response of the beam structure with enough precision and decide the difference between the free vibration macro-strain responses of other assumed structure with different structural parameters and those of the original beam structure. The root mean square (RMS) error vector is presented to evaluate the difference. Subsequently, corresponding to each assumed structure with different structural parameters, the RMS error vector can be calculated. By using the training data set composed of the structural parameters and RMS error vector, a parametric evaluation neural network is trained. A beam structure is considered as an existing structure, based on the trained parametric evaluation neural network, the stiffness of the beam structure can be forecast. It is shown that the parametric identification strategy using macro-strain measurement from long-gage sensors has the potential of being a practical tool for a health monitoring methodology applied to civil engineering structures.
Howell, J.A.; Whiteson, R.
1992-08-01
Detection of anomalies in nuclear safeguards and computer security systems is a tedious and time-consuming task. It typically requires the examination of large amounts of data for unusual patterns of activity. Neural networks provide a flexible pattern-recognition capability that can easily be adapted for these purposes. In this paper, we discuss architectures for accomplishing this task.
Howell, J.A.; Whiteson, R.
1992-01-01
Detection of anomalies in nuclear safeguards and computer security systems is a tedious and time-consuming task. It typically requires the examination of large amounts of data for unusual patterns of activity. Neural networks provide a flexible pattern-recognition capability that can easily be adapted for these purposes. In this paper, we discuss architectures for accomplishing this task.
ERIC Educational Resources Information Center
Chen, Hsinchun
1995-01-01
Presents an overview of artificial-intelligence-based inductive learning techniques and their use in information science research. Three methods are discussed: the connectionist Hopfield network; the symbolic ID3/ID5R; evolution-based genetic algorithms. The knowledge representations and algorithms of these methods are examined in the context of…
NASA Technical Reports Server (NTRS)
Baram, Yoram
1992-01-01
Report presents analysis of nested neural networks, consisting of interconnected subnetworks. Analysis based on simplified mathematical models more appropriate for artificial electronic neural networks, partly applicable to biological neural networks. Nested structure allows for retrieval of individual subpatterns. Requires fewer wires and connection devices than fully connected networks, and allows for local reconstruction of damaged subnetworks without rewiring entire network.
A flexible and robust neural network IASI-NH3 retrieval algorithm
NASA Astrophysics Data System (ADS)
Whitburn, S.; Van Damme, M.; Clarisse, L.; Bauduin, S.; Heald, C. L.; Hadji-Lazaro, J.; Hurtmans, D.; Zondlo, M. A.; Clerbaux, C.; Coheur, P.-F.
2016-06-01
In this paper, we describe a new flexible and robust NH3 retrieval algorithm from measurements of the Infrared Atmospheric Sounding Interferometer (IASI). The method is based on the calculation of a spectral hyperspectral range index (HRI) and subsequent conversion to NH3 columns via a neural network. It is an extension of the method presented in Van Damme et al. (2014a) who used lookup tables (LUT) for the radiance-concentration conversion. The new method inherits the advantages of the LUT-based method while providing several significant improvements. These include the following: (1) Complete temperature and humidity vertical profiles can be accounted for. (2) Third-party NH3 vertical profile information can be used. (3) Reported positive biases of LUT retrieval are reduced, and finally (4) a full measurement uncertainty characterization is provided. A running theme in this study, related to item (2), is the importance of the assumed vertical NH3 profile. We demonstrate the advantages of allowing variable profile shapes in the retrieval. As an example, we analyze how the retrievals change when all NH3 is assumed to be confined to the boundary layer. We analyze different averaging procedures in use for NH3 in the literature, introduced to cope with the variable measurement sensitivity and derive global averaged distributions for the year 2013. A comparison with a GEOS-Chem modeled global distribution is also presented, showing a general good correspondence (within ±3 × 1015 molecules.cm-2) over most of the Northern Hemisphere. However, IASI finds mean columns about 1-1.5 × 1016 molecules.cm-2 (˜50-60%) lower than GEOS-Chem for India and the North China plain.
Fuzzy-Kohonen-clustering neural network trained by genetic algorithm and fuzzy competition learning
NASA Astrophysics Data System (ADS)
Xie, Weixing; Li, Wenhua; Gao, Xinbo
1995-08-01
Kohonen networks are well known for clustering analysis. Classical Kohonen networks for hard c-means clustering (trained by winner-take-all learning) have some severe drawbacks. Fuzzy Kohonen networks (FKCNN) for fuzzy c-means clustering are trained by fuzzy competition learning, and can get better clustering results than the classical Kohonen networks. However, both winner-take-all and fuzzy competition learning algorithms are in essence local search techniques that search for the optimum by using a hill-climbing technique. Thus, they often fail in the search for the global optimum. In this paper we combine genetic algorithms (GAs) with fuzzy competition learning to train the FKCNN. Our experimental results show that the proposed GA/FC learning algorithm has much higher probabilities of finding the global optimal solutions than either the winner-take-all or the fuzzy competition learning.
Neural Networks and Micromechanics
NASA Astrophysics Data System (ADS)
Kussul, Ernst; Baidyk, Tatiana; Wunsch, Donald C.
The title of the book, "Neural Networks and Micromechanics," seems artificial. However, the scientific and technological developments in recent decades demonstrate a very close connection between the two different areas of neural networks and micromechanics. The purpose of this book is to demonstrate this connection. Some artificial intelligence (AI) methods, including neural networks, could be used to improve automation system performance in manufacturing processes. However, the implementation of these AI methods within industry is rather slow because of the high cost of conducting experiments using conventional manufacturing and AI systems. To lower the cost, we have developed special micromechanical equipment that is similar to conventional mechanical equipment but of much smaller size and therefore of lower cost. This equipment could be used to evaluate different AI methods in an easy and inexpensive way. The proved methods could be transferred to industry through appropriate scaling. In this book, we describe the prototypes of low cost microequipment for manufacturing processes and the implementation of some AI methods to increase precision, such as computer vision systems based on neural networks for microdevice assembly and genetic algorithms for microequipment characterization and the increase of microequipment precision.
Edupuganti, Sirisha; Sathish, Thadikamala
2014-01-01
Alpha-galactosidase production in submerged fermentation by Acinetobacter sp. was optimized using feed forward neural networks and genetic algorithm (FFNN-GA). Six different parameters, pH, temperature, agitation speed, carbon source (raffinose), nitrogen source (tryptone), and K2HPO4, were chosen and used to construct 6-10-1 topology of feed forward neural network to study interactions between fermentation parameters and enzyme yield. The predicted values were further optimized by genetic algorithm (GA). The predictability of neural networks was further analysed by using mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and R2-value for training and testing data. Using hybrid neural networks and genetic algorithm, alpha-galactosidase production was improved from 7.5 U/mL to 10.2 U/mL. PMID:25254205
Deinterlacing using modular neural network
NASA Astrophysics Data System (ADS)
Woo, Dong H.; Eom, Il K.; Kim, Yoo S.
2004-05-01
Deinterlacing is the conversion process from the interlaced scan to progressive one. While many previous algorithms that are based on weighted-sum cause blurring in edge region, deinterlacing using neural network can reduce the blurring through recovering of high frequency component by learning process, and is found robust to noise. In proposed algorithm, input image is divided into edge and smooth region, and then, to each region, one neural network is assigned. Through this process, each neural network learns only patterns that are similar, therefore it makes learning more effective and estimation more accurate. But even within each region, there are various patterns such as long edge and texture in edge region. To solve this problem, modular neural network is proposed. In proposed modular neural network, two modules are combined in output node. One is for low frequency feature of local area of input image, and the other is for high frequency feature. With this structure, each modular neural network can learn different patterns with compensating for drawback of counterpart. Therefore it can adapt to various patterns within each region effectively. In simulation, the proposed algorithm shows better performance compared with conventional deinterlacing methods and single neural network method.
NASA Astrophysics Data System (ADS)
Ganapol, B. D.; Furfaro, R.; Johnson, L. F.; Herwitz, S. R.
2003-12-01
Over the past two years, NASA has had great interest in exploring the economic potential of deploying UAVs (Unmanned Aerial Vehicles) as long-duration platforms equipped with high resolution imaging systems for commercial agricultural applications. In October 2002, a team in the Ecosystem Science and Technology Branch at NASA/Ames Research Center prepared and successfully flew a UAV, equipped with off-the-shelf camera systems, over coffee plantations at Kauai (Hawaii). The idea is to help growers to find the best possible harvesting strategy. The most important information that needs to be conveyed to the growers is the percentage of ripe, unripe and overripe cherries in the field. It is of vital importance to devise a robust and reliable "intelligent "algorithm capable of predicting the amount of ripe cherries present in any digital image coming from the onboard cameras. During the campaign, the two UAV camera systems produced digital images that contain information about the down-looking plantation field. These images need to be processed to extract information concerning the percentage of ripe (yellow) cherries. To date, no robust automated algorithm has been developed to perform this task. Currently, every image is viewed by human eyes on a case by case basis. We propose a neural network algorithm that can automate the process in an intelligent way. Biologically inspired Neural Networks are made of elements called "neurons" that can simulate the brain activity during a learning process. The idea is to design an appropriate neural network that learns the relation between the reflectance coming from an image and the percentage of cherries present in a coffee field. We envision a situation in which reflectance from digital images at different wavebands is processed by a trained neural network and the percentage of the different cherries estimated. The key factor is training the network to recognize the reflectance/cherry percentage relation. Over the past few
Ritter, G.X.; Sussner, P.
1996-12-31
The theory of artificial neural networks has been successfully applied to a wide variety of pattern recognition problems. In this theory, the first step in computing the next state of a neuron or in performing the next layer neural network computation involves the linear operation of multiplying neural values by their synaptic strengths and adding the results. Thresholding usually follows the linear operation in order to provide for nonlinearity of the network. In this paper we introduce a novel class of neural networks, called morphological neural networks, in which the operations of multiplication and addition are replaced by addition and maximum (or minimum), respectively. By taking the maximum (or minimum) of sums instead of the sum of products, morphological network computation is nonlinear before thresholding. As a consequence, the properties of morphological neural networks are drastically different than those of traditional neural network models. In this paper we consider some of these differences and provide some particular examples of morphological neural network.
Neural-Network-Development Program
NASA Technical Reports Server (NTRS)
Phillips, Todd A.
1993-01-01
NETS, software tool for development and evaluation of neural networks, provides simulation of neural-network algorithms plus computing environment for development of such algorithms. Uses back-propagation learning method for all of networks it creates. Enables user to customize patterns of connections between layers of network. Also provides features for saving, during learning process, values of weights, providing more-precise control over learning process. Written in ANSI standard C language. Machine-independent version (MSC-21588) includes only code for command-line-interface version of NETS 3.0.
Neural networks and MIMD-multiprocessors
NASA Technical Reports Server (NTRS)
Vanhala, Jukka; Kaski, Kimmo
1990-01-01
Two artificial neural network models are compared. They are the Hopfield Neural Network Model and the Sparse Distributed Memory model. Distributed algorithms for both of them are designed and implemented. The run time characteristics of the algorithms are analyzed theoretically and tested in practice. The storage capacities of the networks are compared. Implementations are done using a distributed multiprocessor system.
NASA Technical Reports Server (NTRS)
Peck, Charles C.; Dhawan, Atam P.; Meyer, Claudia M.
1991-01-01
A genetic algorithm is used to select the inputs to a neural network function approximator. In the application considered, modeling critical parameters of the space shuttle main engine (SSME), the functional relationship between measured parameters is unknown and complex. Furthermore, the number of possible input parameters is quite large. Many approaches have been used for input selection, but they are either subjective or do not consider the complex multivariate relationships between parameters. Due to the optimization and space searching capabilities of genetic algorithms they were employed to systematize the input selection process. The results suggest that the genetic algorithm can generate parameter lists of high quality without the explicit use of problem domain knowledge. Suggestions for improving the performance of the input selection process are also provided.
Fu, Xingang; Li, Shuhui; Fairbank, Michael; Wunsch, Donald C; Alonso, Eduardo
2015-09-01
This paper investigates how to train a recurrent neural network (RNN) using the Levenberg-Marquardt (LM) algorithm as well as how to implement optimal control of a grid-connected converter (GCC) using an RNN. To successfully and efficiently train an RNN using the LM algorithm, a new forward accumulation through time (FATT) algorithm is proposed to calculate the Jacobian matrix required by the LM algorithm. This paper explores how to incorporate FATT into the LM algorithm. The results show that the combination of the LM and FATT algorithms trains RNNs better than the conventional backpropagation through time algorithm. This paper presents an analytical study on the optimal control of GCCs, including theoretically ideal optimal and suboptimal controllers. To overcome the inapplicability of the optimal GCC controller under practical conditions, a new RNN controller with an improved input structure is proposed to approximate the ideal optimal controller. The performance of an ideal optimal controller and a well-trained RNN controller was compared in close to real-life power converter switching environments, demonstrating that the proposed RNN controller can achieve close to ideal optimal control performance even under low sampling rate conditions. The excellent performance of the proposed RNN controller under challenging and distorted system conditions further indicates the feasibility of using an RNN to approximate optimal control in practical applications. PMID:25330496
Jiang, Xiaoming; Van den Broek, Wouter; Koch, Christoph T
2016-04-01
Inverse dynamical photon scattering (IDPS), an artificial neural network based algorithm for three-dimensional quantitative imaging in optical microscopy, is introduced. Because the inverse problem entails numerical minimization of an explicit error metric, it becomes possible to freely choose a more robust metric, to introduce regularization of the solution, and to retrieve unknown experimental settings or microscope values, while the starting guess is simply set to zero. The regularization is accomplished through an alternate directions augmented Lagrangian approach, implemented on a graphics processing unit. These improvements are demonstrated on open source experimental data, retrieving three-dimensional amplitude and phase for a thick specimen. PMID:27136994
Knowledge Discovery in Medical Mining by using Genetic Algorithms and Artificial Neural Networks
NASA Astrophysics Data System (ADS)
Srivathsa, P. K.
2011-12-01
Medical Data mining could be thought of as the search for relationships and patterns within the medical data, which facilitates the acquisition of useful knowledge for effective medical diagnosis. Consequently, the predictability of disease will become more effective and the early detection of disease certainly facilitates an increased exposure to required patient care with focused treatment, economic feasibility and improved cure rates. So, the present investigation is carried on medical data(PIMA) using DM and GA based Neural Network technique and the results predict that the methodology is not only reliable but also helps in furthering the scope of the subject.
NASA Astrophysics Data System (ADS)
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.
NASA Astrophysics Data System (ADS)
Huang, Ying; Jin, Long
2013-08-01
A western North Pacific tropical cyclone (TC) intensity prediction scheme has been developed based on climatology and persistence (CLIPER) factors as potential predictors and using genetic neural network (GNN) model. TC samples during June-October spanning 2001-2010 are used for model development. The GNN model input is constructed from potential predictors by employing both a stepwise regression method and an Isometric Mapping (Isomap) algorithm. The Isomap algorithm is capable of finding meaningful low-dimensional architectures hidden in their nonlinear high-dimensional data space and separating the underlying factors. In this scheme, the new developed model, which is termed the GNN-Isomap model, is used for monthly TC intensity prediction at 24- and 48-h lead times. Using identical modeling samples and independent samples, predictions of the GNN-Isomap model are compared with the widely used CLIPER method. By adopting different numbers of nearest neighbors, results of sensitivity experiments show that the mean absolute prediction errors of the independent samples using GNN-Isomap model at 24- and 48-h forecasts are smaller than those using CLIPER method. Positive skills are obtained as compared to the CLIPER method with being above 12 % at 24 h and above 14 % at 48 h. Analyses of the new scheme suggest that the useful linear and nonlinear prediction information of the full pool of potential predictors is excavated in terms of the stepwise regression method and the Isomap algorithm. Moreover, the GNN is built by integrating multiple individual neural networks with the same expected output and network architecture is optimized by an evolutionary genetic algorithm, so the generalization capacity of the GNN-Isomap model is significantly enhanced, indicating a potentially better operational weather prediction.
NASA Astrophysics Data System (ADS)
Riha, Stefan; Krawczyk, Harald
2011-11-01
Water quality monitoring in the Baltic Sea is of high ecological importance for all its neighbouring countries. They are highly interested in a regular monitoring of water quality parameters of their regional zones. A special attention is paid to the occurrence and dissemination of algae blooms. Among the appearing blooms the possibly toxicological or harmful cyanobacteria cultures are a special case of investigation, due to their specific optical properties and due to the negative influence on the ecological state of the aquatic system. Satellite remote sensing, with its high temporal and spatial resolution opportunities, allows the frequent observations of large areas of the Baltic Sea with special focus on its two seasonal algae blooms. For a better monitoring of the cyanobacteria dominated summer blooms, adapted algorithms are needed which take into account the special optical properties of blue-green algae. Chlorophyll-a standard algorithms typically fail in a correct recognition of these occurrences. To significantly improve the opportunities of observation and propagation of the cyanobacteria blooms, the Marine Remote Sensing group of DLR has started the development of a model based inversion algorithm that includes a four component bio-optical water model for Case2 waters, which extends the commonly calculated parameter set chlorophyll, Suspended Matter and CDOM with an additional parameter for the estimation of phycocyanin absorption. It was necessary to carry out detailed optical laboratory measurements with different cyanobacteria cultures, occurring in the Baltic Sea, for the generation of a specific bio-optical model. The inversion of satellite remote sensing data is based on an artificial Neural Network technique. This is a model based multivariate non-linear inversion approach. The specifically designed Neural Network is trained with a comprehensive dataset of simulated reflectance values taking into account the laboratory obtained specific optical
Metzler, R; Kinzel, W; Kanter, I
2000-08-01
Several scenarios of interacting neural networks which are trained either in an identical or in a competitive way are solved analytically. In the case of identical training each perceptron receives the output of its neighbor. The symmetry of the stationary state as well as the sensitivity to the used training algorithm are investigated. Two competitive perceptrons trained on mutually exclusive learning aims and a perceptron which is trained on the opposite of its own output are examined analytically. An ensemble of competitive perceptrons is used as decision-making algorithms in a model of a closed market (El Farol Bar problem or the Minority Game. In this game, a set of agents who have to make a binary decision is considered.); each network is trained on the history of minority decisions. This ensemble of perceptrons relaxes to a stationary state whose performance can be better than random. PMID:11088736
Salari, Nader; Shohaimi, Shamarina; Najafi, Farid; Nallappan, Meenakshii; Karishnarajah, Isthrinayagy
2014-01-01
Among numerous artificial intelligence approaches, k-Nearest Neighbor algorithms, genetic algorithms, and artificial neural networks are considered as the most common and effective methods in classification problems in numerous studies. In the present study, the results of the implementation of a novel hybrid feature selection-classification model using the above mentioned methods are presented. The purpose is benefitting from the synergies obtained from combining these technologies for the development of classification models. Such a combination creates an opportunity to invest in the strength of each algorithm, and is an approach to make up for their deficiencies. To develop proposed model, with the aim of obtaining the best array of features, first, feature ranking techniques such as the Fisher's discriminant ratio and class separability criteria were used to prioritize features. Second, the obtained results that included arrays of the top-ranked features were used as the initial population of a genetic algorithm to produce optimum arrays of features. Third, using a modified k-Nearest Neighbor method as well as an improved method of backpropagation neural networks, the classification process was advanced based on optimum arrays of the features selected by genetic algorithms. The performance of the proposed model was compared with thirteen well-known classification models based on seven datasets. Furthermore, the statistical analysis was performed using the Friedman test followed by post-hoc tests. The experimental findings indicated that the novel proposed hybrid model resulted in significantly better classification performance compared with all 13 classification methods. Finally, the performance results of the proposed model was benchmarked against the best ones reported as the state-of-the-art classifiers in terms of classification accuracy for the same data sets. The substantial findings of the comprehensive comparative study revealed that performance of the
NASA Astrophysics Data System (ADS)
Abbasi Hoseini, Afshin; Zavareh, Zahra; Lundell, Fredrik; Anderson, Helge I.
2014-04-01
A matching algorithm based on self-organizing map (SOM) neural network is proposed for tracking rod-like particles in 2D optical measurements of dispersed two-phase flows. It is verified by both synthetic images of elongated particles mimicking 2D suspension flows and direct numerical simulations-based results of prolate particles dispersed in a turbulent channel flow. Furthermore, the potential benefit of this algorithm is evaluated by applying it to the experimental data of rod-like fibers tracking in wall turbulence. The study of the behavior of elongated particles suspended in turbulent flows has a practical importance and covers a wide range of applications in engineering and science. In experimental approach, particle tracking velocimetry of the dispersed phase has a key role together with particle image velocimetry of the carrier phase to obtain the velocities of both phases. The essential parts of particle tracking are to identify and match corresponding particles correctly in consecutive images. The present study is focused on the development of an algorithm for pairing non-spherical particles that have one major symmetry axis. The novel idea in the algorithm is to take the orientation of the particles into account for matching in addition to their positions. The method used is based on the SOM neural network that finds the most likely matching link in images on the basis of feature extraction and clustering. The fundamental concept is finding corresponding particles in the images with the nearest characteristics: position and orientation. The most effective aspect of this two-frame matching algorithm is that it does not require any preliminary knowledge of neither the flow field nor the particle behavior. Furthermore, using one additional characteristic of the non-spherical particles, namely their orientation, in addition to its coordinate vector, the pairing is improved both for more reliable matching at higher concentrations of dispersed particles and
Salari, Nader; Shohaimi, Shamarina; Najafi, Farid; Nallappan, Meenakshii; Karishnarajah, Isthrinayagy
2014-01-01
Among numerous artificial intelligence approaches, k-Nearest Neighbor algorithms, genetic algorithms, and artificial neural networks are considered as the most common and effective methods in classification problems in numerous studies. In the present study, the results of the implementation of a novel hybrid feature selection-classification model using the above mentioned methods are presented. The purpose is benefitting from the synergies obtained from combining these technologies for the development of classification models. Such a combination creates an opportunity to invest in the strength of each algorithm, and is an approach to make up for their deficiencies. To develop proposed model, with the aim of obtaining the best array of features, first, feature ranking techniques such as the Fisher's discriminant ratio and class separability criteria were used to prioritize features. Second, the obtained results that included arrays of the top-ranked features were used as the initial population of a genetic algorithm to produce optimum arrays of features. Third, using a modified k-Nearest Neighbor method as well as an improved method of backpropagation neural networks, the classification process was advanced based on optimum arrays of the features selected by genetic algorithms. The performance of the proposed model was compared with thirteen well-known classification models based on seven datasets. Furthermore, the statistical analysis was performed using the Friedman test followed by post-hoc tests. The experimental findings indicated that the novel proposed hybrid model resulted in significantly better classification performance compared with all 13 classification methods. Finally, the performance results of the proposed model was benchmarked against the best ones reported as the state-of-the-art classifiers in terms of classification accuracy for the same data sets. The substantial findings of the comprehensive comparative study revealed that performance of the
Liu, Yu; Xia, Jun; Shi, Chun-Xiang; Hong, Yang
2009-01-01
The crowning objective of this research was to identify a better cloud classification method to upgrade the current window-based clustering algorithm used operationally for China's first operational geostationary meteorological satellite FengYun-2C (FY-2C) data. First, the capabilities of six widely-used Artificial Neural Network (ANN) methods are analyzed, together with the comparison of two other methods: Principal Component Analysis (PCA) and a Support Vector Machine (SVM), using 2864 cloud samples manually collected by meteorologists in June, July, and August in 2007 from three FY-2C channel (IR1, 10.3-11.3 μm; IR2, 11.5-12.5 μm and WV 6.3-7.6 μm) imagery. The result shows that: (1) ANN approaches, in general, outperformed the PCA and the SVM given sufficient training samples and (2) among the six ANN networks, higher cloud classification accuracy was obtained with the Self-Organizing Map (SOM) and Probabilistic Neural Network (PNN). Second, to compare the ANN methods to the present FY-2C operational algorithm, this study implemented SOM, one of the best ANN network identified from this study, as an automated cloud classification system for the FY-2C multi-channel data. It shows that SOM method has improved the results greatly not only in pixel-level accuracy but also in cloud patch-level classification by more accurately identifying cloud types such as cumulonimbus, cirrus and clouds in high latitude. Findings of this study suggest that the ANN-based classifiers, in particular the SOM, can be potentially used as an improved Automated Cloud Classification Algorithm to upgrade the current window-based clustering method for the FY-2C operational products. PMID:22346714
Liu, Yu; Xia, Jun; Shi, Chun-Xiang; Hong, Yang
2009-01-01
The crowning objective of this research was to identify a better cloud classification method to upgrade the current window-based clustering algorithm used operationally for China’s first operational geostationary meteorological satellite FengYun-2C (FY-2C) data. First, the capabilities of six widely-used Artificial Neural Network (ANN) methods are analyzed, together with the comparison of two other methods: Principal Component Analysis (PCA) and a Support Vector Machine (SVM), using 2864 cloud samples manually collected by meteorologists in June, July, and August in 2007 from three FY-2C channel (IR1, 10.3–11.3 μm; IR2, 11.5–12.5 μm and WV 6.3–7.6 μm) imagery. The result shows that: (1) ANN approaches, in general, outperformed the PCA and the SVM given sufficient training samples and (2) among the six ANN networks, higher cloud classification accuracy was obtained with the Self-Organizing Map (SOM) and Probabilistic Neural Network (PNN). Second, to compare the ANN methods to the present FY-2C operational algorithm, this study implemented SOM, one of the best ANN network identified from this study, as an automated cloud classification system for the FY-2C multi-channel data. It shows that SOM method has improved the results greatly not only in pixel-level accuracy but also in cloud patch-level classification by more accurately identifying cloud types such as cumulonimbus, cirrus and clouds in high latitude. Findings of this study suggest that the ANN-based classifiers, in particular the SOM, can be potentially used as an improved Automated Cloud Classification Algorithm to upgrade the current window-based clustering method for the FY-2C operational products. PMID:22346714
Wang, Libing; Mao, Chengxiong; Wang, Dan; Lu, Jiming; Zhang, Junfeng; Chen, Xun
2014-01-01
In order to control the cascaded H-bridges (CHB) converter with staircase modulation strategy in a real-time manner, a real-time and closed-loop control algorithm based on artificial neural network (ANN) for three-phase CHB converter is proposed in this paper. It costs little computation time and memory. It has two steps. In the first step, hierarchical particle swarm optimizer with time-varying acceleration coefficient (HPSO-TVAC) algorithm is employed to minimize the total harmonic distortion (THD) and generate the optimal switching angles offline. In the second step, part of optimal switching angles are used to train an ANN and the well-designed ANN can generate optimal switching angles in a real-time manner. Compared with previous real-time algorithm, the proposed algorithm is suitable for a wider range of modulation index and results in a smaller THD and a lower calculation time. Furthermore, the well-designed ANN is embedded into a closed-loop control algorithm for CHB converter with variable direct voltage (DC) sources. Simulation results demonstrate that the proposed closed-loop control algorithm is able to quickly stabilize load voltage and minimize the line current's THD (<5%) when subjecting the DC sources disturbance or load disturbance. In real design stage, a switching angle pulse generation scheme is proposed and experiment results verify its correctness. PMID:24772025
Kepler, T.B.
1989-01-01
After a brief introduction to the techniques and philosophy of neural network modeling by spin glass inspired system, the author investigates several properties of these discrete models for autoassociative memory. Memories are represented as patterns of neural activity; their traces are stored in a distributed manner in the matrix of synaptic coupling strengths. Recall is dynamic, an initial state containing partial information about one of the memories evolves toward that memory. Activity in each neuron creates fields at every other neuron, the sum total of which determines its activity. By averaging over the space of interaction matrices with memory constraints enforced by the choice of measure, we show that the exist universality classes defined by families of field distributions and the associated network capacities. He demonstrates the dominant role played by the field distribution in determining the size of the domains of attraction and present, in two independent ways, an expression for this size. He presents a class of convergent learning algorithms which improve upon known algorithms for producing such interaction matrices. He demonstrates that spurious states, or unexperienced memories, may be practically suppressed by the inducement of n-cycles and chaos. He investigates aspects of chaos in these systems, and then leave discrete modeling to implement the analysis of chaotic behavior on a continuous valued network realized in electronic hardware. In each section he combine analytical calculation and computer simulations.
NASA Technical Reports Server (NTRS)
Benediktsson, J. A.; Ersoy, O. K.; Swain, P. H.
1991-01-01
A neural network architecture called a consensual neural network (CNN) is proposed for the classification of data from multiple sources. Its relation to hierarchical and ensemble neural networks is discussed. CNN is based on the statistical consensus theory and uses nonlinearly transformed input data. The input data are transformed several times, and the different transformed data are applied as if they were independent inputs. The independent inputs are classified using stage neural networks and outputs from the stage networks are then weighted and combined to make a decision. Experimental results based on remote-sensing data and geographic data are given.
Keshavarz, M; Mojra, A
2015-05-01
Geometrical features of a cancerous tumor embedded in biological soft tissue, including tumor size and depth, are a necessity in the follow-up procedure and making suitable therapeutic decisions. In this paper, a new socio-politically motivated global search strategy which is called imperialist competitive algorithm (ICA) is implemented to train a feed forward neural network (FFNN) to estimate the tumor's geometrical characteristics (FFNNICA). First, a viscoelastic model of liver tissue is constructed by using a series of in vitro uniaxial and relaxation test data. Then, 163 samples of the tissue including a tumor with different depths and diameters are generated by making use of PYTHON programming to link the ABAQUS and MATLAB together. Next, the samples are divided into 123 samples as training dataset and 40 samples as testing dataset. Training inputs of the network are mechanical parameters extracted from palpation of the tissue through a developing noninvasive technology called artificial tactile sensing (ATS). Last, to evaluate the FFNNICA performance, outputs of the network including tumor's depth and diameter are compared with desired values for both training and testing datasets. Deviations of the outputs from desired values are calculated by a regression analysis. Statistical analysis is also performed by measuring Root Mean Square Error (RMSE) and Efficiency (E). RMSE in diameter and depth estimations are 0.50 mm and 1.49, respectively, for the testing dataset. Results affirm that the proposed optimization algorithm for training neural network can be useful to characterize soft tissue tumors accurately by employing an artificial palpation approach. PMID:25645966
NASA Astrophysics Data System (ADS)
Le, Hieu The
This thesis develops a new method to detect delaminations in composite laminates using a combination of finite element method, artificial neural networks, and genetic algorithms. Next, this newly developed method is applied to successfully solve delamination detection problems. Delaminations in a composite laminate with various sizes and locations are considered in the present studies. The improved layerwise shear deformation theory is implemented into the finite element method and used to calculate responses of laminates with single and multiple delaminations. Mappings between the natural frequencies and delamination characteristics are first determined from the developed models. These data are then used to train artificial neural networks of multiplayer perceptron using back-propagation. These trained artificial neural networks are in turn used as an approximate tool to calculate the responses of the delaminated laminates and to feed the data to the delamination detection process. Two different approaches for handling the neural network models are applied in the work and are presented for comparison. The delamination detection problem is formulated as an optimization problem with mixed type design variables. A genetic algorithm, which is a guided probabilistic search technique based on the simulation of Darwin's principle of evolution and natural selection, is developed to solve this optimization problem. Single through-the-width delamination, single internal delamination, and multiple through-the-width delaminations are separately considered for detection study. At last, the application is extended to the most challenging problem, which is the detection of general delamination. Various factors affecting the detection process such as the finite element convergence factor and the laminate geometry factor are also examined. Case studies are made and the findings are summarized in detail in each chapter of the dissertation. It is found that the newly developed
Wang, Jie-sheng; Han, Shuang; Shen, Na-na; Li, Shu-xia
2014-01-01
For meeting the forecasting target of key technology indicators in the flotation process, a BP neural network soft-sensor model based on features extraction of flotation froth images and optimized by shuffled cuckoo search algorithm is proposed. Based on the digital image processing technique, the color features in HSI color space, the visual features based on the gray level cooccurrence matrix, and the shape characteristics based on the geometric theory of flotation froth images are extracted, respectively, as the input variables of the proposed soft-sensor model. Then the isometric mapping method is used to reduce the input dimension, the network size, and learning time of BP neural network. Finally, a shuffled cuckoo search algorithm is adopted to optimize the BP neural network soft-sensor model. Simulation results show that the model has better generalization results and prediction accuracy. PMID:25133210
Wang, Jie-sheng; Han, Shuang; Shen, Na-na; Li, Shu-xia
2014-01-01
For meeting the forecasting target of key technology indicators in the flotation process, a BP neural network soft-sensor model based on features extraction of flotation froth images and optimized by shuffled cuckoo search algorithm is proposed. Based on the digital image processing technique, the color features in HSI color space, the visual features based on the gray level cooccurrence matrix, and the shape characteristics based on the geometric theory of flotation froth images are extracted, respectively, as the input variables of the proposed soft-sensor model. Then the isometric mapping method is used to reduce the input dimension, the network size, and learning time of BP neural network. Finally, a shuffled cuckoo search algorithm is adopted to optimize the BP neural network soft-sensor model. Simulation results show that the model has better generalization results and prediction accuracy. PMID:25133210
Cheng, Jie; Xiao, Qing; Li, Xiao-Wen; Liu, Qin-Huo; Du, Yong-Ming
2008-04-01
The present paper firstly points out the defect of typical temperature and emissivity separation algorithms when dealing with hyperspectral FTIR data: the conventional temperature and emissivity algorithms can not reproduce correct emissivity value when the difference between the ground-leaving radiance and object's blackbody radiation at its true temperature and the instrument random noise are on the same order, and this phenomenon is very prone to occur rence near 714 and 1 250 cm(-1) in the field measurements. In order to settle this defect, a three-layer perceptron neural network has been introduced into the simultaneous inversion of temperature and emissivity from hyperspectral FTIR data. The soil emissivity spectra from the ASTER spectral library were used to produce the training data, the soil emissivity spectra from the MODIS spectral library were used to produce the test data, and the result of network test shows the MLP is robust. Meanwhile, the ISSTES algorithm was used to retrieve the temperature and emissivity form the test data. By comparing the results of MLP and ISSTES, we found the MLP can overcome the disadvantage of typical temperature and emisivity separation, although the rmse of derived emissivity using MLP is lower than the ISSTES as a whole. Hence, the MLP can be regarded as a beneficial complementarity of the typical temperature and emissivity separation. PMID:18619297
Exploring neural network technology
Naser, J.; Maulbetsch, J.
1992-12-01
EPRI is funding several projects to explore neural network technology, a form of artificial intelligence that some believe may mimic the way the human brain processes information. This research seeks to provide a better understanding of fundamental neural network characteristics and to identify promising utility industry applications. Results to date indicate that the unique attributes of neural networks could lead to improved monitoring, diagnostic, and control capabilities for a variety of complex utility operations. 2 figs.
NASA Astrophysics Data System (ADS)
Arnaout, A.; Fruhwirth, R.; Winter, M.; Esmael, B.; Thonhauser, G.
2012-04-01
The use of neural networks and advanced machine learning techniques in the oil & gas industry is a growing trend in the market. Especially in drilling oil & gas wells, prediction and monitoring different drilling parameters is an essential task to prevent serious problems like "Kick", "Lost Circulation" or "Stuck Pipe" among others. The hookload represents the weight load of the drill string at the crane hook. It is one of the most important parameters. During drilling the parameter "Weight on Bit" is controlled by the driller whereby the hookload is the only measure to monitor how much weight on bit is applied to the bit to generate the hole. Any changes in weight on bit will be directly reflected at the hookload. Furthermore any unwanted contact between the drill string and the wellbore - potentially leading to stuck pipe problem - will appear directly in the measurements of the hookload. Therefore comparison of the measured to the predicted hookload will not only give a clear idea on what is happening down-hole, it also enables the prediction of a number of important events that may cause problems in the borehole and yield in some - fortunately rare - cases in catastrophes like blow-outs. Heuristic models using highly sophisticated neural networks were designed for the hookload prediction; the training data sets were prepared in cooperation with drilling experts. Sensor measurements as well as a set of derived feature channels were used as input to the models. The contents of the final data set can be separated into (1) features based on rig operation states, (2) real-time sensors features and (3) features based on physics. A combination of novel neural network architecture - the Completely Connected Perceptron and parallel learning techniques which avoid trapping into local error minima - was used for building the models. In addition automatic network growing algorithms and highly sophisticated stopping criterions offer robust and efficient estimation of the
Data-based system modeling using a type-2 fuzzy neural network with a hybrid learning algorithm.
Yeh, Chi-Yuan; Jeng, Wen-Hau Roger; Lee, Shie-Jue
2011-12-01
We propose a novel approach for building a type-2 neural-fuzzy system from a given set of input-output training data. A self-constructing fuzzy clustering method is used to partition the training dataset into clusters through input-similarity and output-similarity tests. The membership function associated with each cluster is defined with the mean and deviation of the data points included in the cluster. Then a type-2 fuzzy Takagi-Sugeno-Kang IF-THEN rule is derived from each cluster to form a fuzzy rule base. A fuzzy neural network is constructed accordingly and the associated parameters are refined by a hybrid learning algorithm which incorporates particle swarm optimization and a least squares estimation. For a new input, a corresponding crisp output of the system is obtained by combining the inferred results of all the rules into a type-2 fuzzy set, which is then defuzzified by applying a refined type reduction algorithm. Experimental results are presented to demonstrate the effectiveness of our proposed approach. PMID:22010148
Moteghaed, Niloofar Yousefi; Maghooli, Keivan; Pirhadi, Shiva; Garshasbi, Masoud
2015-01-01
The improvement of high-through-put gene profiling based microarrays technology has provided monitoring the expression value of thousands of genes simultaneously. Detailed examination of changes in expression levels of genes can help physicians to have efficient diagnosing, classification of tumors and cancer's types as well as effective treatments. Finding genes that can classify the group of cancers correctly based on hybrid optimization algorithms is the main purpose of this paper. In this paper, a hybrid particle swarm optimization and genetic algorithm method are used for gene selection and also artificial neural network (ANN) is adopted as the classifier. In this work, we have improved the ability of the algorithm for the classification problem by finding small group of biomarkers and also best parameters of the classifier. The proposed approach is tested on three benchmark gene expression data sets: Blood (acute myeloid leukemia, acute lymphoblastic leukemia), colon and breast datasets. We used 10-fold cross-validation to achieve accuracy and also decision tree algorithm to find the relation between the biomarkers for biological point of view. To test the ability of the trained ANN models to categorize the cancers, we analyzed additional blinded samples that were not previously used for the training procedure. Experimental results show that the proposed method can reduce the dimension of the data set and confirm the most informative gene subset and improve classification accuracy with best parameters based on datasets. PMID:26120567
Moteghaed, Niloofar Yousefi; Maghooli, Keivan; Pirhadi, Shiva; Garshasbi, Masoud
2015-01-01
The improvement of high-through-put gene profiling based microarrays technology has provided monitoring the expression value of thousands of genes simultaneously. Detailed examination of changes in expression levels of genes can help physicians to have efficient diagnosing, classification of tumors and cancer's types as well as effective treatments. Finding genes that can classify the group of cancers correctly based on hybrid optimization algorithms is the main purpose of this paper. In this paper, a hybrid particle swarm optimization and genetic algorithm method are used for gene selection and also artificial neural network (ANN) is adopted as the classifier. In this work, we have improved the ability of the algorithm for the classification problem by finding small group of biomarkers and also best parameters of the classifier. The proposed approach is tested on three benchmark gene expression data sets: Blood (acute myeloid leukemia, acute lymphoblastic leukemia), colon and breast datasets. We used 10-fold cross-validation to achieve accuracy and also decision tree algorithm to find the relation between the biomarkers for biological point of view. To test the ability of the trained ANN models to categorize the cancers, we analyzed additional blinded samples that were not previously used for the training procedure. Experimental results show that the proposed method can reduce the dimension of the data set and confirm the most informative gene subset and improve classification accuracy with best parameters based on datasets. PMID:26120567
NASA Astrophysics Data System (ADS)
Yadav, Deepti; Arora, M. K.; Tiwari, K. C.; Ghosh, J. K.
2016-04-01
Hyperspectral imaging is a powerful tool in the field of remote sensing and has been used for many applications like mineral detection, detection of landmines, target detection etc. Major issues in target detection using HSI are spectral variability, noise, small size of the target, huge data dimensions, high computation cost, complex backgrounds etc. Many of the popular detection algorithms do not work for difficult targets like small, camouflaged etc. and may result in high false alarms. Thus, target/background discrimination is a key issue and therefore analyzing target's behaviour in realistic environments is crucial for the accurate interpretation of hyperspectral imagery. Use of standard libraries for studying target's spectral behaviour has limitation that targets are measured in different environmental conditions than application. This study uses the spectral data of the same target which is used during collection of the HSI image. This paper analyze spectrums of targets in a way that each target can be spectrally distinguished from a mixture of spectral data. Artificial neural network (ANN) has been used to identify the spectral range for reducing data and further its efficacy for improving target detection is verified. The results of ANN proposes discriminating band range for targets; these ranges were further used to perform target detection using four popular spectral matching target detection algorithm. Further, the results of algorithms were analyzed using ROC curves to evaluate the effectiveness of the ranges suggested by ANN over full spectrum for detection of desired targets. In addition, comparative assessment of algorithms is also performed using ROC.
Lin, Wei-Qi; Jiang, Jian-Hui; Zhou, Yan-Ping; Wu, Hai-Long; Shen, Guo-Li; Yu, Ru-Qin
2007-01-30
Multilayer feedforward neural networks (MLFNNs) are important modeling techniques widely used in QSAR studies for their ability to represent nonlinear relationships between descriptors and activity. However, the problems of overfitting and premature convergence to local optima still pose great challenges in the practice of MLFNNs. To circumvent these problems, a support vector machine (SVM) based training algorithm for MLFNNs has been developed with the incorporation of particle swarm optimization (PSO). The introduction of the SVM based training mechanism imparts the developed algorithm with inherent capacity for combating the overfitting problem. Moreover, with the implementation of PSO for searching the optimal network weights, the SVM based learning algorithm shows relatively high efficiency in converging to the optima. The proposed algorithm has been evaluated using the Hansch data set. Application to QSAR studies of the activity of COX-2 inhibitors is also demonstrated. The results reveal that this technique provides superior performance to backpropagation (BP) and PSO training neural networks. PMID:17186488
Optimization of the Blank Holder Force Using the Neural Network Algorithm
NASA Astrophysics Data System (ADS)
Albut, A.; Ciubotaru, V.; Radu, C.; Olaru, I.
2011-08-01
In case of sheet metal forming the main dimensional errors are caused by the springback phenomena. The present work deals with numerical simulation related to draw bending and springback of U-shaped parts. The current paper is trying to prove out the important role of the blank holder force variation during the forming process. The Dynaform 5.6 software was used to simulate the forming process, in which the blank holder force varies linearly in four steps between 20 and 50 kN. The factorial simulations test plan was made using the Design Experts 7.0 software and 72 simulations were necessarily to cover completely the variation domain. The part obtained after each simulation is analyzed and measured to quantify the errors caused by springback. Parameters as: angle between flange and sidewall, angle between sidewall and part bottom, chamfer radius between part bottom and sidewall or chamfer radius between sidewall and flange are recorded in a data base. The initial simulations plan together with the generated data base is loaded in a neural network software called NeuroSolution 5. The presented optimization method is a good method to reduce the springback effect. The inconvenient of this method is the large number of simulations tests that must be done and the large amount of data necessarily as input for the NeuroSolution software.
NASA Astrophysics Data System (ADS)
Fang, Ming-chung; Lee, Zi-yi
2013-08-01
This paper develops a nonlinear mathematical model to simulate the dynamic motion behavior of the barge equipped with the portable outboard Dynamic Positioning (DP) system in short-crested waves. The self-tuning Proportional-Derivative (PD) controller based on the neural network algorithm is applied to control the thrusters for optimal adjustment of the barge position in waves. In addition to the wave, the current, the wind and the nonlinear drift force are also considered in the calculations. The time domain simulations for the six-degree-of-freedom motions of the barge with the DP system are solved by the 4th order Runge-Kutta method which can compromise the efficiency and the accuracy of the simulations. The technique of the portable alternative DP system developed here can serve as a practical tool to assist those ships without being equipped with the DP facility while the dynamic positioning missions are needed.
Zaki, Mohammad Reza; Varshosaz, Jaleh; Fathi, Milad
2015-05-20
Multivariate nature of drug loaded nanospheres manufacturing in term of multiplicity of involved factors makes it a time consuming and expensive process. In this study genetic algorithm (GA) and artificial neural network (ANN), two tools inspired by natural process, were employed to optimize and simulate the manufacturing process of agar nanospheres. The efficiency of GA was evaluated against the response surface methodology (RSM). The studied responses included particle size, poly dispersity index, zeta potential, drug loading and release efficiency. GA predicted greater extremum values for response factors compared to RSM. However, real values showed some deviations from predicted data. Appropriate agreement was found between ANN model predicted and real values for all five response factors with high correlation coefficients. GA was more successful than RSM in optimization and along with ANN were efficient tools in optimizing and modeling the fabrication process of drug loaded in agar nanospheres. PMID:25817674
Filho, Faete J; Tolbert, Leon M; Ozpineci, Burak
2012-01-01
The work developed here proposes a methodology for calculating switching angles for varying DC sources in a multilevel cascaded H-bridges converter. In this approach the required fundamental is achieved, the lower harmonics are minimized, and the system can be implemented in real time with low memory requirements. Genetic algorithm (GA) is the stochastic search method to find the solution for the set of equations where the input voltages are the known variables and the switching angles are the unknown variables. With the dataset generated by GA, an artificial neural network (ANN) is trained to store the solutions without excessive memory storage requirements. This trained ANN then senses the voltage of each cell and produces the switching angles in order to regulate the fundamental at 120 V and eliminate or minimize the low order harmonics while operating in real time.
NASA Astrophysics Data System (ADS)
Karabiber, Fethullah; Grassi, Giuseppe; Vecchio, Pietro; Arik, Sabri; Yalcin, M. Erhan
2011-01-01
Based on the cellular neural network (CNN) paradigm, the bio-inspired (bi-i) cellular vision system is a computing platform consisting of state-of-the-art sensing, cellular sensing-processing and digital signal processing. This paper presents the implementation of a novel CNN-based segmentation algorithm onto the bi-i system. The experimental results, carried out for different benchmark video sequences, highlight the feasibility of the approach, which provides a frame rate of about 26 frame/sec. Comparisons with existing CNN-based methods show that, even though these methods are from two to six times faster than the proposed one, the conceived approach is more accurate and, consequently, represents a satisfying trade-off between real-time requirements and accuracy.
NASA Astrophysics Data System (ADS)
Bagheri, H.; Sadjadi, S. Y.; Sadeghian, S.
2013-09-01
One of the most significant tools to study many engineering projects is three-dimensional modelling of the Earth that has many applications in the Geospatial Information System (GIS), e.g. creating Digital Train Modelling (DTM). DTM has numerous applications in the fields of sciences, engineering, design and various project administrations. One of the most significant events in DTM technique is the interpolation of elevation to create a continuous surface. There are several methods for interpolation, which have shown many results due to the environmental conditions and input data. The usual methods of interpolation used in this study along with Genetic Algorithms (GA) have been optimised and consisting of polynomials and the Inverse Distance Weighting (IDW) method. In this paper, the Artificial Intelligent (AI) techniques such as GA and Neural Networks (NN) are used on the samples to optimise the interpolation methods and production of Digital Elevation Model (DEM). The aim of entire interpolation methods is to evaluate the accuracy of interpolation methods. Universal interpolation occurs in the entire neighbouring regions can be suggested for larger regions, which can be divided into smaller regions. The results obtained from applying GA and ANN individually, will be compared with the typical method of interpolation for creation of elevations. The resulting had performed that AI methods have a high potential in the interpolation of elevations. Using artificial networks algorithms for the interpolation and optimisation based on the IDW method with GA could be estimated the high precise elevations.
Neural algorithms on VLSI concurrent architectures
Caviglia, D.D.; Bisio, G.M.; Parodi, G.
1988-09-01
The research concerns the study of neural algorithms for developing CAD tools with A.I. features in VLSI design activities. In this paper the focus is on optimization problems such as partitioning, placement and routing. These problems require massive computational power to be solved (NP-complete problems) and the standard approach is usually based on euristic techniques. Neural algorithms can be represented by a circuital model. This kind of representation can be easily mapped in a real circuit, which, however, features limited flexibility with respect to the variety of problems. In this sense the simulation of the neural circuit, by mapping it on a digital VLSI concurrent architecture seems to be preferrable; in addition this solution offers a wider choice with regard to algorithms characteristics (e.g. transfer curve of neural elements, reconfigurability of interconnections, etc.). The implementation with programmable components, such as transputers, allows an indirect mapping of the algorithm (one transputer for N neurons) accordingly to the dimension and the characteristics of the problem. In this way the neural algorithm described by the circuit is reduced to the algorithm that simulates the network behavior. The convergence properties of that formulation are studied with respect to the characteristics of the neural element transfer curve.
Self-organization of neural networks
NASA Astrophysics Data System (ADS)
Clark, John W.; Winston, Jeffrey V.; Rafelski, Johann
1984-05-01
The plastic development of a neural-network model operating autonomously in discrete time is described by the temporal modification of interneuronal coupling strengths according to momentary neural activity. A simple algorithm (“brainwashing”) is found which, applied to nets with initially quasirandom connectivity, leads to model networks with properties conductive to the simulation of memory and learning phenomena.
NASA Astrophysics Data System (ADS)
Arevalo, J. C.; Hamilton, N.; Ghedira, H.
2004-12-01
Snow coverage and depth are two key parameters that are essential to be estimated and applied in a wide range of hydrological applications. However, the traditional field sampling methods and the ground-based data collection are often very sparse, time consuming, and expensive compared to the coverage provided by remote sensing techniques. Passive microwave remote sensing data have been investigated by numerous researchers and have been demonstrated to be effective for monitoring snow pack parameters. Those researches have resulted that the microwave brightness temperature are related to the snow cover structure with different correlation degrees. The primary objective of this research is to produce a spatial estimation of snow water equivalent with sufficient spatial and temporal resolution using passive microwave data. The final product of this project will be an additional tool for flood warning and water resource forecasts, which can be an additional input to the actual hydrological models. The focus of this paper is to investigate the performance of filtering algorithm (developed by NESDIS NOAA) and Neural Network algorithm for snow cover identification in the Northern Midwest States. Artificial neural networks have been successfully applied to image processing, and have shown a great potential in the classification of a wide range of remote sensing data. The study area is located in the Northern Midwest of the United States within 109° 30'W - 100° 50'W and 48° 40'N - 41° 00'N. A total of 180 ground stations covering the study area have been identified for this experiment. The passive microwave data from the current SSM/I (Special Sensor Microwave Imager) sensors on board the DMSP F13 and F14 satellites are used in both ascending and descending orbits. These images provide (twice-a-day) measurements of the brightness temperature in seven channels with different frequencies and polarizations (19 V, 19 H, 22 V, 37V, 37 H, 85 V, and 85 H). All the seven
Li, Zhongwei; Sun, Beibei; Xin, Yuezhen; Wang, Xun
2016-01-01
Flavones, the secondary metabolites of Phellinus igniarius fungus, have the properties of antioxidation and anticancer. Because of the great medicinal value, there are large demands on flavones for medical use and research. Flavones abstracted from natural Phellinus can not meet the medical and research need, since Phellinus in the natural environment is very rare and is hard to be cultivated artificially. The production of flavones is mainly related to the fermentation culture of Phellinus, which made the optimization of culture conditions an important problem. Some researches were made to optimize the fermentation culture conditions, such as the method of response surface methodology, which claimed the optimal flavones production was 1532.83 μg/mL. In order to further optimize the fermentation culture conditions for flavones, in this work a hybrid intelligent algorithm with genetic algorithm and BP neural network is proposed. Our method has the intelligent learning ability and can overcome the limitation of large-scale biotic experiments. Through simulations, the optimal culture conditions are obtained and the flavones production is increased to 2200 μg/mL. PMID:27595102
Wu, Huai-Ning; Luo, Biao
2012-12-01
It is well known that the nonlinear H∞ state feedback control problem relies on the solution of the Hamilton-Jacobi-Isaacs (HJI) equation, which is a nonlinear partial differential equation that has proven to be impossible to solve analytically. In this paper, a neural network (NN)-based online simultaneous policy update algorithm (SPUA) is developed to solve the HJI equation, in which knowledge of internal system dynamics is not required. First, we propose an online SPUA which can be viewed as a reinforcement learning technique for two players to learn their optimal actions in an unknown environment. The proposed online SPUA updates control and disturbance policies simultaneously; thus, only one iterative loop is needed. Second, the convergence of the online SPUA is established by proving that it is mathematically equivalent to Newton's method for finding a fixed point in a Banach space. Third, we develop an actor-critic structure for the implementation of the online SPUA, in which only one critic NN is needed for approximating the cost function, and a least-square method is given for estimating the NN weight parameters. Finally, simulation studies are provided to demonstrate the effectiveness of the proposed algorithm. PMID:24808144
NASA Astrophysics Data System (ADS)
Li, L.; Riaño, D.; Patricio, M.; Cheng, Y.; Ustin, S.
Remote estimation of vegetation water content has important implications in agricultural management practices and forest fire monitoring Vegetation water content is also found useful in estimating leaf area index using optical remote sensing methods This study aims to investigate the performance of genetic algorithms coupled with partial least squares GA-PLS modeling of spectral reflectance in retrieving equivalent water thickness EWT at leaf and canopy level and to compare results from GA-PLS modeling with those from using artificial neural networks ANN The genetic algorithm is used to identify a subset of spectral bands sensitive to the variation in EWT and PLS is then applied to relate the reflectance of the identified bands to ETW values The advantage of using ANN is to model nonlinear transfer functions at a higher accuracy than regression analysis GA-PLS and ANN were applied to LOPEX dataset datasets simulated by a leaf radiative transfer model PROSPECT and a canopy radiative transfer model SAILH and to remotely sensed AVIRIS and MODIS imagery The results indicate that GA-PLS and ANN both have capability of retrieving EWT from measured and simulated leaf reflectance and achieved very good prediction r 2 0 90 The retrieval of using real and simulated canopy data indicates that both GA-PLS and ANN have degraded performances due to the effects of soil background and leaf dry matter on the reflectance but the retrieving accuracies were still highly valuable The result also shows that although nonlinear transfer functions
2016-01-01
Objective. Our objective is to develop a computerized scheme for liver tumor segmentation in MR images. Materials and Methods. Our proposed scheme consists of four main stages. Firstly, the region of interest (ROI) image which contains the liver tumor region in the T1-weighted MR image series was extracted by using seed points. The noise in this ROI image was reduced and the boundaries were enhanced. A 3D fast marching algorithm was applied to generate the initial labeled regions which are considered as teacher regions. A single hidden layer feedforward neural network (SLFN), which was trained by a noniterative algorithm, was employed to classify the unlabeled voxels. Finally, the postprocessing stage was applied to extract and refine the liver tumor boundaries. The liver tumors determined by our scheme were compared with those manually traced by a radiologist, used as the “ground truth.” Results. The study was evaluated on two datasets of 25 tumors from 16 patients. The proposed scheme obtained the mean volumetric overlap error of 27.43% and the mean percentage volume error of 15.73%. The mean of the average surface distance, the root mean square surface distance, and the maximal surface distance were 0.58 mm, 1.20 mm, and 6.29 mm, respectively. PMID:27597960
Senthil Kumar, A R; Goyal, Manish Kumar; Ojha, C S P; Singh, R D; Swamee, P K
2013-01-01
The prediction of streamflow is required in many activities associated with the planning and operation of the components of a water resources system. Soft computing techniques have proven to be an efficient alternative to traditional methods for modelling qualitative and quantitative water resource variables such as streamflow, etc. The focus of this paper is to present the development of models using multiple linear regression (MLR), artificial neural network (ANN), fuzzy logic and decision tree algorithms such as M5 and REPTree for predicting the streamflow at Kasol located at the upstream of Bhakra reservoir in Sutlej basin in northern India. The input vector to the various models using different algorithms was derived considering statistical properties such as auto-correlation function, partial auto-correlation and cross-correlation function of the time series. It was found that REPtree model performed well compared to other soft computing techniques such as MLR, ANN, fuzzy logic, and M5P investigated in this study and the results of the REPTree model indicate that the entire range of streamflow values were simulated fairly well. The performance of the naïve persistence model was compared with other models and the requirement of the development of the naïve persistence model was also analysed by persistence index. PMID:24355836
Li, Zhongwei; Sun, Beibei; Xin, Yuezhen; Wang, Xun; Zhu, Hu
2016-01-01
Flavones, the secondary metabolites of Phellinus igniarius fungus, have the properties of antioxidation and anticancer. Because of the great medicinal value, there are large demands on flavones for medical use and research. Flavones abstracted from natural Phellinus can not meet the medical and research need, since Phellinus in the natural environment is very rare and is hard to be cultivated artificially. The production of flavones is mainly related to the fermentation culture of Phellinus, which made the optimization of culture conditions an important problem. Some researches were made to optimize the fermentation culture conditions, such as the method of response surface methodology, which claimed the optimal flavones production was 1532.83 μg/mL. In order to further optimize the fermentation culture conditions for flavones, in this work a hybrid intelligent algorithm with genetic algorithm and BP neural network is proposed. Our method has the intelligent learning ability and can overcome the limitation of large-scale biotic experiments. Through simulations, the optimal culture conditions are obtained and the flavones production is increased to 2200 μg/mL. PMID:27595102
Le, Trong-Ngoc; Bao, Pham The; Huynh, Hieu Trung
2016-01-01
Objective. Our objective is to develop a computerized scheme for liver tumor segmentation in MR images. Materials and Methods. Our proposed scheme consists of four main stages. Firstly, the region of interest (ROI) image which contains the liver tumor region in the T1-weighted MR image series was extracted by using seed points. The noise in this ROI image was reduced and the boundaries were enhanced. A 3D fast marching algorithm was applied to generate the initial labeled regions which are considered as teacher regions. A single hidden layer feedforward neural network (SLFN), which was trained by a noniterative algorithm, was employed to classify the unlabeled voxels. Finally, the postprocessing stage was applied to extract and refine the liver tumor boundaries. The liver tumors determined by our scheme were compared with those manually traced by a radiologist, used as the "ground truth." Results. The study was evaluated on two datasets of 25 tumors from 16 patients. The proposed scheme obtained the mean volumetric overlap error of 27.43% and the mean percentage volume error of 15.73%. The mean of the average surface distance, the root mean square surface distance, and the maximal surface distance were 0.58 mm, 1.20 mm, and 6.29 mm, respectively. PMID:27597960
Neural networks for aircraft control
NASA Technical Reports Server (NTRS)
Linse, Dennis
1990-01-01
Current research in Artificial Neural Networks indicates that networks offer some potential advantages in adaptation and fault tolerance. This research is directed at determining the possible applicability of neural networks to aircraft control. The first application will be to aircraft trim. Neural network node characteristics, network topology and operation, neural network learning and example histories using neighboring optimal control with a neural net are discussed.
Critical Branching Neural Networks
ERIC Educational Resources Information Center
Kello, Christopher T.
2013-01-01
It is now well-established that intrinsic variations in human neural and behavioral activity tend to exhibit scaling laws in their fluctuations and distributions. The meaning of these scaling laws is an ongoing matter of debate between isolable causes versus pervasive causes. A spiking neural network model is presented that self-tunes to critical…
Satellite image analysis using neural networks
NASA Technical Reports Server (NTRS)
Sheldon, Roger A.
1990-01-01
The tremendous backlog of unanalyzed satellite data necessitates the development of improved methods for data cataloging and analysis. Ford Aerospace has developed an image analysis system, SIANN (Satellite Image Analysis using Neural Networks) that integrates the technologies necessary to satisfy NASA's science data analysis requirements for the next generation of satellites. SIANN will enable scientists to train a neural network to recognize image data containing scenes of interest and then rapidly search data archives for all such images. The approach combines conventional image processing technology with recent advances in neural networks to provide improved classification capabilities. SIANN allows users to proceed through a four step process of image classification: filtering and enhancement, creation of neural network training data via application of feature extraction algorithms, configuring and training a neural network model, and classification of images by application of the trained neural network. A prototype experimentation testbed was completed and applied to climatological data.
NASA Technical Reports Server (NTRS)
Padgett, Mary L.; Desai, Utpal; Roppel, T.A.; White, Charles R.
1993-01-01
A design procedure is suggested for neural networks which accommodates the inclusion of such knowledge-based systems techniques as fuzzy logic and pairwise comparisons. The use of these procedures in the design of applications combines qualitative and quantitative factors with empirical data to yield a model with justifiable design and parameter selection procedures. The procedure is especially relevant to areas of back-propagation neural network design which are highly responsive to the use of precisely recorded expert knowledge.
NASA Astrophysics Data System (ADS)
Belchansky, G.; Alpatsky, I.; Mordvintsev, I.; Douglas, D.
Investigating new methods to estimate sea-ice geophysical parameters using multisensor satellite data is critical for global change studies. The most widely used and consistent data to study sea ice at global scale are SMMR and SSM/I passive microwave measurements available since 1978. However, comparisons with LANDSAT, AVHRR and ERS-1 SAR have demonstrated substantial seasonal and regional differences in SSM/I ice parameter estimates (Belchansky and Douglas, 2000, 2002). This report presents investigating methods of improving SSM/I and OKEAN sea ice inversion parameters using MLP neural networks, and compare the sea ice classification results from different neural networks and linear mixture model. Efficiency of four sea ice type inversion (classification) algorithms utilizing SSM/I, OKEAN-01, ERS and RADARSAT satellite data were compared and investigated. The first one applied different linear mixture models (NASA Team, Bootstrap, and OKEAN). The second, third and fourth algorithms applied the modified MLP neural networks with different learning algorithms based, respectively, on 1) error back propagation and simulated annealing (Kirkpatrick, 1983); 2) dynamic learning and polynomial basis function (Chen et al., 1996); and 3) dynamic learning and two-step optimization. Both last algorithms used the Kalman filtering technique. Our studies demonstrated that both modified MLP neural networks with dynamic learning were more efficient (in terms of learning time, accuracy, and ability to generalize the selected learning data) than modified MLP neural network with learning algorithms based on the error back propagation and simulated annealing for simple approximation problems. MY sea ice and albedo inversion from SSM/I brightness temperatures and respective OKEAN learning data sets demonstrated that these algorithms caused over-fitting in comparison with the MLP neural network with the error back propagation and simulated annealing. Therefore, for MY sea ice inversion
NASA Astrophysics Data System (ADS)
Moreau, Emmanuel; Mallet, Cecile; Casagrande, Luc; Klapisz, Claude
1998-08-01
A new algorithms is developed whereby the cloud liquid water path (LWP) and the total precipitable water (TPW) may be determined from microwave radiometric data. A large meteorological database obtained from the European Centre for Medium-Range Weather Forecasts forecast model is used to simulate, with a radiative transfer model, brightness temperatures (TB) at the top of the atmosphere for the special sensor microwave imagery frequencies. A single- hidden-layer ANN was used. An error backpropagation training algorithm was applied to train the ANN. A first comparison with a log-linear regression algorithm, shows that the ANN can represent more accurately the underlying relationship between TB and, TPW and LWP. The ANN seems to be able to give a better fit at large values of LWP. Furthermore in the case of TPW, a validation is made with radiosonde data, with another new algorithm.
Nonlinear PLS modeling using neural networks
Qin, S.J.; McAvoy, T.J.
1994-12-31
This paper discusses the embedding of neural networks into the framework of the PLS (partial least squares) modeling method resulting in a neural net PLS modeling approach. By using the universal approximation property of neural networks, the PLS modeling method is genealized to a nonlinear framework. The resulting model uses neural networks to capture the nonlinearity and keeps the PLS projection to attain robust generalization property. In this paper, the standard PLS modeling method is briefly reviewed. Then a neural net PLS (NNPLS) modeling approach is proposed which incorporates feedforward networks into the PLS modeling. A multi-input-multi-output nonlinear modeling task is decomposed into linear outer relations and simple nonlinear inner relations which are performed by a number of single-input-single-output networks. Since only a small size network is trained at one time, the over-parametrized problem of the direct neural network approach is circumvented even when the training data are very sparse. A conjugate gradient learning method is employed to train the network. It is shown that, by analyzing the NNPLS algorithm, the global NNPLS model is equivalent to a multilayer feedforward network. Finally, applications of the proposed NNPLS method are presented with comparison to the standard linear PLS method and the direct neural network approach. The proposed neural net PLS method gives better prediction results than the PLS modeling method and the direct neural network approach.
Data compression using artificial neural networks
Watkins, B.E.
1991-09-01
This thesis investigates the application of artificial neural networks for the compression of image data. An algorithm is developed using the competitive learning paradigm which takes advantage of the parallel processing and classification capability of neural networks to produce an efficient implementation of vector quantization. Multi-Stage, tree searched, and classification vector quantization codebook design are adapted to the neural network design to reduce the computational cost and hardware requirements. The results show that the new algorithm provides a substantial reduction in computational costs and an improvement in performance.
Zandkarimi, Majid; Shafiei, Mohammad; Hadizadeh, Farzin; Darbandi, Mohammad Ali; Tabrizian, Kaveh
2014-03-01
An important goal for drug development within the pharmaceutical industry is the application of simple methods to determine human pharmacokinetic parameters. Effective computing tools are able to increase scientists' ability to make precise selections of chemical compounds in accordance with desired pharmacokinetic and safety profiles. This work presents a method for making predictions of the clearance, plasma protein binding, and volume of distribution for alkaloid drugs. The tools used in this method were genetic algorithms (GAs) combined with artificial neural networks (ANNs) and these were applied to select the most relevant molecular descriptors and to develop quantitative structure-pharmacokinetic relationship (QSPkR) models. Results showed that three-dimensional structural descriptors had more influence on QSPkR models. The models developed in this study were able to predict systemic clearance, volume of distribution, and plasma protein binding with normalized root mean square error (NRMSE) values of 0.151, 0.263, and 0.423, respectively. These results demonstrate an acceptable level of efficiency of the developed models for the prediction of pharmacokinetic parameters. PMID:24634842
Tripathi, C K M; Khan, Mahvish; Praveen, Vandana; Khan, Saif; Srivastava, Akanksha
2012-07-01
Antibiotic production with Streptomyces sindenensis MTCC 8122 was optimized under submerged fermentation conditions by artificial neural network (ANN) coupled with genetic algorithm (GA) and Nelder-Mead downhill simplex (NMDS). Feed forward back-propagation ANN was trained to establish the mathematical relationship among the medium components and length of incubation period for achieving maximum antibiotic yield. The optimization strategy involved growing the culture with varying concentrations of various medium components for different incubation periods. Under non-optimized condition, antibiotic production was found to be 95 microgram/ml, which nearly doubled (176 microgram/ml) with the ANN-GA optimization. ANN-NMDS optimization was found to be more efficacious, and maximum antibiotic production (197 microgram/ml) was obtained by cultivating the cells with (g/l) fructose 2.7602, MgSO4 1.2369, (NH4)2PO4 0.2742, DL-threonine 3.069%, and soyabean meal 1.952%, for 9.8531 days of incubation, which was roughly 12% higher than the yield obtained by ANN coupled with GA under the same conditions. PMID:22580313
Li, Yongqiang; Abbaspour, Mohammadreza R; Grootendorst, Paul V; Rauth, Andrew M; Wu, Xiao Yu
2015-08-01
This study was performed to optimize the formulation of polymer-lipid hybrid nanoparticles (PLN) for the delivery of an ionic water-soluble drug, verapamil hydrochloride (VRP) and to investigate the roles of formulation factors. Modeling and optimization were conducted based on a spherical central composite design. Three formulation factors, i.e., weight ratio of drug to lipid (X1), and concentrations of Tween 80 (X2) and Pluronic F68 (X3), were chosen as independent variables. Drug loading efficiency (Y1) and mean particle size (Y2) of PLN were selected as dependent variables. The predictive performance of artificial neural networks (ANN) and the response surface methodology (RSM) were compared. As ANN was found to exhibit better recognition and generalization capability over RSM, multi-objective optimization of PLN was then conducted based upon the validated ANN models and continuous genetic algorithms (GA). The optimal PLN possess a high drug loading efficiency (92.4%, w/w) and a small mean particle size (∼100nm). The predicted response variables matched well with the observed results. The three formulation factors exhibited different effects on the properties of PLN. ANN in coordination with continuous GA represent an effective and efficient approach to optimize the PLN formulation of VRP with desired properties. PMID:25986587
NASA Astrophysics Data System (ADS)
Ayala, Helon Vicente Hultmann; Coelho, Leandro dos Santos
2016-02-01
The present work introduces a procedure for input selection and parameter estimation for system identification based on Radial Basis Functions Neural Networks (RBFNNs) models with an improved objective function based on the residuals and its correlation function coefficients. We show the results when the proposed methodology is applied to model a magnetorheological damper, with real acquired data, and other two well-known benchmarks. The canonical genetic and differential evolution algorithms are used in cascade to decompose the problem of defining the lags taken as the inputs of the model and its related parameters based on the simultaneous minimization of the residuals and higher orders correlation functions. The inner layer of the cascaded approach is composed of a population which represents the lags on the inputs and outputs of the system and an outer layer represents the corresponding parameters of the RBFNN. The approach is able to define both the inputs of the model and its parameters. This is interesting as it frees the designer of manual procedures, which are time consuming and prone to error, usually done to define the model inputs. We compare the proposed methodology with other works found in the literature, showing overall better results for the cascaded approach.
Marto, Aminaton; Hajihassani, Mohsen; Armaghani, Danial Jahed; Mohamad, Edy Tonnizam; Makhtar, Ahmad Mahir
2014-01-01
Flyrock is one of the major disturbances induced by blasting which may cause severe damage to nearby structures. This phenomenon has to be precisely predicted and subsequently controlled through the changing in the blast design to minimize potential risk of blasting. The scope of this study is to predict flyrock induced by blasting through a novel approach based on the combination of imperialist competitive algorithm (ICA) and artificial neural network (ANN). For this purpose, the parameters of 113 blasting operations were accurately recorded and flyrock distances were measured for each operation. By applying the sensitivity analysis, maximum charge per delay and powder factor were determined as the most influential parameters on flyrock. In the light of this analysis, two new empirical predictors were developed to predict flyrock distance. For a comparison purpose, a predeveloped backpropagation (BP) ANN was developed and the results were compared with those of the proposed ICA-ANN model and empirical predictors. The results clearly showed the superiority of the proposed ICA-ANN model in comparison with the proposed BP-ANN model and empirical approaches. PMID:25147856
Marto, Aminaton; Jahed Armaghani, Danial; Tonnizam Mohamad, Edy; Makhtar, Ahmad Mahir
2014-01-01
Flyrock is one of the major disturbances induced by blasting which may cause severe damage to nearby structures. This phenomenon has to be precisely predicted and subsequently controlled through the changing in the blast design to minimize potential risk of blasting. The scope of this study is to predict flyrock induced by blasting through a novel approach based on the combination of imperialist competitive algorithm (ICA) and artificial neural network (ANN). For this purpose, the parameters of 113 blasting operations were accurately recorded and flyrock distances were measured for each operation. By applying the sensitivity analysis, maximum charge per delay and powder factor were determined as the most influential parameters on flyrock. In the light of this analysis, two new empirical predictors were developed to predict flyrock distance. For a comparison purpose, a predeveloped backpropagation (BP) ANN was developed and the results were compared with those of the proposed ICA-ANN model and empirical predictors. The results clearly showed the superiority of the proposed ICA-ANN model in comparison with the proposed BP-ANN model and empirical approaches. PMID:25147856
NASA Astrophysics Data System (ADS)
Ahmed, M.; Gu, F.; Ball, A.
2011-07-01
Reciprocating compressors are widely used in industry for various purposes and faults occurring in them can degrade their performance, consume additional energy and even cause severe damage to the machine. Vibration monitoring techniques are often used for early fault detection and diagnosis, but it is difficult to prescribe a given set of effective diagnostic features because of the wide variety of operating conditions and the complexity of the vibration signals which originate from the many different vibrating and impact sources. This paper studies the use of genetic algorithms (GAs) and neural networks (NNs) to select effective diagnostic features for the fault diagnosis of a reciprocating compressor. A large number of common features are calculated from the time and frequency domains and envelope analysis. Applying GAs and NNs to these features found that envelope analysis has the most potential for differentiating three common faults: valve leakage, inter-cooler leakage and a loose drive belt. Simultaneously, the spread parameter of the probabilistic NN was also optimised. The selected subsets of features were examined based on vibration source characteristics. The approach developed and the trained NN are confirmed as possessing general characteristics for fault detection and diagnosis.
NASA Astrophysics Data System (ADS)
Ai, Yuewei; Shao, Xinyu; Jiang, Ping; Li, Peigen; Liu, Yang; Yue, Chen
2015-11-01
The welded joints of dissimilar materials have been widely used in automotive, ship and space industries. The joint quality is often evaluated by weld seam geometry, microstructures and mechanical properties. To obtain the desired weld seam geometry and improve the quality of welded joints, this paper proposes a process modeling and parameter optimization method to obtain the weld seam with minimum width and desired depth of penetration for laser butt welding of dissimilar materials. During the process, Taguchi experiments are conducted on the laser welding of the low carbon steel (Q235) and stainless steel (SUS301L-HT). The experimental results are used to develop the radial basis function neural network model, and the process parameters are optimized by genetic algorithm. The proposed method is validated by a confirmation experiment. Simultaneously, the microstructures and mechanical properties of the weld seam generated from optimal process parameters are further studied by optical microscopy and tensile strength test. Compared with the unoptimized weld seam, the welding defects are eliminated in the optimized weld seam and the mechanical properties are improved. The results show that the proposed method is effective and reliable for improving the quality of welded joints in practical production.
Chiroma, Haruna; Abdul-kareem, Sameem; Khan, Abdullah; Nawi, Nazri Mohd.; Gital, Abdulsalam Ya’u; Shuib, Liyana; Abubakar, Adamu I.; Rahman, Muhammad Zubair; Herawan, Tutut
2015-01-01
Background Global warming is attracting attention from policy makers due to its impacts such as floods, extreme weather, increases in temperature by 0.7°C, heat waves, storms, etc. These disasters result in loss of human life and billions of dollars in property. Global warming is believed to be caused by the emissions of greenhouse gases due to human activities including the emissions of carbon dioxide (CO2) from petroleum consumption. Limitations of the previous methods of predicting CO2 emissions and lack of work on the prediction of the Organization of the Petroleum Exporting Countries (OPEC) CO2 emissions from petroleum consumption have motivated this research. Methods/Findings The OPEC CO2 emissions data were collected from the Energy Information Administration. Artificial Neural Network (ANN) adaptability and performance motivated its choice for this study. To improve effectiveness of the ANN, the cuckoo search algorithm was hybridised with accelerated particle swarm optimisation for training the ANN to build a model for the prediction of OPEC CO2 emissions. The proposed model predicts OPEC CO2 emissions for 3, 6, 9, 12 and 16 years with an improved accuracy and speed over the state-of-the-art methods. Conclusion An accurate prediction of OPEC CO2 emissions can serve as a reference point for propagating the reorganisation of economic development in OPEC member countries with the view of reducing CO2 emissions to Kyoto benchmarks—hence, reducing global warming. The policy implications are discussed in the paper. PMID:26305483
Neural networks : iterative unlearning algorithm converging to the projector rule matrix
NASA Astrophysics Data System (ADS)
Plakhov, A. Yu.; Semenov, S. A.
1994-02-01
The iterative unlearning algorithm for connectivity self-correction is proposed. No presentation of patterns during the iteration process is required. Starting from the Hebbian connectivity, the convergence of the (rescaled) iterated connection matrix to the projector rule one is proven, for arbitrary set of p < N binary patterns.
Speech Emotion Feature Selection Method Based on Contribution Analysis Algorithm of Neural Network
Wang Xiaojia; Mao Qirong; Zhan Yongzhao
2008-11-06
There are many emotion features. If all these features are employed to recognize emotions, redundant features may be existed. Furthermore, recognition result is unsatisfying and the cost of feature extraction is high. In this paper, a method to select speech emotion features based on contribution analysis algorithm of NN is presented. The emotion features are selected by using contribution analysis algorithm of NN from the 95 extracted features. Cluster analysis is applied to analyze the effectiveness for the features selected, and the time of feature extraction is evaluated. Finally, 24 emotion features selected are used to recognize six speech emotions. The experiments show that this method can improve the recognition rate and the time of feature extraction.
Neural Networks for Flight Control
NASA Technical Reports Server (NTRS)
Jorgensen, Charles C.
1996-01-01
Neural networks are being developed at NASA Ames Research Center to permit real-time adaptive control of time varying nonlinear systems, enhance the fault-tolerance of mission hardware, and permit online system reconfiguration. In general, the problem of controlling time varying nonlinear systems with unknown structures has not been solved. Adaptive neural control techniques show considerable promise and are being applied to technical challenges including automated docking of spacecraft, dynamic balancing of the space station centrifuge, online reconfiguration of damaged aircraft, and reducing cost of new air and spacecraft designs. Our experiences have shown that neural network algorithms solved certain problems that conventional control methods have been unable to effectively address. These include damage mitigation in nonlinear reconfiguration flight control, early performance estimation of new aircraft designs, compensation for damaged planetary mission hardware by using redundant manipulator capability, and space sensor platform stabilization. This presentation explored these developments in the context of neural network control theory. The discussion began with an overview of why neural control has proven attractive for NASA application domains. The more important issues in control system development were then discussed with references to significant technical advances in the literature. Examples of how these methods have been applied were given, followed by projections of emerging application needs and directions.
VLSI Cells Placement Using the Neural Networks
Azizi, Hacene; Zouaoui, Lamri; Mokhnache, Salah
2008-06-12
The artificial neural networks have been studied for several years. Their effectiveness makes it possible to expect high performances. The privileged fields of these techniques remain the recognition and classification. Various applications of optimization are also studied under the angle of the artificial neural networks. They make it possible to apply distributed heuristic algorithms. In this article, a solution to placement problem of the various cells at the time of the realization of an integrated circuit is proposed by using the KOHONEN network.
Wang, Jie-Sheng; Han, Shuang
2015-01-01
For predicting the key technology indicators (concentrate grade and tailings recovery rate) of flotation process, a feed-forward neural network (FNN) based soft-sensor model optimized by the hybrid algorithm combining particle swarm optimization (PSO) algorithm and gravitational search algorithm (GSA) is proposed. Although GSA has better optimization capability, it has slow convergence velocity and is easy to fall into local optimum. So in this paper, the velocity vector and position vector of GSA are adjusted by PSO algorithm in order to improve its convergence speed and prediction accuracy. Finally, the proposed hybrid algorithm is adopted to optimize the parameters of FNN soft-sensor model. Simulation results show that the model has better generalization and prediction accuracy for the concentrate grade and tailings recovery rate to meet the online soft-sensor requirements of the real-time control in the flotation process. PMID:26583034
Hyperbolic Hopfield neural networks.
Kobayashi, M
2013-02-01
In recent years, several neural networks using Clifford algebra have been studied. Clifford algebra is also called geometric algebra. Complex-valued Hopfield neural networks (CHNNs) are the most popular neural networks using Clifford algebra. The aim of this brief is to construct hyperbolic HNNs (HHNNs) as an analog of CHNNs. Hyperbolic algebra is a Clifford algebra based on Lorentzian geometry. In this brief, a hyperbolic neuron is defined in a manner analogous to a phasor neuron, which is a typical complex-valued neuron model. HHNNs share common concepts with CHNNs, such as the angle and energy. However, HHNNs and CHNNs are different in several aspects. The states of hyperbolic neurons do not form a circle, and, therefore, the start and end states are not identical. In the quantized version, unlike complex-valued neurons, hyperbolic neurons have an infinite number of states. PMID:24808287
Patil, R.B.
1995-05-01
Traditional neural networks like multi-layered perceptrons (MLP) use example patterns, i.e., pairs of real-valued observation vectors, ({rvec x},{rvec y}), to approximate function {cflx f}({rvec x}) = {rvec y}. To determine the parameters of the approximation, a special version of the gradient descent method called back-propagation is widely used. In many situations, observations of the input and output variables are not precise; instead, we usually have intervals of possible values. The imprecision could be due to the limited accuracy of the measuring instrument or could reflect genuine uncertainty in the observed variables. In such situation input and output data consist of mixed data types; intervals and precise numbers. Function approximation in interval domains is considered in this paper. We discuss a modification of the classical backpropagation learning algorithm to interval domains. Results are presented with simple examples demonstrating few properties of nonlinear interval mapping as noise resistance and finding set of solutions to the function approximation problem.
Neural networks and applications tutorial
NASA Astrophysics Data System (ADS)
Guyon, I.
1991-09-01
The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear. The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks. Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks. The tutorial is divided into six lectures, that where presented at the Third Graduate Summer Course on Computational Physics (September 3-7, 1990) on Parallel Architectures and Applications, organized by the European Physical Society: (1) Introduction: machine learning and biological computation. (2) Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations. (3) Neural network systems: architectures, learning algorithms. (4) Applications: pattern recognition, signal processing, etc. (5) Elements of learning theory: how to build networks which generalize. (6) A case study: a neural network for on-line recognition of handwritten alphanumeric characters.
Rangraz, Parisa; Behnam, Hamid; Shakhssalim, Naser; Tavakkoli, Jahan
2012-01-01
Non-invasive ultrasound surgeries such as high intensity focused ultrasound have been developed to treat tumors or to stop bleeding. In this technique, incorporation of a suitable imaging modality to monitor and control the treatments is essential so several imaging methods such as X-ray, Magnetic resonance imaging and ultrasound imaging have been proposed to monitor the induced thermal lesions. Currently, the only ultrasound imaging technique that is clinically used for monitoring this treatment is standard pulse-echo B-mode ultrasound imaging. This paper describes a novel method for detecting high intensity focused ultrasound-induced thermal lesions using a feed forward neural-network. This study was carried on in vitro animal tissue samples. Backscattered radio frequency signals were acquired in real-time during treatment in order to detect induced thermal lesions. Changes in various tissue properties including tissue's attenuation coefficient, integrated backscatter, scaling parameter of Nakagami distribution, frequency dependent scatterer amplitudes and tissue vibration derived from the backscattered radio frequency data acquired 10 minutes after treatment regarding to before treatment were used in this study. These estimated parameters were used as features of the neural network. Estimated parameters of two sample tissues including two thermal lesions and their segmented B-mode images were used along with the pathological results as training data for the neural network. The results of the study shows that the trained feed forward neural network could effectively detect thermal lesions in vitro. Comparing the estimated size of the thermal lesion (9.6 mm × 8.5 mm) using neural network with the actual size of that from physical examination (10.1 mm × 9 mm) shows that we could detect high intensity focused ultrasound thermal lesions with the difference of 0.5 mm × 0.5 mm. PMID:23724369
McDonnell, Mark D.; Tissera, Migel D.; Vladusich, Tony; van Schaik, André; Tapson, Jonathan
2015-01-01
Recent advances in training deep (multi-layer) architectures have inspired a renaissance in neural network use. For example, deep convolutional networks are becoming the default option for difficult tasks on large datasets, such as image and speech recognition. However, here we show that error rates below 1% on the MNIST handwritten digit benchmark can be replicated with shallow non-convolutional neural networks. This is achieved by training such networks using the ‘Extreme Learning Machine’ (ELM) approach, which also enables a very rapid training time (∼ 10 minutes). Adding distortions, as is common practise for MNIST, reduces error rates even further. Our methods are also shown to be capable of achieving less than 5.5% error rates on the NORB image database. To achieve these results, we introduce several enhancements to the standard ELM algorithm, which individually and in combination can significantly improve performance. The main innovation is to ensure each hidden-unit operates only on a randomly sized and positioned patch of each image. This form of random ‘receptive field’ sampling of the input ensures the input weight matrix is sparse, with about 90% of weights equal to zero. Furthermore, combining our methods with a small number of iterations of a single-batch backpropagation method can significantly reduce the number of hidden-units required to achieve a particular performance. Our close to state-of-the-art results for MNIST and NORB suggest that the ease of use and accuracy of the ELM algorithm for designing a single-hidden-layer neural network classifier should cause it to be given greater consideration either as a standalone method for simpler problems, or as the final classification stage in deep neural networks applied to more difficult problems. PMID:26262687
NASA Technical Reports Server (NTRS)
Baram, Yoram
1988-01-01
Nested neural networks, consisting of small interconnected subnetworks, allow for the storage and retrieval of neural state patterns of different sizes. The subnetworks are naturally categorized by layers of corresponding to spatial frequencies in the pattern field. The storage capacity and the error correction capability of the subnetworks generally increase with the degree of connectivity between layers (the nesting degree). Storage of only few subpatterns in each subnetworks results in a vast storage capacity of patterns and subpatterns in the nested network, maintaining high stability and error correction capability.
Radar and infrared data fusion algorithm based on fuzzy-neural network
NASA Astrophysics Data System (ADS)
Han, Feng; Yang, Wan Hai
2007-12-01
In modern war, the war field environment is complex and interfere is heavy, single mode weapon can not meet the military need. Multi-mode guiding weapon has some advantages for its multi-sensor data fusion. Radar and Infrared data fusion has been widely studied due to its implementation of complementary information, improvement of target tracking and enhancement of system viability. During fusing radar and infrared data under the condition of radar-infrared dual mode guidance, there is a problem that radar data is asynchronous with infrared data. The infrared measurement data is fused first to keep synchronous with the radar measurement data. The processed data is transmitted to the central Fuzzy-neutral network (FNN) data fusion central, which is employed to decrease the influence of the uncertainty of sensor state on fusion performance. A fused estimation of target is formed. Simulation result demonstrates that this method can improve the stability and reliability of fusion.
A Neural-Network Clustering-Based Algorithm for Privacy Preserving Data Mining
NASA Astrophysics Data System (ADS)
Tsiafoulis, S.; Zorkadis, V. C.; Karras, D. A.
The increasing use of fast and efficient data mining algorithms in huge collections of personal data, facilitated through the exponential growth of technology, in particular in the field of electronic data storage media and processing power, has raised serious ethical, philosophical and legal issues related to privacy protection. To cope with these concerns, several privacy preserving methodologies have been proposed, classified in two categories, methodologies that aim at protecting the sensitive data and those that aim at protecting the mining results. In our work, we focus on sensitive data protection and compare existing techniques according to their anonymity degree achieved, the information loss suffered and their performance characteristics. The ℓ-diversity principle is combined with k-anonymity concepts, so that background information can not be exploited to successfully attack the privacy of data subjects data refer to. Based on Kohonen Self Organizing Feature Maps (SOMs), we firstly organize data sets in subspaces according to their information theoretical distance to each other, then create the most relevant classes paying special attention to rare sensitive attribute values, and finally generalize attribute values to the minimum extend required so that both the data disclosure probability and the information loss are possibly kept negligible. Furthermore, we propose information theoretical measures for assessing the anonymity degree achieved and empirical tests to demonstrate it.
Kalderstam, Jonas; Edén, Patrik; Ohlsson, Mattias
2015-01-01
We investigate a new method to place patients into risk groups in censored survival data. Properties such as median survival time, and end survival rate, are implicitly improved by optimizing the area under the survival curve. Artificial neural networks (ANN) are trained to either maximize or minimize this area using a genetic algorithm, and combined into an ensemble to predict one of low, intermediate, or high risk groups. Estimated patient risk can influence treatment choices, and is important for study stratification. A common approach is to sort the patients according to a prognostic index and then group them along the quartile limits. The Cox proportional hazards model (Cox) is one example of this approach. Another method of doing risk grouping is recursive partitioning (Rpart), which constructs a decision tree where each branch point maximizes the statistical separation between the groups. ANN, Cox, and Rpart are compared on five publicly available data sets with varying properties. Cross-validation, as well as separate test sets, are used to validate the models. Results on the test sets show comparable performance, except for the smallest data set where Rpart’s predicted risk groups turn out to be inverted, an example of crossing survival curves. Cross-validation shows that all three models exhibit crossing of some survival curves on this small data set but that the ANN model manages the best separation of groups in terms of median survival time before such crossings. The conclusion is that optimizing the area under the survival curve is a viable approach to identify risk groups. Training ANNs to optimize this area combines two key strengths from both prognostic indices and Rpart. First, a desired minimum group size can be specified, as for a prognostic index. Second, the ability to utilize non-linear effects among the covariates, which Rpart is also able to do. PMID:26352405
NASA Astrophysics Data System (ADS)
Aleardi, Mattia
2015-06-01
Predicting missing log data is a useful capability for geophysicists. Geophysical measurements in boreholes are frequently affected by gaps in the recording of one or more logs. In particular, sonic and shear sonic logs are often recorded over limited intervals along the well path, but the information these logs contain is crucial for many geophysical applications. Estimating missing log intervals from a set of recorded logs is therefore of great interest. In this work, I propose to estimate the data in missing parts of velocity logs using a genetic algorithm (GA) optimisation and I demonstrate that this method is capable of extracting linear or exponential relations that link the velocity to other available logs. The technique was tested on different sets of logs (gamma ray, resistivity, density, neutron, sonic and shear sonic) from three wells drilled in different geological settings and through different lithologies (sedimentary and intrusive rocks). The effectiveness of this methodology is demonstrated by a series of blind tests and by evaluating the correlation coefficients between the true versus predicted velocity values. The combination of GA optimisation with a Gibbs sampler (GS) and subsequent Monte Carlo simulations allows the uncertainties in the final predicted velocities to be reliably quantified. The GA method is also compared with the neural networks (NN) approach and classical multilinear regression. The comparisons show that the GA, NN and multilinear methods provide velocity estimates with the same predictive capability when the relation between the input logs and the seismic velocity is approximately linear. The GA and NN approaches are more robust when the relations are non-linear. However, in all cases, the main advantages of the GA optimisation procedure over the NN approach is that it directly provides an interpretable and simple equation that relates the input and predicted logs. Moreover, the GA method is not affected by the disadvantages
Advances in Artificial Neural Networks - Methodological Development and Application
Technology Transfer Automated Retrieval System (TEKTRAN)
Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other ne...
Generalized Adaptive Artificial Neural Networks
NASA Technical Reports Server (NTRS)
Tawel, Raoul
1993-01-01
Mathematical model of supervised learning by artificial neural network provides for simultaneous adjustments of both temperatures of neurons and synaptic weights, and includes feedback as well as feedforward synaptic connections. Extension of mathematical model described in "Adaptive Neurons For Artificial Neural Networks" (NPO-17803). Dynamics of neural network represented in new model by less-restrictive continuous formalism.
NASA Astrophysics Data System (ADS)
Gupta, R. K.; Prasad, T. S.; Vijayan, D.; Balamanikavelu, P. M.
Due to mix-up of contributions from varied features on the ground surface, getting back of individual feature in remote sensing data using pattern recognition techniques is an ill-defined inverse problem. By placing maximum likelihood (ML) constraint, the available operational softwares classify the image. Without placing any parametric constraint, the image could also be classified using artificial neural networks (ANN). As GIS overlay, developed professionally by forest officials, was available for Antilova reserve forest in Andhra Pradesh, India (170 50^' to 170 56^' N, 810 45^' to 810 54^' E), the IRS-1C LISS-III image of February 11, 1999 was used for assessing the limits of classification accuracy attainable from ML and ANN classifiers. In ML classifier, full GIS overlay was used to give training sets over whole of the image (approach `a') and in approach `b', a priori probability (normally taken equal for all the classes in operational softwares) was assigned (in addition to full spectral signature) based on the fraction areas under each class in GIS overlay. Under such ideal situation of inputs, the achieved accuracy, i.e. Kappa coefficients were 0.709 and 0.735 for approaches `a' and `b' , respectively (called iteration `0'). Using fraction area under each class in the classified output to assign a priori probability for the next iteration, the convergence (within 2% variation) was achieved for 2nd and 3rd iterations with Kappa coefficient values of 0.773 and 0.797 for approaches `a' and `b', respectively. The non-attaining of 100% classification accuracy under ideal inputs situation could be due to assumption of guassian distribution in spectral signatures. In back propagation technique based ANN classifier, spectral signatures for training were identified from GIS overlay. The number of learning iterations were 20,000 with momentum and learning rate of 0.7 and 0.25, respectively. With one hidden layer the Kappa coefficient for ANN classifier was 0
Improved Autoassociative Neural Networks
NASA Technical Reports Server (NTRS)
Hand, Charles
2003-01-01
Improved autoassociative neural networks, denoted nexi, have been proposed for use in controlling autonomous robots, including mobile exploratory robots of the biomorphic type. In comparison with conventional autoassociative neural networks, nexi would be more complex but more capable in that they could be trained to do more complex tasks. A nexus would use bit weights and simple arithmetic in a manner that would enable training and operation without a central processing unit, programs, weight registers, or large amounts of memory. Only a relatively small amount of memory (to hold the bit weights) and a simple logic application- specific integrated circuit would be needed. A description of autoassociative neural networks is prerequisite to a meaningful description of a nexus. An autoassociative network is a set of neurons that are completely connected in the sense that each neuron receives input from, and sends output to, all the other neurons. (In some instantiations, a neuron could also send output back to its own input terminal.) The state of a neuron is completely determined by the inner product of its inputs with weights associated with its input channel. Setting the weights sets the behavior of the network. The neurons of an autoassociative network are usually regarded as comprising a row or vector. Time is a quantized phenomenon for most autoassociative networks in the sense that time proceeds in discrete steps. At each time step, the row of neurons forms a pattern: some neurons are firing, some are not. Hence, the current state of an autoassociative network can be described with a single binary vector. As time goes by, the network changes the vector. Autoassociative networks move vectors over hyperspace landscapes of possibilities.
Medical image analysis with artificial neural networks.
Jiang, J; Trundle, P; Ren, J
2010-12-01
Given that neural networks have been widely reported in the research community of medical imaging, we provide a focused literature survey on recent neural network developments in computer-aided diagnosis, medical image segmentation and edge detection towards visual content analysis, and medical image registration for its pre-processing and post-processing, with the aims of increasing awareness of how neural networks can be applied to these areas and to provide a foundation for further research and practical development. Representative techniques and algorithms are explained in detail to provide inspiring examples illustrating: (i) how a known neural network with fixed structure and training procedure could be applied to resolve a medical imaging problem; (ii) how medical images could be analysed, processed, and characterised by neural networks; and (iii) how neural networks could be expanded further to resolve problems relevant to medical imaging. In the concluding section, a highlight of comparisons among many neural network applications is included to provide a global view on computational intelligence with neural networks in medical imaging. PMID:20713305
Neural network with formed dynamics of activity
Dunin-Barkovskii, V.L.; Osovets, N.B.
1995-03-01
The problem of developing a neural network with a given pattern of the state sequence is considered. A neural network structure and an algorithm, of forming its bond matrix which lead to an approximate but robust solution of the problem are proposed and discussed. Limiting characteristics of the serviceability of the proposed structure are studied. Various methods of visualizing dynamic processes in a neural network are compared. Possible applications of the results obtained for interpretation of neurophysiological data and in neuroinformatics systems are discussed.
A new formulation for feedforward neural networks.
Razavi, Saman; Tolson, Bryan A
2011-10-01
Feedforward neural network is one of the most commonly used function approximation techniques and has been applied to a wide variety of problems arising from various disciplines. However, neural networks are black-box models having multiple challenges/difficulties associated with training and generalization. This paper initially looks into the internal behavior of neural networks and develops a detailed interpretation of the neural network functional geometry. Based on this geometrical interpretation, a new set of variables describing neural networks is proposed as a more effective and geometrically interpretable alternative to the traditional set of network weights and biases. Then, this paper develops a new formulation for neural networks with respect to the newly defined variables; this reformulated neural network (ReNN) is equivalent to the common feedforward neural network but has a less complex error response surface. To demonstrate the learning ability of ReNN, in this paper, two training methods involving a derivative-based (a variation of backpropagation) and a derivative-free optimization algorithms are employed. Moreover, a new measure of regularization on the basis of the developed geometrical interpretation is proposed to evaluate and improve the generalization ability of neural networks. The value of the proposed geometrical interpretation, the ReNN approach, and the new regularization measure are demonstrated across multiple test problems. Results show that ReNN can be trained more effectively and efficiently compared to the common neural networks and the proposed regularization measure is an effective indicator of how a network would perform in terms of generalization. PMID:21859600
NASA Technical Reports Server (NTRS)
Villarreal, James A.
1991-01-01
A whole new arena of computer technologies is now beginning to form. Still in its infancy, neural network technology is a biologically inspired methodology which draws on nature's own cognitive processes. The Software Technology Branch has provided a software tool, Neural Execution and Training System (NETS), to industry, government, and academia to facilitate and expedite the use of this technology. NETS is written in the C programming language and can be executed on a variety of machines. Once a network has been debugged, NETS can produce a C source code which implements the network. This code can then be incorporated into other software systems. Described here are various software projects currently under development with NETS and the anticipated future enhancements to NETS and the technology.
NASA Technical Reports Server (NTRS)
Lo, Ching F.
1999-01-01
The integration of Radial Basis Function Networks and Back Propagation Neural Networks with the Multiple Linear Regression has been accomplished to map nonlinear response surfaces over a wide range of independent variables in the process of the Modem Design of Experiments. The integrated method is capable to estimate the precision intervals including confidence and predicted intervals. The power of the innovative method has been demonstrated by applying to a set of wind tunnel test data in construction of response surface and estimation of precision interval.
Target detection using multilayer feedforward neural networks
NASA Astrophysics Data System (ADS)
Scherf, Alan V.; Scott, Peter A.
1991-08-01
Multilayer feedforward neural networks have been integrated with conventional image processing techniques to form a hybrid target detection algorithm for use in the F/A-18 FLIR pod advanced air-to-air track-while-scan mode. The network has been trained to detect and localize small targets in infrared imagery. Comparative performance between this target detection technique is evaluated.
NASA Astrophysics Data System (ADS)
Sanò, P.; Panegrossi, G.; Casella, D.; Di Paola, F.; Milani, L.; Mugnai, A.; Petracca, M.; Dietrich, S.
2015-02-01
The purpose of this study is to describe a new algorithm based on a neural network approach (Passive microwave Neural network Precipitation Retrieval - PNPR) for precipitation rate estimation from AMSU/MHS observations, and to provide examples of its performance for specific case studies over the European/Mediterranean area. The algorithm optimally exploits the different characteristics of Advanced Microwave Sounding Unit-A (AMSU-A) and the Microwave Humidity Sounder (MHS) channels, and their combinations, including the brightness temperature (TB) differences of the 183.31 channels, with the goal of having a single neural network for different types of background surfaces (vegetated land, snow-covered surface, coast and ocean). The training of the neural network is based on the use of a cloud-radiation database, built from cloud-resolving model simulations coupled to a radiative transfer model, representative of the European and Mediterranean Basin precipitation climatology. The algorithm provides also the phase of the precipitation and a pixel-based confidence index for the evaluation of the reliability of the retrieval. Applied to different weather conditions in Europe, the algorithm shows good performance both in the identification of precipitation areas and in the retrieval of precipitation, which is particularly valuable over the extremely variable environmental and meteorological conditions of the region. The PNPR is particularly efficient in (1) screening and retrieval of precipitation over different background surfaces; (2) identification and retrieval of heavy rain for convective events; and (3) identification of precipitation over a cold/iced background, with increased uncertainties affecting light precipitation. In this paper, examples of good agreement of precipitation pattern and intensity with ground-based data (radar and rain gauges) are provided for four different case studies. The algorithm has been developed in order to be easily tailored to new
Multistage neural network model for dynamic scene analysis
Ajjimarangsee, P.
1989-01-01
This research is concerned with dynamic scene analysis. The goal of scene analysis is to recognize objects and have a meaningful interpretation of the scene from which images are obtained. The task of the dynamic scene analysis process generally consists of region identification, motion analysis and object recognition. The objective of this research is to develop clustering algorithms using neural network approach and to investigate a multi-stage neural network model for region identification and motion analysis. The research is separated into three parts. First, a clustering algorithm using Kohonens' self-organizing feature map network is developed to be capable of generating continuous membership valued outputs. A newly developed version of the updating algorithm of the network is introduced to achieve a high degree of parallelism. A neural network model for the fuzzy c-means algorithm is proposed. In the second part, the parallel algorithms of a neural network model for clustering using the self-organizing feature maps approach and a neural network that models the fuzzy c-means algorithm are modified for implementation on a distributed memory parallel architecture. In the third part, supervised and unsupervised neural network models for motion analysis are investigated. For a supervised neural network, a three layer perceptron network is trained by a series of images to recognize the movement of the objects. For the unsupervised neural network, a self-organizing feature mapping network will learn to recognize the movement of the objects without an explicit training phase.
Parallel processing neural networks
Zargham, M.
1988-09-01
A model for Neural Network which is based on a particular kind of Petri Net has been introduced. The model has been implemented in C and runs on the Sequent Balance 8000 multiprocessor, however it can be directly ported to different multiprocessor environments. The potential advantages of using Petri Nets include: (1) the overall system is often easier to understand due to the graphical and precise nature of the representation scheme, (2) the behavior of the system can be analyzed using Petri Net theory. Though, the Petri Net is an obvious choice as a basis for the model, the basic Petri Net definition is not adequate to represent the neuronal system. To eliminate certain inadequacies more information has been added to the Petri Net model. In the model, a token represents either a processor or a post synaptic potential. Progress through a particular Neural Network is thus graphically depicted in the movement of the processor tokens through the Petri Net.
Neural networks for triggering
Denby, B. ); Campbell, M. ); Bedeschi, F. ); Chriss, N.; Bowers, C. ); Nesti, F. )
1990-01-01
Two types of neural network beauty trigger architectures, based on identification of electrons in jets and recognition of secondary vertices, have been simulated in the environment of the Fermilab CDF experiment. The efficiencies for B's and rejection of background obtained are encouraging. If hardware tests are successful, the electron identification architecture will be tested in the 1991 run of CDF. 10 refs., 5 figs., 1 tab.
Uniformly sparse neural networks
NASA Astrophysics Data System (ADS)
Haghighi, Siamack
1992-07-01
Application of neural networks to problems with a large number of sensory inputs is severely limited when the processing elements (PEs) need to be fully connected. This paper presents a new network model in which a trade off between the number of connections to a node and the number of processing layers can be made. This trade off is an important issue in the VLSI implementation of neural networks. The performance and capability of a hierarchical pyramidal network architecture of limited fan-in PE layers is analyzed. Analysis of this architecture requires the development of a new learning rule, since each PE has access to limited information about the entire network input. A spatially local unsupervised training rule is developed in which each PE optimizes the fraction of its output variance contributed by input correlations, resulting in PEs behaving as adaptive local correlation detectors. It is also shown that the output of a PE optimally represents the mutual information among the inputs to that PE. Applications of the developed model in image compression and motion detection are presented.
High-performance neural networks. [Neural computers
Dress, W.B.
1987-06-01
The new Forth hardware architectures offer an intermediate solution to high-performance neural networks while the theory and programming details of neural networks for synthetic intelligence are developed. This approach has been used successfully to determine the parameters and run the resulting network for a synthetic insect consisting of a 200-node ''brain'' with 1760 interconnections. Both the insect's environment and its sensor input have thus far been simulated. However, the frequency-coded nature of the Browning network allows easy replacement of the simulated sensors by real-world counterparts.
Adjoint-Operator Learning For A Neural Network
NASA Technical Reports Server (NTRS)
Barhen, Jacob; Toomarian, Nikzad
1993-01-01
Electronic neural networks made to synthesize initially unknown mathematical models of time-dependent phenomena or to learn temporally evolving patterns by use of algorithms based on adjoint operators. Algorithms less complicated, involve less computation and solve learning equations forward in time possibly simultaneously with equations of evolution of neural network, thereby both increasing computational efficiency and making real-time applications possible.
Budilova, E.V.; Terekhin, A.T.; Chepurnov, S.A.
1995-03-01
A hypothetical neural scheme is proposed that ensures efficient decision making by an animal searching for food in a maze. Only the general structure of the network is fixed; its quantitative characteristics are found by numerical optimization that simulates the process of natural selection. Selection is aimed at maximization of the expected number of descendants, which is directly related to the energy stored during the reproductive cycle. The main parameters to be optimized are the increments of the interneuronal links. and the working-memory constants.
NASA Astrophysics Data System (ADS)
Budilova, E. V.; Terekhin, A. T.; Chepurnov, S. A.
1994-09-01
A hypothetical neural scheme is proposed that ensures efficient decision making by an animal searching for food in a maze. Only the general structure of the network is fixed; its quantitative characteristics are found by numerical optimization that simulates the process of natural selection. Selection is aimed at maximization of the expected number of descendants, which is directly related to the energy stored during the reproductive cycle. The main parameters to be optimized are the increments of the interneuronal links and the working-memory constants.
Constructive Autoassociative Neural Network for Facial Recognition
Fernandes, Bruno J. T.; Cavalcanti, George D. C.; Ren, Tsang I.
2014-01-01
Autoassociative artificial neural networks have been used in many different computer vision applications. However, it is difficult to define the most suitable neural network architecture because this definition is based on previous knowledge and depends on the problem domain. To address this problem, we propose a constructive autoassociative neural network called CANet (Constructive Autoassociative Neural Network). CANet integrates the concepts of receptive fields and autoassociative memory in a dynamic architecture that changes the configuration of the receptive fields by adding new neurons in the hidden layer, while a pruning algorithm removes neurons from the output layer. Neurons in the CANet output layer present lateral inhibitory connections that improve the recognition rate. Experiments in face recognition and facial expression recognition show that the CANet outperforms other methods presented in the literature. PMID:25542018
NASA Technical Reports Server (NTRS)
Villarreal, James A.; Shelton, Robert O.
1992-01-01
Concept of space-time neural network affords distributed temporal memory enabling such network to model complicated dynamical systems mathematically and to recognize temporally varying spatial patterns. Digital filters replace synaptic-connection weights of conventional back-error-propagation neural network.
Moon, S W; Kong, S G
2001-01-01
This paper presents a novel block-based neural network (BBNN) model and the optimization of its structure and weights based on a genetic algorithm. The architecture of the BBNN consists of a 2D array of fundamental blocks with four variable input/output nodes and connection weights. Each block can have one of four different internal configurations depending on the structure settings, The BBNN model includes some restrictions such as 2D array and integer weights in order to allow easier implementation with reconfigurable hardware such as field programmable logic arrays (FPGA). The structure and weights of the BBNN are encoded with bit strings which correspond to the configuration bits of FPGA. The configuration bits are optimized globally using a genetic algorithm with 2D encoding and modified genetic operators. Simulations show that the optimized BBNN can solve engineering problems such as pattern classification and mobile robot control. PMID:18244385
Neural network training with global optimization techniques.
Yamazaki, Akio; Ludermir, Teresa B
2003-04-01
This paper presents an approach of using Simulated Annealing and Tabu Search for the simultaneous optimization of neural network architectures and weights. The problem considered is the odor recognition in an artificial nose. Both methods have produced networks with high classification performance and low complexity. Generalization has been improved by using the backpropagation algorithm for fine tuning. The combination of simple and traditional search methods has shown to be very suitable for generating compact and efficient networks. PMID:12923920
Accelerating Learning By Neural Networks
NASA Technical Reports Server (NTRS)
Toomarian, Nikzad; Barhen, Jacob
1992-01-01
Electronic neural networks made to learn faster by use of terminal teacher forcing. Method of supervised learning involves addition of teacher forcing functions to excitations fed as inputs to output neurons. Initially, teacher forcing functions are strong enough to force outputs to desired values; subsequently, these functions decay with time. When learning successfully completed, terminal teacher forcing vanishes, and dynamics or neural network become equivalent to those of conventional neural network. Simulated neural network with terminal teacher forcing learned to produce close approximation of circular trajectory in 400 iterations.
NASA Astrophysics Data System (ADS)
Sellitto, P.; Del Frate, F.
2014-07-01
Atmospheric temperature profiles are inferred from passive satellite instruments, using thermal infrared or microwave observations. Here we investigate on the feasibility of the retrieval of height resolved temperature information in the ultraviolet spectral region. The temperature dependence of the absorption cross sections of ozone in the Huggins band, in particular in the interval 320-325 nm, is exploited. We carried out a sensitivity analysis and demonstrated that a non-negligible information on the temperature profile can be extracted from this small band. Starting from these results, we developed a neural network inversion algorithm, trained and tested with simulated nadir EnviSat-SCIAMACHY ultraviolet observations. The algorithm is able to retrieve the temperature profile with root mean square errors and biases comparable to existing retrieval schemes that use thermal infrared or microwave observations. This demonstrates, for the first time, the feasibility of temperature profiles retrieval from space-borne instruments operating in the ultraviolet.
Chaudhry, S.R.; Ahmed-Zaid, S.; Demerdash, N.A.
1995-12-01
An artificial neural network (ANN) is used in the identification of saturated synchronous machine parameters under diverse operating conditions. The training data base for the ANN is generated by a time-stepping coupled finite-element/state-space (CFE-SS) modeling technique which is used in the computation of the saturated parameters of a 20-kV, 733-MVA, 0.85 pf (lagging) turbogenerator at discrete load points in the P-Q capability plane for three different levels of terminal voltage. These computed parameters constitute a learning data base for a multilayer ANN structure which is successfully trained using the back-propagation algorithm. Results indicate that the trained ANN can identify saturated machine reactances for arbitrary load points in the P-Q plane with an error less than 2% of those values obtained directly from the CFE-SS algorithm. Thus, significant savings in computational time are obtained in such parameter computation tasks.
NASA Astrophysics Data System (ADS)
Khajeh, Mostafa; Golzary, Ali Reza
2014-10-01
In this work, zinc nanoparticles-chitosan based solid phase extraction has been developed for separation and preconcentration of trace amount of methyl orange from water samples. Artificial neural network-cuckoo optimization algorithm has been employed to develop the model for simulation and optimization of this method. The pH, volume of elution solvent, mass of zinc oxide nanoparticles-chitosan, flow rate of sample and elution solvent were the input variables, while recovery of methyl orange was the output. The optimum conditions were obtained by cuckoo optimization algorithm. At the optimum conditions, the limit of detections of 0.7 μg L-1was obtained for the methyl orange. The developed procedure was then applied to the separation and preconcentration of methyl orange from water samples.
Khajeh, Mostafa; Golzary, Ali Reza
2014-10-15
In this work, zinc nanoparticles-chitosan based solid phase extraction has been developed for separation and preconcentration of trace amount of methyl orange from water samples. Artificial neural network-cuckoo optimization algorithm has been employed to develop the model for simulation and optimization of this method. The pH, volume of elution solvent, mass of zinc oxide nanoparticles-chitosan, flow rate of sample and elution solvent were the input variables, while recovery of methyl orange was the output. The optimum conditions were obtained by cuckoo optimization algorithm. At the optimum conditions, the limit of detections of 0.7μgL(-1)was obtained for the methyl orange. The developed procedure was then applied to the separation and preconcentration of methyl orange from water samples. PMID:24835725
Classification of radar clutter using neural networks.
Haykin, S; Deng, C
1991-01-01
A classifier that incorporates both preprocessing and postprocessing procedures as well as a multilayer feedforward network (based on the back-propagation algorithm) in its design to distinguish between several major classes of radar returns including weather, birds, and aircraft is described. The classifier achieves an average classification accuracy of 89% on generalization for data collected during a single scan of the radar antenna. The procedures of feature selection for neural network training, the classifier design considerations, the learning algorithm development, the implementation, and the experimental results of the neural clutter classifier, which is simulated on a Warp systolic computer, are discussed. A comparative evaluation of the multilayer neural network with a traditional Bayes classifier is presented. PMID:18282874
Bornholdt, S.; Graudenz, D.
1993-07-01
A learning algorithm based on genetic algorithms for asymmetric neural networks with an arbitrary structure is presented. It is suited for the learning of temporal patterns and leads to stable neural networks with feedback.
Ugena, L; Moncayo, S; Manzoor, S; Rosales, D; Cáceres, J O
2016-01-01
The detection of adulteration of fuels and its use in criminal scenes like arson has a high interest in forensic investigations. In this work, a method based on gas chromatography (GC) and neural networks (NN) has been developed and applied to the identification and discrimination of brands of fuels such as gasoline and diesel without the necessity to determine the composition of the samples. The study included five main brands of fuels from Spain, collected from fifteen different local petrol stations. The methodology allowed the identification of the gasoline and diesel brands with a high accuracy close to 100%, without any false positives or false negatives. A success rate of three blind samples was obtained as 73.3%, 80%, and 100%, respectively. The results obtained demonstrate the potential of this methodology to help in resolving criminal situations. PMID:27375919
Ugena, L.; Moncayo, S.; Manzoor, S.; Rosales, D.
2016-01-01
The detection of adulteration of fuels and its use in criminal scenes like arson has a high interest in forensic investigations. In this work, a method based on gas chromatography (GC) and neural networks (NN) has been developed and applied to the identification and discrimination of brands of fuels such as gasoline and diesel without the necessity to determine the composition of the samples. The study included five main brands of fuels from Spain, collected from fifteen different local petrol stations. The methodology allowed the identification of the gasoline and diesel brands with a high accuracy close to 100%, without any false positives or false negatives. A success rate of three blind samples was obtained as 73.3%, 80%, and 100%, respectively. The results obtained demonstrate the potential of this methodology to help in resolving criminal situations. PMID:27375919
Neural network error correction for solving coupled ordinary differential equations
NASA Technical Reports Server (NTRS)
Shelton, R. O.; Darsey, J. A.; Sumpter, B. G.; Noid, D. W.
1992-01-01
A neural network is presented to learn errors generated by a numerical algorithm for solving coupled nonlinear differential equations. The method is based on using a neural network to correctly learn the error generated by, for example, Runge-Kutta on a model molecular dynamics (MD) problem. The neural network programs used in this study were developed by NASA. Comparisons are made for training the neural network using backpropagation and a new method which was found to converge with fewer iterations. The neural net programs, the MD model and the calculations are discussed.
Dynamic interactions in neural networks
Arbib, M.A. ); Amari, S. )
1989-01-01
The study of neural networks is enjoying a great renaissance, both in computational neuroscience, the development of information processing models of living brains, and in neural computing, the use of neurally inspired concepts in the construction of intelligent machines. This volume presents models and data on the dynamic interactions occurring in the brain, and exhibits the dynamic interactions between research in computational neuroscience and in neural computing. The authors present current research, future trends and open problems.
Neural network applications in telecommunications
NASA Technical Reports Server (NTRS)
Alspector, Joshua
1994-01-01
Neural network capabilities include automatic and organized handling of complex information, quick adaptation to continuously changing environments, nonlinear modeling, and parallel implementation. This viewgraph presentation presents Bellcore work on applications, learning chip computational function, learning system block diagram, neural network equalization, broadband access control, calling-card fraud detection, software reliability prediction, and conclusions.
Neural Networks for the Beginner.
ERIC Educational Resources Information Center
Snyder, Robin M.
Motivated by the brain, neural networks are a right-brained approach to artificial intelligence that is used to recognize patterns based on previous training. In practice, one would not program an expert system to recognize a pattern and one would not train a neural network to make decisions from rules; but one could combine the best features of…
Privacy-preserving backpropagation neural network learning.
Chen, Tingting; Zhong, Sheng
2009-10-01
With the development of distributed computing environment , many learning problems now have to deal with distributed input data. To enhance cooperations in learning, it is important to address the privacy concern of each data holder by extending the privacy preservation notion to original learning algorithms. In this paper, we focus on preserving the privacy in an important learning model, multilayer neural networks. We present a privacy-preserving two-party distributed algorithm of backpropagation which allows a neural network to be trained without requiring either party to reveal her data to the other. We provide complete correctness and security analysis of our algorithms. The effectiveness of our algorithms is verified by experiments on various real world data sets. PMID:19709975
Artificial Astrocytes Improve Neural Network Performance
Porto-Pazos, Ana B.; Veiguela, Noha; Mesejo, Pablo; Navarrete, Marta; Alvarellos, Alberto; Ibáñez, Oscar; Pazos, Alejandro; Araque, Alfonso
2011-01-01
Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function. PMID:21526157
Artificial astrocytes improve neural network performance.
Porto-Pazos, Ana B; Veiguela, Noha; Mesejo, Pablo; Navarrete, Marta; Alvarellos, Alberto; Ibáñez, Oscar; Pazos, Alejandro; Araque, Alfonso
2011-01-01
Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function. PMID:21526157
Neural Network Development Tool (NETS)
NASA Technical Reports Server (NTRS)
Baffes, Paul T.
1990-01-01
Artificial neural networks formed from hundreds or thousands of simulated neurons, connected in manner similar to that in human brain. Such network models learning behavior. Using NETS involves translating problem to be solved into input/output pairs, designing network configuration, and training network. Written in C.
Digital Neural Networks for New Media
NASA Astrophysics Data System (ADS)
Spaanenburg, Lambert; Malki, Suleyman
Neural Networks perform computationally intensive tasks offering smart solutions for many new media applications. A number of analog and mixed digital/analog implementations have been proposed to smooth the algorithmic gap. But gradually, the digital implementation has become feasible, and the dedicated neural processor is on the horizon. A notable example is the Cellular Neural Network (CNN). The analog direction has matured for low-power, smart vision sensors; the digital direction is gradually being shaped into an IP-core for algorithm acceleration, especially for use in FPGA-based high-performance systems. The chapter discusses the next step towards a flexible and scalable multi-core engine using Application-Specific Integrated Processors (ASIP). This topographic engine can serve many new media tasks, as illustrated by novel applications in Homeland Security. We conclude with a view on the CNN kaleidoscope for the year 2020.
2013-01-01
Background There is an increasing trend in using robots for medical purposes. One specific area is rehabilitation. Rehabilitation is one of the non-drug treatments in community health which means the restoration of the abilities to maximize independence. It is a prolonged work and costly labor. On the other hand, by using the flexible and efficient robots in rehabilitation area, this process will be more useful for handicapped patients. Methods In this study, a rule-based intelligent control methodology is proposed to mimic the behavior of a healthy limb in a satisfactory way by a 2-DOF planar robot. Inverse kinematic of the planar robot will be solved by neural networks and control parameters will be optimized by genetic algorithm, as rehabilitation progress. Results The results of simulations are presented by defining a physiotherapy simple mode on desired trajectory. MATLAB/Simulink is used for simulations. The system is capable of learning the action of the physiotherapist for each patient and imitating this behaviour in the absence of a physiotherapist that can be called robotherapy. Conclusions In this study, a therapeutic exercise planar 2-DOF robot is designed and controlled for lower-limb rehabilitation. The robot manipulator is controlled by combination of hybrid and adaptive controls. Some safety factors and stability constraints are defined and obtained. The robot is stopped when the safety factors are not satisfied. Kinematics of robot is estimated by an MLP neural network and proper control parameters are achieved using GA optimization. PMID:23945420
Neural network tomography: network replication from output surface geometry.
Minnett, Rupert C J; Smith, Andrew T; Lennon, William C; Hecht-Nielsen, Robert
2011-06-01
Multilayer perceptron networks whose outputs consist of affine combinations of hidden units using the tanh activation function are universal function approximators and are used for regression, typically by reducing the MSE with backpropagation. We present a neural network weight learning algorithm that directly positions the hidden units within input space by numerically analyzing the curvature of the output surface. Our results show that under some sampling requirements, this method can reliably recover the parameters of a neural network used to generate a data set. PMID:21377326
Neural networks: a biased overview
Domany, E.
1988-06-01
An overview of recent activity in the field of neural networks is presented. The long-range aim of this research is to understand how the brain works. First some of the problems are stated and terminology defined; then an attempt is made to explain why physicists are drawn to the field, and their main potential contribution. In particular, in recent years some interesting models have been introduced by physicists. A small subset of these models is described, with particular emphasis on those that are analytically soluble. Finally a brief review of the history and recent developments of single- and multilayer perceptrons is given, bringing the situation up to date regarding the central immediate problem of the field: search for a learning algorithm that has an associated convergence theorem.
Neural networks for calibration tomography
NASA Technical Reports Server (NTRS)
Decker, Arthur
1993-01-01
Artificial neural networks are suitable for performing pattern-to-pattern calibrations. These calibrations are potentially useful for facilities operations in aeronautics, the control of optical alignment, and the like. Computed tomography is compared with neural net calibration tomography for estimating density from its x-ray transform. X-ray transforms are measured, for example, in diffuse-illumination, holographic interferometry of fluids. Computed tomography and neural net calibration tomography are shown to have comparable performance for a 10 degree viewing cone and 29 interferograms within that cone. The system of tomography discussed is proposed as a relevant test of neural networks and other parallel processors intended for using flow visualization data.
Web traffic prediction with artificial neural networks
NASA Astrophysics Data System (ADS)
Gluszek, Adam; Kekez, Michal; Rudzinski, Filip
2005-02-01
The main aim of the paper is to present application of the artificial neural network in the web traffic prediction. First, the general problem of time series modelling and forecasting is shortly described. Next, the details of building of dynamic processes models with the neural networks are discussed. At this point determination of the model structure in terms of its inputs and outputs is the most important question because this structure is a rough approximation of the dynamics of the modelled process. The following section of the paper presents the results obtained applying artificial neural network (classical multilayer perceptron trained with backpropagation algorithm) to the real-world web traffic prediction. Finally, we discuss the results, describe weak points of presented method and propose some alternative approaches.
Modular, Hierarchical Learning By Artificial Neural Networks
NASA Technical Reports Server (NTRS)
Baldi, Pierre F.; Toomarian, Nikzad
1996-01-01
Modular and hierarchical approach to supervised learning by artificial neural networks leads to neural networks more structured than neural networks in which all neurons fully interconnected. These networks utilize general feedforward flow of information and sparse recurrent connections to achieve dynamical effects. The modular organization, sparsity of modular units and connections, and fact that learning is much more circumscribed are all attractive features for designing neural-network hardware. Learning streamlined by imitating some aspects of biological neural networks.
Application of artificial neural networks to composite ply micromechanics
NASA Technical Reports Server (NTRS)
Brown, D. A.; Murthy, P. L. N.; Berke, L.
1991-01-01
Artificial neural networks can provide improved computational efficiency relative to existing methods when an algorithmic description of functional relationships is either totally unavailable or is complex in nature. For complex calculations, significant reductions in elapsed computation time are possible. The primary goal is to demonstrate the applicability of artificial neural networks to composite material characterization. As a test case, a neural network was trained to accurately predict composite hygral, thermal, and mechanical properties when provided with basic information concerning the environment, constituent materials, and component ratios used in the creation of the composite. A brief introduction on neural networks is provided along with a description of the project itself.
Neural Networks for Readability Analysis.
ERIC Educational Resources Information Center
McEneaney, John E.
This paper describes and reports on the performance of six related artificial neural networks that have been developed for the purpose of readability analysis. Two networks employ counts of linguistic variables that simulate a traditional regression-based approach to readability. The remaining networks determine readability from "visual snapshots"…
A neural network approach to cloud classification
NASA Technical Reports Server (NTRS)
Lee, Jonathan; Weger, Ronald C.; Sengupta, Sailes K.; Welch, Ronald M.
1990-01-01
It is shown that, using high-spatial-resolution data, very high cloud classification accuracies can be obtained with a neural network approach. A texture-based neural network classifier using only single-channel visible Landsat MSS imagery achieves an overall cloud identification accuracy of 93 percent. Cirrus can be distinguished from boundary layer cloudiness with an accuracy of 96 percent, without the use of an infrared channel. Stratocumulus is retrieved with an accuracy of 92 percent, cumulus at 90 percent. The use of the neural network does not improve cirrus classification accuracy. Rather, its main effect is in the improved separation between stratocumulus and cumulus cloudiness. While most cloud classification algorithms rely on linear parametric schemes, the present study is based on a nonlinear, nonparametric four-layer neural network approach. A three-layer neural network architecture, the nonparametric K-nearest neighbor approach, and the linear stepwise discriminant analysis procedure are compared. A significant finding is that significantly higher accuracies are attained with the nonparametric approaches using only 20 percent of the database as training data, compared to 67 percent of the database in the linear approach.
NASA Astrophysics Data System (ADS)
Akkaş, Efe; Evren Çubukçu, H.; Akin, Lutfiye; Erkut, Volkan; Yurdakul, Yasin; Karayigit, Ali Ihsan
2016-04-01
Identification of zeolite group minerals is complicated due to their similar chemical formulas and habits. Although the morphologies of various zeolite crystals can be recognized under Scanning Electron Microscope (SEM), it is relatively more challenging and problematic process to identify zeolites using their mineral chemical data. SEMs integrated with energy dispersive X-ray spectrometers (EDS) provide fast and reliable chemical data of minerals. However, considering elemental similarities of characteristic chemical formulae of zeolite species (e.g. Clinoptilolite ((Na,K,Ca)2 ‑3Al3(Al,Si)2Si13O3612H2O) and Erionite ((Na2,K2,Ca)2Al4Si14O36ṡ15H2O)) EDS data alone does not seem to be sufficient for correct identification. Furthermore, the physical properties of the specimen (e.g. roughness, electrical conductivity) and the applied analytical conditions (e.g. accelerating voltage, beam current, spot size) of the SEM-EDS should be uniform in order to obtain reliable elemental results of minerals having high alkali (Na, K) and H2O (approx. %14-18) contents. This study which was funded by The Scientific and Technological Research Council of Turkey (TUBITAK Project No: 113Y439), aims to construct a database as large as possible for various zeolite minerals and to develop a general prediction model for the identification of zeolite minerals using SEM-EDS data. For this purpose, an artificial neural network and rule based decision tree algorithm were employed. Throughout the analyses, a total of 1850 chemical data were collected from four distinct zeolite species, (Clinoptilolite-Heulandite, Erionite, Analcime and Mordenite) observed in various rocks (e.g. coals, pyroclastics). In order to obtain a representative training data set for each minerals, a selection procedure for reference mineral analyses was applied. During the selection procedure, SEM based crystal morphology data, XRD spectra and re-calculated cationic distribution, obtained by EDS have been used for
NASA Technical Reports Server (NTRS)
Villarreal, James A.; Shelton, Robert O.
1991-01-01
Introduced here is a novel technique which adds the dimension of time to the well known back propagation neural network algorithm. Cited here are several reasons why the inclusion of automated spatial and temporal associations are crucial to effective systems modeling. An overview of other works which also model spatiotemporal dynamics is furnished. A detailed description is given of the processes necessary to implement the space-time network algorithm. Several demonstrations that illustrate the capabilities and performance of this new architecture are given.
Chiang, Kai-Wei; Chang, Hsiu-Wen; Li, Chia-Yuan; Huang, Yun-Wen
2009-01-01
Digital mobile mapping, which integrates digital imaging with direct geo-referencing, has developed rapidly over the past fifteen years. Direct geo-referencing is the determination of the time-variable position and orientation parameters for a mobile digital imager. The most common technologies used for this purpose today are satellite positioning using Global Positioning System (GPS) and Inertial Navigation System (INS) using an Inertial Measurement Unit (IMU). They are usually integrated in such a way that the GPS receiver is the main position sensor, while the IMU is the main orientation sensor. The Kalman Filter (KF) is considered as the optimal estimation tool for real-time INS/GPS integrated kinematic position and orientation determination. An intelligent hybrid scheme consisting of an Artificial Neural Network (ANN) and KF has been proposed to overcome the limitations of KF and to improve the performance of the INS/GPS integrated system in previous studies. However, the accuracy requirements of general mobile mapping applications can't be achieved easily, even by the use of the ANN-KF scheme. Therefore, this study proposes an intelligent position and orientation determination scheme that embeds ANN with conventional Rauch-Tung-Striebel (RTS) smoother to improve the overall accuracy of a MEMS INS/GPS integrated system in post-mission mode. By combining the Micro Electro Mechanical Systems (MEMS) INS/GPS integrated system and the intelligent ANN-RTS smoother scheme proposed in this study, a cheaper but still reasonably accurate position and orientation determination scheme can be anticipated. PMID:22574034
Chiang, Kai-Wei; Chang, Hsiu-Wen; Li, Chia-Yuan; Huang, Yun-Wen
2009-01-01
Digital mobile mapping, which integrates digital imaging with direct geo-referencing, has developed rapidly over the past fifteen years. Direct geo-referencing is the determination of the time-variable position and orientation parameters for a mobile digital imager. The most common technologies used for this purpose today are satellite positioning using Global Positioning System (GPS) and Inertial Navigation System (INS) using an Inertial Measurement Unit (IMU). They are usually integrated in such a way that the GPS receiver is the main position sensor, while the IMU is the main orientation sensor. The Kalman Filter (KF) is considered as the optimal estimation tool for real-time INS/GPS integrated kinematic position and orientation determination. An intelligent hybrid scheme consisting of an Artificial Neural Network (ANN) and KF has been proposed to overcome the limitations of KF and to improve the performance of the INS/GPS integrated system in previous studies. However, the accuracy requirements of general mobile mapping applications can’t be achieved easily, even by the use of the ANN-KF scheme. Therefore, this study proposes an intelligent position and orientation determination scheme that embeds ANN with conventional Rauch-Tung-Striebel (RTS) smoother to improve the overall accuracy of a MEMS INS/GPS integrated system in post-mission mode. By combining the Micro Electro Mechanical Systems (MEMS) INS/GPS integrated system and the intelligent ANN-RTS smoother scheme proposed in this study, a cheaper but still reasonably accurate position and orientation determination scheme can be anticipated. PMID:22574034
Neural network and letter recognition
Lee, Hue Yeon.
1989-01-01
Neural net architectures and learning algorithms that recognize hand written 36 alphanumeric characters are studied. The thin line input patterns written in 32 x 32 binary array are used. The system is comprised of two major components, viz. a preprocessing unit and a Recognition unit. The preprocessing unit in turn consists of three layers of neurons; the U-layer, the V-layer, and the C-layer. The functions of the U-layer is to extract local features by template matching. The correlation between the detected local features are considered. Through correlating neurons in a plane with their neighboring neurons, the V-layer would thicken the on-cells or lines that are groups of on-cells of the previous layer. These two correlations would yield some deformation tolerance and some of the rotational tolerance of the system. The C-layer then compresses data through the Gabor transform. Pattern dependent choice of center and wavelengths of Gabor filters is the cause of shift and scale tolerance of the system. Three different learning schemes had been investigated in the recognition unit, namely; the error back propagation learning with hidden units, a simple perceptron learning, and a competitive learning. Their performances were analyzed and compared. Since sometimes the network fails to distinguish between two letters that are inherently similar, additional ambiguity resolving neural nets are introduced on top of the above main neural net. The two dimensional Fourier transform is used as the preprocessing and the perceptron is used as the recognition unit of the ambiguity resolver. One hundred different person's handwriting sets are collected. Some of these are used as the training sets and the remainders are used as the test sets.
Artificial neural networks and Abelian harmonic analysis
NASA Astrophysics Data System (ADS)
Rodriguez, Domingo; Pertuz-Campo, Jairo
1991-12-01
This work deals with the use of artificial neural networks (ANN) for the digital processing of finite discrete time signals. The effort concentrates on the efficient replacement of fast Fourier transform (FFT) algorithms with ANN algorithms in certain engineering and scientific applications. The FFT algorithms are efficient methods of computing the discrete Fourier transform (DFT). The ubiquitous DFT is utilized in almost every digital signal processing application where harmonic analysis information is needed. Applications abound in areas such as audio acoustics, geophysics, biomedicine, telecommunications, astrophysics, etc. To identify more efficient methods to obtain a desired spectral information will result in a reduction in the computational effort required to implement these applications.
Neural Networks Of VLSI Components
NASA Technical Reports Server (NTRS)
Eberhardt, Silvio P.
1991-01-01
Concept for design of electronic neural network calls for assembly of very-large-scale integrated (VLSI) circuits of few standard types. Each VLSI chip, which contains both analog and digital circuitry, used in modular or "building-block" fashion by interconnecting it in any of variety of ways with other chips. Feedforward neural network in typical situation operates under control of host computer and receives inputs from, and sends outputs to, other equipment.
Correlational Neural Networks.
Chandar, Sarath; Khapra, Mitesh M; Larochelle, Hugo; Ravindran, Balaraman
2016-02-01
Common representation learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, has been receiving a lot of attention recently. Two popular paradigms here are canonical correlation analysis (CCA)-based approaches and autoencoder (AE)-based approaches. CCA-based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace. AE-based methods learn a common representation by minimizing the error of reconstructing the two views. Each of these approaches has its own advantages and disadvantages. For example, while CCA-based approaches outperform AE-based approaches for the task of transfer learning, they are not as scalable as the latter. In this work, we propose an AE-based approach, correlational neural network (CorrNet), that explicitly maximizes correlation among the views when projected to the common subspace. Through a series of experiments, we demonstrate that the proposed CorrNet is better than AE and CCA with respect to its ability to learn correlated common representations. We employ CorrNet for several cross-language tasks and show that the representations learned using it perform better than the ones learned using other state-of-the-art approaches. PMID:26654210
Application of four-layer neural network on information extraction.
Han, Min; Cheng, Lei; Meng, Hua
2003-01-01
This paper applies neural network to extract marsh information. An adaptive back-propagation algorithm based on a robust error function is introduced to build a four-layer neural network, and it is used to classify Thematic Mapper (TM) image of Zhalong Wetland in China and then extract marsh information. Comparing marsh information extraction results of the four-layer neural network with three-layer neural network and the maximum likelihood classifier, conclusion can be drawn as follows: the structure of the four-layer neural network and the adaptive back-propagation algorithm based on the robust error function is effective to extract marsh information. The four-layer neural network adopted in this paper succeeded in building the complex model of TM image, and it avoided the problem of great storage of remotely sensed data, and the adaptive back-propagation algorithm speeded up the descending of error. Above all, the four-layer neural network is superior to the three-layer neural network and the maximum likelihood classifier in the accuracy of the total classification and marsh information extraction. PMID:12850006
VLSI implementable neural networks for target tracking
NASA Astrophysics Data System (ADS)
Himes, Glenn S.; Inigo, Rafael M.; Narathong, Chiewcharn
1991-08-01
This paper describes part of an integrated system for target tracking. The image is acquired, edge detected, and segmented by a subsystem not discussed in this paper. Algorithms to determine the centroid of a windowed target using neural networks are developed. Further, once the target centroid is determined, it is continuously updated in order to track the trajectory, since the centroid location is not dependent on scaling or rotation on the optical axis. The image is then mapped to a log-spiral grid. A conformal transformation is used to map the log-spiral grid to a computation plane in which rotations and scalings are transformed to displacements along the vertical and horizonal axes, respectively. The images in this plane are used for recognition. The recognition algorithms are the subject of another paper. A second neural network, also described in this paper, is then used to determine object rotation and scaling. The algorithm used by this network is an original line correlator tracker which, as the name indicates, uses linear instead of 2D correlations. Simulation results using ICBM images are presented for both the centroid neural net and the rotation-scaling detection network.
Computationally Efficient Neural Network Intrusion Security Awareness
Todd Vollmer; Milos Manic
2009-08-01
An enhanced version of an algorithm to provide anomaly based intrusion detection alerts for cyber security state awareness is detailed. A unique aspect is the training of an error back-propagation neural network with intrusion detection rule features to provide a recognition basis. Network packet details are subsequently provided to the trained network to produce a classification. This leverages rule knowledge sets to produce classifications for anomaly based systems. Several test cases executed on ICMP protocol revealed a 60% identification rate of true positives. This rate matched the previous work, but 70% less memory was used and the run time was reduced to less than 1 second from 37 seconds.
NASA Astrophysics Data System (ADS)
Wang, Zhanyong; Lu, Feng; He, Hong-di; Lu, Qing-Chang; Wang, Dongsheng; Peng, Zhong-Ren
2015-03-01
At road intersections, vehicles frequently stop with idling engines during the red-light period and speed up rapidly in the green-light period, which generates higher velocity fluctuation and thus higher emission rates. Additionally, the frequent changes of wind direction further add the highly variable dispersion of pollutants at the street scale. It is, therefore, very difficult to estimate the distribution of pollutant concentrations using conventional deterministic causal models. For this reason, a hybrid model combining wavelet neural network and genetic algorithm (GA-WNN) is proposed for predicting 5-min series of carbon monoxide (CO) and fine particulate matter (PM2.5) concentrations in proximity to an intersection. The proposed model is examined based on the measured data under two situations. As the measured pollutant concentrations are found to be dependent on the distance to the intersection, the model is evaluated in three locations respectively, i.e. 110 m, 330 m and 500 m. Due to the different variation of pollutant concentrations on varied time, the model is also evaluated in peak and off-peak traffic time periods separately. Additionally, the proposed model, together with the back-propagation neural network (BPNN), is examined with the measured data in these situations. The proposed model is found to perform better in predictability and precision for both CO and PM2.5 than BPNN does, implying that the hybrid model can be an effective tool to improve the accuracy of estimating pollutants' distribution pattern at intersections. The outputs of these findings demonstrate the potential of the proposed model to be applicable to forecast the distribution pattern of air pollution in real-time in proximity to road intersection.
Foetal ECG recovery using dynamic neural networks.
Camps-Valls, Gustavo; Martínez-Sober, Marcelino; Soria-Olivas, Emilio; Magdalena-Benedito, Rafael; Calpe-Maravilla, Javier; Guerrero-Martínez, Juan
2004-07-01
Non-invasive electrocardiography has proven to be a very interesting method for obtaining information about the foetus state and thus to assure its well-being during pregnancy. One of the main applications in this field is foetal electrocardiogram (ECG) recovery by means of automatic methods. Evident problems found in the literature are the limited number of available registers, the lack of performance indicators, and the limited use of non-linear adaptive methods. In order to circumvent these problems, we first introduce the generation of synthetic registers and discuss the influence of different kinds of noise to the modelling. Second, a method which is based on numerical (correlation coefficient) and statistical (analysis of variance, ANOVA) measures allows us to select the best recovery model. Finally, finite impulse response (FIR) and gamma neural networks are included in the adaptive noise cancellation (ANC) scheme in order to provide highly non-linear, dynamic capabilities to the recovery model. Neural networks are benchmarked with classical adaptive methods such as the least mean squares (LMS) and the normalized LMS (NLMS) algorithms in simulated and real registers and some conclusions are drawn. For synthetic registers, the most determinant factor in the identification of the models is the foetal-maternal signal-to-noise ratio (SNR). In addition, as the electromyogram contribution becomes more relevant, neural networks clearly outperform the LMS-based algorithm. From the ANOVA test, we found statistical differences between LMS-based models and neural models when complex situations (high foetal-maternal and foetal-noise SNRs) were present. These conclusions were confirmed after doing robustness tests on synthetic registers, visual inspection of the recovered signals and calculation of the recognition rates of foetal R-peaks for real situations. Finally, the best compromise between model complexity and outcomes was provided by the FIR neural network. Both
Program PSNN (Plasma Spectroscopy Neural Network)
Morgan, W.L.; Larsen, J.T.
1993-08-01
This program uses the standard ``delta rule`` back-propagation supervised training algorithm for multi-layer neural networks. The inputs are line intensities in arbitrary units, which are then normalized within the program. The outputs are T{sub e}(eV), N{sub e}(cm{sup {minus}3}), and a fractional ionization, which in our testing using H- and He-like spectra, was N(He)/[N(H) + N(He)].
Membership generation using multilayer neural network
NASA Technical Reports Server (NTRS)
Kim, Jaeseok
1992-01-01
There has been intensive research in neural network applications to pattern recognition problems. Particularly, the back-propagation network has attracted many researchers because of its outstanding performance in pattern recognition applications. In this section, we describe a new method to generate membership functions from training data using a multilayer neural network. The basic idea behind the approach is as follows. The output values of a sigmoid activation function of a neuron bear remarkable resemblance to membership values. Therefore, we can regard the sigmoid activation values as the membership values in fuzzy set theory. Thus, in order to generate class membership values, we first train a suitable multilayer network using a training algorithm such as the back-propagation algorithm. After the training procedure converges, the resulting network can be treated as a membership generation network, where the inputs are feature values and the outputs are membership values in the different classes. This method allows fairly complex membership functions to be generated because the network is highly nonlinear in general. Also, it is to be noted that the membership functions are generated from a classification point of view. For pattern recognition applications, this is highly desirable, although the membership values may not be indicative of the degree of typicality of a feature value in a particular class.
Fuzzy logic and neural network technologies
NASA Technical Reports Server (NTRS)
Villarreal, James A.; Lea, Robert N.; Savely, Robert T.
1992-01-01
Applications of fuzzy logic technologies in NASA projects are reviewed to examine their advantages in the development of neural networks for aerospace and commercial expert systems and control. Examples of fuzzy-logic applications include a 6-DOF spacecraft controller, collision-avoidance systems, and reinforcement-learning techniques. The commercial applications examined include a fuzzy autofocusing system, an air conditioning system, and an automobile transmission application. The practical use of fuzzy logic is set in the theoretical context of artificial neural systems (ANSs) to give the background for an overview of ANS research programs at NASA. The research and application programs include the Network Execution and Training Simulator and faster training algorithms such as the Difference Optimized Training Scheme. The networks are well suited for pattern-recognition applications such as predicting sunspots, controlling posture maintenance, and conducting adaptive diagnoses.
Neural networks: Application to medical imaging
NASA Technical Reports Server (NTRS)
Clarke, Laurence P.
1994-01-01
The research mission is the development of computer assisted diagnostic (CAD) methods for improved diagnosis of medical images including digital x-ray sensors and tomographic imaging modalities. The CAD algorithms include advanced methods for adaptive nonlinear filters for image noise suppression, hybrid wavelet methods for feature segmentation and enhancement, and high convergence neural networks for feature detection and VLSI implementation of neural networks for real time analysis. Other missions include (1) implementation of CAD methods on hospital based picture archiving computer systems (PACS) and information networks for central and remote diagnosis and (2) collaboration with defense and medical industry, NASA, and federal laboratories in the area of dual use technology conversion from defense or aerospace to medicine.
Application of artificial neural networks in nonlinear analysis of trusses
NASA Technical Reports Server (NTRS)
Alam, J.; Berke, L.
1991-01-01
A method is developed to incorporate neural network model based upon the Backpropagation algorithm for material response into nonlinear elastic truss analysis using the initial stiffness method. Different network configurations are developed to assess the accuracy of neural network modeling of nonlinear material response. In addition to this, a scheme based upon linear interpolation for material data, is also implemented for comparison purposes. It is found that neural network approach can yield very accurate results if used with care. For the type of problems under consideration, it offers a viable alternative to other material modeling methods.
Multiprocessor Neural Network in Healthcare.
Godó, Zoltán Attila; Kiss, Gábor; Kocsis, Dénes
2015-01-01
A possible way of creating a multiprocessor artificial neural network is by the use of microcontrollers. The RISC processors' high performance and the large number of I/O ports mean they are greatly suitable for creating such a system. During our research, we wanted to see if it is possible to efficiently create interaction between the artifical neural network and the natural nervous system. To achieve as much analogy to the living nervous system as possible, we created a frequency-modulated analog connection between the units. Our system is connected to the living nervous system through 128 microelectrodes. Two-way communication is provided through A/D transformation, which is even capable of testing psychopharmacons. The microcontroller-based analog artificial neural network can play a great role in medical singal processing, such as ECG, EEG etc. PMID:26152990
Quantum neural networks: Current status and prospects for development
NASA Astrophysics Data System (ADS)
Altaisky, M. V.; Kaputkina, N. E.; Krylov, V. A.
2014-11-01
The idea of quantum artificial neural networks, first formulated in [34], unites the artificial neural network concept with the quantum computation paradigm. Quantum artificial neural networks were first systematically considered in the PhD thesis by T. Menneer (1998). Based on the works of Menneer and Narayanan [42, 43], Kouda, Matsui, and Nishimura [35, 36], Altaisky [2, 68], Zhou [67], and others, quantum-inspired learning algorithms for neural networks were developed, and are now used in various training programs and computer games [29, 30]. The first practically realizable scaled hardware-implemented model of the quantum artificial neural network is obtained by D-Wave Systems, Inc. [33]. It is a quantum Hopfield network implemented on the basis of superconducting quantum interference devices (SQUIDs). In this work we analyze possibilities and underlying principles of an alternative way to implement quantum neural networks on the basis of quantum dots. A possibility of using quantum neural network algorithms in automated control systems, associative memory devices, and in modeling biological and social networks is examined.
Ghaedi, M; Zeinali, N; Ghaedi, A M; Teimuori, M; Tashkhourian, J
2014-05-01
In this study, graphite oxide (GO) nano according to Hummers method was synthesized and subsequently was used for the removal of methylene blue (MB) and brilliant green (BG). The detail information about the structure and physicochemical properties of GO are investigated by different techniques such as XRD and FTIR analysis. The influence of solution pH, initial dye concentration, contact time and adsorbent dosage was examined in batch mode and optimum conditions was set as pH=7.0, 2 mg of GO and 10 min contact time. Employment of equilibrium isotherm models for description of adsorption capacities of GO explore the good efficiency of Langmuir model for the best presentation of experimental data with maximum adsorption capacity of 476.19 and 416.67 for MB and BG dyes in single solution. The analysis of adsorption rate at various stirring times shows that both dyes adsorption followed a pseudo second-order kinetic model with cooperation with interparticle diffusion model. Subsequently, the adsorption data as new combination of artificial neural network was modeled to evaluate and obtain the real conditions for fast and efficient removal of dyes. A three-layer artificial neural network (ANN) model is applicable for accurate prediction of dyes removal percentage from aqueous solution by GO following conduction of 336 experimental data. The network was trained using the obtained experimental data at optimum pH with different GO amount (0.002-0.008 g) and 5-40 mg/L of both dyes over contact time of 0.5-30 min. The ANN model was able to predict the removal efficiency with Levenberg-Marquardt algorithm (LMA), a linear transfer function (purelin) at output layer and a tangent sigmoid transfer function (tansig) at hidden layer with 10 and 11 neurons for MB and BG dyes, respectively. The minimum mean squared error (MSE) of 0.0012 and coefficient of determination (R(2)) of 0.982 were found for prediction and modeling of MB removal, while the respective value for BG was the
NASA Astrophysics Data System (ADS)
Ghaedi, M.; Zeinali, N.; Ghaedi, A. M.; Teimuori, M.; Tashkhourian, J.
In this study, graphite oxide (GO) nano according to Hummers method was synthesized and subsequently was used for the removal of methylene blue (MB) and brilliant green (BG). The detail information about the structure and physicochemical properties of GO are investigated by different techniques such as XRD and FTIR analysis. The influence of solution pH, initial dye concentration, contact time and adsorbent dosage was examined in batch mode and optimum conditions was set as pH = 7.0, 2 mg of GO and 10 min contact time. Employment of equilibrium isotherm models for description of adsorption capacities of GO explore the good efficiency of Langmuir model for the best presentation of experimental data with maximum adsorption capacity of 476.19 and 416.67 for MB and BG dyes in single solution. The analysis of adsorption rate at various stirring times shows that both dyes adsorption followed a pseudo second-order kinetic model with cooperation with interparticle diffusion model. Subsequently, the adsorption data as new combination of artificial neural network was modeled to evaluate and obtain the real conditions for fast and efficient removal of dyes. A three-layer artificial neural network (ANN) model is applicable for accurate prediction of dyes removal percentage from aqueous solution by GO following conduction of 336 experimental data. The network was trained using the obtained experimental data at optimum pH with different GO amount (0.002-0.008 g) and 5-40 mg/L of both dyes over contact time of 0.5-30 min. The ANN model was able to predict the removal efficiency with Levenberg-Marquardt algorithm (LMA), a linear transfer function (purelin) at output layer and a tangent sigmoid transfer function (tansig) at hidden layer with 10 and 11 neurons for MB and BG dyes, respectively. The minimum mean squared error (MSE) of 0.0012 and coefficient of determination (R2) of 0.982 were found for prediction and modeling of MB removal, while the respective value for BG was the
Neural network ultrasound image analysis
NASA Astrophysics Data System (ADS)
Schneider, Alexander C.; Brown, David G.; Pastel, Mary S.
1993-09-01
Neural network based analysis of ultrasound image data was carried out on liver scans of normal subjects and those diagnosed with diffuse liver disease. In a previous study, ultrasound images from a group of normal volunteers, Gaucher's disease patients, and hepatitis patients were obtained by Garra et al., who used classical statistical methods to distinguish from among these three classes. In the present work, neural network classifiers were employed with the same image features found useful in the previous study for this task. Both standard backpropagation neural networks and a recently developed biologically-inspired network called Dystal were used. Classification performance as measured by the area under a receiver operating characteristic curve was generally excellent for the back propagation networks and was roughly comparable to that of classical statistical discriminators tested on the same data set and documented in the earlier study. Performance of the Dystal network was significantly inferior; however, this may be due to the choice of network parameter. Potential methods for enhancing network performance was identified.
Automating parallel implementation of neural learning algorithms.
Rana, O F
2000-06-01
Neural learning algorithms generally involve a number of identical processing units, which are fully or partially connected, and involve an update function, such as a ramp, a sigmoid or a Gaussian function for instance. Some variations also exist, where units can be heterogeneous, or where an alternative update technique is employed, such as a pulse stream generator. Associated with connections are numerical values that must be adjusted using a learning rule, and and dictated by parameters that are learning rule specific, such as momentum, a learning rate, a temperature, amongst others. Usually, neural learning algorithms involve local updates, and a global interaction between units is often discouraged, except in instances where units are fully connected, or involve synchronous updates. In all of these instances, concurrency within a neural algorithm cannot be fully exploited without a suitable implementation strategy. A design scheme is described for translating a neural learning algorithm from inception to implementation on a parallel machine using PVM or MPI libraries, or onto programmable logic such as FPGAs. A designer must first describe the algorithm using a specialised Neural Language, from which a Petri net (PN) model is constructed automatically for verification, and building a performance model. The PN model can be used to study issues such as synchronisation points, resource sharing and concurrency within a learning rule. Specialised constructs are provided to enable a designer to express various aspects of a learning rule, such as the number and connectivity of neural nodes, the interconnection strategies, and information flows required by the learning algorithm. A scheduling and mapping strategy is then used to translate this PN model onto a multiprocessor template. We demonstrate our technique using a Kohonen and backpropagation learning rules, implemented on a loosely coupled workstation cluster, and a dedicated parallel machine, with PVM libraries
Khajeh, Mostafa; Moghaddam, Zahra Safaei; Bohlooli, Mousa; Khajeh, Ahmad
2015-01-01
Dispersive liquid-liquid microextraction (DLLME) coupled with gas chromatography was applied for the extraction and determination of essential oil constituents of the Borago officinalis L. In this study, an experimental data-based artificial neural network (ANN) model was constructed to describe the performance of DLLME method for various operating conditions. The volume of extraction and dispersive solvents, extraction time and salt effect were the input variables of this process, whereas the extraction efficiency was the output. The ANN method was found to be capable of modeling this procedure accurately. The overall agreement between the experimental data and ANN predictions was satisfactory showing a determination coefficient of 0.982. The optimum operating condition was then determined by the genetic algorithm method. The optimal conditions were 248 µL volume of extraction solvent, 260 µL volume of dispersive solvent, 2.5 min extraction time and 0.16 mol L(-1) of salt. The limit of detection and linear dynamic range were 0.15-24.0 and 1.2-1,800 ng mL(-1), respectively. The main components of the essential oil were δ-cadinene (31.02%), carvacrol (24.91%), α-pinene (20.89%) and α-cadinol (16.47%). PMID:26045584
Jacob, Samuel; Banerjee, Rintu
2016-08-01
A novel approach to overcome the acidification problem has been attempted in the present study by codigesting industrial potato waste (PW) with Pistia stratiotes (PS, an aquatic weed). The effectiveness of codigestion of the weed and PW was tested in an equal (1:1) proportion by weight with substrate concentration of 5g total solid (TS)/L (2.5gPW+2.5gPS) which resulted in enhancement of methane yield by 76.45% as compared to monodigestion of PW with a positive synergistic effect. Optimization of process parameters was conducted using central composite design (CCD) based response surface methodology (RSM) and artificial neural network (ANN) coupled genetic algorithm (GA) model. Upon comparison of these two optimization techniques, ANN-GA model obtained through feed forward back propagation methodology was found to be efficient and yielded 447.4±21.43LCH4/kgVSfed (0.279gCH4/kgCODvs) which is 6% higher as compared to the CCD-RSM based approach. PMID:27155267
Yolmeh, Mahmoud; Habibi Najafi, Mohammad B; Salehi, Fakhreddin
2014-01-01
Annatto is commonly used as a coloring agent in the food industry and has antimicrobial and antioxidant properties. In this study, genetic algorithm-artificial neural network (GA-ANN) and adaptive neuro-fuzzy inference system (ANFIS) models were used to predict the effect of annatto dye on Salmonella enteritidis in mayonnaise. The GA-ANN and ANFIS were fed with 3 inputs of annatto dye concentration (0, 0.1, 0.2 and 0.4%), storage temperature (4 and 25°C) and storage time (1-20 days) for prediction of S. enteritidis population. Both models were trained with experimental data. The results showed that the annatto dye was able to reduce of S. enteritidis and its effect was stronger at 25°C than 4°C. The developed GA-ANN, which included 8 hidden neurons, could predict S. enteritidis population with correlation coefficient of 0.999. The overall agreement between ANFIS predictions and experimental data was also very good (r=0.998). Sensitivity analysis results showed that storage temperature was the most sensitive factor for prediction of S. enteritidis population. PMID:24566279
Dil, Ebrahim Alipanahpour; Ghaedi, Mehrorang; Asfaram, Arash; Mehrabi, Fatemeh; Bazrafshan, Ali Akbar; Ghaedi, Abdol Mohammad
2016-11-01
In this study, ultrasound assisted dispersive solid-phase micro extraction combined with spectrophotometry (USA-DSPME-UV) method based on activated carbon modified with Fe2O3 nanoparticles (Fe2O3-NPs-AC) was developed for pre-concentration and determination of safranin O (SO). It is known that the efficiency of USA-DSPME-UV method may be affected by pH, amount of adsorbent, ultrasound time and eluent volume and the extent and magnitude of their contribution on response (in term of main and interaction part) was studied by using central composite design (CCD) and artificial neural network-genetic algorithms (ANN-GA). Accordingly by adjustment of experimental conditions suggested by ANN-GA at pH 6.5, 1.1mg of adsorbent, 10min ultrasound and 150μL of eluent volume led to achievement of best operation performance like low LOD (6.3ngmL(-1)) and LOQ (17.5ngmL(-1)) in the range of 25-3500ngmL(-1). In following stage, the SO content in real water and wastewater samples with recoveries between 93.27-99.41% with RSD lower than 3% was successfully determined. PMID:27245964
NASA Astrophysics Data System (ADS)
Sathiya, P.; Panneerselvam, K.; Soundararajan, R.
2012-09-01
Laser welding input parameters play a very significant role in determining the quality of a weld joint. The joint quality can be defined in terms of properties such as weld bead geometry, mechanical properties and distortion. Therefore, mechanical properties should be controlled to obtain good welded joints. In this study, the weld bead geometry such as depth of penetration (DP), bead width (BW) and tensile strength (TS) of the laser welded butt joints made of AISI 904L super austenitic stainless steel were investigated. Full factorial design was used to carry out the experimental design. Artificial Neural networks (ANN) program was developed in MatLab software to establish the relationships between the laser welding input parameters like beam power, travel speed and focal position and the three responses DP, BW and TS in three different shielding gases (Argon, Helium and Nitrogen). The established models were used for optimizing the process parameters using Genetic Algorithm (GA). Optimum solutions for the three different gases and their respective responses were obtained. Confirmation experiment has also been conducted to validate the optimized parameters obtained from GA.
Khajeh, Mostafa; Sarafraz-Yazdi, Ali; Natavan, Zahra Bameri
2016-03-01
The aim of this research was to develop a low price and environmentally friendly adsorbent with abundant of source to remove methylene blue (MB) from water samples. Sawdust solid-phase extraction coupled with high-performance liquid chromatography was used for the extraction and determination of MB. In this study, an experimental data-based artificial neural network model is constructed to describe the performance of sawdust solid-phase extraction method for various operating conditions. The pH, time, amount of sawdust, and temperature were the input variables, while the percentage of extraction of MB was the output. The optimum operating condition was then determined by genetic algorithm method. The optimized conditions were obtained as follows: 11.5, 22.0 min, 0.3 g, and 26.0°C for pH of the solution, extraction time, amount of adsorbent, and temperature, respectively. Under these optimum conditions, the detection limit and relative standard deviation were 0.067 μg L(-1) and <2.4%, respectively. The Langmuir and Freundlich adsorption models were applied to describe the isotherm constant and for the removal and determination of MB from water samples. PMID:24152432
A fatigue damage estimator using RBF, backpropagation, and CID4 neural algorithms
NASA Technical Reports Server (NTRS)
Cios, Krzysztof J.; Tjia, Robert E.; Liu, Ning
1992-01-01
Fatigue damage estimation using neural networks is described in the paper. Attention is focused on the method of data generation for both the training and test data used by radial basis function (RBF), backpropagation, and CID4 algorithms used in this study. The performance results of the three neural algorithms are analyzed in terms of their strengths and weaknesses in training.
Neural network for tsunami and runup forecast
NASA Astrophysics Data System (ADS)
Namekar, Shailesh; Yamazaki, Yoshiki; Cheung, Kwok Fai
2009-04-01
This paper examines the use of neural network to model nonlinear tsunami processes for forecasting of coastal waveforms and runup. The three-layer network utilizes a radial basis function in the hidden, middle layer for nonlinear transformation of input waveforms near the tsunami source. Events based on the 2006 Kuril Islands tsunami demonstrate the implementation and capability of the network. Division of the Kamchatka-Kuril subduction zone into a number of subfaults facilitates development of a representative tsunami dataset using a nonlinear long-wave model. The computed waveforms near the tsunami source serve as the input and the far-field waveforms and runup provide the target output for training of the network through a back-propagation algorithm. The trained network reproduces the resonance of tsunami waves and the topography-dominated runup patterns at Hawaii's coastlines from input water-level data off the Aleutian Islands.
Character Recognition Using Genetically Trained Neural Networks
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 amount of
Parameter extraction with neural networks
NASA Astrophysics Data System (ADS)
Cazzanti, Luca; Khan, Mumit; Cerrina, Franco
1998-06-01
In semiconductor processing, the modeling of the process is becoming more and more important. While the ultimate goal is that of developing a set of tools for designing a complete process (Technology CAD), it is also necessary to have modules to simulate the various technologies and, in particular, to optimize specific steps. This need is particularly acute in lithography, where the continuous decrease in CD forces the technologies to operate near their limits. In the development of a 'model' for a physical process, we face several levels of challenges. First, it is necessary to develop a 'physical model,' i.e. a rational description of the process itself on the basis of know physical laws. Second, we need an 'algorithmic model' to represent in a virtual environment the behavior of the 'physical model.' After a 'complete' model has been developed and verified, it becomes possible to do performance analysis. In many cases the input parameters are poorly known or not accessible directly to experiment. It would be extremely useful to obtain the values of these 'hidden' parameters from experimental results by comparing model to data. This is particularly severe, because the complexity and costs associated with semiconductor processing make a simple 'trial-and-error' approach infeasible and cost- inefficient. Even when computer models of the process already exists, obtaining data through simulations may be time consuming. Neural networks (NN) are powerful computational tools to predict the behavior of a system from an existing data set. They are able to adaptively 'learn' input/output mappings and to act as universal function approximators. In this paper we use artificial neural networks to build a mapping from the input parameters of the process to output parameters which are indicative of the performance of the process. Once the NN has been 'trained,' it is also possible to observe the process 'in reverse,' and to extract the values of the inputs which yield outputs
Sequential and parallel image restoration: neural network implementations.
Figueiredo, M T; Leitao, J N
1994-01-01
Sequential and parallel image restoration algorithms and their implementations on neural networks are proposed. For images degraded by linear blur and contaminated by additive white Gaussian noise, maximum a posteriori (MAP) estimation and regularization theory lead to the same high dimension convex optimization problem. The commonly adopted strategy (in using neural networks for image restoration) is to map the objective function of the optimization problem into the energy of a predefined network, taking advantage of its energy minimization properties. Departing from this approach, we propose neural implementations of iterative minimization algorithms which are first proved to converge. The developed schemes are based on modified Hopfield (1985) networks of graded elements, with both sequential and parallel updating schedules. An algorithm supported on a fully standard Hopfield network (binary elements and zero autoconnections) is also considered. Robustness with respect to finite numerical precision is studied, and examples with real images are presented. PMID:18296247
Thermoelastic steam turbine rotor control based on neural network
NASA Astrophysics Data System (ADS)
Rzadkowski, Romuald; Dominiczak, Krzysztof; Radulski, Wojciech; Szczepanik, R.
2015-12-01
Considered here are Nonlinear Auto-Regressive neural networks with eXogenous inputs (NARX) as a mathematical model of a steam turbine rotor for controlling steam turbine stress on-line. In order to obtain neural networks that locate critical stress and temperature points in the steam turbine during transient states, an FE rotor model was built. This model was used to train the neural networks on the basis of steam turbine transient operating data. The training included nonlinearity related to steam turbine expansion, heat exchange and rotor material properties during transients. Simultaneous neural networks are algorithms which can be implemented on PLC controllers. This allows for the application neural networks to control steam turbine stress in industrial power plants.
Plant Growth Models Using Artificial Neural Networks
NASA Technical Reports Server (NTRS)
Bubenheim, David
1997-01-01
In this paper, we descrive our motivation and approach to devloping models and the neural network architecture. Initial use of the artificial neural network for modeling the single plant process of transpiration is presented.
Color control of printers by neural networks
NASA Astrophysics Data System (ADS)
Tominaga, Shoji
1998-07-01
A method is proposed for solving the mapping problem from the 3D color space to the 4D CMYK space of printer ink signals by means of a neural network. The CIE-L*a*b* color system is used as the device-independent color space. The color reproduction problem is considered as the problem of controlling an unknown static system with four inputs and three outputs. A controller determines the CMYK signals necessary to produce the desired L*a*b* values with a given printer. Our solution method for this control problem is based on a two-phase procedure which eliminates the need for UCR and GCR. The first phase determines a neural network as a model of the given printer, and the second phase determines the combined neural network system by combining the printer model and the controller in such a way that it represents an identity mapping in the L*a*b* color space. Then the network of the controller part realizes the mapping from the L*a*b* space to the CMYK space. Practical algorithms are presented in the form of multilayer feedforward networks. The feasibility of the proposed method is shown in experiments using a dye sublimation printer and an ink jet printer.
Centroid calculation using neural networks
NASA Astrophysics Data System (ADS)
Himes, Glenn S.; Inigo, Rafael M.
1992-01-01
Centroid calculation provides a means of eliminating translation problems, which is useful for automatic target recognition. a neural network implementation of centroid calculation is described that used a spatial filter and a Hopfield network to determine the centroid location of an object. spatial filtering of a segmented window creates a result whose peak vale occurs at the centroid of the input data set. A Hopfield network then finds the location of this peak and hence gives the location of the centroid. Hardware implementations of the networks are described and simulation results are provided.
FPGA-based artificial neural network using CORDIC modules
NASA Astrophysics Data System (ADS)
Liddicoat, Albert A.; Slivovsky, Lynne A.; McLenegan, Tim; Heyer, Don
2006-08-01
Artificial neural networks have been used in applications that require complex procedural algorithms and in systems which lack an analytical mathematic model. By designing a large network of computing nodes based on the artificial neuron model, new solutions can be developed for computational problems in fields such as image processing and speech recognition. Neural networks are inherently parallel since each neuron, or node, acts as an autonomous computational element. Artificial neural networks use a mathematical model for each node that processes information from other nodes in the same region. The information processing entails computing a weighted average computation followed by a nonlinear mathematical transformation. Some typical artificial neural network applications use the exponential function or trigonometric functions for the nonlinear transformation. Various simple artificial neural networks have been implemented using a processor to compute the output for each node sequentially. This approach uses sequential processing and does not take advantage of the parallelism of a complex artificial neural network. In this work a hardware-based approach is investigated for artificial neural network applications. A Field Programmable Gate Arrays (FPGAs) is used to implement an artificial neuron using hardware multipliers, adders and CORDIC functional units. In order to create a large scale artificial neural network, area efficient hardware units such as CORDIC units are needed. High performance and low cost bit serial CORDIC implementations are presented. Finally, the FPGA resources and the performance of a hardware-based artificial neuron are presented.
Time series prediction using a rational fraction neural networks
Lee, K.; Lee, Y.C.; Barnes, C.; Aldrich, C.H.; Kindel, J.
1988-01-01
An efficient neural network based on a rational fraction representation has been trained to perform time series prediction. The network is a generalization of the Volterra-Wiener network while still retaining the computational efficiency of the latter. Because of the second order convergent nature of the learning algorithm, the rational net is computationally far more efficient than multilayer networks. The rational fractional representation is, however, more restrictive than the multilayer networks.
Neural network classifier of attacks in IP telephony
NASA Astrophysics Data System (ADS)
Safarik, Jakub; Voznak, Miroslav; Mehic, Miralem; Partila, Pavol; Mikulec, Martin
2014-05-01
Various types of monitoring mechanism allow us to detect and monitor behavior of attackers in VoIP networks. Analysis of detected malicious traffic is crucial for further investigation and hardening the network. This analysis is typically based on statistical methods and the article brings a solution based on neural network. The proposed algorithm is used as a classifier of attacks in a distributed monitoring network of independent honeypot probes. Information about attacks on these honeypots is collected on a centralized server and then classified. This classification is based on different mechanisms. One of them is based on the multilayer perceptron neural network. The article describes inner structure of used neural network and also information about implementation of this network. The learning set for this neural network is based on real attack data collected from IP telephony honeypot called Dionaea. We prepare the learning set from real attack data after collecting, cleaning and aggregation of this information. After proper learning is the neural network capable to classify 6 types of most commonly used VoIP attacks. Using neural network classifier brings more accurate attack classification in a distributed system of honeypots. With this approach is possible to detect malicious behavior in a different part of networks, which are logically or geographically divided and use the information from one network to harden security in other networks. Centralized server for distributed set of nodes serves not only as a collector and classifier of attack data, but also as a mechanism for generating a precaution steps against attacks.
Neural networks in the process industries
Ben, L.R.; Heavner, L.
1996-12-01
Neural networks, or more precisely, artificial neural networks (ANNs), are rapidly gaining in popularity. They first began to appear on the process-control scene in the early 1990s, but have been a research focus for more than 30 years. Neural networks are really empirical models that approximate the way man thinks neurons in the human brain work. Neural-net technology is not trying to produce computerized clones, but to model nature in an effort to mimic some of the brain`s capabilities. Modeling, for the purposes of this article, means developing a mathematical description of physical phenomena. The physics and chemistry of industrial processes are usually quite complex and sometimes poorly understood. Our process understanding, and our imperfect ability to describe complexity in mathematical terms, limit fidelity of first-principle models. Computational requirements for executing these complex models are a further limitation. It is often not possible to execute first-principle model algorithms at the high rate required for online control. Nevertheless, rigorous first principle models are commonplace design tools. Process control is another matter. Important model inputs are often not available as process measurements, making real-time application difficult. In fact, engineers often use models to infer unavailable measurements. 5 figs.
NASA Astrophysics Data System (ADS)
Bahrami, Saeed; Doulati Ardejani, Faramarz; Baafi, Ernest
2016-05-01
In this study, hybrid models are designed to predict groundwater inflow to an advancing open pit mine and the hydraulic head (HH) in observation wells at different distances from the centre of the pit during its advance. Hybrid methods coupling artificial neural network (ANN) with genetic algorithm (GA) methods (ANN-GA), and simulated annealing (SA) methods (ANN-SA), were utilised. Ratios of depth of pit penetration in aquifer to aquifer thickness, pit bottom radius to its top radius, inverse of pit advance time and the HH in the observation wells to the distance of observation wells from the centre of the pit were used as inputs to the networks. To achieve the objective two hybrid models consisting of ANN-GA and ANN-SA with 4-5-3-1 arrangement were designed. In addition, by switching the last argument of the input layer with the argument of the output layer of two earlier models, two new models were developed to predict the HH in the observation wells for the period of the mining process. The accuracy and reliability of models are verified by field data, results of a numerical finite element model using SEEP/W, outputs of simple ANNs and some well-known analytical solutions. Predicted results obtained by the hybrid methods are closer to the field data compared to the outputs of analytical and simple ANN models. Results show that despite the use of fewer and simpler parameters by the hybrid models, the ANN-GA and to some extent the ANN-SA have the ability to compete with the numerical models.
Automated brain segmentation using neural networks
NASA Astrophysics Data System (ADS)
Powell, Stephanie; Magnotta, Vincent; Johnson, Hans; Andreasen, Nancy
2006-03-01
Automated methods to delineate brain structures of interest are required to analyze large amounts of imaging data like that being collected in several on going multi-center studies. We have previously reported on using artificial neural networks (ANN) to define subcortical brain structures such as the thalamus (0.825), caudate (0.745), and putamen (0.755). One of the inputs into the ANN is the apriori probability of a structure existing at a given location. In this previous work, the apriori probability information was generated in Talairach space using a piecewise linear registration. In this work we have increased the dimensionality of this registration using Thirion's demons registration algorithm. The input vector consisted of apriori probability, spherical coordinates, and an iris of surrounding signal intensity values. The output of the neural network determined if the voxel was defined as one of the N regions used for training. Training was performed using a standard back propagation algorithm. The ANN was trained on a set of 15 images for 750,000,000 iterations. The resulting ANN weights were then applied to 6 test images not part of the training set. Relative overlap calculated for each structure was 0.875 for the thalamus, 0.845 for the caudate, and 0.814 for the putamen. With the modifications on the neural net algorithm and the use of multi-dimensional registration, we found substantial improvement in the automated segmentation method. The resulting segmented structures are as reliable as manual raters and the output of the neural network can be used without additional rater intervention.
NASA Astrophysics Data System (ADS)
Rahimi, Masoud; Beigzadeh, Reza; Parvizi, Mehdi; Eiamsa-ard, Smith
2016-08-01
The group method of data handling (GMDH) technique was used to predict heat transfer and friction characteristics in heat exchanger tubes equipped with wire-rod bundles. Nusselt number and friction factor were determined as functions of wire-rod bundle geometric parameters and Reynolds number. The performance of the developed GMDH-type neural networks was found to be superior in comparison with the proposed empirical correlations. For optimization, the genetic algorithm-based multi-objective optimization was applied.
Artificial neural networks in medicine
Keller, P.E.
1994-07-01
This Technology Brief provides an overview of artificial neural networks (ANN). A definition and explanation of an ANN is given and situations in which an ANN is used are described. ANN applications to medicine specifically are then explored and the areas in which it is currently being used are discussed. Included are medical diagnostic aides, biochemical analysis, medical image analysis and drug development.
Neural networks for handwriting recognition
NASA Astrophysics Data System (ADS)
Kelly, David A.
1992-09-01
The market for a product that can read handwritten forms, such as insurance applications, re- order forms, or checks, is enormous. Companies could save millions of dollars each year if they had an effective and efficient way to read handwritten forms into a computer without human intervention. Urged on by the potential gold mine that an adequate solution would yield, a number of companies and researchers have developed, and are developing, neural network-based solutions to this long-standing problem. This paper briefly outlines the current state-of-the-art in neural network-based handwriting recognition research and products. The first section of the paper examines the potential market for this technology. The next section outlines the steps in the recognition process, followed by a number of the basic issues that need to be dealt with to solve the recognition problem in a real-world setting. Next, an overview of current commercial solutions and research projects shows the different ways that neural networks are applied to the problem. This is followed by a breakdown of the current commercial market and the future outlook for neural network-based handwriting recognition technology.
How Neural Networks Learn from Experience.
ERIC Educational Resources Information Center
Hinton, Geoffrey E.
1992-01-01
Discusses computational studies of learning in artificial neural networks and findings that may provide insights into the learning abilities of the human brain. Describes efforts to test theories about brain information processing, using artificial neural networks. Vignettes include information concerning how a neural network represents…
Model Of Neural Network With Creative Dynamics
NASA Technical Reports Server (NTRS)
Zak, Michail; Barhen, Jacob
1993-01-01
Paper presents analysis of mathematical model of one-neuron/one-synapse neural network featuring coupled activation and learning dynamics and parametrical periodic excitation. Demonstrates self-programming, partly random behavior of suitable designed neural network; believed to be related to spontaneity and creativity of biological neural networks.
Fault classification by neural networks and fuzzy logic
Chwan-Hwa ``John`` Wu; Chihwen Li; Shih, H.; Alexion, C.C.; Ovick, N.L.; Murphy, J.H.
1995-01-25
A neural fuzzy-based and a backpropagation neural network-based fault classifier for a three-phase motor will be described in this paper. In order to acquire knowledge, the neural fuzzy classifier incorporates a learning technique to automatically generate membership functions for fuzzy rules, and the backpropagation algorithm is used to train the neural network model. Therefore, in this paper, the preprocessing of signals, fuzzy and neural models, training methods, implementations for real-time response and testing results will be discussed in detail. Furthermore, the generalization capabilities of the neural fuzzy- and backpropagation-based classifiers for waveforms with varying magnitudes, frequencies, noises and positions of spikes and chops in a cycle of a sine wave will be investigated, and the computation requirements needed to achieve real-time response for both fuzzy and neural methods will be compared. {copyright} 1995 {ital American} {ital Institute} {ital of} {ital Physics}
Neural network analysis of W UMa eclipsing binaries
NASA Astrophysics Data System (ADS)
Zeraatgari, F. Z.; Abedi, A.; Farshad, M.; Ebadian, M.; Riazi, N.
2015-04-01
We try five different artificial neural models, four models based on PNN (Perceptron Neural Network), and one using GRNN (Generalized Regression Neural Network) as tools for the automated light curve analysis of W UMa-type eclipsing binary systems. These algorithms, which are inspired by the Rucinski method, are designed and trained using MATLAB 7.6. A total of 17,820 generated contact binary light curves are first analyzed using a truncated cosine series with 11 coefficients and the most significant coefficients are applied as inputs of the neural models. The required sample light curves are systematically generated, using the WD2007 program (Wilson and Devinney 2007). The trained neural models are then applied to estimate the geometrical parameters of seven W UMa-type systems. The efficiency of different neural network models are then evaluated and compared to find the most efficient one.
Yarn Quality Prediction Based on Improved BP Neural Network
NASA Astrophysics Data System (ADS)
Yang, Jian-Guo; Xiong, Jing-Wei; Xun, Lan
Aiming at the key quality indexes xbt in spinning processing is caused by many complex and interactions factors. A xbt prediction model is put forward based on the PSO-BP neural network, which adjusts weights of BP neural network using particle swarm optimization (PSO) rather than the traditional gradient descent method, is used to improve the convergence speed of neural network and the ability of getting the global optimal solution. As the object of a large number of field detection data in a spinning workshop, the results show that, compared with the traditional BP algorithm and GA-BP algorithm, the PSO-BP neural network can obvious improve yarn quality prediction model precision and stability.
Measurement and evaluation of instantaneous reactive power using neural networks
Chow, T.W.S.; Yam, Y.F. )
1994-07-01
The erratic disturbance caused by an electric arc furnace requires a fast and accurate VAr evaluation algorithm for compensation. This paper describes the development of a novel method using the approach of Artificial Neural Networks (ANN) to evaluate the instantaneous VAr. Comparing to the conventional methods, this neural network based algorithm is capable of operating at a much lower sampling rate and delivering an accurate and fast response output. By hardware implementation of this algorithm using neuron chips, the erratic VAr fluctuation can be accurately estimated for compensation.
EEG Artifact Removal Using a Wavelet Neural Network
NASA Technical Reports Server (NTRS)
Nguyen, Hoang-Anh T.; Musson, John; Li, Jiang; McKenzie, Frederick; Zhang, Guangfan; Xu, Roger; Richey, Carl; Schnell, Tom
2011-01-01
!n this paper we developed a wavelet neural network. (WNN) algorithm for Electroencephalogram (EEG) artifact removal without electrooculographic (EOG) recordings. The algorithm combines the universal approximation characteristics of neural network and the time/frequency property of wavelet. We. compared the WNN algorithm with .the ICA technique ,and a wavelet thresholding method, which was realized by using the Stein's unbiased risk estimate (SURE) with an adaptive gradient-based optimal threshold. Experimental results on a driving test data set show that WNN can remove EEG artifacts effectively without diminishing useful EEG information even for very noisy data.
On-line lower-order modeling via neural networks.
Ho, H F; Rad, A B; Wong, Y K; Lo, W L
2003-10-01
This paper presents a novel method to determine the parameters of a first-order plus dead-time model using neural networks. The outputs of the neural networks are the gain, dominant time constant, and apparent time delay. By combining this algorithm with a conventional PI or PID controller, we also present an adaptive controller which requires very little a priori knowledge about the plant under control. The simplicity of the scheme for real-time control provides a new approach for implementing neural network applications for a variety of on-line industrial control problems. Simulation and experimental results demonstrate the feasibility and adaptive property of the proposed scheme. PMID:14582882
Real-Time Adaptive Color Segmentation by Neural Networks
NASA Technical Reports Server (NTRS)
Duong, Tuan A.
2004-01-01
Artificial neural networks that would utilize the cascade error projection (CEP) algorithm have been proposed as means of autonomous, real-time, adaptive color segmentation of images that change with time. In the original intended application, such a neural network would be used to analyze digitized color video images of terrain on a remote planet as viewed from an uninhabited spacecraft approaching the planet. During descent toward the surface of the planet, information on the segmentation of the images into differently colored areas would be updated adaptively in real time to capture changes in contrast, brightness, and resolution, all in an effort to identify a safe and scientifically productive landing site and provide control feedback to steer the spacecraft toward that site. Potential terrestrial applications include monitoring images of crops to detect insect invasions and monitoring of buildings and other facilities to detect intruders. The CEP algorithm is reliable and is well suited to implementation in very-large-scale integrated (VLSI) circuitry. It was chosen over other neural-network learning algorithms because it is better suited to realtime learning: It provides a self-evolving neural-network structure, requires fewer iterations to converge and is more tolerant to low resolution (that is, fewer bits) in the quantization of neural-network synaptic weights. Consequently, a CEP neural network learns relatively quickly, and the circuitry needed to implement it is relatively simple. Like other neural networks, a CEP neural network includes an input layer, hidden units, and output units (see figure). As in other neural networks, a CEP network is presented with a succession of input training patterns, giving rise to a set of outputs that are compared with the desired outputs. Also as in other neural networks, the synaptic weights are updated iteratively in an effort to bring the outputs closer to target values. A distinctive feature of the CEP neural
Robust neural network with applications to credit portfolio data analysis
Feng, Yijia; Li, Runze; Sudjianto, Agus; Zhang, Yiyun
2011-01-01
In this article, we study nonparametric conditional quantile estimation via neural network structure. We proposed an estimation method that combines quantile regression and neural network (robust neural network, RNN). It provides good smoothing performance in the presence of outliers and can be used to construct prediction bands. A Majorization-Minimization (MM) algorithm was developed for optimization. Monte Carlo simulation study is conducted to assess the performance of RNN. Comparison with other nonparametric regression methods (e.g., local linear regression and regression splines) in real data application demonstrate the advantage of the newly proposed procedure. PMID:21687821
Failure behavior identification for a space antenna via neural networks
NASA Technical Reports Server (NTRS)
Sartori, Michael A.; Antsaklis, Panos J.
1992-01-01
By using neural networks, a method for the failure behavior identification of a space antenna model is investigated. The proposed method uses three stages. If a fault is suspected by the first stage of fault detection, a diagnostic test is performed on the antenna. The diagnostic test results are used by the second and third stages to identify which fault occurred and to diagnose the extent of the fault, respectively. The first stage uses a multilayer perceptron, the second stage uses a multilayer perceptron and neural networks trained with the quadratic optimization algorithm, a novel training procedure, and the third stage uses backpropagation trained neural networks.
Functional expansion representations of artificial neural networks
NASA Technical Reports Server (NTRS)
Gray, W. Steven
1992-01-01
In the past few years, significant interest has developed in using artificial neural networks to model and control nonlinear dynamical systems. While there exists many proposed schemes for accomplishing this and a wealth of supporting empirical results, most approaches to date tend to be ad hoc in nature and rely mainly on heuristic justifications. The purpose of this project was to further develop some analytical tools for representing nonlinear discrete-time input-output systems, which when applied to neural networks would give insight on architecture selection, pruning strategies, and learning algorithms. A long term goal is to determine in what sense, if any, a neural network can be used as a universal approximator for nonliner input-output maps with memory (i.e., realized by a dynamical system). This property is well known for the case of static or memoryless input-output maps. The general architecture under consideration in this project was a single-input, single-output recurrent feedforward network.
Correcting wave predictions with artificial neural networks
NASA Astrophysics Data System (ADS)
Makarynskyy, O.; Makarynska, D.
2003-04-01
The predictions of wind waves with different lead times are necessary in a large scope of coastal and open ocean activities. Numerical wave models, which usually provide this information, are based on deterministic equations that do not entirely account for the complexity and uncertainty of the wave generation and dissipation processes. An attempt to improve wave parameters short-term forecasts based on artificial neural networks is reported. In recent years, artificial neural networks have been used in a number of coastal engineering applications due to their ability to approximate the nonlinear mathematical behavior without a priori knowledge of interrelations among the elements within a system. The common multilayer feed-forward networks, with a nonlinear transfer functions in the hidden layers, were developed and employed to forecast the wave characteristics over one hour intervals starting from one up to 24 hours, and to correct these predictions. Three non-overlapping data sets of wave characteristics, both from a buoy, moored roughly 60 miles west of the Aran Islands, west coast of Ireland, were used to train and validate the neural nets involved. The networks were trained with error back propagation algorithm. Time series plots and scatterplots of the wave characteristics as well as tables with statistics show an improvement of the results achieved due to the correction procedure employed.
Convolutional Neural Network Based dem Super Resolution
NASA Astrophysics Data System (ADS)
Chen, Zixuan; Wang, Xuewen; Xu, Zekai; Hou, Wenguang
2016-06-01
DEM super resolution is proposed in our previous publication to improve the resolution for a DEM on basis of some learning examples. Meanwhile, the nonlocal algorithm is introduced to deal with it and lots of experiments show that the strategy is feasible. In our publication, the learning examples are defined as the partial original DEM and their related high measurements due to this way can avoid the incompatibility between the data to be processed and the learning examples. To further extent the applications of this new strategy, the learning examples should be diverse and easy to obtain. Yet, it may cause the problem of incompatibility and unrobustness. To overcome it, we intend to investigate a convolutional neural network based method. The input of the convolutional neural network is a low resolution DEM and the output is expected to be its high resolution one. A three layers model will be adopted. The first layer is used to detect some features from the input, the second integrates the detected features to some compressed ones and the final step transforms the compressed features as a new DEM. According to this designed structure, some learning DEMs will be taken to train it. Specifically, the designed network will be optimized by minimizing the error of the output and its expected high resolution DEM. In practical applications, a testing DEM will be input to the convolutional neural network and a super resolution will be obtained. Many experiments show that the CNN based method can obtain better reconstructions than many classic interpolation methods.
AUTOMATED DEFECT CLASSIFICATION USING AN ARTIFICIAL NEURAL NETWORK
Chady, T.; Caryk, M.; Piekarczyk, B.
2009-03-03
The automated defect classification algorithm based on artificial neural network with multilayer backpropagation structure was utilized. The selected features of flaws were used as input data. In order to train the neural network it is necessary to prepare learning data which is representative database of defects. Database preparation requires the following steps: image acquisition and pre-processing, image enhancement, defect detection and feature extraction. The real digital radiographs of welded parts of a ship were used for this purpose.
Automated Defect Classification Using AN Artificial Neural Network
NASA Astrophysics Data System (ADS)
Chady, T.; Caryk, M.; Piekarczyk, B.
2009-03-01
The automated defect classification algorithm based on artificial neural network with multilayer backpropagation structure was utilized. The selected features of flaws were used as input data. In order to train the neural network it is necessary to prepare learning data which is representative database of defects. Database preparation requires the following steps: image acquisition and pre-processing, image enhancement, defect detection and feature extraction. The real digital radiographs of welded parts of a ship were used for this purpose.
Convergence Analysis of a Cascade Architecture Neural Network
NASA Technical Reports Server (NTRS)
Duong, Tuan A.; Stubberub, Allen R.; Daud, Taher; Thakoor, Anil
1997-01-01
In this paper, we present a mathematical foundation, including a convergence analysis, for cascading architecture neural networks. From this, a mathematical foundation for the casade correlation learning algorithm can also be found. Furthermore, it becomes apparent that the cascade correlation scheme is a special case of an efficient hardware learning algorithm called Cascade Error Projection.
Overview of artificial neural networks.
Zou, Jinming; Han, Yi; So, Sung-Sau
2008-01-01
The artificial neural network (ANN), or simply neural network, is a machine learning method evolved from the idea of simulating the human brain. The data explosion in modem drug discovery research requires sophisticated analysis methods to uncover the hidden causal relationships between single or multiple responses and a large set of properties. The ANN is one of many versatile tools to meet the demand in drug discovery modeling. Compared to a traditional regression approach, the ANN is capable of modeling complex nonlinear relationships. The ANN also has excellent fault tolerance and is fast and highly scalable with parallel processing. This chapter introduces the background of ANN development and outlines the basic concepts crucially important for understanding more sophisticated ANN. Several commonly used learning methods and network setups are discussed briefly at the end of the chapter. PMID:19065803
Neural Networks For Visual Telephony
NASA Astrophysics Data System (ADS)
Gottlieb, A. M.; Alspector, J.; Huang, P.; Hsing, T. R.
1988-10-01
By considering how an image is processed by the eye and brain, we may find ways to simplify the task of transmitting complex video images over a telecommunication channel. Just as the retina and visual cortex reduce the amount of information sent to other areas of the brain, electronic systems can be designed to compress visual data, encode features, and adapt to new scenes for video transmission. In this talk, we describe a system inspired by models of neural computation that may, in the future, augment standard digital processing techniques for image compression. In the next few years it is expected that a compact low-cost full motion video telephone operating over an ISDN basic access line (144 KBits/sec) will be shown to be feasible. These systems will likely be based on a standard digital signal processing approach. In this talk, we discuss an alternative method that does not use standard digital signal processing but instead uses eletronic neural networks to realize the large compression necessary for a low bit-rate video telephone. This neural network approach is not being advocated as a near term solution for visual telephony. However, low bit rate visual telephony is an area where neural network technology may, in the future, find a significant application.
Validation and regulation of medical neural networks.
Rodvold, D M
2001-01-01
Using artificial neural networks (ANNs) in medical applications can be challenging because of the often-experimental nature of ANN construction and the "black box" label that is frequently attached to them. In the US, medical neural networks are regulated by the Food and Drug Administration. This article briefly discusses the documented FDA policy on neural networks and the various levels of formal acceptance that neural network development groups might pursue. To assist medical neural network developers in creating robust and verifiable software, this paper provides a development process model targeted specifically to ANNs for critical applications. PMID:11790274
A convolutional neural network neutrino event classifier
Aurisano, A.; Radovic, A.; Rocco, D.; Himmel, A.; Messier, M. D.; Niner, E.; Pawloski, G.; Psihas, F.; Sousa, A.; Vahle, P.
2016-09-01
Here, convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology withoutmore » the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.« less
Cascade Back-Propagation Learning in Neural Networks
NASA Technical Reports Server (NTRS)
Duong, Tuan A.
2003-01-01
The cascade back-propagation (CBP) algorithm is the basis of a conceptual design for accelerating learning in artificial neural networks. The neural networks would be implemented as analog very-large-scale integrated (VLSI) circuits, and circuits to implement the CBP algorithm would be fabricated on the same VLSI circuit chips with the neural networks. Heretofore, artificial neural networks have learned slowly because it has been necessary to train them via software, for lack of a good on-chip learning technique. The CBP algorithm is an on-chip technique that provides for continuous learning in real time. Artificial neural networks are trained by example: A network is presented with training inputs for which the correct outputs are known, and the algorithm strives to adjust the weights of synaptic connections in the network to make the actual outputs approach the correct outputs. The input data are generally divided into three parts. Two of the parts, called the "training" and "cross-validation" sets, respectively, must be such that the corresponding input/output pairs are known. During training, the cross-validation set enables verification of the status of the input-to-output transformation learned by the network to avoid over-learning. The third part of the data, termed the "test" set, consists of the inputs that are required to be transformed into outputs; this set may or may not include the training set and/or the cross-validation set. Proposed neural-network circuitry for on-chip learning would be divided into two distinct networks; one for training and one for validation. Both networks would share the same synaptic weights.
Seismic active control by neural networks.
Tang, Y.
1998-01-01
A study on the application of artificial neural networks (ANNs) to activate structural control under seismic loads is carried out. The structure considered is a single-degree-of-freedom (SDF) system with an active bracing device. The control force is computed by a trained neural network. The feed-forward neural network architecture and an adaptive back-propagation training algorithm is used in the study. The neural net is trained to reproduce the function that represents the response-excitation relationship of the SDF system under seismic loads. The input-output training patterns are generated randomly. In the back-propagation training algorithm, the learning rate is determined by ensuring the decrease of the error function at each epoch. The computer program implemented is validated by solving the classification of the XOR problem. Then, the trained ANN is used to compute the control force according to the control strategy. If the control force exceeds the actuator's capacity limit, it is set equal to that limit. The concept of the control strategy employed herein is to apply the control force at every time step to cancel the system velocity induced at the preceding time step so that the gradual rhythmic buildup of the response is destroyed. The ground motions considered in the numerical example are the 1940 El Centro earthquake and the 1979 Imperial Valley earthquake in California. The system responses with and without the control are calculated and compared. The feasibility and potential of applying ANNs to seismic active control is asserted by the promising results obtained from the numerical examples studied.
Learning Process of a Stochastic Feed-Forward Neural Network
NASA Astrophysics Data System (ADS)
Fujiki, Sumiyoshi; Fujiki, Nahomi
1995-03-01
A positive reinforcement type learning algorithm is formulated for a stochastic feed-forward neural network by minimizing a relative entropic measure, and a learning equation similar to that of the Boltzmann machine is obtained. The learning of the network actually shows a similar result to that of the Boltzmann machine in the classification problems of AND and XOR, by numerical experiments.
Neural Network Modeling of Developmental Effects in Discrimination Shifts.
ERIC Educational Resources Information Center
Sirois, Sylvain; Shultz, Thomas R.
1998-01-01
Presents a theoretical account of human shift learning with the use of neural network tools. Details how simulations using the cascade-correlation algorithm which show that networks can capture the regularities of the discrimination shift literature better than existing psychological theories. Suggests that human developmental differences in shift…
Adaptive Optimization of Aircraft Engine Performance Using Neural Networks
NASA Technical Reports Server (NTRS)
Simon, Donald L.; Long, Theresa W.
1995-01-01
Preliminary results are presented on the development of an adaptive neural network based control algorithm to enhance aircraft engine performance. This work builds upon a previous National Aeronautics and Space Administration (NASA) effort known as Performance Seeking Control (PSC). PSC is an adaptive control algorithm which contains a model of the aircraft's propulsion system which is updated on-line to match the operation of the aircraft's actual propulsion system. Information from the on-line model is used to adapt the control system during flight to allow optimal operation of the aircraft's propulsion system (inlet, engine, and nozzle) to improve aircraft engine performance without compromising reliability or operability. Performance Seeking Control has been shown to yield reductions in fuel flow, increases in thrust, and reductions in engine fan turbine inlet temperature. The neural network based adaptive control, like PSC, will contain a model of the propulsion system which will be used to calculate optimal control commands on-line. Hopes are that it will be able to provide some additional benefits above and beyond those of PSC. The PSC algorithm is computationally intensive, it is valid only at near steady-state flight conditions, and it has no way to adapt or learn on-line. These issues are being addressed in the development of the optimal neural controller. Specialized neural network processing hardware is being developed to run the software, the algorithm will be valid at steady-state and transient conditions, and will take advantage of the on-line learning capability of neural networks. Future plans include testing the neural network software and hardware prototype against an aircraft engine simulation. In this paper, the proposed neural network software and hardware is described and preliminary neural network training results are presented.
Microturbine control based on fuzzy neural network
NASA Astrophysics Data System (ADS)
Yan, Shijie; Bian, Chunyuan; Wang, Zhiqiang
2006-11-01
As microturbine generator (MTG) is a clean, efficient, low cost and reliable energy supply system. From outside characteristics of MTG, it is multi-variable, time-varying and coupling system, so it is difficult to be identified on-line and conventional control law adopted before cannot achieve desirable result. A novel fuzzy-neural networks (FNN) control algorithm was proposed in combining with the conventional PID control. In the paper, IF-THEN rules for tuning were applied by a first-order Sugeno fuzzy model with seven fuzzy rules and the membership function was given as the continuous GAUSSIAN function. Some sample data were utilized to train FNN. Through adjusting shape of membership function and weight continually, objective of auto-tuning fuzzy-rules can be achieved. The FNN algorithm had been applied to "100kW Microturbine control and power converter system". The results of simulation and experiment are shown that the algorithm can work very well.
Ghaedi, M; Shojaeipour, E; Ghaedi, A M; Sahraei, Reza
2015-05-01
In this study, copper nanowires loaded on activated carbon (Cu-NWs-AC) was used as novel efficient adsorbent for the removal of malachite green (MG) from aqueous solution. This new material was synthesized through simple protocol and its surface properties such as surface area, pore volume and functional groups were characterized with different techniques such XRD, BET and FESEM analysis. The relation between removal percentages with variables such as solution pH, adsorbent dosage (0.005, 0.01, 0.015, 0.02 and 0.1g), contact time (1-40min) and initial MG concentration (5, 10, 20, 70 and 100mg/L) was investigated and optimized. A three-layer artificial neural network (ANN) model was utilized to predict the malachite green dye removal (%) by Cu-NWs-AC following conduction of 248 experiments. When the training of the ANN was performed, the parameters of ANN model were as follows: linear transfer function (purelin) at output layer, Levenberg-Marquardt algorithm (LMA), and a tangent sigmoid transfer function (tansig) at the hidden layer with 11 neurons. The minimum mean squared error (MSE) of 0.0017 and coefficient of determination (R(2)) of 0.9658 were found for prediction and modeling of dye removal using testing data set. A good agreement between experimental data and predicted data using the ANN model was obtained. Fitting the experimental data on previously optimized condition confirm the suitability of Langmuir isotherm models for their explanation with maximum adsorption capacity of 434.8mg/g at 25°C. Kinetic studies at various adsorbent mass and initial MG concentration show that the MG maximum removal percentage was achieved within 20min. The adsorption of MG follows the pseudo-second-order with a combination of intraparticle diffusion model. PMID:25699703
NASA Astrophysics Data System (ADS)
Ghaedi, M.; Shojaeipour, E.; Ghaedi, A. M.; Sahraei, Reza
2015-05-01
In this study, copper nanowires loaded on activated carbon (Cu-NWs-AC) was used as novel efficient adsorbent for the removal of malachite green (MG) from aqueous solution. This new material was synthesized through simple protocol and its surface properties such as surface area, pore volume and functional groups were characterized with different techniques such XRD, BET and FESEM analysis. The relation between removal percentages with variables such as solution pH, adsorbent dosage (0.005, 0.01, 0.015, 0.02 and 0.1 g), contact time (1-40 min) and initial MG concentration (5, 10, 20, 70 and 100 mg/L) was investigated and optimized. A three-layer artificial neural network (ANN) model was utilized to predict the malachite green dye removal (%) by Cu-NWs-AC following conduction of 248 experiments. When the training of the ANN was performed, the parameters of ANN model were as follows: linear transfer function (purelin) at output layer, Levenberg-Marquardt algorithm (LMA), and a tangent sigmoid transfer function (tansig) at the hidden layer with 11 neurons. The minimum mean squared error (MSE) of 0.0017 and coefficient of determination (R2) of 0.9658 were found for prediction and modeling of dye removal using testing data set. A good agreement between experimental data and predicted data using the ANN model was obtained. Fitting the experimental data on previously optimized condition confirm the suitability of Langmuir isotherm models for their explanation with maximum adsorption capacity of 434.8 mg/g at 25 °C. Kinetic studies at various adsorbent mass and initial MG concentration show that the MG maximum removal percentage was achieved within 20 min. The adsorption of MG follows the pseudo-second-order with a combination of intraparticle diffusion model.
The design and analysis of effective and efficient neural networks and their applications
Makovoz, W.V.
1989-01-01
A complicated design issue of efficient Multilayer neural networks is addressed, and the perception and similar neural networks are examined. It shows that a three-layer perceptron neural network with specially designed learning algorithms provides an efficient framework to solve an exclusive OR problem using only n {minus} 1 processing elements in the second layer. Two efficient rapidly converging algorithms for any symmetric Boolean function were developed using only n {minus} 1 processing elements in the perceptron neural network and int(n/2) processing elements in the Adaline and perceptron neural network with the stepfunction transfer function. Similar results were obtained for the quasi-symmetric Boolean functions using a linear number of processing elements in perceptron neural networks, Adaline's, and perceptron neural networks with the stepfunction transfer functions. Generalized Boolean functions are discussed and two rapidly converging algorithms are shown for perceptron neural networks, Adaline's, and perceptron neural network with stepfunction transfer function. Many other interesting perceptron neural networks are discussed in the dissertation. Perceptron neural networks are applied to find the largest value of the n inputs. A new perceptron neural network is designed to find the largest value of the n inputs with the minimum number of inputs and the minimum number of layers. New perceptron neural networks are developed to sort n inputs. New, effective and efficient back-propagation Neural networks are designed to sort n inputs. The Sigmoid transfer function was discussed and a generalized Sigmoid function to improve Neural network performance was developed. A modified back-propagation learning algorithm was developed that builds any n input symmetric Boolean function using only int(n/2) processing elements in the second layer.
A scale-free neural network for modelling neurogenesis
NASA Astrophysics Data System (ADS)
Perotti, Juan I.; Tamarit, Francisco A.; Cannas, Sergio A.
2006-11-01
In this work we introduce a neural network model for associative memory based on a diluted Hopfield model, which grows through a neurogenesis algorithm that guarantees that the final network is a small-world and scale-free one. We also analyze the storage capacity of the network and prove that its performance is larger than that measured in a randomly dilute network with the same connectivity.
Inverse kinematics problem in robotics using neural networks
NASA Technical Reports Server (NTRS)
Choi, Benjamin B.; Lawrence, Charles
1992-01-01
In this paper, Multilayer Feedforward Networks are applied to the robot inverse kinematic problem. The networks are trained with endeffector position and joint angles. After training, performance is measured by having the network generate joint angles for arbitrary endeffector trajectories. A 3-degree-of-freedom (DOF) spatial manipulator is used for the study. It is found that neural networks provide a simple and effective way to both model the manipulator inverse kinematics and circumvent the problems associated with algorithmic solution methods.
Analysis of IMS spectra using neural networks
Bell, S.E.
1992-09-01
Ion mobility spectrometry (IMS) has been used for over 20 years, and IMS coupled to gas chromatography (GC/IMS) has been used for over 10 years. There still is no systematic approach to IMS spectral interpretation such as exists for mass spectrometry and infrared spectrometry. Neural networks, a form of adaptive pattern recognition, were examined as a method of data reduction for IMS and GC/IMS. A wide variety of volatile organics were analyzed using IMS and GC/IMS and submitted to different networks for identification. Several different networks and data preprocessing algorithms were studied. A network was linked to a simple rule-based expert system and analyzed. The expert system was used to filter out false positive identifications made by the network using retention indices. The various network configurations were compared to other pattern recognition techniques, including human experts. The network performance was comparable to human experts, but responded much faster. Preliminary comparison of the network to other pattern recognition showed comparable performance. Linkage of the network output to the rule-based retention index system yielded the best performance.
Analysis of IMS spectra using neural networks
Bell, S.E.
1992-01-01
Ion mobility spectrometry (IMS) has been used for over 20 years, and IMS coupled to gas chromatography (GC/IMS) has been used for over 10 years. There still is no systematic approach to IMS spectral interpretation such as exists for mass spectrometry and infrared spectrometry. Neural networks, a form of adaptive pattern recognition, were examined as a method of data reduction for IMS and GC/IMS. A wide variety of volatile organics were analyzed using IMS and GC/IMS and submitted to different networks for identification. Several different networks and data preprocessing algorithms were studied. A network was linked to a simple rule-based expert system and analyzed. The expert system was used to filter out false positive identifications made by the network using retention indices. The various network configurations were compared to other pattern recognition techniques, including human experts. The network performance was comparable to human experts, but responded much faster. Preliminary comparison of the network to other pattern recognition showed comparable performance. Linkage of the network output to the rule-based retention index system yielded the best performance.
Speaker Verification Using Subword Neural Tree Networks.
NASA Astrophysics Data System (ADS)
Liou, Han-Sheng
1995-01-01
In this dissertation, a new neural-network-based algorithm for text-dependent speaker verification is presented. The algorithm uses a set of concatenated Neural Tree Networks (NTN's) trained on subword units to model a password. In contrast to the conventional stochastic approaches which model the subword units by Hidden Markov Models (HMM's), the new approach utilizes the discriminative training scheme to train a NTN for each subword unit. Two types of subword unit are investigated, phone-like units (PLU's) and HMM state-based units (HSU's). The training of the models includes the following steps. The training utterances of a password is first segmented into subword units using a HMM-based segmentation method. A NTN is then trained for each subword unit. In order to retrieve the temporal information which is relatively important in text-dependent speaker verification, the proposed paradigm integrates the discriminatory ability of the NTN with the temporal models of the HMM. A new scoring method using phonetic weighting to improve the speaker verification performance is also introduced. The proposed algorithms are evaluated by experiments on a TI isolated-word database, YOHO database, and several hundred utterances collected over telephone channel. Performance improvements are obtained over conventional techniques.
The next generation of neural network chips
Beiu, V.
1997-08-01
There have been many national and international neural networks research initiatives: USA (DARPA, NIBS), Canada (IRIS), Japan (HFSP) and Europe (BRAIN, GALA TEA, NERVES, ELENE NERVES 2) -- just to mention a few. Recent developments in the field of neural networks, cognitive science, bioengineering and electrical engineering have made it possible to understand more about the functioning of large ensembles of identical processing elements. There are more research papers than ever proposing solutions and hardware implementations are by no means an exception. Two fields (computing and neuroscience) are interacting in ways nobody could imagine just several years ago, and -- with the advent of new technologies -- researchers are focusing on trying to copy the Brain. Such an exciting confluence may quite shortly lead to revolutionary new computers and it is the aim of this invited session to bring to light some of the challenging research aspects dealing with the hardware realizability of future intelligent chips. Present-day (conventional) technology is (still) mostly digital and, thus, occupies wider areas and consumes much more power than the solutions envisaged. The innovative algorithmic and architectural ideals should represent important breakthroughs, paving the way towards making neural network chips available to the industry at competitive prices, in relatively small packages and consuming a fraction of the power required by equivalent digital solutions.
CALIBRATION OF ONLINE ANALYZERS USING NEURAL NETWORKS
Rajive Ganguli; Daniel E. Walsh; Shaohai Yu
2003-12-05
Neural networks were used to calibrate an online ash analyzer at the Usibelli Coal Mine, Healy, Alaska, by relating the Americium and Cesium counts to the ash content. A total of 104 samples were collected from the mine, with 47 being from screened coal, and the rest being from unscreened coal. Each sample corresponded to 20 seconds of coal on the running conveyor belt. Neural network modeling used the quick stop training procedure. Therefore, the samples were split into training, calibration and prediction subsets. Special techniques, using genetic algorithms, were developed to representatively split the sample into the three subsets. Two separate approaches were tried. In one approach, the screened and unscreened coal was modeled separately. In another, a single model was developed for the entire dataset. No advantage was seen from modeling the two subsets separately. The neural network method performed very well on average but not individually, i.e. though each prediction was unreliable, the average of a few predictions was close to the true average. Thus, the method demonstrated that the analyzers were accurate at 2-3 minutes intervals (average of 6-9 samples), but not at 20 seconds (each prediction).
File access prediction using neural networks.
Patra, Prashanta Kumar; Sahu, Muktikanta; Mohapatra, Subasish; Samantray, Ronak Kumar
2010-06-01
One of the most vexing issues in design of a high-speed computer is the wide gap of access times between the memory and the disk. To solve this problem, static file access predictors have been used. In this paper, we propose dynamic file access predictors using neural networks to significantly improve upon the accuracy, success-per-reference, and effective-success-rate-per-reference by using neural-network-based file access predictor with proper tuning. In particular, we verified that the incorrect prediction has been reduced from 53.11% to 43.63% for the proposed neural network prediction method with a standard configuration than the recent popularity (RP) method. With manual tuning for each trace, we are able to improve upon the misprediction rate and effective-success-rate-per-reference using a standard configuration. Simulations on distributed file system (DFS) traces reveal that exact fit radial basis function (RBF) gives better prediction in high end system whereas multilayer perceptron (MLP) trained with Levenberg-Marquardt (LM) backpropagation outperforms in system having good computational capability. Probabilistic and competitive predictors are the most suitable for work stations having limited resources to deal with and the former predictor is more efficient than the latter for servers having maximum system calls. Finally, we conclude that MLP with LM backpropagation algorithm has better success rate of file prediction than those of simple perceptron, last successor, stable successor, and best k out of m predictors. PMID:20421183
Analysis of complex systems using neural networks
Uhrig, R.E. . Dept. of Nuclear Engineering Oak Ridge National Lab., TN )
1992-01-01
The application of neural networks, alone or in conjunction with other advanced technologies (expert systems, fuzzy logic, and/or genetic algorithms), to some of the problems of complex engineering systems has the potential to enhance the safety, reliability, and operability of these systems. Typically, the measured variables from the systems are analog variables that must be sampled and normalized to expected peak values before they are introduced into neural networks. Often data must be processed to put it into a form more acceptable to the neural network (e.g., a fast Fourier transformation of the time-series data to produce a spectral plot of the data). Specific applications described include: (1) Diagnostics: State of the Plant (2) Hybrid System for Transient Identification, (3) Sensor Validation, (4) Plant-Wide Monitoring, (5) Monitoring of Performance and Efficiency, and (6) Analysis of Vibrations. Although specific examples described deal with nuclear power plants or their subsystems, the techniques described can be applied to a wide variety of complex engineering systems.
Analysis of complex systems using neural networks
Uhrig, R.E. |
1992-12-31
The application of neural networks, alone or in conjunction with other advanced technologies (expert systems, fuzzy logic, and/or genetic algorithms), to some of the problems of complex engineering systems has the potential to enhance the safety, reliability, and operability of these systems. Typically, the measured variables from the systems are analog variables that must be sampled and normalized to expected peak values before they are introduced into neural networks. Often data must be processed to put it into a form more acceptable to the neural network (e.g., a fast Fourier transformation of the time-series data to produce a spectral plot of the data). Specific applications described include: (1) Diagnostics: State of the Plant (2) Hybrid System for Transient Identification, (3) Sensor Validation, (4) Plant-Wide Monitoring, (5) Monitoring of Performance and Efficiency, and (6) Analysis of Vibrations. Although specific examples described deal with nuclear power plants or their subsystems, the techniques described can be applied to a wide variety of complex engineering systems.
Multiresolution training of Kohonen neural networks
NASA Astrophysics Data System (ADS)
Tamir, Dan E.
2007-09-01
This paper analyses a trade-off between convergence rate and distortion obtained through a multi-resolution training of a Kohonen Competitive Neural Network. Empirical results show that a multi-resolution approach can improve the training stage of several unsupervised pattern classification algorithms including K-means clustering, LBG vector quantization, and competitive neural networks. While, previous research concentrated on convergence rate of on-line unsupervised training. New results, reported in this paper, show that the multi-resolution approach can be used to improve training quality (measured as a derivative of the rate distortion function) on the account of convergence speed. The probability of achieving a desired point in the quality/convergence-rate space of Kohonen Competitive Neural Networks (KCNN) is evaluated using a detailed Monte Carlo set of experiments. It is shown that multi-resolution can reduce the distortion by a factor of 1.5 to 6 while maintaining the convergence rate of traditional KCNN. Alternatively, the convergence rate can be improved without loss of quality. The experiments include a controlled set of synthetic data, as well as, image data. Experimental results are reported and evaluated.
Terminal attractors in neural networks
NASA Technical Reports Server (NTRS)
Zak, Michail
1989-01-01
A new type of attractor (terminal attractors) for content-addressable memory, associative memory, and pattern recognition in artificial neural networks operating in continuous time is introduced. The idea of a terminal attractor is based upon a violation of the Lipschitz condition at a fixed point. As a result, the fixed point becomes a singular solution which envelopes the family of regular solutions, while each regular solution approaches such an attractor in finite time. It will be shown that terminal attractors can be incorporated into neural networks such that any desired set of these attractors with prescribed basins is provided by an appropriate selection of the synaptic weights. The applications of terminal attractors for content-addressable and associative memories, pattern recognition, self-organization, and for dynamical training are illustrated.
Convolution neural networks for ship type recognition
NASA Astrophysics Data System (ADS)
Rainey, Katie; Reeder, John D.; Corelli, Alexander G.
2016-05-01
Algorithms to automatically recognize ship type from satellite imagery are desired for numerous maritime applications. This task is difficult, and example imagery accurately labeled with ship type is hard to obtain. Convolutional neural networks (CNNs) have shown promise in image recognition settings, but many of these applications rely on the availability of thousands of example images for training. This work attempts to under- stand for which types of ship recognition tasks CNNs might be well suited. We report the results of baseline experiments applying a CNN to several ship type classification tasks, and discuss many of the considerations that must be made in approaching this problem.
Artificial Neural Network applied to lightning flashes
NASA Astrophysics Data System (ADS)
Gin, R. B.; Guedes, D.; Bianchi, R.
2013-05-01
The development of video cameras enabled cientists to study lightning discharges comportment with more precision. The main goal of this project is to create a system able to detect images of lightning discharges stored in videos and classify them using an Artificial Neural Network (ANN)using C Language and OpenCV libraries. The developed system, can be split in two different modules: detection module and classification module. The detection module uses OpenCV`s computer vision libraries and image processing techniques to detect if there are significant differences between frames in a sequence, indicating that something, still not classified, occurred. Whenever there is a significant difference between two consecutive frames, two main algorithms are used to analyze the frame image: brightness and shape algorithms. These algorithms detect both shape and brightness of the event, removing irrelevant events like birds, as well as detecting the relevant events exact position, allowing the system to track it over time. The classification module uses a neural network to classify the relevant events as horizontal or vertical lightning, save the event`s images and calculates his number of discharges. The Neural Network was implemented using the backpropagation algorithm, and was trained with 42 training images , containing 57 lightning events (one image can have more than one lightning). TheANN was tested with one to five hidden layers, with up to 50 neurons each. The best configuration achieved a success rate of 95%, with one layer containing 20 neurons (33 test images with 42 events were used in this phase). This configuration was implemented in the developed system to analyze 20 video files, containing 63 lightning discharges previously manually detected. Results showed that all the lightning discharges were detected, many irrelevant events were unconsidered, and the event's number of discharges was correctly computed. The neural network used in this project achieved a
The LILARTI neural network system
Allen, J.D. Jr.; Schell, F.M.; Dodd, C.V.
1992-10-01
The material of this Technical Memorandum is intended to provide the reader with conceptual and technical background information on the LILARTI neural network system of detail sufficient to confer an understanding of the LILARTI method as it is presently allied and to facilitate application of the method to problems beyond the scope of this document. Of particular importance in this regard are the descriptive sections and the Appendices which include operating instructions, partial listings of program output and data files, and network construction information.
The hysteretic Hopfield neural network.
Bharitkar, S; Mendel, J M
2000-01-01
A new neuron activation function based on a property found in physical systems--hysteresis--is proposed. We incorporate this neuron activation in a fully connected dynamical system to form the hysteretic Hopfield neural network (HHNN). We then present an analog implementation of this architecture and its associated dynamical equation and energy function.We proceed to prove Lyapunov stability for this new model, and then solve a combinatorial optimization problem (i.e., the N-queen problem) using this network. We demonstrate the advantages of hysteresis by showing increased frequency of convergence to a solution, when the parameters associated with the activation function are varied. PMID:18249816
NASA Astrophysics Data System (ADS)
Hassanzadeh, Zeinabe; Kompany-Zareh, Mohsen; Ghavami, Raouf; Gholami, Somayeh; Malek-Khatabi, Atefe
2015-10-01
The configuring of a radial basis function neural network (RBFN) consists of optimizing the architecture and the network parameters (centers, widths, and weights). Methods such as genetic algorithm (GA), K-means and cluster analysis (CA) are among center selection methods. In the most of reports on RBFN modeling optimum centers are selected among rows of descriptors matrix. A combination of RBFN and GA is introduced for better description of quantitative structure-property relationships (QSPR) models. In this method, centers are not exactly rows of the independent matrix and can be located in any point of the samples space. In the proposed approach, initial centers are randomly selected from the calibration set. Then GA changes the locations of the initially selected centers to find the optimum positions of centers from the whole space of scores matrix, in order to obtain highest prediction ability. This approach is called whole space GA-RBFN (wsGA-RBFN) and applied to predict the adsorption coefficients (logk), of 40 small molecules on the surface of multi-walled carbon nanotubes (MWCNTs). The data consists of five solute descriptors [R, π, α, β, V] of the molecules and known as data set1. Prediction ability of wsGA-RBFN is compared to GA-RBFN and MLR models. The obtained Q2 values for wsGA-RBFN, GA-RBFN and MLR are 0.95, 0.85, and 0.78, respectively, which shows the merit of wsGA-RBFN. The method is also applied on the logarithm of surface area normalized adsorption coefficients (logKSA), of organic compounds (OCs) on MWCNTs surface. The data set2 includes 69 aromatic molecules with 13 physicochemical properties of the OCs. Thirty-nine of these molecules were similar to those of data set1 and the others were aromatic compounds included of small and big molecules. Prediction ability of wsGA-RBFN for second data set was compared to GA-RBF. The Q2 values for wsGA-RBFN and GA-RBF are obtained as 0.89 and 0.80, respectively.
Noise-enhanced convolutional neural networks.
Audhkhasi, Kartik; Osoba, Osonde; Kosko, Bart
2016-06-01
Injecting carefully chosen noise can speed convergence in the backpropagation training of a convolutional neural network (CNN). The Noisy CNN algorithm speeds training on average because the backpropagation algorithm is a special case of the generalized expectation-maximization (EM) algorithm and because such carefully chosen noise always speeds up the EM algorithm on average. The CNN framework gives a practical way to learn and recognize images because backpropagation scales with training data. It has only linear time complexity in the number of training samples. The Noisy CNN algorithm finds a special separating hyperplane in the network's noise space. The hyperplane arises from the likelihood-based positivity condition that noise-boosts the EM algorithm. The hyperplane cuts through a uniform-noise hypercube or Gaussian ball in the noise space depending on the type of noise used. Noise chosen from above the hyperplane speeds training on average. Noise chosen from below slows it on average. The algorithm can inject noise anywhere in the multilayered network. Adding noise to the output neurons reduced the average per-iteration training-set cross entropy by 39% on a standard MNIST image test set of handwritten digits. It also reduced the average per-iteration training-set classification error by 47%. Adding noise to the hidden layers can also reduce these performance measures. The noise benefit is most pronounced for smaller data sets because the largest EM hill-climbing gains tend to occur in the first few iterations. This noise effect can assist random sampling from large data sets because it allows a smaller random sample to give the same or better performance than a noiseless sample gives. PMID:26700535
Synthesis of recurrent neural networks for dynamical system simulation.
Trischler, Adam P; D'Eleuterio, Gabriele M T
2016-08-01
We review several of the most widely used techniques for training recurrent neural networks to approximate dynamical systems, then describe a novel algorithm for this task. The algorithm is based on an earlier theoretical result that guarantees the quality of the network approximation. We show that a feedforward neural network can be trained on the vector-field representation of a given dynamical system using backpropagation, then recast it as a recurrent network that replicates the original system's dynamics. After detailing this algorithm and its relation to earlier approaches, we present numerical examples that demonstrate its capabilities. One of the distinguishing features of our approach is that both the original dynamical systems and the recurrent networks that simulate them operate in continuous time. PMID:27182811
Detection of Wildfires with Artificial Neural Networks
NASA Astrophysics Data System (ADS)
Umphlett, B.; Leeman, J.; Morrissey, M. L.
2011-12-01
Currently fire detection for the National Oceanic and Atmospheric Administration (NOAA) using satellite data is accomplished with algorithms and error checking human analysts. Artificial neural networks (ANNs) have been shown to be more accurate than algorithms or statistical methods for applications dealing with multiple datasets of complex observed data in the natural sciences. ANNs also deal well with multiple data sources that are not all equally reliable or equally informative to the problem. An ANN was tested to evaluate its accuracy in detecting wildfires utilizing polar orbiter numerical data from the Advanced Very High Resolution Radiometer (AVHRR). Datasets containing locations of known fires were gathered from the NOAA's polar orbiting satellites via the Comprehensive Large Array-data Stewardship System (CLASS). The data was then calibrated and navigation corrected using the Environment for Visualizing Images (ENVI). Fires were located with the aid of shapefiles generated via ArcGIS. Afterwards, several smaller ten pixel by ten pixel datasets were created for each fire (using the ENVI corrected data). Several datasets were created for each fire in order to vary fire position and avoid training the ANN to look only at fires in the center of an image. Datasets containing no fires were also created. A basic pattern recognition neural network was established with the MATLAB neural network toolbox. The datasets were then randomly separated into categories used to train, validate, and test the ANN. To prevent over fitting of the data, the mean squared error (MSE) of the network was monitored and training was stopped when the MSE began to rise. Networks were tested using each channel of the AVHRR data independently, channels 3a and 3b combined, and all six channels. The number of hidden neurons for each input set was also varied between 5-350 in steps of 5 neurons. Each configuration was run 10 times, totaling about 4,200 individual network evaluations. Thirty
Probabilistic neural networks for infrared imaging target discrimination
NASA Astrophysics Data System (ADS)
Cayouette, Patrice; Labonte, G.; Morin, A.
2003-09-01
The next generation of infrared imaging trackers and seekers will allow for the implementation of more smarter tracking algorithms, able to keep a positive lock on a targeted aircraft in the presence of countermeasures. Pattern recognition algorithms will be able to select targets based on features extracted from all possible targets images. Artificial neural networks provide an important class of such algorithms. In particular, probabilistic neural networks perform almost as optimal Bayesian classifiers, by approximating the probability density functions of the features of the objects. Furthermore, these neural networks generate an output that indicates the confidence it has in its answer. We have evaluated the the possibility of integrating such neural networks in an infrared imaging seeker emulator, devised by the Defense Research and Development establishment at Valcartier. We describe the characteristics extracted from the images and define translation invariant features from these. We give a basis for the selection of which features to use as input for the neural network. We build the network and test it on some real data. Results are shown, which indicate a remarkable efficiency of over 98% correct recognition. For most of the images on which the neural network makes its mistakes, even a human expert would probably have been mistaken. We build a reduced version of this network, with 82% fewer neurons, and only a 0.6% less precision. Such a neural network could well be used in a real time system because its computing time on a normal PC gives a rate of over 5,300 patterns per second.
Design of Neural Networks for Fast Convergence and Accuracy
NASA Technical Reports Server (NTRS)
Maghami, Peiman G.; Sparks, Dean W., Jr.
1998-01-01
A novel procedure for the design and training of artificial neural networks, used for rapid and efficient controls and dynamics design and analysis for flexible space systems, has been developed. Artificial neural networks are employed to provide a means of evaluating the impact of design changes rapidly. Specifically, two-layer feedforward neural networks are designed to approximate the functional relationship between the component spacecraft design changes and measures of its performance. A training algorithm, based on statistical sampling theory, is presented, which guarantees that the trained networks provide a designer-specified degree of accuracy in mapping the functional relationship. Within each iteration of this statistical-based algorithm, a sequential design algorithm is used for the design and training of the feedforward network to provide rapid convergence to the network goals. Here, at each sequence a new network is trained to minimize the error of previous network. The design algorithm attempts to avoid the local minima phenomenon that hampers the traditional network training. A numerical example is performed on a spacecraft application in order to demonstrate the feasibility of the proposed approach.
Road Detection by Neural and Genetic Algorithm in Urban Environment
NASA Astrophysics Data System (ADS)
Barsi, A.
2012-07-01
In the urban object detection challenge organized by the ISPRS WG III/4 high geometric and radiometric resolution aerial images about Vaihingen/Stuttgart, Germany are distributed. The acquired data set contains optical false color, near infrared images and airborne laserscanning data. The presented research focused exclusively on the optical image, so the elevation information was ignored. The road detection procedure has been built up of two main phases: a segmentation done by neural networks and a compilation made by genetic algorithms. The applied neural networks were support vector machines with radial basis kernel function and self-organizing maps with hexagonal network topology and Euclidean distance function for neighborhood management. The neural techniques have been compared by hyperbox classifier, known from the statistical image classification practice. The compilation of the segmentation is realized by a novel application of the common genetic algorithm and by differential evolution technique. The genes were implemented to detect the road elements by evaluating a special binary fitness function. The results have proven that the evolutional technique can automatically find major road segments.
Load forecasting using artificial neural networks
Pham, K.D.
1995-12-31
Artificial neural networks, modeled after their biological counterpart, have been successfully applied in many diverse areas including speech and pattern recognition, remote sensing, electrical power engineering, robotics and stock market forecasting. The most commonly used neural networks are those that gained knowledge from experience. Experience is presented to the network in form of the training data. Once trained, the neural network can recognized data that it has not seen before. This paper will present a fundamental introduction to the manner in which neural networks work and how to use them in load forecasting.
Bagging and boosting negatively correlated neural networks.
Islam, Md Monirul; Yao, Xin; Shahriar Nirjon, S M Shahriar; Islam, Muhammad Asiful; Murase, Kazuyuki
2008-06-01
In this paper, we propose two cooperative ensemble learning algorithms, i.e., NegBagg and NegBoost, for designing neural network (NN) ensembles. The proposed algorithms incrementally train different individual NNs in an ensemble using the negative correlation learning algorithm. Bagging and boosting algorithms are used in NegBagg and NegBoost, respectively, to create different training sets for different NNs in the ensemble. The idea behind using negative correlation learning in conjunction with the bagging/boosting algorithm is to facilitate interaction and cooperation among NNs during their training. Both NegBagg and NegBoost use a constructive approach to automatically determine the number of hidden neurons for NNs. NegBoost also uses the constructive approach to automatically determine the number of NNs for the ensemble. The two algorithms have been tested on a number of benchmark problems in machine learning and NNs, including Australian credit card assessment, breast cancer, diabetes, glass, heart disease, letter recognition, satellite, soybean, and waveform problems. The experimental results show that NegBagg and NegBoost require a small number of training epochs to produce compact NN ensembles with good generalization. PMID:18558541
3-D flame temperature field reconstruction with multiobjective neural network
NASA Astrophysics Data System (ADS)
Wan, Xiong; Gao, Yiqing; Wang, Yuanmei
2003-02-01
A novel 3-D temperature field reconstruction method is proposed in this paper, which is based on multiwavelength thermometry and Hopfield neural network computed tomography. A mathematical model of multi-wavelength thermometry is founded, and a neural network algorithm based on multiobjective optimization is developed. Through computer simulation and comparison with the algebraic reconstruction technique (ART) and the filter back-projection algorithm (FBP), the reconstruction result of the new method is discussed in detail. The study shows that the new method always gives the best reconstruction results. At last, temperature distribution of a section of four peaks candle flame is reconstructed with this novel method.
FPGA implementation of a pyramidal Weightless Neural Networks learning system.
Al-Alawi, Raida
2003-08-01
A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model facilitates the on-chip learning of pyramidal Weightless Neural Networks using a modified probabilistic search reward/penalty training algorithm. The penalization strategy of the training algorithm depends on a predefined parameter called the probabilistic search interval. A complete Weightless Neural Network (WNN) learning system is modeled and implemented on Xilinx XC4005E Field Programmable Gate Array (FPGA), allowing its architecture to be configurable. Various experiments have been conducted to examine the feasibility and performance of the WNN learning system. Results show that the system has a fast convergence rate and good generalization ability. PMID:12964210
A biologically inspired neural network for dynamic programming.
Francelin Romero, R A; Kacpryzk, J; Gomide, F
2001-12-01
An artificial neural network with a two-layer feedback topology and generalized recurrent neurons, for solving nonlinear discrete dynamic optimization problems, is developed. A direct method to assign the weights of neural networks is presented. The method is based on Bellmann's Optimality Principle and on the interchange of information which occurs during the synaptic chemical processing among neurons. The neural network based algorithm is an advantageous approach for dynamic programming due to the inherent parallelism of the neural networks; further it reduces the severity of computational problems that can occur in methods like conventional methods. Some illustrative application examples are presented to show how this approach works out including the shortest path and fuzzy decision making problems. PMID:11852439
Neural network modeling of emotion
NASA Astrophysics Data System (ADS)
Levine, Daniel S.
2007-03-01
This article reviews the history and development of computational neural network modeling of cognitive and behavioral processes that involve emotion. The exposition starts with models of classical conditioning dating from the early 1970s. Then it proceeds toward models of interactions between emotion and attention. Then models of emotional influences on decision making are reviewed, including some speculative (not and not yet simulated) models of the evolution of decision rules. Through the late 1980s, the neural networks developed to model emotional processes were mainly embodiments of significant functional principles motivated by psychological data. In the last two decades, network models of these processes have become much more detailed in their incorporation of known physiological properties of specific brain regions, while preserving many of the psychological principles from the earlier models. Most network models of emotional processes so far have dealt with positive and negative emotion in general, rather than specific emotions such as fear, joy, sadness, and anger. But a later section of this article reviews a few models relevant to specific emotions: one family of models of auditory fear conditioning in rats, and one model of induced pleasure enhancing creativity in humans. Then models of emotional disorders are reviewed. The article concludes with philosophical statements about the essential contributions of emotion to intelligent behavior and the importance of quantitative theories and models to the interdisciplinary enterprise of understanding the interactions of emotion, cognition, and behavior.
Blur identification by multilayer neural network based on multivalued neurons.
Aizenberg, Igor; Paliy, Dmitriy V; Zurada, Jacek M; Astola, Jaakko T
2008-05-01
A multilayer neural network based on multivalued neurons (MLMVN) is a neural network with a traditional feedforward architecture. At the same time, this network has a number of specific different features. Its backpropagation learning algorithm is derivative-free. The functionality of MLMVN is superior to that of the traditional feedforward neural networks and of a variety kernel-based networks. Its higher flexibility and faster adaptation to the target mapping enables to model complex problems using simpler networks. In this paper, the MLMVN is used to identify both type and parameters of the point spread function, whose precise identification is of crucial importance for the image deblurring. The simulation results show the high efficiency of the proposed approach. It is confirmed that the MLMVN is a powerful tool for solving classification problems, especially multiclass ones. PMID:18467216
Hybrid interior point training of modular neural networks.
Szymanski, P T; Lemmon, M; Bett, C J
1998-03-01
Modular neural networks use a single gating neuron to select the outputs of a collection of agent neurons. Expectation-maximization (EM) algorithms provide one way of training modular neural networks to approximate non-linear functionals. This paper introduces a hybrid interior-point (HIP) algorithm for training modular networks. The HIP algorithm combines an interior-point linear programming (LP) algorithm with a Newton-Raphson iteration in such a way that the computational efficiency of the interior point LP methods is preserved. The algorithm is formally proven to converge asymptotically to locally optimal networks with a total computational cost that scales in a polynomial manner with problem size. Simulation experiments show that the HIP algorithm produces networks whose average approximation error is better than that of EM-trained networks. These results also demonstrate that the computational cost of the HIP algorithm scales at a slower rate than the EM-procedure and that, for small-size networks, the total computational costs of both methods are comparable. PMID:12662833
Devices and circuits for nanoelectronic implementation of artificial neural networks
NASA Astrophysics Data System (ADS)
Turel, Ozgur
Biological neural networks perform complicated information processing tasks at speeds better than conventional computers based on conventional algorithms. This has inspired researchers to look into the way these networks function, and propose artificial networks that mimic their behavior. Unfortunately, most artificial neural networks, either software or hardware, do not provide either the speed or the complexity of a human brain. Nanoelectronics, with high density and low power dissipation that it provides, may be used in developing more efficient artificial neural networks. This work consists of two major contributions in this direction. First is the proposal of the CMOL concept, hybrid CMOS-molecular hardware [1-8]. CMOL may circumvent most of the problems in posed by molecular devices, such as low yield, vet provide high active device density, ˜1012/cm 2. The second contribution is CrossNets, artificial neural networks that are based on CMOL. We showed that CrossNets, with their fault tolerance, exceptional speed (˜ 4 to 6 orders of magnitude faster than biological neural networks) can perform any task any artificial neural network can perform. Moreover, there is a hope that if their integration scale is increased to that of human cerebral cortex (˜ 1010 neurons and ˜ 1014 synapses), they may be capable of performing more advanced tasks.
Neural network models for a resource allocation problem.
Walczak, S
1998-01-01
University admissions and business personnel offices use a limited number of resources to process an ever-increasing quantity of student and employment applications. Application systems are further constrained to identify and acquire, in a limited time period, those candidates who are most likely to accept an offer of enrolment or employment. Neural networks are a new methodology to this particular domain. Various neural network architectures and learning algorithms are analyzed comparatively to determine the applicability of supervised learning neural networks to the domain problem of personnel resource allocation and to identify optimal learning strategies in this domain. This paper focuses on multilayer perceptron backpropagation, radial basis function, counterpropagation, general regression, fuzzy ARTMAP, and linear vector quantization neural networks. Each neural network predicts the probability of enrolment and nonenrolment for individual student applicants. Backpropagation networks produced the best overall performance. Network performance results are measured by the reduction in counsellors student case load and corresponding increases in student enrolment. The backpropagation neural networks achieve a 56% reduction in counsellor case load. PMID:18255946
Neural networks for aircraft system identification
NASA Technical Reports Server (NTRS)
Linse, Dennis J.
1991-01-01
Artificial neural networks offer some interesting possibilities for use in control. Our current research is on the use of neural networks on an aircraft model. The model can then be used in a nonlinear control scheme. The effectiveness of network training is demonstrated.
Neural-Network Computer Transforms Coordinates
NASA Technical Reports Server (NTRS)
Josin, Gary M.
1990-01-01
Numerical simulation demonstrated ability of conceptual neural-network computer to generalize what it has "learned" from few examples. Ability to generalize achieved with even simple neural network (relatively few neurons) and after exposure of network to only few "training" examples. Ability to obtain fairly accurate mappings after only few training examples used to provide solutions to otherwise intractable mapping problems.
Neural Networks in Nonlinear Aircraft Control
NASA Technical Reports Server (NTRS)
Linse, Dennis J.
1990-01-01
Recent research indicates that artificial neural networks offer interesting learning or adaptive capabilities. The current research focuses on the potential for application of neural networks in a nonlinear aircraft control law. The current work has been to determine which networks are suitable for such an application and how they will fit into a nonlinear control law.
Resource constrained design of artificial neural networks using comparator neural network
NASA Technical Reports Server (NTRS)
Wah, Benjamin W.; Karnik, Tanay S.
1992-01-01
We present a systematic design method executed under resource constraints for automating the design of artificial neural networks using the back error propagation algorithm. Our system aims at finding the best possible configuration for solving the given application with proper tradeoff between the training time and the network complexity. The design of such a system is hampered by three related problems. First, there are infinitely many possible network configurations, each may take an exceedingly long time to train; hence, it is impossible to enumerate and train all of them to completion within fixed time, space, and resource constraints. Second, expert knowledge on predicting good network configurations is heuristic in nature and is application dependent, rendering it difficult to characterize fully in the design process. A learning procedure that refines this knowledge based on examples on training neural networks for various applications is, therefore, essential. Third, the objective of the network to be designed is ill-defined, as it is based on a subjective tradeoff between the training time and the network cost. A design process that proposes alternate configurations under different cost-performance tradeoff is important. We have developed a Design System which schedules the available time, divided into quanta, for testing alternative network configurations. Its goal is to select/generate and test alternative network configurations in each quantum, and find the best network when time is expended. Since time is limited, a dynamic schedule that determines the network configuration to be tested in each quantum is developed. The schedule is based on relative comparison of predicted training times of alternative network configurations using comparator network paradigm. The comparator network has been trained to compare training times for a large variety of traces of TSSE-versus-time collected during back-propagation learning of various applications.
Associated neural network independent component analysis structure
NASA Astrophysics Data System (ADS)
Kim, Keehoon; Kostrzweski, Andrew
2006-05-01
Detection, classification, and localization of potential security breaches in extremely high-noise environments are important for perimeter protection and threat detection both for homeland security and for military force protection. Physical Optics Corporation has developed a threat detection system to separate acoustic signatures from unknown, mixed sources embedded in extremely high-noise environments where signal-to-noise ratios (SNRs) are very low. Associated neural network structures based on independent component analysis are designed to detect/separate new acoustic sources and to provide reliability information. The structures are tested through computer simulations for each critical component, including a spontaneous detection algorithm for potential threat detection without a predefined knowledge base, a fast target separation algorithm, and nonparametric methodology for quantified confidence measure. The results show that the method discussed can separate hidden acoustic sources of SNR in 5 dB noisy environments with an accuracy of 80%.
Neural network-based sensor signal accelerator.
Vogt, M. C.
2000-10-16
A strategy has been developed to computationally accelerate the response time of a generic electronic sensor. The strategy can be deployed as an algorithm in a control system or as a physical interface (on an embedded microcontroller) between a slower responding external sensor and a higher-speed control system. Optional code implementations are available to adjust algorithm performance when computational capability is limited. In one option, the actual sensor signal can be sampled at the slower rate with adaptive linear neural networks predicting the sensor's future output and interpolating intermediate synthetic output values. In another option, a synchronized collection of predictors sequentially controls the corresponding synthetic output voltage. Error is adaptively corrected in both options. The core strategy has been demonstrated with automotive oxygen sensor data. A prototype interface device is under construction. The response speed increase afforded by this strategy could greatly offset the cost of developing a replacement sensor with a faster physical response time.
Demonstrations of Neural Network Computations Involving Students
May, Christopher J.
2010-01-01
David Marr famously proposed three levels of analysis (implementational, algorithmic, and computational) for understanding information processing systems such as the brain. While two of these levels are commonly taught in neuroscience courses (the implementational level through neurophysiology and the computational level through systems/cognitive neuroscience), the algorithmic level is typically neglected. This leaves an explanatory gap in students’ understanding of how, for example, the flow of sodium ions enables cognition. Neural networks bridge these two levels by demonstrating how collections of interacting neuron-like units can give rise to more overtly cognitive phenomena. The demonstrations in this paper are intended to facilitate instructors’ introduction and exploration of how neurons “process information.” PMID:23493501
Adaptive optimization and control using neural networks
Mead, W.C.; Brown, S.K.; Jones, R.D.; Bowling, P.S.; Barnes, C.W.
1993-10-22
Recent work has demonstrated the ability of neural-network-based controllers to optimize and control machines with complex, non-linear, relatively unknown control spaces. We present a brief overview of neural networks via a taxonomy illustrating some capabilities of different kinds of neural networks. We present some successful control examples, particularly the optimization and control of a small-angle negative ion source.
Neural network computer simulation of medical aerosols.
Richardson, C J; Barlow, D J
1996-06-01
Preliminary investigations have been conducted to assess the potential for using artificial neural networks to simulate aerosol behaviour, with a view to employing this type of methodology in the evaluation and design of pulmonary drug-delivery systems. Details are presented of the general purpose software developed for these tasks; it implements a feed-forward back-propagation algorithm with weight decay and connection pruning, the user having complete run-time control of the network architecture and mode of training. A series of exploratory investigations is then reported in which different network structures and training strategies are assessed in terms of their ability to simulate known patterns of fluid flow in simple model systems. The first of these involves simulations of cellular automata-generated data for fluid flow through a partially obstructed two-dimensional pipe. The artificial neural networks are shown to be highly successful in simulating the behaviour of this simple linear system, but with important provisos relating to the information content of the training data and the criteria used to judge when the network is properly trained. A second set of investigations is then reported in which similar networks are used to simulate patterns of fluid flow through aerosol generation devices, using training data furnished through rigorous computational fluid dynamics modelling. These more complex three-dimensional systems are modelled with equal success. It is concluded that carefully tailored, well trained networks could provide valuable tools not just for predicting but also for analysing the spatial dynamics of pharmaceutical aerosols. PMID:8832491
Complexity matching in neural networks
NASA Astrophysics Data System (ADS)
Usefie Mafahim, Javad; Lambert, David; Zare, Marzieh; Grigolini, Paolo
2015-01-01
In the wide literature on the brain and neural network dynamics the notion of criticality is being adopted by an increasing number of researchers, with no general agreement on its theoretical definition, but with consensus that criticality makes the brain very sensitive to external stimuli. We adopt the complexity matching principle that the maximal efficiency of communication between two complex networks is realized when both of them are at criticality. We use this principle to establish the value of the neuronal interaction strength at which criticality occurs, yielding a perfect agreement with the adoption of temporal complexity as criticality indicator. The emergence of a scale-free distribution of avalanche size is proved to occur in a supercritical regime. We use an integrate-and-fire model where the randomness of each neuron is only due to the random choice of a new initial condition after firing. The new model shares with that proposed by Izikevich the property of generating excessive periodicity, and with it the annihilation of temporal complexity at supercritical values of the interaction strength. We find that the concentration of inhibitory links can be used as a control parameter and that for a sufficiently large concentration of inhibitory links criticality is recovered again. Finally, we show that the response of a neural network at criticality to a harmonic stimulus is very weak, in accordance with the complexity matching principle.
Advances in neural networks research: an introduction.
Kozma, Robert; Bressler, Steven; Perlovsky, Leonid; Venayagamoorthy, Ganesh Kumar
2009-01-01
The present Special Issue "Advances in Neural Networks Research: IJCNN2009" provides a state-of-art overview of the field of neural networks. It includes 39 papers from selected areas of the 2009 International Joint Conference on Neural Networks (IJCNN2009). IJCNN2009 took place on June 14-19, 2009 in Atlanta, Georgia, USA, and it represents an exemplary collaboration between the International Neural Networks Society and the IEEE Computational Intelligence Society. Topics in this issue include neuroscience and cognitive science, computational intelligence and machine learning, hybrid techniques, nonlinear dynamics and chaos, various soft computing technologies, intelligent signal processing and pattern recognition, bioinformatics and biomedicine, and engineering applications. PMID:19632811
Neural network based system for equipment surveillance
Vilim, R.B.; Gross, K.C.; Wegerich, S.W.
1998-04-28
A method and system are disclosed for performing surveillance of transient signals of an industrial device to ascertain the operating state. The method and system involves the steps of reading into a memory training data, determining neural network weighting values until achieving target outputs close to the neural network output. If the target outputs are inadequate, wavelet parameters are determined to yield neural network outputs close to the desired set of target outputs and then providing signals characteristic of an industrial process and comparing the neural network output to the industrial process signals to evaluate the operating state of the industrial process. 33 figs.
Neural network based system for equipment surveillance
Vilim, Richard B.; Gross, Kenneth C.; Wegerich, Stephan W.
1998-01-01
A method and system for performing surveillance of transient signals of an industrial device to ascertain the operating state. The method and system involves the steps of reading into a memory training data, determining neural network weighting values until achieving target outputs close to the neural network output. If the target outputs are inadequate, wavelet parameters are determined to yield neural network outputs close to the desired set of target outputs and then providing signals characteristic of an industrial process and comparing the neural network output to the industrial process signals to evaluate the operating state of the industrial process.
Neural network modeling of distillation columns
Baratti, R.; Vacca, G.; Servida, A.
1995-06-01
Neural network modeling (NNM) was implemented for monitoring and control applications on two actual distillation columns: the butane splitter tower and the gasoline stabilizer. The two distillation columns are in operation at the SARAS refinery. Results show that with proper implementation techniques NNM can significantly improve column operation. The common belief that neural networks can be used as black-box process models is not completely true. Effective implementation always requires a minimum degree of process knowledge to identify the relevant inputs to the net. After background and generalities on neural network modeling, the paper describes efforts on the development of neural networks for the two distillation units.
Electronic neural networks for global optimization
NASA Technical Reports Server (NTRS)
Thakoor, A. P.; Moopenn, A. W.; Eberhardt, S.
1990-01-01
An electronic neural network with feedback architecture, implemented in analog custom VLSI is described. Its application to problems of global optimization for dynamic assignment is discussed. The convergence properties of the neural network hardware are compared with computer simulation results. The neural network's ability to provide optimal or near optimal solutions within only a few neuron time constants, a speed enhancement of several orders of magnitude over conventional search methods, is demonstrated. The effect of noise on the circuit dynamics and the convergence behavior of the neural network hardware is also examined.
Aerodynamic Design Using Neural Networks
NASA Technical Reports Server (NTRS)
Rai, Man Mohan; Madavan, Nateri K.
2003-01-01
The design of aerodynamic components of aircraft, such as wings or engines, involves a process of obtaining the most optimal component shape that can deliver the desired level of component performance, subject to various constraints, e.g., total weight or cost, that the component must satisfy. Aerodynamic design can thus be formulated as an optimization problem that involves the minimization of an objective function subject to constraints. A new aerodynamic design optimization procedure based on neural networks and response surface methodology (RSM) incorporates the advantages of both traditional RSM and neural networks. The procedure uses a strategy, denoted parameter-based partitioning of the design space, to construct a sequence of response surfaces based on both neural networks and polynomial fits to traverse the design space in search of the optimal solution. Some desirable characteristics of the new design optimization procedure include the ability to handle a variety of design objectives, easily impose constraints, and incorporate design guidelines and rules of thumb. It provides an infrastructure for variable fidelity analysis and reduces the cost of computation by using less-expensive, lower fidelity simulations in the early stages of the design evolution. The initial or starting design can be far from optimal. The procedure is easy and economical to use in large-dimensional design space and can be used to perform design tradeoff studies rapidly. Designs involving multiple disciplines can also be optimized. Some practical applications of the design procedure that have demonstrated some of its capabilities include the inverse design of an optimal turbine airfoil starting from a generic shape and the redesign of transonic turbines to improve their unsteady aerodynamic characteristics.
Neural networks for nuclear spectroscopy
Keller, P.E.; Kangas, L.J.; Hashem, S.; Kouzes, R.T.
1995-12-31
In this paper two applications of artificial neural networks (ANNs) in nuclear spectroscopy analysis are discussed. In the first application, an ANN assigns quality coefficients to alpha particle energy spectra. These spectra are used to detect plutonium contamination in the work environment. The quality coefficients represent the levels of spectral degradation caused by miscalibration and foreign matter affecting the instruments. A set of spectra was labeled with quality coefficients by an expert and used to train the ANN expert system. Our investigation shows that the expert knowledge of spectral quality can be transferred to an ANN system. The second application combines a portable gamma-ray spectrometer with an ANN. In this system the ANN is used to automatically identify, radioactive isotopes in real-time from their gamma-ray spectra. Two neural network paradigms are examined: the linear perception and the optimal linear associative memory (OLAM). A comparison of the two paradigms shows that OLAM is superior to linear perception for this application. Both networks have a linear response and are useful in determining the composition of an unknown sample when the spectrum of the unknown is a linear superposition of known spectra. One feature of this technique is that it uses the whole spectrum in the identification process instead of only the individual photo-peaks. For this reason, it is potentially more useful for processing data from lower resolution gamma-ray spectrometers. This approach has been tested with data generated by Monte Carlo simulations and with field data from sodium iodide and Germanium detectors. With the ANN approach, the intense computation takes place during the training process. Once the network is trained, normal operation consists of propagating the data through the network, which results in rapid identification of samples. This approach is useful in situations that require fast response where precise quantification is less important.
Proceedings of the Second Joint Technology Workshop on Neural Networks and Fuzzy Logic, volume 2
NASA Technical Reports Server (NTRS)
Lea, Robert N. (Editor); Villarreal, James A. (Editor)
1991-01-01
Documented here are papers presented at the Neural Networks and Fuzzy Logic Workshop sponsored by NASA and the University of Texas, Houston. Topics addressed included adaptive systems, learning algorithms, network architectures, vision, robotics, neurobiological connections, speech recognition and synthesis, fuzzy set theory and application, control and dynamics processing, space applications, fuzzy logic and neural network computers, approximate reasoning, and multiobject decision making.
Neural Network Classifies Teleoperation Data
NASA Technical Reports Server (NTRS)
Fiorini, Paolo; Giancaspro, Antonio; Losito, Sergio; Pasquariello, Guido
1994-01-01
Prototype artificial neural network, implemented in software, identifies phases of telemanipulator tasks in real time by analyzing feedback signals from force sensors on manipulator hand. Prototype is early, subsystem-level product of continuing effort to develop automated system that assists in training and supervising human control operator: provides symbolic feedback (e.g., warnings of impending collisions or evaluations of performance) to operator in real time during successive executions of same task. Also simplifies transition between teleoperation and autonomous modes of telerobotic system.
Neural Network Modeling of Degradation of Solar Cells
Gupta, Himanshu; Ghosh, Bahniman; Banerjee, Sanjay K.
2011-05-25
Neural network modeling has been used to predict the degradation in conversion efficiency of solar cells in this work. The model takes intensity of light, temperature and exposure time as inputs and predicts the conversion efficiency of the solar cell. Backpropagation algorithm has been used to train the network. It is found that the neural network model satisfactorily predicts the degradation in efficiency of the solar cell with exposure time. The error in the computed results, after comparison with experimental results, lies in the range of 0.005-0.01, which is quite low.
Learning in stochastic neural networks for constraint satisfaction problems
NASA Technical Reports Server (NTRS)
Johnston, Mark D.; Adorf, Hans-Martin
1989-01-01
Researchers describe a newly-developed artificial neural network algorithm for solving constraint satisfaction problems (CSPs) which includes a learning component that can significantly improve the performance of the network from run to run. The network, referred to as the Guarded Discrete Stochastic (GDS) network, is based on the discrete Hopfield network but differs from it primarily in that auxiliary networks (guards) are asymmetrically coupled to the main network to enforce certain types of constraints. Although the presence of asymmetric connections implies that the network may not converge, it was found that, for certain classes of problems, the network often quickly converges to find satisfactory solutions when they exist. The network can run efficiently on serial machines and can find solutions to very large problems (e.g., N-queens for N as large as 1024). One advantage of the network architecture is that network connection strengths need not be instantiated when the network is established: they are needed only when a participating neural element transitions from off to on. They have exploited this feature to devise a learning algorithm, based on consistency techniques for discrete CSPs, that updates the network biases and connection strengths and thus improves the network performance.
The Laplacian spectrum of neural networks
de Lange, Siemon C.; de Reus, Marcel A.; van den Heuvel, Martijn P.
2014-01-01
The brain is a complex network of neural interactions, both at the microscopic and macroscopic level. Graph theory is well suited to examine the global network architecture of these neural networks. Many popular graph metrics, however, encode average properties of individual network elements. Complementing these “conventional” graph metrics, the eigenvalue spectrum of the normalized Laplacian describes a network's structure directly at a systems level, without referring to individual nodes or connections. In this paper, the Laplacian spectra of the macroscopic anatomical neuronal networks of the macaque and cat, and the microscopic network of the Caenorhabditis elegans were examined. Consistent with conventional graph metrics, analysis of the Laplacian spectra revealed an integrative community structure in neural brain networks. Extending previous findings of overlap of network attributes across species, similarity of the Laplacian spectra across the cat, macaque and C. elegans neural networks suggests a certain level of consistency in the overall architecture of the anatomical neural networks of these species. Our results further suggest a specific network class for neural networks, distinct from conceptual small-world and scale-free models as well as several empirical networks. PMID:24454286
Ozone Modeling Using Neural Networks.
NASA Astrophysics Data System (ADS)
Narasimhan, Ramesh; Keller, Joleen; Subramaniam, Ganesh; Raasch, Eric; Croley, Brandon; Duncan, Kathleen; Potter, William T.
2000-03-01
Ozone models for the city of Tulsa were developed using neural network modeling techniques. The neural models were developed using meteorological data from the Oklahoma Mesonet and ozone, nitric oxide, and nitrogen dioxide (NO2) data from Environmental Protection Agency monitoring sites in the Tulsa area. An initial model trained with only eight surface meteorological input variables and NO2 was able to simulate ozone concentrations with a correlation coefficient of 0.77. The trained model was then used to evaluate the sensitivity to the primary variables that affect ozone concentrations. The most important variables (NO2, temperature, solar radiation, and relative humidity) showed response curves with strong nonlinear codependencies. Incorporation of ozone concentrations from the previous 3 days into the model increased the correlation coefficient to 0.82. As expected, the ozone concentrations correlated best with the most recent (1-day previous) values. The model's correlation coefficient was increased to 0.88 by the incorporation of upper-air data from the National Weather Service's Nested Grid Model. Sensitivity analysis for the upper-air variables indicated unusual positive correlations between ozone and the relative humidity from 500 hPa to the tropopause in addition to the other expected correlations with upper-air temperatures, vertical wind velocity, and 1000-500-hPa layer thickness. The neural model results are encouraging for the further use of these systems to evaluate complex parameter cosensitivities, and for the use of these systems in automated ozone forecast systems.
Three dimensional living neural networks
NASA Astrophysics Data System (ADS)
Linnenberger, Anna; McLeod, Robert R.; Basta, Tamara; Stowell, Michael H. B.
2015-08-01
We investigate holographic optical tweezing combined with step-and-repeat maskless projection micro-stereolithography for fine control of 3D positioning of living cells within a 3D microstructured hydrogel grid. Samples were fabricated using three different cell lines; PC12, NT2/D1 and iPSC. PC12 cells are a rat cell line capable of differentiation into neuron-like cells NT2/D1 cells are a human cell line that exhibit biochemical and developmental properties similar to that of an early embryo and when exposed to retinoic acid the cells differentiate into human neurons useful for studies of human neurological disease. Finally induced pluripotent stem cells (iPSC) were utilized with the goal of future studies of neural networks fabricated from human iPSC derived neurons. Cells are positioned in the monomer solution with holographic optical tweezers at 1064 nm and then are encapsulated by photopolymerization of polyethylene glycol (PEG) hydrogels formed by thiol-ene photo-click chemistry via projection of a 512x512 spatial light modulator (SLM) illuminated at 405 nm. Fabricated samples are incubated in differentiation media such that cells cease to divide and begin to form axons or axon-like structures. By controlling the position of the cells within the encapsulating hydrogel structure the formation of the neural circuits is controlled. The samples fabricated with this system are a useful model for future studies of neural circuit formation, neurological disease, cellular communication, plasticity, and repair mechanisms.
UCLA PUNNS --A Neural Network Machine For Computer Vision
NASA Astrophysics Data System (ADS)
Gungner, David; Skrzypek, Josef
1987-06-01
The sequential processing paradigm limits current solutions for computer vision by restricting the number of functions which naturally map onto Von Neumann computing architectures. A variety of physical computing structures underlie the massive parallelism inherent in many visual functions. Therefore, further advances in general purpose vision must assume inseparability of function from structure. To combine function and structure we are investigating connectionist architectures using PUNNS (Perception Using Neural Network Simulation). Our approach is inspired and constrained by the analysis of visual functions that are computed in the neural networks of living things. PUNNS represents a massively parallel computer architecture which is evolving to allow the execution of certain visual functions in constant time, regardless of the size and complexity of the image. Due to the complexity and cost of building a neural net machine, a flexible neural net simulator is needed to invent, study and understand the behavior of complex vision algorithms. Some of the issues involved in building a simulator are how to compactly describe the interconnectivity of the neural network, how to input image data, how to program the neural network, and how to display the results of the network. This paper describes the implementation of PUNNS. Simulation examples and a comparison of PUNNS to other neural net simulators will be presented.
A Biomimetic Adaptive Algorithm and Low-Power Architecture for Implantable Neural Decoders
Rapoport, Benjamin I.; Wattanapanitch, Woradorn; Penagos, Hector L.; Musallam, Sam; Andersen, Richard A.; Sarpeshkar, Rahul
2010-01-01
Algorithmically and energetically efficient computational architectures that operate in real time are essential for clinically useful neural prosthetic devices. Such devices decode raw neural data to obtain direct control signals for external devices. They can also perform data compression and vastly reduce the bandwidth and consequently power expended in wireless transmission of raw data from implantable brain-machine interfaces. We describe a biomimetic algorithm and micropower analog circuit architecture for decoding neural cell ensemble signals. The decoding algorithm implements a continuous-time artificial neural network, using a bank of adaptive linear filters with kernels that emulate synaptic dynamics. The filters transform neural signal inputs into control-parameter outputs, and can be tuned automatically in an on-line learning process. We provide experimental validation of our system using neural data from thalamic head-direction cells in an awake behaving rat. PMID:19964345
Adaptive control of nonlinear systems using multistage dynamic neural networks
NASA Astrophysics Data System (ADS)
Gupta, Madan M.; Rao, Dandina H.
1992-11-01
In this paper we present a new architecture of neuron, called the dynamic neural unit (DNU). The topology of the proposed neuronal model embodies delay elements, feedforward and feedback signals weighted by the synaptic weights and a time-varying nonlinear activation function, and is thus different from the conventionally and assumed architecture of neurons. The learning algorithm for the proposed neuronal structure and the corresponding implementation scheme are presented. A multi-stage dynamic neural network is developed using the DNU as the basic processing element. The performance evaluation of the dynamic neural network is presented for nonlinear dynamic systems under various situations. The capabilities of the proposed neural network model not only account for the learning and control actions emulating some of the biological control functions, but also provide a promising parallel-distributed intelligent control scheme for large-scale complex dynamic systems.
Two-stage neural algorithm for defect detection and characterization uses an active thermography
NASA Astrophysics Data System (ADS)
Dudzik, Sebastian
2015-07-01
In the paper a two-stage neural algorithm for defect detection and characterization is presented. In order to estimate the defect depth two neural networks trained on data obtained using an active thermography were employed. The first stage of the algorithm is developed to detect the defect by a classification neural network. Then the defects depth is estimated using a regressive neural network. In this work the results of experimental investigations and simulations are shown. Further, the sensitivity analysis of the presented algorithm was conducted and the impacts of emissivity error and the ambient temperature error on the depth estimation errors were studied. The results were obtained using a test sample made of material with a low thermal diffusivity.
Neural Networks for Signal Processing and Control
NASA Astrophysics Data System (ADS)
Hesselroth, Ted Daniel
Neural networks are developed for controlling a robot-arm and camera system and for processing images. The networks are based upon computational schemes that may be found in the brain. In the first network, a neural map algorithm is employed to control a five-joint pneumatic robot arm and gripper through feedback from two video cameras. The pneumatically driven robot arm employed shares essential mechanical characteristics with skeletal muscle systems. To control the position of the arm, 200 neurons formed a network representing the three-dimensional workspace embedded in a four-dimensional system of coordinates from the two cameras, and learned a set of pressures corresponding to the end effector positions, as well as a set of Jacobian matrices for interpolating between these positions. Because of the properties of the rubber-tube actuators of the arm, the position as a function of supplied pressure is nonlinear, nonseparable, and exhibits hysteresis. Nevertheless, through the neural network learning algorithm the position could be controlled to an accuracy of about one pixel (~3 mm) after two hundred learning steps. Applications of repeated corrections in each step via the Jacobian matrices leads to a very robust control algorithm since the Jacobians learned by the network have to satisfy the weak requirement that they yield a reduction of the distance between gripper and target. The second network is proposed as a model for the mammalian vision system in which backward connections from the primary visual cortex (V1) to the lateral geniculate nucleus play a key role. The application of hebbian learning to the forward and backward connections causes the formation of receptive fields which are sensitive to edges, bars, and spatial frequencies of preferred orientations. The receptive fields are learned in such a way as to maximize the rate of transfer of information from the LGN to V1. Orientational preferences are organized into a feature map in the primary visual
Nonlinear signal processing using neural networks: Prediction and system modelling
Lapedes, A.; Farber, R.
1987-06-01
The backpropagation learning algorithm for neural networks is developed into a formalism for nonlinear signal processing. We illustrate the method by selecting two common topics in signal processing, prediction and system modelling, and show that nonlinear applications can be handled extremely well by using neural networks. The formalism is a natural, nonlinear extension of the linear Least Mean Squares algorithm commonly used in adaptive signal processing. Simulations are presented that document the additional performance achieved by using nonlinear neural networks. First, we demonstrate that the formalism may be used to predict points in a highly chaotic time series with orders of magnitude increase in accuracy over conventional methods including the Linear Predictive Method and the Gabor-Volterra-Weiner Polynomial Method. Deterministic chaos is thought to be involved in many physical situations including the onset of turbulence in fluids, chemical reactions and plasma physics. Secondly, we demonstrate the use of the formalism in nonlinear system modelling by providing a graphic example in which it is clear that the neural network has accurately modelled the nonlinear transfer function. It is interesting to note that the formalism provides explicit, analytic, global, approximations to the nonlinear maps underlying the various time series. Furthermore, the neural net seems to be extremely parsimonious in its requirements for data points from the time series. We show that the neural net is able to perform well because it globally approximates the relevant maps by performing a kind of generalized mode decomposition of the maps. 24 refs., 13 figs.
Artificial neural networks in neurosurgery.
Azimi, Parisa; Mohammadi, Hasan Reza; Benzel, Edward C; Shahzadi, Sohrab; Azhari, Shirzad; Montazeri, Ali
2015-03-01
Artificial neural networks (ANNs) effectively analyze non-linear data sets. The aimed was A review of the relevant published articles that focused on the application of ANNs as a tool for assisting clinical decision-making in neurosurgery. A literature review of all full publications in English biomedical journals (1993-2013) was undertaken. The strategy included a combination of key words 'artificial neural networks', 'prognostic', 'brain', 'tumor tracking', 'head', 'tumor', 'spine', 'classification' and 'back pain' in the title and abstract of the manuscripts using the PubMed search engine. The major findings are summarized, with a focus on the application of ANNs for diagnostic and prognostic purposes. Finally, the future of ANNs in neurosurgery is explored. A total of 1093 citations were identified and screened. In all, 57 citations were found to be relevant. Of these, 50 articles were eligible for inclusion in this review. The synthesis of the data showed several applications of ANN in neurosurgery, including: (1) diagnosis and assessment of disease progression in low back pain, brain tumours and primary epilepsy; (2) enhancing clinically relevant information extraction from radiographic images, intracranial pressure processing, low back pain and real-time tumour tracking; (3) outcome prediction in epilepsy, brain metastases, lumbar spinal stenosis, lumbar disc herniation, childhood hydrocephalus, trauma mortality, and the occurrence of symptomatic cerebral vasospasm in patients with aneurysmal subarachnoid haemorrhage; (4) the use in the biomechanical assessments of spinal disease. ANNs can be effectively employed for diagnosis, prognosis and outcome prediction in neurosurgery. PMID:24987050
Computational acceleration using neural networks
NASA Astrophysics Data System (ADS)
Cadaret, Paul
2008-04-01
The author's recent participation in the Small Business Innovative Research (SBIR) program has resulted in the development of a patent pending technology that enables the construction of very large and fast artificial neural networks. Through the use of UNICON's CogniMax pattern recognition technology we believe that systems can be constructed that exploit the power of "exhaustive learning" for the benefit of certain types of complex and slow computational problems. This paper presents a theoretical study that describes one potentially beneficial application of exhaustive learning. It describes how a very large and fast Radial Basis Function (RBF) artificial Neural Network (NN) can be used to implement a useful computational system. Viewed another way, it presents an unusual method of transforming a complex, always-precise, and slow computational problem into a fuzzy pattern recognition problem where other methods are available to effectively improve computational performance. The method described recognizes that the need for computational precision in a problem domain sometimes varies throughout the domain's Feature Space (FS) and high precision may only be needed in limited areas. These observations can then be exploited to the benefit of overall computational performance. Addressing computational reliability, we describe how existing always-precise computational methods can be used to reliably train the NN to perform the computational interpolation function. The author recognizes that the method described is not applicable to every situation, but over the last 8 months we have been surprised at how often this method can be applied to enable interesting and effective solutions.
The Effect of Network Parameters on Pi-Sigma Neural Network for Temperature Forecasting
NASA Astrophysics Data System (ADS)
Husaini, Noor Aida; Ghazali, Rozaida; Nawi, Nazri Mohd; Ismail, Lokman Hakim
In this paper, we present the effect of network parameters to forecast temperature of a suburban area in Batu Pahat, Johor. The common ways of predicting the temperature using Neural Network has been applied for most meteorological parameters. However, researchers frequently neglected the network parameters which might affect the Neural Network's performance. Therefore, this study tends to explore the effect of network parameters by using Pi Sigma Neural Network (PSNN) with backpropagation algorithm. The network's performance is evaluated using the historical dataset of temperature in Batu Pahat for one step-ahead and benchmarked against Multilayer Perceptron (MLP) for comparison. We found out that, network parameters have significantly affected the performance of PSNN for temperature forecasting. Towards the end of this paper, we concluded the best forecasting model to predict the temperature based on the comparison of our study.
Drift chamber tracking with neural networks
Lindsey, C.S.; Denby, B.; Haggerty, H.
1992-10-01
We discuss drift chamber tracking with a commercial log VLSI neural network chip. Voltages proportional to the drift times in a 4-layer drift chamber were presented to the Intel ETANN chip. The network was trained to provide the intercept and slope of straight tracks traversing the chamber. The outputs were recorded and later compared off line to conventional track fits. Two types of network architectures were studied. Applications of neural network tracking to high energy physics detector triggers is discussed.
Extrapolation limitations of multilayer feedforward neural networks
NASA Technical Reports Server (NTRS)
Haley, Pamela J.; Soloway, Donald
1992-01-01
The limitations of backpropagation used as a function extrapolator were investigated. Four common functions were used to investigate the network's extrapolation capability. The purpose of the experiment was to determine whether neural networks are capable of extrapolation and, if so, to determine the range for which networks can extrapolate. The authors show that neural networks cannot extrapolate and offer an explanation to support this result.
Finite-sample based learning algorithms for feedforward networks
Rao, N.S.V.; Protopopescu, V.; Mann, R.C.; Oblow, E.M.; Iyengar, S.S.
1995-04-01
We discuss two classes of convergent algorithms for learning continuous functions (and also regression functions) that are represented by FeedForward Networks (FFN). The first class of algorithms, applicable to networks with unknown weights located only in the output layer, is obtained by utilizing the potential function methods of Aizerman et al. The second class, applicable to general feedforward networks, is obtained by utilizing the classical Robbins-Monro style stochastic approximation methods. Conditions relating the sample sizes to the error bounds are derived for both classes of algorithms using martingale-type inequalities. For concreteness, the discussion is presented in terms of neural networks, but the results are applicable to general feedforward networks, in particular to wavelet networks. The algorithms can also be directly applied to concept learning problems. A main distinguishing feature of the this work is that the sample sizes are based on explicit algorithms rather than information-based methods.
Coherence resonance in bursting neural networks
NASA Astrophysics Data System (ADS)
Kim, June Hoan; Lee, Ho Jun; Min, Cheol Hong; Lee, Kyoung J.
2015-10-01
Synchronized neural bursts are one of the most noticeable dynamic features of neural networks, being essential for various phenomena in neuroscience, yet their complex dynamics are not well understood. With extrinsic electrical and optical manipulations on cultured neural networks, we demonstrate that the regularity (or randomness) of burst sequences is in many cases determined by a (few) low-dimensional attractor(s) working under strong neural noise. Moreover, there is an optimal level of noise strength at which the regularity of the interburst interval sequence becomes maximal—a phenomenon of coherence resonance. The experimental observations are successfully reproduced through computer simulations on a well-established neural network model, suggesting that the same phenomena may occur in many in vivo as well as in vitro neural networks.
Distributed neural computations for embedded sensor networks
NASA Astrophysics Data System (ADS)
Peckens, Courtney A.; Lynch, Jerome P.; Pei, Jin-Song
2011-04-01
Wireless sensing technologies have recently emerged as an inexpensive and robust method of data collection in a variety of structural monitoring applications. In comparison with cabled monitoring systems, wireless systems offer low-cost and low-power communication between a network of sensing devices. Wireless sensing networks possess embedded data processing capabilities which allow for data processing directly at the sensor, thereby eliminating the need for the transmission of raw data. In this study, the Volterra/Weiner neural network (VWNN), a powerful modeling tool for nonlinear hysteretic behavior, is decentralized for embedment in a network of wireless sensors so as to take advantage of each sensor's processing capabilities. The VWNN was chosen for modeling nonlinear dynamic systems because its architecture is computationally efficient and allows computational tasks to be decomposed for parallel execution. In the algorithm, each sensor collects it own data and performs a series of calculations. It then shares its resulting calculations with every other sensor in the network, while the other sensors are simultaneously exchanging their information. Because resource conservation is important in embedded sensor design, the data is pruned wherever possible to eliminate excessive communication between sensors. Once a sensor has its required data, it continues its calculations and computes a prediction of the system acceleration. The VWNN is embedded in the computational core of the Narada wireless sensor node for on-line execution. Data generated by a steel framed structure excited by seismic ground motions is used for validation of the embedded VWNN model.
A Neural Network Model of Retrieval-Induced Forgetting
ERIC Educational Resources Information Center
Norman, Kenneth A.; Newman, Ehren L.; Detre, Greg
2007-01-01
Retrieval-induced forgetting (RIF) refers to the finding that retrieving a memory can impair subsequent recall of related memories. Here, the authors present a new model of how the brain gives rise to RIF in both semantic and episodic memory. The core of the model is a recently developed neural network learning algorithm that leverages regular…
From Classical Neural Networks to Quantum Neural Networks
NASA Astrophysics Data System (ADS)
Tirozzi, B.
2013-09-01
First I give a brief description of the classical Hopfield model introducing the fundamental concepts of patterns, retrieval, pattern recognition, neural dynamics, capacity and describe the fundamental results obtained in this field by Amit, Gutfreund and Sompolinsky,1 using the non rigorous method of replica and the rigorous version given by Pastur, Shcherbina, Tirozzi2 using the cavity method. Then I give a formulation of the theory of Quantum Neural Networks (QNN) in terms of the XY model with Hebbian interaction. The problem of retrieval and storage is discussed. The retrieval states are the states of the minimum energy. I apply the estimates found by Lieb3 which give lower and upper bound of the free-energy and expectation of the observables of the quantum model. I discuss also some experiment and the search of ground state using Monte Carlo Dynamics applied to the equivalent classical two dimensional Ising model constructed by Suzuki et al.6 At the end there is a list of open problems.
Adaptive Neurons For Artificial Neural Networks
NASA Technical Reports Server (NTRS)
Tawel, Raoul
1990-01-01
Training time decreases dramatically. In improved mathematical model of neural-network processor, temperature of neurons (in addition to connection strengths, also called weights, of synapses) varied during supervised-learning phase of operation according to mathematical formalism and not heuristic rule. Evidence that biological neural networks also process information at neuronal level.
Radiation Behavior of Analog Neural Network Chip
NASA Technical Reports Server (NTRS)
Langenbacher, H.; Zee, F.; Daud, T.; Thakoor, A.
1996-01-01
A neural network experiment conducted for the Space Technology Research Vehicle (STRV-1) 1-b launched in June 1994. Identical sets of analog feed-forward neural network chips was used to study and compare the effects of space and ground radiation on the chips. Three failure mechanisms are noted.
Creativity in design and artificial neural networks
Neocleous, C.C.; Esat, I.I.; Schizas, C.N.
1996-12-31
The creativity phase is identified as an integral part of the design phase. The characteristics of creative persons which are relevant to designing artificial neural networks manifesting aspects of creativity, are identified. Based on these identifications, a general framework of artificial neural network characteristics to implement such a goal are proposed.
Advanced telerobotic control using neural networks
NASA Technical Reports Server (NTRS)
Pap, Robert M.; Atkins, Mark; Cox, Chadwick; Glover, Charles; Kissel, Ralph; Saeks, Richard
1993-01-01
Accurate Automation is designing and developing adaptive decentralized joint controllers using neural networks. We are then implementing these in hardware for the Marshall Space Flight Center PFMA as well as to be usable for the Remote Manipulator System (RMS) robot arm. Our design is being realized in hardware after completion of the software simulation. This is implemented using a Functional-Link neural network.
Neural network based architectures for aerospace applications
NASA Technical Reports Server (NTRS)
Ricart, Richard
1987-01-01
A brief history of the field of neural networks research is given and some simple concepts are described. In addition, some neural network based avionics research and development programs are reviewed. The need for the United States Air Force and NASA to assume a leadership role in supporting this technology is stressed.
Applications of Neural Networks in Finance.
ERIC Educational Resources Information Center
Crockett, Henry; Morrison, Ronald
1994-01-01
Discusses research with neural networks in the area of finance. Highlights include bond pricing, theoretical exposition of primary bond pricing, bond pricing regression model, and an example that created networks with corporate bonds and NeuralWare Neuralworks Professional H software using the back-propagation technique. (LRW)
A Survey of Neural Network Publications.
ERIC Educational Resources Information Center
Vijayaraman, Bindiganavale S.; Osyk, Barbara
This paper is a survey of publications on artificial neural networks published in business journals for the period ending July 1996. Its purpose is to identify and analyze trends in neural network research during that period. This paper shows which topics have been heavily researched, when these topics were researched, and how that research has…
Cellular neural networks for welding arc thermograms segmentation
NASA Astrophysics Data System (ADS)
Jamrozik, Wojciech
2014-09-01
Machine vision systems are used in many areas for monitoring of technological processes. Among this processes welding takes important place, where often infrared cameras are used. Besides reliable hardware, successful application of vision systems requires suitable software based on proper algorithms. One of most important group of image processing algorithms is connected to image segmentation. Obtainment of exact boundary of an object that changes shape in time, such as the welding arc, represented on a thermogram is not a trivial task. In the paper a segmentation method using supervised approach based on a cellular neural networks is presented. Simulated annealing and genetic algorithm were used for training of the network (template optimization). Comparison of proposed method to a well elaborated segmentation method based on region growing approach was made. Obtained results prove that the cellular neural network can be a valuable tool for infrared welding pool images segmentation.
Diagnosis of hepatitis by use of neural network learning
NASA Astrophysics Data System (ADS)
Fan, Hong-Qing; Zhang, Qy-zi
1994-03-01
An attempt is made to find a new way for better diagnosis of hepatisis through application of artificial neural network theory. Learning from a given sample set, the neural network is used to establish a nonlinear mapping between various factors, such as symptoms, signs, and laboratorial experiments, and diagnosis of hepatisis. It is proved that the used network and values of weight after learning are available to the identification of equivalent class of a new pattern of hepatisis. In this paper, the knowledge learning and learning algorithms used in diagnosis are mainly discussed, an optimal generalization algorithm based on the error decrease algorithm and used to train multilayer feedforward is presented; meanwhile, the application results and their effectiveness are introduced.
Counter-propagation neural network for image compression
NASA Astrophysics Data System (ADS)
Sygnowski, Wojciech; Macukow, Bohdan
1996-08-01
Recently, several image compression techniques based on neural network algorithms have been developed. In this paper, we propose a new method for image compression--the modified counter-propagation neural network algorithm, which is a combination of the self-organizing map of Kohonen and the outstar structure of Grossberg. This algorithm has been successfully used in many applications. The modification presented has also demonstrated an interesting performance in comparison with the standard techniques. It was found that at the learning stage we can use any image for a network training (without a significant influence on the net operation) and the compression ratio and quality depend on the size of the basic element (the number of pixels in the cluster) and the amount of error tolerated when processing.
Introduction to Concepts in Artificial Neural Networks
NASA Technical Reports Server (NTRS)
Niebur, Dagmar
1995-01-01
This introduction to artificial neural networks summarizes some basic concepts of computational neuroscience and the resulting models of artificial neurons. The terminology of biological and artificial neurons, biological and machine learning and neural processing is introduced. The concepts of supervised and unsupervised learning are explained with examples from the power system area. Finally, a taxonomy of different types of neurons and different classes of artificial neural networks is presented.
Relabeling exchange method (REM) for learning in neural networks
NASA Astrophysics Data System (ADS)
Wu, Wen; Mammone, Richard J.
1994-02-01
The supervised training of neural networks require the use of output labels which are usually arbitrarily assigned. In this paper it is shown that there is a significant difference in the rms error of learning when `optimal' label assignment schemes are used. We have investigated two efficient random search algorithms to solve the relabeling problem: the simulated annealing and the genetic algorithm. However, we found them to be computationally expensive. Therefore we shall introduce a new heuristic algorithm called the Relabeling Exchange Method (REM) which is computationally more attractive and produces optimal performance. REM has been used to organize the optimal structure for multi-layered perceptrons and neural tree networks. The method is a general one and can be implemented as a modification to standard training algorithms. The motivation of the new relabeling strategy is based on the present interpretation of dyslexia as an encoding problem.
Mammographic mass detection using wavelets as input to neural networks.
Kilic, Niyazi; Gorgel, Pelin; Ucan, Osman N; Sertbas, Ahmet
2010-12-01
The objective of this paper is to demonstrate the utility of artificial neural networks, in combination with wavelet transforms for the detection of mammogram masses as malign or benign. A total of 45 patients who had breast masses in their mammography were enrolled in the study. The neural network was trained on the wavelet based feature vectors extracted from the mammogram masses for both benign and malign data. Therefore, in this study, Multilayer ANN was trained with the Backpropagation, Conjugate Gradient and Levenberg-Marquardt algorithms and ten-fold cross validation procedure was used. A satisfying sensitivity percentage of 89.2% was achieved with Levenberg-Marquardt algorithm. Since, this algorithm combines the best features of the Gauss-Newton technique and the other steepest-descent algorithms and thus it reaches desired results very fast. PMID:20703600
Artificial neural network for location estimation in wireless communication systems.
Chen, Chien-Sheng
2012-01-01
In a wireless communication system, wireless location is the technique used to estimate the location of a mobile station (MS). To enhance the accuracy of MS location prediction, we propose a novel algorithm that utilizes time of arrival (TOA) measurements and the angle of arrival (AOA) information to locate MS when three base stations (BSs) are available. Artificial neural networks (ANN) are widely used techniques in various areas to overcome the problem of exclusive and nonlinear relationships. When the MS is heard by only three BSs, the proposed algorithm utilizes the intersections of three TOA circles (and the AOA line), based on various neural networks, to estimate the MS location in non-line-of-sight (NLOS) environments. Simulations were conducted to evaluate the performance of the algorithm for different NLOS error distributions. The numerical analysis and simulation results show that the proposed algorithms can obtain more precise location estimation under different NLOS environments. PMID:22736978
Mathematically Reduced Chemical Reaction Mechanism Using Neural Networks
Ziaul Huque
2007-08-31
This is the final technical report for the project titled 'Mathematically Reduced Chemical Reaction Mechanism Using Neural Networks'. The aim of the project was to develop an efficient chemistry model for combustion simulations. The reduced chemistry model was developed mathematically without the need of having extensive knowledge of the chemistry involved. To aid in the development of the model, Neural Networks (NN) was used via a new network topology known as Non-linear Principal Components Analysis (NPCA). A commonly used Multilayer Perceptron Neural Network (MLP-NN) was modified to implement NPCA-NN. The training rate of NPCA-NN was improved with the GEneralized Regression Neural Network (GRNN) based on kernel smoothing techniques. Kernel smoothing provides a simple way of finding structure in data set without the imposition of a parametric model. The trajectory data of the reaction mechanism was generated based on the optimization techniques of genetic algorithm (GA). The NPCA-NN algorithm was then used for the reduction of Dimethyl Ether (DME) mechanism. DME is a recently discovered fuel made from natural gas, (and other feedstock such as coal, biomass, and urban wastes) which can be used in compression ignition engines as a substitute for diesel. An in-house two-dimensional Computational Fluid Dynamics (CFD) code was developed based on Meshfree technique and time marching solution algorithm. The project also provided valuable research experience to two graduate students.
Reducing Wind Tunnel Data Requirements Using Neural Networks
NASA Technical Reports Server (NTRS)
Ross, James C.; Jorgenson, Charles C.; Norgaard, Magnus
1997-01-01
The use of neural networks to minimize the amount of data required to completely define the aerodynamic performance of a wind tunnel model is examined. The accuracy requirements for commercial wind tunnel test data are very severe and are difficult to reproduce using neural networks. For the current work, multiple input, single output networks were trained using a Levenberg-Marquardt algorithm for each of the aerodynamic coefficients. When applied to the aerodynamics of a 55% scale model of a U.S. Air Force/ NASA generic fighter configuration, this scheme provided accurate models of the lift, drag, and pitching-moment coefficients. Using only 50% of the data acquired during, the wind tunnel test, the trained neural network had a predictive accuracy equal to or better than the accuracy of the experimental measurements.
A neural network for the identification of measured helicopter noise
NASA Technical Reports Server (NTRS)
Cabell, R. H.; Fuller, C. R.; O'Brien, W. F.
1991-01-01
The results of a preliminary study of the components of a novel acoustic helicopter identification system are described. The identification system uses the relationship between the amplitudes of the first eight harmonics in the main rotor noise spectrum to distinguish between helicopter types. Two classification algorithms are tested; a statistically optimal Bayes classifier, and a neural network adaptive classifier. The performance of these classifiers is tested using measured noise of three helicopters. The statistical classifier can correctly identify the helicopter an average of 67 percent of the time, while the neural network is correct an average of 65 percent of the time. These results indicate the need for additional study of the envelope of harmonic amplitudes as a component of a helicopter identification system. Issues concerning the implementation of the neural network classifier, such as training time and structure of the network, are discussed.
Analog Delta-Back-Propagation Neural-Network Circuitry
NASA Technical Reports Server (NTRS)
Eberhart, Silvio
1990-01-01
Changes in synapse weights due to circuit drifts suppressed. Proposed fully parallel analog version of electronic neural-network processor based on delta-back-propagation algorithm. Processor able to "learn" when provided with suitable combinations of inputs and enforced outputs. Includes programmable resistive memory elements (corresponding to synapses), conductances (synapse weights) adjusted during learning. Buffer amplifiers, summing circuits, and sample-and-hold circuits arranged in layers of electronic neurons in accordance with delta-back-propagation algorithm.
Microarray data classified by artificial neural networks.
Linder, Roland; Richards, Tereza; Wagner, Mathias
2007-01-01
Systems biology has enjoyed explosive growth in both the number of people participating in this area of research and the number of publications on the topic. The field of systems biology encompasses the in silico analysis of high-throughput data as provided by DNA or protein microarrays. Along with the increasing availability of microarray data, attention is focused on methods of analyzing the expression rates. One important type of analysis is the classification task, for example, distinguishing different types of cell functions or tumors. Recently, interest has been awakened toward artificial neural networks (ANN), which have many appealing characteristics such as an exceptional degree of accuracy. Nonlinear relationships or independence from certain assumptions regarding the data distribution are also considered. The current work reviews advantages as well as disadvantages of neural networks in the context of microarray analysis. Comparisons are drawn to alternative methods. Selected solutions are discussed, and finally algorithms for the effective combination of multiple ANNs are presented. The development of approaches to use ANN-processed microarray data applicable to run cell and tissue simulations may be slated for future investigation. PMID:18220242
Prospecting droughts with stochastic artificial neural networks
NASA Astrophysics Data System (ADS)
Ochoa-Rivera, Juan Camilo
2008-04-01
SummaryA non-linear multivariate model based on an artificial neural network multilayer perceptron is presented, that includes a random component. The developed model is applied to generate monthly streamflows, which are used to obtain synthetic annual droughts. The calibration of the model was undertaken using monthly streamflow records of several geographical sites of a basin. The model calibration consisted of training the neural network with the error back-propagation learning algorithm, and adding a normally distributed random noise. The model was validated by comparing relevant statistics of synthetic streamflow series to those of historical records. Annual droughts were calculated from the generated streamflow series, and then the expected values of length, intensity and magnitude of the droughts were assessed. An exercise on identical basis was made applying a second order auto-regressive multivariate model, AR(2), to compare its results with those of the developed model. The proposed model outperforms the AR(2) model in reproducing the future drought scenarios.
Ordinal neural networks without iterative tuning.
Fernández-Navarro, Francisco; Riccardi, Annalisa; Carloni, Sante
2014-11-01
Ordinal regression (OR) is an important branch of supervised learning in between the multiclass classification and regression. In this paper, the traditional classification scheme of neural network is adapted to learn ordinal ranks. The model proposed imposes monotonicity constraints on the weights connecting the hidden layer with the output layer. To do so, the weights are transcribed using padding variables. This reformulation leads to the so-called inequality constrained least squares (ICLS) problem. Its numerical solution can be obtained by several iterative methods, for example, trust region or line search algorithms. In this proposal, the optimum is determined analytically according to the closed-form solution of the ICLS problem estimated from the Karush-Kuhn-Tucker conditions. Furthermore, following the guidelines of the extreme learning machine framework, the weights connecting the input and the hidden layers are randomly generated, so the final model estimates all its parameters without iterative tuning. The model proposed achieves competitive performance compared with the state-of-the-art neural networks methods for OR. PMID:25330430
Neural network for photoplethysmographic respiratory rate monitoring
NASA Astrophysics Data System (ADS)
Johansson, Anders
2001-10-01
The photoplethysmographic signal (PPG) includes respiratory components seen as frequency modulation of the heart rate (respiratory sinus arrhythmia, RSA), amplitude modulation of the cardiac pulse, and respiratory induced intensity variations (RIIV) in the PPG baseline. The aim of this study was to evaluate the accuracy of these components in determining respiratory rate, and to combine the components in a neural network for improved accuracy. The primary goal is to design a PPG ventilation monitoring system. PPG signals were recorded from 15 healthy subjects. From these signals, the systolic waveform, diastolic waveform, respiratory sinus arrhythmia, pulse amplitude and RIIV were extracted. By using simple algorithms, the rates of false positive and false negative detection of breaths were calculated for each of the five components in a separate analysis. Furthermore, a simple neural network (NN) was tried out in a combined pattern recognition approach. In the separate analysis, the error rates (sum of false positives and false negatives) ranged from 9.7% (pulse amplitude) to 14.5% (systolic waveform). The corresponding value of the NN analysis was 9.5-9.6%.
Wavelet neural network for detection of signals in communications
NASA Astrophysics Data System (ADS)
Gomez-Sanchez, Raquel; Andina, Diego
1998-03-01
Our objective is the design and simulation of an efficient system for detection of signals in communications in terms of speed and computational complexity. The proposed scheme takes advantage of two powerful frameworks in signal processing: wavelets and neural networks. The decision system will take a decision based on the computation of the a prior probabilities of the input signal. For the estimation of such probability density functions, a wavelet neural network has been chosen. The election has risen under the following considerations: (a) neural networks have been established as a general approximation tool for fitting nonlinear models from input/output data and (b) the increasing popularity of the wavelet decomposition as a powerful tool for approximation. The integration of the above factors leads to the wavelet neural network concept. This network preserves the universal approximation property of wavelet series, with the advantage of the speed and efficient computation of a neural network architecture. The topology and learning algorithm of the network will provide an efficient approximation to the required probability density functions.
Neural networks: A versatile tool from artificial intelligence
Yama, B.R.; Lineberry, G.T.
1996-12-31
Artificial Intelligence research has produced several tools for commercial application in recent years. Artificial Neural Networks (ANNs), Fuzzy Logic, and Expert Systems are some of the techniques that are widely used today in various fields of engineering and business. Among these techniques, ANNs are gaining popularity due to their learning and other brain-like capabilities. Within the mining industry, ANN technology is being utilized with large payoffs for real-time process control applications. In this paper, a brief introduction to ANNs and the associated terminology is given. The neural network development process is outlined, followed by the back-propagation learning algorithm. Next, the development of two multi-layer, feed-forward neural networks is described and the results axe presented. One network is developed for prediction of strength of intact rock specimens, and another network is developed for prediction of mineral concentrations. Preliminary results indicate a predictive error less than 10% using cross-validation on a limited data set. The performance of the neural network for prediction of mineral concentrations was compared with kriging. It was found that the neural network performed not only satisfactorily, but in some cases performed better than, the kriging model.
NASA Astrophysics Data System (ADS)
MacDonald, I. R.; Garcia-Pineda, O. G.; Morey, S. L.; Huffer, F.
2011-12-01
Effervescent hydrocarbons rise naturally from hydrocarbon seeps in the Gulf of Mexico and reach the ocean surface. This oil forms thin (~0.1 μm) layers that enhance specular reflectivity and have been widely used to quantify the abundance and distribution of natural seeps using synthetic aperture radar (SAR). An analogous process occurred at a vastly greater scale for oil and gas discharged from BP's Macondo well blowout. SAR data allow direct comparison of the areas of the ocean surface covered by oil from natural sources and the discharge. We used a texture classifying neural network algorithm to quantify the areas of naturally occurring oil-covered water in 176 SAR image collections from the Gulf of Mexico obtained between May 1997 and November 2007, prior to the blowout. Separately we also analyzed 36 SAR images collections obtained between 26 April and 30 July, 2010 while the discharged oil was visible in the Gulf of Mexico. For the naturally occurring oil, we removed pollution events and transient oceanographic effects by including only the reflectance anomalies that that recurred in the same locality over multiple images. We measured the area of oil layers in a grid of 10x10 km cells covering the entire Gulf of Mexico. Floating oil layers were observed in only a fraction of the total Gulf area amounting to 1.22x10^5 km^2. In a bootstrap sample of 2000 replications, the combined average area of these layers was 7.80x10^2 km^2 (sd 86.03). For a regional comparison, we divided the Gulf of Mexico into four quadrates along 90° W longitude, and 25° N latitude. The NE quadrate, where the BP discharge occurred, received on average 7.0% of the total natural seepage in the Gulf of Mexico (5.24 x10^2 km^2, sd 21.99); the NW quadrate received on average 68.0% of this total (5.30 x10^2 km^2, sd 69.67). The BP blowout occurred in the NE quadrate of the Gulf of Mexico; discharged oil that reached the surface drifted over a large area north of 25° N. Performing a
Enhancing neural-network performance via assortativity.
de Franciscis, Sebastiano; Johnson, Samuel; Torres, Joaquín J
2011-03-01
The performance of attractor neural networks has been shown to depend crucially on the heterogeneity of the underlying topology. We take this analysis a step further by examining the effect of degree-degree correlations--assortativity--on neural-network behavior. We make use of a method recently put forward for studying correlated networks and dynamics thereon, both analytically and computationally, which is independent of how the topology may have evolved. We show how the robustness to noise is greatly enhanced in assortative (positively correlated) neural networks, especially if it is the hub neurons that store the information. PMID:21517565
Enhancing neural-network performance via assortativity
Franciscis, Sebastiano de; Johnson, Samuel; Torres, Joaquin J.
2011-03-15
The performance of attractor neural networks has been shown to depend crucially on the heterogeneity of the underlying topology. We take this analysis a step further by examining the effect of degree-degree correlations - assortativity - on neural-network behavior. We make use of a method recently put forward for studying correlated networks and dynamics thereon, both analytically and computationally, which is independent of how the topology may have evolved. We show how the robustness to noise is greatly enhanced in assortative (positively correlated) neural networks, especially if it is the hub neurons that store the information.
Supervised learning in hierarchical neural networks for edge enhancement
NASA Astrophysics Data System (ADS)
Lu, Si W.; Szeto, Anthony
1992-09-01
Hierarchical artificial neural networks are designed to enhance edge measurement. The neural network comprises four subnets: the Edge Contour Detection subnet, the Maximum Detection subnet, the Gradient Adjustment subnet, and the Orientation Determination subnet. The interconnections between these subnets are fashioned in a hierarchical manner. In order for the neural network system to perform correctly and accurately, each of the neural subnets must be given suitable weights by learning. The learning is very difficult for the hierarchical neural networks because of the complicated hierarchical structure. In our learning algorithm the modularity is introduced for fast learning and good generalization, based on the analysis of the local concept and the distributed concept represented by the module. The amount of information which the nets need to learn is drastically reduced. Therefore, only a small number of training patterns are required to train the nets and still derive suitable weights for the nets to perform accurately and efficiently. The neural network is simulated on a MIPS M120-S machine running UNIX. For the test images degraded by random noise up to 20%, the true edges are detected and enhanced, the false edges are suppressed, the noise is eliminated, the weak edges are reinforced, and the missing edge elements are interpolated.
Neural networks using two-component Bose-Einstein condensates
Byrnes, Tim; Koyama, Shinsuke; Yan, Kai; Yamamoto, Yoshihisa
2013-01-01
The authors previously considered a method of solving optimization problems by using a system of interconnected network of two component Bose-Einstein condensates (Byrnes, Yan, Yamamoto New J. Phys. 13, 113025 (2011)). The use of bosonic particles gives a reduced time proportional to the number of bosons N for solving Ising model Hamiltonians by taking advantage of enhanced bosonic cooling rates. Here we consider the same system in terms of neural networks. We find that up to the accelerated cooling of the bosons the previously proposed system is equivalent to a stochastic continuous Hopfield network. This makes it clear that the BEC network is a physical realization of a simulated annealing algorithm, with an additional speedup due to bosonic enhancement. We discuss the BEC network in terms of neural network tasks such as learning and pattern recognition and find that the latter process may be accelerated by a factor of N. PMID:23989391
Sunspot prediction using neural networks
NASA Technical Reports Server (NTRS)
Villarreal, James; Baffes, Paul
1990-01-01
The earliest systematic observance of sunspot activity is known to have been discovered by the Chinese in 1382 during the Ming Dynasty (1368 to 1644) when spots on the sun were noticed by looking at the sun through thick, forest fire smoke. Not until after the 18th century did sunspot levels become more than a source of wonderment and curiosity. Since 1834 reliable sunspot data has been collected by the National Oceanic and Atmospheric Administration (NOAA) and the U.S. Naval Observatory. Recently, considerable effort has been placed upon the study of the effects of sunspots on the ecosystem and the space environment. The efforts of the Artificial Intelligence Section of the Mission Planning and Analysis Division of the Johnson Space Center involving the prediction of sunspot activity using neural network technologies are described.
Wavelet differential neural network observer.
Chairez, Isaac
2009-09-01
State estimation for uncertain systems affected by external noises is an important problem in control theory. This paper deals with a state observation problem when the dynamic model of a plant contains uncertainties or it is completely unknown. Differential neural network (NN) approach is applied in this uninformative situation but with activation functions described by wavelets. A new learning law, containing an adaptive adjustment rate, is suggested to imply the stability condition for the free parameters of the observer. Nominal weights are adjusted during the preliminary training process using the least mean square (LMS) method. Lyapunov theory is used to obtain the upper bounds for the weights dynamics as well as for the mean squared estimation error. Two numeric examples illustrate this approach: first, a nonlinear electric system, governed by the Chua's equation and second the Lorentz oscillator. Both systems are assumed to be affected by external perturbations and their parameters are unknown. PMID:19674951
Introduction to artificial neural networks.
Grossi, Enzo; Buscema, Massimo
2007-12-01
The coupling of computer science and theoretical bases such as nonlinear dynamics and chaos theory allows the creation of 'intelligent' agents, such as artificial neural networks (ANNs), able to adapt themselves dynamically to problems of high complexity. ANNs are able to reproduce the dynamic interaction of multiple factors simultaneously, allowing the study of complexity; they can also draw conclusions on individual basis and not as average trends. These tools can offer specific advantages with respect to classical statistical techniques. This article is designed to acquaint gastroenterologists with concepts and paradigms related to ANNs. The family of ANNs, when appropriately selected and used, permits the maximization of what can be derived from available data and from complex, dynamic, and multidimensional phenomena, which are often poorly predictable in the traditional 'cause and effect' philosophy. PMID:17998827
Design development of a neural network-based telemetry monitor
NASA Technical Reports Server (NTRS)
Lembeck, Michael F.
1992-01-01
This paper identifies the requirements and describes an architectural framework for an artificial neural network-based system that is capable of fulfilling monitoring and control requirements of future aerospace missions. Incorporated into this framework are a newly developed training algorithm and the concept of cooperative network architectures. The feasibility of such an approach is demonstrated for its ability to identify faults in low frequency waveforms.
Neural networks for damage identification
Paez, T.L.; Klenke, S.E.
1997-11-01
Efforts to optimize the design of mechanical systems for preestablished use environments and to extend the durations of use cycles establish a need for in-service health monitoring. Numerous studies have proposed measures of structural response for the identification of structural damage, but few have suggested systematic techniques to guide the decision as to whether or not damage has occurred based on real data. Such techniques are necessary because in field applications the environments in which systems operate and the measurements that characterize system behavior are random. This paper investigates the use of artificial neural networks (ANNs) to identify damage in mechanical systems. Two probabilistic neural networks (PNNs) are developed and used to judge whether or not damage has occurred in a specific mechanical system, based on experimental measurements. The first PNN is a classical type that casts Bayesian decision analysis into an ANN framework; it uses exemplars measured from the undamaged and damaged system to establish whether system response measurements of unknown origin come from the former class (undamaged) or the latter class (damaged). The second PNN establishes the character of the undamaged system in terms of a kernel density estimator of measures of system response; when presented with system response measures of unknown origin, it makes a probabilistic judgment whether or not the data come from the undamaged population. The physical system used to carry out the experiments is an aerospace system component, and the environment used to excite the system is a stationary random vibration. The results of damage identification experiments are presented along with conclusions rating the effectiveness of the approaches.
Tampa Electric Neural Network Sootblowing
Mark A. Rhode
2003-12-31
Boiler combustion dynamics change continuously due to several factors including coal quality, boiler loading, ambient conditions, changes in slag/soot deposits and the condition of plant equipment. NO{sub x} formation, Particulate Matter (PM) emissions, and boiler thermal performance are directly affected by the sootblowing practices on a unit. As part of its Power Plant Improvement Initiative program, the US DOE is providing cofunding (DE-FC26-02NT41425) and NETL is the managing agency for this project at Tampa Electric's Big Bend Station. This program serves to co-fund projects that have the potential to increase thermal efficiency and reduce emissions from coal-fired utility boilers. A review of the Big Bend units helped identify intelligent sootblowing as a suitable application to achieve the desired objectives. The existing sootblower control philosophy uses sequential schemes, whose frequency is either dictated by the control room operator or is timed based. The intent of this project is to implement a neural network based intelligent soot-blowing system, in conjunction with state-of-the-art controls and instrumentation, to optimize the operation of a utility boiler and systematically control boiler fouling. Utilizing unique, on-line, adaptive technology, operation of the sootblowers can be dynamically controlled based on real-time events and conditions within the boiler. This could be an extremely cost-effective technology, which has the ability to be readily and easily adapted to virtually any pulverized coal fired boiler. Through unique on-line adaptive technology, Neural Network-based systems optimize the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to simultaneously reduce NO{sub x} emissions and improve heat rate
Tampa Electric Neural Network Sootblowing
Mark A. Rhode
2004-09-30
Boiler combustion dynamics change continuously due to several factors including coal quality, boiler loading, ambient conditions, changes in slag/soot deposits and the condition of plant equipment. NOx formation, Particulate Matter (PM) emissions, and boiler thermal performance are directly affected by the sootblowing practices on a unit. As part of its Power Plant Improvement Initiative program, the US DOE is providing cofunding (DE-FC26-02NT41425) and NETL is the managing agency for this project at Tampa Electric's Big Bend Station. This program serves to co-fund projects that have the potential to increase thermal efficiency and reduce emissions from coal-fired utility boilers. A review of the Big Bend units helped identify intelligent sootblowing as a suitable application to achieve the desired objectives. The existing sootblower control philosophy uses sequential schemes, whose frequency is either dictated by the control room operator or is timed based. The intent of this project is to implement a neural network based intelligent sootblowing system, in conjunction with state-of-the-art controls and instrumentation, to optimize the operation of a utility boiler and systematically control boiler fouling. Utilizing unique, on-line, adaptive technology, operation of the sootblowers can be dynamically controlled based on real-time events and conditions within the boiler. This could be an extremely cost-effective technology, which has the ability to be readily and easily adapted to virtually any pulverized coal fired boiler. Through unique on-line adaptive technology, Neural Network-based systems optimize the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to simultaneously reduce NO{sub x} emissions and improve heat rate around
Tampa Electric Neural Network Sootblowing
Mark A. Rhode
2004-03-31
Boiler combustion dynamics change continuously due to several factors including coal quality, boiler loading, ambient conditions, changes in slag/soot deposits and the condition of plant equipment. NOx formation, Particulate Matter (PM) emissions, and boiler thermal performance are directly affected by the sootblowing practices on a unit. As part of its Power Plant Improvement Initiative program, the US DOE is providing co-funding (DE-FC26-02NT41425) and NETL is the managing agency for this project at Tampa Electric's Big Bend Station. This program serves to co-fund projects that have the potential to increase thermal efficiency and reduce emissions from coal-fired utility boilers. A review of the Big Bend units helped identify intelligent sootblowing as a suitable application to achieve the desired objectives. The existing sootblower control philosophy uses sequential schemes, whose frequency is either dictated by the control room operator or is timed based. The intent of this project is to implement a neural network based intelligent sootblowing system, in conjunction with state-of-the-art controls and instrumentation, to optimize the operation of a utility boiler and systematically control boiler fouling. Utilizing unique, on-line, adaptive technology, operation of the sootblowers can be dynamically controlled based on real-time events and conditions within the boiler. This could be an extremely cost-effective technology, which has the ability to be readily and easily adapted to virtually any pulverized coal fired boiler. Through unique on-line adaptive technology, Neural Network-based systems optimize the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to simultaneously reduce NO{sub x} emissions and improve heat rate around
Tampa Electric Neural Network Sootblowing
Mark A. Rhode
2002-09-30
Boiler combustion dynamics change continuously due to several factors including coal quality, boiler loading, ambient conditions, changes in slag/soot deposits and the condition of plant equipment. NO{sub x} formation, Particulate Matter (PM) emissions, and boiler thermal performance are directly affected by the sootblowing practices on a unit. As part of its Power Plant Improvement Initiative program, the US DOE is providing cofunding (DE-FC26-02NT41425) and NETL is the managing agency for this project at Tampa Electric's Big Bend Station. This program serves to co-fund projects that have the potential to increase thermal efficiency and reduce emissions from coal-fired utility boilers. A review of the Big Bend units helped identify intelligent sootblowing as a suitable application to achieve the desired objectives. The existing sootblower control philosophy uses sequential schemes, whose frequency is either dictated by the control room operator or is timed based. The intent of this project is to implement a neural network based intelligent soot-blowing system, in conjunction with state-of-the-art controls and instrumentation, to optimize the operation of a utility boiler and systematically control boiler fouling. Utilizing unique, online, adaptive technology, operation of the sootblowers can be dynamically controlled based on real-time events and conditions within the boiler. This could be an extremely cost-effective technology, which has the ability to be readily and easily adapted to virtually any pulverized coal fired boiler. Through unique on-line adaptive technology, Neural Network-based systems optimize the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to simultaneously reduce {sub x} emissions and improve heat rate
Automatic Analysis of Radio Meteor Events Using Neural Networks
NASA Astrophysics Data System (ADS)
Roman, Victor Ştefan; Buiu, Cătălin
2015-12-01
Meteor Scanning Algorithms (MESCAL) is a software application for automatic meteor detection from radio recordings, which uses self-organizing maps and feedforward multi-layered perceptrons. This paper aims to present the theoretical concepts behind this application and the main features of MESCAL, showcasing how radio recordings are handled, prepared for analysis, and used to train the aforementioned neural networks. The neural networks trained using MESCAL allow for valuable detection results, such as high correct detection rates and low false-positive rates, and at the same time offer new possibilities for improving the results.
Automatic Analysis of Radio Meteor Events Using Neural Networks
NASA Astrophysics Data System (ADS)
Roman, Victor Ştefan; Buiu, Cătălin
2015-07-01
Meteor Scanning Algorithms (MESCAL) is a software application for automatic meteor detection from radio recordings, which uses self-organizing maps and feedforward multi-layered perceptrons. This paper aims to present the theoretical concepts behind this application and the main features of MESCAL, showcasing how radio recordings are handled, prepared for analysis, and used to train the aforementioned neural networks. The neural networks trained using MESCAL allow for valuable detection results, such as high correct detection rates and low false-positive rates, and at the same time offer new possibilities for improving the results.
Neural network training as a dissipative process.
Gori, Marco; Maggini, Marco; Rossi, Alessandro
2016-09-01
This paper analyzes the practical issues and reports some results on a theory in which learning is modeled as a continuous temporal process driven by laws describing the interactions of intelligent agents with their own environment. The classic regularization framework is paired with the idea of temporal manifolds by introducing the principle of least cognitive action, which is inspired by the related principle of mechanics. The introduction of the counterparts of the kinetic and potential energy leads to an interpretation of learning as a dissipative process. As an example, we apply the theory to supervised learning in neural networks and show that the corresponding Euler-Lagrange differential equations can be connected to the classic gradient descent algorithm on the supervised pairs. We give preliminary experiments to confirm the soundness of the theory. PMID:27389569
Mesh deformation based on artificial neural networks
NASA Astrophysics Data System (ADS)
Stadler, Domen; Kosel, Franc; Čelič, Damjan; Lipej, Andrej
2011-09-01
In the article a new mesh deformation algorithm based on artificial neural networks is introduced. This method is a point-to-point method, meaning that it does not use connectivity information for calculation of the mesh deformation. Two already known point-to-point methods, based on interpolation techniques, are also presented. In contrast to the two known interpolation methods, the new method does not require a summation over all boundary nodes for one displacement calculation. The consequence of this fact is a shorter computational time of mesh deformation, which is proven by different deformation tests. The quality of the deformed meshes with all three deformation methods was also compared. Finally, the generated and the deformed three-dimensional meshes were used in the computational fluid dynamics numerical analysis of a Francis water turbine. A comparison of the analysis results was made to prove the applicability of the new method in every day computation.
Neural networks and orbit control in accelerators
Bozoki, E.; Friedman, A.
1994-07-01
An overview of the architecture, workings and training of Neural Networks is given. We stress the aspects which are important for the use of Neural Networks for orbit control in accelerators and storage rings, especially its ability to cope with the nonlinear behavior of the orbit response to `kicks` and the slow drift in the orbit response during long-term operation. Results obtained for the two NSLS storage rings with several network architectures and various training methods for each architecture are given.
Stochastic cellular automata model of neural networks.
Goltsev, A V; de Abreu, F V; Dorogovtsev, S N; Mendes, J F F
2010-06-01
We propose a stochastic dynamical model of noisy neural networks with complex architectures and discuss activation of neural networks by a stimulus, pacemakers, and spontaneous activity. This model has a complex phase diagram with self-organized active neural states, hybrid phase transitions, and a rich array of behaviors. We show that if spontaneous activity (noise) reaches a threshold level then global neural oscillations emerge. Stochastic resonance is a precursor of this dynamical phase transition. These oscillations are an intrinsic property of even small groups of 50 neurons. PMID:20866454
F77NNS - A FORTRAN-77 NEURAL NETWORK SIMULATOR
NASA Technical Reports Server (NTRS)
Mitchell, P. H.
1994-01-01
F77NNS (A FORTRAN-77 Neural Network Simulator) simulates the popular back error propagation neural network. F77NNS is an ANSI-77 FORTRAN program designed to take advantage of vectorization when run on machines having this capability, but it will run on any computer with an ANSI-77 FORTRAN Compiler. Artificial neural networks are formed from hundreds or thousands of simulated neurons, connected to each other in a manner similar to biological nerve cells. Problems which involve pattern matching or system modeling readily fit the class of problems which F77NNS is designed to solve. The program's formulation trains a neural network using Rumelhart's back-propagation algorithm. Typically the nodes of a network are grouped together into clumps called layers. A network will generally have an input layer through which the various environmental stimuli are presented to the network, and an output layer for determining the network's response. The number of nodes in these two layers is usually tied to features of the problem being solved. Other layers, which form intermediate stops between the input and output layers, are called hidden layers. The back-propagation training algorithm can require massive computational resources to implement a large network such as a network capable of learning text-to-phoneme pronunciation rules as in the famous Sehnowski experiment. The Sehnowski neural network learns to pronounce 1000 common English words. The standard input data defines the specific inputs that control the type of run to be made, and input files define the NN in terms of the layers and nodes, as well as the input/output (I/O) pairs. The program has a restart capability so that a neural network can be solved in stages suitable to the user's resources and desires. F77NNS allows the user to customize the patterns of connections between layers of a network. The size of the neural network to be solved is limited only by the amount of random access memory (RAM) available to the
Learning algorithms for feedforward networks based on finite samples
Rao, N.S.V.; Protopopescu, V.; Mann, R.C.; Oblow, E.M.; Iyengar, S.S.
1994-09-01
Two classes of convergent algorithms for learning continuous functions (and also regression functions) that are represented by feedforward networks, are discussed. The first class of algorithms, applicable to networks with unknown weights located only in the output layer, is obtained by utilizing the potential function methods of Aizerman et al. The second class, applicable to general feedforward networks, is obtained by utilizing the classical Robbins-Monro style stochastic approximation methods. Conditions relating the sample sizes to the error bounds are derived for both classes of algorithms using martingale-type inequalities. For concreteness, the discussion is presented in terms of neural networks, but the results are applicable to general feedforward networks, in particular to wavelet networks. The algorithms can be directly adapted to concept learning problems.
An artificial neural network for wavelet steganalysis
NASA Astrophysics Data System (ADS)
Davidson, Jennifer; Bergman, Clifford; Bartlett, Eric
2005-08-01
Hiding messages in image data, called steganography, is used for both legal and illicit purposes. The detection of hidden messages in image data stored on websites and computers, called steganalysis, is of prime importance to cyber forensics personnel. Automating the detection of hidden messages is a requirement, since the shear amount of image data stored on computers or websites makes it impossible for a person to investigate each image separately. This paper describes research on a prototype software system that automatically classifies an image as having hidden information or not, using a sophisticated artificial neural network (ANN) system. An ANN software package, the ISU ACL NetWorks Toolkit, is trained on a selection of image features that distinguish between stego and nonstego images. The novelty of this ANN is that it is a blind classifier that gives more accurate results than previous systems. It can detect messages hidden using a variety of different types of embedding algorithms. A Graphical User Interface (GUI) combines the ANN, feature selection, and embedding algorithms into a prototype software package that is not currently available to the cyber forensics community.
NASA Astrophysics Data System (ADS)
Han, Hyung-Suk
2012-12-01
The indoor noise of a ship is usually determined using the A-weighted sound pressure level. However, in order to better understand this phenomenon, evaluation parameters that more accurately reflect the human sense of hearing are required. To find the level of the satisfaction index of the noise inside a naval vessel such as "Loudness" and "Annoyance", psycho-acoustic evaluation of various sound recordings from the naval vessel was performed in a laboratory. The objective of this paper is to develop a single index of "Loudness" and "Annoyance" for noise inside a naval vessel according to a psycho-acoustic evaluation by using psychological responses such as Noise Rating (NR), Noise Criterion (NC), Room Criterion (RC), Preferred Speech Interference Level (PSIL) and loudness level. Additionally, in order to determine a single index of satisfaction for noise such as "Loudness" and "Annoyance", with respect to a human's sense of hearing, a back-propagation neural network is applied.
Neural network regulation driven by autonomous neural firings
NASA Astrophysics Data System (ADS)
Cho, Myoung Won
2016-07-01
Biological neurons naturally fire spontaneously due to the existence of a noisy current. Such autonomous firings may provide a driving force for network formation because synaptic connections can be modified due to neural firings. Here, we study the effect of autonomous firings on network formation. For the temporally asymmetric Hebbian learning, bidirectional connections lose their balance easily and become unidirectional ones. Defining the difference between reciprocal connections as new variables, we could express the learning dynamics as if Ising model spins interact with each other in magnetism. We present a theoretical method to estimate the interaction between the new variables in a neural system. We apply the method to some network systems and find some tendencies of autonomous neural network regulation.
Coronary Artery Diagnosis Aided by Neural Network
NASA Astrophysics Data System (ADS)
Stefko, Kamil
2007-01-01
Coronary artery disease is due to atheromatous narrowing and subsequent occlusion of the coronary vessel. Application of optimised feed forward multi-layer back propagation neural network (MLBP) for detection of narrowing in coronary artery vessels is presented in this paper. The research was performed using 580 data records from traditional ECG exercise test confirmed by coronary arteriography results. Each record of training database included description of the state of a patient providing input data for the neural network. Level and slope of ST segment of a 12 lead ECG signal recorded at rest and after effort (48 floating point values) was the main component of input data for neural network was. Coronary arteriography results (verified the existence or absence of more than 50% stenosis of the particular coronary vessels) were used as a correct neural network training output pattern. More than 96% of cases were correctly recognised by especially optimised and a thoroughly verified neural network. Leave one out method was used for neural network verification so 580 data records could be used for training as well as for verification of neural network.
Neural network definitions of highly predictable protein secondary structure classes
Lapedes, A. |; Steeg, E.; Farber, R.
1994-02-01
We use two co-evolving neural networks to determine new classes of protein secondary structure which are significantly more predictable from local amino sequence than the conventional secondary structure classification. Accurate prediction of the conventional secondary structure classes: alpha helix, beta strand, and coil, from primary sequence has long been an important problem in computational molecular biology. Neural networks have been a popular method to attempt to predict these conventional secondary structure classes. Accuracy has been disappointingly low. The algorithm presented here uses neural networks to similtaneously examine both sequence and structure data, and to evolve new classes of secondary structure that can be predicted from sequence with significantly higher accuracy than the conventional classes. These new classes have both similarities to, and differences with the conventional alpha helix, beta strand and coil.
Description of interatomic interactions with neural networks
NASA Astrophysics Data System (ADS)
Hajinazar, Samad; Shao, Junping; Kolmogorov, Aleksey N.
Neural networks are a promising alternative to traditional classical potentials for describing interatomic interactions. Recent research in the field has demonstrated how arbitrary atomic environments can be represented with sets of general functions which serve as an input for the machine learning tool. We have implemented a neural network formalism in the MAISE package and developed a protocol for automated generation of accurate models for multi-component systems. Our tests illustrate the performance of neural networks and known classical potentials for a range of chemical compositions and atomic configurations. Supported by NSF Grant DMR-1410514.
Multispectral-image fusion using neural networks
NASA Astrophysics Data System (ADS)
Kagel, Joseph H.; Platt, C. A.; Donaven, T. W.; Samstad, Eric A.
1990-08-01
A prototype system is being developed to demonstrate the use of neural network hardware to fuse multispectral imagery. This system consists of a neural network IC on a motherboard a circuit card assembly and a set of software routines hosted by a PC-class computer. Research in support of this consists of neural network simulations fusing 4 to 7 bands of Landsat imagery and fusing (separately) multiple bands of synthetic imagery. The simulations results and a description of the prototype system are presented. 1.
Multispectral image fusion using neural networks
NASA Technical Reports Server (NTRS)
Kagel, J. H.; Platt, C. A.; Donaven, T. W.; Samstad, E. A.
1990-01-01
A prototype system is being developed to demonstrate the use of neural network hardware to fuse multispectral imagery. This system consists of a neural network IC on a motherboard, a circuit card assembly, and a set of software routines hosted by a PC-class computer. Research in support of this consists of neural network simulations fusing 4 to 7 bands of Landsat imagery and fusing (separately) multiple bands of synthetic imagery. The simulations, results, and a description of the prototype system are presented.
Stock market index prediction using neural networks
NASA Astrophysics Data System (ADS)
Komo, Darmadi; Chang, Chein-I.; Ko, Hanseok
1994-03-01
A neural network approach to stock market index prediction is presented. Actual data of the Wall Street Journal's Dow Jones Industrial Index has been used for a benchmark in our experiments where Radial Basis Function based neural networks have been designed to model these indices over the period from January 1988 to Dec 1992. A notable success has been achieved with the proposed model producing over 90% prediction accuracies observed based on monthly Dow Jones Industrial Index predictions. The model has also captured both moderate and heavy index fluctuations. The experiments conducted in this study demonstrated that the Radial Basis Function neural network represents an excellent candidate to predict stock market index.
A neural network prototyping package within IRAF
NASA Technical Reports Server (NTRS)
Bazell, D.; Bankman, I.
1992-01-01
We outline our plans for incorporating a Neural Network Prototyping Package into the IRAF environment. The package we are developing will allow the user to choose between different types of networks and to specify the details of the particular architecture chosen. Neural networks consist of a highly interconnected set of simple processing units. The strengths of the connections between units are determined by weights which are adaptively set as the network 'learns'. In some cases, learning can be a separate phase of the user cycle of the network while in other cases the network learns continuously. Neural networks have been found to be very useful in pattern recognition and image processing applications. They can form very general 'decision boundaries' to differentiate between objects in pattern space and they can be used for associative recall of patterns based on partial cures and for adaptive filtering. We discuss the different architectures we plan to use and give examples of what they can do.