Improving Maritime Domain Awareness Using Neural Networks for Target of Interest Classification

DTIC Science & Technology

2015-03-01

spreading SCG scaled conjugate gradient xv THIS PAGE INTENTIONALLY LEFT BLANK xvi EXECUTIVE SUMMARY The research detailed in this thesis is a...algorithms were explored for training the neural networks: resilient backpropagation (RP) and scaled conjugate gradient backpropagation ( SCG ). The...results of the neural network training performance are presented using mean squared error convergence plots. In all implementations, the SCG learning

Analysis Resilient Algorithm on Artificial Neural Network Backpropagation

NASA Astrophysics Data System (ADS)

Saputra, Widodo; Tulus; Zarlis, Muhammad; Widia Sembiring, Rahmat; Hartama, Dedy

2017-12-01

Prediction required by decision makers to anticipate future planning. Artificial Neural Network (ANN) Backpropagation is one of method. This method however still has weakness, for long training time. This is a reason to improve a method to accelerate the training. One of Artificial Neural Network (ANN) Backpropagation method is a resilient method. Resilient method of changing weights and bias network with direct adaptation process of weighting based on local gradient information from every learning iteration. Predicting data result of Istanbul Stock Exchange training getting better. Mean Square Error (MSE) value is getting smaller and increasing accuracy.

WS-BP: An efficient wolf search based back-propagation algorithm

NASA Astrophysics Data System (ADS)

Nawi, Nazri Mohd; Rehman, M. Z.; Khan, Abdullah

2015-05-01

Wolf Search (WS) is a heuristic based optimization algorithm. Inspired by the preying and survival capabilities of the wolves, this algorithm is highly capable to search large spaces in the candidate solutions. This paper investigates the use of WS algorithm in combination with back-propagation neural network (BPNN) algorithm to overcome the local minima problem and to improve convergence in gradient descent. The performance of the proposed Wolf Search based Back-Propagation (WS-BP) algorithm is compared with Artificial Bee Colony Back-Propagation (ABC-BP), Bat Based Back-Propagation (Bat-BP), and conventional BPNN algorithms. Specifically, OR and XOR datasets are used for training the network. The simulation results show that the WS-BP algorithm effectively avoids the local minima and converge to global minima.

Neuromorphic learning of continuous-valued mappings from noise-corrupted data

NASA Technical Reports Server (NTRS)

Troudet, T.; Merrill, W.

1991-01-01

The effect of noise on the learning performance of the backpropagation algorithm is analyzed. A selective sampling of the training set is proposed to maximize the learning of control laws by backpropagation, when the data have been corrupted by noise. The training scheme is applied to the nonlinear control of a cart-pole system in the presence of noise. The neural computation provides the neurocontroller with good noise-filtering properties. In the presence of plant noise, the neurocontroller is found to be more stable than the teacher. A novel perspective on the application of neural network technology to control engineering is presented.

The power of neural nets

NASA Technical Reports Server (NTRS)

Ryan, J. P.; Shah, B. H.

1987-01-01

Implementation of the Hopfield net which is used in the image processing type of applications where only partial information about the image may be available is discussed. The image classification type of algorithm of Hopfield and other learning algorithms, such as the Boltzmann machine and the back-propagation training algorithm, have many vital applications in space.

Gradient descent learning algorithm overview: a general dynamical systems perspective.

PubMed

Baldi, P

1995-01-01

Gives a unified treatment of gradient descent learning algorithms for neural networks using a general framework of dynamical systems. This general approach organizes and simplifies all the known algorithms and results which have been originally derived for different problems (fixed point/trajectory learning), for different models (discrete/continuous), for different architectures (forward/recurrent), and using different techniques (backpropagation, variational calculus, adjoint methods, etc.). The general approach can also be applied to derive new algorithms. The author then briefly examines some of the complexity issues and limitations intrinsic to gradient descent learning. Throughout the paper, the author focuses on the problem of trajectory learning.

Somato-dendritic Synaptic Plasticity and Error-backpropagation in Active Dendrites

PubMed Central

Schiess, Mathieu; Urbanczik, Robert; Senn, Walter

2016-01-01

In the last decade dendrites of cortical neurons have been shown to nonlinearly combine synaptic inputs by evoking local dendritic spikes. It has been suggested that these nonlinearities raise the computational power of a single neuron, making it comparable to a 2-layer network of point neurons. But how these nonlinearities can be incorporated into the synaptic plasticity to optimally support learning remains unclear. We present a theoretically derived synaptic plasticity rule for supervised and reinforcement learning that depends on the timing of the presynaptic, the dendritic and the postsynaptic spikes. For supervised learning, the rule can be seen as a biological version of the classical error-backpropagation algorithm applied to the dendritic case. When modulated by a delayed reward signal, the same plasticity is shown to maximize the expected reward in reinforcement learning for various coding scenarios. Our framework makes specific experimental predictions and highlights the unique advantage of active dendrites for implementing powerful synaptic plasticity rules that have access to downstream information via backpropagation of action potentials. PMID:26841235

A theory of local learning, the learning channel, and the optimality of backpropagation.

PubMed

Baldi, Pierre; Sadowski, Peter

2016-11-01

In a physical neural system, where storage and processing are intimately intertwined, the rules for adjusting the synaptic weights can only depend on variables that are available locally, such as the activity of the pre- and post-synaptic neurons, resulting in local learning rules. A systematic framework for studying the space of local learning rules is obtained by first specifying the nature of the local variables, and then the functional form that ties them together into each learning rule. Such a framework enables also the systematic discovery of new learning rules and exploration of relationships between learning rules and group symmetries. We study polynomial local learning rules stratified by their degree and analyze their behavior and capabilities in both linear and non-linear units and networks. Stacking local learning rules in deep feedforward networks leads to deep local learning. While deep local learning can learn interesting representations, it cannot learn complex input-output functions, even when targets are available for the top layer. Learning complex input-output functions requires local deep learning where target information is communicated to the deep layers through a backward learning channel. The nature of the communicated information about the targets and the structure of the learning channel partition the space of learning algorithms. For any learning algorithm, the capacity of the learning channel can be defined as the number of bits provided about the error gradient per weight, divided by the number of required operations per weight. We estimate the capacity associated with several learning algorithms and show that backpropagation outperforms them by simultaneously maximizing the information rate and minimizing the computational cost. This result is also shown to be true for recurrent networks, by unfolding them in time. The theory clarifies the concept of Hebbian learning, establishes the power and limitations of local learning rules, introduces the learning channel which enables a formal analysis of the optimality of backpropagation, and explains the sparsity of the space of learning rules discovered so far. Copyright © 2016 Elsevier Ltd. All rights reserved.

Learning in the Machine: Random Backpropagation and the Deep Learning Channel.

PubMed

Baldi, Pierre; Sadowski, Peter; Lu, Zhiqin

2018-07-01

Random backpropagation (RBP) is a variant of the backpropagation algorithm for training neural networks, where the transpose of the forward matrices are replaced by fixed random matrices in the calculation of the weight updates. It is remarkable both because of its effectiveness, in spite of using random matrices to communicate error information, and because it completely removes the taxing requirement of maintaining symmetric weights in a physical neural system. To better understand random backpropagation, we first connect it to the notions of local learning and learning channels. Through this connection, we derive several alternatives to RBP, including skipped RBP (SRPB), adaptive RBP (ARBP), sparse RBP, and their combinations (e.g. ASRBP) and analyze their computational complexity. We then study their behavior through simulations using the MNIST and CIFAR-10 bechnmark datasets. These simulations show that most of these variants work robustly, almost as well as backpropagation, and that multiplication by the derivatives of the activation functions is important. As a follow-up, we study also the low-end of the number of bits required to communicate error information over the learning channel. We then provide partial intuitive explanations for some of the remarkable properties of RBP and its variations. Finally, we prove several mathematical results, including the convergence to fixed points of linear chains of arbitrary length, the convergence to fixed points of linear autoencoders with decorrelated data, the long-term existence of solutions for linear systems with a single hidden layer and convergence in special cases, and the convergence to fixed points of non-linear chains, when the derivative of the activation functions is included.

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.

Embodiment of Learning in Electro-Optical Signal Processors

NASA Astrophysics Data System (ADS)

Hermans, Michiel; Antonik, Piotr; Haelterman, Marc; Massar, Serge

2016-09-01

Delay-coupled electro-optical systems have received much attention for their dynamical properties and their potential use in signal processing. In particular, it has recently been demonstrated, using the artificial intelligence algorithm known as reservoir computing, that photonic implementations of such systems solve complex tasks such as speech recognition. Here, we show how the backpropagation algorithm can be physically implemented on the same electro-optical delay-coupled architecture used for computation with only minor changes to the original design. We find that, compared to when the backpropagation algorithm is not used, the error rate of the resulting computing device, evaluated on three benchmark tasks, decreases considerably. This demonstrates that electro-optical analog computers can embody a large part of their own training process, allowing them to be applied to new, more difficult tasks.

Embodiment of Learning in Electro-Optical Signal Processors.

PubMed

Hermans, Michiel; Antonik, Piotr; Haelterman, Marc; Massar, Serge

2016-09-16

Delay-coupled electro-optical systems have received much attention for their dynamical properties and their potential use in signal processing. In particular, it has recently been demonstrated, using the artificial intelligence algorithm known as reservoir computing, that photonic implementations of such systems solve complex tasks such as speech recognition. Here, we show how the backpropagation algorithm can be physically implemented on the same electro-optical delay-coupled architecture used for computation with only minor changes to the original design. We find that, compared to when the backpropagation algorithm is not used, the error rate of the resulting computing device, evaluated on three benchmark tasks, decreases considerably. This demonstrates that electro-optical analog computers can embody a large part of their own training process, allowing them to be applied to new, more difficult tasks.

Equilibrium Propagation: Bridging the Gap between Energy-Based Models and Backpropagation

PubMed Central

Scellier, Benjamin; Bengio, Yoshua

2017-01-01

We introduce Equilibrium Propagation, a learning framework for energy-based models. It involves only one kind of neural computation, performed in both the first phase (when the prediction is made) and the second phase of training (after the target or prediction error is revealed). Although this algorithm computes the gradient of an objective function just like Backpropagation, it does not need a special computation or circuit for the second phase, where errors are implicitly propagated. Equilibrium Propagation shares similarities with Contrastive Hebbian Learning and Contrastive Divergence while solving the theoretical issues of both algorithms: our algorithm computes the gradient of a well-defined objective function. Because the objective function is defined in terms of local perturbations, the second phase of Equilibrium Propagation corresponds to only nudging the prediction (fixed point or stationary distribution) toward a configuration that reduces prediction error. In the case of a recurrent multi-layer supervised network, the output units are slightly nudged toward their target in the second phase, and the perturbation introduced at the output layer propagates backward in the hidden layers. We show that the signal “back-propagated” during this second phase corresponds to the propagation of error derivatives and encodes the gradient of the objective function, when the synaptic update corresponds to a standard form of spike-timing dependent plasticity. This work makes it more plausible that a mechanism similar to Backpropagation could be implemented by brains, since leaky integrator neural computation performs both inference and error back-propagation in our model. The only local difference between the two phases is whether synaptic changes are allowed or not. We also show experimentally that multi-layer recurrently connected networks with 1, 2, and 3 hidden layers can be trained by Equilibrium Propagation on the permutation-invariant MNIST task. PMID:28522969

A Q-backpropagated time delay neural network for diagnosing severity of gait disturbances in Parkinson's disease.

PubMed

Nancy Jane, Y; Khanna Nehemiah, H; Arputharaj, Kannan

2016-04-01

Parkinson's disease (PD) is a movement disorder that affects the patient's nervous system and health-care applications mostly uses wearable sensors to collect these data. Since these sensors generate time stamped data, analyzing gait disturbances in PD becomes challenging task. The objective of this paper is to develop an effective clinical decision-making system (CDMS) that aids the physician in diagnosing the severity of gait disturbances in PD affected patients. This paper presents a Q-backpropagated time delay neural network (Q-BTDNN) classifier that builds a temporal classification model, which performs the task of classification and prediction in CDMS. The proposed Q-learning induced backpropagation (Q-BP) training algorithm trains the Q-BTDNN by generating a reinforced error signal. The network's weights are adjusted through backpropagating the generated error signal. For experimentation, the proposed work uses a PD gait database, which contains gait measures collected through wearable sensors from three different PD research studies. The experimental result proves the efficiency of Q-BP in terms of its improved classification accuracy of 91.49%, 92.19% and 90.91% with three datasets accordingly compared to other neural network training algorithms. Copyright © 2016 Elsevier Inc. All rights reserved.

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.

Supervised learning of probability distributions by neural networks

NASA Technical Reports Server (NTRS)

Baum, Eric B.; Wilczek, Frank

1988-01-01

Supervised learning algorithms for feedforward neural networks are investigated analytically. The back-propagation algorithm described by Werbos (1974), Parker (1985), and Rumelhart et al. (1986) is generalized by redefining the values of the input and output neurons as probabilities. The synaptic weights are then varied to follow gradients in the logarithm of likelihood rather than in the error. This modification is shown to provide a more rigorous theoretical basis for the algorithm and to permit more accurate predictions. A typical application involving a medical-diagnosis expert system is discussed.

Multilayer perceptron, fuzzy sets, and classification

NASA Technical Reports Server (NTRS)

Pal, Sankar K.; Mitra, Sushmita

1992-01-01

A fuzzy neural network model based on the multilayer perceptron, using the back-propagation algorithm, and capable of fuzzy classification of patterns is described. The input vector consists of membership values to linguistic properties while the output vector is defined in terms of fuzzy class membership values. This allows efficient modeling of fuzzy or uncertain patterns with appropriate weights being assigned to the backpropagated errors depending upon the membership values at the corresponding outputs. During training, the learning rate is gradually decreased in discrete steps until the network converges to a minimum error solution. The effectiveness of the algorithm is demonstrated on a speech recognition problem. The results are compared with those of the conventional MLP, the Bayes classifier, and the other related models.

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

PubMed

Khellal, Atmane; Ma, Hongbin; Fei, Qing

2018-05-09

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

Classification of multispectral image data by the Binary Diamond neural network and by nonparametric, pixel-by-pixel methods

NASA Technical Reports Server (NTRS)

Salu, Yehuda; Tilton, James

1993-01-01

The classification of multispectral image data obtained from satellites has become an important tool for generating ground cover maps. This study deals with the application of nonparametric pixel-by-pixel classification methods in the classification of pixels, based on their multispectral data. A new neural network, the Binary Diamond, is introduced, and its performance is compared with a nearest neighbor algorithm and a back-propagation network. The Binary Diamond is a multilayer, feed-forward neural network, which learns from examples in unsupervised, 'one-shot' mode. It recruits its neurons according to the actual training set, as it learns. The comparisons of the algorithms were done by using a realistic data base, consisting of approximately 90,000 Landsat 4 Thematic Mapper pixels. The Binary Diamond and the nearest neighbor performances were close, with some advantages to the Binary Diamond. The performance of the back-propagation network lagged behind. An efficient nearest neighbor algorithm, the binned nearest neighbor, is described. Ways for improving the performances, such as merging categories, and analyzing nonboundary pixels, are addressed and evaluated.

Classification of underground pipe scanned images using feature extraction and neuro-fuzzy algorithm.

PubMed

Sinha, S K; Karray, F

2002-01-01

Pipeline surface defects such as holes and cracks cause major problems for utility managers, particularly when the pipeline is buried under the ground. Manual inspection for surface defects in the pipeline has a number of drawbacks, including subjectivity, varying standards, and high costs. Automatic inspection system using image processing and artificial intelligence techniques can overcome many of these disadvantages and offer utility managers an opportunity to significantly improve quality and reduce costs. A recognition and classification of pipe cracks using images analysis and neuro-fuzzy algorithm is proposed. In the preprocessing step the scanned images of pipe are analyzed and crack features are extracted. In the classification step the neuro-fuzzy algorithm is developed that employs a fuzzy membership function and error backpropagation algorithm. The idea behind the proposed approach is that the fuzzy membership function will absorb variation of feature values and the backpropagation network, with its learning ability, will show good classification efficiency.

A stable second order method for training back propagation networks

NASA Technical Reports Server (NTRS)

Nachtsheim, Philip R.

1993-01-01

A simple method for improving the learning rate of the back-propagation algorithm is described. The basis of the method is that approximate second order corrections can be incorporated in the output units. The extended method leads to significant improvements in the convergence rate.

Analysis of Artificial Neural Network Backpropagation Using Conjugate Gradient Fletcher Reeves In The Predicting Process

NASA Astrophysics Data System (ADS)

Wanto, Anjar; Zarlis, Muhammad; Sawaluddin; Hartama, Dedy

2017-12-01

Backpropagation is a good artificial neural network algorithm used to predict, one of which is to predict the rate of Consumer Price Index (CPI) based on the foodstuff sector. While conjugate gradient fletcher reeves is a suitable optimization method when juxtaposed with backpropagation method, because this method can shorten iteration without reducing the quality of training and testing result. Consumer Price Index (CPI) data that will be predicted to come from the Central Statistics Agency (BPS) Pematangsiantar. The results of this study will be expected to contribute to the government in making policies to improve economic growth. In this study, the data obtained will be processed by conducting training and testing with artificial neural network backpropagation by using parameter learning rate 0,01 and target error minimum that is 0.001-0,09. The training network is built with binary and bipolar sigmoid activation functions. After the results with backpropagation are obtained, it will then be optimized using the conjugate gradient fletcher reeves method by conducting the same training and testing based on 5 predefined network architectures. The result, the method used can increase the speed and accuracy result.

The quadriceps muscle of knee joint modelling Using Hybrid Particle Swarm Optimization-Neural Network (PSO-NN)

NASA Astrophysics Data System (ADS)

Kamaruddin, Saadi Bin Ahmad; Marponga Tolos, Siti; Hee, Pah Chin; Ghani, Nor Azura Md; Ramli, Norazan Mohamed; Nasir, Noorhamizah Binti Mohamed; Ksm Kader, Babul Salam Bin; Saiful Huq, Mohammad

2017-03-01

Neural framework has for quite a while been known for its ability to handle a complex nonlinear system without a logical model and can learn refined nonlinear associations gives. Theoretically, the most surely understood computation to set up the framework is the backpropagation (BP) count which relies on upon the minimization of the mean square error (MSE). However, this algorithm is not totally efficient in the presence of outliers which usually exist in dynamic data. This paper exhibits the modelling of quadriceps muscle model by utilizing counterfeit smart procedures named consolidated backpropagation neural network nonlinear autoregressive (BPNN-NAR) and backpropagation neural network nonlinear autoregressive moving average (BPNN-NARMA) models in view of utilitarian electrical incitement (FES). We adapted particle swarm optimization (PSO) approach to enhance the performance of backpropagation algorithm. In this research, a progression of tests utilizing FES was led. The information that is gotten is utilized to build up the quadriceps muscle model. 934 preparing information, 200 testing and 200 approval information set are utilized as a part of the improvement of muscle model. It was found that both BPNN-NAR and BPNN-NARMA performed well in modelling this type of data. As a conclusion, the neural network time series models performed reasonably efficient for non-linear modelling such as active properties of the quadriceps muscle with one input, namely output namely muscle force.

Noise-enhanced convolutional neural networks.

PubMed

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. Copyright © 2015 Elsevier Ltd. All rights reserved.

Two papers on feed-forward networks

NASA Technical Reports Server (NTRS)

Buntine, Wray L.; Weigend, Andreas S.

1991-01-01

Connectionist feed-forward networks, trained with back-propagation, can be used both for nonlinear regression and for (discrete one-of-C) classification, depending on the form of training. This report contains two papers on feed-forward networks. The papers can be read independently. They are intended for the theoretically-aware practitioner or algorithm-designer; however, they also contain a review and comparison of several learning theories so they provide a perspective for the theoretician. The first paper works through Bayesian methods to complement back-propagation in the training of feed-forward networks. The second paper addresses a problem raised by the first: how to efficiently calculate second derivatives on feed-forward networks.

Back-Propagation Operation for Analog Neural Network Hardware with Synapse Components Having Hysteresis Characteristics

PubMed Central

Ueda, Michihito; Nishitani, Yu; Kaneko, Yukihiro; Omote, Atsushi

2014-01-01

To realize an analog artificial neural network hardware, the circuit element for synapse function is important because the number of synapse elements is much larger than that of neuron elements. One of the candidates for this synapse element is a ferroelectric memristor. This device functions as a voltage controllable variable resistor, which can be applied to a synapse weight. However, its conductance shows hysteresis characteristics and dispersion to the input voltage. Therefore, the conductance values vary according to the history of the height and the width of the applied pulse voltage. Due to the difficulty of controlling the accurate conductance, it is not easy to apply the back-propagation learning algorithm to the neural network hardware having memristor synapses. To solve this problem, we proposed and simulated a learning operation procedure as follows. Employing a weight perturbation technique, we derived the error change. When the error reduced, the next pulse voltage was updated according to the back-propagation learning algorithm. If the error increased the amplitude of the next voltage pulse was set in such way as to cause similar memristor conductance but in the opposite voltage scanning direction. By this operation, we could eliminate the hysteresis and confirmed that the simulation of the learning operation converged. We also adopted conductance dispersion numerically in the simulation. We examined the probability that the error decreased to a designated value within a predetermined loop number. The ferroelectric has the characteristics that the magnitude of polarization does not become smaller when voltages having the same polarity are applied. These characteristics greatly improved the probability even if the learning rate was small, if the magnitude of the dispersion is adequate. Because the dispersion of analog circuit elements is inevitable, this learning operation procedure is useful for analog neural network hardware. PMID:25393715

Magnified gradient function with deterministic weight modification in adaptive learning.

PubMed

Ng, Sin-Chun; Cheung, Chi-Chung; Leung, Shu-Hung

2004-11-01

This paper presents two novel approaches, backpropagation (BP) with magnified gradient function (MGFPROP) and deterministic weight modification (DWM), to speed up the convergence rate and improve the global convergence capability of the standard BP learning algorithm. The purpose of MGFPROP is to increase the convergence rate by magnifying the gradient function of the activation function, while the main objective of DWM is to reduce the system error by changing the weights of a multilayered feedforward neural network in a deterministic way. Simulation results show that the performance of the above two approaches is better than BP and other modified BP algorithms for a number of learning problems. Moreover, the integration of the above two approaches forming a new algorithm called MDPROP, can further improve the performance of MGFPROP and DWM. From our simulation results, the MDPROP algorithm always outperforms BP and other modified BP algorithms in terms of convergence rate and global convergence capability.

Gross domestic product estimation based on electricity utilization by artificial neural network

NASA Astrophysics Data System (ADS)

Stevanović, Mirjana; Vujičić, Slađana; Gajić, Aleksandar M.

2018-01-01

The main goal of the paper was to estimate gross domestic product (GDP) based on electricity estimation by artificial neural network (ANN). The electricity utilization was analyzed based on different sources like renewable, coal and nuclear sources. The ANN network was trained with two training algorithms namely extreme learning method and back-propagation algorithm in order to produce the best prediction results of the GDP. According to the results it can be concluded that the ANN model with extreme learning method could produce the acceptable prediction of the GDP based on the electricity utilization.

Learning and optimization with cascaded VLSI neural network building-block chips

NASA Technical Reports Server (NTRS)

Duong, T.; Eberhardt, S. P.; Tran, M.; Daud, T.; Thakoor, A. P.

1992-01-01

To demonstrate the versatility of the building-block approach, two neural network applications were implemented on cascaded analog VLSI chips. Weights were implemented using 7-b multiplying digital-to-analog converter (MDAC) synapse circuits, with 31 x 32 and 32 x 32 synapses per chip. A novel learning algorithm compatible with analog VLSI was applied to the two-input parity problem. The algorithm combines dynamically evolving architecture with limited gradient-descent backpropagation for efficient and versatile supervised learning. To implement the learning algorithm in hardware, synapse circuits were paralleled for additional quantization levels. The hardware-in-the-loop learning system allocated 2-5 hidden neurons for parity problems. Also, a 7 x 7 assignment problem was mapped onto a cascaded 64-neuron fully connected feedback network. In 100 randomly selected problems, the network found optimal or good solutions in most cases, with settling times in the range of 7-100 microseconds.

Neural Network Classifier Architectures for Phoneme Recognition. CRC Technical Note No. CRC-TN-92-001.

ERIC Educational Resources Information Center

Treurniet, William

A study applied artificial neural networks, trained with the back-propagation learning algorithm, to modelling phonemes extracted from the DARPA TIMIT multi-speaker, continuous speech data base. A number of proposed network architectures were applied to the phoneme classification task, ranging from the simple feedforward multilayer network to more…

A Novel Handwritten Letter Recognizer Using Enhanced Evolutionary Neural Network

NASA Astrophysics Data System (ADS)

Mahmoudi, Fariborz; Mirzashaeri, Mohsen; Shahamatnia, Ehsan; Faridnia, Saed

This paper introduces a novel design for handwritten letter recognition by employing a hybrid back-propagation neural network with an enhanced evolutionary algorithm. Feeding the neural network consists of a new approach which is invariant to translation, rotation, and scaling of input letters. Evolutionary algorithm is used for the global search of the search space and the back-propagation algorithm is used for the local search. The results have been computed by implementing this approach for recognizing 26 English capital letters in the handwritings of different people. The computational results show that the neural network reaches very satisfying results with relatively scarce input data and a promising performance improvement in convergence of the hybrid evolutionary back-propagation algorithms is exhibited.

Minimal-scan filtered backpropagation algorithms for diffraction tomography.

PubMed

Pan, X; Anastasio, M A

1999-12-01

The filtered backpropagation (FBPP) algorithm, originally developed by Devaney [Ultrason. Imaging 4, 336 (1982)], has been widely used for reconstructing images in diffraction tomography. It is generally known that the FBPP algorithm requires scattered data from a full angular range of 2 pi for exact reconstruction of a generally complex-valued object function. However, we reveal that one needs scattered data only over the angular range 0 < or = phi < or = 3 pi/2 for exact reconstruction of a generally complex-valued object function. Using this insight, we develop and analyze a family of minimal-scan filtered backpropagation (MS-FBPP) algorithms, which, unlike the FBPP algorithm, use scattered data acquired from view angles over the range 0 < or = phi < or = 3 pi/2. We show analytically that these MS-FBPP algorithms are mathematically identical to the FBPP algorithm. We also perform computer simulation studies for validation, demonstration, and comparison of these MS-FBPP algorithms. The numerical results in these simulation studies corroborate our theoretical assertions.

Implementation of neural network for color properties of polycarbonates

NASA Astrophysics Data System (ADS)

Saeed, U.; Ahmad, S.; Alsadi, J.; Ross, D.; Rizvi, G.

2014-05-01

In present paper, the applicability of artificial neural networks (ANN) is investigated for color properties of plastics. The neural networks toolbox of Matlab 6.5 is used to develop and test the ANN model on a personal computer. An optimal design is completed for 10, 12, 14,16,18 & 20 hidden neurons on single hidden layer with five different algorithms: batch gradient descent (GD), batch variable learning rate (GDX), resilient back-propagation (RP), scaled conjugate gradient (SCG), levenberg-marquardt (LM) in the feed forward back-propagation neural network model. The training data for ANN is obtained from experimental measurements. There were twenty two inputs including resins, additives & pigments while three tristimulus color values L*, a* and b* were used as output layer. Statistical analysis in terms of Root-Mean-Squared (RMS), absolute fraction of variance (R squared), as well as mean square error is used to investigate the performance of ANN. LM algorithm with fourteen neurons on hidden layer in Feed Forward Back-Propagation of ANN model has shown best result in the present study. The degree of accuracy of the ANN model in reduction of errors is proven acceptable in all statistical analysis and shown in results. However, it was concluded that ANN provides a feasible method in error reduction in specific color tristimulus values.

Hardware-Efficient On-line Learning through Pipelined Truncated-Error Backpropagation in Binary-State Networks

PubMed Central

Mostafa, Hesham; Pedroni, Bruno; Sheik, Sadique; Cauwenberghs, Gert

2017-01-01

Artificial neural networks (ANNs) trained using backpropagation are powerful learning architectures that have achieved state-of-the-art performance in various benchmarks. Significant effort has been devoted to developing custom silicon devices to accelerate inference in ANNs. Accelerating the training phase, however, has attracted relatively little attention. In this paper, we describe a hardware-efficient on-line learning technique for feedforward multi-layer ANNs that is based on pipelined backpropagation. Learning is performed in parallel with inference in the forward pass, removing the need for an explicit backward pass and requiring no extra weight lookup. By using binary state variables in the feedforward network and ternary errors in truncated-error backpropagation, the need for any multiplications in the forward and backward passes is removed, and memory requirements for the pipelining are drastically reduced. Further reduction in addition operations owing to the sparsity in the forward neural and backpropagating error signal paths contributes to highly efficient hardware implementation. For proof-of-concept validation, we demonstrate on-line learning of MNIST handwritten digit classification on a Spartan 6 FPGA interfacing with an external 1Gb DDR2 DRAM, that shows small degradation in test error performance compared to an equivalently sized binary ANN trained off-line using standard back-propagation and exact errors. Our results highlight an attractive synergy between pipelined backpropagation and binary-state networks in substantially reducing computation and memory requirements, making pipelined on-line learning practical in deep networks. PMID:28932180

Hardware-Efficient On-line Learning through Pipelined Truncated-Error Backpropagation in Binary-State Networks.

PubMed

Mostafa, Hesham; Pedroni, Bruno; Sheik, Sadique; Cauwenberghs, Gert

2017-01-01

Artificial neural networks (ANNs) trained using backpropagation are powerful learning architectures that have achieved state-of-the-art performance in various benchmarks. Significant effort has been devoted to developing custom silicon devices to accelerate inference in ANNs. Accelerating the training phase, however, has attracted relatively little attention. In this paper, we describe a hardware-efficient on-line learning technique for feedforward multi-layer ANNs that is based on pipelined backpropagation. Learning is performed in parallel with inference in the forward pass, removing the need for an explicit backward pass and requiring no extra weight lookup. By using binary state variables in the feedforward network and ternary errors in truncated-error backpropagation, the need for any multiplications in the forward and backward passes is removed, and memory requirements for the pipelining are drastically reduced. Further reduction in addition operations owing to the sparsity in the forward neural and backpropagating error signal paths contributes to highly efficient hardware implementation. For proof-of-concept validation, we demonstrate on-line learning of MNIST handwritten digit classification on a Spartan 6 FPGA interfacing with an external 1Gb DDR2 DRAM, that shows small degradation in test error performance compared to an equivalently sized binary ANN trained off-line using standard back-propagation and exact errors. Our results highlight an attractive synergy between pipelined backpropagation and binary-state networks in substantially reducing computation and memory requirements, making pipelined on-line learning practical in deep networks.

Event-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines

PubMed Central

Neftci, Emre O.; Augustine, Charles; Paul, Somnath; Detorakis, Georgios

2017-01-01

An ongoing challenge in neuromorphic computing is to devise general and computationally efficient models of inference and learning which are compatible with the spatial and temporal constraints of the brain. One increasingly popular and successful approach is to take inspiration from inference and learning algorithms used in deep neural networks. However, the workhorse of deep learning, the gradient descent Gradient Back Propagation (BP) rule, often relies on the immediate availability of network-wide information stored with high-precision memory during learning, and precise operations that are difficult to realize in neuromorphic hardware. Remarkably, recent work showed that exact backpropagated gradients are not essential for learning deep representations. Building on these results, we demonstrate an event-driven random BP (eRBP) rule that uses an error-modulated synaptic plasticity for learning deep representations. Using a two-compartment Leaky Integrate & Fire (I&F) neuron, the rule requires only one addition and two comparisons for each synaptic weight, making it very suitable for implementation in digital or mixed-signal neuromorphic hardware. Our results show that using eRBP, deep representations are rapidly learned, achieving classification accuracies on permutation invariant datasets comparable to those obtained in artificial neural network simulations on GPUs, while being robust to neural and synaptic state quantizations during learning. PMID:28680387

Event-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines.

PubMed

Neftci, Emre O; Augustine, Charles; Paul, Somnath; Detorakis, Georgios

2017-01-01

An ongoing challenge in neuromorphic computing is to devise general and computationally efficient models of inference and learning which are compatible with the spatial and temporal constraints of the brain. One increasingly popular and successful approach is to take inspiration from inference and learning algorithms used in deep neural networks. However, the workhorse of deep learning, the gradient descent Gradient Back Propagation (BP) rule, often relies on the immediate availability of network-wide information stored with high-precision memory during learning, and precise operations that are difficult to realize in neuromorphic hardware. Remarkably, recent work showed that exact backpropagated gradients are not essential for learning deep representations. Building on these results, we demonstrate an event-driven random BP (eRBP) rule that uses an error-modulated synaptic plasticity for learning deep representations. Using a two-compartment Leaky Integrate & Fire (I&F) neuron, the rule requires only one addition and two comparisons for each synaptic weight, making it very suitable for implementation in digital or mixed-signal neuromorphic hardware. Our results show that using eRBP, deep representations are rapidly learned, achieving classification accuracies on permutation invariant datasets comparable to those obtained in artificial neural network simulations on GPUs, while being robust to neural and synaptic state quantizations during learning.

On adaptive learning rate that guarantees convergence in feedforward networks.

PubMed

Behera, Laxmidhar; Kumar, Swagat; Patnaik, Awhan

2006-09-01

This paper investigates new learning algorithms (LF I and LF II) based on Lyapunov function for the training of feedforward neural networks. It is observed that such algorithms have interesting parallel with the popular backpropagation (BP) algorithm where the fixed learning rate is replaced by an adaptive learning rate computed using convergence theorem based on Lyapunov stability theory. LF II, a modified version of LF I, has been introduced with an aim to avoid local minima. This modification also helps in improving the convergence speed in some cases. Conditions for achieving global minimum for these kind of algorithms have been studied in detail. The performances of the proposed algorithms are compared with BP algorithm and extended Kalman filtering (EKF) on three bench-mark function approximation problems: XOR, 3-bit parity, and 8-3 encoder. The comparisons are made in terms of number of learning iterations and computational time required for convergence. It is found that the proposed algorithms (LF I and II) are much faster in convergence than other two algorithms to attain same accuracy. Finally, the comparison is made on a complex two-dimensional (2-D) Gabor function and effect of adaptive learning rate for faster convergence is verified. In a nutshell, the investigations made in this paper help us better understand the learning procedure of feedforward neural networks in terms of adaptive learning rate, convergence speed, and local minima.

Multithreading with separate data to improve the performance of Backpropagation method

NASA Astrophysics Data System (ADS)

Dhamma, Mulia; Zarlis, Muhammad; Budhiarti Nababan, Erna

2017-12-01

Backpropagation is one method of artificial neural network that can make a prediction for a new data with learning by supervised of the past data. The learning process of backpropagation method will become slow if we give too much data for backpropagation method to learn the data. Multithreading with a separate data inside of each thread are being used in order to improve the performance of backpropagtion method . Base on the research for 39 data and also 5 times experiment with separate data into 2 thread, the result showed that the average epoch become 6490 when using 2 thread and 453049 epoch when using only 1 thread. The most lowest epoch for 2 thread is 1295 and 1 thread is 356116. The process of improvement is caused by the minimum error from 2 thread that has been compared to take the weight and bias value. This process will be repeat as long as the backpropagation do learning.

Development of an Efficient Identifier for Nuclear Power Plant Transients Based on Latest Advances of Error Back-Propagation Learning Algorithm

NASA Astrophysics Data System (ADS)

Moshkbar-Bakhshayesh, Khalil; Ghofrani, Mohammad B.

2014-02-01

This study aims to improve the performance of nuclear power plants (NPPs) transients training and identification using the latest advances of error back-propagation (EBP) learning algorithm. To this end, elements of EBP, including input data, initial weights, learning rate, cost function, activation function, and weights updating procedure are investigated and an efficient neural network is developed. Usefulness of modular networks is also examined and appropriate identifiers, one for each transient, are employed. Furthermore, the effect of transient type on transient identifier performance is illustrated. Subsequently, the developed transient identifier is applied to Bushehr nuclear power plant (BNPP). Seven types of the plant events are probed to analyze the ability of the proposed identifier. The results reveal that identification occurs very early with only five plant variables, whilst in the previous studies a larger number of variables (typically 15 to 20) were required. Modular networks facilitated identification due to its sole dependency on the sign of each network output signal. Fast training of input patterns, extendibility for identification of more transients and reduction of false identification are other advantageous of the proposed identifier. Finally, the balance between the correct answer to the trained transients (memorization) and reasonable response to the test transients (generalization) is improved, meeting one of the primary design criteria of identifiers.

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.

Recursive least-squares learning algorithms for neural networks

NASA Astrophysics Data System (ADS)

Lewis, Paul S.; Hwang, Jenq N.

1990-11-01

This paper presents the development of a pair of recursive least squares (ItLS) 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 0(N2) where N is the number of network parameters. This is due to the estimation of the N x N inverse Hessian matrix. Less computationally intensive approximations of the ilLS 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 (6 1 BACKGROUND Artificial neural networks (ANNs) offer an interesting and potentially useful paradigm for signal processing and pattern recognition. The majority of ANN applications employ the feed-forward multilayer perceptron (MLP) network architecture in which network parameters are " trained" by a supervised learning algorithm employing the generalized delta rule (GDIt) [1 2]. The GDR algorithm approximates a fixed step steepest descent algorithm using derivatives computed by error backpropagatiori. The GDII algorithm is sometimes referred to as the backpropagation algorithm. However in this paper we will use the term backpropagation to refer only to the process of computing error derivatives. While multilayer perceptrons provide a very powerful nonlinear modeling capability GDR training can be very slow and inefficient. In linear adaptive filtering the analog of the GDR algorithm is the leastmean- squares (LMS) algorithm. Steepest descent-based algorithms such as GDR or LMS are first order because they use only first derivative or gradient information about the training error to be minimized. To speed up the training process second order algorithms may be employed that take advantage of second derivative or Hessian matrix information. Second order information can be incorporated into MLP training in different ways. In many applications especially in the area of pattern recognition the training set is finite. In these cases block learning can be applied using standard nonlinear optimization techniques [3 4 5].

Understanding the Convolutional Neural Networks with Gradient Descent and Backpropagation

NASA Astrophysics Data System (ADS)

Zhou, XueFei

2018-04-01

With the development of computer technology, the applications of machine learning are more and more extensive. And machine learning is providing endless opportunities to develop new applications. One of those applications is image recognition by using Convolutional Neural Networks (CNNs). CNN is one of the most common algorithms in image recognition. It is significant to understand its theory and structure for every scholar who is interested in this field. CNN is mainly used in computer identification, especially in voice, text recognition and other aspects of the application. It utilizes hierarchical structure with different layers to accelerate computing speed. In addition, the greatest features of CNNs are the weight sharing and dimension reduction. And all of these consolidate the high effectiveness and efficiency of CNNs with idea computing speed and error rate. With the help of other learning altruisms, CNNs could be used in several scenarios for machine learning, especially for deep learning. Based on the general introduction to the background and the core solution CNN, this paper is going to focus on summarizing how Gradient Descent and Backpropagation work, and how they contribute to the high performances of CNNs. Also, some practical applications will be discussed in the following parts. The last section exhibits the conclusion and some perspectives of future work.

Electronic Neural Networks

NASA Technical Reports Server (NTRS)

Thakoor, Anil

1990-01-01

Viewgraphs on electronic neural networks for space station are presented. Topics covered include: electronic neural networks; electronic implementations; VLSI/thin film hybrid hardware for neurocomputing; computations with analog parallel processing; features of neuroprocessors; applications of neuroprocessors; neural network hardware for terrain trafficability determination; a dedicated processor for path planning; neural network system interface; neural network for robotic control; error backpropagation algorithm for learning; resource allocation matrix; global optimization neuroprocessor; and electrically programmable read only thin-film synaptic array.

Deep learning

NASA Astrophysics Data System (ADS)

Lecun, Yann; Bengio, Yoshua; Hinton, Geoffrey

2015-05-01

Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

Deep learning.

PubMed

LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey

2015-05-28

Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

PONS2train: tool for testing the MLP architecture and local traning methods for runoff forecast

NASA Astrophysics Data System (ADS)

Maca, P.; Pavlasek, J.; Pech, P.

2012-04-01

The purpose of presented poster is to introduce the PONS2train developed for runoff prediction via multilayer perceptron - MLP. The software application enables the implementation of 12 different MLP's transfer functions, comparison of 9 local training algorithms and finally the evaluation the MLP performance via 17 selected model evaluation metrics. The PONS2train software is written in C++ programing language. Its implementation consists of 4 classes. The NEURAL_NET and NEURON classes implement the MLP, the CRITERIA class estimates model evaluation metrics and for model performance evaluation via testing and validation datasets. The DATA_PATTERN class prepares the validation, testing and calibration datasets. The software application uses the LAPACK, BLAS and ARMADILLO C++ linear algebra libraries. The PONS2train implements the first order local optimization algorithms: standard on-line and batch back-propagation with learning rate combined with momentum and its variants with the regularization term, Rprop and standard batch back-propagation with variable momentum and learning rate. The second order local training algorithms represents: the Levenberg-Marquardt algorithm with and without regularization and four variants of scaled conjugate gradients. The other important PONS2train features are: the multi-run, the weight saturation control, early stopping of trainings, and the MLP weights analysis. The weights initialization is done via two different methods: random sampling from uniform distribution on open interval or Nguyen Widrow method. The data patterns can be transformed via linear and nonlinear transformation. The runoff forecast case study focuses on PONS2train implementation and shows the different aspects of the MLP training, the MLP architecture estimation, the neural network weights analysis and model uncertainty estimation.

Neuromorphic Learning From Noisy Data

NASA Technical Reports Server (NTRS)

Merrill, Walter C.; Troudet, Terry

1993-01-01

Two reports present numerical study of performance of feedforward neural network trained by back-propagation algorithm in learning continuous-valued mappings from data corrupted by noise. Two types of noise considered: plant noise which affects dynamics of controlled process and data-processing noise, which occurs during analog processing and digital sampling of signals. Study performed with view toward use of neural networks as neurocontrollers to substitute for, or enhance, performances of human experts in controlling mechanical devices in presence of sensor and actuator noise and to enhance performances of more-conventional digital feedback electronic process controllers in noisy environments.

Spatial-Temporal Reasoning Applications of Computational Intelligence in the Game of Go and Computer Networks

DTIC Science & Technology

2012-01-01

dimensionality, Tesauro used a backpropagation- based , three-layer neural network and implemented the outcome from a self-play game as the reinforcement signal...a school of fish, flock of birds, and colony of ants. Our literature review reveals that no one has used PSO to train the neural network ...trained with a variant of PSO called cellular PSO (CPSO). CSRN is a supervised learning neural network (SLNN). The proposed algorithm for the

Learning in the machine: The symmetries of the deep learning channel.

PubMed

Baldi, Pierre; Sadowski, Peter; Lu, Zhiqin

2017-11-01

In a physical neural system, learning rules must be local both in space and time. In order for learning to occur, non-local information must be communicated to the deep synapses through a communication channel, the deep learning channel. We identify several possible architectures for this learning channel (Bidirectional, Conjoined, Twin, Distinct) and six symmetry challenges: (1) symmetry of architectures; (2) symmetry of weights; (3) symmetry of neurons; (4) symmetry of derivatives; (5) symmetry of processing; and (6) symmetry of learning rules. Random backpropagation (RBP) addresses the second and third symmetry, and some of its variations, such as skipped RBP (SRBP) address the first and the fourth symmetry. Here we address the last two desirable symmetries showing through simulations that they can be achieved and that the learning channel is particularly robust to symmetry variations. Specifically, random backpropagation and its variations can be performed with the same non-linear neurons used in the main input-output forward channel, and the connections in the learning channel can be adapted using the same algorithm used in the forward channel, removing the need for any specialized hardware in the learning channel. Finally, we provide mathematical results in simple cases showing that the learning equations in the forward and backward channels converge to fixed points, for almost any initial conditions. In symmetric architectures, if the weights in both channels are small at initialization, adaptation in both channels leads to weights that are essentially symmetric during and after learning. Biological connections are discussed. Copyright © 2017 Elsevier Ltd. All rights reserved.

Optimization of neural network architecture for classification of radar jamming FM signals

NASA Astrophysics Data System (ADS)

Soto, Alberto; Mendoza, Ariadna; Flores, Benjamin C.

2017-05-01

The purpose of this study is to investigate several artificial Neural Network (NN) architectures in order to design a cognitive radar system capable of optimally distinguishing linear Frequency-Modulated (FM) signals from bandlimited Additive White Gaussian Noise (AWGN). The goal is to create a theoretical framework to determine an optimal NN architecture to achieve a Probability of Detection (PD) of 95% or higher and a Probability of False Alarm (PFA) of 1.5% or lower at 5 dB Signal to Noise Ratio (SNR). Literature research reveals that the frequency-domain power spectral densities characterize a signal more efficiently than its time-domain counterparts. Therefore, the input data is preprocessed by calculating the magnitude square of the Discrete Fourier Transform of the digitally sampled bandlimited AWGN and linear FM signals to populate a matrix containing N number of samples and M number of spectra. This matrix is used as input for the NN, and the spectra are divided as follows: 70% for training, 15% for validation, and 15% for testing. The study begins by experimentally deducing the optimal number of hidden neurons (1-40 neurons), then the optimal number of hidden layers (1-5 layers), and lastly, the most efficient learning algorithm. The training algorithms examined are: Resilient Backpropagation, Scaled Conjugate Gradient, Conjugate Gradient with Powell/Beale Restarts, Polak-Ribiére Conjugate Gradient, and Variable Learning Rate Backpropagation. We determine that an architecture with ten hidden neurons (or higher), one hidden layer, and a Scaled Conjugate Gradient for training algorithm encapsulates an optimal architecture for our application.

Three learning phases for radial-basis-function networks.

PubMed

Schwenker, F; Kestler, H A; Palm, G

2001-05-01

In this paper, learning algorithms for radial basis function (RBF) networks are discussed. Whereas multilayer perceptrons (MLP) are typically trained with backpropagation algorithms, starting the training procedure with a random initialization of the MLP's parameters, an RBF network may be trained in many different ways. We categorize these RBF training methods into one-, two-, and three-phase learning schemes. Two-phase RBF learning is a very common learning scheme. The two layers of an RBF network are learnt separately; first the RBF layer is trained, including the adaptation of centers and scaling parameters, and then the weights of the output layer are adapted. RBF centers may be trained by clustering, vector quantization and classification tree algorithms, and the output layer by supervised learning (through gradient descent or pseudo inverse solution). Results from numerical experiments of RBF classifiers trained by two-phase learning are presented in three completely different pattern recognition applications: (a) the classification of 3D visual objects; (b) the recognition hand-written digits (2D objects); and (c) the categorization of high-resolution electrocardiograms given as a time series (ID objects) and as a set of features extracted from these time series. In these applications, it can be observed that the performance of RBF classifiers trained with two-phase learning can be improved through a third backpropagation-like training phase of the RBF network, adapting the whole set of parameters (RBF centers, scaling parameters, and output layer weights) simultaneously. This, we call three-phase learning in RBF networks. A practical advantage of two- and three-phase learning in RBF networks is the possibility to use unlabeled training data for the first training phase. Support vector (SV) learning in RBF networks is a different learning approach. SV learning can be considered, in this context of learning, as a special type of one-phase learning, where only the output layer weights of the RBF network are calculated, and the RBF centers are restricted to be a subset of the training data. Numerical experiments with several classifier schemes including k-nearest-neighbor, learning vector quantization and RBF classifiers trained through two-phase, three-phase and support vector learning are given. The performance of the RBF classifiers trained through SV learning and three-phase learning are superior to the results of two-phase learning, but SV learning often leads to complex network structures, since the number of support vectors is not a small fraction of the total number of data points.

Robust Bioinformatics Recognition with VLSI Biochip Microsystem

NASA Technical Reports Server (NTRS)

Lue, Jaw-Chyng L.; Fang, Wai-Chi

2006-01-01

A microsystem architecture for real-time, on-site, robust bioinformatic patterns recognition and analysis has been proposed. This system is compatible with on-chip DNA analysis means such as polymerase chain reaction (PCR)amplification. A corresponding novel artificial neural network (ANN) learning algorithm using new sigmoid-logarithmic transfer function based on error backpropagation (EBP) algorithm is invented. Our results show the trained new ANN can recognize low fluorescence patterns better than the conventional sigmoidal ANN does. A differential logarithmic imaging chip is designed for calculating logarithm of relative intensities of fluorescence signals. The single-rail logarithmic circuit and a prototype ANN chip are designed, fabricated and characterized.

Clipping in neurocontrol by adaptive dynamic programming.

PubMed

Fairbank, Michael; Prokhorov, Danil; Alonso, Eduardo

2014-10-01

In adaptive dynamic programming, neurocontrol, and reinforcement learning, the objective is for an agent to learn to choose actions so as to minimize a total cost function. In this paper, we show that when discretized time is used to model the motion of the agent, it can be very important to do clipping on the motion of the agent in the final time step of the trajectory. By clipping, we mean that the final time step of the trajectory is to be truncated such that the agent stops exactly at the first terminal state reached, and no distance further. We demonstrate that when clipping is omitted, learning performance can fail to reach the optimum, and when clipping is done properly, learning performance can improve significantly. The clipping problem we describe affects algorithms that use explicit derivatives of the model functions of the environment to calculate a learning gradient. These include backpropagation through time for control and methods based on dual heuristic programming. However, the clipping problem does not significantly affect methods based on heuristic dynamic programming, temporal differences learning, or policy-gradient learning algorithms.

New model for prediction binary mixture of antihistamine decongestant using artificial neural networks and least squares support vector machine by spectrophotometry method

NASA Astrophysics Data System (ADS)

Mofavvaz, Shirin; Sohrabi, Mahmoud Reza; Nezamzadeh-Ejhieh, Alireza

2017-07-01

In the present study, artificial neural networks (ANNs) and least squares support vector machines (LS-SVM) as intelligent methods based on absorption spectra in the range of 230-300 nm have been used for determination of antihistamine decongestant contents. In the first step, one type of network (feed-forward back-propagation) from the artificial neural network with two different training algorithms, Levenberg-Marquardt (LM) and gradient descent with momentum and adaptive learning rate back-propagation (GDX) algorithm, were employed and their performance was evaluated. The performance of the LM algorithm was better than the GDX algorithm. In the second one, the radial basis network was utilized and results compared with the previous network. In the last one, the other intelligent method named least squares support vector machine was proposed to construct the antihistamine decongestant prediction model and the results were compared with two of the aforementioned networks. The values of the statistical parameters mean square error (MSE), Regression coefficient (R2), correlation coefficient (r) and also mean recovery (%), relative standard deviation (RSD) used for selecting the best model between these methods. Moreover, the proposed methods were compared to the high- performance liquid chromatography (HPLC) as a reference method. One way analysis of variance (ANOVA) test at the 95% confidence level applied to the comparison results of suggested and reference methods that there were no significant differences between them.

A comparative study of breast cancer diagnosis based on neural network ensemble via improved training algorithms.

PubMed

Azami, Hamed; Escudero, Javier

2015-08-01

Breast cancer is one of the most common types of cancer in women all over the world. Early diagnosis of this kind of cancer can significantly increase the chances of long-term survival. Since diagnosis of breast cancer is a complex problem, neural network (NN) approaches have been used as a promising solution. Considering the low speed of the back-propagation (BP) algorithm to train a feed-forward NN, we consider a number of improved NN trainings for the Wisconsin breast cancer dataset: BP with momentum, BP with adaptive learning rate, BP with adaptive learning rate and momentum, Polak-Ribikre conjugate gradient algorithm (CGA), Fletcher-Reeves CGA, Powell-Beale CGA, scaled CGA, resilient BP (RBP), one-step secant and quasi-Newton methods. An NN ensemble, which is a learning paradigm to combine a number of NN outputs, is used to improve the accuracy of the classification task. Results demonstrate that NN ensemble-based classification methods have better performance than NN-based algorithms. The highest overall average accuracy is 97.68% obtained by NN ensemble trained by RBP for 50%-50% training-test evaluation method.

Classifying spatially heterogeneous wetland communities using machine learning algorithms and spectral and textural features.

PubMed

Szantoi, Zoltan; Escobedo, Francisco J; Abd-Elrahman, Amr; Pearlstine, Leonard; Dewitt, Bon; Smith, Scot

2015-05-01

Mapping of wetlands (marsh vs. swamp vs. upland) is a common remote sensing application.Yet, discriminating between similar freshwater communities such as graminoid/sedge fromremotely sensed imagery is more difficult. Most of this activity has been performed using medium to low resolution imagery. There are only a few studies using highspatial resolutionimagery and machine learning image classification algorithms for mapping heterogeneouswetland plantcommunities. This study addresses this void by analyzing whether machine learning classifierssuch as decisiontrees (DT) and artificial neural networks (ANN) can accurately classify graminoid/sedgecommunities usinghigh resolution aerial imagery and image texture data in the Everglades National Park, Florida.In addition tospectral bands, the normalized difference vegetation index, and first- and second-order texturefeatures derivedfrom the near-infrared band were analyzed. Classifier accuracies were assessed using confusiontablesand the calculated kappa coefficients of the resulting maps. The results indicated that an ANN(multilayerperceptron based on backpropagation) algorithm produced a statistically significantly higheraccuracy(82.04%) than the DT (QUEST) algorithm (80.48%) or the maximum likelihood (80.56%)classifier (α<0.05). Findings show that using multiple window sizes provided the best results. First-ordertexture featuresalso provided computational advantages and results that were not significantly different fromthose usingsecond-order texture features.

Predicting coronary artery disease using different artificial neural network models.

PubMed

Colak, M Cengiz; Colak, Cemil; Kocatürk, Hasan; Sağiroğlu, Seref; Barutçu, Irfan

2008-08-01

Eight different learning algorithms used for creating artificial neural network (ANN) models and the different ANN models in the prediction of coronary artery disease (CAD) are introduced. This work was carried out as a retrospective case-control study. Overall, 124 consecutive patients who had been diagnosed with CAD by coronary angiography (at least 1 coronary stenosis > 50% in major epicardial arteries) were enrolled in the work. Angiographically, the 113 people (group 2) with normal coronary arteries were taken as control subjects. Multi-layered perceptrons ANN architecture were applied. The ANN models trained with different learning algorithms were performed in 237 records, divided into training (n=171) and testing (n=66) data sets. The performance of prediction was evaluated by sensitivity, specificity and accuracy values based on standard definitions. The results have demonstrated that ANN models trained with eight different learning algorithms are promising because of high (greater than 71%) sensitivity, specificity and accuracy values in the prediction of CAD. Accuracy, sensitivity and specificity values varied between 83.63%-100%, 86.46%-100% and 74.67%-100% for training, respectively. For testing, the values were more than 71% for sensitivity, 76% for specificity and 81% for accuracy. It may be proposed that the use of different learning algorithms other than backpropagation and larger sample sizes can improve the performance of prediction. The proposed ANN models trained with these learning algorithms could be used a promising approach for predicting CAD without the need for invasive diagnostic methods and could help in the prognostic clinical decision.

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.

Designing Artificial Neural Networks Using Particle Swarm Optimization Algorithms

PubMed Central

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

ODTbrain: a Python library for full-view, dense diffraction tomography.

PubMed

Müller, Paul; Schürmann, Mirjam; Guck, Jochen

2015-11-04

Analyzing the three-dimensional (3D) refractive index distribution of a single cell makes it possible to describe and characterize its inner structure in a marker-free manner. A dense, full-view tomographic data set is a set of images of a cell acquired for multiple rotational positions, densely distributed from 0 to 360 degrees. The reconstruction is commonly realized by projection tomography, which is based on the inversion of the Radon transform. The reconstruction quality of projection tomography is greatly improved when first order scattering, which becomes relevant when the imaging wavelength is comparable to the characteristic object size, is taken into account. This advanced reconstruction technique is called diffraction tomography. While many implementations of projection tomography are available today, there is no publicly available implementation of diffraction tomography so far. We present a Python library that implements the backpropagation algorithm for diffraction tomography in 3D. By establishing benchmarks based on finite-difference time-domain (FDTD) simulations, we showcase the superiority of the backpropagation algorithm over the backprojection algorithm. Furthermore, we discuss how measurment parameters influence the reconstructed refractive index distribution and we also give insights into the applicability of diffraction tomography to biological cells. The present software library contains a robust implementation of the backpropagation algorithm. The algorithm is ideally suited for the application to biological cells. Furthermore, the implementation is a drop-in replacement for the classical backprojection algorithm and is made available to the large user community of the Python programming language.

Machine learning modelling for predicting soil liquefaction susceptibility

NASA Astrophysics Data System (ADS)

Samui, P.; Sitharam, T. G.

2011-01-01

This study describes two machine learning techniques applied to predict liquefaction susceptibility of soil based on the standard penetration test (SPT) data from the 1999 Chi-Chi, Taiwan earthquake. The first machine learning technique which uses Artificial Neural Network (ANN) based on multi-layer perceptions (MLP) that are trained with Levenberg-Marquardt backpropagation algorithm. The second machine learning technique uses the Support Vector machine (SVM) that is firmly based on the theory of statistical learning theory, uses classification technique. ANN and SVM have been developed to predict liquefaction susceptibility using corrected SPT [(N1)60] and cyclic stress ratio (CSR). Further, an attempt has been made to simplify the models, requiring only the two parameters [(N1)60 and peck ground acceleration (amax/g)], for the prediction of liquefaction susceptibility. The developed ANN and SVM models have also been applied to different case histories available globally. The paper also highlights the capability of the SVM over the ANN models.

Relative optical navigation around small bodies via Extreme Learning Machine

NASA Astrophysics Data System (ADS)

Law, Andrew M.

To perform close proximity operations under a low-gravity environment, relative and absolute positions are vital information to the maneuver. Hence navigation is inseparably integrated in space travel. Extreme Learning Machine (ELM) is presented as an optical navigation method around small celestial bodies. Optical Navigation uses visual observation instruments such as a camera to acquire useful data and determine spacecraft position. The required input data for operation is merely a single image strip and a nadir image. ELM is a machine learning Single Layer feed-Forward Network (SLFN), a type of neural network (NN). The algorithm is developed on the predicate that input weights and biases can be randomly assigned and does not require back-propagation. The learned model is the output layer weights which are used to calculate a prediction. Together, Extreme Learning Machine Optical Navigation (ELM OpNav) utilizes optical images and ELM algorithm to train the machine to navigate around a target body. In this thesis the asteroid, Vesta, is the designated celestial body. The trained ELMs estimate the position of the spacecraft during operation with a single data set. The results show the approach is promising and potentially suitable for on-board navigation.

Deterministic convergence of chaos injection-based gradient method for training feedforward neural networks.

PubMed

Zhang, Huisheng; Zhang, Ying; Xu, Dongpo; Liu, Xiaodong

2015-06-01

It has been shown that, by adding a chaotic sequence to the weight update during the training of neural networks, the chaos injection-based gradient method (CIBGM) is superior to the standard backpropagation algorithm. This paper presents the theoretical convergence analysis of CIBGM for training feedforward neural networks. We consider both the case of batch learning as well as the case of online learning. Under mild conditions, we prove the weak convergence, i.e., the training error tends to a constant and the gradient of the error function tends to zero. Moreover, the strong convergence of CIBGM is also obtained with the help of an extra condition. The theoretical results are substantiated by a simulation example.

Method and system for training dynamic nonlinear adaptive filters which have embedded memory

NASA Technical Reports Server (NTRS)

Rabinowitz, Matthew (Inventor)

2002-01-01

Described herein is a method and system for training nonlinear adaptive filters (or neural networks) which have embedded memory. Such memory can arise in a multi-layer finite impulse response (FIR) architecture, or an infinite impulse response (IIR) architecture. We focus on filter architectures with separate linear dynamic components and static nonlinear components. Such filters can be structured so as to restrict their degrees of computational freedom based on a priori knowledge about the dynamic operation to be emulated. The method is detailed for an FIR architecture which consists of linear FIR filters together with nonlinear generalized single layer subnets. For the IIR case, we extend the methodology to a general nonlinear architecture which uses feedback. For these dynamic architectures, we describe how one can apply optimization techniques which make updates closer to the Newton direction than those of a steepest descent method, such as backpropagation. We detail a novel adaptive modified Gauss-Newton optimization technique, which uses an adaptive learning rate to determine both the magnitude and direction of update steps. For a wide range of adaptive filtering applications, the new training algorithm converges faster and to a smaller value of cost than both steepest-descent methods such as backpropagation-through-time, and standard quasi-Newton methods. We apply the algorithm to modeling the inverse of a nonlinear dynamic tracking system 5, as well as a nonlinear amplifier 6.

Performance Evaluation of Machine Learning Methods for Leaf Area Index Retrieval from Time-Series MODIS Reflectance Data

PubMed Central

Wang, Tongtong; Xiao, Zhiqiang; Liu, Zhigang

2017-01-01

Leaf area index (LAI) is an important biophysical parameter and the retrieval of LAI from remote sensing data is the only feasible method for generating LAI products at regional and global scales. However, most LAI retrieval methods use satellite observations at a specific time to retrieve LAI. Because of the impacts of clouds and aerosols, the LAI products generated by these methods are spatially incomplete and temporally discontinuous, and thus they cannot meet the needs of practical applications. To generate high-quality LAI products, four machine learning algorithms, including back-propagation neutral network (BPNN), radial basis function networks (RBFNs), general regression neutral networks (GRNNs), and multi-output support vector regression (MSVR) are proposed to retrieve LAI from time-series Moderate Resolution Imaging Spectroradiometer (MODIS) reflectance data in this study and performance of these machine learning algorithms is evaluated. The results demonstrated that GRNNs, RBFNs, and MSVR exhibited low sensitivity to training sample size, whereas BPNN had high sensitivity. The four algorithms performed slightly better with red, near infrared (NIR), and short wave infrared (SWIR) bands than red and NIR bands, and the results were significantly better than those obtained using single band reflectance data (red or NIR). Regardless of band composition, GRNNs performed better than the other three methods. Among the four algorithms, BPNN required the least training time, whereas MSVR needed the most for any sample size. PMID:28045443

Performance Evaluation of Machine Learning Methods for Leaf Area Index Retrieval from Time-Series MODIS Reflectance Data.

PubMed

Wang, Tongtong; Xiao, Zhiqiang; Liu, Zhigang

2017-01-01

Leaf area index (LAI) is an important biophysical parameter and the retrieval of LAI from remote sensing data is the only feasible method for generating LAI products at regional and global scales. However, most LAI retrieval methods use satellite observations at a specific time to retrieve LAI. Because of the impacts of clouds and aerosols, the LAI products generated by these methods are spatially incomplete and temporally discontinuous, and thus they cannot meet the needs of practical applications. To generate high-quality LAI products, four machine learning algorithms, including back-propagation neutral network (BPNN), radial basis function networks (RBFNs), general regression neutral networks (GRNNs), and multi-output support vector regression (MSVR) are proposed to retrieve LAI from time-series Moderate Resolution Imaging Spectroradiometer (MODIS) reflectance data in this study and performance of these machine learning algorithms is evaluated. The results demonstrated that GRNNs, RBFNs, and MSVR exhibited low sensitivity to training sample size, whereas BPNN had high sensitivity. The four algorithms performed slightly better with red, near infrared (NIR), and short wave infrared (SWIR) bands than red and NIR bands, and the results were significantly better than those obtained using single band reflectance data (red or NIR). Regardless of band composition, GRNNs performed better than the other three methods. Among the four algorithms, BPNN required the least training time, whereas MSVR needed the most for any sample size.

Online learning algorithm for time series forecasting suitable for low cost wireless sensor networks nodes.

PubMed

Pardo, Juan; Zamora-Martínez, Francisco; Botella-Rocamora, Paloma

2015-04-21

Time series forecasting is an important predictive methodology which can be applied to a wide range of problems. Particularly, forecasting the indoor temperature permits an improved utilization of the HVAC (Heating, Ventilating and Air Conditioning) systems in a home and thus a better energy efficiency. With such purpose the paper describes how to implement an Artificial Neural Network (ANN) algorithm in a low cost system-on-chip to develop an autonomous intelligent wireless sensor network. The present paper uses a Wireless Sensor Networks (WSN) to monitor and forecast the indoor temperature in a smart home, based on low resources and cost microcontroller technology as the 8051MCU. An on-line learning approach, based on Back-Propagation (BP) algorithm for ANNs, has been developed for real-time time series learning. It performs the model training with every new data that arrive to the system, without saving enormous quantities of data to create a historical database as usual, i.e., without previous knowledge. Consequently to validate the approach a simulation study through a Bayesian baseline model have been tested in order to compare with a database of a real application aiming to see the performance and accuracy. The core of the paper is a new algorithm, based on the BP one, which has been described in detail, and the challenge was how to implement a computational demanding algorithm in a simple architecture with very few hardware resources.

Online Learning Algorithm for Time Series Forecasting Suitable for Low Cost Wireless Sensor Networks Nodes

PubMed Central

Pardo, Juan; Zamora-Martínez, Francisco; Botella-Rocamora, Paloma

2015-01-01

Time series forecasting is an important predictive methodology which can be applied to a wide range of problems. Particularly, forecasting the indoor temperature permits an improved utilization of the HVAC (Heating, Ventilating and Air Conditioning) systems in a home and thus a better energy efficiency. With such purpose the paper describes how to implement an Artificial Neural Network (ANN) algorithm in a low cost system-on-chip to develop an autonomous intelligent wireless sensor network. The present paper uses a Wireless Sensor Networks (WSN) to monitor and forecast the indoor temperature in a smart home, based on low resources and cost microcontroller technology as the 8051MCU. An on-line learning approach, based on Back-Propagation (BP) algorithm for ANNs, has been developed for real-time time series learning. It performs the model training with every new data that arrive to the system, without saving enormous quantities of data to create a historical database as usual, i.e., without previous knowledge. Consequently to validate the approach a simulation study through a Bayesian baseline model have been tested in order to compare with a database of a real application aiming to see the performance and accuracy. The core of the paper is a new algorithm, based on the BP one, which has been described in detail, and the challenge was how to implement a computational demanding algorithm in a simple architecture with very few hardware resources. PMID:25905698

Advances in Artificial Neural Networks - Methodological Development and Application

USDA-ARS?s Scientific Manuscript database

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...

Estimation of biogas and methane yields in an UASB treating potato starch processing wastewater with backpropagation artificial neural network.

PubMed

Antwi, Philip; Li, Jianzheng; Boadi, Portia Opoku; Meng, Jia; Shi, En; Deng, Kaiwen; Bondinuba, Francis Kwesi

2017-03-01

Three-layered feedforward backpropagation (BP) artificial neural networks (ANN) and multiple nonlinear regression (MnLR) models were developed to estimate biogas and methane yield in an upflow anaerobic sludge blanket (UASB) reactor treating potato starch processing wastewater (PSPW). Anaerobic process parameters were optimized to identify their importance on methanation. pH, total chemical oxygen demand, ammonium, alkalinity, total Kjeldahl nitrogen, total phosphorus, volatile fatty acids and hydraulic retention time selected based on principal component analysis were used as input variables, whiles biogas and methane yield were employed as target variables. Quasi-Newton method and conjugate gradient backpropagation algorithms were best among eleven training algorithms. Coefficient of determination (R 2 ) of the BP-ANN reached 98.72% and 97.93% whiles MnLR model attained 93.9% and 91.08% for biogas and methane yield, respectively. Compared with the MnLR model, BP-ANN model demonstrated significant performance, suggesting possible control of the anaerobic digestion process with the BP-ANN model. Copyright © 2016 Elsevier Ltd. All rights reserved.

A novel single neuron perceptron with universal approximation and XOR computation properties.

PubMed

Lotfi, Ehsan; Akbarzadeh-T, M-R

2014-01-01

We propose a biologically motivated brain-inspired single neuron perceptron (SNP) with universal approximation and XOR computation properties. This computational model extends the input pattern and is based on the excitatory and inhibitory learning rules inspired from neural connections in the human brain's nervous system. The resulting architecture of SNP can be trained by supervised excitatory and inhibitory online learning rules. The main features of proposed single layer perceptron are universal approximation property and low computational complexity. The method is tested on 6 UCI (University of California, Irvine) pattern recognition and classification datasets. Various comparisons with multilayer perceptron (MLP) with gradient decent backpropagation (GDBP) learning algorithm indicate the superiority of the approach in terms of higher accuracy, lower time, and spatial complexity, as well as faster training. Hence, we believe the proposed approach can be generally applicable to various problems such as in pattern recognition and classification.

Effect of filtration of signals of brain activity on quality of recognition of brain activity patterns using artificial intelligence methods

NASA Astrophysics Data System (ADS)

Hramov, Alexander E.; Frolov, Nikita S.; Musatov, Vyachaslav Yu.

2018-02-01

In present work we studied features of the human brain states classification, corresponding to the real movements of hands and legs. For this purpose we used supervised learning algorithm based on feed-forward artificial neural networks (ANNs) with error back-propagation along with the support vector machine (SVM) method. We compared the quality of operator movements classification by means of EEG signals obtained experimentally in the absence of preliminary processing and after filtration in different ranges up to 25 Hz. It was shown that low-frequency filtering of multichannel EEG data significantly improved accuracy of operator movements classification.

Application of back-propagation artificial neural network (ANN) to predict crystallite size and band gap energy of ZnO quantum dots

NASA Astrophysics Data System (ADS)

Pelicano, Christian Mark; Rapadas, Nick; Cagatan, Gerard; Magdaluyo, Eduardo

2017-12-01

Herein, the crystallite size and band gap energy of zinc oxide (ZnO) quantum dots were predicted using artificial neural network (ANN). Three input factors including reagent ratio, growth time, and growth temperature were examined with respect to crystallite size and band gap energy as response factors. The generated results from neural network model were then compared with the experimental results. Experimental crystallite size and band gap energy of ZnO quantum dots were measured from TEM images and absorbance spectra, respectively. The Levenberg-Marquardt (LM) algorithm was used as the learning algorithm for the ANN model. The performance of the ANN model was then assessed through mean square error (MSE) and regression values. Based on the results, the ANN modelling results are in good agreement with the experimental data.

Discovering weighted patterns in intron sequences using self-adaptive harmony search and back-propagation algorithms.

PubMed

Huang, Yin-Fu; Wang, Chia-Ming; Liou, Sing-Wu

2013-01-01

A hybrid self-adaptive harmony search and back-propagation mining system was proposed to discover weighted patterns in human intron sequences. By testing the weights under a lazy nearest neighbor classifier, the numerical results revealed the significance of these weighted patterns. Comparing these weighted patterns with the popular intron consensus model, it is clear that the discovered weighted patterns make originally the ambiguous 5SS and 3SS header patterns more specific and concrete.

Discovering Weighted Patterns in Intron Sequences Using Self-Adaptive Harmony Search and Back-Propagation Algorithms

PubMed Central

Wang, Chia-Ming; Liou, Sing-Wu

2013-01-01

A hybrid self-adaptive harmony search and back-propagation mining system was proposed to discover weighted patterns in human intron sequences. By testing the weights under a lazy nearest neighbor classifier, the numerical results revealed the significance of these weighted patterns. Comparing these weighted patterns with the popular intron consensus model, it is clear that the discovered weighted patterns make originally the ambiguous 5SS and 3SS header patterns more specific and concrete. PMID:23737711

Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection.

PubMed

Kim, Jihun; Kim, Jonghong; Jang, Gil-Jin; Lee, Minho

2017-03-01

Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance. Copyright © 2016 Elsevier Ltd. All rights reserved.

Statistical efficiency of adaptive algorithms.

PubMed

Widrow, Bernard; Kamenetsky, Max

2003-01-01

The statistical efficiency of a learning algorithm applied to the adaptation of a given set of variable weights is defined as the ratio of the quality of the converged solution to the amount of data used in training the weights. Statistical efficiency is computed by averaging over an ensemble of learning experiences. A high quality solution is very close to optimal, while a low quality solution corresponds to noisy weights and less than optimal performance. In this work, two gradient descent adaptive algorithms are compared, the LMS algorithm and the LMS/Newton algorithm. LMS is simple and practical, and is used in many applications worldwide. LMS/Newton is based on Newton's method and the LMS algorithm. LMS/Newton is optimal in the least squares sense. It maximizes the quality of its adaptive solution while minimizing the use of training data. Many least squares adaptive algorithms have been devised over the years, but no other least squares algorithm can give better performance, on average, than LMS/Newton. LMS is easily implemented, but LMS/Newton, although of great mathematical interest, cannot be implemented in most practical applications. Because of its optimality, LMS/Newton serves as a benchmark for all least squares adaptive algorithms. The performances of LMS and LMS/Newton are compared, and it is found that under many circumstances, both algorithms provide equal performance. For example, when both algorithms are tested with statistically nonstationary input signals, their average performances are equal. When adapting with stationary input signals and with random initial conditions, their respective learning times are on average equal. However, under worst-case initial conditions, the learning time of LMS can be much greater than that of LMS/Newton, and this is the principal disadvantage of the LMS algorithm. But the strong points of LMS are ease of implementation and optimal performance under important practical conditions. For these reasons, the LMS algorithm has enjoyed very widespread application. It is used in almost every modem for channel equalization and echo cancelling. Furthermore, it is related to the famous backpropagation algorithm used for training neural networks.

Evaluation of multilayer perceptron algorithms for an analysis of network flow data

NASA Astrophysics Data System (ADS)

Bieniasz, Jedrzej; Rawski, Mariusz; Skowron, Krzysztof; Trzepiński, Mateusz

2016-09-01

The volume of exchanged information through IP networks is larger than ever and still growing. It creates a space for both benign and malicious activities. The second one raises awareness on security network devices, as well as network infrastructure and a system as a whole. One of the basic tools to prevent cyber attacks is Network Instrusion Detection System (NIDS). NIDS could be realized as a signature-based detector or an anomaly-based one. In the last few years the emphasis has been placed on the latter type, because of the possibility of applying smart and intelligent solutions. An ideal NIDS of next generation should be composed of self-learning algorithms that could react on known and unknown malicious network activities respectively. In this paper we evaluated a machine learning approach for detection of anomalies in IP network data represented as NetFlow records. We considered Multilayer Perceptron (MLP) as the classifier and we used two types of learning algorithms - Backpropagation (BP) and Particle Swarm Optimization (PSO). This paper includes a comprehensive survey on determining the most optimal MLP learning algorithm for the classification problem in application to network flow data. The performance, training time and convergence of BP and PSO methods were compared. The results show that PSO algorithm implemented by the authors outperformed other solutions if accuracy of classifications is considered. The major disadvantage of PSO is training time, which could be not acceptable for larger data sets or in real network applications. At the end we compared some key findings with the results from the other papers to show that in all cases results from this study outperformed them.

ATHENA: A knowledge-based hybrid backpropagation-grammatical evolution neural network algorithm for discovering epistasis among quantitative trait Loci

PubMed Central

2010-01-01

Background Growing interest and burgeoning technology for discovering genetic mechanisms that influence disease processes have ushered in a flood of genetic association studies over the last decade, yet little heritability in highly studied complex traits has been explained by genetic variation. Non-additive gene-gene interactions, which are not often explored, are thought to be one source of this "missing" heritability. Methods Stochastic methods employing evolutionary algorithms have demonstrated promise in being able to detect and model gene-gene and gene-environment interactions that influence human traits. Here we demonstrate modifications to a neural network algorithm in ATHENA (the Analysis Tool for Heritable and Environmental Network Associations) resulting in clear performance improvements for discovering gene-gene interactions that influence human traits. We employed an alternative tree-based crossover, backpropagation for locally fitting neural network weights, and incorporation of domain knowledge obtainable from publicly accessible biological databases for initializing the search for gene-gene interactions. We tested these modifications in silico using simulated datasets. Results We show that the alternative tree-based crossover modification resulted in a modest increase in the sensitivity of the ATHENA algorithm for discovering gene-gene interactions. The performance increase was highly statistically significant when backpropagation was used to locally fit NN weights. We also demonstrate that using domain knowledge to initialize the search for gene-gene interactions results in a large performance increase, especially when the search space is larger than the search coverage. Conclusions We show that a hybrid optimization procedure, alternative crossover strategies, and incorporation of domain knowledge from publicly available biological databases can result in marked increases in sensitivity and performance of the ATHENA algorithm for detecting and modelling gene-gene interactions that influence a complex human trait. PMID:20875103

Monthly evaporation forecasting using artificial neural networks and support vector machines

NASA Astrophysics Data System (ADS)

Tezel, Gulay; Buyukyildiz, Meral

2016-04-01

Evaporation is one of the most important components of the hydrological cycle, but is relatively difficult to estimate, due to its complexity, as it can be influenced by numerous factors. Estimation of evaporation is important for the design of reservoirs, especially in arid and semi-arid areas. Artificial neural network methods and support vector machines (SVM) are frequently utilized to estimate evaporation and other hydrological variables. In this study, usability of artificial neural networks (ANNs) (multilayer perceptron (MLP) and radial basis function network (RBFN)) and ɛ-support vector regression (SVR) artificial intelligence methods was investigated to estimate monthly pan evaporation. For this aim, temperature, relative humidity, wind speed, and precipitation data for the period 1972 to 2005 from Beysehir meteorology station were used as input variables while pan evaporation values were used as output. The Romanenko and Meyer method was also considered for the comparison. The results were compared with observed class A pan evaporation data. In MLP method, four different training algorithms, gradient descent with momentum and adaptive learning rule backpropagation (GDX), Levenberg-Marquardt (LVM), scaled conjugate gradient (SCG), and resilient backpropagation (RBP), were used. Also, ɛ-SVR model was used as SVR model. The models were designed via 10-fold cross-validation (CV); algorithm performance was assessed via mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R 2). According to the performance criteria, the ANN algorithms and ɛ-SVR had similar results. The ANNs and ɛ-SVR methods were found to perform better than the Romanenko and Meyer methods. Consequently, the best performance using the test data was obtained using SCG(4,2,2,1) with R 2 = 0.905.

Application of structured support vector machine backpropagation to a convolutional neural network for human pose estimation.

PubMed

Witoonchart, Peerajak; Chongstitvatana, Prabhas

2017-08-01

In this study, for the first time, we show how to formulate a structured support vector machine (SSVM) as two layers in a convolutional neural network, where the top layer is a loss augmented inference layer and the bottom layer is the normal convolutional layer. We show that a deformable part model can be learned with the proposed structured SVM neural network by backpropagating the error of the deformable part model to the convolutional neural network. The forward propagation calculates the loss augmented inference and the backpropagation calculates the gradient from the loss augmented inference layer to the convolutional layer. Thus, we obtain a new type of convolutional neural network called an Structured SVM convolutional neural network, which we applied to the human pose estimation problem. This new neural network can be used as the final layers in deep learning. Our method jointly learns the structural model parameters and the appearance model parameters. We implemented our method as a new layer in the existing Caffe library. Copyright © 2017 Elsevier Ltd. All rights reserved.

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.

The pandemonium system of reflective agents.

PubMed

Smieja, F

1996-01-01

The Pandemonium system of reflective MINOS agents solves problems by automatic dynamic modularization of the input space. The agents contain feedforward neural networks which adapt using the backpropagation algorithm. We demonstrate the performance of Pandemonium on various categories of problems. These include learning continuous functions with discontinuities, separating two spirals, learning the parity function, and optical character recognition. It is shown how strongly the advantages gained from using a modularization technique depend on the nature of the problem. The superiority of the Pandemonium method over a single net on the first two test categories is contrasted with its limited advantages for the second two categories. In the first case the system converges quicker with modularization and is seen to lead to simpler solutions. For the second case the problem is not significantly simplified through flat decomposition of the input space, although convergence is still quicker.

Smoothing strategies combined with ARIMA and neural networks to improve the forecasting of traffic accidents.

PubMed

Barba, Lida; Rodríguez, Nibaldo; Montt, Cecilia

2014-01-01

Two smoothing strategies combined with autoregressive integrated moving average (ARIMA) and autoregressive neural networks (ANNs) models to improve the forecasting of time series are presented. The strategy of forecasting is implemented using two stages. In the first stage the time series is smoothed using either, 3-point moving average smoothing, or singular value Decomposition of the Hankel matrix (HSVD). In the second stage, an ARIMA model and two ANNs for one-step-ahead time series forecasting are used. The coefficients of the first ANN are estimated through the particle swarm optimization (PSO) learning algorithm, while the coefficients of the second ANN are estimated with the resilient backpropagation (RPROP) learning algorithm. The proposed models are evaluated using a weekly time series of traffic accidents of Valparaíso, Chilean region, from 2003 to 2012. The best result is given by the combination HSVD-ARIMA, with a MAPE of 0:26%, followed by MA-ARIMA with a MAPE of 1:12%; the worst result is given by the MA-ANN based on PSO with a MAPE of 15:51%.

Study on Temperature and Synthetic Compensation of Piezo-Resistive Differential Pressure Sensors by Coupled Simulated Annealing and Simplex Optimized Kernel Extreme Learning Machine

PubMed Central

Li, Ji; Hu, Guoqing; Zhou, Yonghong; Zou, Chong; Peng, Wei; Alam SM, Jahangir

2017-01-01

As a high performance-cost ratio solution for differential pressure measurement, piezo-resistive differential pressure sensors are widely used in engineering processes. However, their performance is severely affected by the environmental temperature and the static pressure applied to them. In order to modify the non-linear measuring characteristics of the piezo-resistive differential pressure sensor, compensation actions should synthetically consider these two aspects. Advantages such as nonlinear approximation capability, highly desirable generalization ability and computational efficiency make the kernel extreme learning machine (KELM) a practical approach for this critical task. Since the KELM model is intrinsically sensitive to the regularization parameter and the kernel parameter, a searching scheme combining the coupled simulated annealing (CSA) algorithm and the Nelder-Mead simplex algorithm is adopted to find an optimal KLEM parameter set. A calibration experiment at different working pressure levels was conducted within the temperature range to assess the proposed method. In comparison with other compensation models such as the back-propagation neural network (BP), radius basis neural network (RBF), particle swarm optimization optimized support vector machine (PSO-SVM), particle swarm optimization optimized least squares support vector machine (PSO-LSSVM) and extreme learning machine (ELM), the compensation results show that the presented compensation algorithm exhibits a more satisfactory performance with respect to temperature compensation and synthetic compensation problems. PMID:28422080

Study on Temperature and Synthetic Compensation of Piezo-Resistive Differential Pressure Sensors by Coupled Simulated Annealing and Simplex Optimized Kernel Extreme Learning Machine.

PubMed

Li, Ji; Hu, Guoqing; Zhou, Yonghong; Zou, Chong; Peng, Wei; Alam Sm, Jahangir

2017-04-19

As a high performance-cost ratio solution for differential pressure measurement, piezo-resistive differential pressure sensors are widely used in engineering processes. However, their performance is severely affected by the environmental temperature and the static pressure applied to them. In order to modify the non-linear measuring characteristics of the piezo-resistive differential pressure sensor, compensation actions should synthetically consider these two aspects. Advantages such as nonlinear approximation capability, highly desirable generalization ability and computational efficiency make the kernel extreme learning machine (KELM) a practical approach for this critical task. Since the KELM model is intrinsically sensitive to the regularization parameter and the kernel parameter, a searching scheme combining the coupled simulated annealing (CSA) algorithm and the Nelder-Mead simplex algorithm is adopted to find an optimal KLEM parameter set. A calibration experiment at different working pressure levels was conducted within the temperature range to assess the proposed method. In comparison with other compensation models such as the back-propagation neural network (BP), radius basis neural network (RBF), particle swarm optimization optimized support vector machine (PSO-SVM), particle swarm optimization optimized least squares support vector machine (PSO-LSSVM) and extreme learning machine (ELM), the compensation results show that the presented compensation algorithm exhibits a more satisfactory performance with respect to temperature compensation and synthetic compensation problems.

Novel maximum-margin training algorithms for supervised neural networks.

PubMed

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 MICI, MMGDX, and Levenberg-Marquard (LM), respectively. The resulting neural network was named assembled neural network (ASNN). Benchmark data sets of real-world problems have been used in experiments that enable a comparison with other state-of-the-art classifiers. The results provide evidence of the effectiveness of our methods regarding accuracy, AUC, and balanced error rate.

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.

Neural Networks and other Techniques for Fault Identification and Isolation of Aircraft Systems

NASA Technical Reports Server (NTRS)

Innocenti, M.; Napolitano, M.

2003-01-01

Fault identification, isolation, and accomodation have become critical issues in the overall performance of advanced aircraft systems. Neural Networks have shown to be a very attractive alternative to classic adaptation methods for identification and control of non-linear dynamic systems. The purpose of this paper is to show the improvements in neural network applications achievable through the use of learning algorithms more efficient than the classic Back-Propagation, and through the implementation of the neural schemes in parallel hardware. The results of the analysis of a scheme for Sensor Failure, Detection, Identification and Accommodation (SFDIA) using experimental flight data of a research aircraft model are presented. Conventional approaches to the problem are based on observers and Kalman Filters while more recent methods are based on neural approximators. The work described in this paper is based on the use of neural networks (NNs) as on-line learning non-linear approximators. The performances of two different neural architectures were compared. The first architecture is based on a Multi Layer Perceptron (MLP) NN trained with the Extended Back Propagation algorithm (EBPA). The second architecture is based on a Radial Basis Function (RBF) NN trained with the Extended-MRAN (EMRAN) algorithms. In addition, alternative methods for communications links fault detection and accomodation are presented, relative to multiple unmanned aircraft applications.

Learning a single-hidden layer feedforward neural network using a rank correlation-based strategy with application to high dimensional gene expression and proteomic spectra datasets in cancer detection.

PubMed

Belciug, Smaranda; Gorunescu, Florin

2018-06-08

Methods based on microarrays (MA), mass spectrometry (MS), and machine learning (ML) algorithms have evolved rapidly in recent years, allowing for early detection of several types of cancer. A pitfall of these approaches, however, is the overfitting of data due to large number of attributes and small number of instances -- a phenomenon known as the 'curse of dimensionality'. A potentially fruitful idea to avoid this drawback is to develop algorithms that combine fast computation with a filtering module for the attributes. The goal of this paper is to propose a statistical strategy to initiate the hidden nodes of a single-hidden layer feedforward neural network (SLFN) by using both the knowledge embedded in data and a filtering mechanism for attribute relevance. In order to attest its feasibility, the proposed model has been tested on five publicly available high-dimensional datasets: breast, lung, colon, and ovarian cancer regarding gene expression and proteomic spectra provided by cDNA arrays, DNA microarray, and MS. The novel algorithm, called adaptive SLFN (aSLFN), has been compared with four major classification algorithms: traditional ELM, radial basis function network (RBF), single-hidden layer feedforward neural network trained by backpropagation algorithm (BP-SLFN), and support vector-machine (SVM). Experimental results showed that the classification performance of aSLFN is competitive with the comparison models. Copyright © 2018. Published by Elsevier Inc.

Prediction of air pollutant concentration based on sparse response back-propagation training feedforward neural networks.

PubMed

Ding, Weifu; Zhang, Jiangshe; Leung, Yee

2016-10-01

In this paper, we predict air pollutant concentration using a feedforward artificial neural network inspired by the mechanism of the human brain as a useful alternative to traditional statistical modeling techniques. The neural network is trained based on sparse response back-propagation in which only a small number of neurons respond to the specified stimulus simultaneously and provide a high convergence rate for the trained network, in addition to low energy consumption and greater generalization. Our method is evaluated on Hong Kong air monitoring station data and corresponding meteorological variables for which five air quality parameters were gathered at four monitoring stations in Hong Kong over 4 years (2012-2015). Our results show that our training method has more advantages in terms of the precision of the prediction, effectiveness, and generalization of traditional linear regression algorithms when compared with a feedforward artificial neural network trained using traditional back-propagation.

Learning State Space Dynamics in Recurrent Networks

NASA Astrophysics Data System (ADS)

Simard, Patrice Yvon

Fully recurrent (asymmetrical) networks can be used to learn temporal trajectories. The network is unfolded in time, and backpropagation is used to train the weights. The presence of recurrent connections creates internal states in the system which vary as a function of time. The resulting dynamics can provide interesting additional computing power but learning is made more difficult by the existence of internal memories. This study first exhibits the properties of recurrent networks in terms of convergence when the internal states of the system are unknown. A new energy functional is provided to change the weights of the units in order to the control the stability of the fixed points of the network's dynamics. The power of the resultant algorithm is illustrated with the simulation of a content addressable memory. Next, the more general case of time trajectories on a recurrent network is studied. An application is proposed in which trajectories are generated to draw letters as a function of an input. In another application of recurrent systems, a neural network certain temporal properties observed in human callosally sectioned brains. Finally the proposed algorithm for stabilizing dynamics around fixed points is extended to one for stabilizing dynamics around time trajectories. Its effects are illustrated on a network which generates Lisajous curves.

Detection and clustering of features in aerial images by neuron network-based algorithm

NASA Astrophysics Data System (ADS)

Vozenilek, Vit

2015-12-01

The paper presents the algorithm for detection and clustering of feature in aerial photographs based on artificial neural networks. The presented approach is not focused on the detection of specific topographic features, but on the combination of general features analysis and their use for clustering and backward projection of clusters to aerial image. The basis of the algorithm is a calculation of the total error of the network and a change of weights of the network to minimize the error. A classic bipolar sigmoid was used for the activation function of the neurons and the basic method of backpropagation was used for learning. To verify that a set of features is able to represent the image content from the user's perspective, the web application was compiled (ASP.NET on the Microsoft .NET platform). The main achievements include the knowledge that man-made objects in aerial images can be successfully identified by detection of shapes and anomalies. It was also found that the appropriate combination of comprehensive features that describe the colors and selected shapes of individual areas can be useful for image analysis.

Non-proliferative diabetic retinopathy symptoms detection and classification using neural network.

PubMed

Al-Jarrah, Mohammad A; Shatnawi, Hadeel

2017-08-01

Diabetic retinopathy (DR) causes blindness in the working age for people with diabetes in most countries. The increasing number of people with diabetes worldwide suggests that DR will continue to be major contributors to vision loss. Early detection of retinopathy progress in individuals with diabetes is critical for preventing visual loss. Non-proliferative DR (NPDR) is an early stage of DR. Moreover, NPDR can be classified into mild, moderate and severe. This paper proposes a novel morphology-based algorithm for detecting retinal lesions and classifying each case. First, the proposed algorithm detects the three DR lesions, namely haemorrhages, microaneurysms and exudates. Second, we defined and extracted a set of features from detected lesions. The set of selected feature emulates what physicians looked for in classifying NPDR case. Finally, we designed an artificial neural network (ANN) classifier with three layers to classify NPDR to normal, mild, moderate and severe. Bayesian regularisation and resilient backpropagation algorithms are used to train ANN. The accuracy for the proposed classifiers based on Bayesian regularisation and resilient backpropagation algorithms are 96.6 and 89.9, respectively. The obtained results are compared with results of the recent published classifier. Our proposed classifier outperforms the best in terms of sensitivity and specificity.

Identification and discrimination of oral asaccharolytic Eubacterium spp. by pyrolysis mass spectrometry and artificial neural networks.

PubMed

Goodacre, R; Hiom, S J; Cheeseman, S L; Murdoch, D; Weightman, A J; Wade, W G

1996-02-01

Curie-point pyrolysis mass spectra were obtained from 29 oral asaccharolytic Eubacterium strains and 6 abscess isolates previously identified as Peptostreptococcus heliotrinreducens. Pyrolysis mass spectrometry (PyMS) with cluster analysis was able to clarify the taxonomic position of this group of organisms. Artificial neural networks (ANNS) were then trained by supervised learning (with the back-propagation algorithm) to recognize the strains from their pyrolysis mass spectra; all Eubacterium strains were correctly identified, and the abscess isolates were identified as un-named Eubacterium taxon C2 and were distinct from the type strain of P. heliotrinreducens. These results demonstrate that the combination of PyMS and ANNs provides a rapid and accurate identification technique.

Fractional-order gradient descent learning of BP neural networks with Caputo derivative.

PubMed

Wang, Jian; Wen, Yanqing; Gou, Yida; Ye, Zhenyun; Chen, Hua

2017-05-01

Fractional calculus has been found to be a promising area of research for information processing and modeling of some physical systems. In this paper, we propose a fractional gradient descent method for the backpropagation (BP) training of neural networks. In particular, the Caputo derivative is employed to evaluate the fractional-order gradient of the error defined as the traditional quadratic energy function. The monotonicity and weak (strong) convergence of the proposed approach are proved in detail. Two simulations have been implemented to illustrate the performance of presented fractional-order BP algorithm on three small datasets and one large dataset. The numerical simulations effectively verify the theoretical observations of this paper as well. Copyright © 2017 Elsevier Ltd. All rights reserved.

Leukemia and colon tumor detection based on microarray data classification using momentum backpropagation and genetic algorithm as a feature selection method

NASA Astrophysics Data System (ADS)

Wisesty, Untari N.; Warastri, Riris S.; Puspitasari, Shinta Y.

2018-03-01

Cancer is one of the major causes of mordibility and mortality problems in the worldwide. Therefore, the need of a system that can analyze and identify a person suffering from a cancer by using microarray data derived from the patient’s Deoxyribonucleic Acid (DNA). But on microarray data has thousands of attributes, thus making the challenges in data processing. This is often referred to as the curse of dimensionality. Therefore, in this study built a system capable of detecting a patient whether contracted cancer or not. The algorithm used is Genetic Algorithm as feature selection and Momentum Backpropagation Neural Network as a classification method, with data used from the Kent Ridge Bio-medical Dataset. Based on system testing that has been done, the system can detect Leukemia and Colon Tumor with best accuracy equal to 98.33% for colon tumor data and 100% for leukimia data. Genetic Algorithm as feature selection algorithm can improve system accuracy, which is from 64.52% to 98.33% for colon tumor data and 65.28% to 100% for leukemia data, and the use of momentum parameters can accelerate the convergence of the system in the training process of Neural Network.

Prototype-Incorporated Emotional Neural Network.

PubMed

Oyedotun, Oyebade K; Khashman, Adnan

2017-08-15

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

Reliability analysis of C-130 turboprop engine components using artificial neural network

NASA Astrophysics Data System (ADS)

Qattan, Nizar A.

In this study, we predict the failure rate of Lockheed C-130 Engine Turbine. More than thirty years of local operational field data were used for failure rate prediction and validation. The Weibull regression model and the Artificial Neural Network model including (feed-forward back-propagation, radial basis neural network, and multilayer perceptron neural network model); will be utilized to perform this study. For this purpose, the thesis will be divided into five major parts. First part deals with Weibull regression model to predict the turbine general failure rate, and the rate of failures that require overhaul maintenance. The second part will cover the Artificial Neural Network (ANN) model utilizing the feed-forward back-propagation algorithm as a learning rule. The MATLAB package will be used in order to build and design a code to simulate the given data, the inputs to the neural network are the independent variables, the output is the general failure rate of the turbine, and the failures which required overhaul maintenance. In the third part we predict the general failure rate of the turbine and the failures which require overhaul maintenance, using radial basis neural network model on MATLAB tool box. In the fourth part we compare the predictions of the feed-forward back-propagation model, with that of Weibull regression model, and radial basis neural network model. The results show that the failure rate predicted by the feed-forward back-propagation artificial neural network model is closer in agreement with radial basis neural network model compared with the actual field-data, than the failure rate predicted by the Weibull model. By the end of the study, we forecast the general failure rate of the Lockheed C-130 Engine Turbine, the failures which required overhaul maintenance and six categorical failures using multilayer perceptron neural network (MLP) model on DTREG commercial software. The results also give an insight into the reliability of the engine turbine under actual operating conditions, which can be used by aircraft operators for assessing system and component failures and customizing the maintenance programs recommended by the manufacturer.

Neural network based glucose - insulin metabolism models for children with Type 1 diabetes.

PubMed

Mougiakakou, Stavroula G; Prountzou, Aikaterini; Iliopoulou, Dimitra; Nikita, Konstantina S; Vazeou, Andriani; Bartsocas, Christos S

2006-01-01

In this paper two models for the simulation of glucose-insulin metabolism of children with Type 1 diabetes are presented. The models are based on the combined use of Compartmental Models (CMs) and artificial Neural Networks (NNs). Data from children with Type 1 diabetes, stored in a database, have been used as input to the models. The data are taken from four children with Type 1 diabetes and contain information about glucose levels taken from continuous glucose monitoring system, insulin intake and food intake, along with corresponding time. The influences of taken insulin on plasma insulin concentration, as well as the effect of food intake on glucose input into the blood from the gut, are estimated from the CMs. The outputs of CMs, along with previous glucose measurements, are fed to a NN, which provides short-term prediction of glucose values. For comparative reasons two different NN architectures have been tested: a Feed-Forward NN (FFNN) trained with the back-propagation algorithm with adaptive learning rate and momentum, and a Recurrent NN (RNN), trained with the Real Time Recurrent Learning (RTRL) algorithm. The results indicate that the best prediction performance can be achieved by the use of RNN.

Smoothing Strategies Combined with ARIMA and Neural Networks to Improve the Forecasting of Traffic Accidents

PubMed Central

Rodríguez, Nibaldo

2014-01-01

Two smoothing strategies combined with autoregressive integrated moving average (ARIMA) and autoregressive neural networks (ANNs) models to improve the forecasting of time series are presented. The strategy of forecasting is implemented using two stages. In the first stage the time series is smoothed using either, 3-point moving average smoothing, or singular value Decomposition of the Hankel matrix (HSVD). In the second stage, an ARIMA model and two ANNs for one-step-ahead time series forecasting are used. The coefficients of the first ANN are estimated through the particle swarm optimization (PSO) learning algorithm, while the coefficients of the second ANN are estimated with the resilient backpropagation (RPROP) learning algorithm. The proposed models are evaluated using a weekly time series of traffic accidents of Valparaíso, Chilean region, from 2003 to 2012. The best result is given by the combination HSVD-ARIMA, with a MAPE of 0 : 26%, followed by MA-ARIMA with a MAPE of 1 : 12%; the worst result is given by the MA-ANN based on PSO with a MAPE of 15 : 51%. PMID:25243200

Optimize Short Term load Forcasting Anomalous Based Feed Forward Backpropagation

NASA Astrophysics Data System (ADS)

Mulyadi, Y.; Abdullah, A. G.; Rohmah, K. A.

2017-03-01

This paper contains the Short-Term Load Forecasting (STLF) using artificial neural network especially feed forward back propagation algorithm which is particularly optimized in order to getting a reduced error value result. Electrical load forecasting target is a holiday that hasn’t identical pattern and different from weekday’s pattern, in other words the pattern of holiday load is an anomalous. Under these conditions, the level of forecasting accuracy will be decrease. Hence we need a method that capable to reducing error value in anomalous load forecasting. Learning process of algorithm is supervised or controlled, then some parameters are arranged before performing computation process. Momentum constant a value is set at 0.8 which serve as a reference because it has the greatest converge tendency. Learning rate selection is made up to 2 decimal digits. In addition, hidden layer and input component are tested in several variation of number also. The test result leads to the conclusion that the number of hidden layer impact on the forecasting accuracy and test duration determined by the number of iterations when performing input data until it reaches the maximum of a parameter value.

Algebraic and adaptive learning in neural control systems

NASA Astrophysics Data System (ADS)

Ferrari, Silvia

A systematic approach is developed for designing adaptive and reconfigurable nonlinear control systems that are applicable to plants modeled by ordinary differential equations. The nonlinear controller comprising a network of neural networks is taught using a two-phase learning procedure realized through novel techniques for initialization, on-line training, and adaptive critic design. A critical observation is that the gradients of the functions defined by the neural networks must equal corresponding linear gain matrices at chosen operating points. On-line training is based on a dual heuristic adaptive critic architecture that improves control for large, coupled motions by accounting for actual plant dynamics and nonlinear effects. An action network computes the optimal control law; a critic network predicts the derivative of the cost-to-go with respect to the state. Both networks are algebraically initialized based on prior knowledge of satisfactory pointwise linear controllers and continue to adapt on line during full-scale simulations of the plant. On-line training takes place sequentially over discrete periods of time and involves several numerical procedures. A backpropagating algorithm called Resilient Backpropagation is modified and successfully implemented to meet these objectives, without excessive computational expense. This adaptive controller is as conservative as the linear designs and as effective as a global nonlinear controller. The method is successfully implemented for the full-envelope control of a six-degree-of-freedom aircraft simulation. The results show that the on-line adaptation brings about improved performance with respect to the initialization phase during aircraft maneuvers that involve large-angle and coupled dynamics, and parameter variations.

Bio-Inspired Microsystem for Robust Genetic Assay Recognition

PubMed Central

Lue, Jaw-Chyng; Fang, Wai-Chi

2008-01-01

A compact integrated system-on-chip (SoC) architecture solution for robust, real-time, and on-site genetic analysis has been proposed. This microsystem solution is noise-tolerable and suitable for analyzing the weak fluorescence patterns from a PCR prepared dual-labeled DNA microchip assay. In the architecture, a preceding VLSI differential logarithm microchip is designed for effectively computing the logarithm of the normalized input fluorescence signals. A posterior VLSI artificial neural network (ANN) processor chip is used for analyzing the processed signals from the differential logarithm stage. A single-channel logarithmic circuit was fabricated and characterized. A prototype ANN chip with unsupervised winner-take-all (WTA) function was designed, fabricated, and tested. An ANN learning algorithm using a novel sigmoid-logarithmic transfer function based on the supervised backpropagation (BP) algorithm is proposed for robustly recognizing low-intensity patterns. Our results show that the trained new ANN can recognize low-fluorescence patterns better than an ANN using the conventional sigmoid function. PMID:18566679

A Pruning Neural Network Model in Credit Classification Analysis

PubMed Central

Tang, Yajiao; Ji, Junkai; Dai, Hongwei; Yu, Yang; Todo, Yuki

2018-01-01

Nowadays, credit classification models are widely applied because they can help financial decision-makers to handle credit classification issues. Among them, artificial neural networks (ANNs) have been widely accepted as the convincing methods in the credit industry. In this paper, we propose a pruning neural network (PNN) and apply it to solve credit classification problem by adopting the well-known Australian and Japanese credit datasets. The model is inspired by synaptic nonlinearity of a dendritic tree in a biological neural model. And it is trained by an error back-propagation algorithm. The model is capable of realizing a neuronal pruning function by removing the superfluous synapses and useless dendrites and forms a tidy dendritic morphology at the end of learning. Furthermore, we utilize logic circuits (LCs) to simulate the dendritic structures successfully which makes PNN be implemented on the hardware effectively. The statistical results of our experiments have verified that PNN obtains superior performance in comparison with other classical algorithms in terms of accuracy and computational efficiency. PMID:29606961

Deep Unfolding for Topic Models.

PubMed

Chien, Jen-Tzung; Lee, Chao-Hsi

2018-02-01

Deep unfolding provides an approach to integrate the probabilistic generative models and the deterministic neural networks. Such an approach is benefited by deep representation, easy interpretation, flexible learning and stochastic modeling. This study develops the unsupervised and supervised learning of deep unfolded topic models for document representation and classification. Conventionally, the unsupervised and supervised topic models are inferred via the variational inference algorithm where the model parameters are estimated by maximizing the lower bound of logarithm of marginal likelihood using input documents without and with class labels, respectively. The representation capability or classification accuracy is constrained by the variational lower bound and the tied model parameters across inference procedure. This paper aims to relax these constraints by directly maximizing the end performance criterion and continuously untying the parameters in learning process via deep unfolding inference (DUI). The inference procedure is treated as the layer-wise learning in a deep neural network. The end performance is iteratively improved by using the estimated topic parameters according to the exponentiated updates. Deep learning of topic models is therefore implemented through a back-propagation procedure. Experimental results show the merits of DUI with increasing number of layers compared with variational inference in unsupervised as well as supervised topic models.

Where Do Features Come From?

ERIC Educational Resources Information Center

Hinton, Geoffrey

2014-01-01

It is possible to learn multiple layers of non-linear features by backpropagating error derivatives through a feedforward neural network. This is a very effective learning procedure when there is a huge amount of labeled training data, but for many learning tasks very few labeled examples are available. In an effort to overcome the need for…

Minimal perceptrons for memorizing complex patterns

NASA Astrophysics Data System (ADS)

Pastor, Marissa; Song, Juyong; Hoang, Danh-Tai; Jo, Junghyo

2016-11-01

Feedforward neural networks have been investigated to understand learning and memory, as well as applied to numerous practical problems in pattern classification. It is a rule of thumb that more complex tasks require larger networks. However, the design of optimal network architectures for specific tasks is still an unsolved fundamental problem. In this study, we consider three-layered neural networks for memorizing binary patterns. We developed a new complexity measure of binary patterns, and estimated the minimal network size for memorizing them as a function of their complexity. We formulated the minimal network size for regular, random, and complex patterns. In particular, the minimal size for complex patterns, which are neither ordered nor disordered, was predicted by measuring their Hamming distances from known ordered patterns. Our predictions agree with simulations based on the back-propagation algorithm.

Application of artificial neural networks with backpropagation technique in the financial data

NASA Astrophysics Data System (ADS)

Jaiswal, Jitendra Kumar; Das, Raja

2017-11-01

The propensity of applying neural networks has been proliferated in multiple disciplines for research activities since the past recent decades because of its powerful control with regulatory parameters for pattern recognition and classification. It is also being widely applied for forecasting in the numerous divisions. Since financial data have been readily available due to the involvement of computers and computing systems in the stock market premises throughout the world, researchers have also developed numerous techniques and algorithms to analyze the data from this sector. In this paper we have applied neural network with backpropagation technique to find the data pattern from finance section and prediction for stock values as well.

Convolutional networks for fast, energy-efficient neuromorphic computing

PubMed Central

Esser, Steven K.; Merolla, Paul A.; Arthur, John V.; Cassidy, Andrew S.; Appuswamy, Rathinakumar; Andreopoulos, Alexander; Berg, David J.; McKinstry, Jeffrey L.; Melano, Timothy; Barch, Davis R.; di Nolfo, Carmelo; Datta, Pallab; Amir, Arnon; Taba, Brian; Flickner, Myron D.; Modha, Dharmendra S.

2016-01-01

Deep networks are now able to achieve human-level performance on a broad spectrum of recognition tasks. Independently, neuromorphic computing has now demonstrated unprecedented energy-efficiency through a new chip architecture based on spiking neurons, low precision synapses, and a scalable communication network. Here, we demonstrate that neuromorphic computing, despite its novel architectural primitives, can implement deep convolution networks that (i) approach state-of-the-art classification accuracy across eight standard datasets encompassing vision and speech, (ii) perform inference while preserving the hardware’s underlying energy-efficiency and high throughput, running on the aforementioned datasets at between 1,200 and 2,600 frames/s and using between 25 and 275 mW (effectively >6,000 frames/s per Watt), and (iii) can be specified and trained using backpropagation with the same ease-of-use as contemporary deep learning. This approach allows the algorithmic power of deep learning to be merged with the efficiency of neuromorphic processors, bringing the promise of embedded, intelligent, brain-inspired computing one step closer. PMID:27651489

Convolutional networks for fast, energy-efficient neuromorphic computing.

PubMed

Esser, Steven K; Merolla, Paul A; Arthur, John V; Cassidy, Andrew S; Appuswamy, Rathinakumar; Andreopoulos, Alexander; Berg, David J; McKinstry, Jeffrey L; Melano, Timothy; Barch, Davis R; di Nolfo, Carmelo; Datta, Pallab; Amir, Arnon; Taba, Brian; Flickner, Myron D; Modha, Dharmendra S

2016-10-11

Deep networks are now able to achieve human-level performance on a broad spectrum of recognition tasks. Independently, neuromorphic computing has now demonstrated unprecedented energy-efficiency through a new chip architecture based on spiking neurons, low precision synapses, and a scalable communication network. Here, we demonstrate that neuromorphic computing, despite its novel architectural primitives, can implement deep convolution networks that (i) approach state-of-the-art classification accuracy across eight standard datasets encompassing vision and speech, (ii) perform inference while preserving the hardware's underlying energy-efficiency and high throughput, running on the aforementioned datasets at between 1,200 and 2,600 frames/s and using between 25 and 275 mW (effectively >6,000 frames/s per Watt), and (iii) can be specified and trained using backpropagation with the same ease-of-use as contemporary deep learning. This approach allows the algorithmic power of deep learning to be merged with the efficiency of neuromorphic processors, bringing the promise of embedded, intelligent, brain-inspired computing one step closer.

Competitive Deep-Belief Networks for Underwater Acoustic Target Recognition

PubMed Central

Shen, Sheng; Yao, Xiaohui; Sheng, Meiping; Wang, Chen

2018-01-01

Underwater acoustic target recognition based on ship-radiated noise belongs to the small-sample-size recognition problems. A competitive deep-belief network is proposed to learn features with more discriminative information from labeled and unlabeled samples. The proposed model consists of four stages: (1) A standard restricted Boltzmann machine is pretrained using a large number of unlabeled data to initialize its parameters; (2) the hidden units are grouped according to categories, which provides an initial clustering model for competitive learning; (3) competitive training and back-propagation algorithms are used to update the parameters to accomplish the task of clustering; (4) by applying layer-wise training and supervised fine-tuning, a deep neural network is built to obtain features. Experimental results show that the proposed method can achieve classification accuracy of 90.89%, which is 8.95% higher than the accuracy obtained by the compared methods. In addition, the highest accuracy of our method is obtained with fewer features than other methods. PMID:29570642

Adaptive Critic-based Neurofuzzy Controller for the Steam Generator Water Level

NASA Astrophysics Data System (ADS)

Fakhrazari, Amin; Boroushaki, Mehrdad

2008-06-01

In this paper, an adaptive critic-based neurofuzzy controller is presented for water level regulation of nuclear steam generators. The problem has been of great concern for many years as the steam generator is a highly nonlinear system showing inverse response dynamics especially at low operating power levels. Fuzzy critic-based learning is a reinforcement learning method based on dynamic programming. The only information available for the critic agent is the system feedback which is interpreted as the last action the controller has performed in the previous state. The signal produced by the critic agent is used alongside the backpropagation of error algorithm to tune online conclusion parts of the fuzzy inference rules. The critic agent here has a proportional-derivative structure and the fuzzy rule base has nine rules. The proposed controller shows satisfactory transient responses, disturbance rejection and robustness to model uncertainty. Its simple design procedure and structure, nominates it as one of the suitable controller designs for the steam generator water level control in nuclear power plant industry.

Predictive analysis effectiveness in determining the epidemic disease infected area

NASA Astrophysics Data System (ADS)

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

2017-10-01

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

Prediction of protein tertiary structure from sequences using a very large back-propagation neural network

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

Liu, X.; Wilcox, G.L.

1993-12-31

We have implemented large scale back-propagation neural networks on a 544 node Connection Machine, CM-5, using the C language in MIMD mode. The program running on 512 processors performs backpropagation learning at 0.53 Gflops, which provides 76 million connection updates per second. We have applied the network to the prediction of protein tertiary structure from sequence information alone. A neural network with one hidden layer and 40 million connections is trained to learn the relationship between sequence and tertiary structure. The trained network yields predicted structures of some proteins on which it has not been trained given only their sequences.more » Presentation of the Fourier transform of the sequences accentuates periodicity in the sequence and yields good generalization with greatly increased training efficiency. Training simulations with a large, heterologous set of protein structures (111 proteins from CM-5 time) to solutions with under 2% RMS residual error within the training set (random responses give an RMS error of about 20%). Presentation of 15 sequences of related proteins in a testing set of 24 proteins yields predicted structures with less than 8% RMS residual error, indicating good apparent generalization.« less

Intelligent Soft Computing on Forex: Exchange Rates Forecasting with Hybrid Radial Basis Neural Network

PubMed Central

Marcek, Dusan; Durisova, Maria

2016-01-01

This paper deals with application of quantitative soft computing prediction models into financial area as reliable and accurate prediction models can be very helpful in management decision-making process. The authors suggest a new hybrid neural network which is a combination of the standard RBF neural network, a genetic algorithm, and a moving average. The moving average is supposed to enhance the outputs of the network using the error part of the original neural network. Authors test the suggested model on high-frequency time series data of USD/CAD and examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, they perform a comparative statistical out-of-sample analysis of the tested model with autoregressive models and the standard neural network. They also incorporate genetic algorithm as an optimizing technique for adapting parameters of ANN which is then compared with standard backpropagation and backpropagation combined with K-means clustering algorithm. Finally, the authors find out that their suggested hybrid neural network is able to produce more accurate forecasts than the standard models and can be helpful in eliminating the risk of making the bad decision in decision-making process. PMID:26977450

Intelligent Soft Computing on Forex: Exchange Rates Forecasting with Hybrid Radial Basis Neural Network.

PubMed

Falat, Lukas; Marcek, Dusan; Durisova, Maria

2016-01-01

This paper deals with application of quantitative soft computing prediction models into financial area as reliable and accurate prediction models can be very helpful in management decision-making process. The authors suggest a new hybrid neural network which is a combination of the standard RBF neural network, a genetic algorithm, and a moving average. The moving average is supposed to enhance the outputs of the network using the error part of the original neural network. Authors test the suggested model on high-frequency time series data of USD/CAD and examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, they perform a comparative statistical out-of-sample analysis of the tested model with autoregressive models and the standard neural network. They also incorporate genetic algorithm as an optimizing technique for adapting parameters of ANN which is then compared with standard backpropagation and backpropagation combined with K-means clustering algorithm. Finally, the authors find out that their suggested hybrid neural network is able to produce more accurate forecasts than the standard models and can be helpful in eliminating the risk of making the bad decision in decision-making process.

Compensation of significant parametric uncertainties using sliding mode online learning

NASA Astrophysics Data System (ADS)

Schnetter, Philipp; Kruger, Thomas

An augmented nonlinear inverse dynamics (NID) flight control strategy using sliding mode online learning for a small unmanned aircraft system (UAS) is presented. Because parameter identification for this class of aircraft often is not valid throughout the complete flight envelope, aerodynamic parameters used for model based control strategies may show significant deviations. For the concept of feedback linearization this leads to inversion errors that in combination with the distinctive susceptibility of small UAS towards atmospheric turbulence pose a demanding control task for these systems. In this work an adaptive flight control strategy using feedforward neural networks for counteracting such nonlinear effects is augmented with the concept of sliding mode control (SMC). SMC-learning is derived from variable structure theory. It considers a neural network and its training as a control problem. It is shown that by the dynamic calculation of the learning rates, stability can be guaranteed and thus increase the robustness against external disturbances and system failures. With the resulting higher speed of convergence a wide range of simultaneously occurring disturbances can be compensated. The SMC-based flight controller is tested and compared to the standard gradient descent (GD) backpropagation algorithm under the influence of significant model uncertainties and system failures.

Neural network-based run-to-run controller using exposure and resist thickness adjustment

NASA Astrophysics Data System (ADS)

Geary, Shane; Barry, Ronan

2003-06-01

This paper describes the development of a run-to-run control algorithm using a feedforward neural network, trained using the backpropagation training method. The algorithm is used to predict the critical dimension of the next lot using previous lot information. It is compared to a common prediction algorithm - the exponentially weighted moving average (EWMA) and is shown to give superior prediction performance in simulations. The manufacturing implementation of the final neural network showed significantly improved process capability when compared to the case where no run-to-run control was utilised.

Temporal neural networks and transient analysis of complex engineering systems

NASA Astrophysics Data System (ADS)

Uluyol, Onder

A theory is introduced for a multi-layered Local Output Gamma Feedback (LOGF) neural network within the paradigm of Locally-Recurrent Globally-Feedforward neural networks. It is developed for the identification, prediction, and control tasks of spatio-temporal systems and allows for the presentation of different time scales through incorporation of a gamma memory. It is initially applied to the tasks of sunspot and Mackey-Glass series prediction as benchmarks, then it is extended to the task of power level control of a nuclear reactor at different fuel cycle conditions. The developed LOGF neuron model can also be viewed as a Transformed Input and State (TIS) Gamma memory for neural network architectures for temporal processing. The novel LOGF neuron model extends the static neuron model by incorporating into it a short-term memory structure in the form of a digital gamma filter. A feedforward neural network made up of LOGF neurons can thus be used to model dynamic systems. A learning algorithm based upon the Backpropagation-Through-Time (BTT) approach is derived. It is applicable for training a general L-layer LOGF neural network. The spatial and temporal weights and parameters of the network are iteratively optimized for a given problem using the derived learning algorithm.

Using Upper Layer Weights to Efficiently Construct and Train Feedforward Neural Networks Executing Backpropagation

DTIC Science & Technology

2011-03-01

algorithm is utilized by Belue, Steppe, & Bauer and Kocur , et al. (Belue, Steppe, & Bauer, April 1996) ( Kocur , et al., 1996). Bacauskiene and...Society. Cardiff, UK. Kocur , C., Roger, S., Myers, L., Burns, T., Hoffmeister, J., Bauer, K., et al. (1996). Using neural networks to select

Development of a Robust Identifier for NPPs Transients Combining ARIMA Model and EBP Algorithm

NASA Astrophysics Data System (ADS)

Moshkbar-Bakhshayesh, Khalil; Ghofrani, Mohammad B.

2014-08-01

This study introduces a novel identification method for recognition of nuclear power plants (NPPs) transients by combining the autoregressive integrated moving-average (ARIMA) model and the neural network with error backpropagation (EBP) learning algorithm. The proposed method consists of three steps. First, an EBP based identifier is adopted to distinguish the plant normal states from the faulty ones. In the second step, ARIMA models use integrated (I) process to convert non-stationary data of the selected variables into stationary ones. Subsequently, ARIMA processes, including autoregressive (AR), moving-average (MA), or autoregressive moving-average (ARMA) are used to forecast time series of the selected plant variables. In the third step, for identification the type of transients, the forecasted time series are fed to the modular identifier which has been developed using the latest advances of EBP learning algorithm. Bushehr nuclear power plant (BNPP) transients are probed to analyze the ability of the proposed identifier. Recognition of transient is based on similarity of its statistical properties to the reference one, rather than the values of input patterns. More robustness against noisy data and improvement balance between memorization and generalization are salient advantages of the proposed identifier. Reduction of false identification, sole dependency of identification on the sign of each output signal, selection of the plant variables for transients training independent of each other, and extendibility for identification of more transients without unfavorable effects are other merits of the proposed identifier.

Blur identification by multilayer neural network based on multivalued neurons.

PubMed

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

2008-05-01

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

Prediction of the mass gain during high temperature oxidation of aluminized nanostructured nickel using adaptive neuro-fuzzy inference system

NASA Astrophysics Data System (ADS)

Hayati, M.; Rashidi, A. M.; Rezaei, A.

2012-10-01

In this paper, the applicability of ANFIS as an accurate model for the prediction of the mass gain during high temperature oxidation using experimental data obtained for aluminized nanostructured (NS) nickel is presented. For developing the model, exposure time and temperature are taken as input and the mass gain as output. A hybrid learning algorithm consists of back-propagation and least-squares estimation is used for training the network. We have compared the proposed ANFIS model with experimental data. The predicted data are found to be in good agreement with the experimental data with mean relative error less than 1.1%. Therefore, we can use ANFIS model to predict the performances of thermal systems in engineering applications, such as modeling the mass gain for NS materials.

Multimodal Deep Autoencoder for Human Pose Recovery.

PubMed

Hong, Chaoqun; Yu, Jun; Wan, Jian; Tao, Dacheng; Wang, Meng

2015-12-01

Video-based human pose recovery is usually conducted by retrieving relevant poses using image features. In the retrieving process, the mapping between 2D images and 3D poses is assumed to be linear in most of the traditional methods. However, their relationships are inherently non-linear, which limits recovery performance of these methods. In this paper, we propose a novel pose recovery method using non-linear mapping with multi-layered deep neural network. It is based on feature extraction with multimodal fusion and back-propagation deep learning. In multimodal fusion, we construct hypergraph Laplacian with low-rank representation. In this way, we obtain a unified feature description by standard eigen-decomposition of the hypergraph Laplacian matrix. In back-propagation deep learning, we learn a non-linear mapping from 2D images to 3D poses with parameter fine-tuning. The experimental results on three data sets show that the recovery error has been reduced by 20%-25%, which demonstrates the effectiveness of the proposed method.

A generalized LSTM-like training algorithm for second-order recurrent neural networks

PubMed Central

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

Knowledge mining from clinical datasets using rough sets and backpropagation neural network.

PubMed

Nahato, Kindie Biredagn; Harichandran, Khanna Nehemiah; Arputharaj, Kannan

2015-01-01

The availability of clinical datasets and knowledge mining methodologies encourages the researchers to pursue research in extracting knowledge from clinical datasets. Different data mining techniques have been used for mining rules, and mathematical models have been developed to assist the clinician in decision making. The objective of this research is to build a classifier that will predict the presence or absence of a disease by learning from the minimal set of attributes that has been extracted from the clinical dataset. In this work rough set indiscernibility relation method with backpropagation neural network (RS-BPNN) is used. This work has two stages. The first stage is handling of missing values to obtain a smooth data set and selection of appropriate attributes from the clinical dataset by indiscernibility relation method. The second stage is classification using backpropagation neural network on the selected reducts of the dataset. The classifier has been tested with hepatitis, Wisconsin breast cancer, and Statlog heart disease datasets obtained from the University of California at Irvine (UCI) machine learning repository. The accuracy obtained from the proposed method is 97.3%, 98.6%, and 90.4% for hepatitis, breast cancer, and heart disease, respectively. The proposed system provides an effective classification model for clinical datasets.

LVQ and backpropagation neural networks applied to NASA SSME data

NASA Technical Reports Server (NTRS)

Doniere, Timothy F.; Dhawan, Atam P.

1993-01-01

Feedfoward neural networks with backpropagation learning have been used as function approximators for modeling the space shuttle main engine (SSME) sensor signals. The modeling of these sensor signals is aimed at the development of a sensor fault detection system that can be used during ground test firings. The generalization capability of a neural network based function approximator depends on the training vectors which in this application may be derived from a number of SSME ground test-firings. This yields a large number of training vectors. Large training sets can cause the time required to train the network to be very large. Also, the network may not be able to generalize for large training sets. To reduce the size of the training sets, the SSME test-firing data is reduced using the learning vector quantization (LVQ) based technique. Different compression ratios were used to obtain compressed data in training the neural network model. The performance of the neural model trained using reduced sets of training patterns is presented and compared with the performance of the model trained using complete data. The LVQ can also be used as a function approximator. The performance of the LVQ as a function approximator using reduced training sets is presented and compared with the performance of the backpropagation network.

SKYNET: an efficient and robust neural network training tool for machine learning in astronomy

NASA Astrophysics Data System (ADS)

Graff, Philip; Feroz, Farhan; Hobson, Michael P.; Lasenby, Anthony

2014-06-01

We present the first public release of our generic neural network training algorithm, called SKYNET. This efficient and robust machine learning tool is able to train large and deep feed-forward neural networks, including autoencoders, for use in a wide range of supervised and unsupervised learning applications, such as regression, classification, density estimation, clustering and dimensionality reduction. SKYNET uses a `pre-training' method to obtain a set of network parameters that has empirically been shown to be close to a good solution, followed by further optimization using a regularized variant of Newton's method, where the level of regularization is determined and adjusted automatically; the latter uses second-order derivative information to improve convergence, but without the need to evaluate or store the full Hessian matrix, by using a fast approximate method to calculate Hessian-vector products. This combination of methods allows for the training of complicated networks that are difficult to optimize using standard backpropagation techniques. SKYNET employs convergence criteria that naturally prevent overfitting, and also includes a fast algorithm for estimating the accuracy of network outputs. The utility and flexibility of SKYNET are demonstrated by application to a number of toy problems, and to astronomical problems focusing on the recovery of structure from blurred and noisy images, the identification of gamma-ray bursters, and the compression and denoising of galaxy images. The SKYNET software, which is implemented in standard ANSI C and fully parallelized using MPI, is available at http://www.mrao.cam.ac.uk/software/skynet/.

Neural network for processing both spatial and temporal data with time based back-propagation

NASA Technical Reports Server (NTRS)

Villarreal, James A. (Inventor); Shelton, Robert O. (Inventor)

1993-01-01

Neural networks are computing systems modeled after the paradigm of the biological brain. For years, researchers using various forms of neural networks have attempted to model the brain's information processing and decision-making capabilities. Neural network algorithms have impressively demonstrated the capability of modeling spatial information. On the other hand, the application of parallel distributed models to the processing of temporal data has been severely restricted. The invention introduces a novel technique which adds the dimension of time to the well known back-propagation neural network algorithm. In the space-time neural network disclosed herein, the synaptic weights between two artificial neurons (processing elements) are replaced with an adaptable-adjustable filter. Instead of a single synaptic weight, the invention provides a plurality of weights representing not only association, but also temporal dependencies. In this case, the synaptic weights are the coefficients to the adaptable digital filters. Novelty is believed to lie in the disclosure of a processing element and a network of the processing elements which are capable of processing temporal as well as spacial data.

Uniformly stable backpropagation algorithm to train a feedforward neural network.

PubMed

Rubio, José de Jesús; Angelov, Plamen; Pacheco, Jaime

2011-03-01

Neural networks (NNs) have numerous applications to online processes, but the problem of stability is rarely discussed. This is an extremely important issue because, if the stability of a solution is not guaranteed, the equipment that is being used can be damaged, which can also cause serious accidents. It is true that in some research papers this problem has been considered, but this concerns continuous-time NN only. At the same time, there are many systems that are better described in the discrete time domain such as population of animals, the annual expenses in an industry, the interest earned by a bank, or the prediction of the distribution of loads stored every hour in a warehouse. Therefore, it is of paramount importance to consider the stability of the discrete-time NN. This paper makes several important contributions. 1) A theorem is stated and proven which guarantees uniform stability of a general discrete-time system. 2) It is proven that the backpropagation (BP) algorithm with a new time-varying rate is uniformly stable for online identification and the identification error converges to a small zone bounded by the uncertainty. 3) It is proven that the weights' error is bounded by the initial weights' error, i.e., overfitting is eliminated in the proposed algorithm. 4) The BP algorithm is applied to predict the distribution of loads that a transelevator receives from a trailer and places in the deposits in a warehouse every hour, so that the deposits in the warehouse are reserved in advance using the prediction results. 5) The BP algorithm is compared with the recursive least square (RLS) algorithm and with the Takagi-Sugeno type fuzzy inference system in the problem of predicting the distribution of loads in a warehouse, giving that the first and the second are stable and the third is unstable. 6) The BP algorithm is compared with the RLS algorithm and with the Kalman filter algorithm in a synthetic example.

Application of backpropagation artificial neural network prediction model for the PAH bioremediation of polluted soil.

PubMed

Olawoyin, Richard

2016-10-01

The backpropagation (BP) artificial neural network (ANN) is a renowned and extensively functional mathematical tool used for time-series predictions and approximations; which also define results for non-linear functions. ANNs are vital tools in the predictions of toxicant levels, such as polycyclic aromatic hydrocarbons (PAH) potentially derived from anthropogenic activities in the microenvironment. In the present work, BP ANN was used as a prediction tool to study the potential toxicity of PAH carcinogens (PAHcarc) in soils. Soil samples (16 × 4 = 64) were collected from locations in South-southern Nigeria. The concentration of PAHcarc in laboratory cultivated white melilot, Melilotus alba roots grown on treated soils was predicted using ANN model training. Results indicated the Levenberg-Marquardt back-propagation training algorithm converged in 2.5E+04 epochs at an average RMSE value of 1.06E-06. The averagedR(2) comparison between the measured and predicted outputs was 0.9994. It may be deduced from this study that, analytical processes involving environmental risk assessment as used in this study can successfully provide prompt prediction and source identification of major soil toxicants. Copyright © 2016 Elsevier Ltd. All rights reserved.

Neural Network Control of a Magnetically Suspended Rotor System

NASA Technical Reports Server (NTRS)

Choi, Benjamin B.

1998-01-01

Magnetic bearings offer significant advantages because they do not come into contact with other parts during operation, which can reduce maintenance. Higher speeds, no friction, no lubrication, weight reduction, precise position control, and active damping make them far superior to conventional contact bearings. However, there are technical barriers that limit the application of this technology in industry. One of them is the need for a nonlinear controller that can overcome the system nonlinearity and uncertainty inherent in magnetic bearings. At the NASA Lewis Research Center, a neural network was selected as a nonlinear controller because it generates a neural model without any detailed information regarding the internal working of the magnetic bearing system. It can be used even for systems that are too complex for an accurate system model to be derived. A feed-forward architecture with a back-propagation learning algorithm was selected because of its proven performance, accuracy, and relatively easy implementation.

Recurrent neural network control for LCC-resonant ultrasonic motor drive.

PubMed

Lin, F J; Wai, R J; Hong, C M

2000-01-01

A newly designed driving circuit for the traveling wave-type ultrasonic motor (USM), which consists of a push-pull DC-DC power converter and a two-phase voltage source inverter using one inductance and two capacitances (LCC) resonant technique, is presented in this study. Moreover, because the dynamic characteristics of the USM are difficult to obtain and the motor parameters are time varying, a recurrent neural network (RNN) controller is proposed to control the USM drive system. In the proposed controller, the dynamic backpropagation algorithm is adopted to train the RNN on-line using the proposed delta adaptation law. Furthermore, to guarantee the convergence of tracking error, analytical methods based on a discrete-type Lyapunov function are proposed to determine the varied learning rates for the training of the RNN. Finally, the effectiveness of the RNN-controlled USM drive system is demonstrated by some experimental results.

Constitutive flow behaviour of austenitic stainless steels under hot deformation: artificial neural network modelling to understand, evaluate and predict

NASA Astrophysics Data System (ADS)

Mandal, Sumantra; Sivaprasad, P. V.; Venugopal, S.; Murthy, K. P. N.

2006-09-01

An artificial neural network (ANN) model is developed to predict the constitutive flow behaviour of austenitic stainless steels during hot deformation. The input parameters are alloy composition and process variables whereas flow stress is the output. The model is based on a three-layer feed-forward ANN with a back-propagation learning algorithm. The neural network is trained with an in-house database obtained from hot compression tests on various grades of austenitic stainless steels. The performance of the model is evaluated using a wide variety of statistical indices. Good agreement between experimental and predicted data is obtained. The correlation between individual alloying elements and high temperature flow behaviour is investigated by employing the ANN model. The results are found to be consistent with the physical phenomena. The model can be used as a guideline for new alloy development.

Application of Adaptive Neuro-Fuzzy Inference System for Prediction of Neutron Yield of IR-IECF Facility in High Voltages

NASA Astrophysics Data System (ADS)

Adineh-Vand, A.; Torabi, M.; Roshani, G. H.; Taghipour, M.; Feghhi, S. A. H.; Rezaei, M.; Sadati, S. M.

2013-09-01

This paper presents a soft computing based artificial intelligent technique, adaptive neuro-fuzzy inference system (ANFIS) to predict the neutron production rate (NPR) of IR-IECF device in wide discharge current and voltage ranges. A hybrid learning algorithm consists of back-propagation and least-squares estimation is used for training the ANFIS model. The performance of the proposed ANFIS model is tested using the experimental data using four performance measures: correlation coefficient, mean absolute error, mean relative error percentage (MRE%) and root mean square error. The obtained results show that the proposed ANFIS model has achieved good agreement with the experimental results. In comparison to the experimental data the proposed ANFIS model has MRE% <1.53 and 2.85 % for training and testing data respectively. Therefore, this model can be used as an efficient tool to predict the NPR in the IR-IECF device.

Using a binaural biomimetic array to identify bottom objects ensonified by echolocating dolphins

USGS Publications Warehouse

Heiweg, D.A.; Moore, P.W.; Martin, S.W.; Dankiewicz, L.A.

2006-01-01

The development of a unique dolphin biomimetic sonar produced data that were used to study signal processing methods for object identification. Echoes from four metallic objects proud on the bottom, and a substrate-only condition, were generated by bottlenose dolphins trained to ensonify the targets in very shallow water. Using the two-element ('binaural') receive array, object echo spectra were collected and submitted for identification to four neural network architectures. Identification accuracy was evaluated over two receive array configurations, and five signal processing schemes. The four neural networks included backpropagation, learning vector quantization, genetic learning and probabilistic network architectures. The processing schemes included four methods that capitalized on the binaural data, plus a monaural benchmark process. All the schemes resulted in above-chance identification accuracy when applied to learning vector quantization and backpropagation. Beam-forming or concatenation of spectra from both receive elements outperformed the monaural benchmark, with higher sensitivity and lower bias. Ultimately, best object identification performance was achieved by the learning vector quantization network supplied with beam-formed data. The advantages of multi-element signal processing for object identification are clearly demonstrated in this development of a first-ever dolphin biomimetic sonar. ?? 2006 IOP Publishing Ltd.

An Efficient Supervised Training Algorithm for Multilayer Spiking Neural Networks

PubMed Central

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

Application of machine learning methods for traffic signs recognition

NASA Astrophysics Data System (ADS)

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

2018-02-01

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

Digital backpropagation accounting for polarization-mode dispersion.

PubMed

Czegledi, Cristian B; Liga, Gabriele; Lavery, Domaniç; Karlsson, Magnus; Agrell, Erik; Savory, Seb J; Bayvel, Polina

2017-02-06

Digital backpropagation (DBP) is a promising digital-domain technique to mitigate Kerr-induced nonlinear interference. While it successfully removes deterministic signal-signal interactions, the performance of ideal DBP is limited by stochastic effects, such as polarization-mode dispersion (PMD). In this paper, we consider an ideal full-field DBP implementation and modify it to additionally account for PMD; reversing the PMD effects in the backward propagation by passing the reverse propagated signal also through PMD sections, which concatenated equal the inverse of the PMD in the forward propagation. These PMD sections are calculated analytically at the receiver based on the total accumulated PMD of the link estimated from channel equalizers. Numerical simulations show that, accounting for nonlinear polarization-related interactions in the modified DBP algorithm, additional signal-to-noise ratio gains of 1.1 dB are obtained for transmission over 1000 km.

A robust cloud registration method based on redundant data reduction using backpropagation neural network and shift window

NASA Astrophysics Data System (ADS)

Xin, Meiting; Li, Bing; Yan, Xiao; Chen, Lei; Wei, Xiang

2018-02-01

A robust coarse-to-fine registration method based on the backpropagation (BP) neural network and shift window technology is proposed in this study. Specifically, there are three steps: coarse alignment between the model data and measured data, data simplification based on the BP neural network and point reservation in the contour region of point clouds, and fine registration with the reweighted iterative closest point algorithm. In the process of rough alignment, the initial rotation matrix and the translation vector between the two datasets are obtained. After performing subsequent simplification operations, the number of points can be reduced greatly. Therefore, the time and space complexity of the accurate registration can be significantly reduced. The experimental results show that the proposed method improves the computational efficiency without loss of accuracy.

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 user. The program has a memory requirement of about 900K. The standard distribution medium for this package is a .25 inch streaming magnetic tape cartridge in UNIX tar format. It is also available on a 3.5 inch diskette in UNIX tar format. F77NNS was developed in 1989.

Application of the clinical matrix to the diagnosis of leukemia

NASA Astrophysics Data System (ADS)

Pakkala, Sampath Y.; Lin, Frank C.

1992-07-01

A system for diagnosing leukemia subtypes has been formulated using neural networks. The statistical data of the symptoms collected by hematologists is fed into a single training set using a neural network, where the network is trained by using fast backpropagation algorithm, which when done can help the general practitioners for making diagnoses on the basis of signs and symptoms alone.

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

NASA Astrophysics Data System (ADS)

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

2016-12-01

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

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

PubMed

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

2016-12-01

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

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

PubMed Central

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

2016-01-01

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

One-dimensional inversion of geo-electrical resistivity sounding data using artificial neural networks—a case study

NASA Astrophysics Data System (ADS)

Singh, U. K.; Tiwari, R. K.; Singh, S. B.

2005-02-01

This paper deals with the application of artificial neural networks (ANN) technique for the study of a case history using 1-D inversion of vertical electrical resistivity sounding (VES) data from the Puga valley, Kashmir, India. The study area is important for its rich geothermal resources as well as from the tectonic point of view as it is located near the collision boundary of the Indo-Asian crustal plates. In order to understand the resistivity structure and layer thicknesses, we used here three-layer feedforward neural networks to model and predict measured VES data. Three algorithms, e.g. back-propagation (BP), adaptive back-propagation (ABP) and Levenberg-Marquardt algorithm (LMA) were applied to the synthetic as well as real VES field data and efficiency of supervised training network are compared. Analyses suggest that LMA is computationally faster and give results, which are comparatively more accurate and consistent than BP and ABP. The results obtained using the ANN inversions are remarkably correlated with the available borehole litho-logs. The feasibility study suggests that ANN methods offer an excellent complementary tool for the direct detection of layered resistivity structure.

Forecasting the portuguese stock market time series by using artificial neural networks

NASA Astrophysics Data System (ADS)

Isfan, Monica; Menezes, Rui; Mendes, Diana A.

2010-04-01

In this paper, we show that neural networks can be used to uncover the non-linearity that exists in the financial data. First, we follow a traditional approach by analysing the deterministic/stochastic characteristics of the Portuguese stock market data and some typical features are studied, like the Hurst exponents, among others. We also simulate a BDS test to investigate nonlinearities and the results are as expected: the financial time series do not exhibit linear dependence. Secondly, we trained four types of neural networks for the stock markets and used the models to make forecasts. The artificial neural networks were obtained using a three-layer feed-forward topology and the back-propagation learning algorithm. The quite large number of parameters that must be selected to develop a neural network forecasting model involves some trial and as a consequence the error is not small enough. In order to improve this we use a nonlinear optimization algorithm to minimize the error. Finally, the output of the 4 models is quite similar, leading to a qualitative forecast that we compare with the results of the application of k-nearest-neighbor for the same time series.

Data classification using metaheuristic Cuckoo Search technique for Levenberg Marquardt back propagation (CSLM) algorithm

NASA Astrophysics Data System (ADS)

Nawi, Nazri Mohd.; Khan, Abdullah; Rehman, M. Z.

2015-05-01

A nature inspired behavior metaheuristic techniques which provide derivative-free solutions to solve complex problems. One of the latest additions to the group of nature inspired optimization procedure is Cuckoo Search (CS) algorithm. Artificial Neural Network (ANN) training is an optimization task since it is desired to find optimal weight set of a neural network in training process. Traditional training algorithms have some limitation such as getting trapped in local minima and slow convergence rate. This study proposed a new technique CSLM by combining the best features of two known algorithms back-propagation (BP) and Levenberg Marquardt algorithm (LM) for improving the convergence speed of ANN training and avoiding local minima problem by training this network. Some selected benchmark classification datasets are used for simulation. The experiment result show that the proposed cuckoo search with Levenberg Marquardt algorithm has better performance than other algorithm used in this study.

Experiments in Neural-Network Control of a Free-Flying Space Robot

NASA Technical Reports Server (NTRS)

Wilson, Edward

1995-01-01

Four important generic issues are identified and addressed in some depth in this thesis as part of the development of an adaptive neural network based control system for an experimental free flying space robot prototype. The first issue concerns the importance of true system level design of the control system. A new hybrid strategy is developed here, in depth, for the beneficial integration of neural networks into the total control system. A second important issue in neural network control concerns incorporating a priori knowledge into the neural network. In many applications, it is possible to get a reasonably accurate controller using conventional means. If this prior information is used purposefully to provide a starting point for the optimizing capabilities of the neural network, it can provide much faster initial learning. In a step towards addressing this issue, a new generic Fully Connected Architecture (FCA) is developed for use with backpropagation. A third issue is that neural networks are commonly trained using a gradient based optimization method such as backpropagation; but many real world systems have Discrete Valued Functions (DVFs) that do not permit gradient based optimization. One example is the on-off thrusters that are common on spacecraft. A new technique is developed here that now extends backpropagation learning for use with DVFs. The fourth issue is that the speed of adaptation is often a limiting factor in the implementation of a neural network control system. This issue has been strongly resolved in the research by drawing on the above new contributions.

Two States Mapping Based Time Series Neural Network Model for Compensation Prediction Residual Error

NASA Astrophysics Data System (ADS)

Jung, Insung; Koo, Lockjo; Wang, Gi-Nam

2008-11-01

The objective of this paper was to design a model of human bio signal data prediction system for decreasing of prediction error using two states mapping based time series neural network BP (back-propagation) model. Normally, a lot of the industry has been applied neural network model by training them in a supervised manner with the error back-propagation algorithm for time series prediction systems. However, it still has got a residual error between real value and prediction result. Therefore, we designed two states of neural network model for compensation residual error which is possible to use in the prevention of sudden death and metabolic syndrome disease such as hypertension disease and obesity. We determined that most of the simulation cases were satisfied by the two states mapping based time series prediction model. In particular, small sample size of times series were more accurate than the standard MLP model.

Pattern recognition of visible and near-infrared spectroscopy from bayberry juice by use of partial least squares and a backpropagation neural network

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

Cen Haiyan; Bao Yidan; He Yong

2006-10-10

Visible and near-infrared reflectance (visible-NIR) spectroscopy is applied to discriminate different varieties of bayberry juices. The discrimination of visible-NIR spectra from samples is a matter of pattern recognition. By partial least squares (PLS), the spectrum is reduced to certain factors, which are then taken as the input of the backpropagation neural network (BPNN). Through training and prediction, three different varieties of bayberry juice are classified based on the output of the BPNN. In addition, a mathematical model is built and the algorithm is optimized. With proper parameters in the training set,100% accuracy is obtained by the BPNN. Thus it ismore » concluded that the PLS analysis combined with the BPNN is an alternative for pattern recognition based on visible and NIR spectroscopy.« less

Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm

PubMed Central

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

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

PubMed

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

2014-09-01

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

Magnetotelluric inversion via reverse time migration algorithm of seismic data

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

Ha, Taeyoung; Shin, Changsoo

2007-07-01

We propose a new algorithm for two-dimensional magnetotelluric (MT) inversion. Our algorithm is an MT inversion based on the steepest descent method, borrowed from the backpropagation technique of seismic inversion or reverse time migration, introduced in the middle 1980s by Lailly and Tarantola. The steepest descent direction can be calculated efficiently by using the symmetry of numerical Green's function derived from a mixed finite element method proposed by Nedelec for Maxwell's equation, without calculating the Jacobian matrix explicitly. We construct three different objective functions by taking the logarithm of the complex apparent resistivity as introduced in the recent waveform inversionmore » algorithm by Shin and Min. These objective functions can be naturally separated into amplitude inversion, phase inversion and simultaneous inversion. We demonstrate our algorithm by showing three inversion results for synthetic data.« less

Modified multiblock partial least squares path modeling algorithm with backpropagation neural networks approach

NASA Astrophysics Data System (ADS)

Yuniarto, Budi; Kurniawan, Robert

2017-03-01

PLS Path Modeling (PLS-PM) is different from covariance based SEM, where PLS-PM use an approach based on variance or component, therefore, PLS-PM is also known as a component based SEM. Multiblock Partial Least Squares (MBPLS) is a method in PLS regression which can be used in PLS Path Modeling which known as Multiblock PLS Path Modeling (MBPLS-PM). This method uses an iterative procedure in its algorithm. This research aims to modify MBPLS-PM with Back Propagation Neural Network approach. The result is MBPLS-PM algorithm can be modified using the Back Propagation Neural Network approach to replace the iterative process in backward and forward step to get the matrix t and the matrix u in the algorithm. By modifying the MBPLS-PM algorithm using Back Propagation Neural Network approach, the model parameters obtained are relatively not significantly different compared to model parameters obtained by original MBPLS-PM algorithm.

A Digital Liquid State Machine With Biologically Inspired Learning and Its Application to Speech Recognition.

PubMed

Zhang, Yong; Li, Peng; Jin, Yingyezhe; Choe, Yoonsuck

2015-11-01

This paper presents a bioinspired digital liquid-state machine (LSM) for low-power very-large-scale-integration (VLSI)-based machine learning applications. To the best of the authors' knowledge, this is the first work that employs a bioinspired spike-based learning algorithm for the LSM. With the proposed online learning, the LSM extracts information from input patterns on the fly without needing intermediate data storage as required in offline learning methods such as ridge regression. The proposed learning rule is local such that each synaptic weight update is based only upon the firing activities of the corresponding presynaptic and postsynaptic neurons without incurring global communications across the neural network. Compared with the backpropagation-based learning, the locality of computation in the proposed approach lends itself to efficient parallel VLSI implementation. We use subsets of the TI46 speech corpus to benchmark the bioinspired digital LSM. To reduce the complexity of the spiking neural network model without performance degradation for speech recognition, we study the impacts of synaptic models on the fading memory of the reservoir and hence the network performance. Moreover, we examine the tradeoffs between synaptic weight resolution, reservoir size, and recognition performance and present techniques to further reduce the overhead of hardware implementation. Our simulation results show that in terms of isolated word recognition evaluated using the TI46 speech corpus, the proposed digital LSM rivals the state-of-the-art hidden Markov-model-based recognizer Sphinx-4 and outperforms all other reported recognizers including the ones that are based upon the LSM or neural networks.

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

PubMed Central

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

2014-01-01

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

Spike-timing dependent inhibitory plasticity to learn a selective gating of backpropagating action potentials.

PubMed

Wilmes, Katharina Anna; Schleimer, Jan-Hendrik; Schreiber, Susanne

2017-04-01

Inhibition is known to influence the forward-directed flow of information within neurons. However, also regulation of backward-directed signals, such as backpropagating action potentials (bAPs), can enrich the functional repertoire of local circuits. Inhibitory control of bAP spread, for example, can provide a switch for the plasticity of excitatory synapses. Although such a mechanism is possible, it requires a precise timing of inhibition to annihilate bAPs without impairment of forward-directed excitatory information flow. Here, we propose a specific learning rule for inhibitory synapses to automatically generate the correct timing to gate bAPs in pyramidal cells when embedded in a local circuit of feedforward inhibition. Based on computational modeling of multi-compartmental neurons with physiological properties, we demonstrate that a learning rule with anti-Hebbian shape can establish the required temporal precision. In contrast to classical spike-timing dependent plasticity of excitatory synapses, the proposed inhibitory learning mechanism does not necessarily require the definition of an upper bound of synaptic weights because of its tendency to self-terminate once annihilation of bAPs has been reached. Our study provides a functional context in which one of the many time-dependent learning rules that have been observed experimentally - specifically, a learning rule with anti-Hebbian shape - is assigned a relevant role for inhibitory synapses. Moreover, the described mechanism is compatible with an upregulation of excitatory plasticity by disinhibition. © 2016 Federation of European Neuroscience Societies and John Wiley & Sons Ltd.

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.

Automatic analysis and classification of surface electromyography.

PubMed

Abou-Chadi, F E; Nashar, A; Saad, M

2001-01-01

In this paper, parametric modeling of surface electromyography (EMG) algorithms that facilitates automatic SEMG feature extraction and artificial neural networks (ANN) are combined for providing an integrated system for the automatic analysis and diagnosis of myopathic disorders. Three paradigms of ANN were investigated: the multilayer backpropagation algorithm, the self-organizing feature map algorithm and a probabilistic neural network model. The performance of the three classifiers was compared with that of the old Fisher linear discriminant (FLD) classifiers. The results have shown that the three ANN models give higher performance. The percentage of correct classification reaches 90%. Poorer diagnostic performance was obtained from the FLD classifier. The system presented here indicates that surface EMG, when properly processed, can be used to provide the physician with a diagnostic assist device.

Neural network based load and price forecasting and confidence interval estimation in deregulated power markets

NASA Astrophysics Data System (ADS)

Zhang, Li

With the deregulation of the electric power market in New England, an independent system operator (ISO) has been separated from the New England Power Pool (NEPOOL). The ISO provides a regional spot market, with bids on various electricity-related products and services submitted by utilities and independent power producers. A utility can bid on the spot market and buy or sell electricity via bilateral transactions. Good estimation of market clearing prices (MCP) will help utilities and independent power producers determine bidding and transaction strategies with low risks, and this is crucial for utilities to compete in the deregulated environment. MCP prediction, however, is difficult since bidding strategies used by participants are complicated and MCP is a non-stationary process. The main objective of this research is to provide efficient short-term load and MCP forecasting and corresponding confidence interval estimation methodologies. In this research, the complexity of load and MCP with other factors is investigated, and neural networks are used to model the complex relationship between input and output. With improved learning algorithm and on-line update features for load forecasting, a neural network based load forecaster was developed, and has been in daily industry use since summer 1998 with good performance. MCP is volatile because of the complexity of market behaviors. In practice, neural network based MCP predictors usually have a cascaded structure, as several key input factors need to be estimated first. In this research, the uncertainties involved in a cascaded neural network structure for MCP prediction are analyzed, and prediction distribution under the Bayesian framework is developed. A fast algorithm to evaluate the confidence intervals by using the memoryless Quasi-Newton method is also developed. The traditional back-propagation algorithm for neural network learning needs to be improved since MCP is a non-stationary process. The extended Kalman filter (EKF) can be used as an integrated adaptive learning and confidence interval estimation algorithm for neural networks, with fast convergence and small confidence intervals. However, EKF learning is computationally expensive because it involves high dimensional matrix manipulations. A modified U-D factorization within the decoupled EKF (DEKF-UD) framework is developed in this research. The computational efficiency and numerical stability are significantly improved.

An Expedient Study on Back-Propagation (BPN) Neural Networks for Modeling Automated Evaluation of the Answers and Progress of Deaf Students' That Possess Basic Knowledge of the English Language and Computer Skills

NASA Astrophysics Data System (ADS)

Vrettaros, John; Vouros, George; Drigas, Athanasios S.

This article studies the expediency of using neural networks technology and the development of back-propagation networks (BPN) models for modeling automated evaluation of the answers and progress of deaf students' that possess basic knowledge of the English language and computer skills, within a virtual e-learning environment. The performance of the developed neural models is evaluated with the correlation factor between the neural networks' response values and the real value data as well as the percentage measurement of the error between the neural networks' estimate values and the real value data during its training process and afterwards with unknown data that weren't used in the training process.

Gradient Optimization for Analytic conTrols - GOAT

NASA Astrophysics Data System (ADS)

Assémat, Elie; Machnes, Shai; Tannor, David; Wilhelm-Mauch, Frank

Quantum optimal control becomes a necessary step in a number of studies in the quantum realm. Recent experimental advances showed that superconducting qubits can be controlled with an impressive accuracy. However, most of the standard optimal control algorithms are not designed to manage such high accuracy. To tackle this issue, a novel quantum optimal control algorithm have been introduced: the Gradient Optimization for Analytic conTrols (GOAT). It avoids the piecewise constant approximation of the control pulse used by standard algorithms. This allows an efficient implementation of very high accuracy optimization. It also includes a novel method to compute the gradient that provides many advantages, e.g. the absence of backpropagation or the natural route to optimize the robustness of the control pulses. This talk will present the GOAT algorithm and a few applications to transmons systems.

A review and analysis of neural networks for classification of remotely sensed multispectral imagery

NASA Technical Reports Server (NTRS)

Paola, Justin D.; Schowengerdt, Robert A.

1993-01-01

A literature survey and analysis of the use of neural networks for the classification of remotely sensed multispectral imagery is presented. As part of a brief mathematical review, the backpropagation algorithm, which is the most common method of training multi-layer networks, is discussed with an emphasis on its application to pattern recognition. The analysis is divided into five aspects of neural network classification: (1) input data preprocessing, structure, and encoding; (2) output encoding and extraction of classes; (3) network architecture, (4) training algorithms; and (5) comparisons to conventional classifiers. The advantages of the neural network method over traditional classifiers are its non-parametric nature, arbitrary decision boundary capabilities, easy adaptation to different types of data and input structures, fuzzy output values that can enhance classification, and good generalization for use with multiple images. The disadvantages of the method are slow training time, inconsistent results due to random initial weights, and the requirement of obscure initialization values (e.g., learning rate and hidden layer size). Possible techniques for ameliorating these problems are discussed. It is concluded that, although the neural network method has several unique capabilities, it will become a useful tool in remote sensing only if it is made faster, more predictable, and easier to use.

Psycho-acoustic evaluation of the indoor noise in cabins of a naval vessel using a back-propagation neural network algorithm

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.

A conjugate gradients/trust regions algorithms for training multilayer perceptrons for nonlinear mapping

NASA Technical Reports Server (NTRS)

Madyastha, Raghavendra K.; Aazhang, Behnaam; Henson, Troy F.; Huxhold, Wendy L.

1992-01-01

This paper addresses the issue of applying a globally convergent optimization algorithm to the training of multilayer perceptrons, a class of Artificial Neural Networks. The multilayer perceptrons are trained towards the solution of two highly nonlinear problems: (1) signal detection in a multi-user communication network, and (2) solving the inverse kinematics for a robotic manipulator. The research is motivated by the fact that a multilayer perceptron is theoretically capable of approximating any nonlinear function to within a specified accuracy. The algorithm that has been employed in this study combines the merits of two well known optimization algorithms, the Conjugate Gradients and the Trust Regions Algorithms. The performance is compared to a widely used algorithm, the Backpropagation Algorithm, that is basically a gradient-based algorithm, and hence, slow in converging. The performances of the two algorithms are compared with the convergence rate. Furthermore, in the case of the signal detection problem, performances are also benchmarked by the decision boundaries drawn as well as the probability of error obtained in either case.

Optimal line drop compensation parameters under multi-operating conditions

NASA Astrophysics Data System (ADS)

Wan, Yuan; Li, Hang; Wang, Kai; He, Zhe

2017-01-01

Line Drop Compensation (LDC) is a main function of Reactive Current Compensation (RCC) which is developed to improve voltage stability. While LDC has benefit to voltage, it may deteriorate the small-disturbance rotor angle stability of power system. In present paper, an intelligent algorithm which is combined by Genetic Algorithm (GA) and Backpropagation Neural Network (BPNN) is proposed to optimize parameters of LDC. The objective function proposed in present paper takes consideration of voltage deviation and power system oscillation minimal damping ratio under multi-operating conditions. A simulation based on middle area of Jiangxi province power system is used to demonstrate the intelligent algorithm. The optimization result shows that coordinate optimized parameters can meet the multioperating conditions requirement and improve voltage stability as much as possible while guaranteeing enough damping ratio.

Synthesis of recurrent neural networks for dynamical system simulation.

PubMed

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. Copyright © 2016 Elsevier Ltd. All rights reserved.

Locally Bayesian Learning with Applications to Retrospective Revaluation and Highlighting

ERIC Educational Resources Information Center

Kruschke, John K.

2006-01-01

A scheme is described for locally Bayesian parameter updating in models structured as successions of component functions. The essential idea is to back-propagate the target data to interior modules, such that an interior component's target is the input to the next component that maximizes the probability of the next component's target. Each layer…

Elderly fall risk prediction based on a physiological profile approach using artificial neural networks.

PubMed

Razmara, Jafar; Zaboli, Mohammad Hassan; Hassankhani, Hadi

2016-11-01

Falls play a critical role in older people's life as it is an important source of morbidity and mortality in elders. In this article, elders fall risk is predicted based on a physiological profile approach using a multilayer neural network with back-propagation learning algorithm. The personal physiological profile of 200 elders was collected through a questionnaire and used as the experimental data for learning and testing the neural network. The profile contains a series of simple factors putting elders at risk for falls such as vision abilities, muscle forces, and some other daily activities and grouped into two sets: psychological factors and public factors. The experimental data were investigated to select factors with high impact using principal component analysis. The experimental results show an accuracy of ≈90 percent and ≈87.5 percent for fall prediction among the psychological and public factors, respectively. Furthermore, combining these two datasets yield an accuracy of ≈91 percent that is better than the accuracy of single datasets. The proposed method suggests a set of valid and reliable measurements that can be employed in a range of health care systems and physical therapy to distinguish people who are at risk for falls.

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

NASA Astrophysics Data System (ADS)

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

2015-10-01

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

A High Performance Computing Approach to Tree Cover Delineation in 1-m NAIP Imagery Using a Probabilistic Learning Framework

NASA Technical Reports Server (NTRS)

Basu, Saikat; Ganguly, Sangram; Michaelis, Andrew; Votava, Petr; Roy, Anshuman; Mukhopadhyay, Supratik; Nemani, Ramakrishna

2015-01-01

Tree cover delineation is a useful instrument in deriving Above Ground Biomass (AGB) density estimates from Very High Resolution (VHR) airborne imagery data. Numerous algorithms have been designed to address this problem, but most of them do not scale to these datasets, which are of the order of terabytes. In this paper, we present a semi-automated probabilistic framework for the segmentation and classification of 1-m National Agriculture Imagery Program (NAIP) for tree-cover delineation for the whole of Continental United States, using a High Performance Computing Architecture. Classification is performed using a multi-layer Feedforward Backpropagation Neural Network and segmentation is performed using a Statistical Region Merging algorithm. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on Conditional Random Field, which helps in capturing the higher order contextual dependencies between neighboring pixels. Once the final probability maps are generated, the framework is updated and re-trained by relabeling misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates. The tree cover maps were generated for the whole state of California, spanning a total of 11,095 NAIP tiles covering a total geographical area of 163,696 sq. miles. The framework produced true positive rates of around 88% for fragmented forests and 74% for urban tree cover areas, with false positive rates lower than 2% for both landscapes. Comparative studies with the National Land Cover Data (NLCD) algorithm and the LiDAR canopy height model (CHM) showed the effectiveness of our framework for generating accurate high-resolution tree-cover maps.

A High Performance Computing Approach to Tree Cover Delineation in 1-m NAIP Imagery using a Probabilistic Learning Framework

NASA Astrophysics Data System (ADS)

Basu, S.; Ganguly, S.; Michaelis, A.; Votava, P.; Roy, A.; Mukhopadhyay, S.; Nemani, R. R.

2015-12-01

Tree cover delineation is a useful instrument in deriving Above Ground Biomass (AGB) density estimates from Very High Resolution (VHR) airborne imagery data. Numerous algorithms have been designed to address this problem, but most of them do not scale to these datasets which are of the order of terabytes. In this paper, we present a semi-automated probabilistic framework for the segmentation and classification of 1-m National Agriculture Imagery Program (NAIP) for tree-cover delineation for the whole of Continental United States, using a High Performance Computing Architecture. Classification is performed using a multi-layer Feedforward Backpropagation Neural Network and segmentation is performed using a Statistical Region Merging algorithm. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on Conditional Random Field, which helps in capturing the higher order contextual dependencies between neighboring pixels. Once the final probability maps are generated, the framework is updated and re-trained by relabeling misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates. The tree cover maps were generated for the whole state of California, spanning a total of 11,095 NAIP tiles covering a total geographical area of 163,696 sq. miles. The framework produced true positive rates of around 88% for fragmented forests and 74% for urban tree cover areas, with false positive rates lower than 2% for both landscapes. Comparative studies with the National Land Cover Data (NLCD) algorithm and the LiDAR canopy height model (CHM) showed the effectiveness of our framework for generating accurate high-resolution tree-cover maps.

Deep learning in the small sample size setting: cascaded feed forward neural networks for medical image segmentation

NASA Astrophysics Data System (ADS)

Gaonkar, Bilwaj; Hovda, David; Martin, Neil; Macyszyn, Luke

2016-03-01

Deep Learning, refers to large set of neural network based algorithms, have emerged as promising machine- learning tools in the general imaging and computer vision domains. Convolutional neural networks (CNNs), a specific class of deep learning algorithms, have been extremely effective in object recognition and localization in natural images. A characteristic feature of CNNs, is the use of a locally connected multi layer topology that is inspired by the animal visual cortex (the most powerful vision system in existence). While CNNs, perform admirably in object identification and localization tasks, typically require training on extremely large datasets. Unfortunately, in medical image analysis, large datasets are either unavailable or are extremely expensive to obtain. Further, the primary tasks in medical imaging are organ identification and segmentation from 3D scans, which are different from the standard computer vision tasks of object recognition. Thus, in order to translate the advantages of deep learning to medical image analysis, there is a need to develop deep network topologies and training methodologies, that are geared towards medical imaging related tasks and can work in a setting where dataset sizes are relatively small. In this paper, we present a technique for stacked supervised training of deep feed forward neural networks for segmenting organs from medical scans. Each `neural network layer' in the stack is trained to identify a sub region of the original image, that contains the organ of interest. By layering several such stacks together a very deep neural network is constructed. Such a network can be used to identify extremely small regions of interest in extremely large images, inspite of a lack of clear contrast in the signal or easily identifiable shape characteristics. What is even more intriguing is that the network stack achieves accurate segmentation even when it is trained on a single image with manually labelled ground truth. We validate this approach,using a publicly available head and neck CT dataset. We also show that a deep neural network of similar depth, if trained directly using backpropagation, cannot acheive the tasks achieved using our layer wise training paradigm.

An Emotional ANN (EANN) approach to modeling rainfall-runoff process

NASA Astrophysics Data System (ADS)

Nourani, Vahid

2017-01-01

This paper presents the first hydrological implementation of Emotional Artificial Neural Network (EANN), as a new generation of Artificial Intelligence-based models for daily rainfall-runoff (r-r) modeling of the watersheds. Inspired by neurophysiological form of brain, in addition to conventional weights and bias, an EANN includes simulated emotional parameters aimed at improving the network learning process. EANN trained by a modified version of back-propagation (BP) algorithm was applied to single and multi-step-ahead runoff forecasting of two watersheds with two distinct climatic conditions. Also to evaluate the ability of EANN trained by smaller training data set, three data division strategies with different number of training samples were considered for the training purpose. The overall comparison of the obtained results of the r-r modeling indicates that the EANN could outperform the conventional feed forward neural network (FFNN) model up to 13% and 34% in terms of training and verification efficiency criteria, respectively. The superiority of EANN over classic ANN is due to its ability to recognize and distinguish dry (rainless days) and wet (rainy days) situations using hormonal parameters of the artificial emotional system.

Texture classification of lung computed tomography images

NASA Astrophysics Data System (ADS)

Pheng, Hang See; Shamsuddin, Siti M.

2013-03-01

Current development of algorithms in computer-aided diagnosis (CAD) scheme is growing rapidly to assist the radiologist in medical image interpretation. Texture analysis of computed tomography (CT) scans is one of important preliminary stage in the computerized detection system and classification for lung cancer. Among different types of images features analysis, Haralick texture with variety of statistical measures has been used widely in image texture description. The extraction of texture feature values is essential to be used by a CAD especially in classification of the normal and abnormal tissue on the cross sectional CT images. This paper aims to compare experimental results using texture extraction and different machine leaning methods in the classification normal and abnormal tissues through lung CT images. The machine learning methods involve in this assessment are Artificial Immune Recognition System (AIRS), Naive Bayes, Decision Tree (J48) and Backpropagation Neural Network. AIRS is found to provide high accuracy (99.2%) and sensitivity (98.0%) in the assessment. For experiments and testing purpose, publicly available datasets in the Reference Image Database to Evaluate Therapy Response (RIDER) are used as study cases.

Bluetooth gas sensing module combined with smartphones for air quality monitoring.

PubMed

Suárez, José Ignacio; Arroyo, Patricia; Lozano, Jesús; Herrero, José Luis; Padilla, Manuel

2018-08-01

This study addresses the development of a miniaturized (60 × 60 mm) Wireless Sensing Module (WSM) for environmental application and air quality detection. The proposed prototype has six sensors: one for humidity, one for ambient temperature (SHT21 from Sensirion), and four for gas detection (MiCS-4514, MiCS-5526 and MiCS-5914 from SGX Sensortech). The core of the system is based on a high performance 8-bit microcontroller, model PIC18F46K80, from Microchip. The obtained data values were transmitted to the Smartphone through a Bluetooth communication module and a home-developed Android app. The discrimination capability of the module is tested with 10 volatile organic compounds (acetone, acetic acid, benzene, ethanol, ethyl acetate, ethylbenzene, formaldehyde, toluene, xylene, and dimethylacetamide) and the effect of humidity and drift of the sensors is also studied. Results show that 88.33% and 92.22% success rates in classification stage are obtained using Multilayer Perceptron with BackPropagation Learning algorithm and Radial-Basis based Neural Networks, respectively. Copyright © 2018 Elsevier Ltd. All rights reserved.

Application of Chitosan-Zinc Oxide Nanoparticles for Lead Extraction From Water Samples by Combining Ant Colony Optimization with Artificial Neural Network

NASA Astrophysics Data System (ADS)

Khajeh, M.; Pourkarami, A.; Arefnejad, E.; Bohlooli, M.; Khatibi, A.; Ghaffari-Moghaddam, M.; Zareian-Jahromi, S.

2017-09-01

Chitosan-zinc oxide nanoparticles (CZPs) were developed for solid-phase extraction. Combined artificial neural network-ant colony optimization (ANN-ACO) was used for the simultaneous preconcentration and determination of lead (Pb2+) ions in water samples prior to graphite furnace atomic absorption spectrometry (GF AAS). The solution pH, mass of adsorbent CZPs, amount of 1-(2-pyridylazo)-2-naphthol (PAN), which was used as a complexing agent, eluent volume, eluent concentration, and flow rates of sample and eluent were used as input parameters of the ANN model, and the percentage of extracted Pb2+ ions was used as the output variable of the model. A multilayer perception network with a back-propagation learning algorithm was used to fit the experimental data. The optimum conditions were obtained based on the ACO. Under the optimized conditions, the limit of detection for Pb2+ ions was found to be 0.078 μg/L. This procedure was also successfully used to determine the amounts of Pb2+ ions in various natural water samples.

Heart murmur detection based on wavelet transformation and a synergy between artificial neural network and modified neighbor annealing methods.

PubMed

Eslamizadeh, Gholamhossein; Barati, Ramin

2017-05-01

Early recognition of heart disease plays a vital role in saving lives. Heart murmurs are one of the common heart problems. In this study, Artificial Neural Network (ANN) is trained with Modified Neighbor Annealing (MNA) to classify heart cycles into normal and murmur classes. Heart cycles are separated from heart sounds using wavelet transformer. The network inputs are features extracted from individual heart cycles, and two classification outputs. Classification accuracy of the proposed model is compared with five multilayer perceptron trained with Levenberg-Marquardt, Extreme-learning-machine, back-propagation, simulated-annealing, and neighbor-annealing algorithms. It is also compared with a Self-Organizing Map (SOM) ANN. The proposed model is trained and tested using real heart sounds available in the Pascal database to show the applicability of the proposed scheme. Also, a device to record real heart sounds has been developed and used for comparison purposes too. Based on the results of this study, MNA can be used to produce considerable results as a heart cycle classifier. Copyright © 2017 Elsevier B.V. All rights reserved.

A Recurrent Probabilistic Neural Network with Dimensionality Reduction Based on Time-series Discriminant Component Analysis.

PubMed

Hayashi, Hideaki; Shibanoki, Taro; Shima, Keisuke; Kurita, Yuichi; Tsuji, Toshio

2015-12-01

This paper proposes a probabilistic neural network (NN) developed on the basis of time-series discriminant component analysis (TSDCA) that can be used to classify high-dimensional time-series patterns. TSDCA involves the compression of high-dimensional time series into a lower dimensional space using a set of orthogonal transformations and the calculation of posterior probabilities based on a continuous-density hidden Markov model with a Gaussian mixture model expressed in the reduced-dimensional space. The analysis can be incorporated into an NN, which is named a time-series discriminant component network (TSDCN), so that parameters of dimensionality reduction and classification can be obtained simultaneously as network coefficients according to a backpropagation through time-based learning algorithm with the Lagrange multiplier method. The TSDCN is considered to enable high-accuracy classification of high-dimensional time-series patterns and to reduce the computation time taken for network training. The validity of the TSDCN is demonstrated for high-dimensional artificial data and electroencephalogram signals in the experiments conducted during the study.

Non-invasive algorithm for bowel motility estimation using a back-propagation neural network model of bowel sounds.

PubMed

Kim, Keo-Sik; Seo, Jeong-Hwan; Song, Chul-Gyu

2011-08-10

Radiological scoring methods such as colon transit time (CTT) have been widely used for the assessment of bowel motility. However, these radiograph-based methods need cumbersome radiological instruments and their frequent exposure to radiation. Therefore, a non-invasive estimation algorithm of bowel motility, based on a back-propagation neural network (BPNN) model of bowel sounds (BS) obtained by an auscultation, was devised. Twelve healthy males (age: 24.8 ± 2.7 years) and 6 patients with spinal cord injury (6 males, age: 55.3 ± 7.1 years) were examined. BS signals generated during the digestive process were recorded from 3 colonic segments (ascending, descending and sigmoid colon), and then, the acoustical features (jitter and shimmer) of the individual BS segment were obtained. Only 6 features (J1, 3, J3, 3, S1, 2, S2, 1, S2, 2, S3, 2), which are highly correlated to the CTTs measured by the conventional method, were used as the features of the input vector for the BPNN. As a results, both the jitters and shimmers of the normal subjects were relatively higher than those of the patients, whereas the CTTs of the normal subjects were relatively lower than those of the patients (p < 0.01). Also, through k-fold cross validation, the correlation coefficient and mean average error between the CTTs measured by a conventional radiograph and the values estimated by our algorithm were 0.89 and 10.6 hours, respectively. The jitter and shimmer of the BS signals generated during the peristalsis could be clinically useful for the discriminative parameters of bowel motility. Also, the devised algorithm showed good potential for the continuous monitoring and estimation of bowel motility, instead of conventional radiography, and thus, it could be used as a complementary tool for the non-invasive measurement of bowel motility.

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

PubMed

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

2018-01-01

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

Multiscale Methods, Parallel Computation, and Neural Networks for Real-Time Computer Vision.

NASA Astrophysics Data System (ADS)

Battiti, Roberto

1990-01-01

This thesis presents new algorithms for low and intermediate level computer vision. The guiding ideas in the presented approach are those of hierarchical and adaptive processing, concurrent computation, and supervised learning. Processing of the visual data at different resolutions is used not only to reduce the amount of computation necessary to reach the fixed point, but also to produce a more accurate estimation of the desired parameters. The presented adaptive multiple scale technique is applied to the problem of motion field estimation. Different parts of the image are analyzed at a resolution that is chosen in order to minimize the error in the coefficients of the differential equations to be solved. Tests with video-acquired images show that velocity estimation is more accurate over a wide range of motion with respect to the homogeneous scheme. In some cases introduction of explicit discontinuities coupled to the continuous variables can be used to avoid propagation of visual information from areas corresponding to objects with different physical and/or kinematic properties. The human visual system uses concurrent computation in order to process the vast amount of visual data in "real -time." Although with different technological constraints, parallel computation can be used efficiently for computer vision. All the presented algorithms have been implemented on medium grain distributed memory multicomputers with a speed-up approximately proportional to the number of processors used. A simple two-dimensional domain decomposition assigns regions of the multiresolution pyramid to the different processors. The inter-processor communication needed during the solution process is proportional to the linear dimension of the assigned domain, so that efficiency is close to 100% if a large region is assigned to each processor. Finally, learning algorithms are shown to be a viable technique to engineer computer vision systems for different applications starting from multiple-purpose modules. In the last part of the thesis a well known optimization method (the Broyden-Fletcher-Goldfarb-Shanno memoryless quasi -Newton method) is applied to simple classification problems and shown to be superior to the "error back-propagation" algorithm for numerical stability, automatic selection of parameters, and convergence properties.

Intelligent condition monitoring method for bearing faults from highly compressed measurements using sparse over-complete features

NASA Astrophysics Data System (ADS)

Ahmed, H. O. A.; Wong, M. L. D.; Nandi, A. K.

2018-01-01

Condition classification of rolling element bearings in rotating machines is important to prevent the breakdown of industrial machinery. A considerable amount of literature has been published on bearing faults classification. These studies aim to determine automatically the current status of a roller element bearing. Of these studies, methods based on compressed sensing (CS) have received some attention recently due to their ability to allow one to sample below the Nyquist sampling rate. This technology has many possible uses in machine condition monitoring and has been investigated as a possible approach for fault detection and classification in the compressed domain, i.e., without reconstructing the original signal. However, previous CS based methods have been found to be too weak for highly compressed data. The present paper explores computationally, for the first time, the effects of sparse autoencoder based over-complete sparse representations on the classification performance of highly compressed measurements of bearing vibration signals. For this study, the CS method was used to produce highly compressed measurements of the original bearing dataset. Then, an effective deep neural network (DNN) with unsupervised feature learning algorithm based on sparse autoencoder is used for learning over-complete sparse representations of these compressed datasets. Finally, the fault classification is achieved using two stages, namely, pre-training classification based on stacked autoencoder and softmax regression layer form the deep net stage (the first stage), and re-training classification based on backpropagation (BP) algorithm forms the fine-tuning stage (the second stage). The experimental results show that the proposed method is able to achieve high levels of accuracy even with extremely compressed measurements compared with the existing techniques.

Flow rate of some pharmaceutical diluents through die-orifices relevant to mini-tableting.

PubMed

Kachrimanis, K; Petrides, M; Malamataris, S

2005-10-13

The effects of cylindrical orifice length and diameter on the flow rate of three commonly used pharmaceutical direct compression diluents (lactose, dibasic calcium phosphate dihydrate and pregelatinised starch) were investigated, besides the powder particle characteristics (particle size, aspect ratio, roundness and convexity) and the packing properties (true, bulk and tapped density). Flow rate was determined for three different sieve fractions through a series of miniature tableting dies of different orifice diameter (0.4, 0.3 and 0.2 cm) and thickness (1.5, 1.0 and 0.5 cm). It was found that flow rate decreased with the increase of the orifice length for the small diameter (0.2 cm) but for the large diameter (0.4 cm) was increased with the orifice length (die thickness). Flow rate changes with the orifice length are attributed to the flow regime (transitional arch formation) and possible alterations in the position of the free flowing zone caused by pressure gradients arising from the flow of self-entrained air, both above the entrance in the die orifice and across it. Modelling by the conventional Jones-Pilpel non-linear equation and by two machine learning algorithms (lazy learning, LL, and feed-forward back-propagation, FBP) was applied and predictive performance of the fitted models was compared. It was found that both FBP and LL algorithms have significantly higher predictive performance than the Jones-Pilpel non-linear equation, because they account both dimensions of the cylindrical die opening (diameter and length). The automatic relevance determination for FBP revealed that orifice length is the third most influential variable after the orifice diameter and particle size, followed by the bulk density, the difference between bulk and tapped densities and the particle convexity.

A fast automatic recognition and location algorithm for fetal genital organs in ultrasound images.

PubMed

Tang, Sheng; Chen, Si-ping

2009-09-01

Severe sex ratio imbalance at birth is now becoming an important issue in several Asian countries. Its leading immediate cause is prenatal sex-selective abortion following illegal sex identification by ultrasound scanning. In this paper, a fast automatic recognition and location algorithm for fetal genital organs is proposed as an effective method to help prevent ultrasound technicians from unethically and illegally identifying the sex of the fetus. This automatic recognition algorithm can be divided into two stages. In the 'rough' stage, a few pixels in the image, which are likely to represent the genital organs, are automatically chosen as points of interest (POIs) according to certain salient characteristics of fetal genital organs. In the 'fine' stage, a specifically supervised learning framework, which fuses an effective feature data preprocessing mechanism into the multiple classifier architecture, is applied to every POI. The basic classifiers in the framework are selected from three widely used classifiers: radial basis function network, backpropagation network, and support vector machine. The classification results of all the POIs are then synthesized to determine whether the fetal genital organ is present in the image, and to locate the genital organ within the positive image. Experiments were designed and carried out based on an image dataset comprising 658 positive images (images with fetal genital organs) and 500 negative images (images without fetal genital organs). The experimental results showed true positive (TP) and true negative (TN) results from 80.5% (265 from 329) and 83.0% (415 from 500) of samples, respectively. The average computation time was 453 ms per image.

Good Features to Correlate for Visual Tracking

NASA Astrophysics Data System (ADS)

Gundogdu, Erhan; Alatan, A. Aydin

2018-05-01

During the recent years, correlation filters have shown dominant and spectacular results for visual object tracking. The types of the features that are employed in these family of trackers significantly affect the performance of visual tracking. The ultimate goal is to utilize robust features invariant to any kind of appearance change of the object, while predicting the object location as properly as in the case of no appearance change. As the deep learning based methods have emerged, the study of learning features for specific tasks has accelerated. For instance, discriminative visual tracking methods based on deep architectures have been studied with promising performance. Nevertheless, correlation filter based (CFB) trackers confine themselves to use the pre-trained networks which are trained for object classification problem. To this end, in this manuscript the problem of learning deep fully convolutional features for the CFB visual tracking is formulated. In order to learn the proposed model, a novel and efficient backpropagation algorithm is presented based on the loss function of the network. The proposed learning framework enables the network model to be flexible for a custom design. Moreover, it alleviates the dependency on the network trained for classification. Extensive performance analysis shows the efficacy of the proposed custom design in the CFB tracking framework. By fine-tuning the convolutional parts of a state-of-the-art network and integrating this model to a CFB tracker, which is the top performing one of VOT2016, 18% increase is achieved in terms of expected average overlap, and tracking failures are decreased by 25%, while maintaining the superiority over the state-of-the-art methods in OTB-2013 and OTB-2015 tracking datasets.

Neural network recognition of chemical class information in mobility spectra obtained at high temperatures

NASA Technical Reports Server (NTRS)

Bell, S.; Nazarov, E.; Wang, Y. F.; Rodriguez, J. E.; Eiceman, G. A.

2000-01-01

A minimal neural network was applied to a large library of high-temperature mobility spectra drawn from 16 chemical classes including 154 substances with 2000 spectra at various concentrations. A genetic algorithm was used to create a representative subset of points from the mobility spectrum as input to a cascade-type back-propagation network. This network demonstrated that significant information specific to chemical class was located in the spectral region near the reactant ions. This network failed to generalize the solution to unfamiliar compounds necessitating the use of complete spectra in network processing. An extended back-propagation network classified unfamiliar chemicals by functional group with a mean for average values of 0.83 without sulfides and 0.79 with sulfides. Further experiments confirmed that chemical class information was resident in the spectral region near the reactant ions. Deconvolution of spectra demonstrated the presence of ions, merged with the reactant ion peaks that originated from introduced samples. The ability of the neural network to generalize the solution to unfamiliar compounds suggests that these ions are distinct and class specific.

Prediction of Contact Fatigue Life of Alloy Cast Steel Rolls Using Back-Propagation Neural Network

NASA Astrophysics Data System (ADS)

Jin, Huijin; Wu, Sujun; Peng, Yuncheng

2013-12-01

In this study, an artificial neural network (ANN) was employed to predict the contact fatigue life of alloy cast steel rolls (ACSRs) as a function of alloy composition, heat treatment parameters, and contact stress by utilizing the back-propagation algorithm. The ANN was trained and tested using experimental data and a very good performance of the neural network was achieved. The well-trained neural network was then adopted to predict the contact fatigue life of chromium alloyed cast steel rolls with different alloy compositions and heat treatment processes. The prediction results showed that the maximum value of contact fatigue life was obtained with quenching at 960 °C, tempering at 520 °C, and under the contact stress of 2355 MPa. The optimal alloy composition was C-0.54, Si-0.66, Mn-0.67, Cr-4.74, Mo-0.46, V-0.13, Ni-0.34, and Fe-balance (wt.%). Some explanations of the predicted results from the metallurgical viewpoints are given. A convenient and powerful method of optimizing alloy composition and heat treatment parameters of ACSRs has been developed.

Typing SNP based on the near-infrared spectroscopy and artificial neural network

NASA Astrophysics Data System (ADS)

Ren, Li; Wang, Wei-Peng; Gao, Yu-Zhen; Yu, Xiao-Wei; Xie, Hong-Ping

2009-07-01

Based on the near-infrared spectra (NIRS) of the measured samples as the discriminant variables of their genotypes, the genotype discriminant model of SNP has been established by using back-propagation artificial neural network (BP-ANN). Taking a SNP (857G > A) of N-acetyltransferase 2 (NAT2) as an example, DNA fragments containing the SNP site were amplified by the PCR method based on a pair of primers to obtain the three-genotype (GG, AA, and GA) modeling samples. The NIRS-s of the amplified samples were directly measured in transmission by using quartz cell. Based on the sample spectra measured, the two BP-ANN-s were combined to obtain the stronger ability of the three-genotype classification. One of them was established to compress the measured NIRS variables by using the resilient back-propagation algorithm, and another network established by Levenberg-Marquardt algorithm according to the compressed NIRS-s was used as the discriminant model of the three-genotype classification. For the established model, the root mean square error for the training and the prediction sample sets were 0.0135 and 0.0132, respectively. Certainly, this model could rightly predict the three genotypes (i.e. the accuracy of prediction samples was up to100%) and had a good robust for the prediction of unknown samples. Since the three genotypes of SNP could be directly determined by using the NIRS-s without any preprocessing for the analyzed samples after PCR, this method is simple, rapid and low-cost.

Vehicle Classification Using an Imbalanced Dataset Based on a Single Magnetic Sensor.

PubMed

Xu, Chang; Wang, Yingguan; Bao, Xinghe; Li, Fengrong

2018-05-24

This paper aims to improve the accuracy of automatic vehicle classifiers for imbalanced datasets. Classification is made through utilizing a single anisotropic magnetoresistive sensor, with the models of vehicles involved being classified into hatchbacks, sedans, buses, and multi-purpose vehicles (MPVs). Using time domain and frequency domain features in combination with three common classification algorithms in pattern recognition, we develop a novel feature extraction method for vehicle classification. These three common classification algorithms are the k-nearest neighbor, the support vector machine, and the back-propagation neural network. Nevertheless, a problem remains with the original vehicle magnetic dataset collected being imbalanced, and may lead to inaccurate classification results. With this in mind, we propose an approach called SMOTE, which can further boost the performance of classifiers. Experimental results show that the k-nearest neighbor (KNN) classifier with the SMOTE algorithm can reach a classification accuracy of 95.46%, thus minimizing the effect of the imbalance.

Sea ice classification using fast learning neural networks

NASA Technical Reports Server (NTRS)

Dawson, M. S.; Fung, A. K.; Manry, M. T.

1992-01-01

A first learning neural network approach to the classification of sea ice is presented. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) were tested on simulated data sets based on the known dominant scattering characteristics of the target class. Four classes were used in the data simulation: open water, thick lossy saline ice, thin saline ice, and multiyear ice. The BP network was unable to consistently converge to less than 25 percent error while the FL method yielded an average error of approximately 1 percent on the first iteration of training. The fast learning method presented can significantly reduce the CPU time necessary to train a neural network as well as consistently yield higher classification accuracy than BP networks.

Novel Screening Tool for Stroke Using Artificial Neural Network.

PubMed

Abedi, Vida; Goyal, Nitin; Tsivgoulis, Georgios; Hosseinichimeh, Niyousha; Hontecillas, Raquel; Bassaganya-Riera, Josep; Elijovich, Lucas; Metter, Jeffrey E; Alexandrov, Anne W; Liebeskind, David S; Alexandrov, Andrei V; Zand, Ramin

2017-06-01

The timely diagnosis of stroke at the initial examination is extremely important given the disease morbidity and narrow time window for intervention. The goal of this study was to develop a supervised learning method to recognize acute cerebral ischemia (ACI) and differentiate that from stroke mimics in an emergency setting. Consecutive patients presenting to the emergency department with stroke-like symptoms, within 4.5 hours of symptoms onset, in 2 tertiary care stroke centers were randomized for inclusion in the model. We developed an artificial neural network (ANN) model. The learning algorithm was based on backpropagation. To validate the model, we used a 10-fold cross-validation method. A total of 260 patients (equal number of stroke mimics and ACIs) were enrolled for the development and validation of our ANN model. Our analysis indicated that the average sensitivity and specificity of ANN for the diagnosis of ACI based on the 10-fold cross-validation analysis was 80.0% (95% confidence interval, 71.8-86.3) and 86.2% (95% confidence interval, 78.7-91.4), respectively. The median precision of ANN for the diagnosis of ACI was 92% (95% confidence interval, 88.7-95.3). Our results show that ANN can be an effective tool for the recognition of ACI and differentiation of ACI from stroke mimics at the initial examination. © 2017 American Heart Association, Inc.

Forecasting the mortality rates of Indonesian population by using neural network

NASA Astrophysics Data System (ADS)

Safitri, Lutfiani; Mardiyati, Sri; Rahim, Hendrisman

2018-03-01

A model that can represent a problem is required in conducting a forecasting. One of the models that has been acknowledged by the actuary community in forecasting mortality rate is the Lee-Certer model. Lee Carter model supported by Neural Network will be used to calculate mortality forecasting in Indonesia. The type of Neural Network used is feedforward neural network aligned with backpropagation algorithm in python programming language. And the final result of this study is mortality rate in forecasting Indonesia for the next few years

A knowledge-base generating hierarchical fuzzy-neural controller.

PubMed

Kandadai, R M; Tien, J M

1997-01-01

We present an innovative fuzzy-neural architecture that is able to automatically generate a knowledge base, in an extractable form, for use in hierarchical knowledge-based controllers. The knowledge base is in the form of a linguistic rule base appropriate for a fuzzy inference system. First, we modify Berenji and Khedkar's (1992) GARIC architecture to enable it to automatically generate a knowledge base; a pseudosupervised learning scheme using reinforcement learning and error backpropagation is employed. Next, we further extend this architecture to a hierarchical controller that is able to generate its own knowledge base. Example applications are provided to underscore its viability.

Sensorless control for permanent magnet synchronous motor using a neural network based adaptive estimator

NASA Astrophysics Data System (ADS)

Kwon, Chung-Jin; Kim, Sung-Joong; Han, Woo-Young; Min, Won-Kyoung

2005-12-01

The rotor position and speed estimation of permanent-magnet synchronous motor(PMSM) was dealt with. By measuring the phase voltages and currents of the PMSM drive, two diagonally recurrent neural network(DRNN) based observers, a neural current observer and a neural velocity observer were developed. DRNN which has self-feedback of the hidden neurons ensures that the outputs of DRNN contain the whole past information of the system even if the inputs of DRNN are only the present states and inputs of the system. Thus the structure of DRNN may be simpler than that of feedforward and fully recurrent neural networks. If the backpropagation method was used for the training of the DRNN the problem of slow convergence arise. In order to reduce this problem, recursive prediction error(RPE) based learning method for the DRNN was presented. The simulation results show that the proposed approach gives a good estimation of rotor speed and position, and RPE based training has requires a shorter computation time compared to backpropagation based training.

A Novel Machine Vision System for the Inspection of Micro-Spray Nozzle

PubMed Central

Huang, Kuo-Yi; Ye, Yu-Ting

2015-01-01

In this study, we present an application of neural network and image processing techniques for detecting the defects of an internal micro-spray nozzle. The defect regions were segmented by Canny edge detection, a randomized algorithm for detecting circles and a circle inspection (CI) algorithm. The gray level co-occurrence matrix (GLCM) was further used to evaluate the texture features of the segmented region. These texture features (contrast, entropy, energy), color features (mean and variance of gray level) and geometric features (distance variance, mean diameter and diameter ratio) were used in the classification procedures. A back-propagation neural network classifier was employed to detect the defects of micro-spray nozzles. The methodology presented herein effectively works for detecting micro-spray nozzle defects to an accuracy of 90.71%. PMID:26131678

A Novel Machine Vision System for the Inspection of Micro-Spray Nozzle.

PubMed

Huang, Kuo-Yi; Ye, Yu-Ting

2015-06-29

In this study, we present an application of neural network and image processing techniques for detecting the defects of an internal micro-spray nozzle. The defect regions were segmented by Canny edge detection, a randomized algorithm for detecting circles and a circle inspection (CI) algorithm. The gray level co-occurrence matrix (GLCM) was further used to evaluate the texture features of the segmented region. These texture features (contrast, entropy, energy), color features (mean and variance of gray level) and geometric features (distance variance, mean diameter and diameter ratio) were used in the classification procedures. A back-propagation neural network classifier was employed to detect the defects of micro-spray nozzles. The methodology presented herein effectively works for detecting micro-spray nozzle defects to an accuracy of 90.71%.

Target recognition of ladar range images using slice image: comparison of four improved algorithms

NASA Astrophysics Data System (ADS)

Xia, Wenze; Han, Shaokun; Cao, Jingya; Wang, Liang; Zhai, Yu; Cheng, Yang

2017-07-01

Compared with traditional 3-D shape data, ladar range images possess properties of strong noise, shape degeneracy, and sparsity, which make feature extraction and representation difficult. The slice image is an effective feature descriptor to resolve this problem. We propose four improved algorithms on target recognition of ladar range images using slice image. In order to improve resolution invariance of the slice image, mean value detection instead of maximum value detection is applied in these four improved algorithms. In order to improve rotation invariance of the slice image, three new improved feature descriptors-which are feature slice image, slice-Zernike moments, and slice-Fourier moments-are applied to the last three improved algorithms, respectively. Backpropagation neural networks are used as feature classifiers in the last two improved algorithms. The performance of these four improved recognition systems is analyzed comprehensively in the aspects of the three invariances, recognition rate, and execution time. The final experiment results show that the improvements for these four algorithms reach the desired effect, the three invariances of feature descriptors are not directly related to the final recognition performance of recognition systems, and these four improved recognition systems have different performances under different conditions.

Quantifying the Evolution of Melt Ponds in the Marginal Ice Zone Using High Resolution Optical Imagery and Neural Networks

NASA Astrophysics Data System (ADS)

Ortiz, M.; Pinales, J. C.; Graber, H. C.; Wilkinson, J.; Lund, B.

2016-02-01

Melt ponds on sea ice play a significant and complex role on the thermodynamics in the Marginal Ice Zone (MIZ). Ponding reduces the sea ice's ability to reflect sunlight, and in consequence, exacerbates the albedo positive feedback cycle. In order to understand how melt ponds work and their effect on the heat uptake of sea ice, we must quantify ponds through their seasonal evolution first. A semi-supervised neural network three-class learning scheme using a gradient descent with momentum and adaptive learning rate backpropagation function is applied to classify melt ponds/melt areas in the Beaufort Sea region. The network uses high resolution panchromatic satellite images from the MEDEA program, which are collocated with autonomous platform arrays from the Marginal Ice Zone Program, including ice mass-balance buoys, arctic weather stations and wave buoys. The goal of the study is to capture the spatial variation of melt onset and freeze-up of the ponds within the MIZ, and gather ponding statistics such as size and concentration. The innovation of this work comes from training the neural network as the melt ponds evolve over time; making the machine learning algorithm time-dependent, which has not been previously done. We will achieve this by analyzing the image histograms through quantification of the minima and maxima intensity changes as well as linking textural variation information of the imagery. We will compare the evolution of the melt ponds against several different array sites on the sea ice to explore if there are spatial differences among the separated platforms in the MIZ.

Deep Direct Reinforcement Learning for Financial Signal Representation and Trading.

PubMed

Deng, Yue; Bao, Feng; Kong, Youyong; Ren, Zhiquan; Dai, Qionghai

2017-03-01

Can we train the computer to beat experienced traders for financial assert trading? In this paper, we try to address this challenge by introducing a recurrent deep neural network (NN) for real-time financial signal representation and trading. Our model is inspired by two biological-related learning concepts of deep learning (DL) and reinforcement learning (RL). In the framework, the DL part automatically senses the dynamic market condition for informative feature learning. Then, the RL module interacts with deep representations and makes trading decisions to accumulate the ultimate rewards in an unknown environment. The learning system is implemented in a complex NN that exhibits both the deep and recurrent structures. Hence, we propose a task-aware backpropagation through time method to cope with the gradient vanishing issue in deep training. The robustness of the neural system is verified on both the stock and the commodity future markets under broad testing conditions.

Prediction of the Vickers Microhardness and Ultimate Tensile Strength of AA5754 H111 Friction Stir Welding Butt Joints Using Artificial Neural Network.

PubMed

De Filippis, Luigi Alberto Ciro; Serio, Livia Maria; Facchini, Francesco; Mummolo, Giovanni; Ludovico, Antonio Domenico

2016-11-10

A simulation model was developed for the monitoring, controlling and optimization of the Friction Stir Welding (FSW) process. This approach, using the FSW technique, allows identifying the correlation between the process parameters (input variable) and the mechanical properties (output responses) of the welded AA5754 H111 aluminum plates. The optimization of technological parameters is a basic requirement for increasing the seam quality, since it promotes a stable and defect-free process. Both the tool rotation and the travel speed, the position of the samples extracted from the weld bead and the thermal data, detected with thermographic techniques for on-line control of the joints, were varied to build the experimental plans. The quality of joints was evaluated through destructive and non-destructive tests (visual tests, macro graphic analysis, tensile tests, indentation Vickers hardness tests and t thermographic controls). The simulation model was based on the adoption of the Artificial Neural Networks (ANNs) characterized by back-propagation learning algorithm with different types of architecture, which were able to predict with good reliability the FSW process parameters for the welding of the AA5754 H111 aluminum plates in Butt-Joint configuration.

A Software Package for Neural Network Applications Development

NASA Technical Reports Server (NTRS)

Baran, Robert H.

1993-01-01

Original Backprop (Version 1.2) is an MS-DOS package of four stand-alone C-language programs that enable users to develop neural network solutions to a variety of practical problems. Original Backprop generates three-layer, feed-forward (series-coupled) networks which map fixed-length input vectors into fixed length output vectors through an intermediate (hidden) layer of binary threshold units. Version 1.2 can handle up to 200 input vectors at a time, each having up to 128 real-valued components. The first subprogram, TSET, appends a number (up to 16) of classification bits to each input, thus creating a training set of input output pairs. The second subprogram, BACKPROP, creates a trilayer network to do the prescribed mapping and modifies the weights of its connections incrementally until the training set is leaned. The learning algorithm is the 'back-propagating error correction procedures first described by F. Rosenblatt in 1961. The third subprogram, VIEWNET, lets the trained network be examined, tested, and 'pruned' (by the deletion of unnecessary hidden units). The fourth subprogram, DONET, makes a TSR routine by which the finished product of the neural net design-and-training exercise can be consulted under other MS-DOS applications.

Modeling constitutive behavior of a 15Cr-15Ni-2.2Mo-Ti modified austenitic stainless steel under hot compression using artificial neural network

NASA Astrophysics Data System (ADS)

Mandal, Sumantra

2006-11-01

ABSTRACT In this paper, an artificial neural network (ANN) model has been suggested to predict the constitutive flow behavior of a 15Cr-15Ni-2.2Mo-Ti modified austenitic stainless steel under hot deformation. Hot compression tests in the temperature range 850°C- 1250°C and strain rate range 10-3-102 s-1 were carried out. These tests provided the required data for training the neural network and for subsequent testing. The inputs of the neural network are strain, log strain rate and temperature while flow stress is obtained as output. A three layer feed-forward network with ten neurons in a single hidden layer and back-propagation learning algorithm has been employed. A very good correlation between experimental and predicted result has been obtained. The effect of temperature and strain rate on flow behavior has been simulated employing the ANN model. The results have been found to be consistent with the metallurgical trend. Finally, a monte carlo analiysis has been carried out to find out the noise sensitivity of the developed model.

Generative Adversarial Networks: An Overview

NASA Astrophysics Data System (ADS)

Creswell, Antonia; White, Tom; Dumoulin, Vincent; Arulkumaran, Kai; Sengupta, Biswa; Bharath, Anil A.

2018-01-01

Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data. They achieve this through deriving backpropagation signals through a competitive process involving a pair of networks. The representations that can be learned by GANs may be used in a variety of applications, including image synthesis, semantic image editing, style transfer, image super-resolution and classification. The aim of this review paper is to provide an overview of GANs for the signal processing community, drawing on familiar analogies and concepts where possible. In addition to identifying different methods for training and constructing GANs, we also point to remaining challenges in their theory and application.

Application of DBNs for concerned internet information detecting

NASA Astrophysics Data System (ADS)

Wang, Yanfang; Gao, Song

2017-03-01

In recent years, deep learning has achieved great success in many fields, ranging from voice recognition and image classification to computer vision. In this study we apply DBNs to concerned internet information in Chinese detecting problem, since there are inherent differences between English and Chinese. Contrastive divergence (CD) is employed in the DBNs to learn a multi-layer generative model from numerous unlabeled data. The features obtained by this model are used to initialize the feed-forward neural network, which can be fine-tuned with backpropagation. Experiment results indicate that, the model and training method we proposed can be used to detect the concerned internet information effectively and accurately.

Automatic voice recognition using traditional and artificial neural network approaches

NASA Technical Reports Server (NTRS)

Botros, Nazeih M.

1989-01-01

The main objective of this research is to develop an algorithm for isolated-word recognition. This research is focused on digital signal analysis rather than linguistic analysis of speech. Features extraction is carried out by applying a Linear Predictive Coding (LPC) algorithm with order of 10. Continuous-word and speaker independent recognition will be considered in future study after accomplishing this isolated word research. To examine the similarity between the reference and the training sets, two approaches are explored. The first is implementing traditional pattern recognition techniques where a dynamic time warping algorithm is applied to align the two sets and calculate the probability of matching by measuring the Euclidean distance between the two sets. The second is implementing a backpropagation artificial neural net model with three layers as the pattern classifier. The adaptation rule implemented in this network is the generalized least mean square (LMS) rule. The first approach has been accomplished. A vocabulary of 50 words was selected and tested. The accuracy of the algorithm was found to be around 85 percent. The second approach is in progress at the present time.

Deep image mining for diabetic retinopathy screening.

PubMed

Quellec, Gwenolé; Charrière, Katia; Boudi, Yassine; Cochener, Béatrice; Lamard, Mathieu

2017-07-01

Deep learning is quickly becoming the leading methodology for medical image analysis. Given a large medical archive, where each image is associated with a diagnosis, efficient pathology detectors or classifiers can be trained with virtually no expert knowledge about the target pathologies. However, deep learning algorithms, including the popular ConvNets, are black boxes: little is known about the local patterns analyzed by ConvNets to make a decision at the image level. A solution is proposed in this paper to create heatmaps showing which pixels in images play a role in the image-level predictions. In other words, a ConvNet trained for image-level classification can be used to detect lesions as well. A generalization of the backpropagation method is proposed in order to train ConvNets that produce high-quality heatmaps. The proposed solution is applied to diabetic retinopathy (DR) screening in a dataset of almost 90,000 fundus photographs from the 2015 Kaggle Diabetic Retinopathy competition and a private dataset of almost 110,000 photographs (e-ophtha). For the task of detecting referable DR, very good detection performance was achieved: A z =0.954 in Kaggle's dataset and A z =0.949 in e-ophtha. Performance was also evaluated at the image level and at the lesion level in the DiaretDB1 dataset, where four types of lesions are manually segmented: microaneurysms, hemorrhages, exudates and cotton-wool spots. For the task of detecting images containing these four lesion types, the proposed detector, which was trained to detect referable DR, outperforms recent algorithms trained to detect those lesions specifically, with pixel-level supervision. At the lesion level, the proposed detector outperforms heatmap generation algorithms for ConvNets. This detector is part of the Messidor® system for mobile eye pathology screening. Because it does not rely on expert knowledge or manual segmentation for detecting relevant patterns, the proposed solution is a promising image mining tool, which has the potential to discover new biomarkers in images. Copyright © 2017 Elsevier B.V. All rights reserved.

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.

Enhanced online convolutional neural networks for object tracking

NASA Astrophysics Data System (ADS)

Zhang, Dengzhuo; Gao, Yun; Zhou, Hao; Li, Tianwen

2018-04-01

In recent several years, object tracking based on convolution neural network has gained more and more attention. The initialization and update of convolution filters can directly affect the precision of object tracking effective. In this paper, a novel object tracking via an enhanced online convolution neural network without offline training is proposed, which initializes the convolution filters by a k-means++ algorithm and updates the filters by an error back-propagation. The comparative experiments of 7 trackers on 15 challenging sequences showed that our tracker can perform better than other trackers in terms of AUC and precision.

Big Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce.

PubMed

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.

Matching algorithm of missile tail flame based on back-propagation neural network

NASA Astrophysics Data System (ADS)

Huang, Da; Huang, Shucai; Tang, Yidong; Zhao, Wei; Cao, Wenhuan

2018-02-01

This work presents a spectral matching algorithm of missile plume detection that based on neural network. The radiation value of the characteristic spectrum of the missile tail flame is taken as the input of the network. The network's structure including the number of nodes and layers is determined according to the number of characteristic spectral bands and missile types. We can get the network weight matrixes and threshold vectors through training the network using training samples, and we can determine the performance of the network through testing the network using the test samples. A small amount of data cause the network has the advantages of simple structure and practicality. Network structure composed of weight matrix and threshold vector can complete task of spectrum matching without large database support. Network can achieve real-time requirements with a small quantity of data. Experiment results show that the algorithm has the ability to match the precise spectrum and strong robustness.

Artificial Intelligence Techniques to Optimize the EDC/NHS-Mediated Immobilization of Cellulase on Eudragit L-100

PubMed Central

Zhang, Yu; Xu, Jing-Liang; Yuan, Zhen-Hong; Qi, Wei; Liu, Yun-Yun; He, Min-Chao

2012-01-01

Two artificial intelligence techniques, namely artificial neural network (ANN) and genetic algorithm (GA) were combined to be used as a tool for optimizing the covalent immobilization of cellulase on a smart polymer, Eudragit L-100. 1-Ethyl-3-(3-dimethyllaminopropyl) carbodiimide (EDC) concentration, N-hydroxysuccinimide (NHS) concentration and coupling time were taken as independent variables, and immobilization efficiency was taken as the response. The data of the central composite design were used to train ANN by back-propagation algorithm, and the result showed that the trained ANN fitted the data accurately (correlation coefficient R2 = 0.99). Then a maximum immobilization efficiency of 88.76% was searched by genetic algorithm at a EDC concentration of 0.44%, NHS concentration of 0.37% and a coupling time of 2.22 h, where the experimental value was 87.97 ± 6.45%. The application of ANN based optimization by GA is quite successful. PMID:22942683

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

NASA Astrophysics Data System (ADS)

Jelen, Lukasz; Kobel, Joanna; Podbielska, Halina

2003-11-01

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

Prediction of toxic metals concentration using artificial intelligence techniques

NASA Astrophysics Data System (ADS)

Gholami, R.; Kamkar-Rouhani, A.; Doulati Ardejani, F.; Maleki, Sh.

2011-12-01

Groundwater and soil pollution are noted to be the worst environmental problem related to the mining industry because of the pyrite oxidation, and hence acid mine drainage generation, release and transport of the toxic metals. The aim of this paper is to predict the concentration of Ni and Fe using a robust algorithm named support vector machine (SVM). Comparison of the obtained results of SVM with those of the back-propagation neural network (BPNN) indicates that the SVM can be regarded as a proper algorithm for the prediction of toxic metals concentration due to its relative high correlation coefficient and the associated running time. As a matter of fact, the SVM method has provided a better prediction of the toxic metals Fe and Ni and resulted the running time faster compared with that of the BPNN.

Optimization of training backpropagation algorithm using nguyen widrow for angina ludwig diagnosis

NASA Astrophysics Data System (ADS)

Aisyah, Siti; Harahap, Mawaddah; Mahmud Husein Siregar, Amir; Turnip, Mardi

2018-04-01

Tooth and mouth disease is a common disease, with a prevalence of more than 40% (children aged less than 7 years) in milk teeth and about 85% (adults aged 17 years and over) on permanent teeth. Angina Ludwig is one of mouth disease type that occurs due to infection of the tooth root and trauma of the mouth. ‘In this study back propagation algorithm applied to diagnose AnginaLudwig disease (using Nguyen Widrow method in optimization of training time). From the experimental results, it is known that the average BPNN by using Nguyen Widrow is much faster which is about 0.0624 seconds and 0.1019 seconds (without NguyenWidrow). In contrast, for pattern recognition needs, found that back propagation without Nguyen Widrow is much better that is with 90% accuracy (only 70% with NguyenWidrow).

Efficient video-equipped fire detection approach for automatic fire alarm systems

NASA Astrophysics Data System (ADS)

Kang, Myeongsu; Tung, Truong Xuan; Kim, Jong-Myon

2013-01-01

This paper proposes an efficient four-stage approach that automatically detects fire using video capabilities. In the first stage, an approximate median method is used to detect video frame regions involving motion. In the second stage, a fuzzy c-means-based clustering algorithm is employed to extract candidate regions of fire from all of the movement-containing regions. In the third stage, a gray level co-occurrence matrix is used to extract texture parameters by tracking red-colored objects in the candidate regions. These texture features are, subsequently, used as inputs of a back-propagation neural network to distinguish between fire and nonfire. Experimental results indicate that the proposed four-stage approach outperforms other fire detection algorithms in terms of consistently increasing the accuracy of fire detection in both indoor and outdoor test videos.

Biological engineering applications of feedforward neural networks designed and parameterized by genetic algorithms.

PubMed

Ferentinos, Konstantinos P

2005-09-01

Two neural network (NN) applications in the field of biological engineering are developed, designed and parameterized by an evolutionary method based on the evolutionary process of genetic algorithms. The developed systems are a fault detection NN model and a predictive modeling NN system. An indirect or 'weak specification' representation was used for the encoding of NN topologies and training parameters into genes of the genetic algorithm (GA). Some a priori knowledge of the demands in network topology for specific application cases is required by this approach, so that the infinite search space of the problem is limited to some reasonable degree. Both one-hidden-layer and two-hidden-layer network architectures were explored by the GA. Except for the network architecture, each gene of the GA also encoded the type of activation functions in both hidden and output nodes of the NN and the type of minimization algorithm that was used by the backpropagation algorithm for the training of the NN. Both models achieved satisfactory performance, while the GA system proved to be a powerful tool that can successfully replace the problematic trial-and-error approach that is usually used for these tasks.

Artificial neural network with backpropagation learning to predict mean monthly total ozone in Arosa, Switzerland

NASA Astrophysics Data System (ADS)

Chattopadhyay, Surajit; Bandyopadhyay, Goutami

2007-01-01

Present study deals with the mean monthly total ozone time series over Arosa, Switzerland. The study period is 1932-1971. First of all, the total ozone time series has been identified as a complex system and then Artificial Neural Networks models in the form of Multilayer Perceptron with back propagation learning have been developed. The models are Single-hidden-layer and Two-hidden-layer Perceptrons with sigmoid activation function. After sequential learning with learning rate 0.9 the peak total ozone period (February-May) concentrations of mean monthly total ozone have been predicted by the two neural net models. After training and validation, both of the models are found skillful. But, Two-hidden-layer Perceptron is found to be more adroit in predicting the mean monthly total ozone concentrations over the aforesaid period.

Rainfall prediction with backpropagation method

NASA Astrophysics Data System (ADS)

Wahyuni, E. G.; Fauzan, L. M. F.; Abriyani, F.; Muchlis, N. F.; Ulfa, M.

2018-03-01

Rainfall is an important factor in many fields, such as aviation and agriculture. Although it has been assisted by technology but the accuracy can not reach 100% and there is still the possibility of error. Though current rainfall prediction information is needed in various fields, such as agriculture and aviation fields. In the field of agriculture, to obtain abundant and quality yields, farmers are very dependent on weather conditions, especially rainfall. Rainfall is one of the factors that affect the safety of aircraft. To overcome the problems above, then it’s required a system that can accurately predict rainfall. In predicting rainfall, artificial neural network modeling is applied in this research. The method used in modeling this artificial neural network is backpropagation method. Backpropagation methods can result in better performance in repetitive exercises. This means that the weight of the ANN interconnection can approach the weight it should be. Another advantage of this method is the ability in the learning process adaptively and multilayer owned on this method there is a process of weight changes so as to minimize error (fault tolerance). Therefore, this method can guarantee good system resilience and consistently work well. The network is designed using 4 input variables, namely air temperature, air humidity, wind speed, and sunshine duration and 3 output variables ie low rainfall, medium rainfall, and high rainfall. Based on the research that has been done, the network can be used properly, as evidenced by the results of the prediction of the system precipitation is the same as the results of manual calculations.

A morphological perceptron with gradient-based learning for Brazilian stock market forecasting.

PubMed

Araújo, Ricardo de A

2012-04-01

Several linear and non-linear techniques have been proposed to solve the stock market forecasting problem. However, a limitation arises from all these techniques and is known as the random walk dilemma (RWD). In this scenario, forecasts generated by arbitrary models have a characteristic one step ahead delay with respect to the time series values, so that, there is a time phase distortion in stock market phenomena reconstruction. In this paper, we propose a suitable model inspired by concepts in mathematical morphology (MM) and lattice theory (LT). This model is generically called the increasing morphological perceptron (IMP). Also, we present a gradient steepest descent method to design the proposed IMP based on ideas from the back-propagation (BP) algorithm and using a systematic approach to overcome the problem of non-differentiability of morphological operations. Into the learning process we have included a procedure to overcome the RWD, which is an automatic correction step that is geared toward eliminating time phase distortions that occur in stock market phenomena. Furthermore, an experimental analysis is conducted with the IMP using four complex non-linear problems of time series forecasting from the Brazilian stock market. Additionally, two natural phenomena time series are used to assess forecasting performance of the proposed IMP with other non financial time series. At the end, the obtained results are discussed and compared to results found using models recently proposed in the literature. Copyright © 2011 Elsevier Ltd. All rights reserved.

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

NASA Astrophysics Data System (ADS)

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

2010-11-01

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

Antenna analysis using neural networks

NASA Technical Reports Server (NTRS)

Smith, William T.

1992-01-01

Conventional computing schemes have long been used to analyze problems in electromagnetics (EM). The vast majority of EM applications require computationally intensive algorithms involving numerical integration and solutions to large systems of equations. The feasibility of using neural network computing algorithms for antenna analysis is investigated. The ultimate goal is to use a trained neural network algorithm to reduce the computational demands of existing reflector surface error compensation techniques. Neural networks are computational algorithms based on neurobiological systems. Neural nets consist of massively parallel interconnected nonlinear computational elements. They are often employed in pattern recognition and image processing problems. Recently, neural network analysis has been applied in the electromagnetics area for the design of frequency selective surfaces and beam forming networks. The backpropagation training algorithm was employed to simulate classical antenna array synthesis techniques. The Woodward-Lawson (W-L) and Dolph-Chebyshev (D-C) array pattern synthesis techniques were used to train the neural network. The inputs to the network were samples of the desired synthesis pattern. The outputs are the array element excitations required to synthesize the desired pattern. Once trained, the network is used to simulate the W-L or D-C techniques. Various sector patterns and cosecant-type patterns (27 total) generated using W-L synthesis were used to train the network. Desired pattern samples were then fed to the neural network. The outputs of the network were the simulated W-L excitations. A 20 element linear array was used. There were 41 input pattern samples with 40 output excitations (20 real parts, 20 imaginary). A comparison between the simulated and actual W-L techniques is shown for a triangular-shaped pattern. Dolph-Chebyshev is a different class of synthesis technique in that D-C is used for side lobe control as opposed to pattern shaping. The interesting thing about D-C synthesis is that the side lobes have the same amplitude. Five-element arrays were used. Again, 41 pattern samples were used for the input. Nine actual D-C patterns ranging from -10 dB to -30 dB side lobe levels were used to train the network. A comparison between simulated and actual D-C techniques for a pattern with -22 dB side lobe level is shown. The goal for this research was to evaluate the performance of neural network computing with antennas. Future applications will employ the backpropagation training algorithm to drastically reduce the computational complexity involved in performing EM compensation for surface errors in large space reflector antennas.

Antenna analysis using neural networks

NASA Astrophysics Data System (ADS)

Smith, William T.

1992-09-01

Conventional computing schemes have long been used to analyze problems in electromagnetics (EM). The vast majority of EM applications require computationally intensive algorithms involving numerical integration and solutions to large systems of equations. The feasibility of using neural network computing algorithms for antenna analysis is investigated. The ultimate goal is to use a trained neural network algorithm to reduce the computational demands of existing reflector surface error compensation techniques. Neural networks are computational algorithms based on neurobiological systems. Neural nets consist of massively parallel interconnected nonlinear computational elements. They are often employed in pattern recognition and image processing problems. Recently, neural network analysis has been applied in the electromagnetics area for the design of frequency selective surfaces and beam forming networks. The backpropagation training algorithm was employed to simulate classical antenna array synthesis techniques. The Woodward-Lawson (W-L) and Dolph-Chebyshev (D-C) array pattern synthesis techniques were used to train the neural network. The inputs to the network were samples of the desired synthesis pattern. The outputs are the array element excitations required to synthesize the desired pattern. Once trained, the network is used to simulate the W-L or D-C techniques. Various sector patterns and cosecant-type patterns (27 total) generated using W-L synthesis were used to train the network. Desired pattern samples were then fed to the neural network. The outputs of the network were the simulated W-L excitations. A 20 element linear array was used. There were 41 input pattern samples with 40 output excitations (20 real parts, 20 imaginary).

Supervised Learning Using Spike-Timing-Dependent Plasticity of Memristive Synapses.

PubMed

Nishitani, Yu; Kaneko, Yukihiro; Ueda, Michihito

2015-12-01

We propose a supervised learning model that enables error backpropagation for spiking neural network hardware. The method is modeled by modifying an existing model to suit the hardware implementation. An example of a network circuit for the model is also presented. In this circuit, a three-terminal ferroelectric memristor (3T-FeMEM), which is a field-effect transistor with a gate insulator composed of ferroelectric materials, is used as an electric synapse device to store the analog synaptic weight. Our model can be implemented by reflecting the network error to the write voltage of the 3T-FeMEMs and introducing a spike-timing-dependent learning function to the device. An XOR problem was successfully demonstrated as a benchmark learning by numerical simulations using the circuit properties to estimate the learning performance. In principle, the learning time per step of this supervised learning model and the circuit is independent of the number of neurons in each layer, promising a high-speed and low-power calculation in large-scale neural networks.

Training Recurrent Neural Networks With the Levenberg-Marquardt Algorithm for Optimal Control of a Grid-Connected Converter.

PubMed

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.

GPU-accelerated adjoint algorithmic differentiation

NASA Astrophysics Data System (ADS)

Gremse, Felix; Höfter, Andreas; Razik, Lukas; Kiessling, Fabian; Naumann, Uwe

2016-03-01

Many scientific problems such as classifier training or medical image reconstruction can be expressed as minimization of differentiable real-valued cost functions and solved with iterative gradient-based methods. Adjoint algorithmic differentiation (AAD) enables automated computation of gradients of such cost functions implemented as computer programs. To backpropagate adjoint derivatives, excessive memory is potentially required to store the intermediate partial derivatives on a dedicated data structure, referred to as the ;tape;. Parallelization is difficult because threads need to synchronize their accesses during taping and backpropagation. This situation is aggravated for many-core architectures, such as Graphics Processing Units (GPUs), because of the large number of light-weight threads and the limited memory size in general as well as per thread. We show how these limitations can be mediated if the cost function is expressed using GPU-accelerated vector and matrix operations which are recognized as intrinsic functions by our AAD software. We compare this approach with naive and vectorized implementations for CPUs. We use four increasingly complex cost functions to evaluate the performance with respect to memory consumption and gradient computation times. Using vectorization, CPU and GPU memory consumption could be substantially reduced compared to the naive reference implementation, in some cases even by an order of complexity. The vectorization allowed usage of optimized parallel libraries during forward and reverse passes which resulted in high speedups for the vectorized CPU version compared to the naive reference implementation. The GPU version achieved an additional speedup of 7.5 ± 4.4, showing that the processing power of GPUs can be utilized for AAD using this concept. Furthermore, we show how this software can be systematically extended for more complex problems such as nonlinear absorption reconstruction for fluorescence-mediated tomography.

GPU-Accelerated Adjoint Algorithmic Differentiation.

PubMed

Gremse, Felix; Höfter, Andreas; Razik, Lukas; Kiessling, Fabian; Naumann, Uwe

2016-03-01

Many scientific problems such as classifier training or medical image reconstruction can be expressed as minimization of differentiable real-valued cost functions and solved with iterative gradient-based methods. Adjoint algorithmic differentiation (AAD) enables automated computation of gradients of such cost functions implemented as computer programs. To backpropagate adjoint derivatives, excessive memory is potentially required to store the intermediate partial derivatives on a dedicated data structure, referred to as the "tape". Parallelization is difficult because threads need to synchronize their accesses during taping and backpropagation. This situation is aggravated for many-core architectures, such as Graphics Processing Units (GPUs), because of the large number of light-weight threads and the limited memory size in general as well as per thread. We show how these limitations can be mediated if the cost function is expressed using GPU-accelerated vector and matrix operations which are recognized as intrinsic functions by our AAD software. We compare this approach with naive and vectorized implementations for CPUs. We use four increasingly complex cost functions to evaluate the performance with respect to memory consumption and gradient computation times. Using vectorization, CPU and GPU memory consumption could be substantially reduced compared to the naive reference implementation, in some cases even by an order of complexity. The vectorization allowed usage of optimized parallel libraries during forward and reverse passes which resulted in high speedups for the vectorized CPU version compared to the naive reference implementation. The GPU version achieved an additional speedup of 7.5 ± 4.4, showing that the processing power of GPUs can be utilized for AAD using this concept. Furthermore, we show how this software can be systematically extended for more complex problems such as nonlinear absorption reconstruction for fluorescence-mediated tomography.

GPU-Accelerated Adjoint Algorithmic Differentiation

PubMed Central

Gremse, Felix; Höfter, Andreas; Razik, Lukas; Kiessling, Fabian; Naumann, Uwe

2015-01-01

Many scientific problems such as classifier training or medical image reconstruction can be expressed as minimization of differentiable real-valued cost functions and solved with iterative gradient-based methods. Adjoint algorithmic differentiation (AAD) enables automated computation of gradients of such cost functions implemented as computer programs. To backpropagate adjoint derivatives, excessive memory is potentially required to store the intermediate partial derivatives on a dedicated data structure, referred to as the “tape”. Parallelization is difficult because threads need to synchronize their accesses during taping and backpropagation. This situation is aggravated for many-core architectures, such as Graphics Processing Units (GPUs), because of the large number of light-weight threads and the limited memory size in general as well as per thread. We show how these limitations can be mediated if the cost function is expressed using GPU-accelerated vector and matrix operations which are recognized as intrinsic functions by our AAD software. We compare this approach with naive and vectorized implementations for CPUs. We use four increasingly complex cost functions to evaluate the performance with respect to memory consumption and gradient computation times. Using vectorization, CPU and GPU memory consumption could be substantially reduced compared to the naive reference implementation, in some cases even by an order of complexity. The vectorization allowed usage of optimized parallel libraries during forward and reverse passes which resulted in high speedups for the vectorized CPU version compared to the naive reference implementation. The GPU version achieved an additional speedup of 7.5 ± 4.4, showing that the processing power of GPUs can be utilized for AAD using this concept. Furthermore, we show how this software can be systematically extended for more complex problems such as nonlinear absorption reconstruction for fluorescence-mediated tomography. PMID:26941443

Steepest descent with momentum for quadratic functions is a version of the conjugate gradient method.

PubMed

Bhaya, Amit; Kaszkurewicz, Eugenius

2004-01-01

It is pointed out that the so called momentum method, much used in the neural network literature as an acceleration of the backpropagation method, is a stationary version of the conjugate gradient method. Connections with the continuous optimization method known as heavy ball with friction are also made. In both cases, adaptive (dynamic) choices of the so called learning rate and momentum parameters are obtained using a control Liapunov function analysis of the system.

Adaptive neuro fuzzy inference system-based power estimation method for CMOS VLSI circuits

NASA Astrophysics Data System (ADS)

Vellingiri, Govindaraj; Jayabalan, Ramesh

2018-03-01

Recent advancements in very large scale integration (VLSI) technologies have made it feasible to integrate millions of transistors on a single chip. This greatly increases the circuit complexity and hence there is a growing need for less-tedious and low-cost power estimation techniques. The proposed work employs Back-Propagation Neural Network (BPNN) and Adaptive Neuro Fuzzy Inference System (ANFIS), which are capable of estimating the power precisely for the complementary metal oxide semiconductor (CMOS) VLSI circuits, without requiring any knowledge on circuit structure and interconnections. The ANFIS to power estimation application is relatively new. Power estimation using ANFIS is carried out by creating initial FIS modes using hybrid optimisation and back-propagation (BP) techniques employing constant and linear methods. It is inferred that ANFIS with the hybrid optimisation technique employing the linear method produces better results in terms of testing error that varies from 0% to 0.86% when compared to BPNN as it takes the initial fuzzy model and tunes it by means of a hybrid technique combining gradient descent BP and mean least-squares optimisation algorithms. ANFIS is the best suited for power estimation application with a low RMSE of 0.0002075 and a high coefficient of determination (R) of 0.99961.

The Dropout Learning Algorithm

PubMed Central

Baldi, Pierre; Sadowski, Peter

2014-01-01

Dropout is a recently introduced algorithm for training neural network by randomly dropping units during training to prevent their co-adaptation. A mathematical analysis of some of the static and dynamic properties of dropout is provided using Bernoulli gating variables, general enough to accommodate dropout on units or connections, and with variable rates. The framework allows a complete analysis of the ensemble averaging properties of dropout in linear networks, which is useful to understand the non-linear case. The ensemble averaging properties of dropout in non-linear logistic networks result from three fundamental equations: (1) the approximation of the expectations of logistic functions by normalized geometric means, for which bounds and estimates are derived; (2) the algebraic equality between normalized geometric means of logistic functions with the logistic of the means, which mathematically characterizes logistic functions; and (3) the linearity of the means with respect to sums, as well as products of independent variables. The results are also extended to other classes of transfer functions, including rectified linear functions. Approximation errors tend to cancel each other and do not accumulate. Dropout can also be connected to stochastic neurons and used to predict firing rates, and to backpropagation by viewing the backward propagation as ensemble averaging in a dropout linear network. Moreover, the convergence properties of dropout can be understood in terms of stochastic gradient descent. Finally, for the regularization properties of dropout, the expectation of the dropout gradient is the gradient of the corresponding approximation ensemble, regularized by an adaptive weight decay term with a propensity for self-consistent variance minimization and sparse representations. PMID:24771879

Big Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce

PubMed Central

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

Neural Network Compensation for Frequency Cross-Talk in Laser Interferometry

NASA Astrophysics Data System (ADS)

Lee, Wooram; Heo, Gunhaeng; You, Kwanho

The heterodyne laser interferometer acts as an ultra-precise measurement apparatus in semiconductor manufacture. However the periodical nonlinearity property caused from frequency cross-talk is an obstacle to improve the high measurement accuracy in nanometer scale. In order to minimize the nonlinearity error of the heterodyne interferometer, we propose a frequency cross-talk compensation algorithm using an artificial intelligence method. The feedforward neural network trained by back-propagation compensates the nonlinearity error and regulates to minimize the difference with the reference signal. With some experimental results, the improved accuracy is proved through comparison with the position value from a capacitive displacement sensor.

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

PubMed

Morns, L P; Dlay, S S

1999-01-01

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

Prediction of properties of wheat dough using intelligent deep belief networks

NASA Astrophysics Data System (ADS)

Guha, Paramita; Bhatnagar, Taru; Pal, Ishan; Kamboj, Uma; Mishra, Sunita

2017-11-01

In this paper, the rheological and chemical properties of wheat dough are predicted using deep belief networks. Wheat grains are stored at controlled environmental conditions. The internal parameters of grains viz., protein, fat, carbohydrates, moisture, ash are determined using standard chemical analysis and viscosity of the dough is measured using Rheometer. Here, fat, carbohydrates, moisture, ash and temperature are considered as inputs whereas protein and viscosity are chosen as outputs. The prediction algorithm is developed using deep neural network where each layer is trained greedily using restricted Boltzmann machine (RBM) networks. The overall network is finally fine-tuned using standard neural network technique. In most literature, it has been found that fine-tuning is done using back-propagation technique. In this paper, a new algorithm is proposed in which each layer is tuned using RBM and the final network is fine-tuned using deep neural network (DNN). It has been observed that with the proposed algorithm, errors between the actual and predicted outputs are less compared to the conventional algorithm. Hence, the given network can be considered as beneficial as it predicts the outputs more accurately. Numerical results along with discussions are presented.

Genetic algorithm applied to the selection of factors in principal component-artificial neural networks: application to QSAR study of calcium channel antagonist activity of 1,4-dihydropyridines (nifedipine analogous).

PubMed

Hemmateenejad, Bahram; Akhond, Morteza; Miri, Ramin; Shamsipur, Mojtaba

2003-01-01

A QSAR algorithm, principal component-genetic algorithm-artificial neural network (PC-GA-ANN), has been applied to a set of newly synthesized calcium channel blockers, which are of special interest because of their role in cardiac diseases. A data set of 124 1,4-dihydropyridines bearing different ester substituents at the C-3 and C-5 positions of the dihydropyridine ring and nitroimidazolyl, phenylimidazolyl, and methylsulfonylimidazolyl groups at the C-4 position with known Ca(2+) channel binding affinities was employed in this study. Ten different sets of descriptors (837 descriptors) were calculated for each molecule. The principal component analysis was used to compress the descriptor groups into principal components. The most significant descriptors of each set were selected and used as input for the ANN. The genetic algorithm (GA) was used for the selection of the best set of extracted principal components. A feed forward artificial neural network with a back-propagation of error algorithm was used to process the nonlinear relationship between the selected principal components and biological activity of the dihydropyridines. A comparison between PC-GA-ANN and routine PC-ANN shows that the first model yields better prediction ability.

Prediction of the Vickers Microhardness and Ultimate Tensile Strength of AA5754 H111 Friction Stir Welding Butt Joints Using Artificial Neural Network

PubMed Central

De Filippis, Luigi Alberto Ciro; Serio, Livia Maria; Facchini, Francesco; Mummolo, Giovanni; Ludovico, Antonio Domenico

2016-01-01

A simulation model was developed for the monitoring, controlling and optimization of the Friction Stir Welding (FSW) process. This approach, using the FSW technique, allows identifying the correlation between the process parameters (input variable) and the mechanical properties (output responses) of the welded AA5754 H111 aluminum plates. The optimization of technological parameters is a basic requirement for increasing the seam quality, since it promotes a stable and defect-free process. Both the tool rotation and the travel speed, the position of the samples extracted from the weld bead and the thermal data, detected with thermographic techniques for on-line control of the joints, were varied to build the experimental plans. The quality of joints was evaluated through destructive and non-destructive tests (visual tests, macro graphic analysis, tensile tests, indentation Vickers hardness tests and t thermographic controls). The simulation model was based on the adoption of the Artificial Neural Networks (ANNs) characterized by back-propagation learning algorithm with different types of architecture, which were able to predict with good reliability the FSW process parameters for the welding of the AA5754 H111 aluminum plates in Butt-Joint configuration. PMID:28774035

Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices

PubMed Central

Gokmen, Tayfun; Onen, Murat; Haensch, Wilfried

2017-01-01

In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional neural networks (CNNs). We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures. PMID:29066942

Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices.

PubMed

Gokmen, Tayfun; Onen, Murat; Haensch, Wilfried

2017-01-01

In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional neural networks (CNNs). We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures.

Modelling local GPS/levelling geoid undulations using artificial neural networks

NASA Astrophysics Data System (ADS)

Kavzoglu, T.; Saka, M. H.

2005-04-01

The use of GPS for establishing height control in an area where levelling data are available can involve the so-called GPS/levelling technique. Modelling of the GPS/levelling geoid undulations has usually been carried out using polynomial surface fitting, least-squares collocation (LSC) and finite-element methods. Artificial neural networks (ANNs) have recently been used for many investigations, and proven to be effective in solving complex problems represented by noisy and missing data. In this study, a feed-forward ANN structure, learning the characteristics of the training data through the back-propagation algorithm, is employed to model the local GPS/levelling geoid surface. The GPS/levelling geoid undulations for Istanbul, Turkey, were estimated from GPS and precise levelling measurements obtained during a field study in the period 1998-99. The results are compared to those produced by two well-known conventional methods, namely polynomial fitting and LSC, in terms of root mean square error (RMSE) that ranged from 3.97 to 5.73 cm. The results show that ANNs can produce results that are comparable to polynomial fitting and LSC. The main advantage of the ANN-based surfaces seems to be the low deviations from the GPS/levelling data surface, which is particularly important for distorted levelling networks.

Artificial neural network modelling of uncertainty in gamma-ray spectrometry

NASA Astrophysics Data System (ADS)

Dragović, S.; Onjia, A.; Stanković, S.; Aničin, I.; Bačić, G.

2005-03-01

An artificial neural network (ANN) model for the prediction of measuring uncertainties in gamma-ray spectrometry was developed and optimized. A three-layer feed-forward ANN with back-propagation learning algorithm was used to model uncertainties of measurement of activity levels of eight radionuclides ( 226Ra, 238U, 235U, 40K, 232Th, 134Cs, 137Cs and 7Be) in soil samples as a function of measurement time. It was shown that the neural network provides useful data even from small experimental databases. The performance of the optimized neural network was found to be very good, with correlation coefficients ( R2) between measured and predicted uncertainties ranging from 0.9050 to 0.9915. The correlation coefficients did not significantly deteriorate when the network was tested on samples with greatly different uranium-to-thorium ( 238U/ 232Th) ratios. The differences between measured and predicted uncertainties were not influenced by the absolute values of uncertainties of measured radionuclide activities. Once the ANN is trained, it could be employed in analyzing soil samples regardless of the 238U/ 232Th ratio. It was concluded that a considerable saving in time could be obtained using the trained neural network model for predicting the measurement times needed to attain the desired statistical accuracy.

A Hybrid Feature Model and Deep-Learning-Based Bearing Fault Diagnosis

PubMed Central

Sohaib, Muhammad; Kim, Cheol-Hong; Kim, Jong-Myon

2017-01-01

Bearing fault diagnosis is imperative for the maintenance, reliability, and durability of rotary machines. It can reduce economical losses by eliminating unexpected downtime in industry due to failure of rotary machines. Though widely investigated in the past couple of decades, continued advancement is still desirable to improve upon existing fault diagnosis techniques. Vibration acceleration signals collected from machine bearings exhibit nonstationary behavior due to variable working conditions and multiple fault severities. In the current work, a two-layered bearing fault diagnosis scheme is proposed for the identification of fault pattern and crack size for a given fault type. A hybrid feature pool is used in combination with sparse stacked autoencoder (SAE)-based deep neural networks (DNNs) to perform effective diagnosis of bearing faults of multiple severities. The hybrid feature pool can extract more discriminating information from the raw vibration signals, to overcome the nonstationary behavior of the signals caused by multiple crack sizes. More discriminating information helps the subsequent classifier to effectively classify data into the respective classes. The results indicate that the proposed scheme provides satisfactory performance in diagnosing bearing defects of multiple severities. Moreover, the results also demonstrate that the proposed model outperforms other state-of-the-art algorithms, i.e., support vector machines (SVMs) and backpropagation neural networks (BPNNs). PMID:29232908

A Hybrid Spectral Clustering and Deep Neural Network Ensemble Algorithm for Intrusion Detection in Sensor Networks

PubMed Central

Ma, Tao; Wang, Fen; Cheng, Jianjun; Yu, Yang; Chen, Xiaoyun

2016-01-01

The development of intrusion detection systems (IDS) that are adapted to allow routers and network defence systems to detect malicious network traffic disguised as network protocols or normal access is a critical challenge. This paper proposes a novel approach called SCDNN, which combines spectral clustering (SC) and deep neural network (DNN) algorithms. First, the dataset is divided into k subsets based on sample similarity using cluster centres, as in SC. Next, the distance between data points in a testing set and the training set is measured based on similarity features and is fed into the deep neural network algorithm for intrusion detection. Six KDD-Cup99 and NSL-KDD datasets and a sensor network dataset were employed to test the performance of the model. These experimental results indicate that the SCDNN classifier not only performs better than backpropagation neural network (BPNN), support vector machine (SVM), random forest (RF) and Bayes tree models in detection accuracy and the types of abnormal attacks found. It also provides an effective tool of study and analysis of intrusion detection in large networks. PMID:27754380

A Hybrid Spectral Clustering and Deep Neural Network Ensemble Algorithm for Intrusion Detection in Sensor Networks.

PubMed

Ma, Tao; Wang, Fen; Cheng, Jianjun; Yu, Yang; Chen, Xiaoyun

2016-10-13

The development of intrusion detection systems (IDS) that are adapted to allow routers and network defence systems to detect malicious network traffic disguised as network protocols or normal access is a critical challenge. This paper proposes a novel approach called SCDNN, which combines spectral clustering (SC) and deep neural network (DNN) algorithms. First, the dataset is divided into k subsets based on sample similarity using cluster centres, as in SC. Next, the distance between data points in a testing set and the training set is measured based on similarity features and is fed into the deep neural network algorithm for intrusion detection. Six KDD-Cup99 and NSL-KDD datasets and a sensor network dataset were employed to test the performance of the model. These experimental results indicate that the SCDNN classifier not only performs better than backpropagation neural network (BPNN), support vector machine (SVM), random forest (RF) and Bayes tree models in detection accuracy and the types of abnormal attacks found. It also provides an effective tool of study and analysis of intrusion detection in large networks.

Deep neural mapping support vector machines.

PubMed

Li, Yujian; Zhang, Ting

2017-09-01

The choice of kernel has an important effect on the performance of a support vector machine (SVM). The effect could be reduced by NEUROSVM, an architecture using multilayer perceptron for feature extraction and SVM for classification. In binary classification, a general linear kernel NEUROSVM can be theoretically simplified as an input layer, many hidden layers, and an SVM output layer. As a feature extractor, the sub-network composed of the input and hidden layers is first trained together with a virtual ordinary output layer by backpropagation, then with the output of its last hidden layer taken as input of the SVM classifier for further training separately. By taking the sub-network as a kernel mapping from the original input space into a feature space, we present a novel model, called deep neural mapping support vector machine (DNMSVM), from the viewpoint of deep learning. This model is also a new and general kernel learning method, where the kernel mapping is indeed an explicit function expressed as a sub-network, different from an implicit function induced by a kernel function traditionally. Moreover, we exploit a two-stage procedure of contrastive divergence learning and gradient descent for DNMSVM to jointly training an adaptive kernel mapping instead of a kernel function, without requirement of kernel tricks. As a whole of the sub-network and the SVM classifier, the joint training of DNMSVM is done by using gradient descent to optimize the objective function with the sub-network layer-wise pre-trained via contrastive divergence learning of restricted Boltzmann machines. Compared to the separate training of NEUROSVM, the joint training is a new algorithm for DNMSVM to have advantages over NEUROSVM. Experimental results show that DNMSVM can outperform NEUROSVM and RBFSVM (i.e., SVM with the kernel of radial basis function), demonstrating its effectiveness. Copyright © 2017 Elsevier Ltd. All rights reserved.

Neural network simulation of the atmospheric point spread function for the adjacency effect research

NASA Astrophysics Data System (ADS)

Ma, Xiaoshan; Wang, Haidong; Li, Ligang; Yang, Zhen; Meng, Xin

2016-10-01

Adjacency effect could be regarded as the convolution of the atmospheric point spread function (PSF) and the surface leaving radiance. Monte Carlo is a common method to simulate the atmospheric PSF. But it can't obtain analytic expression and the meaningful results can be only acquired by statistical analysis of millions of data. A backward Monte Carlo algorithm was employed to simulate photon emitting and propagating in the atmosphere under different conditions. The PSF was determined by recording the photon-receiving numbers in fixed bin at different position. A multilayer feed-forward neural network with a single hidden layer was designed to learn the relationship between the PSF's and the input condition parameters. The neural network used the back-propagation learning rule for training. Its input parameters involved atmosphere condition, spectrum range, observing geometry. The outputs of the network were photon-receiving numbers in the corresponding bin. Because the output units were too many to be allowed by neural network, the large network was divided into a collection of smaller ones. These small networks could be ran simultaneously on many workstations and/or PCs to speed up the training. It is important to note that the simulated PSF's by Monte Carlo technique in non-nadir viewing angles are more complicated than that in nadir conditions which brings difficulties in the design of the neural network. The results obtained show that the neural network approach could be very useful to compute the atmospheric PSF based on the simulated data generated by Monte Carlo method.

Deep learning classifier with optical coherence tomography images for early dental caries detection

NASA Astrophysics Data System (ADS)

Karimian, Nima; Salehi, Hassan S.; Mahdian, Mina; Alnajjar, Hisham; Tadinada, Aditya

2018-02-01

Dental caries is a microbial disease that results in localized dissolution of the mineral content of dental tissue. Despite considerable decline in the incidence of dental caries, it remains a major health problem in many societies. Early detection of incipient lesions at initial stages of demineralization can result in the implementation of non-surgical preventive approaches to reverse the demineralization process. In this paper, we present a novel approach combining deep convolutional neural networks (CNN) and optical coherence tomography (OCT) imaging modality for classification of human oral tissues to detect early dental caries. OCT images of oral tissues with various densities were input to a CNN classifier to determine variations in tissue densities resembling the demineralization process. The CNN automatically learns a hierarchy of increasingly complex features and a related classifier directly from training data sets. The initial CNN layer parameters were randomly selected. The training set is split into minibatches, with 10 OCT images per batch. Given a batch of training patches, the CNN employs two convolutional and pooling layers to extract features and then classify each patch based on the probabilities from the SoftMax classification layer (output-layer). Afterward, the CNN calculates the error between the classification result and the reference label, and then utilizes the backpropagation process to fine-tune all the layer parameters to minimize this error using batch gradient descent algorithm. We validated our proposed technique on ex-vivo OCT images of human oral tissues (enamel, cortical-bone, trabecular-bone, muscular-tissue, and fatty-tissue), which attested to effectiveness of our proposed method.

Coherent detection and digital signal processing for fiber optic communications

NASA Astrophysics Data System (ADS)

Ip, Ezra

The drive towards higher spectral efficiency in optical fiber systems has generated renewed interest in coherent detection. We review different detection methods, including noncoherent, differentially coherent, and coherent detection, as well as hybrid detection methods. We compare the modulation methods that are enabled and their respective performances in a linear regime. An important system parameter is the number of degrees of freedom (DOF) utilized in transmission. Polarization-multiplexed quadrature-amplitude modulation maximizes spectral efficiency and power efficiency as it uses all four available DOF contained in the two field quadratures in the two polarizations. Dual-polarization homodyne or heterodyne downconversion are linear processes that can fully recover the received signal field in these four DOF. When downconverted signals are sampled at the Nyquist rate, compensation of transmission impairments can be performed using digital signal processing (DSP). Software based receivers benefit from the robustness of DSP, flexibility in design, and ease of adaptation to time-varying channels. Linear impairments, including chromatic dispersion (CD) and polarization-mode dispersion (PMD), can be compensated quasi-exactly using finite impulse response filters. In practical systems, sampling the received signal at 3/2 times the symbol rate is sufficient to enable an arbitrary amount of CD and PMD to be compensated for a sufficiently long equalizer whose tap length scales linearly with transmission distance. Depending on the transmitted constellation and the target bit error rate, the analog-to-digital converter (ADC) should have around 5 to 6 bits of resolution. Digital coherent receivers are naturally suited for the implementation of feedforward carrier recovery, which has superior linewidth tolerance than phase-locked loops, and does not suffer from feedback delay constraints. Differential bit encoding can be used to prevent catastrophic receiver failure due to cycle slips. In systems where nonlinear effects are concentrated mostly at fiber locations with small accumulated dispersion, nonlinear phase de-rotation is a low-complexity algorithm that can partially mitigate nonlinear effects. For systems with arbitrary dispersion maps, however, backpropagation is the only universal technique that can jointly compensate dispersion and fiber nonlinearity. Backpropagation requires solving the nonlinear Schrodinger equation at the receiver, and has high computational cost. Backpropagation is most effective when dispersion compensation fibers are removed, and when signal processing is performed at three times oversampling. Backpropagation can improve system performance and increase transmission distance. With anticipated advances in analog-to-digital converters and integrated circuit technology, DSP-based coherent receivers at bit rates up to 100 Gb/s should become practical in the near future.

The probabilistic neural network architecture for high speed classification of remotely sensed imagery

NASA Technical Reports Server (NTRS)

Chettri, Samir R.; Cromp, Robert F.

1993-01-01

In this paper we discuss a neural network architecture (the Probabilistic Neural Net or the PNN) that, to the best of our knowledge, has not previously been applied to remotely sensed data. The PNN is a supervised non-parametric classification algorithm as opposed to the Gaussian maximum likelihood classifier (GMLC). The PNN works by fitting a Gaussian kernel to each training point. The width of the Gaussian is controlled by a tuning parameter called the window width. If very small widths are used, the method is equivalent to the nearest neighbor method. For large windows, the PNN behaves like the GMLC. The basic implementation of the PNN requires no training time at all. In this respect it is far better than the commonly used backpropagation neural network which can be shown to take O(N6) time for training where N is the dimensionality of the input vector. In addition the PNN can be implemented in a feed forward mode in hardware. The disadvantage of the PNN is that it requires all the training data to be stored. Some solutions to this problem are discussed in the paper. Finally, we discuss the accuracy of the PNN with respect to the GMLC and the backpropagation neural network (BPNN). The PNN is shown to be better than GMLC and not as good as the BPNN with regards to classification accuracy.

Supervised artificial neural network-based method for conversion of solar radiation data (case study: Algeria)

NASA Astrophysics Data System (ADS)

Laidi, Maamar; Hanini, Salah; Rezrazi, Ahmed; Yaiche, Mohamed Redha; El Hadj, Abdallah Abdallah; Chellali, Farouk

2017-04-01

In this study, a backpropagation artificial neural network (BP-ANN) model is used as an alternative approach to predict solar radiation on tilted surfaces (SRT) using a number of variables involved in physical process. These variables are namely the latitude of the site, mean temperature and relative humidity, Linke turbidity factor and Angstrom coefficient, extraterrestrial solar radiation, solar radiation data measured on horizontal surfaces (SRH), and solar zenith angle. Experimental solar radiation data from 13 stations spread all over Algeria around the year (2004) were used for training/validation and testing the artificial neural networks (ANNs), and one station was used to make the interpolation of the designed ANN. The ANN model was trained, validated, and tested using 60, 20, and 20 % of all data, respectively. The configuration 8-35-1 (8 inputs, 35 hidden, and 1 output neurons) presented an excellent agreement between the prediction and the experimental data during the test stage with determination coefficient of 0.99 and root meat squared error of 5.75 Wh/m2, considering a three-layer feedforward backpropagation neural network with Levenberg-Marquardt training algorithm, a hyperbolic tangent sigmoid and linear transfer function at the hidden and the output layer, respectively. This novel model could be used by researchers or scientists to design high-efficiency solar devices that are usually tilted at an optimum angle to increase the solar incident on the surface.

Machinery Monitoring and Diagnostics Using Pseudo Wigner-Ville Distribution and Backpropagation Neural Network

DTIC Science & Technology

1993-09-01

frequency, which when used as an input to an artificial neural network will aide in the detection of location and severity of machinery faults...Research is presented where the union of an artificial neural network , utilizing the highly successful backpropagation paradigm, and the pseudo wigner

Deep Learning: A Primer for Radiologists.

PubMed

Chartrand, Gabriel; Cheng, Phillip M; Vorontsov, Eugene; Drozdzal, Michal; Turcotte, Simon; Pal, Christopher J; Kadoury, Samuel; Tang, An

2017-01-01

Deep learning is a class of machine learning methods that are gaining success and attracting interest in many domains, including computer vision, speech recognition, natural language processing, and playing games. Deep learning methods produce a mapping from raw inputs to desired outputs (eg, image classes). Unlike traditional machine learning methods, which require hand-engineered feature extraction from inputs, deep learning methods learn these features directly from data. With the advent of large datasets and increased computing power, these methods can produce models with exceptional performance. These models are multilayer artificial neural networks, loosely inspired by biologic neural systems. Weighted connections between nodes (neurons) in the network are iteratively adjusted based on example pairs of inputs and target outputs by back-propagating a corrective error signal through the network. For computer vision tasks, convolutional neural networks (CNNs) have proven to be effective. Recently, several clinical applications of CNNs have been proposed and studied in radiology for classification, detection, and segmentation tasks. This article reviews the key concepts of deep learning for clinical radiologists, discusses technical requirements, describes emerging applications in clinical radiology, and outlines limitations and future directions in this field. Radiologists should become familiar with the principles and potential applications of deep learning in medical imaging. © RSNA, 2017.

Hebbian based learning with winner-take-all for spiking neural networks

NASA Astrophysics Data System (ADS)

Gupta, Ankur; Long, Lyle

2009-03-01

Learning methods for spiking neural networks are not as well developed as the traditional neural networks that widely use back-propagation training. We propose and implement a Hebbian based learning method with winner-take-all competition for spiking neural networks. This approach is spike time dependent which makes it naturally well suited for a network of spiking neurons. Homeostasis with Hebbian learning is implemented which ensures stability and quicker learning. Homeostasis implies that the net sum of incoming weights associated with a neuron remains the same. Winner-take-all is also implemented for competitive learning between output neurons. We implemented this learning rule on a biologically based vision processing system that we are developing, and use layers of leaky integrate and fire neurons. The network when presented with 4 bars (or Gabor filters) of different orientation learns to recognize the bar orientations (or Gabor filters). After training, each output neuron learns to recognize a bar at specific orientation and responds by firing more vigorously to that bar and less vigorously to others. These neurons are found to have bell shaped tuning curves and are similar to the simple cells experimentally observed by Hubel and Wiesel in the striate cortex of cat and monkey.

Retrieval of ice thickness from polarimetric SAR data

NASA Technical Reports Server (NTRS)

Kwok, R.; Yueh, S. H.; Nghiem, S. V.; Huynh, D. D.

1993-01-01

We describe a potential procedure for retrieving ice thickness from multi-frequency polarimetric SAR data for thin ice. This procedure includes first masking out the thicker ice types with a simple classifier and then deriving the thickness of the remaining pixels using a model-inversion technique. The technique used to derive ice thickness from polarimetric observations is provided by a numerical estimator or neural network. A three-layer perceptron implemented with the backpropagation algorithm is used in this investigation with several improved aspects for a faster convergence rate and a better accuracy of the neural network. These improvements include weight initialization, normalization of the output range, the selection of offset constant, and a heuristic learning algorithm. The performance of the neural network is demonstrated by using training data generated by a theoretical scattering model for sea ice matched to the database of interest. The training data are comprised of the polarimetric backscattering coefficients of thin ice and the corresponding input ice parameters to the scattering model. The retrieved ice thickness from the theoretical backscattering coefficients is compare with the input ice thickness to the scattering model to illustrate the accuracy of the inversion method. Results indicate that the network convergence rate and accuracy are higher when multi-frequency training sets are presented. In addition, the dominant backscattering coefficients in retrieving ice thickness are found by comparing the behavior of the network trained backscattering data at various incidence angels. After the neural network is trained with the theoretical backscattering data at various incidence anges, the interconnection weights between nodes are saved and applied to the experimental data to be investigated. In this paper, we illustrate the effectiveness of this technique using polarimetric SAR data collected by the JPL DC-8 radar over a sea ice scene.

Neural network modeling and prediction of resistivity structures using VES Schlumberger data over a geothermal area

NASA Astrophysics Data System (ADS)

Singh, Upendra K.; Tiwari, R. K.; Singh, S. B.

2013-03-01

This paper presents the effects of several parameters on the artificial neural networks (ANN) inversion of vertical electrical sounding (VES) data. Sensitivity of ANN parameters was examined on the performance of adaptive backpropagation (ABP) and Levenberg-Marquardt algorithms (LMA) to test the robustness to noisy synthetic as well as field geophysical data and resolving capability of these methods for predicting the subsurface resistivity layers. We trained, tested and validated ANN using the synthetic VES data as input to the networks and layer parameters of the models as network output. ANN learning parameters are varied and corresponding observations are recorded. The sensitivity analysis of synthetic data and real model demonstrate that ANN algorithms applied in VES data inversion should be considered well not only in terms of accuracy but also in terms of high computational efforts. Also the analysis suggests that ANN model with its various controlling parameters are largely data dependent and hence no unique architecture can be designed for VES data analysis. ANN based methods are also applied to the actual VES field data obtained from the tectonically vital geothermal areas of Jammu and Kashmir, India. Analysis suggests that both the ABP and LMA are suitable methods for 1-D VES modeling. But the LMA method provides greater degree of robustness than the ABP in case of 2-D VES modeling. Comparison of the inversion results with known lithology correlates well and also reveals the additional significant feature of reconsolidated breccia of about 7.0 m thickness beneath the overburden in some cases like at sounding point RDC-5. We may therefore conclude that ANN based methods are significantly faster and efficient for detection of complex layered resistivity structures with a relatively greater degree of precision and resolution.

HyFIS: adaptive neuro-fuzzy inference systems and their application to nonlinear dynamical systems.

PubMed

Kim, J; Kasabov, N

1999-11-01

This paper proposes an adaptive neuro-fuzzy system, HyFIS (Hybrid neural Fuzzy Inference System), for building and optimising fuzzy models. The proposed model introduces the learning power of neural networks to fuzzy logic systems and provides linguistic meaning to the connectionist architectures. Heuristic fuzzy logic rules and input-output fuzzy membership functions can be optimally tuned from training examples by a hybrid learning scheme comprised of two phases: rule generation phase from data; and rule tuning phase using error backpropagation learning scheme for a neural fuzzy system. To illustrate the performance and applicability of the proposed neuro-fuzzy hybrid model, extensive simulation studies of nonlinear complex dynamic systems are carried out. The proposed method can be applied to an on-line incremental adaptive learning for the prediction and control of nonlinear dynamical systems. Two benchmark case studies are used to demonstrate that the proposed HyFIS system is a superior neuro-fuzzy modelling technique.

Quantum machine learning with glow for episodic tasks and decision games

NASA Astrophysics Data System (ADS)

Clausen, Jens; Briegel, Hans J.

2018-02-01

We consider a general class of models, where a reinforcement learning (RL) agent learns from cyclic interactions with an external environment via classical signals. Perceptual inputs are encoded as quantum states, which are subsequently transformed by a quantum channel representing the agent's memory, while the outcomes of measurements performed at the channel's output determine the agent's actions. The learning takes place via stepwise modifications of the channel properties. They are described by an update rule that is inspired by the projective simulation (PS) model and equipped with a glow mechanism that allows for a backpropagation of policy changes, analogous to the eligibility traces in RL and edge glow in PS. In this way, the model combines features of PS with the ability for generalization, offered by its physical embodiment as a quantum system. We apply the agent to various setups of an invasion game and a grid world, which serve as elementary model tasks allowing a direct comparison with a basic classical PS agent.

Fuzzy recognition of noncompact musical objects

NASA Astrophysics Data System (ADS)

Cristobal Salas, Alfredo; Tchernykh, Andrei

1997-03-01

This article describes and compares some techniques to extract attributes from black and white images which contain musical objects. The inertia moment, the central moments and the wavelet transform methods are used to describe the images. Two supervised neural networks are applied to classify the images: backpropagation and fuzzy backpropagation. The results are compared.

Impact of Linearity and Write Noise of Analog Resistive Memory Devices in a Neural Algorithm Accelerator

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

Jacobs-Gedrim, Robin B.; Agarwal, Sapan; Knisely, Kathrine E.

Resistive memory (ReRAM) shows promise for use as an analog synapse element in energy-efficient neural network algorithm accelerators. A particularly important application is the training of neural networks, as this is the most computationally-intensive procedure in using a neural algorithm. However, training a network with analog ReRAM synapses can significantly reduce the accuracy at the algorithm level. In order to assess this degradation, analog properties of ReRAM devices were measured and hand-written digit recognition accuracy was modeled for the training using backpropagation. Bipolar filamentary devices utilizing three material systems were measured and compared: one oxygen vacancy system, Ta-TaO x, andmore » two conducting metallization systems, Cu-SiO 2, and Ag/chalcogenide. Analog properties and conductance ranges of the devices are optimized by measuring the response to varying voltage pulse characteristics. Key analog device properties which degrade the accuracy are update linearity and write noise. Write noise may improve as a function of device manufacturing maturity, but write nonlinearity appears relatively consistent among the different device material systems and is found to be the most significant factor affecting accuracy. As a result, this suggests that new materials and/or fundamentally different resistive switching mechanisms may be required to improve device linearity and achieve higher algorithm training accuracy.« less

Impact of Linearity and Write Noise of Analog Resistive Memory Devices in a Neural Algorithm Accelerator

DOE PAGES

Jacobs-Gedrim, Robin B.; Agarwal, Sapan; Knisely, Kathrine E.; ...

2017-12-01

Resistive memory (ReRAM) shows promise for use as an analog synapse element in energy-efficient neural network algorithm accelerators. A particularly important application is the training of neural networks, as this is the most computationally-intensive procedure in using a neural algorithm. However, training a network with analog ReRAM synapses can significantly reduce the accuracy at the algorithm level. In order to assess this degradation, analog properties of ReRAM devices were measured and hand-written digit recognition accuracy was modeled for the training using backpropagation. Bipolar filamentary devices utilizing three material systems were measured and compared: one oxygen vacancy system, Ta-TaO x, andmore » two conducting metallization systems, Cu-SiO 2, and Ag/chalcogenide. Analog properties and conductance ranges of the devices are optimized by measuring the response to varying voltage pulse characteristics. Key analog device properties which degrade the accuracy are update linearity and write noise. Write noise may improve as a function of device manufacturing maturity, but write nonlinearity appears relatively consistent among the different device material systems and is found to be the most significant factor affecting accuracy. As a result, this suggests that new materials and/or fundamentally different resistive switching mechanisms may be required to improve device linearity and achieve higher algorithm training accuracy.« less

Inversion of 2-D DC resistivity data using rapid optimization and minimal complexity neural network

NASA Astrophysics Data System (ADS)

Singh, U. K.; Tiwari, R. K.; Singh, S. B.

2010-02-01

The backpropagation (BP) artificial neural network (ANN) technique of optimization based on steepest descent algorithm is known to be inept for its poor performance and does not ensure global convergence. Nonlinear and complex DC resistivity data require efficient ANN model and more intensive optimization procedures for better results and interpretations. Improvements in the computational ANN modeling process are described with the goals of enhancing the optimization process and reducing ANN model complexity. Well-established optimization methods, such as Radial basis algorithm (RBA) and Levenberg-Marquardt algorithms (LMA) have frequently been used to deal with complexity and nonlinearity in such complex geophysical records. We examined here the efficiency of trained LMA and RB networks by using 2-D synthetic resistivity data and then finally applied to the actual field vertical electrical resistivity sounding (VES) data collected from the Puga Valley, Jammu and Kashmir, India. The resulting ANN reconstruction resistivity results are compared with the result of existing inversion approaches, which are in good agreement. The depths and resistivity structures obtained by the ANN methods also correlate well with the known drilling results and geologic boundaries. The application of the above ANN algorithms proves to be robust and could be used for fast estimation of resistive structures for other complex earth model also.

Selection and collection of multi parameter physiological data for cardiac rhythm diagnostic algorithm development

NASA Astrophysics Data System (ADS)

Bostock, J.; Weller, P.; Cooklin, M.

2010-07-01

Automated diagnostic algorithms are used in implantable cardioverter-defibrillators (ICD's) to detect abnormal heart rhythms. Algorithms misdiagnose and improved specificity is needed to prevent inappropriate therapy. Knowledge engineering (KE) and artificial intelligence (AI) could improve this. A pilot study of KE was performed with artificial neural network (ANN) as AI system. A case note review analysed arrhythmic events stored in patients ICD memory. 13.2% patients received inappropriate therapy. The best ICD algorithm had sensitivity 1.00, specificity 0.69 (p<0.001 different to gold standard). A subset of data was used to train and test an ANN. A feed-forward, back-propagation network with 7 inputs, a 4 node hidden layer and 1 output had sensitivity 1.00, specificity 0.71 (p<0.001). A prospective study was performed using KE to list arrhythmias, factors and indicators for which measurable parameters were evaluated and results reviewed by a domain expert. Waveforms from electrodes in the heart and thoracic bio-impedance; temperature and motion data were collected from 65 patients during cardiac electrophysiological studies. 5 incomplete datasets were due to technical failures. We concluded that KE successfully guided selection of parameters and ANN produced a usable system and that complex data collection carries greater risk of technical failure, leading to data loss.

Multi-objective optimization of a low specific speed centrifugal pump using an evolutionary algorithm

NASA Astrophysics Data System (ADS)

An, Zhao; Zhounian, Lai; Peng, Wu; Linlin, Cao; Dazhuan, Wu

2016-07-01

This paper describes the shape optimization of a low specific speed centrifugal pump at the design point. The target pump has already been manually modified on the basis of empirical knowledge. A genetic algorithm (NSGA-II) with certain enhancements is adopted to improve its performance further with respect to two goals. In order to limit the number of design variables without losing geometric information, the impeller is parametrized using the Bézier curve and a B-spline. Numerical simulation based on a Reynolds averaged Navier-Stokes (RANS) turbulent model is done in parallel to evaluate the flow field. A back-propagating neural network is constructed as a surrogate for performance prediction to save computing time, while initial samples are selected according to an orthogonal array. Then global Pareto-optimal solutions are obtained and analysed. The results manifest that unexpected flow structures, such as the secondary flow on the meridian plane, have diminished or vanished in the optimized pump.

[Portable Epileptic Seizure Monitoring Intelligent System Based on Android System].

PubMed

Liang, Zhenhu; Wu, Shufeng; Yang, Chunlin; Jiang, Zhenzhou; Yu, Tao; Lu, Chengbiao; Li, Xiaoli

2016-02-01

The clinical electroencephalogram (EEG) monitoring systems based on personal computer system can not meet the requirements of portability and home usage. The epilepsy patients have to be monitored in hospital for an extended period of time, which imposes a heavy burden on hospitals. In the present study, we designed a portable 16-lead networked monitoring system based on the Android smart phone. The system uses some technologies including the active electrode, the WiFi wireless transmission, the multi-scale permutation entropy (MPE) algorithm, the back-propagation (BP) neural network algorithm, etc. Moreover, the software of Android mobile application can realize the processing and analysis of EEG data, the display of EEG waveform and the alarm of epileptic seizure. The system has been tested on the mobile phones with Android 2. 3 operating system or higher version and the results showed that this software ran accurately and steadily in the detection of epileptic seizure. In conclusion, this paper provides a portable and reliable solution for epileptic seizure monitoring in clinical and home applications.

Due Date Assignment in a Dynamic Job Shop with the Orthogonal Kernel Least Squares Algorithm

NASA Astrophysics Data System (ADS)

Yang, D. H.; Hu, L.; Qian, Y.

2017-06-01

Meeting due dates is a key goal in the manufacturing industries. This paper proposes a method for due date assignment (DDA) by using the Orthogonal Kernel Least Squares Algorithm (OKLSA). A simulation model is built to imitate the production process of a highly dynamic job shop. Several factors describing job characteristics and system state are extracted as attributes to predict job flow-times. A number of experiments under conditions of varying dispatching rules and 90% shop utilization level have been carried out to evaluate the effectiveness of OKLSA applied for DDA. The prediction performance of OKLSA is compared with those of five conventional DDA models and back-propagation neural network (BPNN). The experimental results indicate that OKLSA is statistically superior to other DDA models in terms of mean absolute lateness and root mean squares lateness in most cases. The only exception occurs when the shortest processing time rule is used for dispatching jobs, the difference between OKLSA and BPNN is not statistically significant.

Evolving RBF neural networks for adaptive soft-sensor design.

PubMed

Alexandridis, Alex

2013-12-01

This work presents an adaptive framework for building soft-sensors based on radial basis function (RBF) neural network models. The adaptive fuzzy means algorithm is utilized in order to evolve an RBF network, which approximates the unknown system based on input-output data from it. The methodology gradually builds the RBF network model, based on two separate levels of adaptation: On the first level, the structure of the hidden layer is modified by adding or deleting RBF centers, while on the second level, the synaptic weights are adjusted with the recursive least squares with exponential forgetting algorithm. The proposed approach is tested on two different systems, namely a simulated nonlinear DC Motor and a real industrial reactor. The results show that the produced soft-sensors can be successfully applied to model the two nonlinear systems. A comparison with two different adaptive modeling techniques, namely a dynamic evolving neural-fuzzy inference system (DENFIS) and neural networks trained with online backpropagation, highlights the advantages of the proposed methodology.

Prediction of friction factor of pure water flowing inside vertical smooth and microfin tubes by using artificial neural networks

NASA Astrophysics Data System (ADS)

Çebi, A.; Akdoğan, E.; Celen, A.; Dalkilic, A. S.

2017-02-01

An artificial neural network (ANN) model of friction factor in smooth and microfin tubes under heating, cooling and isothermal conditions was developed in this study. Data used in ANN was taken from a vertically positioned heat exchanger experimental setup. Multi-layered feed-forward neural network with backpropagation algorithm, radial basis function networks and hybrid PSO-neural network algorithm were applied to the database. Inputs were the ratio of cross sectional flow area to hydraulic diameter, experimental condition number depending on isothermal, heating, or cooling conditions and mass flow rate while the friction factor was the output of the constructed system. It was observed that such neural network based system could effectively predict the friction factor values of the flows regardless of their tube types. A dependency analysis to determine the strongest parameter that affected the network and database was also performed and tube geometry was found to be the strongest parameter of all as a result of analysis.

Arrhythmia Evaluation in Wearable ECG Devices

PubMed Central

Sadrawi, Muammar; Lin, Chien-Hung; Hsieh, Yita; Kuo, Chia-Chun; Chien, Jen Chien; Haraikawa, Koichi; Abbod, Maysam F.; Shieh, Jiann-Shing

2017-01-01

This study evaluates four databases from PhysioNet: The American Heart Association database (AHADB), Creighton University Ventricular Tachyarrhythmia database (CUDB), MIT-BIH Arrhythmia database (MITDB), and MIT-BIH Noise Stress Test database (NSTDB). The ANSI/AAMI EC57:2012 is used for the evaluation of the algorithms for the supraventricular ectopic beat (SVEB), ventricular ectopic beat (VEB), atrial fibrillation (AF), and ventricular fibrillation (VF) via the evaluation of the sensitivity, positive predictivity and false positive rate. Sample entropy, fast Fourier transform (FFT), and multilayer perceptron neural network with backpropagation training algorithm are selected for the integrated detection algorithms. For this study, the result for SVEB has some improvements compared to a previous study that also utilized ANSI/AAMI EC57. In further, VEB sensitivity and positive predictivity gross evaluations have greater than 80%, except for the positive predictivity of the NSTDB database. For AF gross evaluation of MITDB database, the results show very good classification, excluding the episode sensitivity. In advanced, for VF gross evaluation, the episode sensitivity and positive predictivity for the AHADB, MITDB, and CUDB, have greater than 80%, except for MITDB episode positive predictivity, which is 75%. The achieved results show that the proposed integrated SVEB, VEB, AF, and VF detection algorithm has an accurate classification according to ANSI/AAMI EC57:2012. In conclusion, the proposed integrated detection algorithm can achieve good accuracy in comparison with other previous studies. Furthermore, more advanced algorithms and hardware devices should be performed in future for arrhythmia detection and evaluation. PMID:29068369

Neural networks for function approximation in nonlinear control

NASA Technical Reports Server (NTRS)

Linse, Dennis J.; Stengel, Robert F.

1990-01-01

Two neural network architectures are compared with a classical spline interpolation technique for the approximation of functions useful in a nonlinear control system. A standard back-propagation feedforward neural network and a cerebellar model articulation controller (CMAC) neural network are presented, and their results are compared with a B-spline interpolation procedure that is updated using recursive least-squares parameter identification. Each method is able to accurately represent a one-dimensional test function. Tradeoffs between size requirements, speed of operation, and speed of learning indicate that neural networks may be practical for identification and adaptation in a nonlinear control environment.

Computational microscopy: illumination coding and nonlinear optimization enables gigapixel 3D phase imaging

NASA Astrophysics Data System (ADS)

Tian, Lei; Waller, Laura

2017-05-01

Microscope lenses can have either large field of view (FOV) or high resolution, not both. Computational microscopy based on illumination coding circumvents this limit by fusing images from different illumination angles using nonlinear optimization algorithms. The result is a Gigapixel-scale image having both wide FOV and high resolution. We demonstrate an experimentally robust reconstruction algorithm based on a 2nd order quasi-Newton's method, combined with a novel phase initialization scheme. To further extend the Gigapixel imaging capability to 3D, we develop a reconstruction method to process the 4D light field measurements from sequential illumination scanning. The algorithm is based on a 'multislice' forward model that incorporates both 3D phase and diffraction effects, as well as multiple forward scatterings. To solve the inverse problem, an iterative update procedure that combines both phase retrieval and 'error back-propagation' is developed. To avoid local minimum solutions, we further develop a novel physical model-based initialization technique that accounts for both the geometric-optic and 1st order phase effects. The result is robust reconstructions of Gigapixel 3D phase images having both wide FOV and super resolution in all three dimensions. Experimental results from an LED array microscope were demonstrated.

Designing neuro-fuzzy controller for electromagnetic anti-lock braking system (ABS) on electric vehicle

NASA Astrophysics Data System (ADS)

Pramudijanto, Josaphat; Ashfahani, Andri; Lukito, Rian

2018-03-01

Anti-lock braking system (ABS) is used on vehicles to keep the wheels unlocked in sudden break (inside braking) and minimalize the stop distance of the vehicle. The problem of it when sudden break is the wheels locked so the vehicle steering couldn’t be controlled. The designed ABS system will be applied on ABS simulator using the electromagnetic braking. In normal condition or in condition without braking, longitudinal velocity of the vehicle will be equal with the velocity of wheel rotation, so the slip ratio will be 0 (0%) and if the velocity of wheel rotation is 0 (in locked condition) then the wheels will be slip 1 (100%). ABS system will keep the value of slip ratio so it will be 0.2 (20%). In this final assignment, the method that is used is Neuro-Fuzzy method to control the slip value on the wheels. The input is the expectable slip and the output is slip from plant. The learning algorithm which is used is Backpropagation that will work by feedforward to get actual output and work by feedback to get error value with target output. The network that was made based on fuzzy mechanism which are fuzzification, inference and defuzzification, Neuro-fuzzy controller can reduce overshoot plant respond to 43.2% compared to plant respond without controller by open loop.

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.

The application of neural networks to the SSME startup transient

NASA Technical Reports Server (NTRS)

Meyer, Claudia M.; Maul, William A.

1991-01-01

Feedforward neural networks were used to model three parameters during the Space Shuttle Main Engine startup transient. The three parameters were the main combustion chamber pressure, a controlled parameter, the high pressure oxidizer turbine discharge temperature, a redlined parameter, and the high pressure fuel pump discharge pressure, a failure-indicating performance parameter. Network inputs consisted of time windows of data from engine measurements that correlated highly to the modeled parameter. A standard backpropagation algorithm was used to train the feedforward networks on two nominal firings. Each trained network was validated with four additional nominal firings. For all three parameters, the neural networks were able to accurately predict the data in the validation sets as well as the training set.

Intelligent Machine Learning Approaches for Aerospace Applications

NASA Astrophysics Data System (ADS)

Sathyan, Anoop

Machine Learning is a type of artificial intelligence that provides machines or networks the ability to learn from data without the need to explicitly program them. There are different kinds of machine learning techniques. This thesis discusses the applications of two of these approaches: Genetic Fuzzy Logic and Convolutional Neural Networks (CNN). Fuzzy Logic System (FLS) is a powerful tool that can be used for a wide variety of applications. FLS is a universal approximator that reduces the need for complex mathematics and replaces it with expert knowledge of the system to produce an input-output mapping using If-Then rules. The expert knowledge of a system can help in obtaining the parameters for small-scale FLSs, but for larger networks we will need to use sophisticated approaches that can automatically train the network to meet the design requirements. This is where Genetic Algorithms (GA) and EVE come into the picture. Both GA and EVE can tune the FLS parameters to minimize a cost function that is designed to meet the requirements of the specific problem. EVE is an artificial intelligence developed by Psibernetix that is trained to tune large scale FLSs. The parameters of an FLS can include the membership functions and rulebase of the inherent Fuzzy Inference Systems (FISs). The main issue with using the GFS is that the number of parameters in a FIS increase exponentially with the number of inputs thus making it increasingly harder to tune them. To reduce this issue, the FLSs discussed in this thesis consist of 2-input-1-output FISs in cascade (Chapter 4) or as a layer of parallel FISs (Chapter 7). We have obtained extremely good results using GFS for different applications at a reduced computational cost compared to other algorithms that are commonly used to solve the corresponding problems. In this thesis, GFSs have been designed for controlling an inverted double pendulum, a task allocation problem of clustering targets amongst a set of UAVs, a fire detection problem and the aircraft conflict resolution problem. During the last decade, CNNs have become increasingly popular in the domain of image and speech processing. CNNs have a lot more parameters compared to GFSs that are tuned using the back-propagation algorithm. CNNs typically have hundreds of thousands or maybe millions of parameters that are tuned using common cost functions such as integral squared error, softmax loss etc. Chapter 5 discusses a classification problem to classify images as humans or not and Chapter 6 discusses a regression task using CNN for producing an approximate near-optimal route for the Traveling Salesman Problem (TSP) which is regarded as one of the most complicated decision making problem. Both the GFS and CNN are used to develop intelligent systems specific to the application providing them computational efficiency, robustness in the face of uncertainties and scalability.

Forecasting outpatient visits using empirical mode decomposition coupled with back-propagation artificial neural networks optimized by particle swarm optimization

PubMed Central

Huang, Daizheng; Wu, Zhihui

2017-01-01

Accurately predicting the trend of outpatient visits by mathematical modeling can help policy makers manage hospitals effectively, reasonably organize schedules for human resources and finances, and appropriately distribute hospital material resources. In this study, a hybrid method based on empirical mode decomposition and back-propagation artificial neural networks optimized by particle swarm optimization is developed to forecast outpatient visits on the basis of monthly numbers. The data outpatient visits are retrieved from January 2005 to December 2013 and first obtained as the original time series. Second, the original time series is decomposed into a finite and often small number of intrinsic mode functions by the empirical mode decomposition technique. Third, a three-layer back-propagation artificial neural network is constructed to forecast each intrinsic mode functions. To improve network performance and avoid falling into a local minimum, particle swarm optimization is employed to optimize the weights and thresholds of back-propagation artificial neural networks. Finally, the superposition of forecasting results of the intrinsic mode functions is regarded as the ultimate forecasting value. Simulation indicates that the proposed method attains a better performance index than the other four methods. PMID:28222194

Forecasting outpatient visits using empirical mode decomposition coupled with back-propagation artificial neural networks optimized by particle swarm optimization.

PubMed

Huang, Daizheng; Wu, Zhihui

2017-01-01

Accurately predicting the trend of outpatient visits by mathematical modeling can help policy makers manage hospitals effectively, reasonably organize schedules for human resources and finances, and appropriately distribute hospital material resources. In this study, a hybrid method based on empirical mode decomposition and back-propagation artificial neural networks optimized by particle swarm optimization is developed to forecast outpatient visits on the basis of monthly numbers. The data outpatient visits are retrieved from January 2005 to December 2013 and first obtained as the original time series. Second, the original time series is decomposed into a finite and often small number of intrinsic mode functions by the empirical mode decomposition technique. Third, a three-layer back-propagation artificial neural network is constructed to forecast each intrinsic mode functions. To improve network performance and avoid falling into a local minimum, particle swarm optimization is employed to optimize the weights and thresholds of back-propagation artificial neural networks. Finally, the superposition of forecasting results of the intrinsic mode functions is regarded as the ultimate forecasting value. Simulation indicates that the proposed method attains a better performance index than the other four methods.

Non-binary LDPC-coded modulation for high-speed optical metro networks with backpropagation

NASA Astrophysics Data System (ADS)

Arabaci, Murat; Djordjevic, Ivan B.; Saunders, Ross; Marcoccia, Roberto M.

2010-01-01

To simultaneously mitigate the linear and nonlinear channel impairments in high-speed optical communications, we propose the use of non-binary low-density-parity-check-coded modulation in combination with a coarse backpropagation method. By employing backpropagation, we reduce the memory in the channel and in return obtain significant reductions in the complexity of the channel equalizer which is exponentially proportional to the channel memory. We then compensate for the remaining channel distortions using forward error correction based on non-binary LDPC codes. We propose non-binary-LDPC-coded modulation scheme because, compared to bit-interleaved binary-LDPC-coded modulation scheme employing turbo equalization, the proposed scheme lowers the computational complexity and latency of the overall system while providing impressively larger coding gains.

Ethnomathematics elements in Batik Bali using backpropagation method

NASA Astrophysics Data System (ADS)

Lestari, Mei; Irawan, Ari; Rahayu, Wanti; Wayan Parwati, Ni

2018-05-01

Batik is one of traditional arts that has been established by the UNESCO as Indonesia’s cultural heritage. Batik has varieties and motifs, and each motifs has its own uniqueness but seems similar, that makes it difficult to identify. This study aims to develop an application that can identify typical batik Bali with etnomatematics elements on it. Etnomatematics is a study that shows relation between culture and mathematics concepts. Etnomatematics in Batik Bali is more to geometrical concept in line of strong Balinese culture element. The identification process is use backpropagation method. Steps of backpropagation methods are image processing (including scalling and tresholding image process). Next step is insert the processed image to an artificial neural network. This study resulted an accuracy of identification of batik Bali that has Etnomatematics elements on it.

A mathematical theory of shape and neuro-fuzzy methodology-based diagnostic analysis: a comparative study on early detection and treatment planning of brain cancer.

PubMed

Kar, Subrata; Majumder, D Dutta

2017-08-01

Investigation of brain cancer can detect the abnormal growth of tissue in the brain using computed tomography (CT) scans and magnetic resonance (MR) images of patients. The proposed method classifies brain cancer on shape-based feature extraction as either benign or malignant. The authors used input variables such as shape distance (SD) and shape similarity measure (SSM) in fuzzy tools, and used fuzzy rules to evaluate the risk status as an output variable. We presented a classifier neural network system (NNS), namely Levenberg-Marquardt (LM), which is a feed-forward back-propagation learning algorithm used to train the NN for the status of brain cancer, if any, and which achieved satisfactory performance with 100% accuracy. The proposed methodology is divided into three phases. First, we find the region of interest (ROI) in the brain to detect the tumors using CT and MR images. Second, we extract the shape-based features, like SD and SSM, and grade the brain tumors as benign or malignant with the concept of SD function and SSM as shape-based parameters. Third, we classify the brain cancers using neuro-fuzzy tools. In this experiment, we used a 16-sample database with SSM (μ) values and classified the benignancy or malignancy of the brain tumor lesions using the neuro-fuzzy system (NFS). We have developed a fuzzy expert system (FES) and NFS for early detection of brain cancer from CT and MR images. In this experiment, shape-based features, such as SD and SSM, were extracted from the ROI of brain tumor lesions. These shape-based features were considered as input variables and, using fuzzy rules, we were able to evaluate brain cancer risk values for each case. We used an NNS with LM, a feed-forward back-propagation learning algorithm, as a classifier for the diagnosis of brain cancer and achieved satisfactory performance with 100% accuracy. The proposed network was trained with MR image datasets of 16 cases. The 16 cases were fed to the ANN with 2 input neurons, one hidden layer of 10 neurons and 2 output neurons. Of the 16-sample database, 10 datasets for training, 3 datasets for validation, and 3 datasets for testing were used in the ANN classification system. From the SSM (µ) confusion matrix, the number of output datasets of true positive, false positive, true negative and false negative was 6, 0, 10, and 0, respectively. The sensitivity, specificity and accuracy were each equal to 100%. The method of diagnosing brain cancer presented in this study is a successful model to assist doctors in the screening and treatment of brain cancer patients. The presented FES successfully identified the presence of brain cancer in CT and MR images using the extracted shape-based features and the use of NFS for the identification of brain cancer in the early stages. From the analysis and diagnosis of the disease, the doctors can decide the stage of cancer and take the necessary steps for more accurate treatment. Here, we have presented an investigation and comparison study of the shape-based feature extraction method with the use of NFS for classifying brain tumors as showing normal or abnormal patterns. The results have proved that the shape-based features with the use of NFS can achieve a satisfactory performance with 100% accuracy. We intend to extend this methodology for the early detection of cancer in other regions such as the prostate region and human cervix.

A neural network construction method for surrogate modeling of physics-based analysis

NASA Astrophysics Data System (ADS)

Sung, Woong Je

In this thesis existing methodologies related to the developmental methods of neural networks have been surveyed and their approaches to network sizing and structuring are carefully observed. This literature review covers the constructive methods, the pruning methods, and the evolutionary methods and questions about the basic assumption intrinsic to the conventional neural network learning paradigm, which is primarily devoted to optimization of connection weights (or synaptic strengths) for the pre-determined connection structure of the network. The main research hypothesis governing this thesis is that, without breaking a prevailing dichotomy between weights and connectivity of the network during learning phase, the efficient design of a task-specific neural network is hard to achieve because, as long as connectivity and weights are searched by separate means, a structural optimization of the neural network requires either repetitive re-training procedures or computationally expensive topological meta-search cycles. The main contribution of this thesis is designing and testing a novel learning mechanism which efficiently learns not only weight parameters but also connection structure from a given training data set, and positioning this learning mechanism within the surrogate modeling practice. In this work, a simple and straightforward extension to the conventional error Back-Propagation (BP) algorithm has been formulated to enable a simultaneous learning for both connectivity and weights of the Generalized Multilayer Perceptron (GMLP) in supervised learning tasks. A particular objective is to achieve a task-specific network having reasonable generalization performance with a minimal training time. The dichotomy between architectural design and weight optimization is reconciled by a mechanism establishing a new connection for a neuron pair which has potentially higher error-gradient than one of the existing connections. Interpreting an instance of the absence of connection as a zero-weight connection, the potential contribution to training error reduction of any present or absent connection can readily be evaluated using the BP algorithm. Instead of being broken, the connections that contribute less remain frozen with constant weight values optimized to that point but they are excluded from further weight optimization until reselected. In this way, a selective weight optimization is executed only for the dynamically maintained pool of high gradient connections. By searching the rapidly changing weights and concentrating optimization resources on them, the learning process is accelerated without either a significant increase in computational cost or a need for re-training. This results in a more task-adapted network connection structure. Combined with another important criterion for the division of a neuron which adds a new computational unit to a network, a highly fitted network can be grown out of the minimal random structure. This particular learning strategy can belong to a more broad class of the variable connectivity learning scheme and the devised algorithm has been named Optimal Brain Growth (OBG). The OBG algorithm has been tested on two canonical problems; a regression analysis using the Complicated Interaction Regression Function and a classification of the Two-Spiral Problem. A comparative study with conventional Multilayer Perceptrons (MLPs) consisting of single- and double-hidden layers shows that OBG is less sensitive to random initial conditions and generalizes better with only a minimal increase in computational time. This partially proves that a variable connectivity learning scheme has great potential to enhance computational efficiency and reduce efforts to select proper network architecture. To investigate the applicability of the OBG to more practical surrogate modeling tasks, the geometry-to-pressure mapping of a particular class of airfoils in the transonic flow regime has been sought using both the conventional MLP networks with pre-defined architecture and the OBG-developed networks started from the same initial MLP networks. Considering wide variety in airfoil geometry and diversity of flow conditions distributed over a range of flow Mach numbers and angles of attack, the new method shows a great potential to capture fundamentally nonlinear flow phenomena especially related to the occurrence of shock waves on airfoil surfaces in transonic flow regime. (Abstract shortened by UMI.).

Partially pre-calculated weights for the backpropagation learning regime and high accuracy function mapping using continuous input RAM-based sigma-pi nets.

PubMed

Neville, R S; Stonham, T J; Glover, R J

2000-01-01

In this article we present a methodology that partially pre-calculates the weight updates of the backpropagation learning regime and obtains high accuracy function mapping. The paper shows how to implement neural units in a digital formulation which enables the weights to be quantised to 8-bits and the activations to 9-bits. A novel methodology is introduced to enable the accuracy of sigma-pi units to be increased by expanding their internal state space. We, also, introduce a novel means of implementing bit-streams in ring memories instead of utilising shift registers. The investigation utilises digital "Higher Order" sigma-pi nodes and studies continuous input RAM-based sigma-pi units. The units are trained with the backpropagation learning regime to learn functions to a high accuracy. The neural model is the sigma-pi units which can be implemented in digital microelectronic technology. The ability to perform tasks that require the input of real-valued information, is one of the central requirements of any cognitive system that utilises artificial neural network methodologies. In this article we present recent research which investigates a technique that can be used for mapping accurate real-valued functions to RAM-nets. One of our goals was to achieve accuracies of better than 1% for target output functions in the range Y epsilon [0,1], this is equivalent to an average Mean Square Error (MSE) over all training vectors of 0.0001 or an error modulus of 0.01. We present a development of the sigma-pi node which enables the provision of high accuracy outputs. The sigma-pi neural model was initially developed by Gurney (Learning in nets of structured hypercubes. PhD Thesis, Department of Electrical Engineering, Brunel University, Middlessex, UK, 1989; available as Technical Memo CN/R/144). Gurney's neuron models, the Time Integration Node (TIN), utilises an activation that was derived from a bit-stream. In this article we present a new methodology for storing sigma-pi node's activations as single values which are averages. In the course of the article we state what we define as a real number; how we represent real numbers and input of continuous values in our neural system. We show how to utilise the bounded quantised site-values (weights) of sigma-pi nodes to make training of these neurocomputing systems simple, using pre-calculated look-up tables to train the nets. In order to meet our accuracy goal, we introduce a means of increasing the bandwidth capability of sigma-pi units by expanding their internal state-space. In our implementation we utilise bit-streams when we calculate the real-valued outputs of the net. To simplify the hardware implementation of bit-streams we present a method of mapping them to RAM-based hardware using 'ring memories'. Finally, we study the sigma-pi units' ability to generalise once they are trained to map real-valued, high accuracy, continuous functions. We use sigma-pi units as they have been shown to have shorter training times than their analogue counterparts and can also overcome some of the drawbacks of semi-linear units (Gurney, 1992. Neural Networks, 5, 289-303).

Inversion of surface parameters using fast learning neural networks

NASA Technical Reports Server (NTRS)

Dawson, M. S.; Olvera, J.; Fung, A. K.; Manry, M. T.

1992-01-01

A neural network approach to the inversion of surface scattering parameters is presented. Simulated data sets based on a surface scattering model are used so that the data may be viewed as taken from a completely known randomly rough surface. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) are tested on the simulated backscattering data. The RMS error of training the FL network is found to be less than one half the error of the BP network while requiring one to two orders of magnitude less CPU time. When applied to inversion of parameters from a statistically rough surface, the FL method is successful at recovering the surface permittivity, the surface correlation length, and the RMS surface height in less time and with less error than the BP network. Further applications of the FL neural network to the inversion of parameters from backscatter measurements of an inhomogeneous layer above a half space are shown.

Creating Turbulent Flow Realizations with Generative Adversarial Networks

NASA Astrophysics Data System (ADS)

King, Ryan; Graf, Peter; Chertkov, Michael

2017-11-01

Generating valid inflow conditions is a crucial, yet computationally expensive, step in unsteady turbulent flow simulations. We demonstrate a new technique for rapid generation of turbulent inflow realizations that leverages recent advances in machine learning for image generation using a deep convolutional generative adversarial network (DCGAN). The DCGAN is an unsupervised machine learning technique consisting of two competing neural networks that are trained against each other using backpropagation. One network, the generator, tries to produce samples from the true distribution of states, while the discriminator tries to distinguish between true and synthetic samples. We present results from a fully-trained DCGAN that is able to rapidly draw random samples from the full distribution of possible inflow states without needing to solve the Navier-Stokes equations, eliminating the costly process of spinning up inflow turbulence. This suggests a new paradigm in physics informed machine learning where the turbulence physics can be encoded in either the discriminator or generator. Finally, we also propose additional applications such as feature identification and subgrid scale modeling.

The A-Current Modulates Learning via NMDA Receptors Containing the NR2B Subunit

PubMed Central

Fontán-Lozano, Ángela; Suárez-Pereira, Irene; González-Forero, David; Carrión, Ángel Manuel

2011-01-01

Synaptic plasticity involves short- and long-term events, although the molecular mechanisms that underlie these processes are not fully understood. The transient A-type K+ current (IA) controls the excitability of the dendrites from CA1 pyramidal neurons by regulating the back-propagation of action potentials and shaping synaptic input. Here, we have studied how decreases in IA affect cognitive processes and synaptic plasticity. Using wild-type mice treated with 4-AP, an IA inhibitor, and mice lacking the DREAM protein, a transcriptional repressor and modulator of the IA, we demonstrate that impairment of IA decreases the stimulation threshold for learning and the induction of early-LTP. Hippocampal electrical recordings in both models revealed alterations in basal electrical oscillatory properties toward low-theta frequencies. In addition, we demonstrated that the facilitated learning induced by decreased IA requires the activation of NMDA receptors containing the NR2B subunit. Together, these findings point to a balance between the IA and the activity of NR2B-containing NMDA receptors in the regulation of learning. PMID:21966384

Size invariance does not hold for connectionist models: dangers of using a toy model.

PubMed

Yamaguchi, Makoto

2004-03-01

Connectionist models with backpropagation learning rule are known to have a serious problem called catastrophic interference or forgetting, although there have been several reports showing that the interference can be relatively mild with orthogonal inputs. The present study investigated the extent of interference using orthogonal inputs with varying network sizes. One would naturally assume that results obtained from small networks could be extrapolated for larger networks. Unexpectedly, the use of small networks was shown to worsen performance. This result has important implications for interpreting some data in the literature and cautions against the use of a toy model. Copyright 2004 Lippincott Williams & Wilkins

Application of artificial neural network for heat transfer in porous cone

NASA Astrophysics Data System (ADS)

Athani, Abdulgaphur; Ahamad, N. Ameer; Badruddin, Irfan Anjum

2018-05-01

Heat transfer in porous medium is one of the classical areas of research that has been active for many decades. The heat transfer in porous medium is generally studied by using numerical methods such as finite element method; finite difference method etc. that solves coupled partial differential equations by converting them into simpler forms. The current work utilizes an alternate method known as artificial neural network that mimics the learning characteristics of neurons. The heat transfer in porous medium fixed in a cone is predicted using backpropagation neural network. The artificial neural network is able to predict this behavior quite accurately.

Recognition of Roasted Coffee Bean Levels using Image Processing and Neural Network

NASA Astrophysics Data System (ADS)

Nasution, T. H.; Andayani, U.

2017-03-01

The coffee beans roast levels have some characteristics. However, some people cannot recognize the coffee beans roast level. In this research, we propose to design a method to recognize the coffee beans roast level of images digital by processing the image and classifying with backpropagation neural network. The steps consist of how to collect the images data with image acquisition, pre-processing, feature extraction using Gray Level Co-occurrence Matrix (GLCM) method and finally normalization of data extraction using decimal scaling features. The values of decimal scaling features become an input of classifying in backpropagation neural network. We use the method of backpropagation to recognize the coffee beans roast levels. The results showed that the proposed method is able to identify the coffee roasts beans level with an accuracy of 97.5%.

Cortical Action Potential Backpropagation Explains Spike Threshold Variability and Rapid-Onset Kinetics

PubMed Central

Yu, Yuguo; Shu, Yousheng; McCormick, David A.

2008-01-01

Neocortical action potential responses in vivo are characterized by considerable threshold variability, and thus timing and rate variability, even under seemingly identical conditions. This finding suggests that cortical ensembles are required for accurate sensorimotor integration and processing. Intracellularly, trial-to-trial variability results not only from variation in synaptic activities, but also in the transformation of these into patterns of action potentials. Through simultaneous axonal and somatic recordings and computational simulations, we demonstrate that the initiation of action potentials in the axon initial segment followed by backpropagation of these spikes throughout the neuron results in a distortion of the relationship between the timing of synaptic and action potential events. In addition, this backpropagation also results in an unusually high rate of rise of membrane potential at the foot of the action potential. The distortion of the relationship between the amplitude time course of synaptic inputs and action potential output caused by spike back-propagation results in the appearance of high spike threshold variability at the level of the soma. At the point of spike initiation, the axon initial segment, threshold variability is considerably less. Our results indicate that spike generation in cortical neurons is largely as expected by Hodgkin—Huxley theory and is more precise than previously thought. PMID:18632930

MIMO nonlinear ultrasonic tomography by propagation and backpropagation method.

PubMed

Dong, Chengdong; Jin, Yuanwei

2013-03-01

This paper develops a fast ultrasonic tomographic imaging method in a multiple-input multiple-output (MIMO) configuration using the propagation and backpropagation (PBP) method. By this method, ultrasonic excitation signals from multiple sources are transmitted simultaneously to probe the objects immersed in the medium. The scattering signals are recorded by multiple receivers. Utilizing the nonlinear ultrasonic wave propagation equation and the received time domain scattered signals, the objects are to be reconstructed iteratively in three steps. First, the propagation step calculates the predicted acoustic potential data at the receivers using an initial guess. Second, the difference signal between the predicted value and the measured data is calculated. Third, the backpropagation step computes updated acoustical potential data by backpropagating the difference signal to the same medium computationally. Unlike the conventional PBP method for tomographic imaging where each source takes turns to excite the acoustical field until all the sources are used, the developed MIMO-PBP method achieves faster image reconstruction by utilizing multiple source simultaneous excitation. Furthermore, we develop an orthogonal waveform signaling method using a waveform delay scheme to reduce the impact of speckle patterns in the reconstructed images. By numerical experiments we demonstrate that the proposed MIMO-PBP tomographic imaging method results in faster convergence and achieves superior imaging quality.

Application of the Artificial Neural Network model for prediction of monthly Standardized Precipitation and Evapotranspiration Index using hydrometeorological parameters and climate indices in eastern Australia

NASA Astrophysics Data System (ADS)

Deo, Ravinesh C.; Şahin, Mehmet

2015-07-01

The forecasting of drought based on cumulative influence of rainfall, temperature and evaporation is greatly beneficial for mitigating adverse consequences on water-sensitive sectors such as agriculture, ecosystems, wildlife, tourism, recreation, crop health and hydrologic engineering. Predictive models of drought indices help in assessing water scarcity situations, drought identification and severity characterization. In this paper, we tested the feasibility of the Artificial Neural Network (ANN) as a data-driven model for predicting the monthly Standardized Precipitation and Evapotranspiration Index (SPEI) for eight candidate stations in eastern Australia using predictive variable data from 1915 to 2005 (training) and simulated data for the period 2006-2012. The predictive variables were: monthly rainfall totals, mean temperature, minimum temperature, maximum temperature and evapotranspiration, which were supplemented by large-scale climate indices (Southern Oscillation Index, Pacific Decadal Oscillation, Southern Annular Mode and Indian Ocean Dipole) and the Sea Surface Temperatures (Nino 3.0, 3.4 and 4.0). A total of 30 ANN models were developed with 3-layer ANN networks. To determine the best combination of learning algorithms, hidden transfer and output functions of the optimum model, the Levenberg-Marquardt and Broyden-Fletcher-Goldfarb-Shanno (BFGS) quasi-Newton backpropagation algorithms were utilized to train the network, tangent and logarithmic sigmoid equations used as the activation functions and the linear, logarithmic and tangent sigmoid equations used as the output function. The best ANN architecture had 18 input neurons, 43 hidden neurons and 1 output neuron, trained using the Levenberg-Marquardt learning algorithm using tangent sigmoid equation as the activation and output functions. An evaluation of the model performance based on statistical rules yielded time-averaged Coefficient of Determination, Root Mean Squared Error and the Mean Absolute Error ranging from 0.9945-0.9990, 0.0466-0.1117, and 0.0013-0.0130, respectively for individual stations. Also, the Willmott's Index of Agreement and the Nash-Sutcliffe Coefficient of Efficiency were between 0.932-0.959 and 0.977-0.998, respectively. When checked for the severity (S), duration (D) and peak intensity (I) of drought events determined from the simulated and observed SPEI, differences in drought parameters ranged from - 1.41-0.64%, - 2.17-1.92% and - 3.21-1.21%, respectively. Based on performance evaluation measures, we aver that the Artificial Neural Network model is a useful data-driven tool for forecasting monthly SPEI and its drought-related properties in the region of study.

Intelligent navigation and accurate positioning of an assist robot in indoor environments

NASA Astrophysics Data System (ADS)

Hua, Bin; Rama, Endri; Capi, Genci; Jindai, Mitsuru; Tsuri, Yosuke

2017-12-01

Intact robot's navigation and accurate positioning in indoor environments are still challenging tasks. Especially in robot applications, assisting disabled and/or elderly people in museums/art gallery environments. In this paper, we present a human-like navigation method, where the neural networks control the wheelchair robot to reach the goal location safely, by imitating the supervisor's motions, and positioning in the intended location. In a museum similar environment, the mobile robot starts navigation from various positions, and uses a low-cost camera to track the target picture, and a laser range finder to make a safe navigation. Results show that the neural controller with the Conjugate Gradient Backpropagation training algorithm gives a robust response to guide the mobile robot accurately to the goal position.

A Report of Bethune-Cookman College NASA JOVE Projects

NASA Technical Reports Server (NTRS)

Agba, Lawrence C.; David, Sunil K.; Rao, Narsing G.; Rahmani, Munir A.

1997-01-01

This document is the final report for the Joint Venture (JOVE) in Space Sciences, and describes the tasks, performed with the support of the contract. These tasks include work in: (1) interfacing microprocessor systems to high performance parallel interface chips, SCSI drive and memory, needed for the implementation of a Space Optical Data Recorder; (2) designing a digital interface architecture for a microprocessor controlled sensors monitoring unit for a NASA Jitter Attenuation and Dynamics Experiment (JADE) project; (3) developing an enhanced back-propagation training algorithm; (4) studying the effect of simulated spaceflight on Aortic Contractility; (5) developing a course in astronomy; and (6) improving internet access by running cables, and installing hubs in various places on the campus; and (7) researching the characteristics of Nd:YALO laser resonator.

A Novel Approach for Blast-Induced Flyrock Prediction Based on Imperialist Competitive Algorithm and Artificial Neural Network

PubMed Central

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

Compensatory neurofuzzy model for discrete data classification in biomedical

NASA Astrophysics Data System (ADS)

Ceylan, Rahime

2015-03-01

Biomedical data is separated to two main sections: signals and discrete data. So, studies in this area are about biomedical signal classification or biomedical discrete data classification. There are artificial intelligence models which are relevant to classification of ECG, EMG or EEG signals. In same way, in literature, many models exist for classification of discrete data taken as value of samples which can be results of blood analysis or biopsy in medical process. Each algorithm could not achieve high accuracy rate on classification of signal and discrete data. In this study, compensatory neurofuzzy network model is presented for classification of discrete data in biomedical pattern recognition area. The compensatory neurofuzzy network has a hybrid and binary classifier. In this system, the parameters of fuzzy systems are updated by backpropagation algorithm. The realized classifier model is conducted to two benchmark datasets (Wisconsin Breast Cancer dataset and Pima Indian Diabetes dataset). Experimental studies show that compensatory neurofuzzy network model achieved 96.11% accuracy rate in classification of breast cancer dataset and 69.08% accuracy rate was obtained in experiments made on diabetes dataset with only 10 iterations.

Application of neural networks with novel independent component analysis methodologies to a Prussian blue modified glassy carbon electrode array.

PubMed

Wang, Liang; Yang, Die; Fang, Cheng; Chen, Zuliang; Lesniewski, Peter J; Mallavarapu, Megharaj; Naidu, Ravendra

2015-01-01

Sodium potassium absorption ratio (SPAR) is an important measure of agricultural water quality, wherein four exchangeable cations (K(+), Na(+), Ca(2+) and Mg(2+)) should be simultaneously determined. An ISE-array is suitable for this application because its simplicity, rapid response characteristics and lower cost. However, cross-interferences caused by the poor selectivity of ISEs need to be overcome using multivariate chemometric methods. In this paper, a solid contact ISE array, based on a Prussian blue modified glassy carbon electrode (PB-GCE), was applied with a novel chemometric strategy. One of the most popular independent component analysis (ICA) methods, the fast fixed-point algorithm for ICA (fastICA), was implemented by the genetic algorithm (geneticICA) to avoid the local maxima problem commonly observed with fastICA. This geneticICA can be implemented as a data preprocessing method to improve the prediction accuracy of the Back-propagation neural network (BPNN). The ISE array system was validated using 20 real irrigation water samples from South Australia, and acceptable prediction accuracies were obtained. Copyright © 2014 Elsevier B.V. All rights reserved.

Two-dimensional shape recognition using oriented-polar representation

NASA Astrophysics Data System (ADS)

Hu, Neng-Chung; Yu, Kuo-Kan; Hsu, Yung-Li

1997-10-01

To deal with such a problem as object recognition of position, scale, and rotation invariance (PSRI), we utilize some PSRI properties of images obtained from objects, for example, the centroid of the image. The corresponding position of the centroid to the boundary of the image is invariant in spite of rotation, scale, and translation of the image. To obtain the information of the image, we use the technique similar to Radon transform, called the oriented-polar representation of a 2D image. In this representation, two specific points, the centroid and the weighted mean point, are selected to form an initial ray, then the image is sampled with N angularly equispaced rays departing from the initial rays. Each ray contains a number of intersections and the distance information obtained from the centroid to the intersections. The shape recognition algorithm is based on the least total error of these two items of information. Together with a simple noise removal and a typical backpropagation neural network, this algorithm is simple, but the PSRI is achieved with a high recognition rate.

Identification and control of plasma vertical position using neural network in Damavand tokamak.

PubMed

Rasouli, H; Rasouli, C; Koohi, A

2013-02-01

In this work, a nonlinear model is introduced to determine the vertical position of the plasma column in Damavand tokamak. Using this model as a simulator, a nonlinear neural network controller has been designed. In the first stage, the electronic drive and sensory circuits of Damavand tokamak are modified. These circuits can control the vertical position of the plasma column inside the vacuum vessel. Since the vertical position of plasma is an unstable parameter, a direct closed loop system identification algorithm is performed. In the second stage, a nonlinear model is identified for plasma vertical position, based on the multilayer perceptron (MLP) neural network (NN) structure. Estimation of simulator parameters has been performed by back-propagation error algorithm using Levenberg-Marquardt gradient descent optimization technique. The model is verified through simulation of the whole closed loop system using both simulator and actual plant in similar conditions. As the final stage, a MLP neural network controller is designed for simulator model. In the last step, online training is performed to tune the controller parameters. Simulation results justify using of the NN controller for the actual plant.

A novel approach for blast-induced flyrock prediction based on imperialist competitive algorithm and artificial neural network.

PubMed

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.

Feedforward neural network model estimating pollutant removal process within mesophilic upflow anaerobic sludge blanket bioreactor treating industrial starch processing wastewater.

PubMed

Antwi, Philip; Li, Jianzheng; Meng, Jia; Deng, Kaiwen; Koblah Quashie, Frank; Li, Jiuling; Opoku Boadi, Portia

2018-06-01

In this a, three-layered feedforward-backpropagation artificial neural network (BPANN) model was developed and employed to evaluate COD removal an upflow anaerobic sludge blanket (UASB) reactor treating industrial starch processing wastewater. At the end of UASB operation, microbial community characterization revealed satisfactory composition of microbes whereas morphology depicted rod-shaped archaea. pH, COD, NH 4 + , VFA, OLR and biogas yield were selected by principal component analysis and used as input variables. Whilst tangent sigmoid function (tansig) and linear function (purelin) were assigned as activation functions at the hidden-layer and output-layer, respectively, optimum BPANN architecture was achieved with Levenberg-Marquardt algorithm (trainlm) after eleven training algorithms had been tested. Based on performance indicators such the mean squared errors, fractional variance, index of agreement and coefficient of determination (R 2 ), the BPANN model demonstrated significant performance with R 2 reaching 87%. The study revealed that, control and optimization of an anaerobic digestion process with BPANN model was feasible. Copyright © 2018 Elsevier Ltd. All rights reserved.

Dynamic gesture recognition using neural networks: a fundament for advanced interaction construction

NASA Astrophysics Data System (ADS)

Boehm, Klaus; Broll, Wolfgang; Sokolewicz, Michael A.

1994-04-01

Interaction in virtual reality environments is still a challenging task. Static hand posture recognition is currently the most common and widely used method for interaction using glove input devices. In order to improve the naturalness of interaction, and thereby decrease the user-interface learning time, there is a need to be able to recognize dynamic gestures. In this paper we describe our approach to overcoming the difficulties of dynamic gesture recognition (DGR) using neural networks. Backpropagation neural networks have already proven themselves to be appropriate and efficient for posture recognition. However, the extensive amount of data involved in DGR requires a different approach. Because of features such as topology preservation and automatic-learning, Kohonen Feature Maps are particularly suitable for the reduction of the high dimensional data space that is the result of a dynamic gesture, and are thus implemented for this task.

A comparison of neural network architectures for the prediction of MRR in EDM

NASA Astrophysics Data System (ADS)

Jena, A. R.; Das, Raja

2017-11-01

The aim of the research work is to predict the material removal rate of a work-piece in electrical discharge machining (EDM). Here, an effort has been made to predict the material removal rate through back-propagation neural network (BPN) and radial basis function neural network (RBFN) for a work-piece of AISI D2 steel. The input parameters for the architecture are discharge-current (Ip), pulse-duration (Ton), and duty-cycle (τ) taken for consideration to obtained the output for material removal rate of the work-piece. In the architecture, it has been observed that radial basis function neural network is comparatively faster than back-propagation neural network but logically back-propagation neural network results more real value. Therefore BPN may consider as a better process in this architecture for consistent prediction to save time and money for conducting experiments.

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

NASA Technical Reports Server (NTRS)

Sridhar, Banavar; Phatak, Anil; Chatterji, Gano

1993-01-01

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

Development of hybrid genetic-algorithm-based neural networks using regression trees for modeling air quality inside a public transportation bus.

PubMed

Kadiyala, Akhil; Kaur, Devinder; Kumar, Ashok

2013-02-01

The present study developed a novel approach to modeling indoor air quality (IAQ) of a public transportation bus by the development of hybrid genetic-algorithm-based neural networks (also known as evolutionary neural networks) with input variables optimized from using the regression trees, referred as the GART approach. This study validated the applicability of the GART modeling approach in solving complex nonlinear systems by accurately predicting the monitored contaminants of carbon dioxide (CO2), carbon monoxide (CO), nitric oxide (NO), sulfur dioxide (SO2), 0.3-0.4 microm sized particle numbers, 0.4-0.5 microm sized particle numbers, particulate matter (PM) concentrations less than 1.0 microm (PM10), and PM concentrations less than 2.5 microm (PM2.5) inside a public transportation bus operating on 20% grade biodiesel in Toledo, OH. First, the important variables affecting each monitored in-bus contaminant were determined using regression trees. Second, the analysis of variance was used as a complimentary sensitivity analysis to the regression tree results to determine a subset of statistically significant variables affecting each monitored in-bus contaminant. Finally, the identified subsets of statistically significant variables were used as inputs to develop three artificial neural network (ANN) models. The models developed were regression tree-based back-propagation network (BPN-RT), regression tree-based radial basis function network (RBFN-RT), and GART models. Performance measures were used to validate the predictive capacity of the developed IAQ models. The results from this approach were compared with the results obtained from using a theoretical approach and a generalized practicable approach to modeling IAQ that included the consideration of additional independent variables when developing the aforementioned ANN models. The hybrid GART models were able to capture majority of the variance in the monitored in-bus contaminants. The genetic-algorithm-based neural network IAQ models outperformed the traditional ANN methods of the back-propagation and the radial basis function networks. The novelty of this research is the development of a novel approach to modeling vehicular indoor air quality by integration of the advanced methods of genetic algorithms, regression trees, and the analysis of variance for the monitored in-vehicle gaseous and particulate matter contaminants, and comparing the results obtained from using the developed approach with conventional artificial intelligence techniques of back propagation networks and radial basis function networks. This study validated the newly developed approach using holdout and threefold cross-validation methods. These results are of great interest to scientists, researchers, and the public in understanding the various aspects of modeling an indoor microenvironment. This methodology can easily be extended to other fields of study also.

Modeling when and where a secondary accident occurs.

PubMed

Wang, Junhua; Liu, Boya; Fu, Ting; Liu, Shuo; Stipancic, Joshua

2018-01-31

The occurrence of secondary accidents leads to traffic congestion and road safety issues. Secondary accident prevention has become a major consideration in traffic incident management. This paper investigates the location and time of a potential secondary accident after the occurrence of an initial traffic accident. With accident data and traffic loop data collected over three years from California interstate freeways, a shock wave-based method was introduced to identify secondary accidents. A linear regression model and two machine learning algorithms, including a back-propagation neural network (BPNN) and a least squares support vector machine (LSSVM), were implemented to explore the distance and time gap between the initial and secondary accidents using inputs of crash severity, violation category, weather condition, tow away, road surface condition, lighting, parties involved, traffic volume, duration, and shock wave speed generated by the primary accident. From the results, the linear regression model was inadequate in describing the effect of most variables and its goodness-of-fit and accuracy in prediction was relatively poor. In the training programs, the BPNN and LSSVM demonstrated adequate goodness-of-fit, though the BPNN was superior with a higher CORR and lower MSE. The BPNN model also outperformed the LSSVM in time prediction, while both failed to provide adequate distance prediction. Therefore, the BPNN model could be used to forecast the time gap between initial and secondary accidents, which could be used by decision makers and incident management agencies to prevent or reduce secondary collisions. Copyright © 2018 Elsevier Ltd. All rights reserved.

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

PubMed

Draghici, S

1997-02-01

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

Modeling of frost crystal growth over a flat plate using artificial neural networks and fractal geometries

NASA Astrophysics Data System (ADS)

Tahavvor, Ali Reza

2017-03-01

In the present study artificial neural network and fractal geometry are used to predict frost thickness and density on a cold flat plate having constant surface temperature under forced convection for different ambient conditions. These methods are very applicable in this area because phase changes such as melting and solidification are simulated by conventional methods but frost formation is a most complicated phase change phenomenon consists of coupled heat and mass transfer. Therefore conventional mathematical techniques cannot capture the effects of all parameters on its growth and development because this process influenced by many factors and it is a time dependent process. Therefore, in this work soft computing method such as artificial neural network and fractal geometry are used to do this manner. The databases for modeling are generated from the experimental measurements. First, multilayer perceptron network is used and it is found that the back-propagation algorithm with Levenberg-Marquardt learning rule is the best choice to estimate frost growth properties due to accurate and faster training procedure. Second, fractal geometry based on the Von-Koch curve is used to model frost growth procedure especially in frost thickness and density. Comparison is performed between experimental measurements and soft computing methods. Results show that soft computing methods can be used more efficiently to determine frost properties over a flat plate. Based on the developed models, wide range of frost formation over flat plates can be determined for various conditions.

Variable Action Potential Backpropagation during Tonic Firing and Low-Threshold Spike Bursts in Thalamocortical But Not Thalamic Reticular Nucleus Neurons.

PubMed

Connelly, William M; Crunelli, Vincenzo; Errington, Adam C

2017-05-24

Backpropagating action potentials (bAPs) are indispensable in dendritic signaling. Conflicting Ca 2+ -imaging data and an absence of dendritic recording data means that the extent of backpropagation in thalamocortical (TC) and thalamic reticular nucleus (TRN) neurons remains unknown. Because TRN neurons signal electrically through dendrodendritic gap junctions and possibly via chemical dendritic GABAergic synapses, as well as classical axonal GABA release, this lack of knowledge is problematic. To address this issue, we made two-photon targeted patch-clamp recordings from rat TC and TRN neuron dendrites to measure bAPs directly. These recordings reveal that "tonic"' and low-threshold-spike (LTS) "burst" APs in both cell types are always recorded first at the soma before backpropagating into the dendrites while undergoing substantial distance-dependent dendritic amplitude attenuation. In TC neurons, bAP attenuation strength varies according to firing mode. During LTS bursts, somatic AP half-width increases progressively with increasing spike number, allowing late-burst spikes to propagate more efficiently into the dendritic tree compared with spikes occurring at burst onset. Tonic spikes have similar somatic half-widths to late burst spikes and undergo similar dendritic attenuation. In contrast, in TRN neurons, AP properties are unchanged between LTS bursts and tonic firing and, as a result, distance-dependent dendritic attenuation remains consistent across different firing modes. Therefore, unlike LTS-associated global electrical and calcium signals, the spatial influence of bAP signaling in TC and TRN neurons is more restricted, with potentially important behavioral-state-dependent consequences for synaptic integration and plasticity in thalamic neurons. SIGNIFICANCE STATEMENT In most neurons, action potentials (APs) initiate in the axosomatic region and propagate into the dendritic tree to provide a retrograde signal that conveys information about the level of cellular output to the locations that receive most input: the dendrites. In thalamocortical and thalamic reticular nucleus neurons, the site of AP generation and the true extent of backpropagation remain unknown. Using patch-clamp recordings, this study measures dendritic propagation of APs directly in these neurons. In either cell type, high-frequency low-threshold spike burst or lower-frequency tonic APs undergo substantial voltage attenuation as they spread into the dendritic tree. Therefore, backpropagating spikes in these cells can only influence signaling in the proximal part of the dendritic tree. Copyright © 2017 Connelly et al.

Efficient Grammar Induction Algorithm with Parse Forests from Real Corpora

NASA Astrophysics Data System (ADS)

Kurihara, Kenichi; Kameya, Yoshitaka; Sato, Taisuke

The task of inducing grammar structures has received a great deal of attention. The reasons why researchers have studied are different; to use grammar induction as the first stage in building large treebanks or to make up better language models. However, grammar induction has inherent computational complexity. To overcome it, some grammar induction algorithms add new production rules incrementally. They refine the grammar while keeping their computational complexity low. In this paper, we propose a new efficient grammar induction algorithm. Although our algorithm is similar to algorithms which learn a grammar incrementally, our algorithm uses the graphical EM algorithm instead of the Inside-Outside algorithm. We report results of learning experiments in terms of learning speeds. The results show that our algorithm learns a grammar in constant time regardless of the size of the grammar. Since our algorithm decreases syntactic ambiguities in each step, our algorithm reduces required time for learning. This constant-time learning considerably affects learning time for larger grammars. We also reports results of evaluation of criteria to choose nonterminals. Our algorithm refines a grammar based on a nonterminal in each step. Since there can be several criteria to decide which nonterminal is the best, we evaluate them by learning experiments.

Multiscale Modeling of Gene-Behavior Associations in an Artificial Neural Network Model of Cognitive Development.

PubMed

Thomas, Michael S C; Forrester, Neil A; Ronald, Angelica

2016-01-01

In the multidisciplinary field of developmental cognitive neuroscience, statistical associations between levels of description play an increasingly important role. One example of such associations is the observation of correlations between relatively common gene variants and individual differences in behavior. It is perhaps surprising that such associations can be detected despite the remoteness of these levels of description, and the fact that behavior is the outcome of an extended developmental process involving interaction of the whole organism with a variable environment. Given that they have been detected, how do such associations inform cognitive-level theories? To investigate this question, we employed a multiscale computational model of development, using a sample domain drawn from the field of language acquisition. The model comprised an artificial neural network model of past-tense acquisition trained using the backpropagation learning algorithm, extended to incorporate population modeling and genetic algorithms. It included five levels of description-four internal: genetic, network, neurocomputation, behavior; and one external: environment. Since the mechanistic assumptions of the model were known and its operation was relatively transparent, we could evaluate whether cross-level associations gave an accurate picture of causal processes. We established that associations could be detected between artificial genes and behavioral variation, even under polygenic assumptions of a many-to-one relationship between genes and neurocomputational parameters, and when an experience-dependent developmental process interceded between the action of genes and the emergence of behavior. We evaluated these associations with respect to their specificity (to different behaviors, to function vs. structure), to their developmental stability, and to their replicability, as well as considering issues of missing heritability and gene-environment interactions. We argue that gene-behavior associations can inform cognitive theory with respect to effect size, specificity, and timing. The model demonstrates a means by which researchers can undertake multiscale modeling with respect to cognition and develop highly specific and complex hypotheses across multiple levels of description. Copyright © 2015 Cognitive Science Society, Inc.

Efficient model learning methods for actor-critic control.

PubMed

Grondman, Ivo; Vaandrager, Maarten; Buşoniu, Lucian; Babuska, Robert; Schuitema, Erik

2012-06-01

We propose two new actor-critic algorithms for reinforcement learning. Both algorithms use local linear regression (LLR) to learn approximations of the functions involved. A crucial feature of the algorithms is that they also learn a process model, and this, in combination with LLR, provides an efficient policy update for faster learning. The first algorithm uses a novel model-based update rule for the actor parameters. The second algorithm does not use an explicit actor but learns a reference model which represents a desired behavior, from which desired control actions can be calculated using the inverse of the learned process model. The two novel methods and a standard actor-critic algorithm are applied to the pendulum swing-up problem, in which the novel methods achieve faster learning than the standard algorithm.

Neurocontrol and neurobiology - New developments and connections

NASA Technical Reports Server (NTRS)

Werbos, Paul J.; Pellionisz, Andras J.

1992-01-01

At McDonnell-Douglas, controllers which combine adaptive critic networks with the use of backpropagation in real time have solved difficult control problems crucial to the feasibility of building the National Aerospace Plane (NASP) able to reach earth orbit. As details emerged, parallels to neurobiology have grown stronger and have begun to lead to empirical possibilities of importance to neuroscience. This has led to thoughts of institutional collaboration facilitating what could become a Newtonian revolution in neuroscience, with cognitive implications as well. The authors elaborate on each of these points. The topics discussed are recent progress in neurocontrol; progress in optimization and reinforcement learning; implications for neurobiology and science policy; and a new view of the brain.

Neural Network Back-Propagation Algorithm for Sensing Hypergols

NASA Technical Reports Server (NTRS)

Perotti, Jose; Lewis, Mark; Medelius, Pedro; Bastin, Gary

2013-01-01

Fast, continuous detection of a wide range of hazardous substances simultaneously is needed to achieve improved safety for personnel working with hypergolic fuels and oxidizers, as well as other hazardous substances, with a requirement for such detection systems to warn personnel immediately upon the sudden advent of hazardous conditions, with a high probability of detection and a low false alarm rate. The primary purpose of this software is to read the voltage outputs from voltage dividers containing carbon nano - tube sensors as a variable resistance leg, and to recognize quickly when a leak has occurred through recognizing that a generalized pattern change in resistivity of a carbon nanotube sensor has occurred upon exposure to dangerous substances, and, further, to identify quickly just what substance is present through detailed pattern recognition of the shape of the response provided by the carbon nanotube sensor.

Mellin Transform-Based Correction Method for Linear Scale Inconsistency of Intrusion Events Identification in OFPS

NASA Astrophysics Data System (ADS)

Wang, Baocheng; Qu, Dandan; Tian, Qing; Pang, Liping

2018-05-01

For the problem that the linear scale of intrusion signals in the optical fiber pre-warning system (OFPS) is inconsistent, this paper presents a method to correct the scale. Firstly, the intrusion signals are intercepted, and an aggregate of the segments with equal length is obtained. Then, the Mellin transform (MT) is applied to convert them into the same scale. The spectral characteristics are obtained by the Fourier transform. Finally, we adopt back-propagation (BP) neural network to identify intrusion types, which takes the spectral characteristics as input. We carried out the field experiments and collected the optical fiber intrusion signals which contain the picking signal, shoveling signal, and running signal. The experimental results show that the proposed algorithm can effectively improve the recognition accuracy of the intrusion signals.

Effective heart disease prediction system using data mining techniques.

PubMed

Singh, Poornima; Singh, Sanjay; Pandi-Jain, Gayatri S

2018-01-01

The health care industries collect huge amounts of data that contain some hidden information, which is useful for making effective decisions. For providing appropriate results and making effective decisions on data, some advanced data mining techniques are used. In this study, an effective heart disease prediction system (EHDPS) is developed using neural network for predicting the risk level of heart disease. The system uses 15 medical parameters such as age, sex, blood pressure, cholesterol, and obesity for prediction. The EHDPS predicts the likelihood of patients getting heart disease. It enables significant knowledge, eg, relationships between medical factors related to heart disease and patterns, to be established. We have employed the multilayer perceptron neural network with backpropagation as the training algorithm. The obtained results have illustrated that the designed diagnostic system can effectively predict the risk level of heart diseases.

Fast neural net simulation with a DSP processor array.

PubMed

Muller, U A; Gunzinger, A; Guggenbuhl, W

1995-01-01

This paper describes the implementation of a fast neural net simulator on a novel parallel distributed-memory computer. A 60-processor system, named MUSIC (multiprocessor system with intelligent communication), is operational and runs the backpropagation algorithm at a speed of 330 million connection updates per second (continuous weight update) using 32-b floating-point precision. This is equal to 1.4 Gflops sustained performance. The complete system with 3.8 Gflops peak performance consumes less than 800 W of electrical power and fits into a 19-in rack. While reaching the speed of modern supercomputers, MUSIC still can be used as a personal desktop computer at a researcher's own disposal. In neural net simulation, this gives a computing performance to a single user which was unthinkable before. The system's real-time interfaces make it especially useful for embedded applications.

SemiBoost: boosting for semi-supervised learning.

PubMed

Mallapragada, Pavan Kumar; Jin, Rong; Jain, Anil K; Liu, Yi

2009-11-01

Semi-supervised learning has attracted a significant amount of attention in pattern recognition and machine learning. Most previous studies have focused on designing special algorithms to effectively exploit the unlabeled data in conjunction with labeled data. Our goal is to improve the classification accuracy of any given supervised learning algorithm by using the available unlabeled examples. We call this as the Semi-supervised improvement problem, to distinguish the proposed approach from the existing approaches. We design a metasemi-supervised learning algorithm that wraps around the underlying supervised algorithm and improves its performance using unlabeled data. This problem is particularly important when we need to train a supervised learning algorithm with a limited number of labeled examples and a multitude of unlabeled examples. We present a boosting framework for semi-supervised learning, termed as SemiBoost. The key advantages of the proposed semi-supervised learning approach are: 1) performance improvement of any supervised learning algorithm with a multitude of unlabeled data, 2) efficient computation by the iterative boosting algorithm, and 3) exploiting both manifold and cluster assumption in training classification models. An empirical study on 16 different data sets and text categorization demonstrates that the proposed framework improves the performance of several commonly used supervised learning algorithms, given a large number of unlabeled examples. We also show that the performance of the proposed algorithm, SemiBoost, is comparable to the state-of-the-art semi-supervised learning algorithms.

Dynamic mesolimbic dopamine signaling during action sequence learning and expectation violation

PubMed Central

Collins, Anne L.; Greenfield, Venuz Y.; Bye, Jeffrey K.; Linker, Kay E.; Wang, Alice S.; Wassum, Kate M.

2016-01-01

Prolonged mesolimbic dopamine concentration changes have been detected during spatial navigation, but little is known about the conditions that engender this signaling profile or how it develops with learning. To address this, we monitored dopamine concentration changes in the nucleus accumbens core of rats throughout acquisition and performance of an instrumental action sequence task. Prolonged dopamine concentration changes were detected that ramped up as rats executed each action sequence and declined after earned reward collection. With learning, dopamine concentration began to rise increasingly earlier in the execution of the sequence and ultimately backpropagated away from stereotyped sequence actions, becoming only transiently elevated by the most distal and unexpected reward predictor. Action sequence-related dopamine signaling was reactivated in well-trained rats if they became disengaged in the task and in response to an unexpected change in the value, but not identity of the earned reward. Throughout training and test, dopamine signaling correlated with sequence performance. These results suggest that action sequences can engender a prolonged mode of dopamine signaling in the nucleus accumbens core and that such signaling relates to elements of the motivation underlying sequence execution and is dynamic with learning, overtraining and violations in reward expectation. PMID:26869075

A Novel Approach for Lie Detection Based on F-Score and Extreme Learning Machine

PubMed Central

Gao, Junfeng; Wang, Zhao; Yang, Yong; Zhang, Wenjia; Tao, Chunyi; Guan, Jinan; Rao, Nini

2013-01-01

A new machine learning method referred to as F-score_ELM was proposed to classify the lying and truth-telling using the electroencephalogram (EEG) signals from 28 guilty and innocent subjects. Thirty-one features were extracted from the probe responses from these subjects. Then, a recently-developed classifier called extreme learning machine (ELM) was combined with F-score, a simple but effective feature selection method, to jointly optimize the number of the hidden nodes of ELM and the feature subset by a grid-searching training procedure. The method was compared to two classification models combining principal component analysis with back-propagation network and support vector machine classifiers. We thoroughly assessed the performance of these classification models including the training and testing time, sensitivity and specificity from the training and testing sets, as well as network size. The experimental results showed that the number of the hidden nodes can be effectively optimized by the proposed method. Also, F-score_ELM obtained the best classification accuracy and required the shortest training and testing time. PMID:23755136

Dendritic small conductance calcium-activated potassium channels activated by action potentials suppress EPSPs and gate spike-timing dependent synaptic plasticity.

PubMed

Jones, Scott L; To, Minh-Son; Stuart, Greg J

2017-10-23

Small conductance calcium-activated potassium channels (SK channels) are present in spines and can be activated by backpropagating action potentials (APs). This suggests they may play a critical role in spike-timing dependent synaptic plasticity (STDP). Consistent with this idea, EPSPs in both cortical and hippocampal pyramidal neurons were suppressed by preceding APs in an SK-dependent manner. In cortical pyramidal neurons EPSP suppression by preceding APs depended on their precise timing as well as the distance of activated synapses from the soma, was dendritic in origin, and involved SK-dependent suppression of NMDA receptor activation. As a result SK channel activation by backpropagating APs gated STDP induction during low-frequency AP-EPSP pairing, with both LTP and LTD absent under control conditions but present after SK channel block. These findings indicate that activation of SK channels in spines by backpropagating APs plays a key role in regulating both EPSP amplitude and STDP induction.

Development of neural network techniques for finger-vein pattern classification

NASA Astrophysics Data System (ADS)

Wu, Jian-Da; Liu, Chiung-Tsiung; Tsai, Yi-Jang; Liu, Jun-Ching; Chang, Ya-Wen

2010-02-01

A personal identification system using finger-vein patterns and neural network techniques is proposed in the present study. In the proposed system, the finger-vein patterns are captured by a device that can transmit near infrared through the finger and record the patterns for signal analysis and classification. The biometric system for verification consists of a combination of feature extraction using principal component analysis and pattern classification using both back-propagation network and adaptive neuro-fuzzy inference systems. Finger-vein features are first extracted by principal component analysis method to reduce the computational burden and removes noise residing in the discarded dimensions. The features are then used in pattern classification and identification. To verify the effect of the proposed adaptive neuro-fuzzy inference system in the pattern classification, the back-propagation network is compared with the proposed system. The experimental results indicated the proposed system using adaptive neuro-fuzzy inference system demonstrated a better performance than the back-propagation network for personal identification using the finger-vein patterns.

Noise-enhanced clustering and competitive learning algorithms.

PubMed

Osoba, Osonde; Kosko, Bart

2013-01-01

Noise can provably speed up convergence in many centroid-based clustering algorithms. This includes the popular k-means clustering algorithm. The clustering noise benefit follows from the general noise benefit for the expectation-maximization algorithm because many clustering algorithms are special cases of the expectation-maximization algorithm. Simulations show that noise also speeds up convergence in stochastic unsupervised competitive learning, supervised competitive learning, and differential competitive learning. Copyright © 2012 Elsevier Ltd. All rights reserved.

Q-Learning-Based Adjustable Fixed-Phase Quantum Grover Search Algorithm

NASA Astrophysics Data System (ADS)

Guo, Ying; Shi, Wensha; Wang, Yijun; Hu, Jiankun

2017-02-01

We demonstrate that the rotation phase can be suitably chosen to increase the efficiency of the phase-based quantum search algorithm, leading to a dynamic balance between iterations and success probabilities of the fixed-phase quantum Grover search algorithm with Q-learning for a given number of solutions. In this search algorithm, the proposed Q-learning algorithm, which is a model-free reinforcement learning strategy in essence, is used for performing a matching algorithm based on the fraction of marked items λ and the rotation phase α. After establishing the policy function α = π(λ), we complete the fixed-phase Grover algorithm, where the phase parameter is selected via the learned policy. Simulation results show that the Q-learning-based Grover search algorithm (QLGA) enables fewer iterations and gives birth to higher success probabilities. Compared with the conventional Grover algorithms, it avoids the optimal local situations, thereby enabling success probabilities to approach one.

Active action potential propagation but not initiation in thalamic interneuron dendrites

PubMed Central

Casale, Amanda E.; McCormick, David A.

2012-01-01

Inhibitory interneurons of the dorsal lateral geniculate nucleus of the thalamus modulate the activity of thalamocortical cells in response to excitatory input through the release of inhibitory neurotransmitter from both axons and dendrites. The exact mechanisms by which release can occur from dendrites are, however, not well understood. Recent experiments using calcium imaging have suggested that Na/K based action potentials can evoke calcium transients in dendrites via local active conductances, making the back-propagating action potential a candidate for dendritic neurotransmitter release. In this study, we employed high temporal and spatial resolution voltage-sensitive dye imaging to assess the characteristics of dendritic voltage deflections in response to Na/K action potentials in interneurons of the mouse dorsal lateral geniculate nucleus. We found that trains or single action potentials elicited by somatic current injection or local synaptic stimulation led to action potentials that rapidly and actively back-propagated throughout the entire dendritic arbor and into the fine filiform dendritic appendages known to release GABAergic vesicles. Action potentials always appeared first in the soma or proximal dendrite in response to somatic current injection or local synaptic stimulation, and the rapid back-propagation into the dendritic arbor depended upon voltage-gated sodium and TEA-sensitive potassium channels. Our results indicate that thalamic interneuron dendrites integrate synaptic inputs that initiate action potentials, most likely in the axon initial segment, that then back-propagate with high-fidelity into the dendrites, resulting in a nearly synchronous release of GABA from both axonal and dendritic compartments. PMID:22171033

A Learning Framework for Winner-Take-All Networks with Stochastic Synapses.

PubMed

Mostafa, Hesham; Cauwenberghs, Gert

2018-06-01

Many recent generative models make use of neural networks to transform the probability distribution of a simple low-dimensional noise process into the complex distribution of the data. This raises the question of whether biological networks operate along similar principles to implement a probabilistic model of the environment through transformations of intrinsic noise processes. The intrinsic neural and synaptic noise processes in biological networks, however, are quite different from the noise processes used in current abstract generative networks. This, together with the discrete nature of spikes and local circuit interactions among the neurons, raises several difficulties when using recent generative modeling frameworks to train biologically motivated models. In this letter, we show that a biologically motivated model based on multilayer winner-take-all circuits and stochastic synapses admits an approximate analytical description. This allows us to use the proposed networks in a variational learning setting where stochastic backpropagation is used to optimize a lower bound on the data log likelihood, thereby learning a generative model of the data. We illustrate the generality of the proposed networks and learning technique by using them in a structured output prediction task and a semisupervised learning task. Our results extend the domain of application of modern stochastic network architectures to networks where synaptic transmission failure is the principal noise mechanism.

Predicting the survival of diabetes using neural network

NASA Astrophysics Data System (ADS)

Mamuda, Mamman; Sathasivam, Saratha

2017-08-01

Data mining techniques at the present time are used in predicting diseases of health care industries. Neural Network is one among the prevailing method in data mining techniques of an intelligent field for predicting diseases in health care industries. This paper presents a study on the prediction of the survival of diabetes diseases using different learning algorithms from the supervised learning algorithms of neural network. Three learning algorithms are considered in this study: (i) The levenberg-marquardt learning algorithm (ii) The Bayesian regulation learning algorithm and (iii) The scaled conjugate gradient learning algorithm. The network is trained using the Pima Indian Diabetes Dataset with the help of MATLAB R2014(a) software. The performance of each algorithm is further discussed through regression analysis. The prediction accuracy of the best algorithm is further computed to validate the accurate prediction

Prediction Surface Morphology of Nanostructure Fabricated by Nano-Oxidation Technology.

PubMed

Huang, Jen-Ching; Chang, Ho; Kuo, Chin-Guo; Li, Jeen-Fong; You, Yong-Chin

2015-12-04

Atomic force microscopy (AFM) was used for visualization of a nano-oxidation technique performed on diamond-like carbon (DLC) thin film. Experiments of the nano-oxidation technique of the DLC thin film include those on nano-oxidation points and nano-oxidation lines. The feature sizes of the DLC thin film, including surface morphology, depth, and width, were explored after application of a nano-oxidation technique to the DLC thin film under different process parameters. A databank for process parameters and feature sizes of thin films was then established, and multiple regression analysis (MRA) and a back-propagation neural network (BPN) were used to carry out the algorithm. The algorithmic results are compared with the feature sizes acquired from experiments, thus obtaining a prediction model of the nano-oxidation technique of the DLC thin film. The comparative results show that the prediction accuracy of BPN is superior to that of MRA. When the BPN algorithm is used to predict nano-point machining, the mean absolute percentage errors (MAPE) of depth, left side, and right side are 8.02%, 9.68%, and 7.34%, respectively. When nano-line machining is being predicted, the MAPEs of depth, left side, and right side are 4.96%, 8.09%, and 6.77%, respectively. The obtained data can also be used to predict cross-sectional morphology in the DLC thin film treated with a nano-oxidation process.

An Educational System for Learning Search Algorithms and Automatically Assessing Student Performance

ERIC Educational Resources Information Center

Grivokostopoulou, Foteini; Perikos, Isidoros; Hatzilygeroudis, Ioannis

2017-01-01

In this paper, first we present an educational system that assists students in learning and tutors in teaching search algorithms, an artificial intelligence topic. Learning is achieved through a wide range of learning activities. Algorithm visualizations demonstrate the operational functionality of algorithms according to the principles of active…

Using an improved association rules mining optimization algorithm in web-based mobile-learning system

NASA Astrophysics Data System (ADS)

Huang, Yin; Chen, Jianhua; Xiong, Shaojun

2009-07-01

Mobile-Learning (M-learning) makes many learners get the advantages of both traditional learning and E-learning. Currently, Web-based Mobile-Learning Systems have created many new ways and defined new relationships between educators and learners. Association rule mining is one of the most important fields in data mining and knowledge discovery in databases. Rules explosion is a serious problem which causes great concerns, as conventional mining algorithms often produce too many rules for decision makers to digest. Since Web-based Mobile-Learning System collects vast amounts of student profile data, data mining and knowledge discovery techniques can be applied to find interesting relationships between attributes of learners, assessments, the solution strategies adopted by learners and so on. Therefore ,this paper focus on a new data-mining algorithm, combined with the advantages of genetic algorithm and simulated annealing algorithm , called ARGSA(Association rules based on an improved Genetic Simulated Annealing Algorithm), to mine the association rules. This paper first takes advantage of the Parallel Genetic Algorithm and Simulated Algorithm designed specifically for discovering association rules. Moreover, the analysis and experiment are also made to show the proposed method is superior to the Apriori algorithm in this Mobile-Learning system.

Loss tolerant speech decoder for telecommunications

NASA Technical Reports Server (NTRS)

Prieto, Jr., Jaime L. (Inventor)

1999-01-01

A method and device for extrapolating past signal-history data for insertion into missing data segments in order to conceal digital speech frame errors. The extrapolation method uses past-signal history that is stored in a buffer. The method is implemented with a device that utilizes a finite-impulse response (FIR) multi-layer feed-forward artificial neural network that is trained by back-propagation for one-step extrapolation of speech compression algorithm (SCA) parameters. Once a speech connection has been established, the speech compression algorithm device begins sending encoded speech frames. As the speech frames are received, they are decoded and converted back into speech signal voltages. During the normal decoding process, pre-processing of the required SCA parameters will occur and the results stored in the past-history buffer. If a speech frame is detected to be lost or in error, then extrapolation modules are executed and replacement SCA parameters are generated and sent as the parameters required by the SCA. In this way, the information transfer to the SCA is transparent, and the SCA processing continues as usual. The listener will not normally notice that a speech frame has been lost because of the smooth transition between the last-received, lost, and next-received speech frames.

Fuzzy Emotional Semantic Analysis and Automated Annotation of Scene Images

PubMed Central

Cao, Jianfang; Chen, Lichao

2015-01-01

With the advances in electronic and imaging techniques, the production of digital images has rapidly increased, and the extraction and automated annotation of emotional semantics implied by images have become issues that must be urgently addressed. To better simulate human subjectivity and ambiguity for understanding scene images, the current study proposes an emotional semantic annotation method for scene images based on fuzzy set theory. A fuzzy membership degree was calculated to describe the emotional degree of a scene image and was implemented using the Adaboost algorithm and a back-propagation (BP) neural network. The automated annotation method was trained and tested using scene images from the SUN Database. The annotation results were then compared with those based on artificial annotation. Our method showed an annotation accuracy rate of 91.2% for basic emotional values and 82.4% after extended emotional values were added, which correspond to increases of 5.5% and 8.9%, respectively, compared with the results from using a single BP neural network algorithm. Furthermore, the retrieval accuracy rate based on our method reached approximately 89%. This study attempts to lay a solid foundation for the automated emotional semantic annotation of more types of images and therefore is of practical significance. PMID:25838818

Prediction of mortality after radical cystectomy for bladder cancer by machine learning techniques.

PubMed

Wang, Guanjin; Lam, Kin-Man; Deng, Zhaohong; Choi, Kup-Sze

2015-08-01

Bladder cancer is a common cancer in genitourinary malignancy. For muscle invasive bladder cancer, surgical removal of the bladder, i.e. radical cystectomy, is in general the definitive treatment which, unfortunately, carries significant morbidities and mortalities. Accurate prediction of the mortality of radical cystectomy is therefore needed. Statistical methods have conventionally been used for this purpose, despite the complex interactions of high-dimensional medical data. Machine learning has emerged as a promising technique for handling high-dimensional data, with increasing application in clinical decision support, e.g. cancer prediction and prognosis. Its ability to reveal the hidden nonlinear interactions and interpretable rules between dependent and independent variables is favorable for constructing models of effective generalization performance. In this paper, seven machine learning methods are utilized to predict the 5-year mortality of radical cystectomy, including back-propagation neural network (BPN), radial basis function (RBFN), extreme learning machine (ELM), regularized ELM (RELM), support vector machine (SVM), naive Bayes (NB) classifier and k-nearest neighbour (KNN), on a clinicopathological dataset of 117 patients of the urology unit of a hospital in Hong Kong. The experimental results indicate that RELM achieved the highest average prediction accuracy of 0.8 at a fast learning speed. The research findings demonstrate the potential of applying machine learning techniques to support clinical decision making. Copyright © 2015 Elsevier Ltd. All rights reserved.

Self-organizing neural networks--an alternative way of cluster analysis in clinical chemistry.

PubMed

Reibnegger, G; Wachter, H

1996-04-15

Supervised learning schemes have been employed by several workers for training neural networks designed to solve clinical problems. We demonstrate that unsupervised techniques can also produce interesting and meaningful results. Using a data set on the chemical composition of milk from 22 different mammals, we demonstrate that self-organizing feature maps (Kohonen networks) as well as a modified version of error backpropagation technique yield results mimicking conventional cluster analysis. Both techniques are able to project a potentially multi-dimensional input vector onto a two-dimensional space whereby neighborhood relationships remain conserved. Thus, these techniques can be used for reducing dimensionality of complicated data sets and for enhancing comprehensibility of features hidden in the data matrix.

Learning to train neural networks for real-world control problems

NASA Technical Reports Server (NTRS)

Feldkamp, Lee A.; Puskorius, G. V.; Davis, L. I., Jr.; Yuan, F.

1994-01-01

Over the past three years, our group has concentrated on the application of neural network methods to the training of controllers for real-world systems. This presentation describes our approach, surveys what we have found to be important, mentions some contributions to the field, and shows some representative results. Topics discussed include: (1) executing model studies as rehearsal for experimental studies; (2) the importance of correct derivatives; (3) effective training with second-order (DEKF) methods; (4) the efficacy of time-lagged recurrent networks; (5) liberation from the tyranny of the control cycle using asynchronous truncated backpropagation through time; and (6) multistream training for robustness. Results from model studies of automotive idle speed control serve as examples for several of these topics.

Detection of Atrial Fibrillation Using Artifical Neural Network with Power Spectrum Density of RR Interval of Electrocardiogram

NASA Astrophysics Data System (ADS)

Afdala, Adfal; Nuryani, Nuryani; Satrio Nugroho, Anto

2017-01-01

Atrial fibrillation (AF) is a disorder of the heart with fairly high mortality in adults. AF is a common heart arrythmia which is characterized by a missing or irregular contraction of atria. Therefore, finding a method to detect atrial fibrillation is necessary. In this article a system to detect atrial fibrillation has been proposed. Detection system utilized backpropagation artifical neural network. Data input in this method includes power spectrum density of R-peaks interval of electrocardiogram which is selected by wrapping method. This research uses parameter learning rate, momentum, epoch and hidden layer. System produces good performance with accuracy, sensitivity, and specificity of 83.55%, 86.72 % and 81.47 %, respectively.

Learning control system design based on 2-D theory - An application to parallel link manipulator

NASA Technical Reports Server (NTRS)

Geng, Z.; Carroll, R. L.; Lee, J. D.; Haynes, L. H.

1990-01-01

An approach to iterative learning control system design based on two-dimensional system theory is presented. A two-dimensional model for the iterative learning control system which reveals the connections between learning control systems and two-dimensional system theory is established. A learning control algorithm is proposed, and the convergence of learning using this algorithm is guaranteed by two-dimensional stability. The learning algorithm is applied successfully to the trajectory tracking control problem for a parallel link robot manipulator. The excellent performance of this learning algorithm is demonstrated by the computer simulation results.

Forecast Modelling via Variations in Binary Image-Encoded Information Exploited by Deep Learning Neural Networks.

PubMed

Liu, Da; Xu, Ming; Niu, Dongxiao; Wang, Shoukai; Liang, Sai

2016-01-01

Traditional forecasting models fit a function approximation from dependent invariables to independent variables. However, they usually get into trouble when date are presented in various formats, such as text, voice and image. This study proposes a novel image-encoded forecasting method that input and output binary digital two-dimensional (2D) images are transformed from decimal data. Omitting any data analysis or cleansing steps for simplicity, all raw variables were selected and converted to binary digital images as the input of a deep learning model, convolutional neural network (CNN). Using shared weights, pooling and multiple-layer back-propagation techniques, the CNN was adopted to locate the nexus among variations in local binary digital images. Due to the computing capability that was originally developed for binary digital bitmap manipulation, this model has significant potential for forecasting with vast volume of data. The model was validated by a power loads predicting dataset from the Global Energy Forecasting Competition 2012.

Forecast Modelling via Variations in Binary Image-Encoded Information Exploited by Deep Learning Neural Networks

PubMed Central

Xu, Ming; Niu, Dongxiao; Wang, Shoukai; Liang, Sai

2016-01-01

Traditional forecasting models fit a function approximation from dependent invariables to independent variables. However, they usually get into trouble when date are presented in various formats, such as text, voice and image. This study proposes a novel image-encoded forecasting method that input and output binary digital two-dimensional (2D) images are transformed from decimal data. Omitting any data analysis or cleansing steps for simplicity, all raw variables were selected and converted to binary digital images as the input of a deep learning model, convolutional neural network (CNN). Using shared weights, pooling and multiple-layer back-propagation techniques, the CNN was adopted to locate the nexus among variations in local binary digital images. Due to the computing capability that was originally developed for binary digital bitmap manipulation, this model has significant potential for forecasting with vast volume of data. The model was validated by a power loads predicting dataset from the Global Energy Forecasting Competition 2012. PMID:27281032

An adequacy-constrained integrated planning method for effective accommodation of DG and electric vehicles in smart distribution systems

NASA Astrophysics Data System (ADS)

Tan, Zhukui; Xie, Baiming; Zhao, Yuanliang; Dou, Jinyue; Yan, Tong; Liu, Bin; Zeng, Ming

2018-06-01

This paper presents a new integrated planning framework for effective accommodating electric vehicles in smart distribution systems (SDS). The proposed method incorporates various investment options available for the utility collectively, including distributed generation (DG), capacitors and network reinforcement. Using a back-propagation algorithm combined with cost-benefit analysis, the optimal network upgrade plan, allocation and sizing of the selected components are determined, with the purpose of minimizing the total system capital and operating costs of DG and EV accommodation. Furthermore, a new iterative reliability test method is proposed. It can check the optimization results by subsequently simulating the reliability level of the planning scheme, and modify the generation reserve margin to guarantee acceptable adequacy levels for each year of the planning horizon. Numerical results based on a 32-bus distribution system verify the effectiveness of the proposed method.

Optimization of Adaboost Algorithm for Sonar Target Detection in a Multi-Stage ATR System

NASA Technical Reports Server (NTRS)

Lin, Tsung Han (Hank)

2011-01-01

JPL has developed a multi-stage Automated Target Recognition (ATR) system to locate objects in images. First, input images are preprocessed and sent to a Grayscale Optical Correlator (GOC) filter to identify possible regions-of-interest (ROIs). Second, feature extraction operations are performed using Texton filters and Principal Component Analysis (PCA). Finally, the features are fed to a classifier, to identify ROIs that contain the targets. Previous work used the Feed-forward Back-propagation Neural Network for classification. In this project we investigate a version of Adaboost as a classifier for comparison. The version we used is known as GentleBoost. We used the boosted decision tree as the weak classifier. We have tested our ATR system against real-world sonar images using the Adaboost approach. Results indicate an improvement in performance over a single Neural Network design.

Analysis of fault-tolerant neurocontrol architectures

NASA Technical Reports Server (NTRS)

Troudet, T.; Merrill, W.

1992-01-01

The fault-tolerance of analog parallel distributed implementations of a multivariable aircraft neurocontroller is analyzed by simulating weight and neuron failures in a simplified scheme of analog processing based on the functional architecture of the ETANN chip (Electrically Trainable Artificial Neural Network). The neural information processing is found to be only partially distributed throughout the set of weights of the neurocontroller synthesized with the backpropagation algorithm. Although the degree of distribution of the neural processing, and consequently the fault-tolerance of the neurocontroller, could be enhanced using Locally Distributed Weight and Neuron Approaches, a satisfactory level of fault-tolerance could only be obtained by retraining the degrated VLSI neurocontroller. The possibility of maintaining neurocontrol performance and stability in the presence of single weight of neuron failures was demonstrated through an automated retraining procedure of the neurocontroller based on a pre-programmed choice and sequence of the training parameters.

Fatigue design of a cellular phone folder using regression model-based multi-objective optimization

NASA Astrophysics Data System (ADS)

Kim, Young Gyun; Lee, Jongsoo

2016-08-01

In a folding cellular phone, the folding device is repeatedly opened and closed by the user, which eventually results in fatigue damage, particularly to the front of the folder. Hence, it is important to improve the safety and endurance of the folder while also reducing its weight. This article presents an optimal design for the folder front that maximizes its fatigue endurance while minimizing its thickness. Design data for analysis and optimization were obtained experimentally using a test jig. Multi-objective optimization was carried out using a nonlinear regression model. Three regression methods were employed: back-propagation neural networks, logistic regression and support vector machines. The AdaBoost ensemble technique was also used to improve the approximation. Two-objective Pareto-optimal solutions were identified using the non-dominated sorting genetic algorithm (NSGA-II). Finally, a numerically optimized solution was validated against experimental product data, in terms of both fatigue endurance and thickness index.

A neural approach for improving the measurement capability of an electronic nose

NASA Astrophysics Data System (ADS)

Chimenti, M.; DeRossi, D.; Di Francesco, F.; Domenici, C.; Pieri, G.; Pioggia, G.; Salvetti, O.

2003-06-01

Electronic noses, instruments for automatic recognition of odours, are typically composed of an array of partially selective sensors, a sampling system, a data acquisition device and a data processing system. For the purpose of evaluating the quality of olive oil, an electronic nose based on an array of conducting polymer sensors capable of discriminating olive oil aromas was developed. The selection of suitable pattern recognition techniques for a particular application can enhance the performance of electronic noses. Therefore, an advanced neural recognition algorithm for improving the measurement capability of the device was designed and implemented. This method combines multivariate statistical analysis and a hierarchical neural-network architecture based on self-organizing maps and error back-propagation. The complete system was tested using samples composed of characteristic olive oil aromatic components in refined olive oil. The results obtained have shown that this approach is effective in grouping aromas into different categories representative of their chemical structure.

Neural network approach to the inverse problem of the crack-depth determination from ultrasonic backscattering data

NASA Astrophysics Data System (ADS)

Takadoya, M.; Notake, M.; Kitahara, M.; Achenbach, J. D.; Guo, Q. C.; Peterson, M. L.

A neural network approach has been developed to determine the depth of a surface breaking crack in a steel plate from ultrasonic backscattering data. The network is trained by the use of a feedforward three-layered network together with a back-propagation algorithm for error corrections. Synthetic data are employed for network training. The signal used for crack isonification is a mode converted 45 deg transverse wave. The plate with a surface breaking crack is immersed in water, and the crack is insonified from the opposite uncracked side of the plate. A numerical analysis of the backscattered field is carried out based on the elastic wave theory by the use of the boundary element method. The numerical analysis provides synthetic data for the training of the network. The training data have been calculated for cracks with specific increments of the experimental data which are different from the training data.

On the importance of FIB-SEM specific segmentation algorithms for porous media

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

Salzer, Martin, E-mail: martin.salzer@uni-ulm.de; Thiele, Simon, E-mail: simon.thiele@imtek.uni-freiburg.de; Zengerle, Roland, E-mail: zengerle@imtek.uni-freiburg.de

2014-09-15

A new algorithmic approach to segmentation of highly porous three dimensional image data gained by focused ion beam tomography is described which extends the key-principle of local threshold backpropagation described in Salzer et al. (2012). The technique of focused ion beam tomography has shown to be capable of imaging the microstructure of functional materials. In order to perform a quantitative analysis on the corresponding microstructure a segmentation task needs to be performed. However, algorithmic segmentation of images obtained with focused ion beam tomography is a challenging problem for highly porous materials if filling the pore phase, e.g. with epoxy resin,more » is difficult. The gray intensities of individual voxels are not sufficient to determine the phase represented by them and usual thresholding methods are not applicable. We thus propose a new approach to segmentation that pays respect to the specifics of the imaging process of focused ion beam tomography. As an application of our approach, the segmentation of three dimensional images for a cathode material used in polymer electrolyte membrane fuel cells is discussed. We show that our approach preserves significantly more of the original nanostructure than a thresholding approach. - Highlights: • We describe a new approach to the segmentation of FIB-SEM images of porous media. • The first and last occurrences of structures are detected by analysing the z-profiles. • The algorithm is validated by comparing it to a manual segmentation. • The new approach shows significantly less artifacts than a thresholding approach. • A structural analysis also shows improved results for the obtained microstructure.« less

Active Learning Using Hint Information.

PubMed

Li, Chun-Liang; Ferng, Chun-Sung; Lin, Hsuan-Tien

2015-08-01

The abundance of real-world data and limited labeling budget calls for active learning, an important learning paradigm for reducing human labeling efforts. Many recently developed active learning algorithms consider both uncertainty and representativeness when making querying decisions. However, exploiting representativeness with uncertainty concurrently usually requires tackling sophisticated and challenging learning tasks, such as clustering. In this letter, we propose a new active learning framework, called hinted sampling, which takes both uncertainty and representativeness into account in a simpler way. We design a novel active learning algorithm within the hinted sampling framework with an extended support vector machine. Experimental results validate that the novel active learning algorithm can result in a better and more stable performance than that achieved by state-of-the-art algorithms. We also show that the hinted sampling framework allows improving another active learning algorithm designed from the transductive support vector machine.

Dynamics of action potential backpropagation in basal dendrites of prefrontal cortical pyramidal neurons.

PubMed

Zhou, Wen-Liang; Yan, Ping; Wuskell, Joseph P; Loew, Leslie M; Antic, Srdjan D

2008-02-01

Basal dendrites of neocortical pyramidal neurons are relatively short and directly attached to the cell body. This allows electrical signals arising in basal dendrites to strongly influence the neuronal output. Likewise, somatic action potentials (APs) should readily propagate back into the basilar dendritic tree to influence synaptic plasticity. Two recent studies, however, determined that sodium APs are severely attenuated in basal dendrites of cortical pyramidal cells, so that they completely fail in distal dendritic segments. Here we used the latest improvements in the voltage-sensitive dye imaging technique (Zhou et al., 2007) to study AP backpropagation in basal dendrites of layer 5 pyramidal neurons of the rat prefrontal cortex. With a signal-to-noise ratio of > 15 and minimal temporal averaging (only four sweeps) we were able to sample AP waveforms from the very last segments of individual dendritic branches (dendritic tips). We found that in short- (< 150 microm) and medium (150-200 microm in length)-range basal dendrites APs backpropagated with modest changes in AP half-width or AP rise-time. The lack of substantial changes in AP shape and dynamics of rise is inconsistent with the AP-failure model. The lack of substantial amplitude boosting of the third AP in the high-frequency burst also suggests that in short- and medium-range basal dendrites backpropagating APs were not severely attenuated. Our results show that the AP-failure concept does not apply in all basal dendrites of the rat prefrontal cortex. The majority of synaptic contacts in the basilar dendritic tree actually received significant AP-associated electrical and calcium transients.

Brain-machine interface control of a manipulator using small-world neural network and shared control strategy.

PubMed

Li, Ting; Hong, Jun; Zhang, Jinhua; Guo, Feng

2014-03-15

The improvement of the resolution of brain signal and the ability to control external device has been the most important goal in BMI research field. This paper describes a non-invasive brain-actuated manipulator experiment, which defined a paradigm for the motion control of a serial manipulator based on motor imagery and shared control. The techniques of component selection, spatial filtering and classification of motor imagery were involved. Small-world neural network (SWNN) was used to classify five brain states. To verify the effectiveness of the proposed classifier, we replace the SWNN classifier by a radial basis function (RBF) networks neural network, a standard multi-layered feed-forward backpropagation network (SMN) and a multi-SVM classifier, with the same features for the classification. The results also indicate that the proposed classifier achieves a 3.83% improvement over the best results of other classifiers. We proposed a shared control method consisting of two control patterns to expand the control of BMI from the software angle. The job of path building for reaching the 'end' point was designated as an assessment task. We recorded all paths contributed by subjects and picked up relevant parameters as evaluation coefficients. With the assistance of two control patterns and series of machine learning algorithms, the proposed BMI originally achieved the motion control of a manipulator in the whole workspace. According to experimental results, we confirmed the feasibility of the proposed BMI method for 3D motion control of a manipulator using EEG during motor imagery. Copyright © 2013 Elsevier B.V. All rights reserved.

Autonomous self-configuration of artificial neural networks for data classification or system control

NASA Astrophysics Data System (ADS)

Fink, Wolfgang

2009-05-01

Artificial neural networks (ANNs) are powerful methods for the classification of multi-dimensional data as well as for the control of dynamic systems. In general terms, ANNs consist of neurons that are, e.g., arranged in layers and interconnected by real-valued or binary neural couplings or weights. ANNs try mimicking the processing taking place in biological brains. The classification and generalization capabilities of ANNs are given by the interconnection architecture and the coupling strengths. To perform a certain classification or control task with a particular ANN architecture (i.e., number of neurons, number of layers, etc.), the inter-neuron couplings and their accordant coupling strengths must be determined (1) either by a priori design (i.e., manually) or (2) using training algorithms such as error back-propagation. The more complex the classification or control task, the less obvious it is how to determine an a priori design of an ANN, and, as a consequence, the architecture choice becomes somewhat arbitrary. Furthermore, rather than being able to determine for a given architecture directly the corresponding coupling strengths necessary to perform the classification or control task, these have to be obtained/learned through training of the ANN on test data. We report on the use of a Stochastic Optimization Framework (SOF; Fink, SPIE 2008) for the autonomous self-configuration of Artificial Neural Networks (i.e., the determination of number of hidden layers, number of neurons per hidden layer, interconnections between neurons, and respective coupling strengths) for performing classification or control tasks. This may provide an approach towards cognizant and self-adapting computing architectures and systems.

Assessment of earthquake-triggered landslide susceptibility in El Salvador based on an Artificial Neural Network model

NASA Astrophysics Data System (ADS)

García-Rodríguez, M. J.; Malpica, J. A.

2010-06-01

This paper presents an approach for assessing earthquake-triggered landslide susceptibility using artificial neural networks (ANNs). The computational method used for the training process is a back-propagation learning algorithm. It is applied to El Salvador, one of the most seismically active regions in Central America, where the last severe destructive earthquakes occurred on 13 January 2001 (Mw 7.7) and 13 February 2001 (Mw 6.6). The first one triggered more than 600 landslides (including the most tragic, Las Colinas landslide) and killed at least 844 people. The ANN is designed and programmed to develop landslide susceptibility analysis techniques at a regional scale. This approach uses an inventory of landslides and different parameters of slope instability: slope gradient, elevation, aspect, mean annual precipitation, lithology, land use, and terrain roughness. The information obtained from ANN is then used by a Geographic Information System (GIS) to map the landslide susceptibility. In a previous work, a Logistic Regression (LR) was analysed with the same parameters considered in the ANN as independent variables and the occurrence or non-occurrence of landslides as dependent variables. As a result, the logistic approach determined the importance of terrain roughness and soil type as key factors within the model. The results of the landslide susceptibility analysis with ANN are checked using landslide location data. These results show a high concordance between the landslide inventory and the high susceptibility estimated zone. Finally, a comparative analysis of the ANN and LR models are made. The advantages and disadvantages of both approaches are discussed using Receiver Operating Characteristic (ROC) curves.

A developmental approach to learning causal models for cyber security

NASA Astrophysics Data System (ADS)

Mugan, Jonathan

2013-05-01

To keep pace with our adversaries, we must expand the scope of machine learning and reasoning to address the breadth of possible attacks. One approach is to employ an algorithm to learn a set of causal models that describes the entire cyber network and each host end node. Such a learning algorithm would run continuously on the system and monitor activity in real time. With a set of causal models, the algorithm could anticipate novel attacks, take actions to thwart them, and predict the second-order effects flood of information, and the algorithm would have to determine which streams of that flood were relevant in which situations. This paper will present the results of efforts toward the application of a developmental learning algorithm to the problem of cyber security. The algorithm is modeled on the principles of human developmental learning and is designed to allow an agent to learn about the computer system in which it resides through active exploration. Children are flexible learners who acquire knowledge by actively exploring their environment and making predictions about what they will find,1, 2 and our algorithm is inspired by the work of the developmental psychologist Jean Piaget.3 Piaget described how children construct knowledge in stages and learn new concepts on top of those they already know. Developmental learning allows our algorithm to focus on subsets of the environment that are most helpful for learning given its current knowledge. In experiments, the algorithm was able to learn the conditions for file exfiltration and use that knowledge to protect sensitive files.

Discrete-Time Deterministic $Q$ -Learning: A Novel Convergence Analysis.

PubMed

Wei, Qinglai; Lewis, Frank L; Sun, Qiuye; Yan, Pengfei; Song, Ruizhuo

2017-05-01

In this paper, a novel discrete-time deterministic Q -learning algorithm is developed. In each iteration of the developed Q -learning algorithm, the iterative Q function is updated for all the state and control spaces, instead of updating for a single state and a single control in traditional Q -learning algorithm. A new convergence criterion is established to guarantee that the iterative Q function converges to the optimum, where the convergence criterion of the learning rates for traditional Q -learning algorithms is simplified. During the convergence analysis, the upper and lower bounds of the iterative Q function are analyzed to obtain the convergence criterion, instead of analyzing the iterative Q function itself. For convenience of analysis, the convergence properties for undiscounted case of the deterministic Q -learning algorithm are first developed. Then, considering the discounted factor, the convergence criterion for the discounted case is established. Neural networks are used to approximate the iterative Q function and compute the iterative control law, respectively, for facilitating the implementation of the deterministic Q -learning algorithm. Finally, simulation results and comparisons are given to illustrate the performance of the developed algorithm.

A study on the performance comparison of metaheuristic algorithms on the learning of neural networks

NASA Astrophysics Data System (ADS)

Lai, Kee Huong; Zainuddin, Zarita; Ong, Pauline

2017-08-01

The learning or training process of neural networks entails the task of finding the most optimal set of parameters, which includes translation vectors, dilation parameter, synaptic weights, and bias terms. Apart from the traditional gradient descent-based methods, metaheuristic methods can also be used for this learning purpose. Since the inception of genetic algorithm half a century ago, the last decade witnessed the explosion of a variety of novel metaheuristic algorithms, such as harmony search algorithm, bat algorithm, and whale optimization algorithm. Despite the proof of the no free lunch theorem in the discipline of optimization, a survey in the literature of machine learning gives contrasting results. Some researchers report that certain metaheuristic algorithms are superior to the others, whereas some others argue that different metaheuristic algorithms give comparable performance. As such, this paper aims to investigate if a certain metaheuristic algorithm will outperform the other algorithms. In this work, three metaheuristic algorithms, namely genetic algorithms, particle swarm optimization, and harmony search algorithm are considered. The algorithms are incorporated in the learning of neural networks and their classification results on the benchmark UCI machine learning data sets are compared. It is found that all three metaheuristic algorithms give similar and comparable performance, as captured in the average overall classification accuracy. The results corroborate the findings reported in the works done by previous researchers. Several recommendations are given, which include the need of statistical analysis to verify the results and further theoretical works to support the obtained empirical results.

Chromatic characterization of a three-channel colorimeter using back-propagation neural networks

NASA Astrophysics Data System (ADS)

Pardo, P. J.; Pérez, A. L.; Suero, M. I.

2004-09-01

This work describes a method for the chromatic characterization of a three-channel colorimeter of recent design and construction dedicated to color vision research. The colorimeter consists of two fixed monochromators and a third monochromator interchangeable with a cathode ray tube or any other external light source. Back-propagation neural networks were used for the chromatic characterization to establish the relationship between each monochromator's input parameters and the tristimulus values of each chromatic stimulus generated. The results showed the effectiveness of this type of neural-network-based system for the chromatic characterization of the stimuli produced by any monochromator.

A junction-tree based learning algorithm to optimize network wide traffic control: A coordinated multi-agent framework

DOE PAGES

Zhu, Feng; Aziz, H. M. Abdul; Qian, Xinwu; ...

2015-01-31

Our study develops a novel reinforcement learning algorithm for the challenging coordinated signal control problem. Traffic signals are modeled as intelligent agents interacting with the stochastic traffic environment. The model is built on the framework of coordinated reinforcement learning. The Junction Tree Algorithm (JTA) based reinforcement learning is proposed to obtain an exact inference of the best joint actions for all the coordinated intersections. Moreover, the algorithm is implemented and tested with a network containing 18 signalized intersections in VISSIM. Finally, our results show that the JTA based algorithm outperforms independent learning (Q-learning), real-time adaptive learning, and fixed timing plansmore » in terms of average delay, number of stops, and vehicular emissions at the network level.« less

Grounding the Meanings in Sensorimotor Behavior using Reinforcement Learning

PubMed Central

Farkaš, Igor; Malík, Tomáš; Rebrová, Kristína

2012-01-01

The recent outburst of interest in cognitive developmental robotics is fueled by the ambition to propose ecologically plausible mechanisms of how, among other things, a learning agent/robot could ground linguistic meanings in its sensorimotor behavior. Along this stream, we propose a model that allows the simulated iCub robot to learn the meanings of actions (point, touch, and push) oriented toward objects in robot’s peripersonal space. In our experiments, the iCub learns to execute motor actions and comment on them. Architecturally, the model is composed of three neural-network-based modules that are trained in different ways. The first module, a two-layer perceptron, is trained by back-propagation to attend to the target position in the visual scene, given the low-level visual information and the feature-based target information. The second module, having the form of an actor-critic architecture, is the most distinguishing part of our model, and is trained by a continuous version of reinforcement learning to execute actions as sequences, based on a linguistic command. The third module, an echo-state network, is trained to provide the linguistic description of the executed actions. The trained model generalizes well in case of novel action-target combinations with randomized initial arm positions. It can also promptly adapt its behavior if the action/target suddenly changes during motor execution. PMID:22393319

A renaissance of neural networks in drug discovery.

PubMed

Baskin, Igor I; Winkler, David; Tetko, Igor V

2016-08-01

Neural networks are becoming a very popular method for solving machine learning and artificial intelligence problems. The variety of neural network types and their application to drug discovery requires expert knowledge to choose the most appropriate approach. In this review, the authors discuss traditional and newly emerging neural network approaches to drug discovery. Their focus is on backpropagation neural networks and their variants, self-organizing maps and associated methods, and a relatively new technique, deep learning. The most important technical issues are discussed including overfitting and its prevention through regularization, ensemble and multitask modeling, model interpretation, and estimation of applicability domain. Different aspects of using neural networks in drug discovery are considered: building structure-activity models with respect to various targets; predicting drug selectivity, toxicity profiles, ADMET and physicochemical properties; characteristics of drug-delivery systems and virtual screening. Neural networks continue to grow in importance for drug discovery. Recent developments in deep learning suggests further improvements may be gained in the analysis of large chemical data sets. It's anticipated that neural networks will be more widely used in drug discovery in the future, and applied in non-traditional areas such as drug delivery systems, biologically compatible materials, and regenerative medicine.

An analysis dictionary learning algorithm under a noisy data model with orthogonality constraint.

PubMed

Zhang, Ye; Yu, Tenglong; Wang, Wenwu

2014-01-01

Two common problems are often encountered in analysis dictionary learning (ADL) algorithms. The first one is that the original clean signals for learning the dictionary are assumed to be known, which otherwise need to be estimated from noisy measurements. This, however, renders a computationally slow optimization process and potentially unreliable estimation (if the noise level is high), as represented by the Analysis K-SVD (AK-SVD) algorithm. The other problem is the trivial solution to the dictionary, for example, the null dictionary matrix that may be given by a dictionary learning algorithm, as discussed in the learning overcomplete sparsifying transform (LOST) algorithm. Here we propose a novel optimization model and an iterative algorithm to learn the analysis dictionary, where we directly employ the observed data to compute the approximate analysis sparse representation of the original signals (leading to a fast optimization procedure) and enforce an orthogonality constraint on the optimization criterion to avoid the trivial solutions. Experiments demonstrate the competitive performance of the proposed algorithm as compared with three baselines, namely, the AK-SVD, LOST, and NAAOLA algorithms.

Active learning for clinical text classification: is it better than random sampling?

PubMed

Figueroa, Rosa L; Zeng-Treitler, Qing; Ngo, Long H; Goryachev, Sergey; Wiechmann, Eduardo P

2012-01-01

This study explores active learning algorithms as a way to reduce the requirements for large training sets in medical text classification tasks. Three existing active learning algorithms (distance-based (DIST), diversity-based (DIV), and a combination of both (CMB)) were used to classify text from five datasets. The performance of these algorithms was compared to that of passive learning on the five datasets. We then conducted a novel investigation of the interaction between dataset characteristics and the performance results. Classification accuracy and area under receiver operating characteristics (ROC) curves for each algorithm at different sample sizes were generated. The performance of active learning algorithms was compared with that of passive learning using a weighted mean of paired differences. To determine why the performance varies on different datasets, we measured the diversity and uncertainty of each dataset using relative entropy and correlated the results with the performance differences. The DIST and CMB algorithms performed better than passive learning. With a statistical significance level set at 0.05, DIST outperformed passive learning in all five datasets, while CMB was found to be better than passive learning in four datasets. We found strong correlations between the dataset diversity and the DIV performance, as well as the dataset uncertainty and the performance of the DIST algorithm. For medical text classification, appropriate active learning algorithms can yield performance comparable to that of passive learning with considerably smaller training sets. In particular, our results suggest that DIV performs better on data with higher diversity and DIST on data with lower uncertainty.

Active learning for clinical text classification: is it better than random sampling?

PubMed Central

Figueroa, Rosa L; Ngo, Long H; Goryachev, Sergey; Wiechmann, Eduardo P

2012-01-01

Objective This study explores active learning algorithms as a way to reduce the requirements for large training sets in medical text classification tasks. Design Three existing active learning algorithms (distance-based (DIST), diversity-based (DIV), and a combination of both (CMB)) were used to classify text from five datasets. The performance of these algorithms was compared to that of passive learning on the five datasets. We then conducted a novel investigation of the interaction between dataset characteristics and the performance results. Measurements Classification accuracy and area under receiver operating characteristics (ROC) curves for each algorithm at different sample sizes were generated. The performance of active learning algorithms was compared with that of passive learning using a weighted mean of paired differences. To determine why the performance varies on different datasets, we measured the diversity and uncertainty of each dataset using relative entropy and correlated the results with the performance differences. Results The DIST and CMB algorithms performed better than passive learning. With a statistical significance level set at 0.05, DIST outperformed passive learning in all five datasets, while CMB was found to be better than passive learning in four datasets. We found strong correlations between the dataset diversity and the DIV performance, as well as the dataset uncertainty and the performance of the DIST algorithm. Conclusion For medical text classification, appropriate active learning algorithms can yield performance comparable to that of passive learning with considerably smaller training sets. In particular, our results suggest that DIV performs better on data with higher diversity and DIST on data with lower uncertainty. PMID:22707743

Machine Learning Methods for Attack Detection in the Smart Grid.

PubMed

Ozay, Mete; Esnaola, Inaki; Yarman Vural, Fatos Tunay; Kulkarni, Sanjeev R; Poor, H Vincent

2016-08-01

Attack detection problems in the smart grid are posed as statistical learning problems for different attack scenarios in which the measurements are observed in batch or online settings. In this approach, machine learning algorithms are used to classify measurements as being either secure or attacked. An attack detection framework is provided to exploit any available prior knowledge about the system and surmount constraints arising from the sparse structure of the problem in the proposed approach. Well-known batch and online learning algorithms (supervised and semisupervised) are employed with decision- and feature-level fusion to model the attack detection problem. The relationships between statistical and geometric properties of attack vectors employed in the attack scenarios and learning algorithms are analyzed to detect unobservable attacks using statistical learning methods. The proposed algorithms are examined on various IEEE test systems. Experimental analyses show that machine learning algorithms can detect attacks with performances higher than attack detection algorithms that employ state vector estimation methods in the proposed attack detection framework.

A Locality-Constrained and Label Embedding Dictionary Learning Algorithm for Image Classification.

PubMed

Zhengming Li; Zhihui Lai; Yong Xu; Jian Yang; Zhang, David

2017-02-01

Locality and label information of training samples play an important role in image classification. However, previous dictionary learning algorithms do not take the locality and label information of atoms into account together in the learning process, and thus their performance is limited. In this paper, a discriminative dictionary learning algorithm, called the locality-constrained and label embedding dictionary learning (LCLE-DL) algorithm, was proposed for image classification. First, the locality information was preserved using the graph Laplacian matrix of the learned dictionary instead of the conventional one derived from the training samples. Then, the label embedding term was constructed using the label information of atoms instead of the classification error term, which contained discriminating information of the learned dictionary. The optimal coding coefficients derived by the locality-based and label-based reconstruction were effective for image classification. Experimental results demonstrated that the LCLE-DL algorithm can achieve better performance than some state-of-the-art algorithms.

Fidelity-Based Ant Colony Algorithm with Q-learning of Quantum System

NASA Astrophysics Data System (ADS)

Liao, Qin; Guo, Ying; Tu, Yifeng; Zhang, Hang

2018-03-01

Quantum ant colony algorithm (ACA) has potential applications in quantum information processing, such as solutions of traveling salesman problem, zero-one knapsack problem, robot route planning problem, and so on. To shorten the search time of the ACA, we suggest the fidelity-based ant colony algorithm (FACA) for the control of quantum system. Motivated by structure of the Q-learning algorithm, we demonstrate the combination of a FACA with the Q-learning algorithm and suggest the design of a fidelity-based ant colony algorithm with the Q-learning to improve the performance of the FACA in a spin-1/2 quantum system. The numeric simulation results show that the FACA with the Q-learning can efficiently avoid trapping into local optimal policies and increase the speed of convergence process of quantum system.

Fidelity-Based Ant Colony Algorithm with Q-learning of Quantum System

NASA Astrophysics Data System (ADS)

Liao, Qin; Guo, Ying; Tu, Yifeng; Zhang, Hang

2017-12-01

Quantum ant colony algorithm (ACA) has potential applications in quantum information processing, such as solutions of traveling salesman problem, zero-one knapsack problem, robot route planning problem, and so on. To shorten the search time of the ACA, we suggest the fidelity-based ant colony algorithm (FACA) for the control of quantum system. Motivated by structure of the Q-learning algorithm, we demonstrate the combination of a FACA with the Q-learning algorithm and suggest the design of a fidelity-based ant colony algorithm with the Q-learning to improve the performance of the FACA in a spin-1/2 quantum system. The numeric simulation results show that the FACA with the Q-learning can efficiently avoid trapping into local optimal policies and increase the speed of convergence process of quantum system.

Human resource recommendation algorithm based on ensemble learning and Spark

NASA Astrophysics Data System (ADS)

Cong, Zihan; Zhang, Xingming; Wang, Haoxiang; Xu, Hongjie

2017-08-01

Aiming at the problem of “information overload” in the human resources industry, this paper proposes a human resource recommendation algorithm based on Ensemble Learning. The algorithm considers the characteristics and behaviours of both job seeker and job features in the real business circumstance. Firstly, the algorithm uses two ensemble learning methods-Bagging and Boosting. The outputs from both learning methods are then merged to form user interest model. Based on user interest model, job recommendation can be extracted for users. The algorithm is implemented as a parallelized recommendation system on Spark. A set of experiments have been done and analysed. The proposed algorithm achieves significant improvement in accuracy, recall rate and coverage, compared with recommendation algorithms such as UserCF and ItemCF.

A Globally Optimal Particle Tracking Technique for Stereo Imaging Velocimetry Experiments

NASA Technical Reports Server (NTRS)

McDowell, Mark

2008-01-01

An important phase of any Stereo Imaging Velocimetry experiment is particle tracking. Particle tracking seeks to identify and characterize the motion of individual particles entrained in a fluid or air experiment. We analyze a cylindrical chamber filled with water and seeded with density-matched particles. In every four-frame sequence, we identify a particle track by assigning a unique track label for each camera image. The conventional approach to particle tracking is to use an exhaustive tree-search method utilizing greedy algorithms to reduce search times. However, these types of algorithms are not optimal due to a cascade effect of incorrect decisions upon adjacent tracks. We examine the use of a guided evolutionary neural net with simulated annealing to arrive at a globally optimal assignment of tracks. The net is guided both by the minimization of the search space through the use of prior limiting assumptions about valid tracks and by a strategy which seeks to avoid high-energy intermediate states which can trap the net in a local minimum. A stochastic search algorithm is used in place of back-propagation of error to further reduce the chance of being trapped in an energy well. Global optimization is achieved by minimizing an objective function, which includes both track smoothness and particle-image utilization parameters. In this paper we describe our model and present our experimental results. We compare our results with a nonoptimizing, predictive tracker and obtain an average increase in valid track yield of 27 percent

Application of Artificial Neural Network to Predict the use of Runway at Juanda International Airport

NASA Astrophysics Data System (ADS)

Putra, J. C. P.; Safrilah

2017-06-01

Artificial neural network approaches are useful to solve many complicated problems. It solves a number of problems in various areas such as engineering, medicine, business, manufacturing, etc. This paper presents an application of artificial neural network to predict a runway capacity at Juanda International Airport. An artificial neural network model of backpropagation and multi-layer perceptron is adopted to this research to learning process of runway capacity at Juanda International Airport. The results indicate that the training data is successfully recognizing the certain pattern of runway use at Juanda International Airport. Whereas, testing data indicate vice versa. Finally, it can be concluded that the approach of uniformity data and network architecture is the critical part to determine the accuracy of prediction results.

Challenges in the Verification of Reinforcement Learning Algorithms

NASA Technical Reports Server (NTRS)

Van Wesel, Perry; Goodloe, Alwyn E.

2017-01-01

Machine learning (ML) is increasingly being applied to a wide array of domains from search engines to autonomous vehicles. These algorithms, however, are notoriously complex and hard to verify. This work looks at the assumptions underlying machine learning algorithms as well as some of the challenges in trying to verify ML algorithms. Furthermore, we focus on the specific challenges of verifying reinforcement learning algorithms. These are highlighted using a specific example. Ultimately, we do not offer a solution to the complex problem of ML verification, but point out possible approaches for verification and interesting research opportunities.

Semi-supervised learning via regularized boosting working on multiple semi-supervised assumptions.

PubMed

Chen, Ke; Wang, Shihai

2011-01-01

Semi-supervised learning concerns the problem of learning in the presence of labeled and unlabeled data. Several boosting algorithms have been extended to semi-supervised learning with various strategies. To our knowledge, however, none of them takes all three semi-supervised assumptions, i.e., smoothness, cluster, and manifold assumptions, together into account during boosting learning. In this paper, we propose a novel cost functional consisting of the margin cost on labeled data and the regularization penalty on unlabeled data based on three fundamental semi-supervised assumptions. Thus, minimizing our proposed cost functional with a greedy yet stagewise functional optimization procedure leads to a generic boosting framework for semi-supervised learning. Extensive experiments demonstrate that our algorithm yields favorite results for benchmark and real-world classification tasks in comparison to state-of-the-art semi-supervised learning algorithms, including newly developed boosting algorithms. Finally, we discuss relevant issues and relate our algorithm to the previous work.

Efficient Learning Algorithms with Limited Information

ERIC Educational Resources Information Center

De, Anindya

2013-01-01

The thesis explores efficient learning algorithms in settings which are more restrictive than the PAC model of learning (Valiant) in one of the following two senses: (i) The learning algorithm has a very weak access to the unknown function, as in, it does not get labeled samples for the unknown function (ii) The error guarantee required from the…

The Role of Architectural and Learning Constraints in Neural Network Models: A Case Study on Visual Space Coding.

PubMed

Testolin, Alberto; De Filippo De Grazia, Michele; Zorzi, Marco

2017-01-01

The recent "deep learning revolution" in artificial neural networks had strong impact and widespread deployment for engineering applications, but the use of deep learning for neurocomputational modeling has been so far limited. In this article we argue that unsupervised deep learning represents an important step forward for improving neurocomputational models of perception and cognition, because it emphasizes the role of generative learning as opposed to discriminative (supervised) learning. As a case study, we present a series of simulations investigating the emergence of neural coding of visual space for sensorimotor transformations. We compare different network architectures commonly used as building blocks for unsupervised deep learning by systematically testing the type of receptive fields and gain modulation developed by the hidden neurons. In particular, we compare Restricted Boltzmann Machines (RBMs), which are stochastic, generative networks with bidirectional connections trained using contrastive divergence, with autoencoders, which are deterministic networks trained using error backpropagation. For both learning architectures we also explore the role of sparse coding, which has been identified as a fundamental principle of neural computation. The unsupervised models are then compared with supervised, feed-forward networks that learn an explicit mapping between different spatial reference frames. Our simulations show that both architectural and learning constraints strongly influenced the emergent coding of visual space in terms of distribution of tuning functions at the level of single neurons. Unsupervised models, and particularly RBMs, were found to more closely adhere to neurophysiological data from single-cell recordings in the primate parietal cortex. These results provide new insights into how basic properties of artificial neural networks might be relevant for modeling neural information processing in biological systems.

The Role of Architectural and Learning Constraints in Neural Network Models: A Case Study on Visual Space Coding

PubMed Central

Testolin, Alberto; De Filippo De Grazia, Michele; Zorzi, Marco

2017-01-01

The recent “deep learning revolution” in artificial neural networks had strong impact and widespread deployment for engineering applications, but the use of deep learning for neurocomputational modeling has been so far limited. In this article we argue that unsupervised deep learning represents an important step forward for improving neurocomputational models of perception and cognition, because it emphasizes the role of generative learning as opposed to discriminative (supervised) learning. As a case study, we present a series of simulations investigating the emergence of neural coding of visual space for sensorimotor transformations. We compare different network architectures commonly used as building blocks for unsupervised deep learning by systematically testing the type of receptive fields and gain modulation developed by the hidden neurons. In particular, we compare Restricted Boltzmann Machines (RBMs), which are stochastic, generative networks with bidirectional connections trained using contrastive divergence, with autoencoders, which are deterministic networks trained using error backpropagation. For both learning architectures we also explore the role of sparse coding, which has been identified as a fundamental principle of neural computation. The unsupervised models are then compared with supervised, feed-forward networks that learn an explicit mapping between different spatial reference frames. Our simulations show that both architectural and learning constraints strongly influenced the emergent coding of visual space in terms of distribution of tuning functions at the level of single neurons. Unsupervised models, and particularly RBMs, were found to more closely adhere to neurophysiological data from single-cell recordings in the primate parietal cortex. These results provide new insights into how basic properties of artificial neural networks might be relevant for modeling neural information processing in biological systems. PMID:28377709

Compressive sensing of electrocardiogram signals by promoting sparsity on the second-order difference and by using dictionary learning.

PubMed

Pant, Jeevan K; Krishnan, Sridhar

2014-04-01

A new algorithm for the reconstruction of electrocardiogram (ECG) signals and a dictionary learning algorithm for the enhancement of its reconstruction performance for a class of signals are proposed. The signal reconstruction algorithm is based on minimizing the lp pseudo-norm of the second-order difference, called as the lp(2d) pseudo-norm, of the signal. The optimization involved is carried out using a sequential conjugate-gradient algorithm. The dictionary learning algorithm uses an iterative procedure wherein a signal reconstruction and a dictionary update steps are repeated until a convergence criterion is satisfied. The signal reconstruction step is implemented by using the proposed signal reconstruction algorithm and the dictionary update step is implemented by using the linear least-squares method. Extensive simulation results demonstrate that the proposed algorithm yields improved reconstruction performance for temporally correlated ECG signals relative to the state-of-the-art lp(1d)-regularized least-squares and Bayesian learning based algorithms. Also for a known class of signals, the reconstruction performance of the proposed algorithm can be improved by applying it in conjunction with a dictionary obtained using the proposed dictionary learning algorithm.

Recognition of strong earthquake-prone areas with a single learning class

NASA Astrophysics Data System (ADS)

Gvishiani, A. D.; Agayan, S. M.; Dzeboev, B. A.; Belov, I. O.

2017-05-01

This article presents a new Barrier recognition algorithm with learning, designed for recognition of earthquake-prone areas. In comparison to the Crust (Kora) algorithm, used by the classical EPA approach, the Barrier algorithm proceeds with learning just on one "pure" high-seismic class. The new algorithm operates in the space of absolute values of the geological-geophysical parameters of the objects. The algorithm is used for recognition of earthquake-prone areas with M ≥ 6.0 in the Caucasus region. Comparative analysis of the Crust and Barrier algorithms justifies their productive coherence.

Bare-Bones Teaching-Learning-Based Optimization

PubMed Central

Zou, Feng; Wang, Lei; Hei, Xinhong; Chen, Debao; Jiang, Qiaoyong; Li, Hongye

2014-01-01

Teaching-learning-based optimization (TLBO) algorithm which simulates the teaching-learning process of the class room is one of the recently proposed swarm intelligent (SI) algorithms. In this paper, a new TLBO variant called bare-bones teaching-learning-based optimization (BBTLBO) is presented to solve the global optimization problems. In this method, each learner of teacher phase employs an interactive learning strategy, which is the hybridization of the learning strategy of teacher phase in the standard TLBO and Gaussian sampling learning based on neighborhood search, and each learner of learner phase employs the learning strategy of learner phase in the standard TLBO or the new neighborhood search strategy. To verify the performance of our approaches, 20 benchmark functions and two real-world problems are utilized. Conducted experiments can been observed that the BBTLBO performs significantly better than, or at least comparable to, TLBO and some existing bare-bones algorithms. The results indicate that the proposed algorithm is competitive to some other optimization algorithms. PMID:25013844

Bare-bones teaching-learning-based optimization.

PubMed

Zou, Feng; Wang, Lei; Hei, Xinhong; Chen, Debao; Jiang, Qiaoyong; Li, Hongye

2014-01-01

Teaching-learning-based optimization (TLBO) algorithm which simulates the teaching-learning process of the class room is one of the recently proposed swarm intelligent (SI) algorithms. In this paper, a new TLBO variant called bare-bones teaching-learning-based optimization (BBTLBO) is presented to solve the global optimization problems. In this method, each learner of teacher phase employs an interactive learning strategy, which is the hybridization of the learning strategy of teacher phase in the standard TLBO and Gaussian sampling learning based on neighborhood search, and each learner of learner phase employs the learning strategy of learner phase in the standard TLBO or the new neighborhood search strategy. To verify the performance of our approaches, 20 benchmark functions and two real-world problems are utilized. Conducted experiments can been observed that the BBTLBO performs significantly better than, or at least comparable to, TLBO and some existing bare-bones algorithms. The results indicate that the proposed algorithm is competitive to some other optimization algorithms.

[Detection of the main quality indicators in red wine with infrared spectroscopy based on FastICA and neural network].

PubMed

Fang, Li-Min; Lin, Min

2009-08-01

For the rapid detection of the ethanol, pH and rest sugar in red wine, infrared (IR) spectra of 44 wine samples were analyzed. The algorithm of fast independent component analysis (FastICA) was used to decompose the data of IR spectra, and their independent components and the mixing matrix were obtained. Then, the ICA-NNR calibration model with three-level artificial neural network (ANN) structure was built by using back-propagation (BP) algorithm. The models were used to estimate the contents of ethanol, pH and rest sugar in red wine samples for both in calibration set and predicted set. Correlation coefficient (r) of prediction and root mean square error of prediction (RMSEP) were used as the evaluation indexes. The results indicate that the r and RMSEP for the prediction of ethanol content, pH and rest sugar content are 0.953, 0.983 and 0.994, and 0.161, 0.017 and 0.181, respectively. The maximum relative deviations between the ICA-NNR method predicted value and referenced value of the 22 samples in predicted set are less than 4%. The results of this paper provide a foundation for the application and further development of IR on-line red wine analyzer.

Artificial neural networks for acoustic target recognition

NASA Astrophysics Data System (ADS)

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

1995-04-01

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

Optical diffraction tomography: accuracy of an off-axis reconstruction

NASA Astrophysics Data System (ADS)

Kostencka, Julianna; Kozacki, Tomasz

2014-05-01

Optical diffraction tomography is an increasingly popular method that allows for reconstruction of three-dimensional refractive index distribution of semi-transparent samples using multiple measurements of an optical field transmitted through the sample for various illumination directions. The process of assembly of the angular measurements is usually performed with one of two methods: filtered backprojection (FBPJ) or filtered backpropagation (FBPP) tomographic reconstruction algorithm. The former approach, although conceptually very simple, provides an accurate reconstruction for the object regions located close to the plane of focus. However, since FBPJ ignores diffraction, its use for spatially extended structures is arguable. According to the theory of scattering, more precise restoration of a 3D structure shall be achieved with the FBPP algorithm, which unlike the former approach incorporates diffraction. It is believed that with this method one is allowed to obtain a high accuracy reconstruction in a large measurement volume exceeding depth of focus of an imaging system. However, some studies have suggested that a considerable improvement of the FBPP results can be achieved with prior propagation of the transmitted fields back to the centre of the object. This, supposedly, enables reduction of errors due to approximated diffraction formulas used in FBPP. In our view this finding casts doubt on quality of the FBPP reconstruction in the regions far from the rotation axis. The objective of this paper is to investigate limitation of the FBPP algorithm in terms of an off-axis reconstruction and compare its performance with the FBPJ approach. Moreover, in this work we propose some modifications to the FBPP algorithm that allow for more precise restoration of a sample structure in off-axis locations. The research is based on extensive numerical simulations supported with wave-propagation method.

A strategy for quantum algorithm design assisted by machine learning

NASA Astrophysics Data System (ADS)

Bang, Jeongho; Ryu, Junghee; Yoo, Seokwon; Pawłowski, Marcin; Lee, Jinhyoung

2014-07-01

We propose a method for quantum algorithm design assisted by machine learning. The method uses a quantum-classical hybrid simulator, where a ‘quantum student’ is being taught by a ‘classical teacher’. In other words, in our method, the learning system is supposed to evolve into a quantum algorithm for a given problem, assisted by a classical main-feedback system. Our method is applicable for designing quantum oracle-based algorithms. We chose, as a case study, an oracle decision problem, called a Deutsch-Jozsa problem. We showed by using Monte Carlo simulations that our simulator can faithfully learn a quantum algorithm for solving the problem for a given oracle. Remarkably, the learning time is proportional to the square root of the total number of parameters, rather than showing the exponential dependence found in the classical machine learning-based method.

Forecast of Antarctic Sea Ice and Meteorological Fields

NASA Astrophysics Data System (ADS)

Barreira, S.; Orquera, F.

2017-12-01

Since 2001, we have been forecasting the climatic fields of the Antarctic sea ice (SI) and surface air temperature, surface pressure and precipitation anomalies for the Southern Hemisphere at the Meteorological Department of the Argentine Naval Hydrographic Service with different techniques that have evolved with the years. Forecast is based on the results of Principal Components Analysis applied to SI series (S-Mode) that gives patterns of temporal series with validity areas (these series are important to determine which areas in Antarctica will have positive or negative SI anomalies based on what happen in the atmosphere) and, on the other hand, to SI fields (T-Mode) that give us the form of the SI fields anomalies based on a classification of 16 patterns. Each T-Mode pattern has unique atmospheric fields associated to them. Therefore, it is possible to forecast whichever atmosphere variable we decide for the Southern Hemisphere. When the forecast is obtained, each pattern has a probability of occurrence and sometimes it is necessary to compose more than one of them to obtain the final result. S-Mode and T-Mode are monthly updated with new data, for that reason the forecasts improved with the increase of cases since 2001. We used the Monthly Polar Gridded Sea Ice Concentrations database derived from satellite information generated by NASA Team algorithm provided monthly by the National Snow and Ice Data Center of USA that begins in November 1978. Recently, we have been experimenting with multilayer Perceptron (neuronal network) with supervised learning and a back-propagation algorithm to improve the forecast. The Perceptron is the most common Artificial Neural Network topology dedicated to image pattern recognition. It was implemented through the use of temperature and pressure anomalies field images that were associated with a the different sea ice anomaly patterns. The variables analyzed included only composites of surface air temperature and pressure anomalies to simplify the density of input data and avoid a non-converging solution. Sea ice and atmospheric variables forecast can be checked every month at our web page http://www.hidro.gob.ar/smara/sb/sb.asp and at World Meteorological web page (Global Cryosphere Watch) http://globalcryospherewatch.org/state_of_cryo/seaice/.

Online Feature Transformation Learning for Cross-Domain Object Category Recognition.

PubMed

Zhang, Xuesong; Zhuang, Yan; Wang, Wei; Pedrycz, Witold

2017-06-09

In this paper, we introduce a new research problem termed online feature transformation learning in the context of multiclass object category recognition. The learning of a feature transformation is viewed as learning a global similarity metric function in an online manner. We first consider the problem of online learning a feature transformation matrix expressed in the original feature space and propose an online passive aggressive feature transformation algorithm. Then these original features are mapped to kernel space and an online single kernel feature transformation (OSKFT) algorithm is developed to learn a nonlinear feature transformation. Based on the OSKFT and the existing Hedge algorithm, a novel online multiple kernel feature transformation algorithm is also proposed, which can further improve the performance of online feature transformation learning in large-scale application. The classifier is trained with k nearest neighbor algorithm together with the learned similarity metric function. Finally, we experimentally examined the effect of setting different parameter values in the proposed algorithms and evaluate the model performance on several multiclass object recognition data sets. The experimental results demonstrate the validity and good performance of our methods on cross-domain and multiclass object recognition application.

A linear recurrent kernel online learning algorithm with sparse updates.

PubMed

Fan, Haijin; Song, Qing

2014-02-01

In this paper, we propose a recurrent kernel algorithm with selectively sparse updates for online learning. The algorithm introduces a linear recurrent term in the estimation of the current output. This makes the past information reusable for updating of the algorithm in the form of a recurrent gradient term. To ensure that the reuse of this recurrent gradient indeed accelerates the convergence speed, a novel hybrid recurrent training is proposed to switch on or off learning the recurrent information according to the magnitude of the current training error. Furthermore, the algorithm includes a data-dependent adaptive learning rate which can provide guaranteed system weight convergence at each training iteration. The learning rate is set as zero when the training violates the derived convergence conditions, which makes the algorithm updating process sparse. Theoretical analyses of the weight convergence are presented and experimental results show the good performance of the proposed algorithm in terms of convergence speed and estimation accuracy. Copyright © 2013 Elsevier Ltd. All rights reserved.

Kernel Temporal Differences for Neural Decoding

PubMed Central

Bae, Jihye; Sanchez Giraldo, Luis G.; Pohlmeyer, Eric A.; Francis, Joseph T.; Sanchez, Justin C.; Príncipe, José C.

2015-01-01

We study the feasibility and capability of the kernel temporal difference (KTD)(λ) algorithm for neural decoding. KTD(λ) is an online, kernel-based learning algorithm, which has been introduced to estimate value functions in reinforcement learning. This algorithm combines kernel-based representations with the temporal difference approach to learning. One of our key observations is that by using strictly positive definite kernels, algorithm's convergence can be guaranteed for policy evaluation. The algorithm's nonlinear functional approximation capabilities are shown in both simulations of policy evaluation and neural decoding problems (policy improvement). KTD can handle high-dimensional neural states containing spatial-temporal information at a reasonable computational complexity allowing real-time applications. When the algorithm seeks a proper mapping between a monkey's neural states and desired positions of a computer cursor or a robot arm, in both open-loop and closed-loop experiments, it can effectively learn the neural state to action mapping. Finally, a visualization of the coadaptation process between the decoder and the subject shows the algorithm's capabilities in reinforcement learning brain machine interfaces. PMID:25866504

Time-reversal imaging techniques applied to tremor waveforms near Cholame, California to locate tectonic tremor

NASA Astrophysics Data System (ADS)

Horstmann, T.; Harrington, R. M.; Cochran, E. S.

2012-12-01

Frequently, the lack of distinctive phase arrivals makes locating tectonic tremor more challenging than locating earthquakes. Classic location algorithms based on travel times cannot be directly applied because impulsive phase arrivals are often difficult to recognize. Traditional location algorithms are often modified to use phase arrivals identified from stacks of recurring low-frequency events (LFEs) observed within tremor episodes, rather than single events. Stacking the LFE waveforms improves the signal-to-noise ratio for the otherwise non-distinct phase arrivals. In this study, we apply a different method to locate tectonic tremor: a modified time-reversal imaging approach that potentially exploits the information from the entire tremor waveform instead of phase arrivals from individual LFEs. Time reversal imaging uses the waveforms of a given seismic source recorded by multiple seismometers at discrete points on the surface and a 3D velocity model to rebroadcast the waveforms back into the medium to identify the seismic source location. In practice, the method works by reversing the seismograms recorded at each of the stations in time, and back-propagating them from the receiver location individually into the sub-surface as a new source time function. We use a staggered-grid, finite-difference code with 2.5 ms time steps and a grid node spacing of 50 m to compute the rebroadcast wavefield. We calculate the time-dependent curl field at each grid point of the model volume for each back-propagated seismogram. To locate the tremor, we assume that the source time function back-propagated from each individual station produces a similar curl field at the source position. We then cross-correlate the time dependent curl field functions and calculate a median cross-correlation coefficient at each grid point. The highest median cross-correlation coefficient in the model volume is expected to represent the source location. For our analysis, we use the velocity model of Thurber et al. (2006) interpolated to a grid spacing of 50 m. Such grid spacing corresponds to frequencies of up to 8 Hz, which is suitable to calculate the wave propagation of tremor. Our dataset contains continuous broadband data from 13 STS-2 seismometers deployed from May 2010 to July 2011 along the Cholame segment of the San Andreas Fault as well as data from the HRSN and PBO networks. Initial synthetic results from tests on a 2D plane using a line of 15 receivers suggest that we are able to recover accurate event locations to within 100 m horizontally and 300 m depth. We conduct additional synthetic tests to determine the influence of signal-to-noise ratio, number of stations used, and the uncertainty in the velocity model on the location result by adding noise to the seismograms and perturbations to the velocity model. Preliminary results show accurate show location results to within 400 m with a median signal-to-noise ratio of 3.5 and 5% perturbations in the velocity model. The next steps will entail performing the synthetic tests on the 3D velocity model, and applying the method to tremor waveforms. Furthermore, we will determine the spatial and temporal distribution of the source locations and compare our results to those by Sumy and others.

Research on B Cell Algorithm for Learning to Rank Method Based on Parallel Strategy.

PubMed

Tian, Yuling; Zhang, Hongxian

2016-01-01

For the purposes of information retrieval, users must find highly relevant documents from within a system (and often a quite large one comprised of many individual documents) based on input query. Ranking the documents according to their relevance within the system to meet user needs is a challenging endeavor, and a hot research topic-there already exist several rank-learning methods based on machine learning techniques which can generate ranking functions automatically. This paper proposes a parallel B cell algorithm, RankBCA, for rank learning which utilizes a clonal selection mechanism based on biological immunity. The novel algorithm is compared with traditional rank-learning algorithms through experimentation and shown to outperform the others in respect to accuracy, learning time, and convergence rate; taken together, the experimental results show that the proposed algorithm indeed effectively and rapidly identifies optimal ranking functions.

Research on B Cell Algorithm for Learning to Rank Method Based on Parallel Strategy

PubMed Central

Tian, Yuling; Zhang, Hongxian

2016-01-01

For the purposes of information retrieval, users must find highly relevant documents from within a system (and often a quite large one comprised of many individual documents) based on input query. Ranking the documents according to their relevance within the system to meet user needs is a challenging endeavor, and a hot research topic–there already exist several rank-learning methods based on machine learning techniques which can generate ranking functions automatically. This paper proposes a parallel B cell algorithm, RankBCA, for rank learning which utilizes a clonal selection mechanism based on biological immunity. The novel algorithm is compared with traditional rank-learning algorithms through experimentation and shown to outperform the others in respect to accuracy, learning time, and convergence rate; taken together, the experimental results show that the proposed algorithm indeed effectively and rapidly identifies optimal ranking functions. PMID:27487242

Network congestion control algorithm based on Actor-Critic reinforcement learning model

NASA Astrophysics Data System (ADS)

Xu, Tao; Gong, Lina; Zhang, Wei; Li, Xuhong; Wang, Xia; Pan, Wenwen

2018-04-01

Aiming at the network congestion control problem, a congestion control algorithm based on Actor-Critic reinforcement learning model is designed. Through the genetic algorithm in the congestion control strategy, the network congestion problems can be better found and prevented. According to Actor-Critic reinforcement learning, the simulation experiment of network congestion control algorithm is designed. The simulation experiments verify that the AQM controller can predict the dynamic characteristics of the network system. Moreover, the learning strategy is adopted to optimize the network performance, and the dropping probability of packets is adaptively adjusted so as to improve the network performance and avoid congestion. Based on the above finding, it is concluded that the network congestion control algorithm based on Actor-Critic reinforcement learning model can effectively avoid the occurrence of TCP network congestion.

A comparison of two neural network schemes for navigation

NASA Technical Reports Server (NTRS)

Munro, Paul W.

1989-01-01

Neural networks have been applied to tasks in several areas of artificial intelligence, including vision, speech, and language. Relatively little work has been done in the area of problem solving. Two approaches to path-finding are presented, both using neural network techniques. Both techniques require a training period. Training under the back propagation (BPL) method was accomplished by presenting representations of (current position, goal position) pairs as input and appropriate actions as output. The Hebbian/interactive activation (HIA) method uses the Hebbian rule to associate points that are nearby. A path to a goal is found by activating a representation of the goal in the network and processing until the current position is activated above some threshold level. BPL, using back-propagation learning, failed to learn, except in a very trivial fashion, that is equivalent to table lookup techniques. HIA, performed much better, and required storage of fewer weights. In drawing a comparison, it is important to note that back propagation techniques depend critically upon the forms of representation used, and can be sensitive to parameters in the simulations; hence the BPL technique may yet yield strong results.

A comparison of two neural network schemes for navigation

NASA Technical Reports Server (NTRS)

Munro, Paul

1990-01-01

Neural networks have been applied to tasks in several areas of artificial intelligence, including vision, speech, and language. Relatively little work has been done in the area of problem solving. Two approaches to path-finding are presented, both using neural network techniques. Both techniques require a training period. Training under the back propagation (BPL) method was accomplished by presenting representations of current position, goal position pairs as input and appropriate actions as output. The Hebbian/interactive activation (HIA) method uses the Hebbian rule to associate points that are nearby. A path to a goal is found by activating a representation of the goal in the network and processing until the current position is activated above some threshold level. BPL, using back-propagation learning, failed to learn, except in a very trivial fashion, that is equivalent to table lookup techniques. HIA, performed much better, and required storage of fewer weights. In drawing a comparison, it is important to note that back propagation techniques depend critically upon the forms of representation used, and can be sensitive to parameters in the simulations; hence the BPL technique may yet yield strong results.

Regular Cycles of Forward and Backward Signal Propagation in Prefrontal Cortex and in Consciousness

PubMed Central

Werbos, Paul J.; Davis, Joshua J. J.

2016-01-01

This paper addresses two fundamental questions: (1) Is it possible to develop mathematical neural network models which can explain and replicate the way in which higher-order capabilities like intelligence, consciousness, optimization, and prediction emerge from the process of learning (Werbos, 1994, 2016a; National Science Foundation, 2008)? and (2) How can we use and test such models in a practical way, to track, to analyze and to model high-frequency (≥ 500 hz) many-channel data from recording the brain, just as econometrics sometimes uses models grounded in the theory of efficient markets to track real-world time-series data (Werbos, 1990)? This paper first reviews some of the prior work addressing question (1), and then reports new work performed in MATLAB analyzing spike-sorted and burst-sorted data on the prefrontal cortex from the Buzsaki lab (Fujisawa et al., 2008, 2015) which is consistent with a regular clock cycle of about 153.4 ms and with regular alternation between a forward pass of network calculations and a backwards pass, as in the general form of the backpropagation algorithm which one of us first developed in the period 1968–1974 (Werbos, 1994, 2006; Anderson and Rosenfeld, 1998). In business and finance, it is well known that adjustments for cycles of the year are essential to accurate prediction of time-series data (Box and Jenkins, 1970); in a similar way, methods for identifying and using regular clock cycles offer large new opportunities in neural time-series analysis. This paper demonstrates a few initial footprints on the large “continent” of this type of neural time-series analysis, and discusses a few of the many further possibilities opened up by this new approach to “decoding” the neural code (Heller et al., 1995). PMID:27965547

Regular Cycles of Forward and Backward Signal Propagation in Prefrontal Cortex and in Consciousness.

PubMed

Werbos, Paul J; Davis, Joshua J J

2016-01-01

This paper addresses two fundamental questions: (1) Is it possible to develop mathematical neural network models which can explain and replicate the way in which higher-order capabilities like intelligence, consciousness, optimization, and prediction emerge from the process of learning (Werbos, 1994, 2016a; National Science Foundation, 2008)? and (2) How can we use and test such models in a practical way, to track, to analyze and to model high-frequency (≥ 500 hz) many-channel data from recording the brain, just as econometrics sometimes uses models grounded in the theory of efficient markets to track real-world time-series data (Werbos, 1990)? This paper first reviews some of the prior work addressing question (1), and then reports new work performed in MATLAB analyzing spike-sorted and burst-sorted data on the prefrontal cortex from the Buzsaki lab (Fujisawa et al., 2008, 2015) which is consistent with a regular clock cycle of about 153.4 ms and with regular alternation between a forward pass of network calculations and a backwards pass, as in the general form of the backpropagation algorithm which one of us first developed in the period 1968-1974 (Werbos, 1994, 2006; Anderson and Rosenfeld, 1998). In business and finance, it is well known that adjustments for cycles of the year are essential to accurate prediction of time-series data (Box and Jenkins, 1970); in a similar way, methods for identifying and using regular clock cycles offer large new opportunities in neural time-series analysis. This paper demonstrates a few initial footprints on the large "continent" of this type of neural time-series analysis, and discusses a few of the many further possibilities opened up by this new approach to "decoding" the neural code (Heller et al., 1995).

Real-time classification of signals from three-component seismic sensors using neural nets

NASA Astrophysics Data System (ADS)

Bowman, B. C.; Dowla, F.

1992-05-01

Adaptive seismic data acquisition systems with capabilities of signal discrimination and event classification are important in treaty monitoring, proliferation, and earthquake early detection systems. Potential applications include monitoring underground chemical explosions, as well as other military, cultural, and natural activities where characteristics of signals change rapidly and without warning. In these applications, the ability to detect and interpret events rapidly without falling behind the influx of the data is critical. We developed a system for real-time data acquisition, analysis, learning, and classification of recorded events employing some of the latest technology in computer hardware, software, and artificial neural networks methods. The system is able to train dynamically, and updates its knowledge based on new data. The software is modular and hardware-independent; i.e., the front-end instrumentation is transparent to the analysis system. The software is designed to take advantage of the multiprocessing environment of the Unix operating system. The Unix System V shared memory and static RAM protocols for data access and the semaphore mechanism for interprocess communications were used. As the three-component sensor detects a seismic signal, it is displayed graphically on a color monitor using X11/Xlib graphics with interactive screening capabilities. For interesting events, the triaxial signal polarization is computed, a fast Fourier Transform (FFT) algorithm is applied, and the normalized power spectrum is transmitted to a backpropagation neural network for event classification. The system is currently capable of handling three data channels with a sampling rate of 500 Hz, which covers the bandwidth of most seismic events. The system has been tested in laboratory setting with artificial events generated in the vicinity of a three-component sensor.

Algorithm Visualization System for Teaching Spatial Data Algorithms

ERIC Educational Resources Information Center

Nikander, Jussi; Helminen, Juha; Korhonen, Ari

2010-01-01

TRAKLA2 is a web-based learning environment for data structures and algorithms. The system delivers automatically assessed algorithm simulation exercises that are solved using a graphical user interface. In this work, we introduce a novel learning environment for spatial data algorithms, SDA-TRAKLA2, which has been implemented on top of the…

Constrained Metric Learning by Permutation Inducing Isometries.

PubMed

Bosveld, Joel; Mahmood, Arif; Huynh, Du Q; Noakes, Lyle

2016-01-01

The choice of metric critically affects the performance of classification and clustering algorithms. Metric learning algorithms attempt to improve performance, by learning a more appropriate metric. Unfortunately, most of the current algorithms learn a distance function which is not invariant to rigid transformations of images. Therefore, the distances between two images and their rigidly transformed pair may differ, leading to inconsistent classification or clustering results. We propose to constrain the learned metric to be invariant to the geometry preserving transformations of images that induce permutations in the feature space. The constraint that these transformations are isometries of the metric ensures consistent results and improves accuracy. Our second contribution is a dimension reduction technique that is consistent with the isometry constraints. Our third contribution is the formulation of the isometry constrained logistic discriminant metric learning (IC-LDML) algorithm, by incorporating the isometry constraints within the objective function of the LDML algorithm. The proposed algorithm is compared with the existing techniques on the publicly available labeled faces in the wild, viewpoint-invariant pedestrian recognition, and Toy Cars data sets. The IC-LDML algorithm has outperformed existing techniques for the tasks of face recognition, person identification, and object classification by a significant margin.

An incremental approach to genetic-algorithms-based classification.

PubMed

Guan, Sheng-Uei; Zhu, Fangming

2005-04-01

Incremental learning has been widely addressed in the machine learning literature to cope with learning tasks where the learning environment is ever changing or training samples become available over time. However, most research work explores incremental learning with statistical algorithms or neural networks, rather than evolutionary algorithms. The work in this paper employs genetic algorithms (GAs) as basic learning algorithms for incremental learning within one or more classifier agents in a multiagent environment. Four new approaches with different initialization schemes are proposed. They keep the old solutions and use an "integration" operation to integrate them with new elements to accommodate new attributes, while biased mutation and crossover operations are adopted to further evolve a reinforced solution. The simulation results on benchmark classification data sets show that the proposed approaches can deal with the arrival of new input attributes and integrate them with the original input space. It is also shown that the proposed approaches can be successfully used for incremental learning and improve classification rates as compared to the retraining GA. Possible applications for continuous incremental training and feature selection are also discussed.

SMARTbot: A Behavioral Analysis Framework Augmented with Machine Learning to Identify Mobile Botnet Applications

PubMed Central

Karim, Ahmad; Salleh, Rosli; Khan, Muhammad Khurram

2016-01-01

Botnet phenomenon in smartphones is evolving with the proliferation in mobile phone technologies after leaving imperative impact on personal computers. It refers to the network of computers, laptops, mobile devices or tablets which is remotely controlled by the cybercriminals to initiate various distributed coordinated attacks including spam emails, ad-click fraud, Bitcoin mining, Distributed Denial of Service (DDoS), disseminating other malwares and much more. Likewise traditional PC based botnet, Mobile botnets have the same operational impact except the target audience is particular to smartphone users. Therefore, it is import to uncover this security issue prior to its widespread adaptation. We propose SMARTbot, a novel dynamic analysis framework augmented with machine learning techniques to automatically detect botnet binaries from malicious corpus. SMARTbot is a component based off-device behavioral analysis framework which can generate mobile botnet learning model by inducing Artificial Neural Networks’ back-propagation method. Moreover, this framework can detect mobile botnet binaries with remarkable accuracy even in case of obfuscated program code. The results conclude that, a classifier model based on simple logistic regression outperform other machine learning classifier for botnet apps’ detection, i.e 99.49% accuracy is achieved. Further, from manual inspection of botnet dataset we have extracted interesting trends in those applications. As an outcome of this research, a mobile botnet dataset is devised which will become the benchmark for future studies. PMID:26978523

A Deep Learning Scheme for Motor Imagery Classification based on Restricted Boltzmann Machines.

PubMed

Lu, Na; Li, Tengfei; Ren, Xiaodong; Miao, Hongyu

2017-06-01

Motor imagery classification is an important topic in brain-computer interface (BCI) research that enables the recognition of a subject's intension to, e.g., implement prosthesis control. The brain dynamics of motor imagery are usually measured by electroencephalography (EEG) as nonstationary time series of low signal-to-noise ratio. Although a variety of methods have been previously developed to learn EEG signal features, the deep learning idea has rarely been explored to generate new representation of EEG features and achieve further performance improvement for motor imagery classification. In this study, a novel deep learning scheme based on restricted Boltzmann machine (RBM) is proposed. Specifically, frequency domain representations of EEG signals obtained via fast Fourier transform (FFT) and wavelet package decomposition (WPD) are obtained to train three RBMs. These RBMs are then stacked up with an extra output layer to form a four-layer neural network, which is named the frequential deep belief network (FDBN). The output layer employs the softmax regression to accomplish the classification task. Also, the conjugate gradient method and backpropagation are used to fine tune the FDBN. Extensive and systematic experiments have been performed on public benchmark datasets, and the results show that the performance improvement of FDBN over other selected state-of-the-art methods is statistically significant. Also, several findings that may be of significant interest to the BCI community are presented in this article.

SMARTbot: A Behavioral Analysis Framework Augmented with Machine Learning to Identify Mobile Botnet Applications.

PubMed

Karim, Ahmad; Salleh, Rosli; Khan, Muhammad Khurram

2016-01-01

Botnet phenomenon in smartphones is evolving with the proliferation in mobile phone technologies after leaving imperative impact on personal computers. It refers to the network of computers, laptops, mobile devices or tablets which is remotely controlled by the cybercriminals to initiate various distributed coordinated attacks including spam emails, ad-click fraud, Bitcoin mining, Distributed Denial of Service (DDoS), disseminating other malwares and much more. Likewise traditional PC based botnet, Mobile botnets have the same operational impact except the target audience is particular to smartphone users. Therefore, it is import to uncover this security issue prior to its widespread adaptation. We propose SMARTbot, a novel dynamic analysis framework augmented with machine learning techniques to automatically detect botnet binaries from malicious corpus. SMARTbot is a component based off-device behavioral analysis framework which can generate mobile botnet learning model by inducing Artificial Neural Networks' back-propagation method. Moreover, this framework can detect mobile botnet binaries with remarkable accuracy even in case of obfuscated program code. The results conclude that, a classifier model based on simple logistic regression outperform other machine learning classifier for botnet apps' detection, i.e 99.49% accuracy is achieved. Further, from manual inspection of botnet dataset we have extracted interesting trends in those applications. As an outcome of this research, a mobile botnet dataset is devised which will become the benchmark for future studies.

Data-driven advice for applying machine learning to bioinformatics problems

PubMed Central

Olson, Randal S.; La Cava, William; Mustahsan, Zairah; Varik, Akshay; Moore, Jason H.

2017-01-01

As the bioinformatics field grows, it must keep pace not only with new data but with new algorithms. Here we contribute a thorough analysis of 13 state-of-the-art, commonly used machine learning algorithms on a set of 165 publicly available classification problems in order to provide data-driven algorithm recommendations to current researchers. We present a number of statistical and visual comparisons of algorithm performance and quantify the effect of model selection and algorithm tuning for each algorithm and dataset. The analysis culminates in the recommendation of five algorithms with hyperparameters that maximize classifier performance across the tested problems, as well as general guidelines for applying machine learning to supervised classification problems. PMID:29218881

Designing the Architecture of Hierachical Neural Networks Model Attention, Learning and Goal-Oriented Behavior

DTIC Science & Technology

1993-12-31

19,23,25,26,27,28,32,33,35,41]) - A new cost function is postulated and an algorithm that employs this cost function is proposed for the learning of...updates the controller parameters from time to time [53]. The learning control algorithm consist of updating the parameter estimates as used in the...proposed cost function with the other learning type algorithms , such as based upon learning of iterative tasks [Kawamura-85], variable structure

Behavioral Profiling of Scada Network Traffic Using Machine Learning Algorithms

DTIC Science & Technology

2014-03-27

BEHAVIORAL PROFILING OF SCADA NETWORK TRAFFIC USING MACHINE LEARNING ALGORITHMS THESIS Jessica R. Werling, Captain, USAF AFIT-ENG-14-M-81 DEPARTMENT...subject to copyright protection in the United States. AFIT-ENG-14-M-81 BEHAVIORAL PROFILING OF SCADA NETWORK TRAFFIC USING MACHINE LEARNING ...AFIT-ENG-14-M-81 BEHAVIORAL PROFILING OF SCADA NETWORK TRAFFIC USING MACHINE LEARNING ALGORITHMS Jessica R. Werling, B.S.C.S. Captain, USAF Approved

FDI and Accommodation Using NN Based Techniques

NASA Astrophysics Data System (ADS)

Garcia, Ramon Ferreiro; de Miguel Catoira, Alberto; Sanz, Beatriz Ferreiro

Massive application of dynamic backpropagation neural networks is used on closed loop control FDI (fault detection and isolation) tasks. The process dynamics is mapped by means of a trained backpropagation NN to be applied on residual generation. Process supervision is then applied to discriminate faults on process sensors, and process plant parameters. A rule based expert system is used to implement the decision making task and the corresponding solution in terms of faults accommodation and/or reconfiguration. Results show an efficient and robust FDI system which could be used as the core of an SCADA or alternatively as a complement supervision tool operating in parallel with the SCADA when applied on a heat exchanger.

Median Filter Noise Reduction of Image and Backpropagation Neural Network Model for Cervical Cancer Classification

NASA Astrophysics Data System (ADS)

Wutsqa, D. U.; Marwah, M.

2017-06-01

In this paper, we consider spatial operation median filter to reduce the noise in the cervical images yielded by colposcopy tool. The backpropagation neural network (BPNN) model is applied to the colposcopy images to classify cervical cancer. The classification process requires an image extraction by using a gray level co-occurrence matrix (GLCM) method to obtain image features that are used as inputs of BPNN model. The advantage of noise reduction is evaluated by comparing the performances of BPNN models with and without spatial operation median filter. The experimental result shows that the spatial operation median filter can improve the accuracy of the BPNN model for cervical cancer classification.

Water Level Prediction of Lake Cascade Mahakam Using Adaptive Neural Network Backpropagation (ANNBP)

NASA Astrophysics Data System (ADS)

Mislan; Gaffar, A. F. O.; Haviluddin; Puspitasari, N.

2018-04-01

A natural hazard information and flood events are indispensable as a form of prevention and improvement. One of the causes is flooding in the areas around the lake. Therefore, forecasting the surface of Lake water level to anticipate flooding is required. The purpose of this paper is implemented computational intelligence method namely Adaptive Neural Network Backpropagation (ANNBP) to forecasting the Lake Cascade Mahakam. Based on experiment, performance of ANNBP indicated that Lake water level prediction have been accurate by using mean square error (MSE) and mean absolute percentage error (MAPE). In other words, computational intelligence method can produce good accuracy. A hybrid and optimization of computational intelligence are focus in the future work.

Modulation format dependence of digital nonlinearity compensation performance in optical fibre communication systems.

PubMed

Xu, Tianhua; Shevchenko, Nikita A; Lavery, Domaniç; Semrau, Daniel; Liga, Gabriele; Alvarado, Alex; Killey, Robert I; Bayvel, Polina

2017-02-20

The relationship between modulation format and the performance of multi-channel digital back-propagation (MC-DBP) in ideal Nyquist-spaced optical communication systems is investigated. It is found that the nonlinear distortions behave independent of modulation format in the case of full-field DBP, in contrast to the cases of electronic dispersion compensation and partial-bandwidth DBP. It is shown that the minimum number of steps per span required for MC-DBP depends on the chosen modulation format. For any given target information rate, there exists a possible trade-off between modulation format and back-propagated bandwidth, which could be used to reduce the computational complexity requirement of MC-DBP.

Super-resolution reconstruction of MR image with a novel residual learning network algorithm

NASA Astrophysics Data System (ADS)

Shi, Jun; Liu, Qingping; Wang, Chaofeng; Zhang, Qi; Ying, Shihui; Xu, Haoyu

2018-04-01

Spatial resolution is one of the key parameters of magnetic resonance imaging (MRI). The image super-resolution (SR) technique offers an alternative approach to improve the spatial resolution of MRI due to its simplicity. Convolutional neural networks (CNN)-based SR algorithms have achieved state-of-the-art performance, in which the global residual learning (GRL) strategy is now commonly used due to its effectiveness for learning image details for SR. However, the partial loss of image details usually happens in a very deep network due to the degradation problem. In this work, we propose a novel residual learning-based SR algorithm for MRI, which combines both multi-scale GRL and shallow network block-based local residual learning (LRL). The proposed LRL module works effectively in capturing high-frequency details by learning local residuals. One simulated MRI dataset and two real MRI datasets have been used to evaluate our algorithm. The experimental results show that the proposed SR algorithm achieves superior performance to all of the other compared CNN-based SR algorithms in this work.

Hardware Acceleration of Adaptive Neural Algorithms.

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

James, Conrad D.

As tradit ional numerical computing has faced challenges, researchers have turned towards alternative computing approaches to reduce power - per - computation metrics and improve algorithm performance. Here, we describe an approach towards non - conventional computing that strengthens the connection between machine learning and neuroscience concepts. The Hardware Acceleration of Adaptive Neural Algorithms (HAANA) project ha s develop ed neural machine learning algorithms and hardware for applications in image processing and cybersecurity. While machine learning methods are effective at extracting relevant features from many types of data, the effectiveness of these algorithms degrades when subjected to real - worldmore » conditions. Our team has generated novel neural - inspired approa ches to improve the resiliency and adaptability of machine learning algorithms. In addition, we have also designed and fabricated hardware architectures and microelectronic devices specifically tuned towards the training and inference operations of neural - inspired algorithms. Finally, our multi - scale simulation framework allows us to assess the impact of microelectronic device properties on algorithm performance.« less

NASA Tech Briefs, May 2003

NASA Technical Reports Server (NTRS)

2003-01-01

Topics covered include: Using Diffusion Bonding in Making Piezoelectric Actuators; Wireless Temperature-Monitoring System; Analog Binaural Circuits for Detecting and Locating Leaks; Mirrors Containing Biomimetic Shape-Control Actuators; Surface-Micromachined Planar Arrays of Thermopiles; Cascade Back-Propagation Learning in Neural Networks; Perovskite Superlattices as Tunable Microwave Devices; Rollable Thin-Shell Nanolaminate Mirrors; Flight Tests of a Ministick Controller in an F/A-18 Airplane; Piezoelectrically Actuated Shutter for High Vacuum; Bio-Inspired Engineering of Exploration Systems; Microscope Cells Containing Multiple Micromachined Wells; Electrophoretic Deposition for Fabricating Microbatteries; Integrated Arrays of Ion-Sensitive Electrodes; Model of Fluidized Bed Containing Reacting Solids and Gases; Membrane Mirrors With Bimorph Shape Actuators; Using Fractional Clock-Period Delays in Telemetry Arraying; Developing Generic Software for Spacecraft Avionics; Numerical Study of Pyrolysis of Biomass in Fluidized Beds; and Assessment of Models of Chemically Reacting Granular Flows.

Optimization of Artificial Neural Network using Evolutionary Programming for Prediction of Cascading Collapse Occurrence due to the Hidden Failure Effect

NASA Astrophysics Data System (ADS)

Idris, N. H.; Salim, N. A.; Othman, M. M.; Yasin, Z. M.

2018-03-01

This paper presents the Evolutionary Programming (EP) which proposed to optimize the training parameters for Artificial Neural Network (ANN) in predicting cascading collapse occurrence due to the effect of protection system hidden failure. The data has been collected from the probability of hidden failure model simulation from the historical data. The training parameters of multilayer-feedforward with backpropagation has been optimized with objective function to minimize the Mean Square Error (MSE). The optimal training parameters consists of the momentum rate, learning rate and number of neurons in first hidden layer and second hidden layer is selected in EP-ANN. The IEEE 14 bus system has been tested as a case study to validate the propose technique. The results show the reliable prediction of performance validated through MSE and Correlation Coefficient (R).

Using human brain activity to guide machine learning.

PubMed

Fong, Ruth C; Scheirer, Walter J; Cox, David D

2018-03-29

Machine learning is a field of computer science that builds algorithms that learn. In many cases, machine learning algorithms are used to recreate a human ability like adding a caption to a photo, driving a car, or playing a game. While the human brain has long served as a source of inspiration for machine learning, little effort has been made to directly use data collected from working brains as a guide for machine learning algorithms. Here we demonstrate a new paradigm of "neurally-weighted" machine learning, which takes fMRI measurements of human brain activity from subjects viewing images, and infuses these data into the training process of an object recognition learning algorithm to make it more consistent with the human brain. After training, these neurally-weighted classifiers are able to classify images without requiring any additional neural data. We show that our neural-weighting approach can lead to large performance gains when used with traditional machine vision features, as well as to significant improvements with already high-performing convolutional neural network features. The effectiveness of this approach points to a path forward for a new class of hybrid machine learning algorithms which take both inspiration and direct constraints from neuronal data.

Javascript Library for Developing Interactive Micro-Level Animations for Teaching and Learning Algorithms on One-Dimensional Arrays

ERIC Educational Resources Information Center

Végh, Ladislav

2016-01-01

The first data structure that first-year undergraduate students learn during the programming and algorithms courses is the one-dimensional array. For novice programmers, it might be hard to understand different algorithms on arrays (e.g. searching, mirroring, sorting algorithms), because the algorithms dynamically change the values of elements. In…

Inductive learning of thyroid functional states using the ID3 algorithm. The effect of poor examples on the learning result.

PubMed

Forsström, J

1992-01-01

The ID3 algorithm for inductive learning was tested using preclassified material for patients suspected to have a thyroid illness. Classification followed a rule-based expert system for the diagnosis of thyroid function. Thus, the knowledge to be learned was limited to the rules existing in the knowledge base of that expert system. The learning capability of the ID3 algorithm was tested with an unselected learning material (with some inherent missing data) and with a selected learning material (no missing data). The selected learning material was a subgroup which formed a part of the unselected learning material. When the number of learning cases was increased, the accuracy of the program improved. When the learning material was large enough, an increase in the learning material did not improve the results further. A better learning result was achieved with the selected learning material not including missing data as compared to unselected learning material. With this material we demonstrate a weakness in the ID3 algorithm: it can not find available information from good example cases if we add poor examples to the data.

Learning Cue Phrase Patterns from Radiology Reports Using a Genetic Algorithm

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

Patton, Robert M; Beckerman, Barbara G; Potok, Thomas E

2009-01-01

Various computer-assisted technologies have been developed to assist radiologists in detecting cancer; however, the algorithms still lack high degrees of sensitivity and specificity, and must undergo machine learning against a training set with known pathologies in order to further refine the algorithms with higher validity of truth. This work describes an approach to learning cue phrase patterns in radiology reports that utilizes a genetic algorithm (GA) as the learning method. The approach described here successfully learned cue phrase patterns for two distinct classes of radiology reports. These patterns can then be used as a basis for automatically categorizing, clustering, ormore » retrieving relevant data for the user.« less

Optimizing the learning rate for adaptive estimation of neural encoding models

PubMed Central

2018-01-01

Closed-loop neurotechnologies often need to adaptively learn an encoding model that relates the neural activity to the brain state, and is used for brain state decoding. The speed and accuracy of adaptive learning algorithms are critically affected by the learning rate, which dictates how fast model parameters are updated based on new observations. Despite the importance of the learning rate, currently an analytical approach for its selection is largely lacking and existing signal processing methods vastly tune it empirically or heuristically. Here, we develop a novel analytical calibration algorithm for optimal selection of the learning rate in adaptive Bayesian filters. We formulate the problem through a fundamental trade-off that learning rate introduces between the steady-state error and the convergence time of the estimated model parameters. We derive explicit functions that predict the effect of learning rate on error and convergence time. Using these functions, our calibration algorithm can keep the steady-state parameter error covariance smaller than a desired upper-bound while minimizing the convergence time, or keep the convergence time faster than a desired value while minimizing the error. We derive the algorithm both for discrete-valued spikes modeled as point processes nonlinearly dependent on the brain state, and for continuous-valued neural recordings modeled as Gaussian processes linearly dependent on the brain state. Using extensive closed-loop simulations, we show that the analytical solution of the calibration algorithm accurately predicts the effect of learning rate on parameter error and convergence time. Moreover, the calibration algorithm allows for fast and accurate learning of the encoding model and for fast convergence of decoding to accurate performance. Finally, larger learning rates result in inaccurate encoding models and decoders, and smaller learning rates delay their convergence. The calibration algorithm provides a novel analytical approach to predictably achieve a desired level of error and convergence time in adaptive learning, with application to closed-loop neurotechnologies and other signal processing domains. PMID:29813069

Optimizing the learning rate for adaptive estimation of neural encoding models.

PubMed

Hsieh, Han-Lin; Shanechi, Maryam M

2018-05-01

Closed-loop neurotechnologies often need to adaptively learn an encoding model that relates the neural activity to the brain state, and is used for brain state decoding. The speed and accuracy of adaptive learning algorithms are critically affected by the learning rate, which dictates how fast model parameters are updated based on new observations. Despite the importance of the learning rate, currently an analytical approach for its selection is largely lacking and existing signal processing methods vastly tune it empirically or heuristically. Here, we develop a novel analytical calibration algorithm for optimal selection of the learning rate in adaptive Bayesian filters. We formulate the problem through a fundamental trade-off that learning rate introduces between the steady-state error and the convergence time of the estimated model parameters. We derive explicit functions that predict the effect of learning rate on error and convergence time. Using these functions, our calibration algorithm can keep the steady-state parameter error covariance smaller than a desired upper-bound while minimizing the convergence time, or keep the convergence time faster than a desired value while minimizing the error. We derive the algorithm both for discrete-valued spikes modeled as point processes nonlinearly dependent on the brain state, and for continuous-valued neural recordings modeled as Gaussian processes linearly dependent on the brain state. Using extensive closed-loop simulations, we show that the analytical solution of the calibration algorithm accurately predicts the effect of learning rate on parameter error and convergence time. Moreover, the calibration algorithm allows for fast and accurate learning of the encoding model and for fast convergence of decoding to accurate performance. Finally, larger learning rates result in inaccurate encoding models and decoders, and smaller learning rates delay their convergence. The calibration algorithm provides a novel analytical approach to predictably achieve a desired level of error and convergence time in adaptive learning, with application to closed-loop neurotechnologies and other signal processing domains.

Parsing recursive sentences with a connectionist model including a neural stack and synaptic gating.

PubMed

Fedor, Anna; Ittzés, Péter; Szathmáry, Eörs

2011-02-21

It is supposed that humans are genetically predisposed to be able to recognize sequences of context-free grammars with centre-embedded recursion while other primates are restricted to the recognition of finite state grammars with tail-recursion. Our aim was to construct a minimalist neural network that is able to parse artificial sentences of both grammars in an efficient way without using the biologically unrealistic backpropagation algorithm. The core of this network is a neural stack-like memory where the push and pop operations are regulated by synaptic gating on the connections between the layers of the stack. The network correctly categorizes novel sentences of both grammars after training. We suggest that the introduction of the neural stack memory will turn out to be substantial for any biological 'hierarchical processor' and the minimalist design of the model suggests a quest for similar, realistic neural architectures. Copyright © 2010 Elsevier Ltd. All rights reserved.

Embedded intelligent adaptive PI controller for an electromechanical system.

PubMed

El-Nagar, Ahmad M

2016-09-01

In this study, an intelligent adaptive controller approach using the interval type-2 fuzzy neural network (IT2FNN) is presented. The proposed controller consists of a lower level proportional - integral (PI) controller, which is the main controller and an upper level IT2FNN which tuning on-line the parameters of a PI controller. The proposed adaptive PI controller based on IT2FNN (API-IT2FNN) is implemented practically using the Arduino DUE kit for controlling the speed of a nonlinear DC motor-generator system. The parameters of the IT2FNN are tuned on-line using back-propagation algorithm. The Lyapunov theorem is used to derive the stability and convergence of the IT2FNN. The obtained experimental results, which are compared with other controllers, demonstrate that the proposed API-IT2FNN is able to improve the system response over a wide range of system uncertainties. Copyright © 2016 ISA. Published by Elsevier Ltd. All rights reserved.

Classification of E-Nose Aroma Data of Four Fruit Types by ABC-Based Neural Network

PubMed Central

Adak, M. Fatih; Yumusak, Nejat

2016-01-01

Electronic nose technology is used in many areas, and frequently in the beverage industry for classification and quality-control purposes. In this study, four different aroma data (strawberry, lemon, cherry, and melon) were obtained using a MOSES II electronic nose for the purpose of fruit classification. To improve the performance of the classification, the training phase of the neural network with two hidden layers was optimized using artificial bee colony algorithm (ABC), which is known to be successful in exploration. Test data were given to two different neural networks, each of which were trained separately with backpropagation (BP) and ABC, and average test performances were measured as 60% for the artificial neural network trained with BP and 76.39% for the artificial neural network trained with ABC. Training and test phases were repeated 30 times to obtain these average performance measurements. This level of performance shows that the artificial neural network trained with ABC is successful in classifying aroma data. PMID:26927124

Utilizing gamma band to improve mental task based brain-computer interface design.

PubMed

Palaniappan, Ramaswamy

2006-09-01

A common method for designing brain-computer Interface (BCI) is to use electroencephalogram (EEG) signals extracted during mental tasks. In these BCI designs, features from EEG such as power and asymmetry ratios from delta, theta, alpha, and beta bands have been used in classifying different mental tasks. In this paper, the performance of the mental task based BCI design is improved by using spectral power and asymmetry ratios from gamma (24-37 Hz) band in addition to the lower frequency bands. In the experimental study, EEG signals extracted during five mental tasks from four subjects were used. Elman neural network (ENN) trained by the resilient backpropagation algorithm was used to classify the power and asymmetry ratios from EEG into different combinations of two mental tasks. The results indicated that ((1) the classification performance and training time of the BCI design were improved through the use of additional gamma band features; (2) classification performances were nearly invariant to the number of ENN hidden units or feature extraction method.

Automatic recognition of ship types from infrared images using superstructure moment invariants

NASA Astrophysics Data System (ADS)

Li, Heng; Wang, Xinyu

2007-11-01

Automatic object recognition is an active area of interest for military and commercial applications. In this paper, a system addressing autonomous recognition of ship types in infrared images is proposed. Firstly, an approach of segmentation based on detection of salient features of the target with subsequent shadow removing is proposed, as is the base of the subsequent object recognition. Considering the differences between the shapes of various ships mainly lie in their superstructures, we then use superstructure moment functions invariant to translation, rotation and scale differences in input patterns and develop a robust algorithm of obtaining ship superstructure. Subsequently a back-propagation neural network is used as a classifier in the recognition stage and projection images of simulated three-dimensional ship models are used as the training sets. Our recognition model was implemented and experimentally validated using both simulated three-dimensional ship model images and real images derived from video of an AN/AAS-44V Forward Looking Infrared(FLIR) sensor.

Creation and testing of an artificial neural network based carbonate detector for Mars rovers

NASA Technical Reports Server (NTRS)

Bornstein, Benjamin; Castano, Rebecca; Gilmore, Martha S.; Merrill, Matthew; Greenwood, James P.

2005-01-01

We have developed an artificial neural network (ANN) based carbonate detector capable of running on current and future rover hardware. The detector can identify calcite in visible/NIR (350-2500 nm) spectra of both laboratory specimens covered by ferric dust and rocks in Mars analogue field environments. The ANN was trained using the Backpropagation algorithm with sigmoid activation neurons. For the training dataset, we chose nine carbonate and eight non-carbonate representative mineral spectra from the USGS spectral library. Using these spectra as seeds, we generated 10,000 variants with up to 2% Gaussian noise in each reflectance measurement. We cross-validated several ANN architectures, training on 9,900 spectra and testing on the remaining 100. The best performing ANN correctly detected, with perfect accuracy, the presence (or absence) of carbonate in spectral data taken on field samples from the Mojave desert and clean, pure marbles from CT. Sensitivity experiments with JSC Mars-1 simulant dust suggest the carbonate detector would perform well in aeolian Martian environments.

An optimization method for defects reduction in fiber laser keyhole welding

NASA Astrophysics Data System (ADS)

Ai, Yuewei; Jiang, Ping; Shao, Xinyu; Wang, Chunming; Li, Peigen; Mi, Gaoyang; Liu, Yang; Liu, Wei

2016-01-01

Laser welding has been widely used in automotive, power, chemical, nuclear and aerospace industries. The quality of welded joints is closely related to the existing defects which are primarily determined by the welding process parameters. This paper proposes a defects optimization method that takes the formation mechanism of welding defects and weld geometric features into consideration. The analysis of welding defects formation mechanism aims to investigate the relationship between welding defects and process parameters, and weld features are considered to identify the optimal process parameters for the desired welded joints with minimum defects. The improved back-propagation neural network possessing good modeling for nonlinear problems is adopted to establish the mathematical model and the obtained model is solved by genetic algorithm. The proposed method is validated by macroweld profile, microstructure and microhardness in the confirmation tests. The results show that the proposed method is effective at reducing welding defects and obtaining high-quality joints for fiber laser keyhole welding in practical production.

Artificial neural network modelling of a large-scale wastewater treatment plant operation.

PubMed

Güçlü, Dünyamin; Dursun, Sükrü

2010-11-01

Artificial Neural Networks (ANNs), a method of artificial intelligence method, provide effective predictive models for complex processes. Three independent ANN models trained with back-propagation algorithm were developed to predict effluent chemical oxygen demand (COD), suspended solids (SS) and aeration tank mixed liquor suspended solids (MLSS) concentrations of the Ankara central wastewater treatment plant. The appropriate architecture of ANN models was determined through several steps of training and testing of the models. ANN models yielded satisfactory predictions. Results of the root mean square error, mean absolute error and mean absolute percentage error were 3.23, 2.41 mg/L and 5.03% for COD; 1.59, 1.21 mg/L and 17.10% for SS; 52.51, 44.91 mg/L and 3.77% for MLSS, respectively, indicating that the developed model could be efficiently used. The results overall also confirm that ANN modelling approach may have a great implementation potential for simulation, precise performance prediction and process control of wastewater treatment plants.

Optimized pulsed write schemes improve linearity and write speed for low-power organic neuromorphic devices

NASA Astrophysics Data System (ADS)

Keene, Scott T.; Melianas, Armantas; Fuller, Elliot J.; van de Burgt, Yoeri; Talin, A. Alec; Salleo, Alberto

2018-06-01

Neuromorphic devices are becoming increasingly appealing as efficient emulators of neural networks used to model real world problems. However, no hardware to date has demonstrated the necessary high accuracy and energy efficiency gain over CMOS in both (1) training via backpropagation and (2) in read via vector matrix multiplication. Such shortcomings are due to device non-idealities, particularly asymmetric conductance tuning in response to uniform voltage pulse inputs. Here, by formulating a general circuit model for capacitive ion-exchange neuromorphic devices, we show that asymmetric nonlinearity in organic electrochemical neuromorphic devices (ENODes) can be suppressed by an appropriately chosen write scheme. Simulations based upon our model suggest that a nonlinear write-selector could reduce the switching voltage and energy, enabling analog tuning via a continuous set of resistance states (100 states) with extremely low switching energy (~170 fJ · µm‑2). This work clarifies the pathway to neural algorithm accelerators capable of parallelism during both read and write operations.

Classification of E-Nose Aroma Data of Four Fruit Types by ABC-Based Neural Network.

PubMed

Adak, M Fatih; Yumusak, Nejat

2016-02-27

Electronic nose technology is used in many areas, and frequently in the beverage industry for classification and quality-control purposes. In this study, four different aroma data (strawberry, lemon, cherry, and melon) were obtained using a MOSES II electronic nose for the purpose of fruit classification. To improve the performance of the classification, the training phase of the neural network with two hidden layers was optimized using artificial bee colony algorithm (ABC), which is known to be successful in exploration. Test data were given to two different neural networks, each of which were trained separately with backpropagation (BP) and ABC, and average test performances were measured as 60% for the artificial neural network trained with BP and 76.39% for the artificial neural network trained with ABC. Training and test phases were repeated 30 times to obtain these average performance measurements. This level of performance shows that the artificial neural network trained with ABC is successful in classifying aroma data.

Markov chain-incorporated and synthetic data-supported conditional artificial neural network models for forecasting monthly precipitation in arid regions

NASA Astrophysics Data System (ADS)

Aksoy, Hafzullah; Dahamsheh, Ahmad

2018-07-01

For forecasting monthly precipitation in an arid region, the feed forward back-propagation, radial basis function and generalized regression artificial neural networks (ANNs) are used in this study. The ANN models are improved after incorporation of a Markov chain-based algorithm (MC-ANNs) with which the percentage of dry months is forecasted perfectly, thus generation of any non-physical negative precipitation is eliminated. Due to the fact that recorded precipitation time series are usually shorter than the length needed for a proper calibration of ANN models, synthetic monthly precipitation data are generated by Thomas-Fiering model to further improve the performance of forecasting. For case studies from Jordan, it is seen that only a slightly better performance is achieved with the use of MC and synthetic data. A conditional statement is, therefore, established and imbedded into the ANN models after the incorporation of MC and support of synthetic data, to substantially improve the ability of the models for forecasting monthly precipitation in arid regions.

Scheduling the blended solution as industrial CO2 absorber in separation process by back-propagation artificial neural networks.

PubMed

Abdollahi, Yadollah; Sairi, Nor Asrina; Said, Suhana Binti Mohd; Abouzari-lotf, Ebrahim; Zakaria, Azmi; Sabri, Mohd Faizul Bin Mohd; Islam, Aminul; Alias, Yatimah

2015-11-05

It is believe that 80% industrial of carbon dioxide can be controlled by separation and storage technologies which use the blended ionic liquids absorber. Among the blended absorbers, the mixture of water, N-methyldiethanolamine (MDEA) and guanidinium trifluoromethane sulfonate (gua) has presented the superior stripping qualities. However, the blended solution has illustrated high viscosity that affects the cost of separation process. In this work, the blended fabrication was scheduled with is the process arranging, controlling and optimizing. Therefore, the blend's components and operating temperature were modeled and optimized as input effective variables to minimize its viscosity as the final output by using back-propagation artificial neural network (ANN). The modeling was carried out by four mathematical algorithms with individual experimental design to obtain the optimum topology using root mean squared error (RMSE), R-squared (R(2)) and absolute average deviation (AAD). As a result, the final model (QP-4-8-1) with minimum RMSE and AAD as well as the highest R(2) was selected to navigate the fabrication of the blended solution. Therefore, the model was applied to obtain the optimum initial level of the input variables which were included temperature 303-323 K, x[gua], 0-0.033, x[MDAE], 0.3-0.4, and x[H2O], 0.7-1.0. Moreover, the model has obtained the relative importance ordered of the variables which included x[gua]>temperature>x[MDEA]>x[H2O]. Therefore, none of the variables was negligible in the fabrication. Furthermore, the model predicted the optimum points of the variables to minimize the viscosity which was validated by further experiments. The validated results confirmed the model schedulability. Accordingly, ANN succeeds to model the initial components of the blended solutions as absorber of CO2 capture in separation technologies that is able to industries scale up. Copyright © 2015 Elsevier B.V. All rights reserved.

Trans-algorithmic nature of learning in biological systems.

PubMed

Shimansky, Yury P

2018-05-02

Learning ability is a vitally important, distinctive property of biological systems, which provides dynamic stability in non-stationary environments. Although several different types of learning have been successfully modeled using a universal computer, in general, learning cannot be described by an algorithm. In other words, algorithmic approach to describing the functioning of biological systems is not sufficient for adequate grasping of what is life. Since biosystems are parts of the physical world, one might hope that adding some physical mechanisms and principles to the concept of algorithm could provide extra possibilities for describing learning in its full generality. However, a straightforward approach to that through the so-called physical hypercomputation so far has not been successful. Here an alternative approach is proposed. Biosystems are described as achieving enumeration of possible physical compositions though random incremental modifications inflicted on them by active operating resources (AORs) in the environment. Biosystems learn through algorithmic regulation of the intensity of the above modifications according to a specific optimality criterion. From the perspective of external observers, biosystems move in the space of different algorithms driven by random modifications imposed by the environmental AORs. A particular algorithm is only a snapshot of that motion, while the motion itself is essentially trans-algorithmic. In this conceptual framework, death of unfit members of a population, for example, is viewed as a trans-algorithmic modification made in the population as a biosystem by environmental AORs. Numerous examples of AOR utilization in biosystems of different complexity, from viruses to multicellular organisms, are provided.

A study of metaheuristic algorithms for high dimensional feature selection on microarray data

NASA Astrophysics Data System (ADS)

Dankolo, Muhammad Nasiru; Radzi, Nor Haizan Mohamed; Sallehuddin, Roselina; Mustaffa, Noorfa Haszlinna

2017-11-01

Microarray systems enable experts to examine gene profile at molecular level using machine learning algorithms. It increases the potentials of classification and diagnosis of many diseases at gene expression level. Though, numerous difficulties may affect the efficiency of machine learning algorithms which includes vast number of genes features comprised in the original data. Many of these features may be unrelated to the intended analysis. Therefore, feature selection is necessary to be performed in the data pre-processing. Many feature selection algorithms are developed and applied on microarray which including the metaheuristic optimization algorithms. This paper discusses the application of the metaheuristics algorithms for feature selection in microarray dataset. This study reveals that, the algorithms have yield an interesting result with limited resources thereby saving computational expenses of machine learning algorithms.

Comparison between extreme learning machine and wavelet neural networks in data classification

NASA Astrophysics Data System (ADS)

Yahia, Siwar; Said, Salwa; Jemai, Olfa; Zaied, Mourad; Ben Amar, Chokri

2017-03-01

Extreme learning Machine is a well known learning algorithm in the field of machine learning. It's about a feed forward neural network with a single-hidden layer. It is an extremely fast learning algorithm with good generalization performance. In this paper, we aim to compare the Extreme learning Machine with wavelet neural networks, which is a very used algorithm. We have used six benchmark data sets to evaluate each technique. These datasets Including Wisconsin Breast Cancer, Glass Identification, Ionosphere, Pima Indians Diabetes, Wine Recognition and Iris Plant. Experimental results have shown that both extreme learning machine and wavelet neural networks have reached good results.

Neural network modeling of a dolphin's sonar discrimination capabilities.

PubMed

Au, W W; Andersen, L N; Rasmussen, A R; Roitblat, H L; Nachtigall, P E

1995-07-01

The capability of an echolocating dolphin to discriminate differences in the wall thickness of cylinders was previously modeled by a counterpropagation neural network using only spectral information from the echoes. In this study, both time and frequency information were used to model the dolphin discrimination capabilities. Echoes from the same cylinders were digitized using a broadband simulated dolphin sonar signal with the transducer mounted on the dolphin's pen. The echoes were filtered by a bank of continuous constant-Q digital filters and the energy from each filter was computed in time increments of 1/bandwidth. Echo features of the standard and each comparison target were analyzed in pairs by a counterpropagation neural network, a backpropagation neural network, and a model using Euclidean distance measures. The backpropagation network performed better than both the counterpropagation network, and the Euclidean model, using either spectral-only features or combined temporal and spectral features. All models performed better using features containing both temporal and spectral information. The backpropagation network was able to perform better than the dolphins for noise-free echoes with Q values as low as 2 and 3. For a Q of 2, only temporal information was available. However, with noisy data, the network required a Q of 8 in order to perform as well as the dolphin.

Optimizing the Learning Order of Chinese Characters Using a Novel Topological Sort Algorithm

PubMed Central

Wang, Jinzhao

2016-01-01

We present a novel algorithm for optimizing the order in which Chinese characters are learned, one that incorporates the benefits of learning them in order of usage frequency and in order of their hierarchal structural relationships. We show that our work outperforms previously published orders and algorithms. Our algorithm is applicable to any scheduling task where nodes have intrinsic differences in importance and must be visited in topological order. PMID:27706234

Creating Engaging Online Learning Material with the JSAV JavaScript Algorithm Visualization Library

ERIC Educational Resources Information Center

Karavirta, Ville; Shaffer, Clifford A.

2016-01-01

Data Structures and Algorithms are a central part of Computer Science. Due to their abstract and dynamic nature, they are a difficult topic to learn for many students. To alleviate these learning difficulties, instructors have turned to algorithm visualizations (AV) and AV systems. Research has shown that especially engaging AVs can have an impact…

Research on intelligent algorithm of electro - hydraulic servo control system

NASA Astrophysics Data System (ADS)

Wang, Yannian; Zhao, Yuhui; Liu, Chengtao

2017-09-01

In order to adapt the nonlinear characteristics of the electro-hydraulic servo control system and the influence of complex interference in the industrial field, using a fuzzy PID switching learning algorithm is proposed and a fuzzy PID switching learning controller is designed and applied in the electro-hydraulic servo controller. The designed controller not only combines the advantages of the fuzzy control and PID control, but also introduces the learning algorithm into the switching function, which makes the learning of the three parameters in the switching function can avoid the instability of the system during the switching between the fuzzy control and PID control algorithms. It also makes the switch between these two control algorithm more smoother than that of the conventional fuzzy PID.

Decision tree and ensemble learning algorithms with their applications in bioinformatics.

PubMed

Che, Dongsheng; Liu, Qi; Rasheed, Khaled; Tao, Xiuping

2011-01-01

Machine learning approaches have wide applications in bioinformatics, and decision tree is one of the successful approaches applied in this field. In this chapter, we briefly review decision tree and related ensemble algorithms and show the successful applications of such approaches on solving biological problems. We hope that by learning the algorithms of decision trees and ensemble classifiers, biologists can get the basic ideas of how machine learning algorithms work. On the other hand, by being exposed to the applications of decision trees and ensemble algorithms in bioinformatics, computer scientists can get better ideas of which bioinformatics topics they may work on in their future research directions. We aim to provide a platform to bridge the gap between biologists and computer scientists.

Recovering Long-wavelength Velocity Models using Spectrogram Inversion with Single- and Multi-frequency Components

NASA Astrophysics Data System (ADS)

Ha, J.; Chung, W.; Shin, S.

2015-12-01

Many waveform inversion algorithms have been proposed in order to construct subsurface velocity structures from seismic data sets. These algorithms have suffered from computational burden, local minima problems, and the lack of low-frequency components. Computational efficiency can be improved by the application of back-propagation techniques and advances in computing hardware. In addition, waveform inversion algorithms, for obtaining long-wavelength velocity models, could avoid both the local minima problem and the effect of the lack of low-frequency components in seismic data. In this study, we proposed spectrogram inversion as a technique for recovering long-wavelength velocity models. In spectrogram inversion, decomposed frequency components from spectrograms of traces, in the observed and calculated data, are utilized to generate traces with reproduced low-frequency components. Moreover, since each decomposed component can reveal the different characteristics of a subsurface structure, several frequency components were utilized to analyze the velocity features in the subsurface. We performed the spectrogram inversion using a modified SEG/SEGE salt A-A' line. Numerical results demonstrate that spectrogram inversion could also recover the long-wavelength velocity features. However, inversion results varied according to the frequency components utilized. Based on the results of inversion using a decomposed single-frequency component, we noticed that robust inversion results are obtained when a dominant frequency component of the spectrogram was utilized. In addition, detailed information on recovered long-wavelength velocity models was obtained using a multi-frequency component combined with single-frequency components. Numerical examples indicate that various detailed analyses of long-wavelength velocity models can be carried out utilizing several frequency components.

Human recognition based on head-shoulder contour extraction and BP neural network

NASA Astrophysics Data System (ADS)

Kong, Xiao-fang; Wang, Xiu-qin; Gu, Guohua; Chen, Qian; Qian, Wei-xian

2014-11-01

In practical application scenarios like video surveillance and human-computer interaction, human body movements are uncertain because the human body is a non-rigid object. Based on the fact that the head-shoulder part of human body can be less affected by the movement, and will seldom be obscured by other objects, in human detection and recognition, a head-shoulder model with its stable characteristics can be applied as a detection feature to describe the human body. In order to extract the head-shoulder contour accurately, a head-shoulder model establish method with combination of edge detection and the mean-shift algorithm in image clustering has been proposed in this paper. First, an adaptive method of mixture Gaussian background update has been used to extract targets from the video sequence. Second, edge detection has been used to extract the contour of moving objects, and the mean-shift algorithm has been combined to cluster parts of target's contour. Third, the head-shoulder model can be established, according to the width and height ratio of human head-shoulder combined with the projection histogram of the binary image, and the eigenvectors of the head-shoulder contour can be acquired. Finally, the relationship between head-shoulder contour eigenvectors and the moving objects will be formed by the training of back-propagation (BP) neural network classifier, and the human head-shoulder model can be clustered for human detection and recognition. Experiments have shown that the method combined with edge detection and mean-shift algorithm proposed in this paper can extract the complete head-shoulder contour, with low calculating complexity and high efficiency.

Learning Intelligent Genetic Algorithms Using Japanese Nonograms

ERIC Educational Resources Information Center

Tsai, Jinn-Tsong; Chou, Ping-Yi; Fang, Jia-Cen

2012-01-01

An intelligent genetic algorithm (IGA) is proposed to solve Japanese nonograms and is used as a method in a university course to learn evolutionary algorithms. The IGA combines the global exploration capabilities of a canonical genetic algorithm (CGA) with effective condensed encoding, improved fitness function, and modified crossover and…

Location-Aware Mobile Learning of Spatial Algorithms

ERIC Educational Resources Information Center

Karavirta, Ville

2013-01-01

Learning an algorithm--a systematic sequence of operations for solving a problem with given input--is often difficult for students due to the abstract nature of the algorithms and the data they process. To help students understand the behavior of algorithms, a subfield in computing education research has focused on algorithm…

Sequential and Mixed Genetic Algorithm and Learning Automata (SGALA, MGALA) for Feature Selection in QSAR

PubMed Central

MotieGhader, Habib; Gharaghani, Sajjad; Masoudi-Sobhanzadeh, Yosef; Masoudi-Nejad, Ali

2017-01-01

Feature selection is of great importance in Quantitative Structure-Activity Relationship (QSAR) analysis. This problem has been solved using some meta-heuristic algorithms such as GA, PSO, ACO and so on. In this work two novel hybrid meta-heuristic algorithms i.e. Sequential GA and LA (SGALA) and Mixed GA and LA (MGALA), which are based on Genetic algorithm and learning automata for QSAR feature selection are proposed. SGALA algorithm uses advantages of Genetic algorithm and Learning Automata sequentially and the MGALA algorithm uses advantages of Genetic Algorithm and Learning Automata simultaneously. We applied our proposed algorithms to select the minimum possible number of features from three different datasets and also we observed that the MGALA and SGALA algorithms had the best outcome independently and in average compared to other feature selection algorithms. Through comparison of our proposed algorithms, we deduced that the rate of convergence to optimal result in MGALA and SGALA algorithms were better than the rate of GA, ACO, PSO and LA algorithms. In the end, the results of GA, ACO, PSO, LA, SGALA, and MGALA algorithms were applied as the input of LS-SVR model and the results from LS-SVR models showed that the LS-SVR model had more predictive ability with the input from SGALA and MGALA algorithms than the input from all other mentioned algorithms. Therefore, the results have corroborated that not only is the predictive efficiency of proposed algorithms better, but their rate of convergence is also superior to the all other mentioned algorithms. PMID:28979308

Sequential and Mixed Genetic Algorithm and Learning Automata (SGALA, MGALA) for Feature Selection in QSAR.

PubMed

MotieGhader, Habib; Gharaghani, Sajjad; Masoudi-Sobhanzadeh, Yosef; Masoudi-Nejad, Ali

2017-01-01

Feature selection is of great importance in Quantitative Structure-Activity Relationship (QSAR) analysis. This problem has been solved using some meta-heuristic algorithms such as GA, PSO, ACO and so on. In this work two novel hybrid meta-heuristic algorithms i.e. Sequential GA and LA (SGALA) and Mixed GA and LA (MGALA), which are based on Genetic algorithm and learning automata for QSAR feature selection are proposed. SGALA algorithm uses advantages of Genetic algorithm and Learning Automata sequentially and the MGALA algorithm uses advantages of Genetic Algorithm and Learning Automata simultaneously. We applied our proposed algorithms to select the minimum possible number of features from three different datasets and also we observed that the MGALA and SGALA algorithms had the best outcome independently and in average compared to other feature selection algorithms. Through comparison of our proposed algorithms, we deduced that the rate of convergence to optimal result in MGALA and SGALA algorithms were better than the rate of GA, ACO, PSO and LA algorithms. In the end, the results of GA, ACO, PSO, LA, SGALA, and MGALA algorithms were applied as the input of LS-SVR model and the results from LS-SVR models showed that the LS-SVR model had more predictive ability with the input from SGALA and MGALA algorithms than the input from all other mentioned algorithms. Therefore, the results have corroborated that not only is the predictive efficiency of proposed algorithms better, but their rate of convergence is also superior to the all other mentioned algorithms.

Label consistent K-SVD: learning a discriminative dictionary for recognition.

PubMed

Jiang, Zhuolin; Lin, Zhe; Davis, Larry S

2013-11-01

A label consistent K-SVD (LC-KSVD) algorithm to learn a discriminative dictionary for sparse coding is presented. In addition to using class labels of training data, we also associate label information with each dictionary item (columns of the dictionary matrix) to enforce discriminability in sparse codes during the dictionary learning process. More specifically, we introduce a new label consistency constraint called "discriminative sparse-code error" and combine it with the reconstruction error and the classification error to form a unified objective function. The optimal solution is efficiently obtained using the K-SVD algorithm. Our algorithm learns a single overcomplete dictionary and an optimal linear classifier jointly. The incremental dictionary learning algorithm is presented for the situation of limited memory resources. It yields dictionaries so that feature points with the same class labels have similar sparse codes. Experimental results demonstrate that our algorithm outperforms many recently proposed sparse-coding techniques for face, action, scene, and object category recognition under the same learning conditions.

Autonomous learning based on cost assumptions: theoretical studies and experiments in robot control.

PubMed

Ribeiro, C H; Hemerly, E M

2000-02-01

Autonomous learning techniques are based on experience acquisition. In most realistic applications, experience is time-consuming: it implies sensor reading, actuator control and algorithmic update, constrained by the learning system dynamics. The information crudeness upon which classical learning algorithms operate make such problems too difficult and unrealistic. Nonetheless, additional information for facilitating the learning process ideally should be embedded in such a way that the structural, well-studied characteristics of these fundamental algorithms are maintained. We investigate in this article a more general formulation of the Q-learning method that allows for a spreading of information derived from single updates towards a neighbourhood of the instantly visited state and converges to optimality. We show how this new formulation can be used as a mechanism to safely embed prior knowledge about the structure of the state space, and demonstrate it in a modified implementation of a reinforcement learning algorithm in a real robot navigation task.

Machine learning of molecular properties: Locality and active learning

NASA Astrophysics Data System (ADS)

Gubaev, Konstantin; Podryabinkin, Evgeny V.; Shapeev, Alexander V.

2018-06-01

In recent years, the machine learning techniques have shown great potent1ial in various problems from a multitude of disciplines, including materials design and drug discovery. The high computational speed on the one hand and the accuracy comparable to that of density functional theory on another hand make machine learning algorithms efficient for high-throughput screening through chemical and configurational space. However, the machine learning algorithms available in the literature require large training datasets to reach the chemical accuracy and also show large errors for the so-called outliers—the out-of-sample molecules, not well-represented in the training set. In the present paper, we propose a new machine learning algorithm for predicting molecular properties that addresses these two issues: it is based on a local model of interatomic interactions providing high accuracy when trained on relatively small training sets and an active learning algorithm of optimally choosing the training set that significantly reduces the errors for the outliers. We compare our model to the other state-of-the-art algorithms from the literature on the widely used benchmark tests.

QUEST: Eliminating Online Supervised Learning for Efficient Classification Algorithms.

PubMed

Zwartjes, Ardjan; Havinga, Paul J M; Smit, Gerard J M; Hurink, Johann L

2016-10-01

In this work, we introduce QUEST (QUantile Estimation after Supervised Training), an adaptive classification algorithm for Wireless Sensor Networks (WSNs) that eliminates the necessity for online supervised learning. Online processing is important for many sensor network applications. Transmitting raw sensor data puts high demands on the battery, reducing network life time. By merely transmitting partial results or classifications based on the sampled data, the amount of traffic on the network can be significantly reduced. Such classifications can be made by learning based algorithms using sampled data. An important issue, however, is the training phase of these learning based algorithms. Training a deployed sensor network requires a lot of communication and an impractical amount of human involvement. QUEST is a hybrid algorithm that combines supervised learning in a controlled environment with unsupervised learning on the location of deployment. Using the SITEX02 dataset, we demonstrate that the presented solution works with a performance penalty of less than 10% in 90% of the tests. Under some circumstances, it even outperforms a network of classifiers completely trained with supervised learning. As a result, the need for on-site supervised learning and communication for training is completely eliminated by our solution.

Autonomous reinforcement learning with experience replay.

PubMed

Wawrzyński, Paweł; Tanwani, Ajay Kumar

2013-05-01

This paper considers the issues of efficiency and autonomy that are required to make reinforcement learning suitable for real-life control tasks. A real-time reinforcement learning algorithm is presented that repeatedly adjusts the control policy with the use of previously collected samples, and autonomously estimates the appropriate step-sizes for the learning updates. The algorithm is based on the actor-critic with experience replay whose step-sizes are determined on-line by an enhanced fixed point algorithm for on-line neural network training. An experimental study with simulated octopus arm and half-cheetah demonstrates the feasibility of the proposed algorithm to solve difficult learning control problems in an autonomous way within reasonably short time. Copyright © 2012 Elsevier Ltd. All rights reserved.

Immune allied genetic algorithm for Bayesian network structure learning

NASA Astrophysics Data System (ADS)

Song, Qin; Lin, Feng; Sun, Wei; Chang, KC

2012-06-01

Bayesian network (BN) structure learning is a NP-hard problem. In this paper, we present an improved approach to enhance efficiency of BN structure learning. To avoid premature convergence in traditional single-group genetic algorithm (GA), we propose an immune allied genetic algorithm (IAGA) in which the multiple-population and allied strategy are introduced. Moreover, in the algorithm, we apply prior knowledge by injecting immune operator to individuals which can effectively prevent degeneration. To illustrate the effectiveness of the proposed technique, we present some experimental results.

Deep learning improves prediction of CRISPR-Cpf1 guide RNA activity.

PubMed

Kim, Hui Kwon; Min, Seonwoo; Song, Myungjae; Jung, Soobin; Choi, Jae Woo; Kim, Younggwang; Lee, Sangeun; Yoon, Sungroh; Kim, Hyongbum Henry

2018-03-01

We present two algorithms to predict the activity of AsCpf1 guide RNAs. Indel frequencies for 15,000 target sequences were used in a deep-learning framework based on a convolutional neural network to train Seq-deepCpf1. We then incorporated chromatin accessibility information to create the better-performing DeepCpf1 algorithm for cell lines for which such information is available and show that both algorithms outperform previous machine learning algorithms on our own and published data sets.

Toward Intelligent Machine Learning Algorithms

DTIC Science & Technology

1988-05-01

Machine learning is recognized as a tool for improving the performance of many kinds of systems, yet most machine learning systems themselves are not...directed systems, and with the addition of a knowledge store for organizing and maintaining knowledge to assist learning, a learning machine learning (L...ML) algorithm is possible. The necessary components of L-ML systems are presented along with several case descriptions of existing machine learning systems

A Large-Scale Multi-Hop Localization Algorithm Based on Regularized Extreme Learning for Wireless Networks.

PubMed

Zheng, Wei; Yan, Xiaoyong; Zhao, Wei; Qian, Chengshan

2017-12-20

A novel large-scale multi-hop localization algorithm based on regularized extreme learning is proposed in this paper. The large-scale multi-hop localization problem is formulated as a learning problem. Unlike other similar localization algorithms, the proposed algorithm overcomes the shortcoming of the traditional algorithms which are only applicable to an isotropic network, therefore has a strong adaptability to the complex deployment environment. The proposed algorithm is composed of three stages: data acquisition, modeling and location estimation. In data acquisition stage, the training information between nodes of the given network is collected. In modeling stage, the model among the hop-counts and the physical distances between nodes is constructed using regularized extreme learning. In location estimation stage, each node finds its specific location in a distributed manner. Theoretical analysis and several experiments show that the proposed algorithm can adapt to the different topological environments with low computational cost. Furthermore, high accuracy can be achieved by this method without setting complex parameters.

Spiking neuron network Helmholtz machine.

PubMed

Sountsov, Pavel; Miller, Paul

2015-01-01

An increasing amount of behavioral and neurophysiological data suggests that the brain performs optimal (or near-optimal) probabilistic inference and learning during perception and other tasks. Although many machine learning algorithms exist that perform inference and learning in an optimal way, the complete description of how one of those algorithms (or a novel algorithm) can be implemented in the brain is currently incomplete. There have been many proposed solutions that address how neurons can perform optimal inference but the question of how synaptic plasticity can implement optimal learning is rarely addressed. This paper aims to unify the two fields of probabilistic inference and synaptic plasticity by using a neuronal network of realistic model spiking neurons to implement a well-studied computational model called the Helmholtz Machine. The Helmholtz Machine is amenable to neural implementation as the algorithm it uses to learn its parameters, called the wake-sleep algorithm, uses a local delta learning rule. Our spiking-neuron network implements both the delta rule and a small example of a Helmholtz machine. This neuronal network can learn an internal model of continuous-valued training data sets without supervision. The network can also perform inference on the learned internal models. We show how various biophysical features of the neural implementation constrain the parameters of the wake-sleep algorithm, such as the duration of the wake and sleep phases of learning and the minimal sample duration. We examine the deviations from optimal performance and tie them to the properties of the synaptic plasticity rule.

Spiking neuron network Helmholtz machine

PubMed Central

Sountsov, Pavel; Miller, Paul

2015-01-01

An increasing amount of behavioral and neurophysiological data suggests that the brain performs optimal (or near-optimal) probabilistic inference and learning during perception and other tasks. Although many machine learning algorithms exist that perform inference and learning in an optimal way, the complete description of how one of those algorithms (or a novel algorithm) can be implemented in the brain is currently incomplete. There have been many proposed solutions that address how neurons can perform optimal inference but the question of how synaptic plasticity can implement optimal learning is rarely addressed. This paper aims to unify the two fields of probabilistic inference and synaptic plasticity by using a neuronal network of realistic model spiking neurons to implement a well-studied computational model called the Helmholtz Machine. The Helmholtz Machine is amenable to neural implementation as the algorithm it uses to learn its parameters, called the wake-sleep algorithm, uses a local delta learning rule. Our spiking-neuron network implements both the delta rule and a small example of a Helmholtz machine. This neuronal network can learn an internal model of continuous-valued training data sets without supervision. The network can also perform inference on the learned internal models. We show how various biophysical features of the neural implementation constrain the parameters of the wake-sleep algorithm, such as the duration of the wake and sleep phases of learning and the minimal sample duration. We examine the deviations from optimal performance and tie them to the properties of the synaptic plasticity rule. PMID:25954191

Learning algorithms for human-machine interfaces.

PubMed

Danziger, Zachary; Fishbach, Alon; Mussa-Ivaldi, Ferdinando A

2009-05-01

The goal of this study is to create and examine machine learning algorithms that adapt in a controlled and cadenced way to foster a harmonious learning environment between the user and the controlled device. To evaluate these algorithms, we have developed a simple experimental framework. Subjects wear an instrumented data glove that records finger motions. The high-dimensional glove signals remotely control the joint angles of a simulated planar two-link arm on a computer screen, which is used to acquire targets. A machine learning algorithm was applied to adaptively change the transformation between finger motion and the simulated robot arm. This algorithm was either LMS gradient descent or the Moore-Penrose (MP) pseudoinverse transformation. Both algorithms modified the glove-to-joint angle map so as to reduce the endpoint errors measured in past performance. The MP group performed worse than the control group (subjects not exposed to any machine learning), while the LMS group outperformed the control subjects. However, the LMS subjects failed to achieve better generalization than the control subjects, and after extensive training converged to the same level of performance as the control subjects. These results highlight the limitations of coadaptive learning using only endpoint error reduction.

Learning Algorithms for Human–Machine Interfaces

PubMed Central

Fishbach, Alon; Mussa-Ivaldi, Ferdinando A.

2012-01-01

The goal of this study is to create and examine machine learning algorithms that adapt in a controlled and cadenced way to foster a harmonious learning environment between the user and the controlled device. To evaluate these algorithms, we have developed a simple experimental framework. Subjects wear an instrumented data glove that records finger motions. The high-dimensional glove signals remotely control the joint angles of a simulated planar two-link arm on a computer screen, which is used to acquire targets. A machine learning algorithm was applied to adaptively change the transformation between finger motion and the simulated robot arm. This algorithm was either LMS gradient descent or the Moore–Penrose (MP) pseudoinverse transformation. Both algorithms modified the glove-to-joint angle map so as to reduce the endpoint errors measured in past performance. The MP group performed worse than the control group (subjects not exposed to any machine learning), while the LMS group outperformed the control subjects. However, the LMS subjects failed to achieve better generalization than the control subjects, and after extensive training converged to the same level of performance as the control subjects. These results highlight the limitations of coadaptive learning using only endpoint error reduction. PMID:19203886

Implementing a self-structuring data learning algorithm

NASA Astrophysics Data System (ADS)

Graham, James; Carson, Daniel; Ternovskiy, Igor

2016-05-01

In this paper, we elaborate on what we did to implement our self-structuring data learning algorithm. To recap, we are working to develop a data learning algorithm that will eventually be capable of goal driven pattern learning and extrapolation of more complex patterns from less complex ones. At this point we have developed a conceptual framework for the algorithm, but have yet to discuss our actual implementation and the consideration and shortcuts we needed to take to create said implementation. We will elaborate on our initial setup of the algorithm and the scenarios we used to test our early stage algorithm. While we want this to be a general algorithm, it is necessary to start with a simple scenario or two to provide a viable development and testing environment. To that end, our discussion will be geared toward what we include in our initial implementation and why, as well as what concerns we may have. In the future, we expect to be able to apply our algorithm to a more general approach, but to do so within a reasonable time, we needed to pick a place to start.

Learning overcomplete representations from distributed data: a brief review

NASA Astrophysics Data System (ADS)

Raja, Haroon; Bajwa, Waheed U.

2016-05-01

Most of the research on dictionary learning has focused on developing algorithms under the assumption that data is available at a centralized location. But often the data is not available at a centralized location due to practical constraints like data aggregation costs, privacy concerns, etc. Using centralized dictionary learning algorithms may not be the optimal choice in such settings. This motivates the design of dictionary learning algorithms that consider distributed nature of data as one of the problem variables. Just like centralized settings, distributed dictionary learning problem can be posed in more than one way depending on the problem setup. Most notable distinguishing features are the online versus batch nature of data and the representative versus discriminative nature of the dictionaries. In this paper, several distributed dictionary learning algorithms that are designed to tackle different problem setups are reviewed. One of these algorithms is cloud K-SVD, which solves the dictionary learning problem for batch data in distributed settings. One distinguishing feature of cloud K-SVD is that it has been shown to converge to its centralized counterpart, namely, the K-SVD solution. On the other hand, no such guarantees are provided for other distributed dictionary learning algorithms. Convergence of cloud K-SVD to the centralized K-SVD solution means problems that are solvable by K-SVD in centralized settings can now be solved in distributed settings with similar performance. Finally, cloud K-SVD is used as an example to show the advantages that are attainable by deploying distributed dictionary algorithms for real world distributed datasets.

Sparsity-constrained PET image reconstruction with learned dictionaries

NASA Astrophysics Data System (ADS)

Tang, Jing; Yang, Bao; Wang, Yanhua; Ying, Leslie

2016-09-01

PET imaging plays an important role in scientific and clinical measurement of biochemical and physiological processes. Model-based PET image reconstruction such as the iterative expectation maximization algorithm seeking the maximum likelihood solution leads to increased noise. The maximum a posteriori (MAP) estimate removes divergence at higher iterations. However, a conventional smoothing prior or a total-variation (TV) prior in a MAP reconstruction algorithm causes over smoothing or blocky artifacts in the reconstructed images. We propose to use dictionary learning (DL) based sparse signal representation in the formation of the prior for MAP PET image reconstruction. The dictionary to sparsify the PET images in the reconstruction process is learned from various training images including the corresponding MR structural image and a self-created hollow sphere. Using simulated and patient brain PET data with corresponding MR images, we study the performance of the DL-MAP algorithm and compare it quantitatively with a conventional MAP algorithm, a TV-MAP algorithm, and a patch-based algorithm. The DL-MAP algorithm achieves improved bias and contrast (or regional mean values) at comparable noise to what the other MAP algorithms acquire. The dictionary learned from the hollow sphere leads to similar results as the dictionary learned from the corresponding MR image. Achieving robust performance in various noise-level simulation and patient studies, the DL-MAP algorithm with a general dictionary demonstrates its potential in quantitative PET imaging.

Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms.

PubMed

Ozcift, Akin; Gulten, Arif

2011-12-01

Improving accuracies of machine learning algorithms is vital in designing high performance computer-aided diagnosis (CADx) systems. Researches have shown that a base classifier performance might be enhanced by ensemble classification strategies. In this study, we construct rotation forest (RF) ensemble classifiers of 30 machine learning algorithms to evaluate their classification performances using Parkinson's, diabetes and heart diseases from literature. While making experiments, first the feature dimension of three datasets is reduced using correlation based feature selection (CFS) algorithm. Second, classification performances of 30 machine learning algorithms are calculated for three datasets. Third, 30 classifier ensembles are constructed based on RF algorithm to assess performances of respective classifiers with the same disease data. All the experiments are carried out with leave-one-out validation strategy and the performances of the 60 algorithms are evaluated using three metrics; classification accuracy (ACC), kappa error (KE) and area under the receiver operating characteristic (ROC) curve (AUC). Base classifiers succeeded 72.15%, 77.52% and 84.43% average accuracies for diabetes, heart and Parkinson's datasets, respectively. As for RF classifier ensembles, they produced average accuracies of 74.47%, 80.49% and 87.13% for respective diseases. RF, a newly proposed classifier ensemble algorithm, might be used to improve accuracy of miscellaneous machine learning algorithms to design advanced CADx systems. Copyright © 2011 Elsevier Ireland Ltd. All rights reserved.

Theoretical and Empirical Analysis of a Spatial EA Parallel Boosting Algorithm.

PubMed

Kamath, Uday; Domeniconi, Carlotta; De Jong, Kenneth

2018-01-01

Many real-world problems involve massive amounts of data. Under these circumstances learning algorithms often become prohibitively expensive, making scalability a pressing issue to be addressed. A common approach is to perform sampling to reduce the size of the dataset and enable efficient learning. Alternatively, one customizes learning algorithms to achieve scalability. In either case, the key challenge is to obtain algorithmic efficiency without compromising the quality of the results. In this article we discuss a meta-learning algorithm (PSBML) that combines concepts from spatially structured evolutionary algorithms (SSEAs) with concepts from ensemble and boosting methodologies to achieve the desired scalability property. We present both theoretical and empirical analyses which show that PSBML preserves a critical property of boosting, specifically, convergence to a distribution centered around the margin. We then present additional empirical analyses showing that this meta-level algorithm provides a general and effective framework that can be used in combination with a variety of learning classifiers. We perform extensive experiments to investigate the trade-off achieved between scalability and accuracy, and robustness to noise, on both synthetic and real-world data. These empirical results corroborate our theoretical analysis, and demonstrate the potential of PSBML in achieving scalability without sacrificing accuracy.

Basis Expansion Approaches for Regularized Sequential Dictionary Learning Algorithms With Enforced Sparsity for fMRI Data Analysis.

PubMed

Seghouane, Abd-Krim; Iqbal, Asif

2017-09-01

Sequential dictionary learning algorithms have been successfully applied to functional magnetic resonance imaging (fMRI) data analysis. fMRI data sets are, however, structured data matrices with the notions of temporal smoothness in the column direction. This prior information, which can be converted into a constraint of smoothness on the learned dictionary atoms, has seldomly been included in classical dictionary learning algorithms when applied to fMRI data analysis. In this paper, we tackle this problem by proposing two new sequential dictionary learning algorithms dedicated to fMRI data analysis by accounting for this prior information. These algorithms differ from the existing ones in their dictionary update stage. The steps of this stage are derived as a variant of the power method for computing the SVD. The proposed algorithms generate regularized dictionary atoms via the solution of a left regularized rank-one matrix approximation problem where temporal smoothness is enforced via regularization through basis expansion and sparse basis expansion in the dictionary update stage. Applications on synthetic data experiments and real fMRI data sets illustrating the performance of the proposed algorithms are provided.

Error vector magnitude based parameter estimation for digital filter back-propagation mitigating SOA distortions in 16-QAM.

PubMed

Amiralizadeh, Siamak; Nguyen, An T; Rusch, Leslie A

2013-08-26

We investigate the performance of digital filter back-propagation (DFBP) using coarse parameter estimation for mitigating SOA nonlinearity in coherent communication systems. We introduce a simple, low overhead method for parameter estimation for DFBP based on error vector magnitude (EVM) as a figure of merit. The bit error rate (BER) penalty achieved with this method has negligible penalty as compared to DFBP with fine parameter estimation. We examine different bias currents for two commercial SOAs used as booster amplifiers in our experiments to find optimum operating points and experimentally validate our method. The coarse parameter DFBP efficiently compensates SOA-induced nonlinearity for both SOA types in 80 km propagation of 16-QAM signal at 22 Gbaud.

Learning in Structured Connectionist Networks

DTIC Science & Technology

1988-04-01

the structure is too rigid and learning too difficult for cognitive modeling. Two algorithms for learning simple, feature-based concept descriptions...and learning too difficult for cognitive model- ing. Two algorithms for learning simple, feature-based concept descriptions were also implemented. The...Term Goals Recent progress in connectionist research has been encouraging; networks have success- fully modeled human performance for various cognitive

An Ensemble Approach in Converging Contents of LMS and KMS

ERIC Educational Resources Information Center

Sabitha, A. Sai; Mehrotra, Deepti; Bansal, Abhay

2017-01-01

Currently the challenges in e-Learning are converging the learning content from various sources and managing them within e-learning practices. Data mining learning algorithms can be used and the contents can be converged based on the Metadata of the objects. Ensemble methods use multiple learning algorithms and it can be used to converge the…

Reinforcement Learning for Weakly-Coupled MDPs and an Application to Planetary Rover Control

NASA Technical Reports Server (NTRS)

Bernstein, Daniel S.; Zilberstein, Shlomo

2003-01-01

Weakly-coupled Markov decision processes can be decomposed into subprocesses that interact only through a small set of bottleneck states. We study a hierarchical reinforcement learning algorithm designed to take advantage of this particular type of decomposability. To test our algorithm, we use a decision-making problem faced by autonomous planetary rovers. In this problem, a Mars rover must decide which activities to perform and when to traverse between science sites in order to make the best use of its limited resources. In our experiments, the hierarchical algorithm performs better than Q-learning in the early stages of learning, but unlike Q-learning it converges to a suboptimal policy. This suggests that it may be advantageous to use the hierarchical algorithm when training time is limited.

Modeling level change in Lake Urmia using hybrid artificial intelligence approaches

NASA Astrophysics Data System (ADS)

Esbati, M.; Ahmadieh Khanesar, M.; Shahzadi, Ali

2017-06-01

The investigation of water level fluctuations in lakes for protecting them regarding the importance of these water complexes in national and regional scales has found a special place among countries in recent years. The importance of the prediction of water level balance in Lake Urmia is necessary due to several-meter fluctuations in the last decade which help the prevention from possible future losses. For this purpose, in this paper, the performance of adaptive neuro-fuzzy inference system (ANFIS) for predicting the lake water level balance has been studied. In addition, for the training of the adaptive neuro-fuzzy inference system, particle swarm optimization (PSO) and hybrid backpropagation-recursive least square method algorithm have been used. Moreover, a hybrid method based on particle swarm optimization and recursive least square (PSO-RLS) training algorithm for the training of ANFIS structure is introduced. In order to have a more fare comparison, hybrid particle swarm optimization and gradient descent are also applied. The models have been trained, tested, and validated based on lake level data between 1991 and 2014. For performance evaluation, a comparison is made between these methods. Numerical results obtained show that the proposed methods with a reasonable error have a good performance in water level balance prediction. It is also clear that with continuing the current trend, Lake Urmia will experience more drop in the water level balance in the upcoming years.

Investigating the performance of wavelet neural networks in ionospheric tomography using IGS data over Europe

NASA Astrophysics Data System (ADS)

Ghaffari Razin, Mir Reza; Voosoghi, Behzad

2017-04-01

Ionospheric tomography is a very cost-effective method which is used frequently to modeling of electron density distributions. In this paper, residual minimization training neural network (RMTNN) is used in voxel based ionospheric tomography. Due to the use of wavelet neural network (WNN) with back-propagation (BP) algorithm in RMTNN method, the new method is named modified RMTNN (MRMTNN). To train the WNN with BP algorithm, two cost functions is defined: total and vertical cost functions. Using minimization of cost functions, temporal and spatial ionospheric variations is studied. The GPS measurements of the international GNSS service (IGS) in the central Europe have been used for constructing a 3-D image of the electron density. Three days (2009.04.15, 2011.07.20 and 2013.06.01) with different solar activity index is used for the processing. To validate and better assess reliability of the proposed method, 4 ionosonde and 3 testing stations have been used. Also the results of MRMTNN has been compared to that of the RMTNN method, international reference ionosphere model 2012 (IRI-2012) and spherical cap harmonic (SCH) method as a local ionospheric model. The comparison of MRMTNN results with RMTNN, IRI-2012 and SCH models shows that the root mean square error (RMSE) and standard deviation of the proposed approach are superior to those of the traditional method.

An application of artificial neural intelligence for personal dose assessment using a multi-area OSL dosimetry system.

PubMed

Lee, S Y; Kim, B H; Lee, K J

2001-06-01

Significant advances have been made in recent years to improve measurement technology and performance of phosphor materials in the fields of optically stimulated luminescence (OSL) dosimetry. Pulsed and continuous wave OSL studies recently carried out on alpha-Al2O3:C have shown that the material seems to be the most promising for routine application of OSL for dosimetric purposes. The main objective of the study is to propose a new personal dosimetry system using alpha-Al2O3:C by taking advantage of its optical properties and energy dependencies. In the process of the study, a new dose assessment algorithm was developed using artificial neural networks in hopes of achieving a higher degree of accuracy and precision in personal OSL dosimetry system. The original hypothesis of this work is that the spectral information of X- and gamma-ray fields may be obtained by the analysis of the response of a multi-element system. In this study, a feedforward neural network using the error back-propagation method with Bayesian optimization was applied for the response unfolding procedure. The validation of the proposed algorithm was investigated by unfolding the 10 measured responses of alpha-Al2O3:C for arbitrarily mixed photon fields which range from 20 to 662 keV. c2001 Elsevier Science Ltd. All rights reserved.

Identification of cataract and post-cataract surgery optical images using artificial intelligence techniques.

PubMed

Acharya, Rajendra Udyavara; Yu, Wenwei; Zhu, Kuanyi; Nayak, Jagadish; Lim, Teik-Cheng; Chan, Joey Yiptong

2010-08-01

Human eyes are most sophisticated organ, with perfect and interrelated subsystems such as retina, pupil, iris, cornea, lens and optic nerve. The eye disorder such as cataract is a major health problem in the old age. Cataract is formed by clouding of lens, which is painless and developed slowly over a long period. Cataract will slowly diminish the vision leading to the blindness. At an average age of 65, it is most common and one third of the people of this age in world have cataract in one or both the eyes. A system for detection of the cataract and to test for the efficacy of the post-cataract surgery using optical images is proposed using artificial intelligence techniques. Images processing and Fuzzy K-means clustering algorithm is applied on the raw optical images to detect the features specific to three classes to be classified. Then the backpropagation algorithm (BPA) was used for the classification. In this work, we have used 140 optical image belonging to the three classes. The ANN classifier showed an average rate of 93.3% in detecting normal, cataract and post cataract optical images. The system proposed exhibited 98% sensitivity and 100% specificity, which indicates that the results are clinically significant. This system can also be used to test the efficacy of the cataract operation by testing the post-cataract surgery optical images.

Design of Learning Model of Logic and Algorithms Based on APOS Theory

ERIC Educational Resources Information Center

Hartati, Sulis Janu

2014-01-01

This research questions were "how do the characteristics of learning model of logic & algorithm according to APOS theory" and "whether or not these learning model can improve students learning outcomes". This research was conducted by exploration, and quantitative approach. Exploration used in constructing theory about the…

An improved clustering algorithm based on reverse learning in intelligent transportation

NASA Astrophysics Data System (ADS)

Qiu, Guoqing; Kou, Qianqian; Niu, Ting

2017-05-01

With the development of artificial intelligence and data mining technology, big data has gradually entered people's field of vision. In the process of dealing with large data, clustering is an important processing method. By introducing the reverse learning method in the clustering process of PAM clustering algorithm, to further improve the limitations of one-time clustering in unsupervised clustering learning, and increase the diversity of clustering clusters, so as to improve the quality of clustering. The algorithm analysis and experimental results show that the algorithm is feasible.

Particle Swarm Optimization With Interswarm Interactive Learning Strategy.

PubMed

Qin, Quande; Cheng, Shi; Zhang, Qingyu; Li, Li; Shi, Yuhui

2016-10-01

The learning strategy in the canonical particle swarm optimization (PSO) algorithm is often blamed for being the primary reason for loss of diversity. Population diversity maintenance is crucial for preventing particles from being stuck into local optima. In this paper, we present an improved PSO algorithm with an interswarm interactive learning strategy (IILPSO) by overcoming the drawbacks of the canonical PSO algorithm's learning strategy. IILPSO is inspired by the phenomenon in human society that the interactive learning behavior takes place among different groups. Particles in IILPSO are divided into two swarms. The interswarm interactive learning (IIL) behavior is triggered when the best particle's fitness value of both the swarms does not improve for a certain number of iterations. According to the best particle's fitness value of each swarm, the softmax method and roulette method are used to determine the roles of the two swarms as the learning swarm and the learned swarm. In addition, the velocity mutation operator and global best vibration strategy are used to improve the algorithm's global search capability. The IIL strategy is applied to PSO with global star and local ring structures, which are termed as IILPSO-G and IILPSO-L algorithm, respectively. Numerical experiments are conducted to compare the proposed algorithms with eight popular PSO variants. From the experimental results, IILPSO demonstrates the good performance in terms of solution accuracy, convergence speed, and reliability. Finally, the variations of the population diversity in the entire search process provide an explanation why IILPSO performs effectively.

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

Jamieson, Kevin; Davis, IV, Warren L.

Active learning methods automatically adapt data collection by selecting the most informative samples in order to accelerate machine learning. Because of this, real-world testing and comparing active learning algorithms requires collecting new datasets (adaptively), rather than simply applying algorithms to benchmark datasets, as is the norm in (passive) machine learning research. To facilitate the development, testing and deployment of active learning for real applications, we have built an open-source software system for large-scale active learning research and experimentation. The system, called NEXT, provides a unique platform for realworld, reproducible active learning research. This paper details the challenges of building themore » system and demonstrates its capabilities with several experiments. The results show how experimentation can help expose strengths and weaknesses of active learning algorithms, in sometimes unexpected and enlightening ways.« less

Regularised extreme learning machine with misclassification cost and rejection cost for gene expression data classification.

PubMed

Lu, Huijuan; Wei, Shasha; Zhou, Zili; Miao, Yanzi; Lu, Yi

2015-01-01

The main purpose of traditional classification algorithms on bioinformatics application is to acquire better classification accuracy. However, these algorithms cannot meet the requirement that minimises the average misclassification cost. In this paper, a new algorithm of cost-sensitive regularised extreme learning machine (CS-RELM) was proposed by using probability estimation and misclassification cost to reconstruct the classification results. By improving the classification accuracy of a group of small sample which higher misclassification cost, the new CS-RELM can minimise the classification cost. The 'rejection cost' was integrated into CS-RELM algorithm to further reduce the average misclassification cost. By using Colon Tumour dataset and SRBCT (Small Round Blue Cells Tumour) dataset, CS-RELM was compared with other cost-sensitive algorithms such as extreme learning machine (ELM), cost-sensitive extreme learning machine, regularised extreme learning machine, cost-sensitive support vector machine (SVM). The results of experiments show that CS-RELM with embedded rejection cost could reduce the average cost of misclassification and made more credible classification decision than others.

Decentralized indirect methods for learning automata games.

PubMed

Tilak, Omkar; Martin, Ryan; Mukhopadhyay, Snehasis

2011-10-01

We discuss the application of indirect learning methods in zero-sum and identical payoff learning automata games. We propose a novel decentralized version of the well-known pursuit learning algorithm. Such a decentralized algorithm has significant computational advantages over its centralized counterpart. The theoretical study of such a decentralized algorithm requires the analysis to be carried out in a nonstationary environment. We use a novel bootstrapping argument to prove the convergence of the algorithm. To our knowledge, this is the first time that such analysis has been carried out for zero-sum and identical payoff games. Extensive simulation studies are reported, which demonstrate the proposed algorithm's fast and accurate convergence in a variety of game scenarios. We also introduce the framework of partial communication in the context of identical payoff games of learning automata. In such games, the automata may not communicate with each other or may communicate selectively. This comprehensive framework has the capability to model both centralized and decentralized games discussed in this paper.

Validating Machine Learning Algorithms for Twitter Data Against Established Measures of Suicidality.

PubMed

Braithwaite, Scott R; Giraud-Carrier, Christophe; West, Josh; Barnes, Michael D; Hanson, Carl Lee

2016-05-16

One of the leading causes of death in the United States (US) is suicide and new methods of assessment are needed to track its risk in real time. Our objective is to validate the use of machine learning algorithms for Twitter data against empirically validated measures of suicidality in the US population. Using a machine learning algorithm, the Twitter feeds of 135 Mechanical Turk (MTurk) participants were compared with validated, self-report measures of suicide risk. Our findings show that people who are at high suicidal risk can be easily differentiated from those who are not by machine learning algorithms, which accurately identify the clinically significant suicidal rate in 92% of cases (sensitivity: 53%, specificity: 97%, positive predictive value: 75%, negative predictive value: 93%). Machine learning algorithms are efficient in differentiating people who are at a suicidal risk from those who are not. Evidence for suicidality can be measured in nonclinical populations using social media data.

Validating Machine Learning Algorithms for Twitter Data Against Established Measures of Suicidality

PubMed Central

2016-01-01

Background One of the leading causes of death in the United States (US) is suicide and new methods of assessment are needed to track its risk in real time. Objective Our objective is to validate the use of machine learning algorithms for Twitter data against empirically validated measures of suicidality in the US population. Methods Using a machine learning algorithm, the Twitter feeds of 135 Mechanical Turk (MTurk) participants were compared with validated, self-report measures of suicide risk. Results Our findings show that people who are at high suicidal risk can be easily differentiated from those who are not by machine learning algorithms, which accurately identify the clinically significant suicidal rate in 92% of cases (sensitivity: 53%, specificity: 97%, positive predictive value: 75%, negative predictive value: 93%). Conclusions Machine learning algorithms are efficient in differentiating people who are at a suicidal risk from those who are not. Evidence for suicidality can be measured in nonclinical populations using social media data. PMID:27185366

Theory of impossible worlds: Toward a physics of information.

PubMed

Buscema, Paolo Massimo; Sacco, Pier Luigi; Della Torre, Francesca; Massini, Giulia; Breda, Marco; Ferilli, Guido

2018-05-01

In this paper, we introduce an innovative approach to the fusion between datasets in terms of attributes and observations, even when they are not related at all. With our technique, starting from datasets representing independent worlds, it is possible to analyze a single global dataset, and transferring each dataset onto the others is always possible. This procedure allows a deeper perspective in the study of a problem, by offering the chance of looking into it from other, independent points of view. Even unrelated datasets create a metaphoric representation of the problem, useful in terms of speed of convergence and predictive results, preserving the fundamental relationships in the data. In order to extract such knowledge, we propose a new learning rule named double backpropagation, by which an auto-encoder concurrently codifies all the different worlds. We test our methodology on different datasets and different issues, to underline the power and flexibility of the Theory of Impossible Worlds.