Digital Backpropagation in the Nonlinear Fourier Domain
Wahls, Sander; Prilepsky, Jaroslaw E; Poor, H Vincent; Turitsyn, Sergei K
2015-01-01
Nonlinear and dispersive transmission impairments in coherent fiber-optic communication systems are often compensated by reverting the nonlinear Schr\\"odinger equation, which describes the evolution of the signal in the link, numerically. This technique is known as digital backpropagation. Typical digital backpropagation algorithms are based on split-step Fourier methods in which the signal has to be discretized in time and space. The need to discretize in both time and space however makes the real-time implementation of digital backpropagation a challenging problem. In this paper, a new fast algorithm for digital backpropagation based on nonlinear Fourier transforms is presented. Aiming at a proof of concept, the main emphasis will be put on fibers with normal dispersion in order to avoid the issue of solitonic components in the signal. However, it is demonstrated that the algorithm also works for anomalous dispersion if the signal power is low enough. Since the spatial evolution of a signal governed by the ...
Stochastic Digital Backpropagation with Residual Memory Compensation
Irukulapati, Naga V; Johannisson, Pontus; Agrell, Erik; Secondini, Marco; Wymeersch, Henk
2015-01-01
Stochastic digital backpropagation (SDBP) is an extension of digital backpropagation (DBP) and is based on the maximum a posteriori principle. SDBP takes into account noise from the optical amplifiers in addition to handling deterministic linear and nonlinear impairments. The decisions in SDBP are taken on a symbol-by-symbol (SBS) basis, ignoring any residual memory, which may be present due to matched filtering in SDBP. In this paper, we extend SDBP to account for memory between symbols. In particular, two different methods are proposed: a Viterbi algorithm (VA) and a decision directed approach. Symbol error rate (SER) for memory-based SDBP is significantly lower than the previously proposed SBS-SDBP. For inline dispersion-managed links, the VA-SDBP has 10 and 14 times lower SER than DBP for QPSK and 16-QAM, respectively.
Ocean wave parameters estimation using backpropagation neural networks
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.; SubbaRao; Raju, D.H.
and lack of any exogenous input requirement makes the NN attractive. A NN is an information processing system modeled on the structure of the dynamic process. Its merit is the ability to deal with information whose interrelation is ambiguous or whose... output at the kth output nodes. 2.1. Backpropagation learning Backpropagation is the most widely used algorithm for supervised learning with multi- layer feed-forward networks. The idea of the backpropagation learning algorithm is the repeated application...
Generalized Backpropagation Algorithms for Diffraction Tomography
Paladhi, Pavel Roy; Tayebi, Amin; Udpa, Lalita
2016-01-01
Filtered backpropagation (FBPP) is a well-known technique used for Diffraction Tomography (DT). For accurate reconstruction of a complex image using FBPP, full $360^{\\circ}$ angular coverage is necessary. However, it has been shown that using some inherent redundancies in projection data in a tomographic setup, accurate reconstruction is still possible with $270^{\\circ}$ coverage which is called the minimal-scan angle range. This can be done by applying weighing functions (or filters) on projection data of the object to eliminate the redundancies and accurately reconstruct the image from this lower angular coverage. This paper demonstrates procedures to generate many general classes of these weighing filters. These are all equivalent at $270^{\\circ}$ coverage but would perform differently at lower angular coverages and under presence of noise. This paper does a comparative analysis of different filters when angular coverage is lower than minimal-scan angle of $270^{\\circ}$. Simulation studies have been done t...
Prediction of tides using back-propagation neural networks
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.
Prediction of tides is very much essential for human activities and to reduce the construction cost in marine environment. This paper presents an application of the artificial neural network with back-propagation procedures for accurate prediction...
Training Deep Spiking Neural Networks Using Backpropagation.
Lee, Jun Haeng; Delbruck, Tobi; Pfeiffer, Michael
2016-01-01
Deep spiking neural networks (SNNs) hold the potential for improving the latency and energy efficiency of deep neural networks through data-driven event-based computation. However, training such networks is difficult due to the non-differentiable nature of spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are considered as noise. This enables an error backpropagation mechanism for deep SNNs that follows the same principles as in conventional deep networks, but works directly on spike signals and membrane potentials. Compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statistics of spikes more precisely. We evaluate the proposed framework on artificially generated events from the original MNIST handwritten digit benchmark, and also on the N-MNIST benchmark recorded with an event-based dynamic vision sensor, in which the proposed method reduces the error rate by a factor of more than three compared to the best previous SNN, and also achieves a higher accuracy than a conventional convolutional neural network (CNN) trained and tested on the same data. We demonstrate in the context of the MNIST task that thanks to their event-driven operation, deep SNNs (both fully connected and convolutional) trained with our method achieve accuracy equivalent with conventional neural networks. In the N-MNIST example, equivalent accuracy is achieved with about five times fewer computational operations.
The adaptation of spike backpropagation delays in cortical neurons
Directory of Open Access Journals (Sweden)
Yossi eBuskila
2013-10-01
Full Text Available We measured the action potential backpropagation delays in apical dendrites of layer 5 pyramidal neurons of the somatosensory cortex under different stimulation regimes that exclude synaptic involvement. These delays showed robust features and did not correlate to either transient change in the stimulus strength or low frequency stimulation of suprathreshold membrane oscillations. However, our results indicate that backpropagation delays correlate with high frequency (>10 Hz stimulation of membrane oscillations, and that persistent suprathreshold sinusoidal stimulation injected directly into the soma results in an increase of the backpropagation delay, suggesting an intrinsic adaptation of the bAP, which does not involve any synaptic modifications. Moreover, the calcium chelator BAPTA eliminated the alterations in the backpropagation delays, strengthening the hypothesis that increased calcium concentration in the dendrites modulates dendritic excitability and can impact the backpropagation velocity. These results emphasize the impact of dendritic excitability on bAP velocity along the dendritic tree, which affects the precision of the bAP arrival at the synapse during specific stimulus regimes, and is capable of shifting the extent and polarity of synaptic strength during suprathreshold synaptic processes such as STDP.
Non-Linear Back-propagation: Doing Back-Propagation withoutDerivatives of the Activation Function
DEFF Research Database (Denmark)
Hertz, John; Krogh, Anders Stærmose; Lautrup, Benny
1997-01-01
The conventional linear back-propagation algorithm is replaced by a non-linear version, which avoids the necessity for calculating the derivative of the activation function. This may be exploited in hardware realizations of neural processors. In this paper we derive the non-linear back-propagatio......-propagation algorithms in the framework of recurrent back-propagation and present some numerical simulations of feed-forward networks on the NetTalk problem. A discussion of implementation in analog VLSI electronics concludes the paper.......The conventional linear back-propagation algorithm is replaced by a non-linear version, which avoids the necessity for calculating the derivative of the activation function. This may be exploited in hardware realizations of neural processors. In this paper we derive the non-linear back...
Random synaptic feedback weights support error backpropagation for deep learning
Lillicrap, Timothy P.; Cownden, Daniel; Tweed, Douglas B.; Akerman, Colin J.
2016-11-01
The brain processes information through multiple layers of neurons. This deep architecture is representationally powerful, but complicates learning because it is difficult to identify the responsible neurons when a mistake is made. In machine learning, the backpropagation algorithm assigns blame by multiplying error signals with all the synaptic weights on each neuron's axon and further downstream. However, this involves a precise, symmetric backward connectivity pattern, which is thought to be impossible in the brain. Here we demonstrate that this strong architectural constraint is not required for effective error propagation. We present a surprisingly simple mechanism that assigns blame by multiplying errors by even random synaptic weights. This mechanism can transmit teaching signals across multiple layers of neurons and performs as effectively as backpropagation on a variety of tasks. Our results help reopen questions about how the brain could use error signals and dispel long-held assumptions about algorithmic constraints on learning.
BACKPROPAGATION TRAINING ALGORITHM WITH ADAPTIVE PARAMETERS TO SOLVE DIGITAL PROBLEMS
Directory of Open Access Journals (Sweden)
R. Saraswathi
2011-01-01
Full Text Available An efficient technique namely Backpropagation training with adaptive parameters using Lyapunov Stability Theory for training single hidden layer feed forward network is proposed. A three-layered Feedforward neural network architecture is used to solve the selected problems. Sequential Training Mode is used to train the network. Lyapunov stability theory is employed to ensure the faster and steady state error convergence and to construct and energy surface with a single global minimum point through the adaptive adjustment of the weights and the adaptive parameter ß. To avoid local minima entrapment, an adaptive backpropagation algorithm based on Lyapunov stability theory is used. Lyapunov stability theory gives the algorithm, the efficiency of attaining a single global minimum point. The learning parameters used in this algorithm is responsible for the faster error convergence. The adaptive learning parameter used in this algorithm is chosen properly for faster error convergence. The error obtained has been asymptotically converged to zero according to Lyapunov Stability theory. The performance of the adaptive Backpropagation algorithm is measured by solving parity problem, half adder and full adder problems.
Impact of Mutation Weights on Training Backpropagation Neural Networks
Directory of Open Access Journals (Sweden)
Lamia Abed Noor Muhammed
2014-07-01
Full Text Available Neural network is a computational approach, which based on the simulation of biology neural network. This approach is conducted by several parameters; learning rate, initialized weights, network architecture, and so on. However, this paper would be focused on one of these parameters that is weights. The aim is to shed lights on the mutation weights through training network and its effects on the results. The experiment was done using backpropagation neural network with one hidden layer. The results reveal the role of mutation in escape from the local minima and making the change
1990-01-01
A new recursive prediction error routine is compared with the backpropagation method of training neural networks. Results based on simulated systems, the prediction of Canadian Lynx data and the modelling of an automotive diesel engine indicate that the recursive prediction error algorithm is far superior to backpropagation.
Evolving Resilient Back-Propagation Algorithm for Energy Efficiency Problem
Directory of Open Access Journals (Sweden)
Yang Fei
2016-01-01
Full Text Available Energy efficiency is one of our most economical sources of new energy. When it comes to efficient building design, the computation of the heating load (HL and cooling load (CL is required to determine the specifications of the heating and cooling equipment. The objective of this paper is to model heating load and cooling load buildings using neural networks in order to predict HL load and CL load. Rprop with genetic algorithm was proposed to increase the global convergence capability of Rprop by modifying a corresponding weight. Comparison results show that Rprop with GA can successfully improve the global convergence capability of Rprop and achieve lower MSE than other perceptron training algorithms, such as Back-Propagation or original Rprop. In addition, the trained network has better generalization ability and stabilization performance.
Backpropagation Artificial Neural Network To Detect Hyperthermic Seizures In Rats
Directory of Open Access Journals (Sweden)
Rakesh Kumar Sinha
2003-02-01
Full Text Available A three-layered feed-forward back-propagation Artificial Neural Network was used to classify the seizure episodes in rats. Seizure patterns were induced by subjecting anesthetized rats to a Biological Oxygen Demand incubator at 45-47ºC for 30 to 60 minutes. Selected fast Fourier transform data of one second epochs of electroencephalogram were used to train and test the network for the classification of seizure and normal patterns. The results indicate that the present network with the architecture of 40-12-1 (input-hidden-output nodes agrees with manual scoring of seizure and normal patterns with a high recognition rate of 98.6%.
Single-step digital backpropagation for nonlinearity mitigation
DEFF Research Database (Denmark)
Secondini, Marco; Rommel, Simon; Meloni, Gianluca;
2015-01-01
Nonlinearity mitigation based on the enhanced split-step Fourier method (ESSFM) for the implementation of low-complexity digital backpropagation (DBP) is investigated and experimentally demonstrated. After reviewing the main computational aspects of DBP and of the conventional split-step Fourier...... method (SSFM), the ESSFM for dual-polarization signals is introduced. Computational complexity, latency, and power consumption of DBP based on the SSFM and ESSFM algorithms are estimated and compared. Effective low-complexity nonlinearity mitigation in a 112 Gb/s polarization-multiplexed QPSK system...... of the SSFM algorithm to achieve the same performance. An analysis of the computational complexity and structure of the two algorithms reveals that the overall complexity and power consumption of DBP are reduced by a factor of 16 with respect to a conventional implementation, while the computation time...
Conjugate descent formulation of backpropagation error in feedforward neural networks
Directory of Open Access Journals (Sweden)
NK Sharma
2009-06-01
Full Text Available The feedforward neural network architecture uses backpropagation learning to determine optimal weights between different interconnected layers. This learning procedure uses a gradient descent technique applied to a sum-of-squares error function for the given input-output pattern. It employs an iterative procedure to minimise the error function for a given set of patterns, by adjusting the weights of the network. The first derivates of the error with respect to the weights identify the local error surface in the descent direction. Hence the network exhibits a different local error surface for every different pattern presented to it, and weights are iteratively modified in order to minimise the current local error. The determination of an optimal weight vector is possible only when the total minimum error (mean of the minimum local errors for all patterns from the training set may be minimised. In this paper, we present a general mathematical formulation for the second derivative of the error function with respect to the weights (which represents a conjugate descent for arbitrary feedforward neural network topologies, and we use this derivative information to obtain the optimal weight vector. The local error is backpropagated among the units of hidden layers via the second order derivative of the error with respect to the weights of the hidden and output layers independently and also in combination. The new total minimum error point may be evaluated with the help of the current total minimum error and the current minimised local error. The weight modification processes is performed twice: once with respect to the present local error and once more with respect to the current total or mean error. We present some numerical evidence that our proposed method yields better network weights than those determined via a conventional gradient descent approach.
Directory of Open Access Journals (Sweden)
Sheela Tiwari
2013-08-01
Full Text Available This paperexplores theapplicationof artificial neural networksfor online identification of a multimachinepower system.Arecurrent neural networkhas been proposedas the identifier of the two area, four machinesystemwhich is a benchmark system for studying electromechanical oscillations in multimachine powersystems. This neural identifier is trained using the static Backpropagation algorithm. The emphasis of thepaper is on investigating the performance of the variants of the Backpropagation algorithm in training theneural identifier. The paper also compares the performances of the neural identifiers trained usingvariantsof the Backpropagation algorithmover a wide range of operating conditions.The simulation resultsestablish a satisfactory performance of the trained neural identifiers in identification of the test powersystem
Ibnu Hajar
2009-01-01
Relay jarak digunakan untuk mengamankan jaringan transmisi dari gangguan hubung singkat, biasanya dirancang dengan range setting yang tetap. Jika impedansi jaringan transmisi yang akan diamankan tidak berada derange setting impedansi relay jarak, maka relay tidak bias bekerja. Penggunaan backpropagation neural network pada relay jarak untuk mendeteksi gangguan dengan mengenali pola-pola bentuk gelombang tegangan dan arus. Prinsip dari backpropagation neural network pada aplikasi relay jarak a...
Uniformly stable backpropagation algorithm to train a feedforward neural network.
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.
Backpropagation Neural Network Modeling for Fault Location in Transmission Line 150 kV
Directory of Open Access Journals (Sweden)
Azriyenni Narwan
2014-03-01
Full Text Available In this topic research was provided about the backpropagation neural network to detect fault location in transmission line 150 kV between substation to substation. The distance relay is one of the good protective device and safety devices that often used on transmission line 150 kV. The disturbances in power system are used distance relay protection equipment in the transmission line. However, it needs more increasing large load and network systems are increasing complex. The protection system use the digital control, in order to avoid the error calculation of the distance relay impedance settings and spent time will be more efficient. Then backpropagation neural network is a computational model that uses the training process that can be used to solve the problem of work limitations of distance protection relays. The backpropagation neural network does not have limitations cause of the impedance range setting. If the output gives the wrong result, so the correct of the weights can be minimized and also the response of galat, the backpropagation neural network is expected to be closer to the correct value. In the end, backpropagation neural network modeling is expected to detect the fault location and identify operational output current circuit breaker was tripped it. The tests are performance with interconnected system 150 kV of Riau Region.
Training a Feed-Forward Neural Network with Artificial Bee Colony based Backpropagation Method
Directory of Open Access Journals (Sweden)
Sudarshan Nandy
2012-09-01
Full Text Available Back-propagation algorithm is one of the most widely used and popular techniques to optimize the feedforward neural network training. Nature inspired meta-heuristic algorithms also provide derivative-freesolution to optimize complex problem. Artificial bee colony algorithm is a nature inspired meta-heuristicalgorithm, mimicking the foraging or food source searching behaviour of bees in a bee colony and thisalgorithm is implemented in several applications for an improved optimized outcome. The proposedmethod in this paper includes an improved artificial bee colony algorithm based back-propagation neuralnetwork training method for fast and improved convergence rate of the hybrid neural network learningmethod. The result is analysed with the genetic algorithm based back-propagation method, and it isanother hybridized procedure of its kind. Analysis is performed over standard data sets, reflecting the lightof efficiency of proposed method in terms of convergence speed and rate.
Directory of Open Access Journals (Sweden)
I Gede Sujana Eka Putra
2014-12-01
Full Text Available Kepribadian dapat diidentifikasi melalui analisis pola sidik jari. Pengenalan kepribadian umumnyamenggunakan uji psikometri melalui serangkaian tahapan yang relatif panjang. Melalui analisis pola sidik jari, dapatdiidentifikasi kepribadian secara lebih efisien. Penelitian ini mengajukan algoritma klasifikasi Fuzzy LearningVector Quantization (Fuzzy LVQ karena waktu komputasi yang lebih cepat dan tingkat pengenalan yang tinggi, dandengan metode Fuzzy Backpropagation yang mampu menyelesaikan model data non linier. Tahapan penelitianterdiri dari akuisisi dan klasifikasi. Tahapan pertama melalui akuisisi sidik jari, ekstraksi fitur, proses pelatihan, danpre-klasifikasi. Selanjutnya tahap klasifikasi, melalui klasifikasi fitur sidik jari uji menggunakan algoritma FuzzyLVQ, dibandingkan dengan Fuzzy Backpropagation. Kepribadian diidentifikasi melalui pola hasil klasifikasimenggunakan basis pengetahuan dermatoglyphics. Unjuk kerja diukur dari pencocokan pola hasil pre-klasifikasidan hasil klasifikasi. Hasil penelitian menunjukkan klasifikasi Fuzzy LVQ tingkat kecocokan tertinggi 93,78%dengan iterasi pelatihan maksimum=100 epoh pada target error 10-6. Sedangkan Fuzzy Backpropagation dengantingkat kecocokan tertinggi 93,30% dengan iterasi maksimum diatas 1000 epoh pada target error 10-3. Hal inimenunjukkan Fuzzy LVQ memiliki unjuk kerja lebih baik dibandingkan Fuzzy Backpropagation. Survey respondendilakukan untuk menguji kesesuaian analisa kepribadian sistem dibandingkan dengan kepribadian responden, danhasil survey menunjukkan analisa kepribadian sistem sebagian besar cocok dengan kepribadian responden.
Self-Organized Robust Principal Component Analysis by Back-Propagation Learning
樋口, 勇夫
2004-01-01
The purpose of this study is the suggestion of a self-organized back-propagation algorithm for robust principal component analysis. The self-organizing algorithm that discriminates the influence of data automatically is applied to learning of a sandglass type neural network.
Alfina, Ommi
2012-01-01
As one of the information processing systems, artificial neural networks (ANN) which resembles biological neural networks has grown rapidly. One application of artificial neural networks is in the field of biology which to categorize plant species. In order to determine the species of a plant, one usually looks at its flowers or its leaves. In this research, two artificial neural networks (ANN) methods which are backpropagation and simple perceptron are applied separately in order to evalua...
Assembly Quality Prediction Based on Back-propagation Artificial Neural Network
Directory of Open Access Journals (Sweden)
He Yong-yi
2013-07-01
Full Text Available Because of the severe geometrical distortion induced by the optical system and the limited kinetic accuracy of mechanical system in the vision-based mobile-phone lens’s assembly system, the nonlinear, perspective distortion errors and the kinematics errors generally exist in the assembly process of the mobile-phone lens. It is necessary to predict the assembly quality of the vision-based mobile-phone lens’s pick-and-place system so as to eliminate the immediate effect on the assembling process before extracting quantitative assembling. Comparison with current research methods, the back-propagation artificial neural network is applied to predict the assembly quality of the vision-based mobile-phone lens’s pick-and-place system. Firstly, the mobile-phone lens’s assembly quality characteristics are defined and sampled; Secondly, a back-propagation artificial neural network of the mobile-phone lens’s assembly quality prediction is presented; Finally apply some training samples obtained from the experiments to train and test this back-propagation artificial neural network. The results show that the proposed method is effective to predict the assembly quality of the vision-based mobile-phone lens’s pick-and-place system with high accuracy and high reliability.
A Selective Dynamic Sampling Back-Propagation Approach for Handling the Two-Class Imbalance Problem
Directory of Open Access Journals (Sweden)
Roberto Alejo
2016-07-01
Full Text Available In this work, we developed a Selective Dynamic Sampling Approach (SDSA to deal with the class imbalance problem. It is based on the idea of using only the most appropriate samples during the neural network training stage. The “average samples”are the best to train the neural network, they are neither hard, nor easy to learn, and they could improve the classifier performance. The experimental results show that the proposed method is a successful method to deal with the two-class imbalance problem. It is very competitive with respect to well-known over-sampling approaches and dynamic sampling approaches, even often outperforming the under-sampling and standard back-propagation methods. SDSA is a very simple method for automatically selecting the most appropriate samples (average samples during the training of the back-propagation, and it is very efficient. In the training stage, SDSA uses significantly fewer samples than the popular over-sampling approaches and even than the standard back-propagation trained with the original dataset.
Diagnosing coronary artery disease with a backpropagation neural network: Lessons learned
Energy Technology Data Exchange (ETDEWEB)
Turner, D.D. [Pacific Northwest Lab., Richland, WA (United States); Holmes, E.R. [Sacred Heart Medical Center, Spokane, WA (United States)
1995-12-31
The SPECT (single photon emitted computed tomography) procedure, while widely used for diagnosing coronary artery disease, is not a perfect technology. We have investigated using a backpropagation neural network to diagnose patients suffering from coronary artery disease that is independent from the SPECT procedure. The raw thallium-201 scintigrams produced before the SPECT tomographic reconstruction were used as input patterns for the backpropagation neural network, and the diagnoses resulting mainly from cardiac catheterization as the desired outputs for each pattern. Several preprocessing techniques were applied to the scintigrams, in an attempt to improve the information to noise ratio. After using the a procedure that extracted a subimage containing the heart from each scintigram, we used a data reduction technique, thereby encoding the scintigram in 12 values, which were the inputs to the backpropagation neural network. The network was then trained. This network per-formed superbly for patients suffering from inferolateral disease (classifying 10 out of 10 correctly), but performance was less than optimal for cases involving other coronary zones. While the scope of this project was limited to diagnosing coronary artery disease, this initial work can be extended to other medical imaging procedures, such as diagnosing breast cancer from a mammogram and evaluating lung perfusion studies.
Scanner color management model based on improved back-propagation neural network
Institute of Scientific and Technical Information of China (English)
Xinwu Li
2008-01-01
Scanner color management is one of the key techniques for color reproduction in information optics.A new scanner color management model is presented based on analyzing rendering principle of scanning objects.In this model,a standard color target is taken as experimental sample.Color blocks in color shade area are used to substitute complete color space to solve the difficulties in selecting experimental color blocks.Immune genetic algorithm is used to correct back-propagation neural network(BPNN)to speed up the convergence of the model.Experimental results show that the model can improve the accuracy of scanner color management.
A constrained backpropagation approach for the adaptive solution of partial differential equations.
Rudd, Keith; Di Muro, Gianluca; Ferrari, Silvia
2014-03-01
This paper presents a constrained backpropagation (CPROP) methodology for solving nonlinear elliptic and parabolic partial differential equations (PDEs) adaptively, subject to changes in the PDE parameters or external forcing. Unlike existing methods based on penalty functions or Lagrange multipliers, CPROP solves the constrained optimization problem associated with training a neural network to approximate the PDE solution by means of direct elimination. As a result, CPROP reduces the dimensionality of the optimization problem, while satisfying the equality constraints associated with the boundary and initial conditions exactly, at every iteration of the algorithm. The effectiveness of this method is demonstrated through several examples, including nonlinear elliptic and parabolic PDEs with changing parameters and nonhomogeneous terms.
Abidin, Zaenal; Anompa, Muhammad Angger; Muhtadan
2013-09-01
Development of Welding Defect Identifiers for application in Radiographic Film by using Gray Level Co-Occurrence Matrix and Back-Propagation. A research on the application development to interpret the welding defects in industrial radiographic films by using neural networks has been conducted. This research is aimed to produce an application that implement the digital image processing, feature extraction and pattern recognition using artificial neural networks. Digital image processing applied in the development is the technique of noise removal using median filter, contrast stretching and image sharpening by Laplacian filter. Method of Grey level co-occurrence matrix (GLCM) is applied to extract features from digital images radiographic films. Back-propagation artificial neural network method is used for defect classification and interpretation of welding defect in radiographic films. The result of this research is an application of back-propagation neural networks with classification results for 60 simulated data with 95% of classification successful rate.
Directory of Open Access Journals (Sweden)
Omaima N. A.
2010-01-01
Full Text Available Problem statement: The problem inherent to any digital image is the large amount of bandwidth required for transmission or storage. This has driven the research area of image compression to develop algorithms that compress images to lower data rates with better quality. Artificial neural networks are becoming attractive in image processing where high computational performance and parallel architectures are required. Approach: In this research, a three layered Backpropagation Neural Network (BPNN was designed for building image compression/decompression system. The Backpropagation neural network algorithm (BP was used for training the designed BPNN. Many techniques were used to speed up and improve this algorithm by using different BPNN architecture and different values of learning rate and momentum variables. Results: Experiments had been achieved, the results obtained, such as Compression Ratio (CR and peak signal to noise ratio (PSNR are compared with the performance of BP with different BPNN architecture and different learning parameters. The efficiency of the designed BPNN comes from reducing the chance of error occurring during the compressed image transmission through analog or digital channel. Conclusion: The performance of the designed BPNN image compression system can be increased by modifying the network itself, learning parameters and weights. Practically, we can note that the BPNN has the ability to compress untrained images but not in the same performance of the trained images.
Energy Technology Data Exchange (ETDEWEB)
Kerr, J.P.
1992-01-01
The objective of this study was to determine the feasibility of using an Artificial Neural Network (ANN), in particular a backpropagation ANN, to improve the speed and quality of the reconstruction of three-dimensional SPECT (single photon emission computed tomography) images. In addition, since the processing elements (PE)s in each layer of an ANN are independent of each other, the speed and efficiency of the neural network architecture could be better optimized by implementing the ANN on a massively parallel computer. The specific goals of this research were: to implement a fully interconnected backpropagation neural network on a serial computer and a SIMD parallel computer, to identify any reduction in the time required to train these networks on the parallel machine versus the serial machine, to determine if these neural networks can learn to recognize SPECT data by training them on a section of an actual SPECT image, and to determine from the knowledge obtained in this research if full SPECT image reconstruction by an ANN implemented on a parallel computer is feasible both in time required to train the network, and in quality of the images reconstructed.
Energy Technology Data Exchange (ETDEWEB)
Kerr, J.P.
1992-12-31
The objective of this study was to determine the feasibility of using an Artificial Neural Network (ANN), in particular a backpropagation ANN, to improve the speed and quality of the reconstruction of three-dimensional SPECT (single photon emission computed tomography) images. In addition, since the processing elements (PE)s in each layer of an ANN are independent of each other, the speed and efficiency of the neural network architecture could be better optimized by implementing the ANN on a massively parallel computer. The specific goals of this research were: to implement a fully interconnected backpropagation neural network on a serial computer and a SIMD parallel computer, to identify any reduction in the time required to train these networks on the parallel machine versus the serial machine, to determine if these neural networks can learn to recognize SPECT data by training them on a section of an actual SPECT image, and to determine from the knowledge obtained in this research if full SPECT image reconstruction by an ANN implemented on a parallel computer is feasible both in time required to train the network, and in quality of the images reconstructed.
Parallel implementation of backpropagation neural networks on a heterogeneous array of transputers.
Foo, S K; Saratchandran, P; Sundararajan, N
1997-01-01
This paper analyzes parallel implementation of the backpropagation training algorithm on a heterogeneous transputer network (i.e., transputers of different speed and memory) connected in a pipelined ring topology. Training-set parallelism is employed as the parallelizing paradigm for the backpropagation algorithm. It is shown through analysis that finding the optimal allocation of the training patterns amongst the processors to minimize the time for a training epoch is a mixed integer programming problem. Using mixed integer programming optimal pattern allocations for heterogeneous processor networks having a mixture of T805-20 (20 MHz) and T805-25 (25 MHz) transputers are theoretically found for two benchmark problems. The time for an epoch corresponding to the optimal pattern allocations is then obtained experimentally for the benchmark problems from the T805-20, TS805-25 heterogeneous networks. A Monte Carlo simulation study is carried out to statistically verify the optimality of the epoch time obtained from the mixed integer programming based allocations. In this study pattern allocations are randomly generated and the corresponding time for an epoch is experimentally obtained from the heterogeneous network. The mean and standard deviation for the epoch times from the random allocations are then compared with the optimal epoch time. The results show the optimal epoch time to be always lower than the mean epoch times by more than three standard deviations (3sigma) for all the sample sizes used in the study thus giving validity to the theoretical analysis.
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.
Directory of Open Access Journals (Sweden)
Ikhthison Mekongga
2014-02-01
Full Text Available The need for bandwidth has been increasing recently. This is because the development of internet infrastructure is also increasing so that we need an economic and efficient provider system. This can be achieved through good planning and a proper system. The prediction of the bandwidth consumption is one of the factors that support the planning for an efficient internet service provider system. Bandwidth consumption is predicted using ANN. ANN is an information processing system which has similar characteristics as the biologic al neural network. ANN is chosen to predict the consumption of the bandwidth because ANN has good approachability to non-linearity. The variable used in ANN is the historical load data. A bandwidth consumption information system was built using neural networks with a backpropagation algorithm to make the use of bandwidth more efficient in the future both in the rental rate of the bandwidth and in the usage of the bandwidth.Keywords: Forecasting, Bandwidth, Backpropagation
Institute of Scientific and Technical Information of China (English)
无
2007-01-01
Back-propagation neural network was applied to predict and optimize the synthetic technology of 2-chloro-4,6-dinitroresorcinol. A model was established based on back-propagation neural network using the experimental data of homogeneous design as the training sample set and the technological parameters were optimized by it. The optimal technological parameters are as follows: the reaction time is 4h, the rewere performed and the average yield of 2-chloro-4,6-dinitroresorcinol is 96.64%, the absolute error of it with the predicted value is - 1.07 %.
Goldberg, Jesse H; Tamas, Gabor; Yuste, Rafael
2003-01-01
GABAergic interneurones are essential in cortical processing, yet the functional properties of their dendrites are still poorly understood. In this first study, we combined two-photon calcium imaging with whole-cell recording and anatomical reconstructions to examine the calcium dynamics during action potential (AP) backpropagation in three types of V1 supragranular interneurones: parvalbumin-positive fast spikers (FS), calretinin-positive irregular spikers (IS), and adapting cells (AD). Somatically generated APs actively backpropagated into the dendritic tree and evoked instantaneous calcium accumulations. Although voltage-gated calcium channels were expressed throughout the dendritic arbor, calcium signals during backpropagation of both single APs and AP trains were restricted to proximal dendrites. This spatial control of AP backpropagation was mediated by Ia-type potassium currents and could be mitigated by by previous synaptic activity. Further, we observed supralinear summation of calcium signals in synaptically activated dendritic compartments. Together, these findings indicate that in interneurons, dendritic AP propagation is synaptically regulated. We propose that interneurones have a perisomatic and a distal dendritic functional compartment, with different integrative functions. PMID:12844506
Nonlinear inverse modeling of sensor based on back-propagation fuzzy logical system
Institute of Scientific and Technical Information of China (English)
Li Jun; Liu Junhua
2007-01-01
Objective To correct the nonlinear error of sensor output, a new approach to sensor inverse modeling based on Back-Propagation Fuzzy Logical System (BP FS) is presented. Methods The BP FS is a computationally efficient nonlinear universal approximator, which is capable of implementing complex nonlinear mapping from its input pattern space to the output with fast convergence speed. Results The neuro-fuzzy hybrid system, i.e. BP FS, is then applied to construct nonlinear inverse model of pressure sensor. The experimental results show that the proposed inverse modeling method automatically compensates the associated nonlinear error in pressure estimation, and thus the performance of pressure sensor is significantly improved. Conclusion The proposed method can be widely used in nonlinearity correction of various kinds of sensors to compensate the effects of nonlinearity and temperature on sensor output.
Back-Propagation Artificial Neural Networks for Water Supply Pipeline Model
Institute of Scientific and Technical Information of China (English)
朱东海; 张土乔; 毛根海
2002-01-01
Water supply pipelines are the lifelines of a city. When pipelines burst, the burst site is difficult to locate by traditional methods such as manual tools or only by watching. In this paper, the burst site was identified using back-propagation (BP) artificial neural networks (ANN). The study is based on an indoor urban water supply model experiment. The key to appling BP ANN is to optimize the ANN's topological structure and learning parameters. This paper presents the optimizing method for a 3-layer BP neural network's topological structure and its learning parameters-learning ratio and the momentum factor. The indoor water supply pipeline model experimental results show that BP ANNs can be used to locate the burst point in urban water supply systems. The topological structure and learning parameters were optimized using the experimental results.
Directory of Open Access Journals (Sweden)
Suhendry Effendy
2010-11-01
artificial neural network. Discrete Wavelet Transform processes the input image to obtain the essential features found on the face image. These features are then classified using an back-propagation artificial neural network for the input image to be identified. Testing the system using facial images in AT & T Database of Faces of 400 images comprising 40 facial images of individuals and web-camera catches as many as 100 images of 10 individuals. The accuracy of level of recognition on AT & T Database of Faces reaches 93.5%, while the accuracy of level of recognition on a web-camera capture images up to 96%. Testing is also done on image of AT & T Database of Faces with given noise. Apparently the noise in the image does not give meaningful effect on the level of recognition accuracy.
Prediction of the breakdown voltage of transformer oil based on a backpropagation network
Energy Technology Data Exchange (ETDEWEB)
Cao Shun' an; Li Rui; Sheng Kai [Wuhan Univ., Hubei Province (China). Dept. of Water Quality Engineering
2008-03-15
Prediction of the breakdown voltage of transformer oil facilitates the early fault diagnosis of transformers, and provides a scientific basis for the prevention of faults in transformer oil. In this paper, based on the correlation between performance parameters of transformer oil, along with the excellent fault-tolerant ability, prominent non-linear approximation capability and self-learning capacity of backpropagation (BP) networks, a BP network with a BP algorithm and a BP network with an improved BP algorithm are developed to simulate the correlation between breakdown voltage and four relevant parameters, using the monitoring data of transformer oil. The results show that the latter algorithm gives more accurate predicted values, which proves to be of high application value. (orig.)
Directory of Open Access Journals (Sweden)
Attariuas Hicham
2012-12-01
Full Text Available ales forecasting is one of the most crucial issues addressed in business. Control and evaluation of future sales still seem concerned both researchers and policy makers and managers of companies. this research propose an intelligent hybrid sales forecasting system Delphi-FCBPN sales forecast based on Delphi Method, fuzzy clustering and Back-propagation (BP Neural Networks with adaptive learning rate. The proposed model is constructed to integrate expert judgments, using Delphi method, in enhancing the model of FCBPN. Winter’s Exponential Smoothing method will be utilized to take the trend effect into consideration. The data for this search come from an industrial company that manufactures packaging. Analyze of results show that the proposed model outperforms other three different forecasting models in MAPE and RMSE measures.
Application of the Backpropagation Neural Network Method in Designing Tungsten Heavy Alloy
Institute of Scientific and Technical Information of China (English)
ZHANG Zhao-hui; WANG Wei-jie; WANG Fu-chi; LI Shu-kui
2006-01-01
The model describing the dependence of the mechanical properties on the chemical composition and as deformation techniques of tungsten heavy alloy is established by the method of improved the backpropagation neural network. The mechanical properties' parameters of tungsten alloy and deformation techniques for tungsten alloy are used as the inputs. The chemical composition and deformation amount of tungsten alloy are used as the outputs. Then they are used for training the neural network. At the same time,the optimal number of the hidden neurons is obtained through the experiential equations,and the varied step learning method is adopted to ensure the stability of the training process. According to the requirements for mechanical properties,the chemical composition and the deformation condition for tungsten heavy alloy can be designed by this artificial neural network system.
Institute of Scientific and Technical Information of China (English)
Yingwei LI; Bingguo LIU; Jinhui PENG; Wei LI; Daifu HUANG; Libo ZHANG
2011-01-01
The incremental improved Back-Propagation (BP) neural network prediction model using the Levenberg-Marquardt algorithm based on optimizing theory is put forward,which can solve the problems existing in the process of calcinations for ammonium diuranate (ADU) by microwave heating,such as long testing cycle,high testing quantity,difficulty of optimization for process parameters. Many training data probably were offered by the way of increment batch and the limitation of the system memory could make the training data infeasible when the sample scale was large. The prediction model of the nonlinear system is built,which can effectively predict the experiment of microwave calcining of ADU,and the incremental improved BP neural network is very useful in overcoming the local minimum problem,finding the global optinal solution and accelerating the convergence speed.
The Performance of EEG-P300 Classification using Backpropagation Neural Networks
Directory of Open Access Journals (Sweden)
Arjon Turnip
2013-12-01
Full Text Available Electroencephalogram (EEG recordings signal provide an important function of brain-computer communication, but the accuracy of their classification is very limited in unforeseeable signal variations relating to artifacts. In this paper, we propose a classification method entailing time-series EEG-P300 signals using backpropagation neural networks to predict the qualitative properties of a subject’s mental tasks by extracting useful information from the highly multivariate non-invasive recordings of brain activity. To test the improvement in the EEG-P300 classification performance (i.e., classification accuracy and transfer rate with the proposed method, comparative experiments were conducted using Bayesian Linear Discriminant Analysis (BLDA. Finally, the result of the experiment showed that the average of the classification accuracy was 97% and the maximum improvement of the average transfer rate is 42.4%, indicating the considerable potential of the using of EEG-P300 for the continuous classification of mental tasks.
A theory of local learning, the learning channel, and the optimality of backpropagation.
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
Directory of Open Access Journals (Sweden)
Tummala Pradeep
2011-11-01
Full Text Available This paper investigates the use of variable learning rate back-propagation algorithm and Levenberg-Marquardt back-propagation algorithm in Intrusion detection system for detecting attacks. Inthe present study, these 2 neural network (NN algorithms are compared according to their speed,accuracy and, performance using mean squared error (MSE (Closer the value of MSE to 0, higher willbe the performance. Based on the study and test results, the Levenberg-Marquardt algorithm has been found to be faster and having more accuracy and performance than variable learning rate backpropagation algorithm.
Directory of Open Access Journals (Sweden)
Didi Supriyadi
2014-01-01
Full Text Available Dengue disease is a major health problem and endemic in several countries including Indonesia. Indonesia is included in the category "A" in the stratification of DHF by WHO in 2001 which indicates the high rate of treatment in hospital and deaths from dengue. The purpose of this study was to investigate the ability of artificial neural networks Backpropagation method for information of the spread of dengue fever in a region. In this study uses six input variables which are environmental factors that influence the spread of dengue fever, include average temperature - average, rainfall, number of rainy days, the population density, sea surface height, and the percentage of larvae-free number for which data is sourced from BMKG, BPS and the Public Health Service. Network architecture applied to a multilayer network that uses an input with 6 neurons, one hidden lay er and an output with the output neuron is one. From the results obtained by training the best network architecture is the number one hidden layer with the number of neurons obtained a total of 110 neurons and also the system can recognize the entire training data. The best training algorithm using a variable learning rate and momentum of 0.9 by 0.6 by the end of the training MSE 0.000999879. in the process of testing using test data obtained 17 tissue levels of approximately 88.23% accuracy. Therefore we can conclude that the network is implemented in this study when subjected to the test data other then the error rate of about 11.77%.Keywords : Artificial Neural Networks; Backpropagation; Dengue fever
Directory of Open Access Journals (Sweden)
Nugroho Nugroho
2012-01-01
Full Text Available The research on image identification has been conducted to identify the type of beef. The research is aimed to compare the performance of artificial neural network of backpropagation and general regression neural network model in identifying the type of meat. Image management is processed by counting R, G and B value in every meat image, and normalization process is then carried out by obtaining R, G, and B index value which is then converted from RGB model to HSI model to obtain the value of hue, saturation and intensity. The resulting value of image processing will be used as input parameter of training and validation programs. The performance of G RNN model is more accurate than the backpropagation with accuracy ratio by 51%.Keyword: Identification; Backpropagation; GRNN
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.
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
A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification
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.
Automatic Selection of Open Source Multimedia Softwares Using Error Back-Propagation Neural Network
Directory of Open Access Journals (Sweden)
Deepika
2015-07-01
Full Text Available Open source opens a new era to provide license of the software for the user at free of cost which is advantage over paid licensed software. In Multimedia applications there are many versions of software are available and there is a problem for the user to select compatible software for their own system. Most of the time while surfing for software a huge list of software opens in response. The selection of particular software which is pretty suitable for the system from a real big list is the biggest challenge that is faced by the users. This work has been done that focuses on the existing open source software that are widely used and to design an automatic system for selection of particular open source software according to the compatibility of users own system. In this work, error back-propagation based neural network is designed in MATLAB for automatic selection of open source software. The system provides the open source software name after taking the information from user. Regression coefficient of 0.93877 is obtained and the results shown are up to the mark and can be utilized for the fast and effective software search.
Energy Technology Data Exchange (ETDEWEB)
Saini, Lalit Mohan [Department of Electrical Engineering, National Institute of Technology, Kurukshetra, Haryana 136119 (India)
2008-07-15
Up to 7 days ahead electrical peak load forecasting has been done using feed forward neural network based on Steepest descent, Bayesian regularization, Resilient and adaptive backpropagation learning methods, by incorporating the effect of eleven weather parameters and past peak load information. To avoid trapping of network into a state of local minima, the optimization of user-defined parameters viz., learning rate and error goal has been performed. The sliding window concept has been incorporated for selection of training data set. It was then reduced as per relevant selection according to the day type and season for which the forecast is made. To reduce the dimensionality of input matrix, the Principal Component Analysis method of factor extraction or correlation analysis technique has been used and their performance has been compared. The resultant data set was used for training of three-layered neural network. In order to increase the learning speed, the weights and biases were initialized according to Nguyen and Widrow method. To avoid over fitting, early stopping of training was done at the minimum validation error. (author)
Class of backpropagation techniques for limited-angle reconstruction in microwave tomography
Energy Technology Data Exchange (ETDEWEB)
Paladhi, P. Roy; Tayebi, A.; Udpa, L.; Udpa, S. [Non-destructive Evaluation Lab, Dept. of Electrical and Computer Engineering, College of Engineering, Michigan State University, Lansing, MI 48824-1226 (United States); Sinha, A. [Department of Statistics and Probability, Michigan State University, East Lansing, MI 48824 (United States)
2015-03-31
Filtered backpropagation (FBPP) is a well-known technique used in Diffraction Tomography (DT). For accurate reconstruction using FBPP, full 360° angular coverage is necessary. However, it has been shown that using some inherent redundancies in the projection data in a tomographic setup, accurate reconstruction is still possible with 270° coverage which is called the minimal-scan angle range. This can be done by applying weighing functions (or filters) on projection data of the object to eliminate the redundancies and accurately reconstruct the image from 270° coverage. This paper demonstrates procedures to generate many general classes of these weighing filters. These are all equivalent at 270° coverage but vary in performance at lower angular coverages and in presence of noise. This paper does a comparative analysis of different filters when angular coverage is lower than minimal-scan angle of 270°. Simulation studies have been done to find optimum weight filters for sub-minimal angular coverage (<270°)
Parallelizing Backpropagation Neural Network Using MapReduce and Cascading Model.
Liu, Yang; Jing, Weizhe; Xu, Lixiong
2016-01-01
Artificial Neural Network (ANN) is a widely used algorithm in pattern recognition, classification, and prediction fields. Among a number of neural networks, backpropagation neural network (BPNN) has become the most famous one due to its remarkable function approximation ability. However, a standard BPNN frequently employs a large number of sum and sigmoid calculations, which may result in low efficiency in dealing with large volume of data. Therefore to parallelize BPNN using distributed computing technologies is an effective way to improve the algorithm performance in terms of efficiency. However, traditional parallelization may lead to accuracy loss. Although several complements have been done, it is still difficult to find out a compromise between efficiency and precision. This paper presents a parallelized BPNN based on MapReduce computing model which supplies advanced features including fault tolerance, data replication, and load balancing. And also to improve the algorithm performance in terms of precision, this paper creates a cascading model based classification approach, which helps to refine the classification results. The experimental results indicate that the presented parallelized BPNN is able to offer high efficiency whilst maintaining excellent precision in enabling large-scale machine learning.
Parallelizing Backpropagation Neural Network Using MapReduce and Cascading Model
Directory of Open Access Journals (Sweden)
Yang Liu
2016-01-01
Full Text Available Artificial Neural Network (ANN is a widely used algorithm in pattern recognition, classification, and prediction fields. Among a number of neural networks, backpropagation neural network (BPNN has become the most famous one due to its remarkable function approximation ability. However, a standard BPNN frequently employs a large number of sum and sigmoid calculations, which may result in low efficiency in dealing with large volume of data. Therefore to parallelize BPNN using distributed computing technologies is an effective way to improve the algorithm performance in terms of efficiency. However, traditional parallelization may lead to accuracy loss. Although several complements have been done, it is still difficult to find out a compromise between efficiency and precision. This paper presents a parallelized BPNN based on MapReduce computing model which supplies advanced features including fault tolerance, data replication, and load balancing. And also to improve the algorithm performance in terms of precision, this paper creates a cascading model based classification approach, which helps to refine the classification results. The experimental results indicate that the presented parallelized BPNN is able to offer high efficiency whilst maintaining excellent precision in enabling large-scale machine learning.
A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification.
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.
Institute of Scientific and Technical Information of China (English)
FENG Yerong; David H.KITZMILLER
2006-01-01
A back-propagation neural network (BPNN) was used to establish relationships between the shortrange (0-3-h) rainfall and the predictors ranging from extrapolative forecasts of radar reflectivity, satelliteestimated cloud-top temperature, lightning strike rates, and Nested Grid Model (NGM) outputs. Quantitative precipitation forecasts (QPF) and the probabilities of categorical precipitation were obtained.Results of the BPNN algorithm were compared to the results obtained from the multiple linear regression algorithm for an independent dataset from the 1999 warm season over the continental United States. A sample forecast was made over the southeastern United States. Results showed that the BPNN categorical rainfall forecasts agreed well with Stage Ⅲ observations in terms of the size and shape of the area of rainfall. The BPNN tended to over-forecast the spatial extent of heavier rainfall amounts, but the positioning of the areas with rainfall ≥25.4 mm was still generally accurate. It appeared that the BPNN and linear regression approaches produce forecasts of very similar quality, although in some respects BPNN slightly outperformed the regression.
Forest Fire Smoke Detection Using Back-Propagation Neural Network Based on MODIS Data
Directory of Open Access Journals (Sweden)
Xiaolian Li
2015-04-01
Full Text Available Satellite remote sensing provides global observations of the Earth’s surface and provides useful information for monitoring smoke plumes emitted from forest fires. The aim of this study is to automatically separate smoke plumes from the background by analyzing the MODIS data. An identification algorithm was improved based on the spectral analysis among the smoke, cloud and underlying surface. In order to get satisfactory results, a multi-threshold method is used for extracting training sample sets to train back-propagation neural network (BPNN classification for merging the smoke detection algorithm. The MODIS data from three forest fires were used to develop the algorithm and get parameter values. These fires occurred in (i China on 16 October 2004, (ii Northeast Asia on 29 April 2009 and (iii Russia on 29 July 2010 in different seasons. Then, the data from four other fires were used to validate the algorithm. Results indicated that the algorithm captured both thick smoke and thin dispersed smoke over land, as well as the mixed pixels of smoke over the ocean. These results could provide valuable information concerning forest fire location, fire spreading and so on.
Institute of Scientific and Technical Information of China (English)
WU Shun-chuan(吴顺川); ZHANG You-pa(张友葩); GAO Yong-tao(高永涛)
2003-01-01
Taking the practical reinforced engineering of a reinforced soil retaining wall as an example, which located in Shandong Province and set on 104 national highway, the stress-spread behaviors of the anchor bars in the preforced proceeding were tested. According to the test data, and by use of the update backpropagation (BP) algorithm neural network(NN), the test method and it's mechanism were studied by the network, then the learning results show the mean square error(MSE) only at the 2.55% level, and the proof-testing results show the MSE at 4.38% level (the main aim is to build a NN directly from the in-situ test results (the learning phase)). Ipso-facto, the learning and adjustment abilities of the NN permit us to develop the test data, subsequently, 36 test data were acquired from the NN. By use of the provide data, as well as the failure situation and carried loading capacity of the retaining wall, finally, the choice the reasonable range interval distance of prestress cement grouting anchor bars were carried out, and the result was 2 m×2 m.
Low complexity digital backpropagation for high baud subcarrier-multiplexing systems.
Zhang, Fangyuan; Zhuge, Qunbi; Qiu, Meng; Plant, David V
2016-07-25
In this paper, we propose two modifications to reduce the complexity of the subcarrier-multiplexing (SCM) based digital backpropagation (DBP) for high symbol rate SCM systems. The first one is to reduce the number of interfering subcarriers (RS-SCM-DBP) when evaluating the cross-subcarrier nonlinearity (CSN). The second one is to replace the original frequency domain CSN filters with the infinite impulse response (IIR) filters (IIR-RS-SCM-DBP) in the CSN compensation. The performance of the proposed schemes are numerically evaluated in three-channel dual-polarization (DP) 16QAM wavelength-division multiplexing (WDM) transmissions. The aggregate symbol rate for each channel is 120 GBaud and the transmission distance is 1600 km. For the SCM system with 16 subcarriers, the IIR-RS-SCM-DBP with only 4 interfering subcarriers and 2 steps can achieve a 0.3 dB Q-factor improvement in the WDM transmission. Compared to the original SCM-DBP, the proposed IIR-RS-SCM-DBP reduces the complexity by 48% at a performance loss of only 0.07 dB.
Automatic volcanic ash detection from MODIS observations using a back-propagation neural network
Directory of Open Access Journals (Sweden)
T. M. Gray
2015-08-01
Full Text Available Due to the climate effects and aviation threats of volcanic eruptions, it is important to accurately locate ash in the atmosphere. This study aims to explore the accuracy and reliability of training a neural network to identify cases of ash using observations from the Moderate Resolution Imaging Spectroradiometer (MODIS. Satellite images were obtained for the following eruptions: Kasatochi, Aleutian Islands, 2008; Okmok, Aleutian Islands, 2008; Grímsvötn, northeastern Iceland, 2011; Chaiteìn, southern Chile, 2008; Puyehue-Cordoìn Caulle, central Chile, 2011; Sangeang Api, Indonesia, 2014; and Kelut, Indonesia, 2014. The Hybrid Single Particle Lagrangian Integrated Trajectory Model (HYSPLIT was used to obtain ash concentrations for the same archived eruptions. Two back-propagation neural networks were then trained using brightness temperature differences as inputs obtained via the following band combinations: 12-11, 11-8.6, 11-7.3, and 11 μm. Using the ash concentrations determined via HYSPLIT, flags were created to differentiate between ash (1 and no ash (0 and SO2-rich ash (1 and no SO2-rich ash (0 and used as output. When neural network output was compared to the test dataset, 93 % of pixels containing ash were correctly identified and 7 % were missed. Nearly 100 % of pixels containing SO2-rich ash were correctly identified. The optimal thresholds, determined using Heidke skill scores, for ash retrieval and SO2-rich ash retrieval were 0.48 and 0.47, respectively. The networks show significantly less accuracy in the presence of high water vapor, liquid water, ice, or dust concentrations. Significant errors are also observed at the edge of the MODIS swath.
Directory of Open Access Journals (Sweden)
Mutasem K. Alsmadi
2011-01-01
Full Text Available Problem statement: Image recognition was a challenging problem researchers had been research into this area for so long especially in the recent years, due to distortion, noise, segmentation errors, overlap and occlusion of objects in digital images. In our study, there are many fields concern with pattern recognition, for example, fingerprint verification, face recognition, iris discrimination, chromosome shape discrimination, optical character recognition, texture discrimination and speech recognition, the subject of pattern recognition appears. A system for recognizing isolated pattern of interest may be as an approach for dealing with such application. Scientists and engineers with interests in image processing and pattern recognition have developed various approaches to deal with digital image recognition problems such as, neural network, contour matching and statistics. Approach: In this study, our aim was to recognize an isolated pattern of interest (fish in the image based robust features extraction. Where depend on color signatures that are extracted by RGB color space, color histogram and gray level co-occurrence matrix. Results: We presented a system prototype for dealing with such problem. The system started by acquiring an image containing pattern of fish, then the image segmentation was performed relying on color signature. Our system has been applied on 20 different fish families, each family has a different number of fish types and our sample consists of distinct 610 of fish images. These images are divided into two datasets: 400 training images and 210 testing images. An overall accuracy was obtained using back-propagation classifier was 84% on the test dataset used. Conclusion: We developed a classifier for fish images recognition. We efficiently have chosen an image segmentation method to fit our demands. Our classifier successfully design and implement a decision which performed efficiently without any
Institute of Scientific and Technical Information of China (English)
QIN Zhong; SU Gao-li; YU Qiang; HU Bing-min; LI Jun
2005-01-01
In this work, datasets of water and carbon fluxes measured with eddy covariance technique above a summer maize field in the North China Plain were simulated with artificial neural networks (ANNs) to explore the fluxes responses to local environmental variables. The results showed that photosynthetically active radiation (PAR), vapor pressure deficit (VPD), air temperature (T) and leaf area index (LAI) were primary factors regulating both water vapor and carbon dioxide fluxes. Three-layer back-propagation neural networks (BP) could be applied to model fluxes exchange between cropland surface and atmosphere without using detailed physiological information or specific parameters of the plant.
Directory of Open Access Journals (Sweden)
Attariuas Hicham
2012-11-01
Full Text Available In recent years, there has been a strong tendency by companies to use centralized management systems like Enterprise resource planning (ERP. ERP systems offer a comprehensive and simplified process managements and extensive functional coverage. Sales management module is an important element business management of ERP. This paper describes an intelligent hybrid sales forecasting system ERP-FCBPN sales forecast based on architecture of ERP through Delphi, fuzzy clustering and Back-propagation (BP Neural Networks with adaptive learning rate (FCBPN. The proposed approach is composed of three stages: (1 Stage of data collection: Data collection will be implemented from the fields (attributes existing at the interfaces (Tables the database of the ERP. Collection of Key factors that influence sales be made using the Delphi method; (2 Stage of Data preprocessing: Winter Exponential Smoothing method will be utilized to take the trend effect into consideration. (3 Stage of learning by FCBPN: We use hybrid sales forecasting system based on Delphi, fuzzy clustering and Back-propagation (BP Neural Networks with adaptive learning rate (FCBPN. The data for this study come from an industrial company that manufactures packaging. Experimental results show that the proposed model outperforms the previous and traditional approaches. Therefore, it is a very promising solution for industrial forecasting.
Directory of Open Access Journals (Sweden)
Satyanarayana D
2006-01-01
Full Text Available A chemometric model for the simultaneous estimation of phenobarbitone and phenytoin sodium anticonvulsant tablets using the back-propagation neural network calibration has been presented. The use of calibration datasets constructed from the spectral data of pure components is proposed. The calibration sets were designed such that the concentrations were orthogonal and span the possible mixture space fairly evenly. Spectra of phenobarbitone and phenytoin sodium were recorded at several concentrations within their linear range and used to compute the calibration mixture between wavelengths 220 and 260 nm at an interval of 1 nm. The back-propagation neural network model was optimized using three different sets of calibration and monitoring data for the number of hidden sigmoid neurons. The calibration model was thoroughly evaluated at several concentration levels using spectra obtained for 95 synthetic binary mixtures prepared using orthogonal designs. The optimized model showed sufficient robustness even when the calibration sets were constructed from different sets of pure spectra of components. Although the components showed complete spectral overlap, the model could accurately estimate the drugs, with satisfactory precision and accuracy, in tablet dosage with no interference from excipients, as indicated by the recovery study results.
Directory of Open Access Journals (Sweden)
Yi-jun Liu
2015-12-01
Full Text Available Childhood nephrotic syndrome is a chronic disease harmful to growth of children. Scientific and accurate prediction of negative conversion days for children with nephrotic syndrome offers potential benefits for treatment of patients and helps achieve better cure effect. In this study, the improved backpropagation neural network with momentum is used for prediction. Momentum speeds up convergence and maintains the generalization performance of the neural network, and therefore overcomes weaknesses of the standard backpropagation algorithm. The three-tier network structure is constructed. Eight indicators including age, lgG, lgA and lgM, etc. are selected for network inputs. The scientific computing software of MATLAB and its neural network tools are used to create model and predict. The training sample of twenty-eight cases is used to train the neural network. The test sample of six typical cases belonging to six different age groups respectively is used to test the predictive model. The low mean absolute error of predictive results is achieved at 0.83. The experimental results of the small-size sample show that the proposed approach is to some degree applicable for the prediction of negative conversion days of childhood nephrotic syndrome.
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.
Directory of Open Access Journals (Sweden)
Li Honglian
2013-07-01
Full Text Available It is difficult to accurately reckon vehicle position for vehicle navigation system (VNS during GPS outages, a novel prediction algorithm of dead reckon (DR position error is put forward, which based on Bayesian regularization back-propagation (BRBP neural network. DR, GPS position data are first de-noised and compared at different stationary wavelet transformation (SWT decomposition level, and DR position error data are acquired after the SWT coefficients differences are reconstructed. A neural network to mimic position error property is trained with back-propagation algorithm, and the algorithm is improved for improving its generalization by Bayesian regularization theory. During GPS outages, the established prediction algorithm predictes DR position errors, and provides precise position for VNS through DR position error data updating DR position data. The simulation results show the positioning precision of the BRBP algorithm is best among the presented prediction algorithms such as simple DR and adaptive linear network, and a precise mathematical model of navigation sensors isn’t established.
Directory of Open Access Journals (Sweden)
Bahman O. Taha
2015-06-01
Full Text Available The reinforced concrete with fiber reinforced polymer (FRP bars (carbon, aramid, basalt and glass is used in places where a high ratio of strength to weight is required and corrosion is not acceptable. Behavior of structural members using (FRP bars is hard to be modeled using traditional methods because of the high non-linearity relationship among factors influencing the strength of structural members. Back-propagation neural network is a very effective method for modeling such complicated relationships. In this paper, back-propagation neural network is used for modeling the flexural behavior of beams reinforced with (FRP bars. 101 samples of beams reinforced with fiber bars were collected from literatures. Five important factors are taken in consideration for predicting the strength of beams. Two models of Multilayer Perceptron (MLP are created, first with single-hidden layer and the second with two-hidden layers. The two-hidden layer model showed better accuracy ratio than the single-hidden layer model. Parametric study has been done for two-hidden layer model only. Equations are derived to be used instead of the model and the importance of input factors is determined. Results showed that the neural network is successful in modeling the behavior of concrete beams reinforced with different types of (FRP bars.
DEFF Research Database (Denmark)
Porto da Silva, Edson; Yankov, Metodi Plamenov; Da Ros, Francesco;
2016-01-01
Gains in achievable information rates from probabilistic shaping and digital backpropagation are compared for WDM transmission of 5 × 10 GBd DP-256QAM/1024QAM up to 1700 km of reach. The combination of both techniques its shown to provide gains of up to ∼0.5 bits/QAM symbol...
Directory of Open Access Journals (Sweden)
Lin Liu
2010-01-01
Full Text Available Cognitive radio (CR is a technology to implement opportunistic spectrum sharing to improve the spectrum utilization. However, there exists a hidden-node problem, which can be a big challenge to solve especially when the primary receiver is passive listening. We aim to provide a solution to the hidden-node problem for passive-listening receiver based on cooperation of multiple CRs. Specifically, we consider a cooperative GPS-enabled cognitive network. Once the existence of PU is detected, a localization algorithm will be employed to first estimate the path loss model for the environment based on backpropagation method and then to locate the position of PU. Finally, a disable region is identified taking into account the communication range of both the PU and the CR. The CRs within the disabled region are prohibited to transmit in order to avoid interfering with the primary receiver. Both analysis and simulation results are provided.
Institute of Scientific and Technical Information of China (English)
GUO Zhongyang; DAI Xiaoyan; LI Xiaodong; YE Shufeng
2013-01-01
To reduce typhoon-caused damages,numerical and empirical methods are often used to forecast typhoon storm surge.However,typhoon surge is a complex nonlinear process that is difficult to forecast accurately.We applied a principal component back-propagation neural network (PCBPNN) to predict the deviation in typhoon storm surge,in which data of the typhoon,upstream flood,and historical case studies were involved.With principal component analysis,15 input factors were reduced to five principal components,and the application of the model was improved.Observation data from Huangpu Park in Shanghai,China were used to test the feasibility of the model.The results indicate that the model is capable of predicting a 12-hour warning before a typhoon surge.
Tang, Chen; Lu, Wenjing; Chen, Song; Zhang, Zhen; Li, Botao; Wang, Wenping; Han, Lin
2007-10-20
We extend and refine previous work [Appl. Opt. 46, 2907 (2007)]. Combining the coupled nonlinear partial differential equations (PDEs) denoising model with the ordinary differential equations enhancement method, we propose the new denoising and enhancing model for electronic speckle pattern interferometry (ESPI) fringe patterns. Meanwhile, we propose the backpropagation neural networks (BPNN) method to obtain unwrapped phase values based on a skeleton map instead of traditional interpolations. We test the introduced methods on the computer-simulated speckle ESPI fringe patterns and experimentally obtained fringe pattern, respectively. The experimental results show that the coupled nonlinear PDEs denoising model is capable of effectively removing noise, and the unwrapped phase values obtained by the BPNN method are much more accurate than those obtained by the well-known traditional interpolation. In addition, the accuracy of the BPNN method is adjustable by changing the parameters of networks such as the number of neurons.
Directory of Open Access Journals (Sweden)
Turner Stephen D
2010-09-01
Full Text Available Abstract 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
Gupta, Vinod Kumar; Khani, Hadi; Ahmadi-Roudi, Behzad; Mirakhorli, Shima; Fereyduni, Ehsan; Agarwal, Shilpi
2011-01-15
Quantitative structure-retention relationship (QSRR) models correlating the retention times of fatty acid methyl esters in high resolution capillary gas chromatography and their structures were developed based on non-linear and linear modeling methods. Genetic algorithm (GA) was used for the selection of the variables that resulted in the best-fitted models. Gravitational index (G2), number of cis double bond (NcDB) and number of trans double bond (NtDB) were selected among a large number of descriptors. The selected descriptors were considered as inputs for artificial neural networks (ANNs) with three different weights update functions including Levenberg-Marquardt backpropagation network (LM-ANN), BFGS (Broyden, Fletcher, Goldfarb, and Shanno) quasi-Newton backpropagation (BFG-ANN) and conjugate gradient backpropagation with Polak-Ribiére updates (CGP-ANN). Computational result indicates that the LM-ANN method has better predictive power than the other methods. The model was also tested successfully for external validation criteria. Standard error for the training set using LM-ANN was SE=0.932 with correlation coefficient R=0.996. For the prediction and validation sets, standard error was SE=0.645 and SE=0.445 and correlation coefficient was R=0.999 and R=0.999, respectively. The accuracy of 3-2-1 LM-ANN model was illustrated using leave multiple out-cross validations (LMO-CVs) and Y-randomization.
Indian Academy of Sciences (India)
S Traore; Y M Wang; W G Chung
2014-03-01
The present study evaluates the predictive accuracy of the feed forward backpropagation artificial neural network (BP) in evapotranspiration forecasting from temperature data basis in Dédougou region located in western Burkina Faso, sub-Saharan Africa. BP accuracy is compared to the conventional Blaney–Criddle (BCR) and Reference Model developed for Burkina Faso (RMBF) by referring to the FAO56 Penman–Monteith (PM) as the standard method. Statistically, the models accuracies were evaluated with the goodness-of-fit measures of root mean square error, mean absolute error and coefficient of determination between their estimated and PM observed values. From the statistical results, BP shows similar contour trends to PM, and performs better than the conventional methods in reference evapotranspiration (ET_ref) forecasting in the region. In poor data situation, BP based only on temperature data is much more preferred than the other alternative methods for ET_ref forecasting. Furthermore, it is noted that the BP network computing technique accuracy improves significantly with the addition of wind velocity into the network input set. Therefore, in the region, wind velocity is recommended to be incorporated into the BP model for high accuracy management purpose of irrigation water, which relies on accurate values of ET_ref.
Xu, Tianhua; Liga, Gabriele; Lavery, Domaniç; Thomsen, Benn C; Savory, Seb J; Killey, Robert I; Bayvel, Polina
2015-09-14
Superchannel transmission spaced at the symbol rate, known as Nyquist spacing, has been demonstrated for effectively maximizing the optical communication channel capacity and spectral efficiency. However, the achievable capacity and reach of transmission systems using advanced modulation formats are affected by fibre nonlinearities and equalization enhanced phase noise (EEPN). Fibre nonlinearities can be effectively compensated using digital back-propagation (DBP). However EEPN which arises from the interaction between laser phase noise and dispersion cannot be efficiently mitigated, and can significantly degrade the performance of transmission systems. Here we report the first investigation of the origin and the impact of EEPN in Nyquist-spaced superchannel system, employing electronic dispersion compensation (EDC) and multi-channel DBP (MC-DBP). Analysis was carried out in a Nyquist-spaced 9-channel 32-Gbaud DP-64QAM transmission system. Results confirm that EEPN significantly degrades the performance of all sub-channels of the superchannel system and that the distortions are more severe for the outer sub-channels, both using EDC and MC-DBP. It is also found that the origin of EEPN depends on the relative position between the carrier phase recovery module and the EDC (or MC-DBP) module. Considering EEPN, diverse coding techniques and modulation formats have to be applied for optimizing different sub-channels in superchannel systems.
Directory of Open Access Journals (Sweden)
Salim Lahmiri
2014-07-01
Full Text Available This paper presents a forecasting model that integrates the discrete wavelet transform (DWT and backpropagation neural networks (BPNN for predicting financial time series. The presented model first uses the DWT to decompose the financial time series data. Then, the obtained approximation (low-frequency and detail (high-frequency components after decomposition of the original time series are used as input variables to forecast future stock prices. Indeed, while high-frequency components can capture discontinuities, ruptures and singularities in the original data, low-frequency components characterize the coarse structure of the data, to identify the long-term trends in the original data. As a result, high-frequency components act as a complementary part of low-frequency components. The model was applied to seven datasets. For all of the datasets, accuracy measures showed that the presented model outperforms a conventional model that uses only low-frequency components. In addition, the presented model outperforms both the well-known auto-regressive moving-average (ARMA model and the random walk (RW process.
Directory of Open Access Journals (Sweden)
Is Mardianto
2008-05-01
Full Text Available There are various ways to detect osteoporosis disease (bone loss. One of them is by observing the osteoporosisimage through rontgen picture or X-ray. Then, it is analyzed manually by Rheumatology experts. Article present the creationof a system which could detect osteoporosis disease on human, by implementing the Rheumatology principles. The main areasidentified were between wrist and hand fingers. The working system in this software included 3 important processing, whichwere process of basic image processing, pixel reduction process, pixel reduction, and artificial neural networks. Initially, thecolor of digital X-ray image (30 x 30 pixels was converted from RGB to grayscale. Then, it was threshold and its gray levelvalue was taken. These values then were normalized to an interval [0.1, 0.9], then reduced using a PCA (Principal ComponentAnalysis method. The results were used as input on the process of Backpropagation artificial neural networks to detect thedisease analysis of X-ray being inputted. It can be concluded that from the testing result, with a learning rate of 0.7 andmomentum of 0.4, this system had a success rate of 73 to 100 percent for the non-learning data testing, and 100 percent forlearning data.Keywords: osteoporosis, image processing, PCA, artificial neural networks
Fuenzalida, Marco; Fernández de Sevilla, David; Couve, Alejandro; Buño, Washington
2010-01-01
The cellular mechanisms that mediate spike timing-dependent plasticity (STDP) are largely unknown. We studied in vitro in CA1 pyramidal neurons the contribution of AMPA and N-methyl-d-aspartate (NMDA) components of Schaffer collateral (SC) excitatory postsynaptic potentials (EPSPs; EPSP(AMPA) and EPSP(NMDA)) and of the back-propagating action potential (BAP) to the long-term potentiation (LTP) induced by a STDP protocol that consisted in pairing an EPSP and a BAP. Transient blockade of EPSP(AMPA) with 7-nitro-2,3-dioxo-1,4-dihydroquinoxaline-6-carbonitrile (CNQX) during the STDP protocol prevented LTP. Contrastingly LTP was induced under transient inhibition of EPSP(AMPA) by combining SC stimulation, an imposed EPSP(AMPA)-like depolarization, and BAP or by coupling the EPSP(NMDA) evoked under sustained depolarization (approximately -40 mV) and BAP. In Mg(2+)-free solution EPSP(NMDA) and BAP also produced LTP. Suppression of EPSP(NMDA) or BAP always prevented LTP. Thus activation of NMDA receptors and BAPs are needed but not sufficient because AMPA receptor activation is also obligatory for STDP. However, a transient depolarization of another origin that unblocks NMDA receptors and a BAP may also trigger LTP.
Lin, Bin; Lin, Gaotong; Liu, Xianyun; Ma, Jianshe; Wang, Xianchuan; Lin, Feiyan; Hu, Lufeng
2015-01-01
In order to develop pharmacokinetic model, a well-known multilayer feed-forward algorithm back-propagation artificial neural networks (BP-ANN) was applied to the pharmacokinetics of losartan in rabbit. The plasma concentrations of losartan in twelve rabbits, which were divided into two groups and given losartan 2 mg/kg by intravenous (Iv) and intragastrical (Ig) administration, were determined by LC-MS. The BP-ANN model included one input layer, hidden layers, and one output layer was constructed and compared with curve estimation based on the time-concentration data of losartan. The results showed the BP-ANN model had high goodness of fit index and good coherence (R > 0.99) between forecasted concentration and measured concentration both in Iv and Ig administration. The residuals of each concentrations generated by BP-ANN model were all smaller than Curve estimation. The pharmacokinetic result showed there was no significant difference between measured and simulated pharmacokinetic parameters including AUC(0-t), AUC(0-∞), MRT(0-t), MRT(0-∞), T1/2 V and Cmax (P > 0.05). In conclusion, the BP-ANN model has remarkably accurate predictions ability, which better than Curve estimation, and can be used as a utility tool in pharmacokinetic experiment.
Institute of Scientific and Technical Information of China (English)
Lean YU; Shouyang WANG; Kin Keung LAI
2009-01-01
The slow convergence of back-propagation neu-ral network (BPNN) has become a challenge in data-mining and knowledge discovery applications due to the drawbacks of the gradient descent (GD) optimization method, which is widely adopted in BPNN learning. To solve this problem,some standard Optimization techniques such as conjugate-gradient and Newton method have been proposed to improve the convergence rate of BP learning algorithm. This paper presents a heuristic method that adds an adaptive smooth-ing momentum term to original BP learning algorithm to speedup the convergence. In this improved BP learning al-gorithm, adaptive smoothing technique is used to adjust the momentums of weight updating formula automatically in terms of "3 σ limits theory." Using the adaptive smoothing momentum terms, the improved BP learning algorithm can make the network training and convergence process faster,and the network's generalization performance stronger than the standard BP learning algorithm can do. In order to ver-ify the effectiveness of the proposed BP learning algorithm,three typical foreign exchange rates, British pound (GBP),Euro (EUR), and Japanese yen (JPY), are chosen as the fore-casting targets for illustration purpose. Experimental results from homogeneous algorithm comparisons reveal that the proposed BP learning algorithm outperforms the other com-parable BP algorithms in performance and convergence rate.Furthermore, empirical results from heterogeneous model comparisons also show the effectiveness of the proposed BP learning algorithm.
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.
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
Ul-Saufie, Ahmad Zia; Yahaya, Ahmad Shukri; Ramli, Nor Azam; Rosaida, Norrimi; Hamid, Hazrul Abdul
2013-10-01
Future PM10 concentration prediction is very important because it can help local authorities to enact preventative measures to reduce the impact of air pollution. The aims of this study are to improve prediction of Multiple Linear Regression (MLR) and Feedforward backpropagation (FFBP) by combining them with principle component analysis for predicting future (next day, next two-day and next three-day) PM10 concentration in Negeri Sembilan, Malaysia. Annual hourly observations for PM10 in Negeri Sembilan, Malaysia from January 2003 to December 2010 were selected for predicting PM10 concentration level. Eighty percent of the monitoring records were used for training and twenty percent were used for validation of the models. Three accuracy measures - Prediction Accuracy (PA), Coefficient of Determination (R2) and Index of Agreement (IA), as well as two error measures - Normalized Absolute Error (NAE) and Root Mean Square Error (RMSE) were used to evaluate the performance of the models. Results show that PCA models combined with MLR and PCA with FFBP improved MLR and FFBP models for all three days in advance of predicting PM10 concentration, with reduced errors by as much as 18.1% (PCA-MLR) and 17.68% (PCA-FFBP) for next day, 19.2% (PCA-MLR) and 22.1% (PCA-FFBP) for next two-day and 18.7% (PCA-MLR) and 22.79% (PCA-FFBP) for next three-day predictions. Including PCA improved the accuracy of the models by as much as by 12.9% (PCA-MLR) and 13.3% (PCA-FFBP) for next day, 32.3% (PCA-MLR) and 14.7% (PCA-FFBP) for next two-day and 46.1% (PCA-MLR) and 19.3% (PCA-FFBP) for next three-day predictions.
Galdino, Lidia; Tan, Mingming; Lavery, Domaniç; Rosa, Pawel; Maher, Robert; Phillips, Ian D; Ania Castañón, Juan D; Harper, Paul; Killey, Robert I; Thomsen, Benn C; Makovejs, Sergejs; Bayvel, Polina
2015-07-01
Transmission of a net 467-Gb/s PDM-16QAM Nyquist-spaced superchannel is reported with an intra-superchannel net spectral efficiency (SE) of 6.6 (b/s)/Hz, over 364-km SMF-28 ULL ultra-low loss optical fiber, enabled by bi-directional second-order Raman amplification and digital nonlinearity compensation. Multi-channel digital back-propagation (MC-DBP) was applied to compensate for nonlinear interference; an improvement of 2 dB in Q(2) factor was achieved when 70-GHz DBP bandwidth was applied, allowing an increase in span length of 37 km.
DEFF Research Database (Denmark)
Sackey, Isaac; Da Ros, Francesco; Karl Fischer, Johannes;
2015-01-01
We experimentally investigate Kerr nonlinearity mitigation of a 28-GBd polarization-multiplexed 16-QAM signal in a five-channel 50-GHz spaced wavelength-division multiplexing (WDM) system. Optical phase conjugation (OPC) employing the mid-link spectral inversion technique is implemented by using...... a dual-pump polarization-independent fiber-optic parametric amplifier and compared to digital backpropagation (DBP) compensation over up to 800-km in a dispersion-managed link. In the single-channel case, the use of the DBP algorithm outperformed the OPC with a Q-factor improvement of 0.9 dB after 800-km...
Yu, Hao; Rossi, Giammarco; Braglia, Andrea; Perrone, Guido
2016-08-10
The paper presents the development of a tool based on a back-propagation artificial neural network to assist in the accurate positioning of the lenses used to collimate the beam from semiconductor laser diodes along the so-called fast axis. After training using a Gaussian beam ray-equivalent model, the network is capable of indicating the tilt, decenter, and defocus of such lenses from the measured field distribution, so the operator can determine the errors with respect to the actual lens position and optimize the diode assembly procedure. An experimental validation using a typical configuration exploited in multi-emitter diode module assembly and fast axis collimating lenses with different focal lengths and numerical apertures is reported.
Kai, Xiao-ming
2004-11-01
The contents of four microamount elements (Sr, Cu, Mg and Zn) in human blood were chosen as recognition index of coronary heart disease patients and normal persons. The recognition pattern of Levenberg-Marquardt Backpropagation algorithm has been established. The first-layer transfer function is Tansig function; the second-layer transfer function is linear Purelin function. There are four input vectors, eight neurons on hidden layer, and one neuron of output vector. Four samples were chosen as a teat group and 22 samples as a training group. The weights and biases of the neural network were given. The given data could be completely identified, which predicted that this method could be a supplementary tool to diagnose this kind of disease with the determined contents of microamount of elements in human blood.
Trillo, Cristina; Doval, Ángel F.; Fernández, José L.; Rodríguez-Gómez, Pablo; López-Vázquez, J. Carlos
2014-10-01
This article presents a method aimed at the characterization of the narrowband transient acoustic field radiated by an ultrasonic plane transducer into a homogeneous, isotropic and optically opaque prismatic solid, and the assessment of the performance of the acoustic source. The method relies on a previous technique based on the full-field optical measurement of an acoustic wavepacket at the surface of a solid and its subsequent numerical backpropagation within the material. The experimental results show that quantitative transversal and axial profiles of the complex amplitude of the beam can be obtained at any plane between the measurement and excitation surfaces. The reconstruction of the acoustic field at the transducer face, carried out on a defective transducer model, shows that the method could also be suitable for the nondestructive testing of the performance of ultrasonic sources. In all cases, the measurements were performed with the transducer working under realistic loading conditions.
Institute of Scientific and Technical Information of China (English)
王菲; 曾庆军; 黄国建; 李洪瑞
2001-01-01
The development and system composition of underwater target recognition system is expounded at first, and then a novel method for training neural network target classifier by using genetic-backpropagation algorithm is proposed. The result of experiment shows that the performance of neural network target classifier based on genetic-backpropagation algorithm is better than that of neural network target classifier based on the improved backpropagation algorithm.%首先阐述了水下目标识别的研究发展和系统组成，然后提出了一种基于遗传BP算法训练神经网络目标分类器的新方法。实验结果表明采用新方法的神经网络分类器比采用改进BP算法的神经网络分类器具有更优的分类效果。
Quan, Guo-zheng; Zou, Zhen-yu; Wang, Tong; Liu, Bo; Li, Jun-chao
2017-01-01
In order to investigate the hot deformation behaviors of as-extruded 7075 aluminum alloy, the isothermal compressive tests were conducted at the temperatures of 573, 623, 673 and 723 K and the strain rates of 0.01, 0.1, 1 and 10 s-1 on a Gleeble 1500 thermo-mechanical simulator. The flow behaviors showing complex characteristics are sensitive to strain, strain rate and temperature. The effects of strain, temperature and strain rate on flow stress were analyzed and dynamic recrystallization (DRX)-type softening characteristics of the flow behaviors with single peak were identified. An artificial neural network (ANN) with back-propagation (BP) algorithm was developed to deal with the complex deformation behavior characteristics based on the experimental data. The performance of ANN model has been evaluated in terms of correlation coefficient (R) and average absolute relative error (AARE). A comparative study on Arrhenius-type constitutive equation and ANN model for as-extruded 7075 aluminum alloy was conducted. Finally, the ANN model was successfully applied to the development of processing map and implanted into finite element simulation. The results have sufficiently articulated that the well-trained ANN model with BP algorithm has excellent capability to deal with the complex flow behaviors of as-extruded 7075 aluminum alloy and has great application potentiality in hot deformation processes.
Directory of Open Access Journals (Sweden)
Attariuas Hicham
2012-05-01
Full Text Available This paper describes new hybrid sales forecasting system based on fuzzy clustering and Back-propagation (BP Neural Networks with adaptive learning rate (FCBPN.The proposed approach is composed of three stages: (1 Winters Exponential Smoothing method will be utilized to take the trend effect into consideration; (2 utilizing Fuzzy C-Means clustering method (Used in an clusters memberships fuzzy system (CMFS, the clusters membership levels of each normalized data records will be extracted; (3 Each cluster will be fed into parallel BP networks with a learning rate adapted as the level of cluster membership of training data records. Compared to many researches which use Hard clustering, we employ fuzzy clustering which permits each data record to belong to each cluster to a certain degree, which allows the clusters to be larger which consequently increases the accuracy of the proposed forecasting system . Printed Circuit Board (PCB will be used as a case study to evaluate the precision of our proposed architecture. Experimental results show that the proposed model outperforms the previous and traditional approaches. Therefore, it is a very promising solution for industrial forecasting.
Directory of Open Access Journals (Sweden)
Zhilong Wang
2014-01-01
Full Text Available In the electricity market, the electricity price plays an inevitable role. Nevertheless, accurate price forecasting, a vital factor affecting both government regulatory agencies and public power companies, remains a huge challenge and a critical problem. Determining how to address the accurate forecasting problem becomes an even more significant task in an era in which electricity is increasingly important. Based on the chaos particle swarm optimization (CPSO, the backpropagation artificial neural network (BPANN, and the idea of bivariate division, this paper proposes a bivariate division BPANN (BD-BPANN method and the CPSO-BD-BPANN method for forecasting electricity price. The former method creatively transforms the electricity demand and price to be a new variable, named DV, which is calculated using the division principle, to forecast the day-ahead electricity by multiplying the forecasted values of the DVs and forecasted values of the demand. Next, to improve the accuracy of BD-BPANN, chaos particle swarm optimization and BD-BPANN are synthesized to form a novel model, CPSO-BD-BPANN. In this study, CPSO is utilized to optimize the initial parameters of BD-BPANN to make its output more stable than the original model. Finally, two forecasting strategies are proposed regarding different situations.
Energy Technology Data Exchange (ETDEWEB)
Doh, Jaeh Yeok; Lee, Jong Soo [Yonsei University, Seoul (Korea, Republic of); Lee, Seung Uk [Gyeongbuk Hybrid Technology Institute, Yeongcheon (Korea, Republic of)
2016-03-15
In this study, a Back-propagation neural network (BPN) is employed to conduct an approximation of a true stress-strain curve using the load-displacement experimental data of DP590, a high-strength material used in automobile bodies and chassis. The optimized interconnection weights are obtained with hidden layers and output layers of the BPN through intelligent learning and training of the experimental data; by using these weights, a mathematical model of the material's behavior is suggested through this feed-forward neural network. Generally, the material properties from the tensile test cannot be acquired until the fracture regions, since it is difficult to measure the cross-section area of a specimen after diffusion necking. For this reason, the plastic properties of the true stress-strain are extrapolated using the weighted-average method after diffusion necking. The accuracies of BPN-based meta-models for predicting material properties are validated in terms of the Root mean square error (RMSE). By applying the approximate material properties, the reliable finite element solution can be obtained to realize the different shapes of the finite element models. Furthermore, the sensitivity analysis of the approximate meta-model is performed using the first-order approximate derivatives of the BPN and is compared with the results of the finite difference method. In addition, we predict the tension velocity's effect on the material property through a first-order sensitivity analysis.
Institute of Scientific and Technical Information of China (English)
王士同; 朱晓铭
2001-01-01
研究了模糊反向传播神经网络FBP(Fuzzy Backpropagation)的函数逼近能力.给出了单调连续函数的FBP按序单调特性、连续映射定理以及非函数一致逼近定理,并且说明了FBP虽然能保持连续性映射,但不如原神经网络具有函数逼近能力.
Institute of Scientific and Technical Information of China (English)
瞿晓娜; 张腾宇; 王喜太
2012-01-01
背景:虽然在人体步态方面已有大量研究,但针对膝踝协调运动的研究很少.目的:用BP神经网络分析膝踝协调运动关系.方法:利用三维步态分析系统检测了30名健康志愿者以快、中、慢3种步速行走时的步态数据,进行统计分析;并通过建立BP神经网络预测数据,同时对膝踝协调的控制方法进行探讨.结果与结论:不同的人步态不同,但BP神经网络预测所得曲线与实验基本一致,证实了用BP神经网络做膝踝运动关系预测的合理性和可行性,很好的研究了膝踝协调性,给全智能膝踝协调控制假肢的研发提供了理论依据.%BACKGROUND: The study of the relationship between knee and ankle is poor although there have been a lot of researches on gait of people. OBJECTIVE: To analyze the relationship between knee and ankle based on back-propagation network. METHODS: The gaits of 30 healthy young people walking at fast, normal, and low speeds separately were detected by three-dimensional gait analysis system, and the gait data were investigated and analyzed. The data were predicted through the establishment of the back-propagation neural network and the knee-ankle coordination control method was explored. RESULTS AND CONCLUSION: Different people had different gaits, but the curve obtained by back-propagation neural network was similar with the experimental curve. The paper investigated and validated that it was viable and reasonable to forecast the kinematic relationship between the knee and ankle by back-propagation network system. The paper studied the coordination between the knee and ankle well, and provided the theory foundation for the design of the intelligent prostheses.
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.
Directory of Open Access Journals (Sweden)
Xianzhi Song
Full Text Available Sand production and blockage are common during the drilling and production of horizontal oil and gas wells as a result of formation breakdown. The use of high-pressure rotating jets and annular helical flow is an effective way to enhance horizontal wellbore cleanout. In this paper, we propose the idea of using supercritical CO2 (SC-CO2 as washing fluid in water-sensitive formation. SC-CO2 is manifested to be effective in preventing formation damage and enhancing production rate as drilling fluid, which justifies tis potential in wellbore cleanout. In order to investigate the effectiveness of SC-CO2 helical flow cleanout, we perform the numerical study on the annular flow field, which significantly affects sand cleanout efficiency, of SC-CO2 jets in horizontal wellbore. Based on the field data, the geometry model and mathematical models were built. Then a numerical simulation of the annular helical flow field by SC-CO2 jets was accomplished. The influences of several key parameters were investigated, and SC-CO2 jets were compared to conventional water jets. The results show that flow rate, ambient temperature, jet temperature, and nozzle assemblies play the most important roles on wellbore flow field. Once the difference between ambient temperatures and jet temperatures is kept constant, the wellbore velocity distributions will not change. With increasing lateral nozzle size or decreasing rear/forward nozzle size, suspending ability of SC-CO2 flow improves obviously. A back-propagation artificial neural network (BP-ANN was successfully employed to match the operation parameters and SC-CO2 flow velocities. A comprehensive model was achieved to optimize the operation parameters according to two strategies: cost-saving strategy and local optimal strategy. This paper can help to understand the distinct characteristics of SC-CO2 flow. And it is the first time that the BP-ANN is introduced to analyze the flow field during wellbore cleanout in
Song, Xianzhi; Peng, Chi; Li, Gensheng
2016-01-01
Sand production and blockage are common during the drilling and production of horizontal oil and gas wells as a result of formation breakdown. The use of high-pressure rotating jets and annular helical flow is an effective way to enhance horizontal wellbore cleanout. In this paper, we propose the idea of using supercritical CO2 (SC-CO2) as washing fluid in water-sensitive formation. SC-CO2 is manifested to be effective in preventing formation damage and enhancing production rate as drilling fluid, which justifies tis potential in wellbore cleanout. In order to investigate the effectiveness of SC-CO2 helical flow cleanout, we perform the numerical study on the annular flow field, which significantly affects sand cleanout efficiency, of SC-CO2 jets in horizontal wellbore. Based on the field data, the geometry model and mathematical models were built. Then a numerical simulation of the annular helical flow field by SC-CO2 jets was accomplished. The influences of several key parameters were investigated, and SC-CO2 jets were compared to conventional water jets. The results show that flow rate, ambient temperature, jet temperature, and nozzle assemblies play the most important roles on wellbore flow field. Once the difference between ambient temperatures and jet temperatures is kept constant, the wellbore velocity distributions will not change. With increasing lateral nozzle size or decreasing rear/forward nozzle size, suspending ability of SC-CO2 flow improves obviously. A back-propagation artificial neural network (BP-ANN) was successfully employed to match the operation parameters and SC-CO2 flow velocities. A comprehensive model was achieved to optimize the operation parameters according to two strategies: cost-saving strategy and local optimal strategy. This paper can help to understand the distinct characteristics of SC-CO2 flow. And it is the first time that the BP-ANN is introduced to analyze the flow field during wellbore cleanout in horizontal wells. PMID
Institute of Scientific and Technical Information of China (English)
韩明红; 韩捷; 关惠玲
2001-01-01
The reasons for the slowness in convergence of standard backpropagation algorithm and the imperfection of conventional improved algorithms have been fully analyzed. In order to improve the convergence rate of multilayer feedforward neural networks, a new highly efficent unitary backpropagation algorithm based on the unitary-function is proposed. Numerical simulation and experimental results show that the algorithm can greatly increase the convergence rate and highly improve their imminent accurary.%分析了引起标准BP算法收敛速度慢的原因，以及传统改进方法的不足之处，探讨了解决的途径。为了提高BP算法的收敛速度，定义并引入了基量函数的概念，并将其运用到BP算法中，给出了一种高效的单位BP算法。仿真和实例结构均表明该算法能够较好地克服标准BP算法收敛速度慢的缺点，并可以达到很高的网络逼近精度。
Institute of Scientific and Technical Information of China (English)
开小明; 沈玉华; 谢安建; 郑学根
2004-01-01
提出用Levenberg-Marquardt Backpropagation Neural Network (LM-BP)网络对酸性偶氮染料进行分类,网络结构为4-6-5.优化了隐含层神经元数和网络训练次数,表明隐含层神经元数应比输出层神经元数多一个.考察了训练集样本的选择对结果的影响,测试集的样本参数大小要处于训练集样本之间.本网络把其中22种染料作为训练集,把另外18种染料作为测试集,与采用GCEDM逐次分类法比较,测试集识别率为83%.
Institute of Scientific and Technical Information of China (English)
易忠胜; 吴永华
2001-01-01
为了提高此网络算法的学习效率及稳定性,在反向传播算法(backpropagation(BP))中引入了基于非线性最小二乘法的Levenberg-Marquart(LM)最优算法,替代原BP算法中的梯度下降法寻找最佳网络连接权值.LM优化算法其学习效率比带动量项的BP算法高一个数量级以上,值得推广应用.将其用于混合体系的多组份CAS-CTMAB显色体系光度法同时测定Ca、Mg、Fe,得到平均预测误差为2.6534 mg/L,平均预测方差为1.9580,能够满足多组分测定的需要.
Institute of Scientific and Technical Information of China (English)
杜雨静; 范英芳
2011-01-01
目的:探讨误差反向传播(backpropagation,BP)神经网络在雌二醇衍生物定量结构-活性关系(quantitative structure-activity relationships,QSAR)研究中的应用.方法:采用BP神经网络法和多元线性回归法,分别建立了30个雌二醇衍生物在0℃下与羔羊子宫雌激素受体间亲合力logRBA与疏水性参数logP、分子的体积V和9号碳原子的净电荷Q之间的QSAR模型.结果:BP模型的相关系数R=0.9962,标准偏差SD=0.0588；MLR模型的相关系数R=0.9090,标准偏差SD=0.2904.结论:BP神经网络是一种比较精密的拟合方法,具有良好的预测效果.
Al-Abadi, Alaa M.
2016-11-01
The potential of using three different data-driven techniques namely, multilayer perceptron with backpropagation artificial neural network (MLP), M5 decision tree model, and Takagi-Sugeno (TS) inference system for mimic stage-discharge relationship at Gharraf River system, southern Iraq has been investigated and discussed in this study. The study used the available stage and discharge data for predicting discharge using different combinations of stage, antecedent stages, and antecedent discharge values. The models' results were compared using root mean squared error (RMSE) and coefficient of determination ( R 2) error statistics. The results of the comparison in testing stage reveal that M5 and Takagi-Sugeno techniques have certain advantages for setting up stage-discharge than multilayer perceptron artificial neural network. Although the performance of TS inference system was very close to that for M5 model in terms of R 2, the M5 method has the lowest RMSE (8.10 m3/s). The study implies that both M5 and TS inference systems are promising tool for identifying stage-discharge relationship in the study area.
Institute of Scientific and Technical Information of China (English)
何超; 徐立新; 张宇河
1999-01-01
目的为了消除普遍存在于伺服系统中的间隙非线性的影响,提出一种利用BP神经网络进行非线性补偿的方法.方法以某武器跟踪伺服系统为例,采用一个3层BP神经网络对其间隙非线性特性进行离线辨识,然后根据辨识结果设计一个非线性补偿器.结果仿真结果表明所提出的方法能够有效消除间隙特性引起的系统自振荡(极限环),并且能够提高系统精度.结论利用BP神经网络进行间隙非线性补偿的方法能够有效解决伺服系统中间隙特性带来的影响,且易于在工程中实现.%Aim To eliminate the influences of backlash nonlinear characteristics generally existing in servo systems, a nonlinear compensation method using backpropagation neural networks(BPNN) is presented. Methods Based on some weapon tracking servo system, a three-layer BPNN was used to off-line identify the backlash characteristics, then a nonlinear compensator was designed according to the identification results. Results The simulation results show that the method can effectively get rid of the sustained oscillation(limit cycle) of the system caused by the backlash characteristics, and can improve the system accuracy. Conclusion The method is effective on sloving the problems produced by the backlash characteristics in servo systems, and it can be easily accomplished in engineering.
Energy Technology Data Exchange (ETDEWEB)
Toda-Caraballo, I.; Garcia-Mateo, C.; Capdevila, C.
2010-07-01
At the beginning of the decade of the nineties, the industrial interest for TRIP steels leads to a significant increase of the investigation and application in this field. In this work, the flexibility of neural networks for the modelling of complex properties is used to tackle the problem of determining the retained austenite content in TRIP-steel. Applying a combination of two learning algorithms (backpropagation and creeping-random-search) for the neural network, a model has been created that enables the prediction of retained austenite in low-Si / low-Al multiphase steels as a function of processing parameters. (Author). 34 refs.
Institute of Scientific and Technical Information of China (English)
韦添尹; 蒋永荣; 刘可慧; 刘成良; 张威
2013-01-01
The back-propagation neural network (BPNN) trained with the data from the sulfate organic wastewater treatment of anaerobic baffled reactor(ABR) and a network model was buih.The better training function and times were ‘ traingda' and 1 900,respectively.Partition connection weights (PCW) was adopted to analyze the dominant factors of effluent COD and SO42-.The results showed that all of the factors (feed COD,SO42-,pH,COD/SO42-and HRT) had an influence on effluent COD and SO42-.Nevertheless,the feed pH was the dominant factor,which relative importance (RI) were 30.79％ and 23.44％,respectively.The model and simulink on restrictive factors for COD and SO42-removal were built respectively,which can be used for prediction on sulfate organic wastewater treatment.%通过厌氧折流板反应器(ABR)处理硫酸盐有机废水的实验数据对BP神经网络进行训练,建立了ABR处理硫酸盐有机废水的BPNN模型,通过测试对比,找出了较优训练函数为traingda,较优训练次数为1 900.利用分割连接权值法(PCW)对影响出水SO42-和COD的主要因素进行分析,结果显示进水COD、SO42-、pH、COD/SO42-和HRT对出水SO42-和COD均产生一定影响,其中进水pH对出水SO42-和COD的影响最大,相对重要性(RI)指数分别为30.79％和23.44％;并通过样本试验数据分别建立了对SO42-和COD去除率的限制因子仿真模型,为预测硫酸盐有机废水的厌氧处理过程提供指导.
Backpropagation Learning Algorithms for Email Classification.
Directory of Open Access Journals (Sweden)
*David Ndumiyana and Tarirayi Mukabeta
2016-07-01
Full Text Available Today email has become one the fastest and most effective form of communication. The popularity of this mode of transmitting goods, information and services has motivated spammers to perfect their technical skills to fool spam filters. This development has worsened the problems faced by Internet users as they have to deal with email congestion, email overload and unprioritised email messages. The result was an exponential increase in the number of email classification management tools for the past few decades. In this paper we propose a new spam classifier using a learning process of multilayer neural network to implement back propagation technique. Our contribution to the body of knowledge is the use of an improved empirical analysis to choose an optimum, novel collection of attributes of a user’s email contents that allows a quick detection of most important words in emails. We also demonstrate the effectiveness of two equal sets of emails training and testing data.
Learning associative memories by error backpropagation.
Zheng, Pengsheng; Zhang, Jianxiong; Tang, Wansheng
2011-03-01
In this paper, a method for the design of Hopfield networks, bidirectional and multidirectional associative memories with asymmetric connections, is proposed. The given patterns can be assigned as locally asymptotically stable equilibria of the network by training a single-layer feedforward network. It is shown that the robustness in respect to acceptable noise in the input of the constructed networks is enhanced as the memory dimension increases and weakened as the number of the stored patterns grows. More important is that the remembered patterns are not necessarily of binary forms. Neural associative memories for storing gray-level images are constructed based on the proposed method. Numerical simulations show that the proposed method is efficient for the design of Hopfield-type recurrent neural networks.
Institute of Scientific and Technical Information of China (English)
李伟; 何鹏举; 杨恒; 陈明
2012-01-01
针对BP神经网络结构由于特征维数增多变得复杂,以及网络易陷入局部极值点,提出了粗糙集和改进遗传算法结合共同优化神经网络的方法.首先利用粗糙集对样本空间进行属性约简,降低特征维数,进而简化BP神经网络的结构;然后训练过程中先用改进的遗传算法全局搜索网络的权值和阀值,再使用BP算法局部搜索细化,避免网络过早收敛.试验分析证明优化后BP神经网络比传统BP网络的预测精度得到了极大提高,泛化能力得到了增强,说明了该方法的可行性、有效性.%Considering that the BP neural network became complex due to the increase of the sample dimension and it fell easily into local maximums or minimums, we combined genetic algorithm and rough set to optimize the BP neural network. Sections 1 through 3 explain our backpropagation algorithm mentioned in the title, which we believe is effective and whose core consists of; (1) rough set was applied to simplify the network by reducing the attribute dimension; (2) modified genetic algorithm was used to globally search the weights and bios and, further, the BP algorithm was to locally optimize them to avoid the network falling into the local extremes. Simulation results, presented in Fig. 1 and Table 2 in subsection 3. 4, and their analysis indicated preliminarily that prediction accuracy was increased greatly over that of the traditional BP neural network and that generalization was enhanced, thus showing that our backpropagation algorithm is indeed effective.
Neural Network Back-Propagation Algorithm for Sensing Hypergols
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.
Impairment mitigation in superchannels with digital backpropagation and MLSD
DEFF Research Database (Denmark)
Porto da Silva, Edson; Larsen, Knud J.; Zibar, Darko
2015-01-01
and NRZ spectra, and digital Nyquist filtering. We investigate the limits for carrier proximity of each spectral shaping technique and the correspondent performance behavior of each algorithm, for both modulation formats. For superchannels with carrier spacing close to the Nyquist limit, it is shown...
Backpropagation Neural Network Implementation for Medical Image Compression
Directory of Open Access Journals (Sweden)
Kamil Dimililer
2013-01-01
Full Text Available Medical images require compression, before transmission or storage, due to constrained bandwidth and storage capacity. An ideal image compression system must yield high-quality compressed image with high compression ratio. In this paper, Haar wavelet transform and discrete cosine transform are considered and a neural network is trained to relate the X-ray image contents to their ideal compression method and their optimum compression ratio.
Application of backpropagation neural networks to phonetic element classification
Energy Technology Data Exchange (ETDEWEB)
Bryan, S.R.
1990-01-01
A need was established in conjunction with an USAF-sponsored project to develop a speech element classifier. This classifier had to be capable of placing continuous speech into a number of phoneme-like categories, and also had to be independent of speaker identity and individual voice characteristics. The feasibility of using a neural network to perform this classification task was explored. The results of this exploration are discussed here.
Implementing Recurrent Back-Propagation on the Connection Machine.
1988-12-02
arc-end-function) (let ((slot ( gensym )) (out-box!! ( gensym ))) ’(let (,label-name) (*all (*let (,in-box!! ,out-box!!) (declare (type ,in-box-type ,in...values-list ( gensym )) (i -1)) ’(let ((,values-list (multiple-value-list ,values-form))) (setf GQ(mapcan *’(lambda (accessor-form) ’(,accessor-form...let ((elapsed-time ( gensym )) (cm-time ( gensym )) (percent ( gensym ))) ’(multiple-value-bind (,elapsed-time ,cm-time ,percent) (cm:time ,form :return
Optimize Short Term load Forcasting Anomalous Based Feed Forward Backpropagation
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.
Ilin, Roman; Werbos, Paul J
2007-01-01
Cellular Simultaneous Recurrent Neural Network (SRN) has been shown to be a function approximator more powerful than the MLP. This means that the complexity of MLP would be prohibitively large for some problems while SRN could realize the desired mapping with acceptable computational constraints. The speed of training of complex recurrent networks is crucial to their successful application. Present work improves the previous results by training the network with extended Kalman filter (EKF). We implemented a generic Cellular SRN and applied it for solving two challenging problems: 2D maze navigation and a subset of the connectedness problem. The speed of convergence has been improved by several orders of magnitude in comparison with the earlier results in the case of maze navigation, and superior generalization has been demonstrated in the case of connectedness. The implications of this improvements are discussed.
Axon-somatic back-propagation in detailed models of spinal alpha motoneurons
Directory of Open Access Journals (Sweden)
Pietro eBalbi
2015-02-01
Full Text Available Antidromic action potentials following distal stimulation of motor axons occasionally fail to invade the soma of alpha motoneurons in spinal cord, due to their passing through regions of high non-uniformity.Morphologically detailed conductance-based models of cat spinal alpha motoneurons have been developed, with the aim to reproduce and clarify some aspects of the electrophysiological behavior of the antidromic axon-somatic spike propagation. Fourteen 3D morphologically detailed somata and dendrites of cat spinal alpha motoneurons have been imported from an open-access web-based database of neuronal morphologies, NeuroMorpho.org, and instantiated in neurocomputational models. An axon hillock, an axonal initial segment and a myelinated axon are added to each model.By sweeping the diameter of the axonal initial segment (AIS and the axon hillock, as well as the maximal conductances of sodium channels at the AIS and at the soma, the developed models are able to show the relationships between different geometric and electrophysiological configurations and the voltage attenuation of the antidromically travelling wave.In particular, a greater than usually admitted sodium conductance at AIS is necessary and sufficient to overcome the dramatic voltage attenuation occurring during antidromic spike propagation both at the myelinated axon-AIS and at the AIS-soma transitions.
The performance of the backpropagation algorithm with varying slope of the activation function
Energy Technology Data Exchange (ETDEWEB)
Bai Yanping [National Key Laboratory of Micro/Nano Fabrication Technology, Institute of Microelectronics, Peking University, 100871 (China); Department of Applied Mathematics, North University of China, No. 3 Xueyuan Road, TaiYuan, ShanXi 030051 (China)], E-mail: baiyp@nuc.edu.cn; Zhang Haixia [National Key Laboratory of Micro/Nano Fabrication Technology, Institute of Microelectronics, Peking University, 100871 (China); Hao Yilong [National Key Laboratory of Micro/Nano Fabrication Technology, Institute of Microelectronics, Peking University, 100871 (China)], E-mail: yilonghao@ime.pke.edu.cn
2009-04-15
Some adaptations are proposed to the basic BP algorithm in order to provide an efficient method to non-linear data learning and prediction. In this paper, an adopted BP algorithm with varying slope of activation function and different learning rates is put forward. The results of experiment indicated that this algorithm can get very good performance of training. We also test the prediction performance of our adopted BP algorithm on 16 instances. We compared the test results to the ones of the BP algorithm with gradient descent momentum and an adaptive learning rate. The results indicate this adopted BP algorithm gives best performance (100%) for test example, which conclude this adopted BP algorithm produces a smoothed reconstruction that learns better to new prediction function values than the BP algorithm improved with momentum.
Directory of Open Access Journals (Sweden)
S.P.Kosbatwar
2012-03-01
Full Text Available The use of artificial neural network in applications can dramatically simplify the code and improve quality of recognition while achieving good performance. Another benefit of using neural network in application is extensibility of the system – ability to recognize more character sets than initially defined. Most of traditional systems are not extensible enough. In this paper recognition ofcharacters is possible by using neural network back propagation algorithm.
Directory of Open Access Journals (Sweden)
Lei Si
2014-01-01
Full Text Available Classification is an important theme in data mining. Rough sets and neural networks are the most common techniques applied in data mining problems. In order to extract useful knowledge and classify ambiguous patterns effectively, this paper presented a hybrid algorithm based on the integration of rough sets and BP neural network to construct a novel classification system. The attribution values were discretized through PSO algorithm firstly to establish a decision table. The attribution reduction algorithm and rules extraction method based on rough sets were proposed, and the flowchart of proposed approach was designed. Finally, a prototype system was developed and some simulation examples were carried out. Simulation results indicated that the proposed approach was feasible and accurate and was outperforming others.
New backpropagation algorithm with type-2 fuzzy weights for neural networks
Gaxiola, Fernando; Valdez, Fevrier
2016-01-01
In this book a neural network learning method with type-2 fuzzy weight adjustment is proposed. The mathematical analysis of the proposed learning method architecture and the adaptation of type-2 fuzzy weights are presented. The proposed method is based on research of recent methods that handle weight adaptation and especially fuzzy weights. The internal operation of the neuron is changed to work with two internal calculations for the activation function to obtain two results as outputs of the proposed method. Simulation results and a comparative study among monolithic neural networks, neural network with type-1 fuzzy weights and neural network with type-2 fuzzy weights are presented to illustrate the advantages of the proposed method. The proposed approach is based on recent methods that handle adaptation of weights using fuzzy logic of type-1 and type-2. The proposed approach is applied to a cases of prediction for the Mackey-Glass (for ô=17) and Dow-Jones time series, and recognition of person with iris bi...
An Adaptive Filtering Algorithm Based on Genetic Algorithm-Backpropagation Network
Directory of Open Access Journals (Sweden)
Kai Hu
2013-01-01
Full Text Available A new image filtering algorithm is proposed. GA-BPN algorithm uses genetic algorithm (GA to decide weights in a back propagation neural network (BPN. It has better global optimal characteristics than traditional optimal algorithm. In this paper, we used GA-BPN to do image noise filter researching work. Firstly, this paper uses training samples to train GA-BPN as the noise detector. Then, we utilize the well-trained GA-BPN to recognize noise pixels in target image. And at last, an adaptive weighted average algorithm is used to recover noise pixels recognized by GA-BPN. Experiment data shows that this algorithm has better performance than other filters.
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.
CONVERGENCE OF GRADIENT METHOD WITH MOMENTUM FOR BACK-PROPAGATION NEURAL NETWORKS
Institute of Scientific and Technical Information of China (English)
Wei Wu; Naimin Zhang; Zhengxue Li; Long Li; Yan Liu
2008-01-01
In this work,a gradient method with momentum for BP neural networks is considered.The momentum coefficient is chosen in an adaptive manner to accelerate and stabilize the learning procedure of the network weights.Corresponding convergence results are proved.
The Prediction of Bankruptcy Using Backpropagation Algorithm for “IO” Model Analysis
Directory of Open Access Journals (Sweden)
Ciprian Dragota
2007-01-01
Full Text Available The basic question which every bank it putswhen a client or a future client whishes to take a bank loanis: “The future debtor it’s capable to refund the loan atmaturity? (Installments plus the interest“. To answer atthis question the bank makes an assessment in which assetsand liabilities are analyze. There is also assessed the creditrating, the cash flow, the securities and, very important,bankrupt risk analysis.For the last one, to calculate bankrupt risk analysis,banks use some models (knows as “Z” score. Few of themare financials methods (like Altman, Canon & Holder,Yves Colonques etc. Nevertheless, these models are beendevelop for a specific situation and for a western economywhich is functional and very articulated. For our economy,we propose a new model that is been build with the specificeconomic dates and inputs, the model we called “IO”model.Without pretending to be able to penetrate over thecomplexity of the phenomenon, this study is trying to do apractical and experimental analysis of bankruptcy usingback propagation algorithm applied to the ”IO” model.
Directory of Open Access Journals (Sweden)
Z Abidin
2013-07-01
Full Text Available Di dalam kehidupan sehari-hari, khususnya dalam komunikasi interpersonal, wajah sering digunakan untuk berekspresi. Melalui ekspresi wajah, maka dapat dipahami emosi yang sedang bergejolak pada diri individu. Ekspresi wajah merupakan salah satu karakteristik perilaku. Penggunaan sistem teknologi biometrika dengan karakteristik ekspresi wajah memungkinkan untuk mengenali mood atau emosi seseorang. Komponen dasar sistem analisis ekspresi wajah adalah deteksi wajah, ekstraksi data wajah, dan pengenalan ekspresi wajah. Sehingga untuk membangun sebuah sistem pengenal ekspersi wajah, maka perlu dirancang tiga buah sub sistem yaitu sistem deteksi wajah, sistem pembelajaran jaringan syaraf tiruan. Prinsipnya data wajah yang telah dideteksi, diolah menggunakan fisherface, yang selanjutnya hasilnya digunakan sebagai input untuk jaringan syaraf tiruan. Bobot yang dihasilkan pada saat proses pembelajaran jaringan syaraf tiruan inilah yang akan digunakan untuk pengenalan ekspresi wajah.Â In daily life, especially in interpersonal communication, face often used for express of emotions. Facial expressions are the facial changes in response to a personâ€™s internal emotional states. A facial expression is one of the behavioral characteristics. The use of facial expression characteristics enables to recognize of personâ€™s mood. Basic components of a facial expression analysis system are face detection, face data extraction, and facial expression recognition. So that, to build a facial expression recognition system, it should be designed three subsystems, namely face detection system, learning of neural network system, and facial expression recognition system itself. In principle, face data that has been successfully detected, then it will be constructed by fisherface, and the results of it will be used as an input of neural network. Afterwards, the weights of neural network learning will be used to recognize facial expression.
Reversible Back-Propagation Imaging Algorithm for Post-Processing of Ultrasonic Array Data
Velichko, A.; Wilcox, P. D.
2009-03-01
The paper describes a method for processing data from an ultrasonic transducer array. The proposed algorithm is formulated in such a way that it is reversible, i.e. the raw data set can be recovered from the image. This is of practical significance because it allows the raw-data to be spatially filtered using the image to extract, for example, only the raw data associated with a particular reflector. The method is tested on experimental data obtained from a commercial 64-element, 5-MHZ array on an aluminium specimen that contains a number of machined slots and side-drilled holes. The raw transmitter-receiver data corresponded to each reflector is extracted and the scattering matrices of different reflectors are reconstructed. It allows the signals from 1-mm-long slot and a 1-mm-diameter hole to be clearly distinguished and the orientation and the size of the slots to be determined.
Back-propagating the light of field stars to probe telescope mirrors aberrations
Soulez, Ferréol; Unser, Michael
2016-01-01
We propose a wavefront-based method to estimate the PSF over the whole field of view. This method estimate the aberrations of all the mirrors of the telescope using only field stars. In this proof of concept paper, we described the method and present some qualitative results.
Kostencka, J.; Kozacki, T.
2016-04-01
Filtered back propagation (FBPP) is a well-established reconstruction technique that is used in diffractive holographic tomography. The great advantage of the algorithm is the space-domain implementation, which enables avoiding the error-prone interpolation in the spectral domain that is an inherent part of the main counterpart of FBPP - the direct inversion tomographic reconstruction method. However, the fundamental flaw of FBPP is lack of generality, i.e. the method can be applied solely for the classical tomographic systems, where alternation of the measurement views is achieved by rotating a sample. At the same time, majority of the nowadays tomographic setups apply an alternative measurement concept, which is based on scanning of an illumination beam. The aim of this paper is to remove the mentioned limitation of the FBPP and enable its application in the systems utilizing scanning of illumination. This is achieved by introducing a new method of accounting for uneven cover of the sampled object frequencies, which applies normalization of the object spectrum with coherent transfer function of a considered tomographic system. The feasibility of the proposed, modified filtered back propagation algorithm is demonstrated with numerical simulations, which mimic tomographic measurement of a complex sample, i.e. the Shepp-Logan phantom.
Application of a Back-Propagation Neural Network to Isolated-Word Speech Recognition
1993-06-01
discusses the limitations of the proposed BNN system, and offers ideas for further reseach . 2 II. NEURAL NETWORKS A. WHY NEURAL NETWORKS? Recently...Besides the syntactic and semantic issues in the linguistic theories, speech segmentation is a big concern. Boundaries between words and phonemes are...can be estimated by a sudden large variation in the speech spectrum, this method is not very reliable due to coarticulation, i.e., the changes in the
Directory of Open Access Journals (Sweden)
Yi-Qing Wang
2015-09-01
Full Text Available Recent years have seen a surge of interest in multilayer neural networks fueled by their successful applications in numerous image processing and computer vision tasks. In this article, we describe a C++ implementation of the stochastic gradient descent to train a multilayer neural network, where a fast and accurate acceleration of tanh(· is achieved with linear interpolation. As an example of application, we present a neural network able to deliver state-of-the-art performance in image demosaicing.
Trainable hardware for dynamical computing using error backpropagation through physical media
Hermans, Michiel; Burm, Michaël; van Vaerenbergh, Thomas; Dambre, Joni; Bienstman, Peter
2015-03-01
Neural networks are currently implemented on digital Von Neumann machines, which do not fully leverage their intrinsic parallelism. We demonstrate how to use a novel class of reconfigurable dynamical systems for analogue information processing, mitigating this problem. Our generic hardware platform for dynamic, analogue computing consists of a reciprocal linear dynamical system with nonlinear feedback. Thanks to reciprocity, a ubiquitous property of many physical phenomena like the propagation of light and sound, the error backpropagation—a crucial step for tuning such systems towards a specific task—can happen in hardware. This can potentially speed up the optimization process significantly, offering important benefits for the scalability of neuro-inspired hardware. In this paper, we show, using one experimentally validated and one conceptual example, that such systems may provide a straightforward mechanism for constructing highly scalable, fully dynamical analogue computers.
Fuzzy Backpropagation Algorithms and Their Convergence%模糊反向传播算法及其收敛性
Institute of Scientific and Technical Information of China (English)
魏延; 李世宏; 曹长修; 曾绍华
2007-01-01
针对S.Stoeva提出的基于相同样本及网络输出的模糊神经网络模型,通过对基于极大-极小模糊算子的模糊神经网络模型的研究,证明了其与S.Stoeva提出的网络模型的等价性.在此基础上提出了依赖于模糊逻辑神经元输出的调整模糊权值的模糊反向传播学习算法,并进一步研究了其收敛性.最后以汽轮发电机组的状态监测为例进行仿真分析.结果表明:在网络输入神经元满足样本输出介于样本输入的极大与极小之间时,所提出的模糊反向传播学习算法是收敛的.
Self-tuning Learning Rate of the Backpropagation Algorithm%步长动态寻优的BP算法
Institute of Scientific and Technical Information of China (English)
张燕; 刘作军; 孙慧
2000-01-01
从BP算法原理出发,找到造成这一结果的根本原因,利用目标函数对学习步长的一阶、二阶梯度值,应用牛顿近似法和线性寻优法来求得动态最优步长,这种算法所需存储一阶二阶导数的单元结构和标准BP算法中的结构相同,不会对存储造成大的负担,可使编程易于实现.计算机的仿真实验结果表明,这种方法是切实有效的.
Bahadir, Elif
2016-01-01
The purpose of this study is to examine a neural network based approach to predict achievement in graduate education for Elementary Mathematics prospective teachers. With the help of this study, it can be possible to make an effective prediction regarding the students' achievement in graduate education with Artificial Neural Networks (ANN). Two…
Institute of Scientific and Technical Information of China (English)
无
2008-01-01
Since the complexity and structural diversity of man-made compounds are considered,quantitative structure-activity relationships(QSARs)-based fast screening approaches are urgently needed for the assessment of the potential risk of endocrine disrupting chemicals(EDCs).The artificial neural networks(ANN)are capable of recognizing highly nonlinear relationships,so it will have a bright application prospect in building high-quality QSAR models.As a popular supervised training algorithm in ANN,back-propagation(BP)converges slowly and immerses in vibration frequently.In this paper,a research strategy that BP neural network was improved by conjugate gradient(CG)algorithm with a variable selection method based on genetic algorithm was applied to investigate the QSAR of EDCs.This resulted in a robust and highly predictive ANN model with R2 of 0.845 for the training set,q2 pred of 0.81 and root-mean-square error(RMSE) of 0.688 for the test set.The result shows that our method can provide a feasible and practical tool for the rapid screening of the estrogen activity of organic compounds.
William
2016-01-01
Image identification is one of the phases used in automated system, spesifically Chinese character recognition. Image recognition on Chinese chess is a process to recognize Chinese character on Chinese chess in order to obtain the number of each chess set. Due to the fact that Chinese character’s pattern has complex contours and strokes; Handwritten Chinese Character Recognition (HCCR) is difficult to be recognized by new learners, especially humans. Based on the fact stated above, Chinese ch...
Bashkansky, Mark; Pruessner, Marcel W.; Vurgaftman, Igor; Kim, Mijin; Reintjes, J.
2016-05-01
Spontaneous parametric downconversion (SPDC) using periodically poled nonlinear optical crystals under the quasiphase- matching condition has found wide use in quantum optics. High efficiencies and good coupling to single-mode fibers resulted from using channel waveguides in crystals. It is often desirable to have a very narrow bandwidth for the signal and idler photons, but under the typical operating conditions, phase matching dictates the bandwidth of the SPDC to be of the order of inversion on the wavelength scale is required. In this work, we experimentally demonstrate SPDC in one-dimensional KTP-based waveguides with sub-micron poling for forward and backward interactions. Some of the spectral features of the generated light are accounted for by mode coupling theory in periodically poled waveguides but other features are as yet not explained.
Carrasco, Manuel; Garde, Andres; Murillo, Pilar; Serrano, Luis
2005-06-01
In this paper a novel design and implementation of a VLSI Analogue Neural Net based on Multi-Layer Perceptron (MLP) with on-chip Back Propagation (BP) learning algorithm suitable for the resolution of classification problems is described. In order to implement a general and programmable analogue architecture, the design has been carried out in a hierarchical way. In this way the net has been divided in synapsis-blocks and neuron-blocks providing an easy method for the analysis. These blocks basically consist on simple cells, which are mainly, the activation functions (NAF), derivatives (DNAF), multipliers and weight update circuits. The analogue design is based on current-mode translinear techniques using MOS transistors working in the weak inversion region in order to reduce both the voltage supply and the power consumption. Moreover, with the purpose of minimizing the noise, offset and distortion of even order, the topologies are fully-differential and balanced. The circuit, named ANNE (Analogue Neural NEt), has been prototyped and characterized as a proof of concept on CMOS AMI-0.5A technology occupying a total area of 2.7mm2. The chip includes two versions of neural nets with on-chip BP learning algorithm, which are respectively a 2-1 and a 2-2-1 implementations. The proposed nets have been experimentally tested using supply voltages from 2.5V to 1.8V, which is suitable for single cell lithium-ion battery supply applications. Experimental results of both implementations included in ANNE exhibit a good performance on solving classification problems. These results have been compared with other proposed Analogue VLSI implementations of Neural Nets published in the literature demonstrating that our proposal is very efficient in terms of occupied area and power consumption.
Diagnosis of Hydraulic Gate's Typical Faults Based on Backpropagation%基于BP网络的闸门典型故障诊断
Institute of Scientific and Technical Information of China (English)
唐建; 张梅军; 夏志高
2004-01-01
用BP网络实现闸门典型故障的诊断.信号依次经历小波除噪、归一化和去趋3个预处理过程,从处理前和处理后的信号中提取能有效描述信号特征的特征量作为网络输入.同时,为4种典型信号设立了相对应的网络输出,形成输入-输出样本对.网络用这些样本对训练自身.网络性能测试表明,它能有效识别典型故障,而没有训练过的模式,网络也能判断出其为陌生信号模式.
Institute of Scientific and Technical Information of China (English)
陈爱国; 叶家玮; 苏曙
2010-01-01
建立了基于系列60船模原始实验数据的船舶阻力计算3层BP神经网络系统,利用随机选取的检验样本和插值样本作为输入向量,应用输出与目标的线性回归、相关系数和相对误差,以及利用该神经网络绘制的曲线,验证了该神经网络的可靠性.在该神经网络的建立过程中,对训练函数、性能函数、传递函数、隐层神经无数和神经网络绘制的性能曲线进行了实验,并通过数据预处理方式,确定了最佳的船舶阻力计算3层BP神经网络系统.
基于BP网络的燃烧器火焰燃烧状态识别%Burner Flame Recognition Based on Backpropagation Neural Network
Institute of Scientific and Technical Information of China (English)
董晓峰; 高庆忠; 刘广生
2005-01-01
基于原有数字图像处理系统,根据采集的电站锅炉直流燃烧器和旋流燃烧器火焰图像,讨论了特征值的意义和提取方法,运用现代人工神经网络智能理论,设计并训练了BP网络实现燃烧状态实时判断的功能.
Institute of Scientific and Technical Information of China (English)
李志全; 樊春玲; 张志民; 刘文双
2000-01-01
提出了一种基于优化过程的结构自整定BP算法.针对误差函数的特征,进行了优化处理,提高了收敛速度:通过结构自整定使网络结构动态变化,在误差精度达到要求的同时实现了结构最优.
汽车追尾事故的BP网络模型研究%A Study of Backpropagation Neural Network Model for Car Tracing Cauda
Institute of Scientific and Technical Information of China (English)
熊和金; 刘清; 杨杰
2000-01-01
高速公路汽车追尾是一种严重的交通安全事故,引起了交通科技界的广泛重视.近几年来,人们试图从理论与技术上解决高速公路汽车追尾问题,其中建立追尾的数学模型是研究追尾现象的基础.文中在分析了汽车追尾的原因后,基于神经网络理论,建立了追尾的BP网络模型,并讨论了追尾预测系统的技术实现方案.
Expert System of Chinese Syntax Analysis Based on Backpropagation Networks%基于BP网络的汉语句法分析专家系统
Institute of Scientific and Technical Information of China (English)
王玉美; 阮晓钢
2003-01-01
提出了一种基于BP网络的汉语句法分析专家系统的设计方案.知识库采用产生式规则的知识表达方式,并将知识二元化存储在神经网络中.推理机采用神经网络进行推理.在论文的结尾给出了系统的运行实例,说明了该系统的有效性.
Institute of Scientific and Technical Information of China (English)
张弘强; 王春红
2005-01-01
根据影响教师评估成绩的指标构建了BP神经网络模型,应用MAT-LAB工具直接根据教师的表现来估算教师的评估成绩,对神经网络在教师评估中的应用作了新的尝试.
吸气式脉冲爆震发动机反传数值研究%Numerical Investigation of Backpropagation of Air-Breathing Pulse Detonation Engine
Institute of Scientific and Technical Information of China (English)
彭畅新; 王治武; 郑龙席; 陈星谷; 卢杰
2013-01-01
采用小能量点火方法,对吸气式脉冲爆震发动机的反传现象进行了数值研究.获得了反传现象的形成及传播特性.结果表明,吸气式脉冲爆震发动机的反传可以分为压力反传和燃气反传两部分.两者都是由缓燃和回传爆震引起的,回传爆震占主导作用.反传燃气的影响区域小于反传压力,由于尾部膨胀波的作用,反传燃气在一定位置会停止向上游进气道流动.反传压力会一直向进气道上游传播,并且迫使流道内的流体也向上游流动.等截面流道内反传压力减小的速度较慢,应对进气道进行优化设计.
Inverted Pendulum Control Based on Feed- forward backpropagation Algorithm of ANN%基于前馈BP网的倒立摆控制
Institute of Scientific and Technical Information of China (English)
张滔; 谢宗安
2004-01-01
本文分析了直线一级倒立摆的受力情况,建立状态空间数学模型,构造4输入1输出的三层前馈BP网络.运用引入动量项的改进BP算法对网络进行训练,并将这一网络对倒立摆进行实时控制.实验结果表明BP算法具有算法精度高,实现快,鲁棒性好等优点,应用前景广阔.
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.
for practical application are the major benefit over the conventional harmonic analysis. The under- estimation of the tidal range may depend on the number of the major tidal constituents and, consequently, be improved once the influencing factors are known... constituents were found (M 2 , K 1 , and O 1 in Fig. 12). Although the use of BPN at Mirtour may underestimate the real tidal event, as in Fig. 4, it has particular benefit for other locations where long-term tidal records are not available and a design water...
Yang, Tsung-Ming; Fan, Shu-Kai; Fan, Chihhao; Hsu, Nien-Sheng
2014-08-01
The purpose of this study is to establish a turbidity forecasting model as well as an early-warning system for turbidity management using rainfall records as the input variables. The Taipei Water Source Domain was employed as the study area, and ANOVA analysis showed that the accumulative rainfall records of 1-day Ping-lin, 2-day Ping-lin, 2-day Fei-tsui, 2-day Shi-san-gu, 2-day Tai-pin and 2-day Tong-hou were the six most significant parameters for downstream turbidity development. The artificial neural network model was developed and proven capable of predicting the turbidity concentration in the investigated catchment downstream area. The observed and model-calculated turbidity data were applied to developing the turbidity early-warning system. Using a previously determined turbidity as the threshold, the rainfall criterion, above which the downstream turbidity would possibly exceed this respective threshold turbidity, for the investigated rain gauge stations was determined. An exemplary illustration demonstrated the effectiveness of the proposed turbidity early-warning system as a precautionary alarm of possible significant increase of downstream turbidity. This study is the first report of the establishment of the turbidity early-warning system. Hopefully, this system can be applied to source water turbidity forecasting during storm events and provide a useful reference for subsequent adjustment of drinking water treatment operation.
Srinivas, Kadivendi; Vundavilli, Pandu R.; Manzoor Hussain, M.; Saiteja, M.
2016-09-01
Welding input parameters such as current, gas flow rate and torch angle play a significant role in determination of qualitative mechanical properties of weld joint. Traditionally, it is necessary to determine the weld input parameters for every new welded product to obtain a quality weld joint which is time consuming. In the present work, the effect of plasma arc welding parameters on mild steel was studied using a neural network approach. To obtain a response equation that governs the input-output relationships, conventional regression analysis was also performed. The experimental data was constructed based on Taguchi design and the training data required for neural networks were randomly generated, by varying the input variables within their respective ranges. The responses were calculated for each combination of input variables by using the response equations obtained through the conventional regression analysis. The performances in Levenberg-Marquardt back propagation neural network and radial basis neural network (RBNN) were compared on various randomly generated test cases, which are different from the training cases. From the results, it is interesting to note that for the above said test cases RBNN analysis gave improved training results compared to that of feed forward back propagation neural network analysis. Also, RBNN analysis proved a pattern of increasing performance as the data points moved away from the initial input values.
DEFF Research Database (Denmark)
Kobayashi, T.; Takara, H.; Sano, A.;
2013-01-01
We demonstrate 12-core fiber bidirectional long-haul transmission with sub-petabit-class capacity (2 × 344 Tb/s). Inter-core crosstalk management and multicarrier nonlinear compensation enabled the longest distance of 1500 km in SDM transmission with unidirectional capacity over 300 Tb/s....
Institute of Scientific and Technical Information of China (English)
宋晓娟; 马胜前
2007-01-01
应用MATLAB7.0中神经网络工具箱对BP神经网络的四种共轭梯度算法、标准算法和其它常用改进算法进行了仿真.并从训练速度、训练平均误差、收敛精度和所需内存空间等方面分别加以分析比较,指出针对不同的问题应选择相对较优的算法.
The Application of Strategy of Early-stopping in Back-propagation Neural Network%早停止策略在BP神经网络中的应用
Institute of Scientific and Technical Information of China (English)
李丽霞; 王彤; 范逢曦
2004-01-01
探讨了BP神经网络在应用中如何避免过度拟合情况的发生以防止网络的泛化功能降低.结果显示,在BP神经网络的训练中,早停止策略是避免过度拟合的一个有效方法.
Institute of Scientific and Technical Information of China (English)
王士同; 朱晓铭
2002-01-01
研究了模糊反向传播神经网络的函数逼近能力.研究结果给出了单调连续函数的FBP按序单调特性、连续映射定理以及非函数一致逼近定理,并且说明了FBP虽然能保持连续性映射,但不如原神经网络具有函数逼近能力.
Institute of Scientific and Technical Information of China (English)
张葛祥; 唐钟
2002-01-01
本文针对用GA训练NN权值时,花费的代价随精度的提高而剧烈增加的缺陷,提出了一种利用IGA较强的全局搜索能力和IBPA较强的局部搜索能力的结合算法;先利用IGA优化多层前馈神经网络的权值,然后再用IBPA提高搜索精度,有效地避免了IBPA易陷入局部极小点和IGA过早收敛的缺点,实验结果表明,此算法是有效的.
Institute of Scientific and Technical Information of China (English)
张茂元; 卢正鼎
2004-01-01
针对前馈神经网络应时变输入的自学习机制,采用李雅普诺夫函数来分析权值的收敛性,从而揭示BP神经网络算法朝最小误差方向调整权值的内在因素,并在分析单参数BP算法收敛性基础上,提出单参数变调整法则的离散型BP神经网络算法.
Institute of Scientific and Technical Information of China (English)
夏刚
2005-01-01
在分析前向型BP神经网络基本原理的基础上,建立了基于BP神经网络的柴油机工作过程模型,提出了建模与实际工作过程分离的方法,建模过程简洁,计算结果与实际值取得较好的吻合.
Institute of Scientific and Technical Information of China (English)
赵志勇; 张志礼; 李永利
2003-01-01
根据影响铁矿产品成本的指标构建了BP神经网络模型,应用MATLAB工具直接根据资源状况和生产状况来估算矿产品成本,对神经网络在矿产品成本计算中的应用作了新的尝试.
A new backpropagation algorithm with knowledge-based optimizing process%一种采用基于知识的优化过程的BP算法研究
Institute of Scientific and Technical Information of China (English)
朱江海; 戚飞虎
1997-01-01
针对BP算法的固有缺点,提出一种实用有效的改进算法.此算法在每次得到的搜索方向上,都进行一维优化,从而解决了BP算法须人工由经验选取固定步长而带来的弊病;针对误差函数高度非线性的特征,改进算法采用基于知识的处理过程,全面利用每一步计算所得到的误差函数值和导数进行误差函数曲面地形判断,指导搜索计算,使算法具有极好的收敛稳定性,同时大大提高了收敛速度.
Institute of Scientific and Technical Information of China (English)
蔡章利; 陈小林; 石为人
2007-01-01
考试是检查学生学习效果和教师教学水平的一种重要工具,利用现代科技手段对其进行定量分析并做出客观评价,有助于准确把握学生的学习水平,从而改进教学方法,提高教学质量.为了进一步提高利用B-P神经网络研究学生学习效果的综合评价方法的实用性,笔者从评价指标、评价模型、训练样本3个方面作了改进研究,建立了评价模型,给出了仿真结果.
Institute of Scientific and Technical Information of China (English)
王科俊; 金鸿章; 李国斌
1998-01-01
提出一种用于多层前向神经网络的快速收敛全局最优的综合反向传播算法.该算法使用了综合考虑绝对误差和相对误差的广义指标函数,采用了在网络输出空间搜索的反传技术,具有动态自调整学习率和动量因子,有神经元激活特性自调整、减少平台现象和消除学习过程中不平衡现象的能力.对比实验表明该算法有比基本BP算法快得多的收敛速度,并能取得全局最优解.
Institute of Scientific and Technical Information of China (English)
何池洋
2005-01-01
本文应用人工神经网络原理,采用Levenberg-Marquardt BP算法,对于吸收光谱严重重叠的PAR-Cu、Co、Ni、Zn四组分显色体系同时进行含量测定.Cu、Co、Ni、Zn的平均回收率分别为100%、99%、101%、99%.实验表明,与普通BP网络、改进型BP网络和径向基网络相比,该算法具有训练速度快、预测结果准确度高等特点,和光度法结合有望成为多组分分析的有效方法之一.
Energy Technology Data Exchange (ETDEWEB)
Rosas Ortiz, German
2000-01-01
Fault detection and diagnosis on transmission systems is an interesting area of investigation to Artificial Intelligence (AI) based systems. Neurocomputing is one of fastest growing areas of research in the fields of AI and pattern recognition. This work explores the possible suitability of pattern recognition approach of neural networks for fault detection and classification on power systems. The conventional detection techniques in modern relays are based in digital processing of signals and it need some time (around 1 cycle) to send a tripping signal, also they are likely to make incorrect decisions if the signals are noisy. It's desirable to develop a fast, accurate and robust approach that perform accurately for changing system conditions (like load variations and fault resistance). The aim of this work is to develop a novel technique based on Artificial Neural Networks (ANN), which explores the suitability of a pattern classification approach for fault detection and diagnosis. The suggested approach is based in the fact that when a fault occurs, a change in the system impedance take place and, as a consequence changes in amplitude and phase of line voltage and current signals take place. The ANN-based fault discriminator is trained to detect this changes as indicators of the instant of fault inception. This detector uses instantaneous values of these signals to make decisions. Suitability of using neural network as pattern classifiers for transmission systems fault diagnosis is described in detail a neural network design and simulation environment for real-time is presented. Results showing the performance of this approach are presented and indicate that it is fast, secure and exact enough, and it can be used in high speed fault detection and classification schemes. [Spanish] El diagnostico y la deteccion de fallas en sistemas de transmision es una area de interes en investigacion para sistemas basados en Inteligencia Artificial (IA). El calculo neuronal es una de las areas de investigacion de mas rapido crecimiento en el campo de la IA y el reconocimiento de patrones. Este trabajo explora la posible aplicabilidad de una tecnica de reconocimiento de patrones basada en redes neuronales para la deteccion y la clasificacion de fallas en un SEP. Las tecnicas convencionales de deteccion en los relevadores modernos se basan en un procesamiento digital de senales y requieren de cierto tiempo (alrededor de 1 ciclo) para enviar una senal de disparo, ademas de ser propensas a tomar decisiones incorrectas si las senales se encuentran contaminadas por ruido. Es deseable entonces desarrollar tecnicas que sean rapidas, exactas y robustas y que tengan un buen desempeno ante las condiciones cambiantes del sistema (como variaciones de carga y resistencia de falla, por ejemplo). El objetivo de este trabajo es desarrollar una tecnica novedosa basada en Redes Neuronales Atificales (RNA), la cual explora la aplicabilidad de la propuesta de reconocimiento de patrones para el diagnostico y deteccion de fallas. La tecnica sugerida se basa en el hecho de que cuando ocurre una falla, toma lugar un cambio de impedancia en el sistema y como consecuencia, cambios en la amplitud y fase de las senales de voltajes y corrientes de linea toman lugar. Se desarrolla un discriminador de fallas basado en redes neuronales que es entrenado para detectar estos cambios como indicadores del instante de ocurrencia de la falla. Este detector utiliza valores instantaneos de esas senales para tomar decisiones. Se describe a detalle la aplicabilidad de las redes neuronales como clasificadores de patrones para el diagnostico de fallas en sistemas de transmision y ademas, se presenta un diseno basado en redes neuronales y su ambiente de simulacion para la deteccion y clasificacion de fallas en tiempo real. Se presentan resultados del desempeno de esta tecnica que muestran que es rapida, segura y suficientemente exacta e indican su aplicabilidad dentro de esquemas de deteccion y clasificacion de fallas a muy alta velocidad.
Institute of Scientific and Technical Information of China (English)
梁哲浩; 鲁伟
2015-01-01
目的：探讨超声结合人工神经网络技术在女童中枢性性早熟诊断中的应用价值。方法选用170例性早熟女童进行常规超声检查子宫、卵巢，以其中130例的子宫体积、卵巢体积以及双侧卵巢最大卵泡内径为输入变量，以中枢性性早熟或非中枢性性早熟为输出变量，建立反向传播（BP）神经网络，并对另40例性早熟病例分类。结果利用 BP 神经网络结合常规超声检查对中枢性性早熟诊断的敏感性、特异性和准确率分别为95．0％、85．0％、90．0％。结论神经网络结合超声检查对中枢性性早熟的诊断和鉴别诊断具有较大的价值。%Objective To explore the value of ultrasonic combined with Back‐propagation artificial neural network in the diagnosis of central precocious puberty .Methods In 170 girls with precocious puberty ,the uterine and ovarian were ex‐amined with ultrasound ,in which 130 cases of uterine volume ,ovarian volume and bilateral ovarian follicles biggest diame‐ter were taken as inputs ,the central precocious puberty or non‐central precocious puberty as output variable .The back‐propagation (BP) neural network was established using such data .The other 40 cases were sorted by this BP neural net‐work .Results The diagnostic sensitivity ,specificity and accuracy of the BP neural network combination of ultrasound were 95 .0% ,85 .0% and 90 .0% ,respectively .Conclusion The BP neural network in combination of ultrasound is help‐ful in diagnosing central precocious puberty .
基于动态BP神经网络的财务危机预警算法研究%Efficient financial forecast based on dynamic back-propagation neural network
Institute of Scientific and Technical Information of China (English)
杨济亭
2013-01-01
Most of the classical methods in the investigations of financial forecast are generally based on a static pre-warning modeling by only exploring the single-period financial data, such as the signal-variable analysis, multiple-variables analysis, Logit regression analysis, which unfortunately ignores the potential influences from the historical data. In order to enhance the accuracy and stability of the financial forecasting, a promising dynamic back propagation ( BP) neural network relying on the Logit nonlinear mapping is proposed to perform financial forecasting. The historical panel data of financial companies is also fully taken into consideration in this new method, and different weights associated with different period data is used. The experimental results have demonstrated the effectiveness and the fair accuracy of the new forecasting model.%为进一步提升模型合理性和预测结果准确度,充分考虑公司财务情况历史值的影响,通过对不同时期的财务面板数据赋以不同权重,设计提出了一种基于Logit-动态BP神经网络的财务危机预警机制.实证结果显示,基于面板数据的新模型能更好地体现财务危机的发生机理,因而具备良好预警精度；在对财务危机公司及财务正常公司预警实验中,其预测性能均优于现有Logit回归分析模型和传统神经网络模型.
Institute of Scientific and Technical Information of China (English)
王振雷; 王建辉; 顾树生
2002-01-01
提出一种新的动态对角回归神经网络学习算法--局部动态误差反传算法(LDBP),该算法定义了一种新的局部均方差函数,并为回归单元建立一种新的学习结构.如果估计出各层的期望输出值,多层回归网络便可分解成一组自适应单元(Adaline),而每个单元可通过二次优化方法进行训练.采用可在有限步内找出全局最优解的共轭梯度法(CG)进行寻优.由于学习过程采用超线性搜索,大大减少了循环步数和计算时间.
Institute of Scientific and Technical Information of China (English)
王伟; 张玉; 吴应淼; 徐丽红; 王建清
2011-01-01
以‘庆元9015’香菇作为研究对象,以香菇样品的生长天数(d)和样品中总SO2-3含量、鲜香菇样品的SO2含量和采摘期的出菇时间(d)为输入层参数,以干香菇中SO2含量为输出层参数,建立三层BP神经网络模型,经过356次训练后模型收敛,模型具有满意的预测能力.%A three-layer BP network model was constructed with Qingyuan 9015 as the experimental material, and the mushroom growth days and the SO, content in mushrooms, the SO2 content in fresh mushroom samples and the mushroom producing time (days) in picking period were used as the four input parameters, and the SO2 content in dried mushroom was used as output parameter. After 356 times of training process, the model converged with satisfying predictive ability.
GENETIC ALGORITHM AND NEURAL NETWORK FOR OPTICAL CHARACTER RECOGNITION
Directory of Open Access Journals (Sweden)
Hendy Yeremia
2013-01-01
Full Text Available Computer system has been able to recognize writing as human brain does. The method mostly used for character recognition is the backpropagation network. Backpropagation network has been known for its accuracy because it allows itself to learn and improving itself thus it can achieve higher accuracy. On the other hand, backpropagation was less to be used because of its time length needed to train the network to achieve the best result possible. In this study, backpropagation network algorithm is combined with genetic algorithm to achieve both accuracy and training swiftness for recognizing alphabets. Genetic algorithm is used to define the best initial values for the networkâs architecture and synapsesâ weight thus within a shorter period of time, the network could achieve the best accuracy. The optimized backpropagation network has better accuracy and less training time than the standard backpropagation network. The accuracy in recognizing character differ by 10, 77%, with a success rate of 90, 77% for the optimized backpropagation and 80% accuracy for the standard backpropagation network. The training time needed for backpropagation learning phase improved significantly from 03 h, 14 min and 40 sec, a standard backpropagation training time, to 02 h 18 min and 1 sec for the optimized backpropagation network.
Hindcasting cyclonic waves using neural networks
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.; Rao, S.; Chakravarty, N.V.
network attractive. A neural network (NN) is an information processing system modeled on the structure of the dynamic process. Its merit is the ability to deal with information whose interrelation is ambiguous or whose functional relation is not clear... the backpropagation networks with updated algorithms are used in this paper. A brief description about the working of a back propagation neural network and three updated algorithms is given below. Backpropagation learning: Backpropagation is the most widely used...
Institute of Scientific and Technical Information of China (English)
黄德生; 刘延令; 金一和
2001-01-01
Objective Using BP Artificial Neural Network to study the Structure-Activity relationship between aromatics compounds and rat LD50, improved precision of toxicity prediction. Methods Firstly, Principal-Components-Analysis was adopted, then used BP ANN net-structure, and applied LM arithumetic as iteration method to train the network. Result We have discussed the relationship betwenn the structure parameter of 120 varieties of aromatics compound and rat LD50, and optimized the parameter design of the net to avoid over-fitting. I found that three-layer BP ANN which using log-sigmoid function, (i.e.) f(x)=1/1(+exp(-x)) as network transfer function got better fitting power. When the number of the hidden layer node is 13, the sum-square error is 0.36 which is far less than linear models. While the outer prediction precision of multiplayer BP ANN is higher than linear model in evidence, SSE=4.63. Conclusion We can consider that the classify power of multiplayer BP ANN is superior to linear nodels. Multilayer BP ANN can be use to predict toxicity of aromatics compounds, this method is better than traditional methods.%对结构参数采用主成分变换，再利用BP人工神经网络，采用LM算法作为迭代方法训练网络，预测检验集化合物的LD50。结果显示，BP人工神经网络可以用于定量毒性构效关系研究，含隐层的BP人工神经网络拟合能力明显优于传统方法，消除过度拟合后的多层BP网络预测能力也好于传统方法，可以用于预测。
Institute of Scientific and Technical Information of China (English)
姚卫峰; 曹琳琳; 单鸣秋; 张丽; 丁安伟
2010-01-01
目的:研究利用紫外-可见光谱预测不同产地的荆芥穗样品.方法:首先采用主成分分析法对10个产地的荆芥穗紫外-可见光谱进行降维处理,将累积贡献率达99.82%的前6个新变量进行反向传播神经网络的建模.结果:所建主成分-神经网络模型预测结果的识别率为100%,均方误差为0.0010.结论:主成分-神经网络预测模型可用于不同产地荆芥穗药材的分类识别,方法简便快速.
Institute of Scientific and Technical Information of China (English)
赵俊; 何碧; 程新路; 杨向东
2006-01-01
引入神经网络BP算法研究了36种炸药分子的撞击感度与其分子特征量间的关联关系.所有分子的特征量均采用DFT3P86/6-31G**方法计算所得.共设计了8个不同的输入方案,训练和预测结果表明,在均方误差允许范围内(0.6245-4,4900),网络是可靠的.同时,含特征量(HOMO-LUMO)*BDE的方案训练预测结果最理想,说明在网络结构和训练参数基本相同的情况下,(HOMO-LUMO)*BDE与撞击感度的关联度最强,仅次于它的特征量是(HOMO-LUMO).
Institute of Scientific and Technical Information of China (English)
周廷刚; 张笃见
2002-01-01
针对误差反向传播(Bp)算法局部收敛等局限性和单亲遗传(PGA)算法的优点,提出了融PGA和Bp为一体的单亲遗传误差反向传播(PGA-BP)算法,并用于县级生态农业的综合评价.评价结果表明:PGA-BP算法具有简便、高效、适应性强等优点,用于县级生态农业的综合评价是切实可行的.
Institute of Scientific and Technical Information of China (English)
蒋淑梅; 柯以侃; 时彦; 迟锡增; 周宏珠
1999-01-01
应用火焰原子吸收法(FASS)和石墨炉原子吸收法(GFASS)测定了脑栓塞患者和对照组(健康人)血清中Zn、Cu、Fe、Ca、Mg、Cr、Mn和Sr等的含量.对所得数据用反向传播神经网络(B-P法)进行分析,建立了脑栓塞的神经网络识别系统,预报识别率达100%,可作为该病诊断的一种有效的辅助手段.
Institute of Scientific and Technical Information of China (English)
吴义平; 开小明
2011-01-01
基于LM-BP神经网络算法,建立了饱和醇结构拓扑指数和物理化学性质与在不同固定相上保留指数相关性的人工神经模型.网络的传输函数都是线性的(Purelin函数),隐含层有3个神经元.饱和醇包括带有伯、仲、叔基官能团的直链和支链醇.讨论了隐含层神经元数对神经网络的影响,由19个饱和醇得到的网络适合预测测试醇的精确保留指数.与多元线性回归比较,人工神经网络模型预测结果略优于多元线性回归法.
Neural Networks For Electrohydrodynamic Effect Modelling
Directory of Open Access Journals (Sweden)
Wiesław Wajs
2004-01-01
Full Text Available This paper presents currently achieved results concerning methods of electrohydrodynamiceffect used in geophysics simulated with feedforward networks trained with backpropagation algorithm, radial basis function networks and generalized regression networks.
Neural Networks for Electrohydrodynamic Effect Modelling
Directory of Open Access Journals (Sweden)
Jolanta Gancarz
2004-01-01
Full Text Available This paper presents currently achieved results concerning methods of electrohydrodynamic effect used in geophysics simulated with feedforward networks trained with backpropagation algorithm, radial basis function networks and generalized regression networks.
Recurrent networks for wave forecasting
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.; Prabaharan, N.
, merchant vessel routing, nearshore construction, etc. more efficiently and safely. This paper presents an application of the Artificial Neural Network, namely Backpropagation Recurrent Neural Network (BRNN) with rprop update algorithm for wave forecasting...
Spectral Textile Detection in the VNIR/SWIR Band
2015-03-01
an algorithm called back-propagation is used to iteratively up- date all of the weights of the network. The backpropagation used in this thesis is...Beisley, Andrew P. Spectral Detection of Human Skin in VIS-SWIR Hyperspectral Imagery Without Radiometric Calibration. Master’s thesis, 2012. 6. Bernard...control number. PLEASE DO NOT RETURN YOUR FORM TO THE ABOVE ADDRESS. 1. REPORT DATE (DD–MM–YYYY) 2. REPORT TYPE 3. DATES COVERED (From — To) 4. TITLE
Mitigation of Linear and Nonlinear Impairments in Spectrally Efficient Superchannels
DEFF Research Database (Denmark)
Porto da Silva, Edson; Larsen, Knud J.; Zibar, Darko
2015-01-01
We assess numerically the performance of single-carrier digital backpropagation and maximum-likelihood sequence detection (MLSD) for DP-QPSK superchannel transmission. It is shown that MLSD is advantageous only against inter-carrier linear crosstalk.......We assess numerically the performance of single-carrier digital backpropagation and maximum-likelihood sequence detection (MLSD) for DP-QPSK superchannel transmission. It is shown that MLSD is advantageous only against inter-carrier linear crosstalk....
Energy Technology Data Exchange (ETDEWEB)
Nose Filho, Kenji; Araujo, Klayton A.M.; Maeda, Jorge L.Y.; Lotufo, Anna Diva P. [Universidade Estadual Paulista Julio de Mesquita Filho (UNESP), Ilha Solteira, SP (Brazil)], Emails: kenjinose@yahoo.com.br, klayton_ama@hotmail.com, jorge-maeda@hotmail.com, annadiva@dee.feis.unesp.br
2009-07-01
This paper presents a development and implementation of a program to electrical load forecasting with data from a Brazilian electrical company, using four different architectures of neural networks of the MATLAB toolboxes: multilayer backpropagation gradient descendent with momentum, multilayer backpropagation Levenberg-Marquardt, adaptive network based fuzzy inference system and general regression neural network. The program presented a satisfactory performance, guaranteeing very good results. (author)
A Novel Handwritten Letter Recognizer Using Enhanced Evolutionary Neural Network
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.
Recognition of Roasted Coffee Bean Levels using Image Processing and Neural Network
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%.
Stability Analysis of Neural Networks-Based System Identification
Directory of Open Access Journals (Sweden)
Talel Korkobi
2008-01-01
Full Text Available This paper treats some problems related to nonlinear systems identification. A stability analysis neural network model for identifying nonlinear dynamic systems is presented. A constrained adaptive stable backpropagation updating law is presented and used in the proposed identification approach. The proposed backpropagation training algorithm is modified to obtain an adaptive learning rate guarantying convergence stability. The proposed learning rule is the backpropagation algorithm under the condition that the learning rate belongs to a specified range defining the stability domain. Satisfying such condition, unstable phenomena during the learning process are avoided. A Lyapunov analysis leads to the computation of the expression of a convenient adaptive learning rate verifying the convergence stability criteria. Finally, the elaborated training algorithm is applied in several simulations. The results confirm the effectiveness of the CSBP algorithm.
Multiple modes of action potential initiation and propagation in mitral cell primary dendrite
DEFF Research Database (Denmark)
Chen, Wei R; Shen, Gongyu Y; Shepherd, Gordon M
2002-01-01
to support the back-propagation of the evoked somatic action potential to produce the second dendritic spike. In summary, the balance of spatially distributed excitatory and inhibitory inputs can dynamically switch the mitral cell firing among four different modes: axo-somatic initiation with back......-to-moderate olfactory nerve input, an action potential was initiated near the soma and then back-propagated into the primary dendrite. As olfactory nerve input increased, the initiation site suddenly shifted to the distal primary dendrite. Multi-compartmental modeling indicated that this abrupt shift of the spike......-propagation, dendritic initiation either with no forward propagation, forward propagation alone, or forward propagation followed by back-propagation....
A synaptically controlled, associative signal for Hebbian plasticity in hippocampal neurons.
Magee, J C; Johnston, D
1997-01-10
The role of back-propagating dendritic action potentials in the induction of long-term potentiation (LTP) was investigated in CA1 neurons by means of dendritic patch recordings and simultaneous calcium imaging. Pairing of subthreshold excitatory postsynaptic potentials (EPSPs) with back-propagating action potentials resulted in an amplification of dendritic action potentials and evoked calcium influx near the site of synaptic input. This pairing also induced a robust LTP, which was reduced when EPSPs were paired with non-back-propagating action potentials or when stimuli were unpaired. Action potentials thus provide a synaptically controlled, associative signal to the dendrites for Hebbian modifications of synaptic strength.
FUZZY NEURAL NETWORK FOR MACHINE PARTS RECOGNITION SYSTEM
Institute of Scientific and Technical Information of China (English)
Luo Xiaobin; Yin Guofu; Chen Ke; Hu Xiaobing; Luo Yang
2003-01-01
The primary purpose is to develop a robust adaptive machine parts recognition system. A fuzzy neural network classifier is proposed for machine parts classifier. It is an efficient modeling method. Through learning, it can approach a random nonlinear function. A fuzzy neural network classifier is presented based on fuzzy mapping model. It is used for machine parts classification. The experimental system of machine parts classification is introduced. A robust least square back-propagation (RLSBP) training algorithm which combines robust least square (RLS) with back-propagation (BP) algorithm is put forward. Simulation and experimental results show that the learning property of RLSBP is superior to BP.
Multigradient for Neural Networks for Equalizers
Directory of Open Access Journals (Sweden)
Chulhee Lee
2003-06-01
Full Text Available Recently, a new training algorithm, multigradient, has been published for neural networks and it is reported that the multigradient outperforms the backpropagation when neural networks are used as a classifier. When neural networks are used as an equalizer in communications, they can be viewed as a classifier. In this paper, we apply the multigradient algorithm to train the neural networks that are used as equalizers. Experiments show that the neural networks trained using the multigradient noticeably outperforms the neural networks trained by the backpropagation.
Using Genetic Algorithms in Secured Business Intelligence Mobile Applications
Directory of Open Access Journals (Sweden)
Silvia TRIF
2011-01-01
Full Text Available The paper aims to assess the use of genetic algorithms for training neural networks used in secured Business Intelligence Mobile Applications. A comparison is made between classic back-propagation method and a genetic algorithm based training. The design of these algorithms is presented. A comparative study is realized for determining the better way of training neural networks, from the point of view of time and memory usage. The results show that genetic algorithms based training offer better performance and memory usage than back-propagation and they are fit to be implemented on mobile devices.
Nonlinear Time Series Prediction Using Chaotic Neural Networks
Institute of Scientific and Technical Information of China (English)
LI KePing; CHEN TianLun
2001-01-01
A nonlinear feedback term is introduced into the evaluation equation of weights of the backpropagation algorithm for neural network, the network becomes a chaotic one. For the purpose of that we can investigate how the different feedback terms affect the process of learning and forecasting, we use the model to forecast the nonlinear time series which is produced by Makey-Glass equation. By selecting the suitable feedback term, the system can escape from the local minima and converge to the global minimum or its approximate solutions, and the forecasting results are better than those of backpropagation algorithm.``
Neural network modeling of a dolphin's sonar discrimination capabilities
DEFF Research Database (Denmark)
Andersen, Lars Nonboe; René Rasmussen, A; Au, WWL
1994-01-01
The capability of an echo-locating dolphin to discriminate differences in the wall thickness of cylinders was previously modeled by a counterpropagation neural network using only spectral information of the echoes [W. W. L. Au, J. Acoust. Soc. Am. 95, 2728–2735 (1994)]. In this study, both time...... 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 both a counterpropagation and a backpropagation neural network. The backpropagation network performed better than the counterpropagation network...
Neural Approach for Calculating Permeability of Porous Medium
Institute of Scientific and Technical Information of China (English)
ZHANG Ji-Cheng; LIU Li; SONG Kao-Ping
2006-01-01
@@ Permeability is one of the most important properties of porous media. It is considerably difficult to calculate reservoir permeability precisely by using single well-logging response and simple formula because reservoir is of serious heterogeneity, and well-logging response curves are badly affected by many complicated factors underground. We propose a neural network method to calculate permeability of porous media. By improving the algorithm of the back-propagation neural network, convergence speed is enhanced and better results can be achieved. A four-layer back-propagation network is constructed to effectively calculate permeability from well log data.
Institute of Scientific and Technical Information of China (English)
无
2003-01-01
Three-layer Adaptive Back-Propagation Neural Networks(TABPNN) are employed for the demodulation of spread spectrum signals in a multiple-access environment. A configuration employing three-layer adaptive Back-propagation neural networks is put forward for the demodulation of spread-spectrum signals in asynchronous Gaussian channels. The theoretical arguments and practical performance based on the neural networks are analyzed. The results show that whether the resistance to the multiple access interference or the robust to near-far effects, the proposed detector significantly outperforms not only the conventional detector but also the BP neural networks detector and is comparable to the optimum detector.
MPPT control of wind generation systems based on FNN with PSO algorithm
Energy Technology Data Exchange (ETDEWEB)
Hong, Chih-Ming; Lin, Whei-Min [Department of Electrical Engineering, National Sun Yat-Sen University, Kaosiung 80424 (Taiwan); Chen, Chiung-Hsing [Electronic Communication Engineering, National Kaohsiung Marine University, Kaohsiung 81157 (Taiwan); Ou, Ting-Chia [Institute of Nuclear Energy Research, Atomic Energy Council, Taoyuan 32546 (Taiwan)
2011-07-01
This paper presents the design of an on-line training fuzzy neural network (FNN) using back-propagation learning algorithm with particle swarm optimization (PSO) regulating controller for the induction generator (IG). The PSO is adopted in this study to adapt the learning rates in the back-propagation process of the FNN to improve the learning capability. The proposed output maximization control is achieved without mechanical sensors such as the wind speed or position sensor, and the new control system will deliver maximum electric power with light weight, high efficiency, and high reliability. The estimation of the rotor speed is designed on the basis of the sliding mode control theory.
A Connectionist Model of Stimulus Class Formation with a Yes/No Procedure and Compound Stimuli
Tovar, Angel E.; Chavez, Alvaro Torres
2012-01-01
We analyzed stimulus class formation in a human study and in a connectionist model (CM) with a yes/no procedure, using compound stimuli. In the human study, the participants were six female undergraduate students; the CM was a feed-forward back-propagation network. Two 3-member stimulus classes were trained with a similar procedure in both the…
Use of a Neural Network for Damage Detection and Location in a Steel Member
DEFF Research Database (Denmark)
Kirkegaard, Poul Henning; Rytter, A.
The paper explores the potential of using a Multilayer Perceptron (MLP) network trained with the Backpropagation algorithm for damage assessment of free-free cracked straight steel beam based on vibration measurements. The problem of damage assessment, i.e. detecting, locating and quantifying...
Speech Recognizing for Presentation Tool Navigation Using Back Propagation Artificial Neural Network
Directory of Open Access Journals (Sweden)
Hasanah Nur
2016-01-01
Full Text Available Backpropagation Artificial Neural Network (ANN is a well known branch of Artificial Intelligence and has been proven to solve various problems of complex speech recognizing in health [1], [2], education [4] and engineering [3]. Today, many kinds of presentation tools are used by society. One popular example is MsPowerpoint. The transition process between slides in presentation tools will be more easily done through speech, the sound emitted directly by the user during the presentation. This study uses research and development to create a simulation using Backpropagation ANN for speech recognition from number one to five to navigate slides of the presentation tool. The Backpropagation ANN consists of one input layer, one hidden layer with 100 neurons and one output layer. The simulation is built by using a Neural Network Toolbox Matlab R2014a. Speech samples were taken from five different people with wav format. This research shows that the Backpropagation ANN can be used as navigation through speech with 96% accuracy rate based on the network training result. Thesimulation can produce 63% accuracy based on 100 new speech samples from various sources.
Kv4 Potassium Channels Modulate Hippocampal EPSP-Spike Potentiation and Spatial Memory in Rats
Truchet, Bruno; Manrique, Christine; Sreng, Leam; Chaillan, Franck A.; Roman, Francois S.; Mourre, Christiane
2012-01-01
Kv4 channels regulate the backpropagation of action potentials (b-AP) and have been implicated in the modulation of long-term potentiation (LTP). Here we showed that blockade of Kv4 channels by the scorpion toxin AmmTX3 impaired reference memory in a radial maze task. In vivo, AmmTX3 intracerebroventricular (i.c.v.) infusion increased and…
Yorek, Nurettin; Ugulu, Ilker
2015-01-01
In this study, artificial neural networks are suggested as a model that can be "trained" to yield qualitative results out of a huge amount of categorical data. It can be said that this is a new approach applied in educational qualitative data analysis. In this direction, a cascade-forward back-propagation neural network (CFBPN) model was…
A comparison of SONAH and IBEM for near-field acoustic holography
DEFF Research Database (Denmark)
Juhl, Peter Møller
2008-01-01
implementations: Whereas SONAH performs the back-propagation of the sound field to a plane surface; the IBEM has no restrictions on the radiating geometry. On the other hand, IBEM requires the generation of a surface mesh and a time consuming solution process. The present paper compares the performance...
Jet analysis by neural networks in high energy hadron-hadron collisions
De Felice, P; Pasquariello, G; De Felice, P; Nardulli, G; Pasquariello, G
1995-01-01
We study the possibility to employ neural networks to simulate jet clustering procedures in high energy hadron-hadron collisions. We concentrate our analysis on the Fermilab Tevatron energy and on the k_\\bot algorithm. We consider both supervised multilayer feed-forward network trained by the backpropagation algorithm and unsupervised learning, where the neural network autonomously organizes the events in clusters.
SOLVING INVERSE KINEMATICS OF REDUNDANT MANIPULATOR BASED ON NEURAL NETWORK
Institute of Scientific and Technical Information of China (English)
无
2003-01-01
For the redundant manipulators, neural network is used to tackle the velocity inverse kinematics of robot manipulators. The neural networks utilized are multi-layered perceptions with a back-propagation training algorithm. The weight table is used to save the weights solving the inverse kinematics based on the different optimization performance criteria. Simulations verify the effectiveness of using neural network.
Institute of Scientific and Technical Information of China (English)
董一芬
2009-01-01
前馈神经网络中的向后传播算法(Backpropagation(BP)Algorithm)算法存在固有的缺陷,Levenberg-Marquardt神经网络算法可以有效地克服这一点BP算法的缺陷.本文给出了Levenberg-Marquardt算法.
1991-03-01
20 2. Perceptrons..................21 3. Adaline /Madaline................24 4. Backpropagation................28 a. General Architecture...perceptron called an Adaline (Adaptive Linear Element) , which was the basis of the first commercially successful neural network enterprise, the...Memistor corporation. They also developed a theorem which stated that an adaline and a perceptron are each capable of classifying any input space that could
Chen, Chau-Kuang
2010-01-01
Artificial Neural Network (ANN) and Support Vector Machine (SVM) approaches have been on the cutting edge of science and technology for pattern recognition and data classification. In the ANN model, classification accuracy can be achieved by using the feed-forward of inputs, back-propagation of errors, and the adjustment of connection weights. In…
The transport of sediment and nutrients from land application areas is an environmental concern. New methods are needed for estimating soil and nutrient concentrations of runoff from cropland areas on which manure is applied. Artificial Neural Networks (ANN) trained with a Backpropagation (BP) algor...
DEFF Research Database (Denmark)
S. Nadimi, Esmaeil; Nyholm Jørgensen, Rasmus; Blanes-Vidal, Victoria;
2012-01-01
perceptron (MLP)-based artificial neural network (ANN). The best performance of the ANN in terms of the mean squared error (MSE) and the convergence speed was achieved when it was initialized and trained using the Nguyen–Widrow and Levenberg–Marquardt back-propagation algorithms, respectively. The success...
Gas metal arc welding of butt joint with varying gap width based on neural networks
DEFF Research Database (Denmark)
Christensen, Kim Hardam; Sørensen, Torben
2005-01-01
squares has been used with the back-propagation algorithm for training the network, while a Bayesian regularization technique has been successfully applied for minimizing the risk of inexpedient over-training. Finally, a predictive closed-loop control strategy based on a so-called single-neuron self...
A Neural Network Approach for GMA Butt Joint Welding
DEFF Research Database (Denmark)
Christensen, Kim Hardam; Sørensen, Torben
2003-01-01
squares has been used with the back-propagation algorithm for training the network, while a Bayesian regularization technique has been successfully applied for minimizing the risk of inexpedient over-training. Finally, a predictive closed-loop control strategy based on a so-called single-neuron self...
Advances in Artificial Neural Networks - Methodological Development and Application
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...
Institute of Scientific and Technical Information of China (English)
无
2005-01-01
Prediction of the Dimensional Changes during Sintering using Backpropagation Algorithm，Prediction of the next stock price using neural network-extraction the feature to predict next stock price by filtering，Pulse mode neuron with piecewise linear activation function，Remarks on multi layer neural networks involving chaos neurons……
Performance of Multi-Channel DBP with Long-haul Frequency-Referenced Transmission
DEFF Research Database (Denmark)
Porto da Silva, Edson; Da Ros, Francesco; Zibar, Darko
2016-01-01
The impact of frequency referenced WDM source on the performance of dual polarization multi-channel digital backpropagation (MC-DBP) is experimentally investigated up to 4000 km of transmission. For a system with 4 × 8 GBd DP-QPSK, such approach allows 0.6 dB more MC-DBP Q2-factor gain in the non...
DEFF Research Database (Denmark)
Bhowmik, Subrata; Weber, Felix; Høgsberg, Jan Becker
2013-01-01
This paper presents a systematic design and training procedure for the feed-forward backpropagation neural network (NN) modeling of both forward and inverse behavior of a rotary magnetorheological (MR) damper based on experimental data. For the forward damper model, with damper force as output an...
Experimental Study of Nonlinear Phase Noise and its Impact on WDM Systems with DP-256QAM
DEFF Research Database (Denmark)
Yankov, Metodi Plamenov; Da Ros, Francesco; Porto da Silva, Edson
2016-01-01
A probabilistic method for mitigating the phase noise component of the non-linear interference in WDM systems with Raman amplification is experimentally demonstrated. The achieved gains increase with distance and are comparable to the gains of single-channel digital back-propagation....
Vibration Based Damage Assessment of a Civil Engineering Structures using a Neural Networks
DEFF Research Database (Denmark)
Kirkegaard, Poul Henning; Rytter, A.
In this paper the possibility of using a Multilayer Perceptron (MLP) network trained with the Backpropagation Algorith as a non-destructive damage assessment technique to locate and quantify a damage in Civil Engineering structures is investigated. Since artificial neural networks are proving...
On-line learning algorithms for locally recurrent neural networks.
Campolucci, P; Uncini, A; Piazza, F; Rao, B D
1999-01-01
This paper focuses on on-line learning procedures for locally recurrent neural networks with emphasis on multilayer perceptron (MLP) with infinite impulse response (IIR) synapses and its variations which include generalized output and activation feedback multilayer networks (MLN's). We propose a new gradient-based procedure called recursive backpropagation (RBP) whose on-line version, causal recursive backpropagation (CRBP), presents some advantages with respect to the other on-line training methods. The new CRBP algorithm includes as particular cases backpropagation (BP), temporal backpropagation (TBP), backpropagation for sequences (BPS), Back-Tsoi algorithm among others, thereby providing a unifying view on gradient calculation techniques for recurrent networks with local feedback. The only learning method that has been proposed for locally recurrent networks with no architectural restriction is the one by Back and Tsoi. The proposed algorithm has better stability and higher speed of convergence with respect to the Back-Tsoi algorithm, which is supported by the theoretical development and confirmed by simulations. The computational complexity of the CRBP is comparable with that of the Back-Tsoi algorithm, e.g., less that a factor of 1.5 for usual architectures and parameter settings. The superior performance of the new algorithm, however, easily justifies this small increase in computational burden. In addition, the general paradigms of truncated BPTT and RTRL are applied to networks with local feedback and compared with the new CRBP method. The simulations show that CRBP exhibits similar performances and the detailed analysis of complexity reveals that CRBP is much simpler and easier to implement, e.g., CRBP is local in space and in time while RTRL is not local in space.
The development of intelligent expert system with SAT for semiconductor
Energy Technology Data Exchange (ETDEWEB)
Kim, Jae Yeol; Shim, Jae Gi; Jeong, Hyun Jo; Cho, Young Tae; Kim, Chang Hyun; Ko, Myung Soo [Chosun University, Gwangju (Korea, Republic of)
2001-05-15
In this study, the researches classifying the artificial flaws in semiconductor packages are performed using pattern recognition technology. For this purposes image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtering, binary processing, edge detection and classifier selection is treated by BP(backpropagation). Specially, it is compared IP(image processing) and SOM(self-organizing map) as preprocessing method for dimensionality reduction for entrance into multi-layer perceptron(backpropagation). Also, the pattern recognition techniques is applied to the classification problem of semiconductor flaws as crack, delamination. According to this results, it is possible to acquire the recognition rate of 83.4% about delamination, 75.7% about crack for SOM, and to acquire the recognition rate of 100% for BP.
Flax, Michal
2015-01-01
Tato práce se zabývá simulací neuronových sítí a algoritmem Backpropagation. Simulace je akcelerována pomocí standardu OpenMP. Aplikace také umožňuje modifikovat strukturu neuronových sítí a simulovat tak nestandardní chování sítě. This thesis deals with neural network simulation and the Backpropagation algorithm. The simulation is accelerated using the OpenMP standard. The application is also able to modify the structure of neural networks and thus simulate their non-standard behavior. ...
Crop Classification by Forward Neural Network with Adaptive Chaotic Particle Swarm Optimization
Directory of Open Access Journals (Sweden)
Yudong Zhang
2011-05-01
Full Text Available This paper proposes a hybrid crop classifier for polarimetric synthetic aperture radar (SAR images. The feature sets consisted of span image, the H/A/α decomposition, and the gray-level co-occurrence matrix (GLCM based texture features. Then, the features were reduced by principle component analysis (PCA. Finally, a two-hidden-layer forward neural network (NN was constructed and trained by adaptive chaotic particle swarm optimization (ACPSO. K-fold cross validation was employed to enhance generation. The experimental results on Flevoland sites demonstrate the superiority of ACPSO to back-propagation (BP, adaptive BP (ABP, momentum BP (MBP, Particle Swarm Optimization (PSO, and Resilient back-propagation (RPROP methods. Moreover, the computation time for each pixel is only 1.08 × 10−7 s.
Liao, Pei-Hung; Hsu, Pei-Ti; Chu, William; Chu, Woei-Chyn
2015-06-01
This study applied artificial intelligence to help nurses address problems and receive instructions through information technology. Nurses make diagnoses according to professional knowledge, clinical experience, and even instinct. Without comprehensive knowledge and thinking, diagnostic accuracy can be compromised and decisions may be delayed. We used a back-propagation neural network and other tools for data mining and statistical analysis. We further compared the prediction accuracy of the previous methods with an adaptive-network-based fuzzy inference system and the back-propagation neural network, identifying differences in the questions and in nurse satisfaction levels before and after using the nursing information system. This study investigated the use of artificial intelligence to generate nursing diagnoses. The percentage of agreement between diagnoses suggested by the information system and those made by nurses was as much as 87 percent. When patients are hospitalized, we can calculate the probability of various nursing diagnoses based on certain characteristics.
Initial Investigation of Software-Based Bone-Suppressed Imaging
Energy Technology Data Exchange (ETDEWEB)
Park, Eunpyeong; Youn, Hanbean; Kim, Ho Kyung [Pusan National University, Busan (Korea, Republic of)
2015-05-15
Chest radiography is the most widely used imaging modality in medicine. However, the diagnostic performance of chest radiography is deteriorated by the anatomical background of the patient. So, dual energy imaging (DEI) has recently been emerged and demonstrated an improved. However, the typical DEI requires more than two projections, hence causing additional patient dose. The motion artifact is another concern in the DEI. In this study, we investigate DEI-like bone-suppressed imaging based on the post processing of a single radiograph. To obtain bone-only images, we use the artificial neural network (ANN) method with the error backpropagation-based machine learning approach. The computational load of learning process of the ANN is too heavy for a practical implementation because we use the gradient descent method for the error backpropagation. We will use a more advanced error propagation method for the learning process.
Multilayer perceptron, fuzzy sets, and classification
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.
Extraction of Symbolic Rules from Artificial Neural Networks
Kamruzzaman, S M
2010-01-01
Although backpropagation ANNs generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions cannot be explained as those of decision trees. In many applications, it is desirable to extract knowledge from trained ANNs for the users to gain a better understanding of how the networks solve the problems. A new rule extraction algorithm, called rule extraction from artificial neural networks (REANN) is proposed and implemented to extract symbolic rules from ANNs. A standard three-layer feedforward ANN is the basis of the algorithm. A four-phase training algorithm is proposed for backpropagation learning. Explicitness of the extracted rules is supported by comparing them to the symbolic rules generated by other methods. Extracted rules are comparable with other methods in terms of number of rules, average number of conditions for a rule, and predictive accuracy. Extensive experimental studies on several benchmarks classification ...
Face Recognition using Eigenfaces and Neural Networks
Directory of Open Access Journals (Sweden)
Mohamed Rizon
2006-01-01
Full Text Available In this study, we develop a computational model to identify the face of an unknown persons by applying eigenfaces. The eigenfaces has been applied to extract the basic face of the human face images. The eigenfaces is then projecting onto human faces to identify unique features vectors. This significant features vector can be used to identify an unknown face by using the backpropagation neural network that utilized euclidean distance for classification and recognition. The ORL database for this investigation consists of 40 people with various 400 face images had been used for the learning. The eigenfaces including implemented Jacobis method for eigenvalues and eigenvectors has been performed. The classification and recognition using backpropagation neural network showed impressive positive result to classify face images.
Energy Technology Data Exchange (ETDEWEB)
Song Kexing; Xing Jiandong; Dong Qiming; Liu Ping; Tian Baohong; Cao Xianjie
2005-06-15
Internal oxidation is a commercial method for producing oxide dispersion strengthened copper (ODS Cu). In this paper, the dilute Cu-Al alloy powders containing 0.26 wt% of Al have been internally oxidized at temperatures (T) from 700 to 1000 deg. C, for holding times (t) up to 10 h. The alumina particle size has been observed and determined by electron microscopy using the two-stage preshadowed carbon replica method. By the use of backpropagation network, the non-linear relationship between internal oxidation process parameters (T,t) and alumina particle size has been established on the base of dealing with the experimental data. The results show that the well-trained backpropagation neural network can predict the alumina particle size during internal oxidation precisely and the prediction values have sufficiently mined the basic domain knowledge of internal oxidation process. Therefore, a new way of optimizing process parameters has been provided by the authors.
An ANN Based Call Handoff Management Scheme for Mobile Cellular Network
Directory of Open Access Journals (Sweden)
P. P. Bhattacharya
2013-12-01
Full Text Available Handoff decisions are usually signal strength based because of simplicity and effectiveness. Apart fro m the conventional techniques, such as threshold and hyst eresis based schemes, recently many artificial intelligent techniques such as Fuzzy Logic, Artific ial Neural Network (ANN etc. are also used for tak ing handoff decision. In this paper, an Artificial Neur al Network based handoff algorithm is proposed and it’s performance is studied. We have used ANNhere for ta king fast and accurate handoff decision. In our proposed handoff algorithm, Backpropagation Neural Network model is used.The advantages of Backpropagation method are its simplicity and reaso nable speed. The algorithm is designed, tested and found to give optimum results.
Boundness of a Neural Network Weights Using the Notion of a Limit of a Sequence
Directory of Open Access Journals (Sweden)
Hazem Migdady
2014-06-01
Full Text Available feed forward neural network with backpropagation learning algorithm is considered as a black box learning classifier since there is no certain interpretation or nticipation of the behavior of a neural network weights. The weights of a neural network ar e considered as the learning tool of the classifier, and the learning task is performed by the repetition modification of those weights. This modification is performed using the delta rule which is mainly usedin the gradient descent technique. In this article a proof is provided that helps to understand and explain the behavior of the weights in a feed forward neural network with backpropagation learning algorithm. Also, it illustrates why a feed forward neural network is not always guaranteed to converge in a global minimum. Moreover, the proof shows that the weights in t he neural network are upper bounded (i.e. they do not approach infinity.
Boundness of a Neural Network Weights Using the Notion of a Limit of a Sequence
Directory of Open Access Journals (Sweden)
Hazem Migdady
2014-05-01
Full Text Available feed forward neural network with backpropagation learning algorithm is considered as a black box learning classifier since there is no certain interpretation or anticipation of the behavior of a neural network weights. The weights of a neural network are considered as the learning tool of the classifier, and the learning task is performed by the repetition modification of those weights. This modification is performed using the delta rule which is mainly used in the gradient descent technique. In this article a proof is provided that helps to understand and explain the behavior of the weights in a feed forward neural network with backpropagation learning algorithm. Also, it illustrates why a feed forward neural network is not always guaranteed to converge in a global minimum. Moreover, the proof shows that the weights in the neural network are upper bounded (i.e. they do not approach infinity.
Directory of Open Access Journals (Sweden)
Khondker Jahid Reza
2014-01-01
Full Text Available Ultra Wideband is one of the promising microwave imaging techniques for breast tumor prognosis. The basic principle of tumor detection depends on the dielectric properties discrepancies between healthy and tumorous tissue. Usually, the tumor affected tissues scatter more signal than the healthy one and are used for early tumor detection through received pulses. Feedforward backpropagation neural network(NN was so far used for some research works by showing its detection efficiency up to 1mm (radius size with 95.8% accuracy. This paper introduces an efficient feature extraction method to further improve the performance by considering four main features of backpropagation NN. This performance is being increased to 99.99%. This strategy is well justified for classifying the normal and tumor affected breast with 100% accuracy in its early stage. It also enhances the training and testing performances by reducing the required duration. The overall performance is 99.99% verified by using thirteen different tumor sizes.
Rule Extraction using Artificial Neural Networks
Kamruzzaman, S M
2010-01-01
Artificial neural networks have been successfully applied to a variety of business application problems involving classification and regression. Although backpropagation neural networks generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions are not as interpretable as those of decision trees. In many applications, it is desirable to extract knowledge from trained neural networks so that the users can gain a better understanding of the solution. This paper presents an efficient algorithm to extract rules from artificial neural networks. We use two-phase training algorithm for backpropagation learning. In the first phase, the number of hidden nodes of the network is determined automatically in a constructive fashion by adding nodes one after another based on the performance of the network on training data. In the second phase, the number of relevant input units of the network is determined using pruning algorithm. The ...
FDI and Accommodation Using NN Based Techniques
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.
Embodiment of Learning in Electro-Optical Signal Processors
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 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.
DEFF Research Database (Denmark)
Prato, Carlo Giacomo; Gitelman, Victoria; Bekhor, Shlomo
2011-01-01
on 1,793 fatal traffic accidents occurred during the period between 2003 and 2006 and applies Kohonen and feed-forward back-propagation neural networks with the objective of extracting from the data typical patterns and relevant factors. Kohonen neural networks reveal five compelling accident patterns....... Feed-forward back-propagation neural networks indicate that sociodemographic characteristics of drivers and victims, accident location, and period of the day are extremely relevant factors. Accident patterns suggest that countermeasures are necessary for identified problems concerning mainly vulnerable...... road users such as pedestrians, cyclists, motorcyclists and young drivers. A “safe-system” integrating a system approach for the design of countermeasures and a monitoring process of performance indicators might address the priorities highlighted by the neural networks....
López-Rosales, L; Gallardo-Rodríguez, J J; Sánchez-Mirón, A; Contreras-Gómez, A; García-Camacho, F; Molina-Grima, E
2013-10-01
This study examines the use of artificial neural networks as predictive tools for the growth of the dinoflagellate microalga Protoceratium reticulatum. Feed-forward back-propagation neural networks (FBN), using Levenberg-Marquardt back-propagation or Bayesian regularization as training functions, offered the best results in terms of representing the nonlinear interactions among all nutrients in a culture medium containing 26 different components. A FBN configuration of 26-14-1 layers was selected. The FBN model was trained using more than 500 culture experiments on a shake flask scale. Garson's algorithm provided a valuable means of evaluating the relative importance of nutrients in terms of microalgal growth. Microelements and vitamins had a significant importance (approximately 70%) in relation to macronutrients (nearly 25%), despite their concentrations in the culture medium being various orders of magnitude smaller. The approach presented here may be useful for modelling multi-nutrient interactions in photobioreactors.
Directory of Open Access Journals (Sweden)
Rohmatulloh 1
2007-12-01
Full Text Available This paper discussed quality improvement of black tea using fuzzy approach on quality functions deployment and the development of backpropagation neural the software NWP II plus. The research was conducted at PTPN VIII tea industry, Goalpara plantation. Result of the study showed that, parameter first priority based on customer evaluation was tea flavour. The Important process parameter of black tea based on result of fuzzy relationship matrix was the withering process. Based on the test of “trial and error” of network training process, the best network architecture for withering process monitoring [3-15-1] was obtained, that is 3 neurons in input layer, 15 neurons in hidden layer and 1 neuron in output layer. Three inputs and output consist of time, flow, temperature and moisture content. The result sugges that development of backpropagation neural network can be used for process evaluation of withering processes.
Energy Technology Data Exchange (ETDEWEB)
Lin, Whei-Min; Hong, Chih-Ming [Department of Electrical Engineering, National Sun Yat-Sen University, Kaohsiung 80424 (China)
2010-06-15
To achieve maximum power point tracking (MPPT) for wind power generation systems, the rotational speed of wind turbines should be adjusted in real time according to wind speed. In this paper, a Wilcoxon radial basis function network (WRBFN) with hill-climb searching (HCS) MPPT strategy is proposed for a permanent magnet synchronous generator (PMSG) with a variable-speed wind turbine. A high-performance online training WRBFN using a back-propagation learning algorithm with modified particle swarm optimization (MPSO) regulating controller is designed for a PMSG. The MPSO is adopted in this study to adapt to the learning rates in the back-propagation process of the WRBFN to improve the learning capability. The MPPT strategy locates the system operation points along the maximum power curves based on the dc-link voltage of the inverter, thus avoiding the generator speed detection. (author)
Handwritten Farsi Character Recognition using Artificial Neural Network
Ahangar, Reza Gharoie
2009-01-01
Neural Networks are being used for character recognition from last many years but most of the work was confined to English character recognition. Till date, a very little work has been reported for Handwritten Farsi Character recognition. In this paper, we have made an attempt to recognize handwritten Farsi characters by using a multilayer perceptron with one hidden layer. The error backpropagation algorithm has been used to train the MLP network. In addition, an analysis has been carried out to determine the number of hidden nodes to achieve high performance of backpropagation network in the recognition of handwritten Farsi characters. The system has been trained using several different forms of handwriting provided by both male and female participants of different age groups. Finally, this rigorous training results an automatic HCR system using MLP network. In this work, the experiments were carried out on two hundred fifty samples of five writers. The results showed that the MLP networks trained by the err...
A hybrid Evolutionary Functional Link Artificial Neural Network for Data mining and Classification
Directory of Open Access Journals (Sweden)
Faissal MILI
2012-08-01
Full Text Available This paper presents a specific structure of neural network as the functional link artificial neural network (FLANN. This technique has been employed for classification tasks of data mining. In fact, there are a few studies that used this tool for solving classification problems. In this present research, we propose a hybrid FLANN (HFLANN model, where the optimization process is performed using 3 known population based techniques such as genetic algorithms, particle swarm and differential evolution. This model will be empirically compared to FLANN based back-propagation algorithm and to others classifiers as decision tree, multilayer perceptron based back-propagation algorithm, radical basic function, support vector machine, and K-nearest Neighbor. Our results proved that the proposed model outperforms the other single model. (Abstract
Classification of Rat FTIR Colon Cancer Data Using Waveletsand BPNN
Institute of Scientific and Technical Information of China (English)
CHENG,Cungui; XIONG,Wei; TIAN,Yumei
2009-01-01
A feature extracting method based on wavelets for horizontal attenuated total reflectance Fourier transform in-frared spectroscopy (HATR-FTIR) and the cancer classification using artificial neural network trained with back-propagation algorithm is presented. The FTIR data collected from 36 normal Sprague-dawley (SD) rats, 60 1,2-DMH-induced SD rats, and 44 second generation rats of those induced rats were first preprocessed. Then, 12 feature variants were extracted using continuous wavelet analysis. Based on BPNN classification, all spectra were classified into two categories: normal and abnormal ones. The accuracy values of identifying normal, dysplastic, early carcinoma, and advanced carcinoma were 100%, 94%, 97.5%, and 100%, respectively. This result indicated that FTIR with continuous wavelet transform (CWT) and the back-propagation neural network (BPNN) could ef- fectively and easily diagnose colon cancer in its early stages.
Tighter Lower Bounds on Mutual Information for Fiber-Optic Channels
Irukulapati, Naga V; Agrell, Erik; Johannisson, Pontus; Wymeersch, Henk
2016-01-01
In fiber-optic communications, evaluation of mutual information (MI) is still an open issue due to the unavailability of an exact and mathematically tractable channel model. Traditionally, lower bounds on MI are computed by approximating the (original) channel with an auxiliary forward channel. In this paper, lower bounds are computed using an auxiliary backward channel, which has not been previously considered in the context of fiber-optic communications. Distributions obtained through two variations of the stochastic digital backpropagation (SDBP) algorithm are used as auxiliary backward channels and these bounds are compared with bounds obtained through the conventional digital backpropagation (DBP). Through simulations, higher information rates were achieved with SDBP compared with DBP, which implies that tighter lower bound on MI can be achieved through SDBP.
Developing energy forecasting model using hybrid artificial intelligence method
Institute of Scientific and Technical Information of China (English)
Shahram Mollaiy-Berneti
2015-01-01
An important problem in demand planning for energy consumption is developing an accurate energy forecasting model. In fact, it is not possible to allocate the energy resources in an optimal manner without having accurate demand value. A new energy forecasting model was proposed based on the back-propagation (BP) type neural network and imperialist competitive algorithm. The proposed method offers the advantage of local search ability of BP technique and global search ability of imperialist competitive algorithm. Two types of empirical data regarding the energy demand (gross domestic product (GDP), population, import, export and energy demand) in Turkey from 1979 to 2005 and electricity demand (population, GDP, total revenue from exporting industrial products and electricity consumption) in Thailand from 1986 to 2010 were investigated to demonstrate the applicability and merits of the present method. The performance of the proposed model is found to be better than that of conventional back-propagation neural network with low mean absolute error.
Intelligent Detection of Drill Wear
Liu, T. I.; Chen, W. Y.; Anatharaman, K. S.
1998-11-01
Backpropagation neural networks (BPNs) were used for on-line detection of drill wear. The neural network consisted of three layers: input, hidden, and output. The input vector comprised drill size, feed rate, spindle speed, and eight features obtained by processing the thrust and torque signals. The output was the drill wear state which either usable or failure. Drilling experiments with various drill sizes, feed rates and spindle speeds were carried out. The learning process was performed effectively by utilising backpropagation with smoothing and an activation function slope. The on-line detection of drill wear states using BPNs achieved 100% reliability even when the drill size, feed rate and spindle speed were changed. In other words, the developed on-line drill wear detection systems have very high robustness and hence can be used in very complex production environments, such as flexible manufacturing systems.
An application of Hamiltonian neurodynamics using Pontryagin's Maximum (Minimum) Principle.
Koshizen, T; Fulcher, J
1995-12-01
Classical optimal control methods, notably Pontryagin's Maximum (Minimum) Principle (PMP) can be employed, together with Hamiltonians, to determine optimal system weights in Artificial Neural dynamical systems. A new learning rule based on weight equations derived using PMP is shown to be suitable for both discrete- and continuous-time systems, and moreover, can also be applied to feedback networks. Preliminary testing shows that this PMP learning rule compares favorably with Standard BackPropagations (SBP) on the XOR problem.
Automatic detection of intruders using a neural network
Carvalho, Fernando D.; Novo, Pedro; Pais, Cassiano P.; Rodrigues, Fernando C.; Rego, Toste
1992-09-01
A system is presented that applies a neural network to a video surveillance system. It consists of a pre-processing unit that extract high level information from images and introduces it in the neural network. This system can learn in operational conditions while under the supervision of an unskilled operator. It uses the error backpropagation learning algorithm in a multilayer perceptron structure. The results obtained show that the system performs well, and with a high degree of efficiency.
Applying Neural Network in Evaporative Cooler Performance Prediction
Institute of Scientific and Technical Information of China (English)
QIANG Tian-wei; SHEN Heng-gen; HUANG Xiang; XUAN Yong-mei
2007-01-01
The back-propagation (BP) neural network is created to predict the performance of a direct evaporative cooling (DEC) air conditioner with GLASdek pads. The experiment data about the performance of the DEC air conditioner are obtained. Some experiment data are used to train the network until these data can approximate a function, then, simulate the network with the remanent data. The predicted result shows satisfying effects.
Beyond Hebb XOR and biological learning
Klemm, K; Schuster, H G; Klemm, Konstantin; Bornholdt, Stefan; Schuster, Heinz Georg
1999-01-01
A learning algorithm for multilayer neural networks based on biologically plausible mechanisms is studied. Motivated by findings in experimental neurobiology, we consider synaptic averaging in the induction of plasticity changes, which happen on a slower time scale than firing dynamics. This mechanism is shown to enable learning of the exclusive-or (XOR) problem without the aid of error back-propagation, as well as to increase robustness of learning in the presence of noise.
Energy Technology Data Exchange (ETDEWEB)
Zio, Enrico; Pedroni, Nicola; Broggi, Matteo; Golea, Lucia Roxana [Polytechnic of Milan, Milan (Italy)
2009-12-15
In this paper, an infinite impulse response locally recurrent neural network (IIR-LRNN) is employed for modelling the dynamics of the Lead Bismuth Eutectic eXperimental Accelerator Driven System (LBE-XADS). The network is trained by recursive back-propagation (RBP) and its ability in estimating transients is tested under various conditions. The results demonstrate the robustness of the locally recurrent scheme in the reconstruction of complex nonlinear dynamic relationships
Image Segmentation Based on Support Vector Machine
Institute of Scientific and Technical Information of China (English)
XU Hai-xiang; ZHU Guang-xi; TIAN Jin-wen; ZHANG Xiang; PENG Fu-yuan
2005-01-01
Image segmentation is a necessary step in image analysis. Support vector machine (SVM) approach is proposed to segment images and its segmentation performance is evaluated.Experimental results show that: the effects of kernel function and model parameters on the segmentation performance are significant; SVM approach is less sensitive to noise in image segmentation; The segmentation performance of SVM approach is better than that of back-propagation multi-layer perceptron (BP-MLP) approach and fuzzy c-means (FCM) approach.
2014-01-01
We derive a synaptic weight update rule for learning temporally precise spike train to spike train transformations in multilayer feedforward networks of spiking neurons. The framework, aimed at seamlessly generalizing error backpropagation to the deterministic spiking neuron setting, is based strictly on spike timing and avoids invoking concepts pertaining to spike rates or probabilistic models of spiking. The derivation is founded on two innovations. First, an error functional is proposed th...
Using Genetic Algorithms in Secured Business Intelligence Mobile Applications
Silvia TRIF
2011-01-01
The paper aims to assess the use of genetic algorithms for training neural networks used in secured Business Intelligence Mobile Applications. A comparison is made between classic back-propagation method and a genetic algorithm based training. The design of these algorithms is presented. A comparative study is realized for determining the better way of training neural networks, from the point of view of time and memory usage. The results show that genetic algorithms based training offer bette...
A selective learning method to improve the generalization of multilayer feedforward neural networks.
2001-01-01
Multilayer feedforward neural networks with backpropagation algorithm have been used successfully in many applications. However, the level of generalization is heavily dependent on the quality of the training data. That is, some of the training patterns can be redundant or irrelevant. It has been shown that with careful dynamic selection of training patterns, better generalization performance may be obtained. Nevertheless, generalization is carried out independently of the novel patterns to b...
Rule Extraction using Artificial Neural Networks
2010-01-01
Artificial neural networks have been successfully applied to a variety of business application problems involving classification and regression. Although backpropagation neural networks generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions are not as interpretable as those of decision trees. In many applications, it is desirable to extract knowledge from trained neural networks so that the users can...
Yousefi, Fakhri; Karimi, Hajir; Mohammadiyan, Somayeh
2016-11-01
This paper applies the model including back-propagation network (BPN) and principal component analysis (PCA) to estimate the effective viscosity of carbon nanotubes suspension. The effective viscosities of multiwall carbon nanotubes suspension are examined as a function of the temperature, nanoparticle volume fraction, effective length of nanoparticle and the viscosity of base fluids using artificial neural network. The obtained results by BPN-PCA model have good agreement with the experimental data.
Institute of Scientific and Technical Information of China (English)
REN Hongwu; FANG Zujie
2000-01-01
A backpropagation (BP) network is applied to the inversion of spatially resolved diffuse reflectance from turbid media and then to determine its optical properties. A standard BP network may be trapped to the local minimum. A BP network with variable momentum and variable leaning rate can reduce this effect. After being trained, this network will produce reduced scattering coefficients and absorption coefficients when the spatially resolved diffuse reflectance are fed to its input.
Training product unit neural networks with genetic algorithms
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.
Mónica Bocco; Gustavo Ovando; Silvina Sayago
2006-01-01
The objective of this work was to develop neural network models of backpropagation type to estimate solar radiation based on extraterrestrial radiation data, daily temperature range, precipitation, cloudiness and relative sunshine duration. Data from Córdoba, Argentina, were used for development and validation. The behaviour and adjustment between values observed and estimates obtained by neural networks for different combinations of input were assessed. These estimations showed root mean squ...
Khaled Mammar; Abdelkader Chaker
2012-01-01
The paper is focused especially on presenting possibilities of applying artificial neural networks at creating the optimal model PEM fuel cell. Various ANN approaches have been tested; the back-propagation feed-forward networks show satisfactory performance with regard to cell voltage prediction. The model is then used in a power system for residential application. This models include an ANN fuel cell stack model, reformer model and DC/AC inverter model. Furthermore a neural network (NNTC) an...
2010-01-01
Back-propagation with gradient method is the most popular learning algorithm for feed-forward neural networks. However, it is critical to determine a proper fixed learning rate for the algorithm. In this paper, an optimized recursive algorithm is presented for online learning based on matrix operation and optimization methods analytically, which can avoid the trouble to select a proper learning rate for the gradient method. The proof of weak convergence of the proposed algorithm also is given...
Visual Working Efficiency Analysis Method of Cockpit Based On ANN
Directory of Open Access Journals (Sweden)
Yingchun CHEN
2012-09-01
Full Text Available The Artificial Neural Networks method is applied on visual working efficiency of cockpit. A Self-Organizing Map (SOM network is demonstrated selecting material with near properties. Then a Back-Propagation (BP network automatically learns the relationship between input and output. After a set of training, the BP network is able to estimate material characteristics using knowledge and criteria learned before. Results indicate that trained network can give effective prediction for material.
Training two-layered feedforward networks with variable projection method.
Kim, C T; Lee, J J
2008-02-01
The variable projection (VP) method for separable nonlinear least squares (SNLLS) is presented and incorporated into the Levenberg-Marquardt optimization algorithm for training two-layered feedforward neural networks. It is shown that the Jacobian of variable projected networks can be computed by simple modification of the backpropagation algorithm. The suggested algorithm is efficient compared to conventional techniques such as conventional Levenberg-Marquardt algorithm (LMA), hybrid gradient algorithm (HGA), and extreme learning machine (ELM).
Control of a hybrid compensator in a power network by an artificial neural network
Directory of Open Access Journals (Sweden)
I. S. Shaw
1998-07-01
Full Text Available Increased interest in the elimination of distortion in electrical power networks has led to the development of various compensator topologies. The increasing cost of electrical energy necessitates the cost-effective operation of any of these topologies. This paper considers the development of an artificial neural network based controller, trained by means of the backpropagation method, that ensures the cost-effective operation of the hybrid compensator consisting of various converters and filters.
Neural-estimator for the surface emission rate of atmospheric gases
Paes, F F
2009-01-01
The emission rate of minority atmospheric gases is inferred by a new approach based on neural networks. The neural network applied is the multi-layer perceptron with backpropagation algorithm for learning. The identification of these surface fluxes is an inverse problem. A comparison between the new neural-inversion and regularized inverse solution id performed. The results obtained from the neural networks are significantly better. In addition, the inversion with the neural netwroks is fster than regularized approaches, after training.
Forecasting Exchange Rate Using Neural Networks
Raksaseree, Sukhita
2009-01-01
The artificial neural network models become increasingly popular among researchers and investors since many studies have shown that it has superior performance over the traditional statistical model. This paper aims to investigate the neural network performance in forecasting foreign exchange rates based on backpropagation algorithm. The forecast of Thai Baht against seven currencies are conducted to observe the performance of the neural network models using the performance criteria for both ...
Application of Artificial Neural Network in Indicator Diagram
Institute of Scientific and Technical Information of China (English)
WuXiaodong; JiangHua; HanGuoqing
2004-01-01
Indicator diagram plays an important role in identifying the production state of oil wells. With an ability to reflect any non-linear mapping relationship, the artificial neural network (ANN) can be used in shape identification. This paper illuminates ANN realization in identifying fault kinds of indicator diagrams, including a back-propagation algorithm, characteristics of the indicator diagram and some examples. It is concluded that the buildup of a neural network and the abstract of indicator diagrams are important to successful application.
MEASUREMENT AND CORRELATION OF SOLUBILITY OF CAFFEINE IN WATER AND ETHANOL%咖啡因在水和乙醇中的溶解度及其关联
Institute of Scientific and Technical Information of China (English)
韩佳宾; 王静康
2004-01-01
The solubility of caffeine in water and ethanol at 0—50 ℃ was measured using the laser method. The results were regressed with an empirical equation and simplified EOS correlation. A 2 - 2 - 1 backpropagation (BP) artificial neural network (ANN) model was selected from many other models. The prediction of interpolation and extrapolation of the data was made with trained 2 - 2 - 1 BP ANN model. The result was satisfactory.
Geyer, Hannes; Mandischer, Martin; Ulbig, Peter
2001-01-01
In this paper we report results for the prediction of thermodynamic properties based on neural networks, evolutionary algorithms and a combination of them. We compare backpropagation trained networks and evolution strategy trained networks with two physical models. Experimental data for the enthalpy of vaporization were taken from the literature in our investigation. The input information for both neural network and physical models consists of parameters describing the molecular structure of ...
Christie, B R; Magee, J C; Johnston, D
1996-01-01
Long-term depression (LTD) of synaptic efficacy at CA1 synapses is believed to be a Ca(2+)-dependent process. We used high-speed fluorescence imaging and patch-clamp techniques to quantify the spatial distribution of changes in intracellular Ca2+ accompanying the induction of LTD at Schaffer collateral synapses in CA1 pyramidal neurons. Low-frequency stimulation (3 Hz), which was subthreshold for action potentials, produced small changes in [Ca2+]i and failed to elicit LTD. Increasing the stimulus strength so that action potentials were generated produced both robust LTD and increases in [Ca2+]i. Back-propagating action potentials at 3 Hz in the absence of synaptic stimulation also produced increases in [Ca2+]i, but failed to induce LTD. When subthreshold synaptic stimulation was paired with back-propagating action potentials, however, large increases in [Ca2+]i were observed and robust LTD was induced. The LTD was blocked by the N-methyl-D-aspartate receptor (NMDAr) antagonist APV, and stimulus-induced increases in [Ca2+]i were reduced throughout the neuron under these conditions. The LTD was also dependent on Ca2+ influx via voltage-gated Ca2+ channels (VGCCs), because LTD was severely attenuated or blocked by both nimodipine and Ni2+. These findings suggest that back-propagating action potentials can exert a powerful control over the induction of LTD and that both VGCCs and NMDArs are involved in the induction of this form of plasticity.
Implementation of neural network for color properties of polycarbonates
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.
Directory of Open Access Journals (Sweden)
Qian Wang
2016-01-01
Full Text Available Spectroscopy is an efficient and widely used quantitative analysis method. In this paper, a spectral quantitative analysis model with combining wavelength selection and topology structure optimization is proposed. For the proposed method, backpropagation neural network is adopted for building the component prediction model, and the simultaneousness optimization of the wavelength selection and the topology structure of neural network is realized by nonlinear adaptive evolutionary programming (NAEP. The hybrid chromosome in binary scheme of NAEP has three parts. The first part represents the topology structure of neural network, the second part represents the selection of wavelengths in the spectral data, and the third part represents the parameters of mutation of NAEP. Two real flue gas datasets are used in the experiments. In order to present the effectiveness of the methods, the partial least squares with full spectrum, the partial least squares combined with genetic algorithm, the uninformative variable elimination method, the backpropagation neural network with full spectrum, the backpropagation neural network combined with genetic algorithm, and the proposed method are performed for building the component prediction model. Experimental results verify that the proposed method has the ability to predict more accurately and robustly as a practical spectral analysis tool.
Application of neural networks for permanent magnet synchronous motor direct torque control
Institute of Scientific and Technical Information of China (English)
Zhang Chunmei; Liu Heping; Chen Shujin; Wang Fangjun
2008-01-01
Neural networks require a lot of training to understand the model of a plant or a process. Issues such as learning speed, stability, and weight convergence remain as areas of research and comparison of many training algorithms. The application of neural networks to control interior permanent magnet synchronous motor using direct torque control (DTC) is discussed. A neural network is used to emulate the state selector of the DTC. The neural networks used are the back-propagation and radial basis function. To reduce the training patterns and increase the execution speed of the training process, the inputs of switching table are converted to digital signals, i.e., one bit represent the flux error, one bit the torque error, and three bits the region of stator flux. Computer simulations of the motor and neural-network system using the two approaches are presented and compared. Discussions about the back-propagation and radial basis function as the most promising training techniques are presented, giving its advantages and disadvantages. The system using back-propagation and radial basis function networks controller has quick parallel speed and high torque response.
Dendritic potassium channels in hippocampal pyramidal neurons.
Johnston, D; Hoffman, D A; Magee, J C; Poolos, N P; Watanabe, S; Colbert, C M; Migliore, M
2000-05-15
Potassium channels located in the dendrites of hippocampal CA1 pyramidal neurons control the shape and amplitude of back-propagating action potentials, the amplitude of excitatory postsynaptic potentials and dendritic excitability. Non-uniform gradients in the distribution of potassium channels in the dendrites make the dendritic electrical properties markedly different from those found in the soma. For example, the influence of a fast, calcium-dependent potassium current on action potential repolarization is progressively reduced in the first 150 micrometer of the apical dendrites, so that action potentials recorded farther than 200 micrometer from the soma have no fast after-hyperpolarization and are wider than those in the soma. The peak amplitude of back-propagating action potentials is also progressively reduced in the dendrites because of the increasing density of a transient potassium channel with distance from the soma. The activation of this channel can be reduced by the activity of a number of protein kinases as well as by prior depolarization. The depolarization from excitatory postsynaptic potentials (EPSPs) can inactivate these A-type K+ channels and thus lead to an increase in the amplitude of dendritic action potentials, provided the EPSP and the action potentials occur within the appropriate time window. This time window could be in the order of 15 ms and may play a role in long-term potentiation induced by pairing EPSPs and back-propagating action potentials.
Differential gating of dendritic spikes by compartmentalized inhibition
Directory of Open Access Journals (Sweden)
Katharina Anna Wilmes
2014-03-01
Full Text Available Different types of local inhibitory interneurons innervate different dendritic sites of pyramidal neurons in cortex and hippocampus (Klausberger 2009. What could be the functional role of compartmentalized inhibition? Pyramidal cell dendrites support different forms of active signal propagation, which are important not only for dendritic and neuronal signal processing (Smith et al. 2013, but also for synaptic plasticity. While back-propagating action potentials signal post-synaptic activity to synapses in apical oblique and basal dendrites (Markram et al. 1997, Cho et al. 2006, calcium spikes cause plasticity of distal apical tuft synapses (Golding et al. 2002. Suspiciously, the associated regions of the dendrite are targeted by different interneuron populations. Parvalbumin-positive interneurons typically target the proximal dendritic and somatic parts of the neuron, while somatostatin-positive interneurons target the apical dendrite. The matching compartmentalization in terms of dendritic spikes and inhibitory control suggests that inhibition could differentially regulate different dendritic spikes and thereby introduce a compartment-specific modulation of synaptic plasticity. We evaluate this hypothesis in a biophysical multi-compartment model of a pyramidal neuron, receiving shunting inhibition at different locations on the dendrite. The model shows that, first, inhibition can gate dendritic spikes in an all-or-none manner. Second, spatially selective inhibition can individually suppress back-propagating action potentials and calcium spikes, thereby allowing a compartment-specific switch for synaptic plasticity. In our model, proximal inhibition on the apical dendrite eliminated both the back-propagating action potential and the calcium spike, thus influencing plasticity in the whole apical dendrite. Distal apical inhibition could selectively affect calcium spikes and thus distal plasticity, without suppressing backpropagation of action
PEMBUATAN PERANGKAT LUNAK PENGENALAN WAJAH MENGGUNAKAN PRINCIPAL COMPONENTS ANALYSIS
Directory of Open Access Journals (Sweden)
Kartika Gunadi
2001-01-01
Full Text Available Face recognition is one of many important researches, and today, many applications have implemented it. Through development of techniques like Principal Components Analysis (PCA, computers can now outperform human in many face recognition tasks, particularly those in which large database of faces must be searched. Principal Components Analysis was used to reduce facial image dimension into fewer variables, which are easier to observe and handle. Those variables then fed into artificial neural networks using backpropagation method to recognise the given facial image. The test results show that PCA can provide high face recognition accuracy. For the training faces, a correct identification of 100% could be obtained. From some of network combinations that have been tested, a best average correct identification of 91,11% could be obtained for the test faces while the worst average result is 46,67 % correct identification Abstract in Bahasa Indonesia : Pengenalan wajah manusia merupakan salah satu bidang penelitian yang penting, dan dewasa ini banyak aplikasi yang dapat menerapkannya. Melalui pengembangan suatu teknik seperti Principal Components Analysis (PCA, komputer sekarang dapat melebihi kemampuan otak manusia dalam berbagai tugas pengenalan wajah, terutama tugas-tugas yang membutuhkan pencarian pada database wajah yang besar. Principal Components Analysis digunakan untuk mereduksi dimensi gambar wajah sehingga menghasilkan variabel yang lebih sedikit yang lebih mudah untuk diobsevasi dan ditangani. Hasil yang diperoleh kemudian akan dimasukkan ke suatu jaringan saraf tiruan dengan metode Backpropagation untuk mengenali gambar wajah yang telah diinputkan ke dalam sistem. Hasil pengujian sistem menunjukkan bahwa penggunaan PCA untuk pengenalan wajah dapat memberikan tingkat akurasi yang cukup tinggi. Untuk gambar wajah yang diikutsertakankan dalam latihan, dapat diperoleh 100% identifikasi yang benar. Dari beberapa kombinasi jaringan yang
Noise-enhanced convolutional neural networks.
Audhkhasi, Kartik; Osoba, Osonde; Kosko, Bart
2016-06-01
Injecting carefully chosen noise can speed convergence in the backpropagation training of a convolutional neural network (CNN). The Noisy CNN algorithm speeds training on average because the backpropagation algorithm is a special case of the generalized expectation-maximization (EM) algorithm and because such carefully chosen noise always speeds up the EM algorithm on average. The CNN framework gives a practical way to learn and recognize images because backpropagation scales with training data. It has only linear time complexity in the number of training samples. The Noisy CNN algorithm finds a special separating hyperplane in the network's noise space. The hyperplane arises from the likelihood-based positivity condition that noise-boosts the EM algorithm. The hyperplane cuts through a uniform-noise hypercube or Gaussian ball in the noise space depending on the type of noise used. Noise chosen from above the hyperplane speeds training on average. Noise chosen from below slows it on average. The algorithm can inject noise anywhere in the multilayered network. Adding noise to the output neurons reduced the average per-iteration training-set cross entropy by 39% on a standard MNIST image test set of handwritten digits. It also reduced the average per-iteration training-set classification error by 47%. Adding noise to the hidden layers can also reduce these performance measures. The noise benefit is most pronounced for smaller data sets because the largest EM hill-climbing gains tend to occur in the first few iterations. This noise effect can assist random sampling from large data sets because it allows a smaller random sample to give the same or better performance than a noiseless sample gives.
局部式反传网络的改进BP算法及应用%BP algorithm based on partial counter propagation network and its application
Institute of Scientific and Technical Information of China (English)
霍爱清; 汪跃龙; 汤楠; 程为彬; 葛蕾
2012-01-01
针对标准BP算法收敛速度慢的缺点,分析了其产生的主要原因,提出了一种改进BP算法.在传统BP算法基础上通过对其激励函数增加陡度因子并在误差反传权值修正时增加协调器,通过对网络灵敏度的分析将全反传式网络变成局部式反传网络,从而达到提高网络学习速率及精度的目的.改进的BP算法应用于导向钻井稳定平台系统的辨识,仿真结果表明该算法收敛速度快,精度高.%According to the shortcomings of slow convergence of the standard BP (Back-Propagation) algorithm, its main causes are analyzed and the improved algorithm of BP algorithm with the partial counter propagation network is proposed. Through increasing steepness factor of activation functions and increasing coordinator to modify weights when the error is in the back propagation, a full back-propagation type network becomes local-style back-propagation network by means of the analysis of the sensitivity of the network, so as to achieve the purpose of enhancing the learning speed and accuracy. Improved BP algorithm is applied to identification of the stable platform on steerable drilling system. Simulation comparison results show that, in a given accuracy requirement and its convergence speed, this improved BP neural network is superior to traditional BP network, so it has good research and application value.
Advances in Artificial Neural Networks – Methodological Development and Application
Directory of Open Access Journals (Sweden)
Yanbo Huang
2009-08-01
Full Text Available 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 networks such as radial basis function, recurrent network, feedback network, and unsupervised Kohonen self-organizing network. These networks, especially the multilayer perceptron network with a backpropagation training algorithm, have gained recognition in research and applications in various scientific and engineering areas. In order to accelerate the training process and overcome data over-fitting, research has been conducted to improve the backpropagation algorithm. Further, artificial neural networks have been integrated with other advanced methods such as fuzzy logic and wavelet analysis, to enhance the ability of data interpretation and modeling and to avoid subjectivity in the operation of the training algorithm. In recent years, support vector machines have emerged as a set of high-performance supervised generalized linear classifiers in parallel with artificial neural networks. A review on development history of artificial neural networks is presented and the standard architectures and algorithms of artificial neural networks are described. Furthermore, advanced artificial neural networks will be introduced with support vector machines, and limitations of ANNs will be identified. The future of artificial neural network development in tandem with support vector machines will be discussed in conjunction with further applications to food science and engineering, soil and water relationship for crop management, and decision support for precision agriculture. Along with the network structures and training algorithms, the applications of artificial neural networks will be reviewed as well, especially in the fields of agricultural and biological
A neural feedforward network with a polynomial nonlinearity
DEFF Research Database (Denmark)
Hoffmann, Nils
1992-01-01
A novel neural network based on the Wiener model is proposed. The network is composed of a hidden layer of preprocessing neurons followed by a polynomial nonlinearity and a linear output neuron. The author tries to solve the problem of finding an appropriate preprocessing method by using a modified...... backpropagation algorithm. It is shown by the use of calculation trees that the proposed approach is simple to implement, and that the computational complexity is not much larger than for the alternative method of using PCA to determine the weights in the preprocessing network. A simulation is given which...... indicates superior performance of the proposed network compared to the PCA network...
Mixed Analog/Digital Matrix-Vector Multiplier for Neural Network Synapses
DEFF Research Database (Denmark)
Lehmann, Torsten; Bruun, Erik; Dietrich, Casper
1996-01-01
In this work we present a hardware efficient matrix-vector multiplier architecture for artificial neural networks with digitally stored synapse strengths. We present a novel technique for manipulating bipolar inputs based on an analog two's complements method and an accurate current rectifier....../sign detector. Measurements on a CMOS test chip are presented and validates the techniques. Further, we propose to use an analog extension, based on a simple capacitive storage, for enhancing weight resolution during learning. It is shown that the implementation of Hebbian learning and back-propagation learning...
Systolic implementation of neural networks
Energy Technology Data Exchange (ETDEWEB)
De Groot, A.J.; Parker, S.R.
1989-01-01
The backpropagation algorithm for error gradient calculations in multilayer, feed-forward neural networks is derived in matrix form involving inner and outer products. It is demonstrated that these calculations can be carried out efficiently using systolic processing techniques, particularly using the SPRINT, a 64-element systolic processor developed at Lawrence Livermore National Laboratory. This machine contains one million synapses, and forward-propagates 12 million connections per second, using 100 watts of power. When executing the algorithm, each SPRINT processor performs useful work 97% of the time. The theory and applications are confirmed by some nontrivial examples involving seismic signal recognition. 4 refs., 7 figs.
Eukaryotic Promoter Recognition Using Back propagation Neural Network
Institute of Scientific and Technical Information of China (English)
XIONGQing; WANGYuan-Qiang; LIZhi-Liang
2004-01-01
A new system is developed to recognize promoter sequences from non-promoter sequences based on position weight matrix and backpropagation neural network in this paper. The system performs significantly better on the training set and the test set, the mean recognition rate is as high as 99% on the training set and 97% on the testing set. Experimental results demonstrate the effectiveness of the system to recognize the promoter sequences that have been trained and the promoter sequences that have not been seen previously.
Use of Neural Networks for Damage Assessment in a Steel Mast
DEFF Research Database (Denmark)
Kirkegaard, Poul Henning; Rytter, A.
1994-01-01
In this paper the possibility of using a Multilayer Perceptron (MLP) network trained with the Backpropagation Algorithm for detecting location and size of a damage in a civil engineering structure is investigated. The structure considered is a 20 m high steel lattice mast subjected to wind excita...... as well as full-scale tests where the mast is identified by an ARMA-model. The results show that a neural network trained with simulated data is capable for detecting location of a damage in a steel lattice mast when the network is subjected to experimental data.·...
Energy Technology Data Exchange (ETDEWEB)
Ferreira, Francisco J.O.; Crispim, Verginia R.; Silva, Ademir X., E-mail: fferreira@ien.gov.b, E-mail: verginia@con.ufri.b, E-mail: ademir@con.ufri.b [Coordenacao dos Programas de Pos-graduacao de Engenharia (COPPE/UFRJ), Rio de Janeiro, RJ (Brazil). Programa de Engenharia Nuclear
2009-07-01
The artificial neural network technique was used to identify drugs and plastic explosives, from a tomography composed by a set of six neutrongraphic projections obtained in real time. Bidimensional tomographic images of samples of drugs, explosives and other materials, when digitally processed, yield the characteristic spectra of each type of material. The information contained in those spectra was then used for ANN training, the best images being obtained when the multilayer perceptron model, the back-propagation training algorithm and the Cross-validation interruption criterion were used. ANN showed to be useful in forecasting presence of drugs and explosives hitting a rate of success above 97 %. (author)
Improved Marquardt Algorithm for Training Neural Networks for Chemical Process Modeling
Institute of Scientific and Technical Information of China (English)
吴建昱; 何小荣
2002-01-01
Back-propagation (BP) artificial neural networks have been widely used to model chemical processes. BP networks are often trained using the generalized delta-rule (GDR) algorithm but application of such networks is limited because of the low convergent speed of the algorithm. This paper presents a new algorithm incorporating the Marquardt algorithm into the BP algorithm for training feedforward BP neural networks. The new algorithm was tested with several case studies and used to model the Reid vapor pressure (RVP) of stabilizer gasoline. The new algorithm has faster convergence and is much more efficient than the GDR algorithm.
Vehicle License Plate Recognition Syst
Directory of Open Access Journals (Sweden)
Meenakshi,R. B. Dubey
2012-12-01
Full Text Available The vehicle license plate recognition system has greater efficiency for vehicle monitoring in automatic zone access control. This Plate recognition system will avoid special tags, since all vehicles possess a unique registration number plate. A number of techniques have been used for car plate characters recognition. This system uses neural network character recognition and pattern matching of characters as two character recognition techniques. In this approach multilayer feed-forward back-propagation algorithm is used. The performance of the proposed algorithm has been tested on several car plates and provides very satisfactory results.
A Generalized Rough Set Modeling Method for Welding Process
Institute of Scientific and Technical Information of China (English)
无
2007-01-01
Modeling is essential, significant and difficult for the quality and shaping control of arc welding process. A generalized rough set based modeling method was brought forward and a dynamic predictive model for pulsed gas tungsten arc welding (GTAW) was obtained by this modeling method. The results show that this modeling method can well acquire knowledge in welding and satisfy the real life application. In addition, the results of comparison between classic rough set model and back-propagation neural network model respectively are also satisfying.
Directory of Open Access Journals (Sweden)
Rudiati Evi Masithoh
2013-03-01
Full Text Available Artificial neural networks (ANN was used to predict the quality parameters of tomato, i.e. Brix, citric acid, total carotene, and vitamin C. ANN was developed from Red Green Blue (RGB image data of tomatoes measured using a developed computer vision system (CVS. Qualitative analysis of tomato compositions were obtained from laboratory experiments. ANN model was based on a feedforward backpropagation network with different training functions, namely gradient descent (traingd, gradient descent with the resilient backpropagation (trainrp, Broyden, Fletcher, Goldfrab and Shanno (BFGS quasi-Newton (trainbfg, as well as Levenberg Marquardt (trainlm. The network structure using logsig and linear (purelin activation function at the hidden and output layer, respectively, and using the trainlm as a training function resulted in the best performance. Correlation coefficient (r of training and validation process were 0.97 - 0.99 and 0.92 - 0.99, whereas the MAE values ranged from 0.01 to 0.23 and 0.03 to 0.59, respectively. Keywords: Artificial neural network, trainlm, tomato, RGB Jaringan syaraf tiruan (JST digunakan untuk memprediksi parameter kualitas tomat, yaitu Brix, asam sitrat, karoten total, dan vitamin C. JST dikembangkan dari data Red Green Blue (RGB citra tomat yang diukur menggunakan computer vision system. Data kualitas tomat diperoleh dari analisis di laboratorium. Struktur model JST didasarkan pada jaringan feedforward backpropagation dengan berbagai fungsi pelatihan, yaitu gradient descent (traingd, gradient descent dengan resilient backpropagation (trainrp, Broyden, Fletcher, Goldfrab dan Shanno (BFGS quasi-Newton (trainbfg, serta Levenberg Marquardt (trainlm. Fungsi pelatihan yang terbaik adalah menggunakan trainlm, serta pada struktur jaringan digunakan fungsi aktivasi logsig pada lapisan tersembunyi dan linier (purelin pada lapisan keluaran. dengan 1000 epoch. Nilai koefisien korelasi (r pada tahap pelatihan dan validasi
Neural and Cognitive Modeling with Networks of Leaky Integrator Units
Graben, Peter beim; Liebscher, Thomas; Kurths, Jürgen
After reviewing several physiological findings on oscillations in the electroencephalogram (EEG) and their possible explanations by dynamical modeling, we present neural networks consisting of leaky integrator units as a universal paradigm for neural and cognitive modeling. In contrast to standard recurrent neural networks, leaky integrator units are described by ordinary differential equations living in continuous time. We present an algorithm to train the temporal behavior of leaky integrator networks by generalized back-propagation and discuss their physiological relevance. Eventually, we show how leaky integrator units can be used to build oscillators that may serve as models of brain oscillations and cognitive processes.
Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification
Directory of Open Access Journals (Sweden)
R. Sathya
2013-02-01
Full Text Available This paper presents a comparative account of unsupervised and supervised learning models and their pattern classification evaluations as applied to the higher education scenario. Classification plays a vital role in machine based learning algorithms and in the present study, we found that, though the error back-propagation learning algorithm as provided by supervised learning model is very efficient for a number of non-linear real-time problems, KSOM of unsupervised learning model, offers efficient solution and classification in the present study.
Pulse frequency classification based on BP neural network
Institute of Scientific and Technical Information of China (English)
WANG Rui; WANG Xu; YANG Dan; FU Rong
2006-01-01
In Traditional Chinese Medicine (TCM), it is an important parameter of the clinic disease diagnosis to analysis the pulse frequency. This article accords to pulse eight major essentials to identify pulse type of the pulse frequency classification based on back-propagation neural networks (BPNN). The pulse frequency classification includes slow pulse, moderate pulse, rapid pulse etc. By feature parameter of the pulse frequency analysis research and establish to identify system of pulse frequency features. The pulse signal from detecting system extracts period, frequency etc feature parameter to compare with standard feature value of pulse type. The result shows that identify-rate attains 92.5% above.
NEURAL NETWORK FOR THE QUANTUM CORRECTION OF NANOSCALE SOI MOSFETS
Institute of Scientific and Technical Information of China (English)
Li Zunchao; Jiang Yaolin; Zhang Lili
2006-01-01
The quantum effect of carrier distribution in nanoscale SOI MOSFETs is evident and must be taken into consideration in device modeling and simulation. In this paper, a backpropagation neural network was applied to predict the quantum density of carriers from the classical density, and the influence of the network structure on training speed and accuracy was studied. It was concluded that a carefully trained neural network with two hidden layers using the Levenberg-Marquardt learning algorithm could predict the carrier quantum density of SOI MOSFETs in very good agreement with Schrdinger Poisson equations.
弹性BP神经网络的旋转机械故障诊断%Fault diagnosis for rotating machinery based on RPROP neural network
Institute of Scientific and Technical Information of China (English)
王光研; 许宝杰
2007-01-01
针对BP神经网络存在局部极小值和收敛速度慢等问题,提出了一种resilient backpropagation(RPROP)的改进BP网络.RPROP神经网络具有优良的非线性映射能力,可以很好地描述频率特征和诊断结果之间的关系,经改进算法训练的网络适合旋转机械故障诊断.
ANOMALY INTRUSION DETECTION DESIGN USING HYBRID OF UNSUPERVISED AND SUPERVISED NEURAL NETWORK
Directory of Open Access Journals (Sweden)
M. Bahrololum
2009-07-01
Full Text Available This paper proposed a new approach to design the system using a hybrid of misuse and anomalydetection for training of normal and attack packets respectively. The utilized method for attack training isthe combination of unsupervised and supervised Neural Network (NN for Intrusion Detection System. Bythe unsupervised NN based on Self Organizing Map (SOM, attacks will be classified into smallercategories considering their similar features, and then unsupervised NN based on Backpropagation willbe used for clustering. By misuse approach known packets would be identified fast and unknown attackswill be able to detect by this method.
Institute of Scientific and Technical Information of China (English)
范红
2006-01-01
本文对基于传感器系统确定避碰策略的移动机器人所走过的路径用两层LMBP(Levenberg-Marquardt Backpropagation)网络进行学习,从而将环境信息与决策储存在神经网络中.通过使学习网络的样本不断进化从而实现网络的进化,使机器人对环境的适应能力不断增强.仿真结果表明结果较好.
Normalized RBF networks: application to a system of integral equations
Energy Technology Data Exchange (ETDEWEB)
Golbabai, A; Seifollahi, S; Javidi, M [Department of Mathematics, Iran University of Science and Technology, Narmak, Tehran 16844 (Iran, Islamic Republic of)], E-mail: golbabai@iust.ac.ir, E-mail: seif@iust.ac.ir, E-mail: mojavidi@yahoo.com
2008-07-15
Linear integral and integro-differential equations of Fredholm and Volterra types have been successfully treated using radial basis function (RBF) networks in previous works. This paper deals with the case of a system of integral equations of Fredholm and Volterra types with a normalized radial basis function (NRBF) network. A novel learning algorithm is developed for the training of NRBF networks in which the BFGS backpropagation (BFGS-BP) least-squares optimization method as a recursive model is used. In the approach presented here, a trial solution is given by an NRBF network of incremental architecture with a set of unknown parameters. Detailed learning algorithms and concrete examples are also included.
Institute of Scientific and Technical Information of China (English)
杨晓菲
1999-01-01
@@ 神经网络(Neural Networks,NN)是应用脑神经科学、计算机技术、数理科学、信息科学和认知科学系统地模拟人脑智能特点和结构的计算机体系.本文简要介绍NN的基本概念,及前向型误差反向传播神经网络(Backpropagation Neural Net-work,BPNN)在临床药理学中应用.
A Neural Network Appraoch to Fault Diagnosis in Analog Circuits
Institute of Scientific and Technical Information of China (English)
尉乃红; 杨士元; 等
1996-01-01
Thia paper presents a neural network based fault diagnosis approach for analog circuits,taking the tolerances of circuit elements into account.Specifically,a normalization rule of input information,a pseudo-fault domain border(PFDB)pattern selection method and a new output error function are proposed for training the backpropagation(BP) network to be a fault diagnoser.Experimental results demonstrate that the diagnoser performs as well as or better than any classical approaches in terms of accuracy,and provides at least an order-of-magnitude improvement in post-fault diagnostic speed.
Studies on Dynamic Damage Evolution for Pp/pa Polymer Blends Under High Strain Rates
Sun, Zi-Jian; Wang, Li-Li
The dynamic damage evolution for PP/PA blends with different compatibilizers is studied in high strain rates from two different approaches, namely by determining the unloading elastic modulus of specimen experienced impact deformation and by combining the split Hopkinson pressure bar (SHPB) experimental technique with the back-propagation (BP) neural network. The results obtained by both approaches consistently show that a threshold strain ɛth exists for dynamic damage evolution, and both the damage evolution and ɛth are dependent on strain and strain rate. For non-linear visco-elastic materials, the damage evolution determined by the unloading elastic modulus provides an underestimation of real damage evolution.
Que, Ruiyi; Zhu, Rong
2012-01-01
Air speed, angle of sideslip and angle of attack are fundamental aerodynamic parameters for controlling most aircraft. For small aircraft for which conventional detecting devices are too bulky and heavy to be utilized, a novel and practical methodology by which the aerodynamic parameters are inferred using a micro hot-film flow sensor array mounted on the surface of the wing is proposed. A back-propagation neural network is used to model the coupling relationship between readings of the sensor array and aerodynamic parameters. Two different sensor arrangements are tested in wind tunnel experiments and dependence of the system performance on the sensor arrangement is analyzed. PMID:23112638
Star pattern recognition method based on neural network
Institute of Scientific and Technical Information of China (English)
LI Chunyan; LI Ke; ZHANG Longyun; JIN Shengzhen; ZU Jifeng
2003-01-01
Star sensor is an avionics instrument used to provide the absolute 3-axis attitude of a spacecraft by utilizing star observations. The key function is to recognize the observed stars by comparing them with the reference catalogue. Autonomous star pattern recognition requires that similar patterns can be distinguished from each other with a small training set. Therefore, a new method based on neural network technology is proposed and a recognition system containing parallel backpropagation (BP) multi-subnets is designed. The simulation results show that the method performs much better than traditional algorithms and the proposed system can achieve both higher recognition accuracy and faster recognition speed.
A knowledge base system for ground control over abandoned mines
Energy Technology Data Exchange (ETDEWEB)
Nazimko, V.V.; Zviagilsky, E.L. [Donetsk State Technical University, Donetsk (Ukraine)
1999-07-01
The knowledge of engineering systems has been developed to choose optimal technology for subsidence prevention over abandoned mines. The expert system treats a specific case, maps consequences of actions and derives relevant technology (or a set of technologies) that should be used to prevent ground subsidence. Input parameters that characterise the case are treated using fuzzy logic and are then fed to a neural network. The network has been successfully trained by a backpropagation algorithm on the basis of three fuzzy rules. 5 refs., 2 figs., 3 tabs.
Reconocimiento de caracteres por medio de una red neuronal artificial
Directory of Open Access Journals (Sweden)
Cesar Rivera-Ordoñez
2009-01-01
Full Text Available In this project we develop a characters recognition system implemented in a general purpose FPGA card. First, The characters classification is executed by a neural network model called feed-forward backpropagation. The Matlab toobox, NNTool used for neural networks is used to create, training and simulate this kind of Artificial Neural Network (ANN with five different patterns of training. For the implementation the ANN computer model is realizes as hardware system, which is described in a block diagram using both Matlab/ Simulink and Xilinx System Generator (XSG. Subsequently, the bitstream configuration file -necessary for the FPGA programming- is generated by XSG for implementing with Xilinx ISE foundation.
Estimation of half-wave potential of anabolic androgenic steroids by means of QSER Approach
Institute of Scientific and Technical Information of China (English)
戴益民; 刘辉; 牛兰利; 陈聪; 陈晓青; 刘又年
2016-01-01
The quantitative structure-property relationship (QSPR) of anabolic androgenic steroids was studied on the half-wave reduction potential (E1/2) using quantum and physico-chemical molecular descriptors. The descriptors were calculated by semi-empirical calculations. Models were established using partial least square (PLS) regression and back-propagation artificial neural network (BP-ANN). The QSPR results indicate that the descriptors of these derivatives have significant relationship with half-wave reduction potential. The stability and prediction ability of these models were validated using leave-one-out cross-validation and external test set.
Forecasting Models for Hydropower Unit Stability Using LS-SVM
Directory of Open Access Journals (Sweden)
Liangliang Qiao
2015-01-01
Full Text Available This paper discusses a least square support vector machine (LS-SVM approach for forecasting stability parameters of Francis turbine unit. To achieve training and testing data for the models, four field tests were presented, especially for the vibration in Y-direction of lower generator bearing (LGB and pressure in draft tube (DT. A heuristic method such as a neural network using Backpropagation (NNBP is introduced as a comparison model to examine the feasibility of forecasting performance. In the experimental results, LS-SVM showed superior forecasting accuracies and performances to the NNBP, which is of significant importance to better monitor the unit safety and potential faults diagnosis.
A System for Predicting Subcellular Localization of Yeast Genome Using Neural Network
Thampi, Sabu M
2007-01-01
The subcellular location of a protein can provide valuable information about its function. With the rapid increase of sequenced genomic data, the need for an automated and accurate tool to predict subcellular localization becomes increasingly important. Many efforts have been made to predict protein subcellular localization. This paper aims to merge the artificial neural networks and bioinformatics to predict the location of protein in yeast genome. We introduce a new subcellular prediction method based on a backpropagation neural network. The results show that the prediction within an error limit of 5 to 10 percentage can be achieved with the system.
On-Line Condition Monitoring System for High Level Trip Water in Steam Boiler’s Drum
Directory of Open Access Journals (Sweden)
Ismail Alnaimi Firas B.
2014-07-01
Full Text Available This paper presents a monitoring technique using Artificial Neural Networks (ANN with four different training algorithms for high level water in steam boiler’s drum. Four Back-Propagations neural networks multidimensional minimization algorithms have been utilized. Real time data were recorded from power plant located in Malaysia. The developed relevant variables were selected based on a combination of theory, experience and execution phases of the model. The Root Mean Square (RMS Error has been used to compare the results of one and two hidden layer (1HL, (2HL ANN structures
Computationally Efficient Neural Network Intrusion Security Awareness
Energy Technology Data Exchange (ETDEWEB)
Todd Vollmer; Milos Manic
2009-08-01
An enhanced version of an algorithm to provide anomaly based intrusion detection alerts for cyber security state awareness is detailed. A unique aspect is the training of an error back-propagation neural network with intrusion detection rule features to provide a recognition basis. Network packet details are subsequently provided to the trained network to produce a classification. This leverages rule knowledge sets to produce classifications for anomaly based systems. Several test cases executed on ICMP protocol revealed a 60% identification rate of true positives. This rate matched the previous work, but 70% less memory was used and the run time was reduced to less than 1 second from 37 seconds.
Energy Technology Data Exchange (ETDEWEB)
Mickalonis, J.I.
1998-10-06
Statistical models have been developed to predict the occurrence of pitting corrosion in carbon steel waste storage tanks exposed to radioactive nuclear waste. The levels of nitrite concentrations necessary to inhibit pitting at various temperatures and nitrate concentrations were experimentally determined via electrochemical polarization and coupon immersion corrosion tests. Models for the pitting behavior were developed based on various statistical analyses of the experimental data. Feed-forward Artificial Neural Network (ANN) models, trained using the Back-Propagation of Error Algorithm, more accurately predicted conditions at which pitting occurred than the logistic regression models developed using the same data.
Identification methods for nonlinear stochastic systems.
Fullana, Jose-Maria; Rossi, Maurice
2002-03-01
Model identifications based on orbit tracking methods are here extended to stochastic differential equations. In the present approach, deterministic and statistical features are introduced via the time evolution of ensemble averages and variances. The aforementioned quantities are shown to follow deterministic equations, which are explicitly written within a linear as well as a weakly nonlinear approximation. Based on such equations and the observed time series, a cost function is defined. Its minimization by simulated annealing or backpropagation algorithms then yields a set of best-fit parameters. This procedure is successfully applied for various sampling time intervals, on a stochastic Lorenz system.
An Improved BP Algorithm and Its Application in Classification of Surface Defects of Steel Plate
Institute of Scientific and Technical Information of China (English)
ZHAO Xiang-yang; LAI Kang-sheng; DAI Dong-ming
2007-01-01
Artificial neural network is a new approach to pattern recognition and classification. The model of multilayer perceptron (MLP) and back-propagation (BP) is used to train the algorithm in the artificial neural network. An improved fast algorithm of the BP network was presented, which adopts a singular value decomposition (SVD) and a generalized inverse matrix. It not only increases the speed of network learning but also achieves a satisfying precision. The simulation and experiment results show the effect of improvement of BP algorithm on the classification of the surface defects of steel plate.
Deep learning in neural networks: an overview.
Schmidhuber, Jürgen
2015-01-01
In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
Coherent detection and digital signal processing for fiber optic communications
Ip, Ezra
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.
Direct Adaptive Soft Computing Neural Control of a Continuous Bioprocess via Second Order Learning
Baruch, Ieroham; Mariaca-Gaspar, Carlos-Roman; Barrera-Cortes, Josefina
This paper proposes a new Kalman Filter Recurrent Neural Network (KFRNN) topology and a recursive Levenberg-Marquardt (L-M) second order learning algorithm capable to estimate parameters and states of highly nonlinear bioprocess in a noisy environment. The proposed KFRNN identifier, learned by the Backpropagation and L-M learning algorithm, was incorporated in a direct adaptive neural control scheme. The proposed control scheme was applied for real-time soft computing identification and control of a continuous stirred tank bioreactor model, where fast convergence, noise filtering and low mean squared error of reference tracking were achieved.
Neural networks for function approximation in nonlinear control
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.
A Recursive Born Approach to Nonlinear Inverse Scattering
Kamilov, Ulugbek S; Mansour, Hassan; Boufounos, Petros T
2016-01-01
The Iterative Born Approximation (IBA) is a well-known method for describing waves scattered by semi-transparent objects. In this paper, we present a novel nonlinear inverse scattering method that combines IBA with an edge-preserving total variation (TV) regularizer. The proposed method is obtained by relating iterations of IBA to layers of a feedforward neural network and developing a corresponding error backpropagation algorithm for efficiently estimating the permittivity of the object. Simulations illustrate that, by accounting for multiple scattering, the method successfully recovers the permittivity distribution where the traditional linear inverse scattering fails.
Institute of Scientific and Technical Information of China (English)
王晖; 刘大有; 等
1994-01-01
In this paper we consider the problem of sequential processing and present a sequential model based on the back-propagation algorithm.This model is intended to deal with intrinsically sequential problems,such as word recognition,speech recognition,natural language understanding.This model can be used to train a network to learn the sequence of input patterns,in a fixed order or a random order.Besides,this model is open- and partial-associative,characterized as “resognizing while accumulating”, which, as we argue, is mental cognition process oriented.
Identification of Nonlinear Dynamic Systems Using Hammerstein-Type Neural Network
Directory of Open Access Journals (Sweden)
Hongshan Yu
2014-01-01
Full Text Available Hammerstein model has been popularly applied to identify the nonlinear systems. In this paper, a Hammerstein-type neural network (HTNN is derived to formulate the well-known Hammerstein model. The HTNN consists of a nonlinear static gain in cascade with a linear dynamic part. First, the Lipschitz criterion for order determination is derived. Second, the backpropagation algorithm for updating the network weights is presented, and the stability analysis is also drawn. Finally, simulation results show that HTNN identification approach demonstrated identification performances.
Mesopic Visual Performance of Cockpit’s Interior based on Artificial Neural Network
Directory of Open Access Journals (Sweden)
Dongdong WEI
2012-09-01
Full Text Available The ambient light of cockpit is usually under mesopic vision, and it’s mainly related to the cockpit’s interior. In this paper, a SB model is come up to simplify the relationship between the mesopic luminous efficiency and the different photometric and colorimetric variables in the cockpit. Self-Organizing Map (SOM network is demonstrated classifying and selecting samples. A Back-Propagation (BP network can automatically learn the relationship between material characteristics and mesopic luminous efficiency. Comparing with the MOVE model, SB model can quickly calculate the mesopic luminous efficiency with certain accuracy.
Directory of Open Access Journals (Sweden)
R. Rajesh Sharma
2015-01-01
algorithm (RGSA. Support vector machines, over backpropagation network, and k-nearest neighbor are used to evaluate the goodness of classifier approach. The preliminary evaluation of the system is performed using 320 real-time brain MRI images. The system is trained and tested by using a leave-one-case-out method. The performance of the classifier is tested using the receiver operating characteristic curve of 0.986 (±002. The experimental results demonstrate the systematic and efficient feature extraction and feature selection algorithm to the performance of state-of-the-art feature classification methods.
Nonlinear system identification based on internal recurrent neural networks.
Puscasu, Gheorghe; Codres, Bogdan; Stancu, Alexandru; Murariu, Gabriel
2009-04-01
A novel approach for nonlinear complex system identification based on internal recurrent neural networks (IRNN) is proposed in this paper. The computational complexity of neural identification can be greatly reduced if the whole system is decomposed into several subsystems. This approach employs internal state estimation when no measurements coming from the sensors are available for the system states. A modified backpropagation algorithm is introduced in order to train the IRNN for nonlinear system identification. The performance of the proposed design approach is proven on a car simulator case study.
Notación matricial en el entrenamiento de redes neuronales
Molina V., Jason Edwin; Restrepo Patiño, Carlos Alberto
2007-01-01
Este documento contiene la formulación para efectuar el entrenamiento de una red neuronal con el algoritmo Backpropagation, en el cual se ha usado un método poco usual, el cual es la formulación del mismo utilizando matrices. Esto se realiza aprovechando el hecho de que algunas operaciones permiten ser realizadas como las que usualmente se utilizan con matrices. Además las operaciones matriciales proporcionan una notación y una programación mucho más resumida, lo cual se ve reflejado en el...
Robust Bioinformatics Recognition with VLSI Biochip Microsystem
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.
Nonlinear wind prediction using a fuzzy modular temporal neural network
Energy Technology Data Exchange (ETDEWEB)
Wu, G.G. [GeoControl Systems, Inc., Houston, TX (United States); Zhijie Dou [West Texas A& M Univ., Canyon, TX (United States)
1995-12-31
This paper introduces a new approach utilizing a fuzzy classifier and a modular temporal neural network to predict wind speed and direction for advanced wind turbine control systems. The fuzzy classifier estimates wind patterns and then assigns weights accordingly to each module of the temporal neural network. A temporal network with the finite-duration impulse response and multiple-layer structure is used to represent the underlying dynamics of physical phenomena. Using previous wind measurements and information given by the classifier, the modular network trained by a standard back-propagation algorithm predicts wind speed and direction effectively. Meanwhile, the feedback from the network helps auto-tuning the classifier.
Detection of Denial of Service Attacks against Domain Name System Using Neural Networks
Directory of Open Access Journals (Sweden)
Mohd Fadlee A. Rasid
2009-11-01
Full Text Available In this paper we introduce an intrusion detection system for Denial of Service (DoS attacks against Domain Name System (DNS. Our system architecture consists of two most important parts: a statistical preprocessor and a neural network classifier. The preprocessor extracts required statistical features in a short-time frame from traffic received by the target name server. We compared three different neural networks for detecting and classifying different types of DoS attacks. The proposed system is evaluated in a simulated network and showed that the best performed neural network is a feed-forward backpropagation with an accuracy of 99%.
Identification of the nonlinear vibration system of power transformers
Jing, Zheng; Hai, Huang; Pan, Jie; Yanni, Zhang
2017-01-01
This paper focuses on the identification of the nonlinear vibration system of power transformers. A Hammerstein model is used to identify the system with electrical inputs and the vibration of the transformer tank as the output. The nonlinear property of the system is modelled using a Fourier neural network consisting of a nonlinear element and a linear dynamic block. The order and weights of the network are determined based on the Lipschitz criterion and the back-propagation algorithm. This system identification method is tested on several power transformers. Promising results for predicting the transformer vibration and extracting system parameters are presented and discussed.
Estimation of Solar Radiation using Artificial Neural Network
Directory of Open Access Journals (Sweden)
Slamet Suprayogi
2004-01-01
Full Text Available The solar radiation is the most important fator affeccting evapotranspiration, the mechanism of transporting the vapor from the water surface has also a great effect. The main objectives of this study were to investigate the potential of using Artificial Neural Network (ANN to predict solar radiation related to temperature. The three-layer backpropagation were developed, trained, and tested to forecast solar radiation for Ciriung sub Cachment. Result revealed that the ANN were able to well learn the events they were trained to recognize. Moreover, they were capable of effecctively generalize their training by predicting solar radiation for sets unseen cases.
A BOD-DO coupling model for water quality simulation by artificial neural network
Institute of Scientific and Technical Information of China (English)
郭劲松; LONG; Tengrui; 等
2002-01-01
A one-dimensional BOD-DO coupling model for water quality simulation is presented,which adopts Streeter-Phelps equations and the theory of back-propagation artificial neural network.The water quality data of Yangtze River in the Chongqing region in the year of 1989 are divided into 5 groups and used in the learning and testing courses of this model.The result shows that such model is feasible for water quality simulation and is more accurate than traditional models.
APLIKASI JARINGAN SYARAF TIRUAN PERAMBATAN BALIK PADA PENGENALAN ANGKA TULISAN TANGAN
Directory of Open Access Journals (Sweden)
Widyadi Setiawan
2009-05-01
Full Text Available Pengenalan Angka terlihat sederhana bagi manusia, namun menjadi tugas yang sangat sulit bagi program komputer untuk menyelesaikannya. Pengenalan angka secara otomatis menjadi sangat vital pada berbagai aplikasi seperti aplikasi pengolahan check dan pengolahan dokumen keuangan lainnya pada bank. Pada penelitian ini, sistem yang dikembangkan melibatkan Jaringan Syaraf Tiruan Perambatan Balik (Neural Network Backpropagation. Jaringan dilatih memakai algoritma pelatihan terbimbing, dengan memasukkan sampel-sampel digit yang bervariasi yang dilakukan secara berulang-ulang. Hasil yang didapat berupa parameter unjuk-kerja optimal sistem pengenalan tulisan tangan angka sebesar 80,31 %.
Application of artificial neural network for prediction of marine diesel engine performance
Mohd Noor, C. W.; Mamat, R.; Najafi, G.; Nik, W. B. Wan; Fadhil, M.
2015-12-01
This study deals with an artificial neural network (ANN) modelling of a marine diesel engine to predict the brake power, output torque, brake specific fuel consumption, brake thermal efficiency and volumetric efficiency. The input data for network training was gathered from engine laboratory testing running at various engine speed. The prediction model was developed based on standard back-propagation Levenberg-Marquardt training algorithm. The performance of the model was validated by comparing the prediction data sets with the measured experiment data. Results showed that the ANN model provided good agreement with the experimental data with high accuracy.
Yamagiwa, Masatomo; Komatsu, Aya; Awatsuji, Yasuhiro; Kubota, Toshihiro
2005-05-02
We observed a propagating femtosecond light pulse train generated by an integrated array illuminator as a spatially and temporally continuous motion picture. To observe the light pulse train propagating in air, light-in-flight holography is applied. The integrated array illuminator is an optical device for generating an ultrashort light pulse train from a single ultrashort pulse. The experimentally obtained pulse width and pulse interval were 130 fs and 19.7 ps, respectively. A back-propagating femtosecond light pulse train, which is the -2 order diffracted light pulse from the array illuminator and which is difficult to observe using conventional methods, was observed.
Application of DBNs for concerned internet information detecting
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.
Artificial Neural Network Model for Predicting Ultimate Tensile Capacity of Adhesive Anchors
Institute of Scientific and Technical Information of China (English)
XU Bo; WU Zhi-min; SONG Zhi-fei
2007-01-01
To predict the tensile capacity of adhesive anchors, a multilayered feed-forward neural network trained with the backpropagation algorithm is constructed. The ANN model have 5 inputs, including the compressive strength of concrete, tensile strength of concrete, anchor diameter, hole diameter, embedment of anchors, and ultimate load. The predictions obtained from the trained ANN show a good agreement with the experiments. Meanwhile, the predicted ultinate tensile capacity of anchors is close to the one calculated from the strength formula of the combined cone-bond failure model.
Fault Tolerant Neural Network for ECG Signal Classification Systems
Directory of Open Access Journals (Sweden)
MERAH, M.
2011-08-01
Full Text Available The aim of this paper is to apply a new robust hardware Artificial Neural Network (ANN for ECG classification systems. This ANN includes a penalization criterion which makes the performances in terms of robustness. Specifically, in this method, the ANN weights are normalized using the auto-prune method. Simulations performed on the MIT ? BIH ECG signals, have shown that significant robustness improvements are obtained regarding potential hardware artificial neuron failures. Moreover, we show that the proposed design achieves better generalization performances, compared to the standard back-propagation algorithm.
Artificial neural network models for biomass gasification in fluidized bed gasifiers
DEFF Research Database (Denmark)
Puig Arnavat, Maria; Hernández, J. Alfredo; Bruno, Joan Carles
2013-01-01
bed gasifier can be successfully predicted by applying neural networks. ANNs models use in the input layer the biomass composition and few operating parameters, two neurons in the hidden layer and the backpropagation algorithm. The results obtained by these ANNs show high agreement with published......Artificial neural networks (ANNs) have been applied for modeling biomass gasification process in fluidized bed reactors. Two architectures of ANNs models are presented; one for circulating fluidized bed gasifiers (CFB) and the other for bubbling fluidized bed gasifiers (BFB). Both models determine...
Reconstruction of periodic signals using neural networks
Directory of Open Access Journals (Sweden)
José Danilo Rairán Antolines
2014-01-01
Full Text Available In this paper, we reconstruct a periodic signal by using two neural networks. The first network is trained to approximate the period of a signal, and the second network estimates the corresponding coefficients of the signal's Fourier expansion. The reconstruction strategy consists in minimizing the mean-square error via backpro-pagation algorithms over a single neuron with a sine transfer function. Additionally, this paper presents mathematical proof about the quality of the approximation as well as a first modification of the algorithm, which requires less data to reach the same estimation; thus making the algorithm suitable for real-time implementations.
Model identification with BPNN on restrictive ecological factors of SRB for sulfate-reduction
Institute of Scientific and Technical Information of China (English)
无
2002-01-01
The model of back-propagation neural network(BPNN)was presented to demonstrate the effect of restrictive ecological factors,COD/SO42-ratio,pH value,alkalinity(ALK)and SO42-loading rate(Ns),on sulfate-reduction of Sulfate Reducing Bacteria(SRB)in an acidogenic sulfate-reducing reactor supplied with molasses as sole organic carbon source and sodium sulfate as electron acceptor.The compare of experimental results and computer simulation was also discussed.It was shown that the method of BPNN had a powerful ability to analyze the ecological characteristic of acidogenic sulfate-reducing ecosystem quantitatively.
Adler, Stephen Louis; Weckel, J D
1994-01-01
We study a modular neuron alternative to the McCulloch-Pitts neuron that arises naturally in analog devices in which the neuron inputs are represented as coherent oscillatory wave signals. Although the modular neuron can compute XOR at the one neuron level, it is still characterized by the same Vapnik-Chervonenkis dimension as the standard neuron. We give the formulas needed for constructing networks using the new neuron and training them using back-propagation. A numerical study of the modular neuron on two data sets is presented, which demonstrates that the new neuron performs at least as well as the standard neuron.
Stern, Adrian; Javidi, Bahram
2015-05-01
Recently we introduced the notion of "perceivable light field" (PLF) as an efficient tool for the analysis and design of three dimensional (3D) displays. The PLF is used with a 3D display analysis approach that puts the viewer in the center of the model; that is, first the human visual system requirements are defined through the PLF and then they are back-propagated to the display devices to evaluate its specifications. Here we use such an analysis to evaluate the information requirements that autostereoscopic 3D display devices need to provide for ideal visual conditions.
Directory of Open Access Journals (Sweden)
Oliveira-Esquerre K.P.
2002-01-01
Full Text Available This work presents a way to predict the biochemical oxygen demand (BOD of the output stream of the biological wastewater treatment plant at RIPASA S/A Celulose e Papel, one of the major pulp and paper plants in Brazil. The best prediction performance is achieved when the data are preprocessed using principal components analysis (PCA before they are fed to a backpropagated neural network. The influence of input variables is analyzed and satisfactory prediction results are obtained for an optimized situation.
Intelligent Surveillance Robot with Obstacle Avoidance Capabilities Using Neural Network.
Budiharto, Widodo
2015-01-01
For specific purpose, vision-based surveillance robot that can be run autonomously and able to acquire images from its dynamic environment is very important, for example, in rescuing disaster victims in Indonesia. In this paper, we propose architecture for intelligent surveillance robot that is able to avoid obstacles using 3 ultrasonic distance sensors based on backpropagation neural network and a camera for face recognition. 2.4 GHz transmitter for transmitting video is used by the operator/user to direct the robot to the desired area. Results show the effectiveness of our method and we evaluate the performance of the system.
Energy Technology Data Exchange (ETDEWEB)
Koenig, R.W.T.; Von Hellermann, M. [Commission of the European Communities, Abingdon (United Kingdom). JET Joint Undertaking; Svensson, J. [Royal Inst. of Tech., Stockholm (Sweden)
1994-07-01
A back-propagation neural network technique is used at JET to extract plasma parameters like ion temperature, rotation velocities or spectral line intensities from charge exchange (CX) spectra. It is shown that in the case of the C VI CX spectra, neural networks can give a good estimation (better than +-20% accuracy) for the main plasma parameters (Ti, V{sub rot}). Since the neural network approach involves no iterations or initial guesses the speed with which a spectrum is processed is so high (0.2 ms/spectrum) that real time analysis will be achieved in the near future. 4 refs., 8 figs.
A Neural Network Based Recognition and Classification of Commonly Used Indian Non Leafy Vegetables
Directory of Open Access Journals (Sweden)
Ajit Danti
2014-09-01
Full Text Available A methodology to characterize the commonly used Indian non-leafy vegetables’ images is developed. From the captured images of Indian non-leafy vegetables, color components, namely, RGB and HSV features are extracted, analyzed and classified. A feed forward backpropagation artificial neural network (BPNN is used for the classification. The results show that it has good robustness and a very high success rate in the range of 96-100% for eight types of vegetables. The work finds usefulness in developing recognition system for super market, automatic vending, packing and grading of vegetables, food preparation and Agriculture Produce Market Committee (APMC.
A SIMULATION OF THE PENICILLIN G PRODUCTION BIOPROCESS APPLYING NEURAL NETWORKS
Directory of Open Access Journals (Sweden)
A.J.G. da Cruz
1997-12-01
Full Text Available The production of penicillin G by Penicillium chrysogenum IFO 8644 was simulated employing a feedforward neural network with three layers. The neural network training procedure used an algorithm combining two procedures: random search and backpropagation. The results of this approach were very promising, and it was observed that the neural network was able to accurately describe the nonlinear behavior of the process. Besides, the results showed that this technique can be successfully applied to control process algorithms due to its long processing time and its flexibility in the incorporation of new data
Assessment of highway slope failure using neural networks
Institute of Scientific and Technical Information of China (English)
Tsung-lin LEE; Hung-ming LIN; Yuh-pin LU
2009-01-01
An artificial intelligence technique of back-propagation neural networks is used to assess the slope failure. On-site slope failure data from the South Cross-Island Highway in southern Taiwan are used to test the performance of the neural network model. The numerical results demonstrate the effectiveness of artificial neural networks in the evaluation of slope failure potential based on five major factors, such as the slope gradient angle, the slope height, the cumulative precipitation, daily rainfall and strength of materials.
Energy Technology Data Exchange (ETDEWEB)
Egger, A.; Schmid, M.
1999-07-01
An array consisting of a double layer condensers and a suitable actuator forms the short-term storage of the Autarkic Hybrid. Experimental investigations are supposed to confirm the calculated conservation potentials. The operational strategy based on neuronal networks and the error-back-propagation algorithm allow a self optimising condenser control. (orig.) [German] Eine Anordnung aus Doppelschicht-Kondensatoren und einem geeigneten Stellglied bildet den Kurzzeitspeicher des Autarken Hybrid. Experimentelle Untersuchungen sollen die berechneten Einsparpotentiale bestaetigen. Die Betriebsstrategie auf Grundlage neuronaler Netze und der Error-Backpropagation-Algorithmus gestatten eine selbstoptimierende Kondensatorsteuerung. (orig.)
A Worsted Yarn Virtual Production System Based on BP Neural Network
Institute of Scientific and Technical Information of China (English)
董奎勇; 于伟东
2004-01-01
Back-Propagation (BP) neural network and its modified algorithm are introduced. Two series of BP neural network models have been established to predict yarn properties and to deduce wool fiber qualities. The results from these two series of models have been compared with the measured values respectively, proving that the accuracy in both the prediction model and the deduction model is high. The experimental results and the corresponding analysis show that the BP neural network is an efficient technique for the quality prediction and has wide prospect in the application of worsted yarn production system.
Hoffman, D A; Johnston, D
1998-05-15
We have reported recently a high density of transient A-type K+ channels located in the distal dendrites of CA1 hippocampal pyramidal neurons and shown that these channels shape EPSPs, limit the back-propagation of action potentials, and prevent dendritic action potential initiation (). Because of the importance of these channels in dendritic signal propagation, their modulation by protein kinases would be of significant interest. We investigated the effects of activators of cAMP-dependent protein kinase (PKA) and the Ca2+-dependent phospholipid-sensitive protein kinase (PKC) on K+ channels in cell-attached patches from the distal dendrites of hippocampal CA1 pyramidal neurons. Inclusion of the membrane-permeant PKA activators 8-bromo-cAMP (8-br-cAMP) or forskolin in the dendritic patch pipette resulted in a depolarizing shift in the activation curve for the transient channels of approximately 15 mV. Activation of PKC by either of two phorbol esters also resulted in a 15 mV depolarizing shift of the activation curve. Neither PKA nor PKC activation affected the sustained or slowly inactivating component of the total outward current. This downregulation of transient K+ channels in the distal dendrites may be responsible for some of the frequently reported increases in cell excitability found after PKA and PKC activation. In support of this hypothesis, we found that activation of either PKA or PKC significantly increased the amplitude of back-propagating action potentials in distal dendrites.
Implementation and performance results of neural network for power quality event detection
Huang, Weijian; Tian, Wenzhi
2008-10-01
A novel method to detect power quality event in distributed power system combing wavelet network with the improved back-propagation algorithm is presented. The paper tries to explain to design complex supported orthogonal wavelets by compactly supported orthogonal real wavelets, and then explore the extraction of disturbance signal to obtain the feature information, and finally propose several novel wavelet combined information to analyze the disturbance signal, superior to real wavelet analysis result. The feature obtained from WT coefficients are inputted into wavelet network for power quality disturbance pattern recognition. The power quality disturbance recognition model is established and the improved back-propagation algorithm is used to fulfill the network parameter initialization. By means of choosing enough samples to train the recognition model, the type of disturbance can be obtained when signal representing fault is inputted to the trained network. The results of simulation analysis show that the complex wavelet transform combined with wavelet network are more sensitive to signal singularity, and found to be significant improvement over current methods in real-time detection.
Jaringan Syaraf Tiruan Perambatan Balik Untuk Pengenalan Wajah
Directory of Open Access Journals (Sweden)
Nahdi Sabuari
2016-11-01
Full Text Available This research discusses about face detection and face recognition in an image. Face detection has only two classifications, i.e face and not face. Face recognition is compatible with some classifications of a number individuals who want to be recognized. Face detection and face recognition in thi study using Haar-Like Feature method and Artificial Neural Network Backpropagation. A method Haar-Like Feature used for detection and extraction in an image, because the clasification on this method showed success at used to detect image of the face. Artificial Neural Network Backpropagation is a training algorithm that is used to do training simulated on facial image data training stored in a database. This study uses Ms. Excel 2007 as database with 10 individual sample image, every image in each individuals having three distance with every range has four defferent light intensities, so that the data training stored in the database reached 120 data training. The results shows that the face detection and face recognition which is developed can recognize a face image with an average accuracy rate reaches 80,8% for each distance.
Directory of Open Access Journals (Sweden)
Ayedh Alqahtani
2013-09-01
Full Text Available Industrial application of life-cycle cost analysis (LCCA is somewhat limited, with techniques deemed overly theoretical, resulting in a reluctance to realise (and pass onto the client the advantages to be gained from objective (LCCA comparison of (subcomponent material specifications. To address the need for a user-friendly structured approach to facilitate complex processing, the work described here develops a new, accessible framework for LCCA of construction projects; it acknowledges Artificial Neural Networks (ANNs to compute the whole-cost(s of construction and uses the concept of cost significant items (CSI to identify the main cost factors affecting the accuracy of estimation. ANNs is a powerful means to handle non-linear problems and subsequently map between complex input/output data, address uncertainties. A case study documenting 20 building projects was used to test the framework and estimate total running costs accurately. Two methods were used to develop a neural network model; firstly a back-propagation method was adopted (using MATLAB SOFTWARE; and secondly, spread-sheet optimisation was conducted (using Microsoft Excel Solver. The best network was established as consisting of 19 hidden nodes, with the tangent sigmoid used as a transfer function of NNs model for both methods. The results find that in both neural network models, the accuracy of the developed NNs model is 1% (via Excel-solver and 2% (via back-propagation respectively.
Selective interferometric imaging of internal multiples
Zuberi, M. A H
2013-01-01
Internal multiples deteriorate the image when the imaging procedure assumes only single scattering, especially if the velocity model does not reproduce such scattering in the Green’s function. If properly imaged, internal multiples (and internally-scattered energy) can enhance the seismic image and illuminate areas otherwise neglected or poorly imaged by conventional single-scattering approaches. Conventionally, in order to image internal multiples, accurate, sharp contrasts in the velocity model are required to construct a Green’s function with all the scattered energy. As an alternative, we develop a three-step procedure, which images the first-order internal scattering using the background Green’s function (from the surface to each image point), constructed from a smooth velocity model: We first back-propagate the recorded surface data using the background Green’s function, then cross-correlate the back-propagated data with the recorded data and finally cross-correlate the result with the original background Green’s function. This procedure images the contribution of the recorded first-order internal multiples and is almost free of the single-scattering recorded energy. This image can be added to the conventional single-scattering image, obtained e.g. from Kirchhoff migration, to enhance the image. Application to synthetic data with reflectors illuminated by multiple scattering only demonstrates the effectiveness of the approach.
State-dependent firing determines intrinsic dendritic Ca2+ signaling in thalamocortical neurons.
Errington, Adam C; Renger, John J; Uebele, Victor N; Crunelli, Vincenzo
2010-11-01
Activity-dependent dendritic Ca(2+) signals play a critical role in multiple forms of nonlinear cellular output and plasticity. In thalamocortical neurons, despite the well established spatial separation of sensory and cortical inputs onto proximal and distal dendrites, respectively, little is known about the spatiotemporal dynamics of intrinsic dendritic Ca(2+) signaling during the different state-dependent firing patterns that are characteristic of these neurons. Here we demonstrate that T-type Ca(2+) channels are expressed throughout the entire dendritic tree of rat thalamocortical neurons and that they mediate regenerative propagation of low threshold spikes, typical of, but not exclusive to, sleep states, resulting in global dendritic Ca(2+) influx. In contrast, actively backpropagating action potentials, typical of wakefulness, result in smaller Ca(2+) influxes that can temporally summate to produce dendritic Ca(2+) accumulations that are linearly related to firing frequency but spatially confined to proximal dendritic regions. Furthermore, dendritic Ca(2+) transients evoked by both action potentials and low-threshold spikes are shaped by Ca(2+) uptake by sarcoplasmic/endoplasmic reticulum Ca(2+) ATPases but do not rely on Ca(2+)-induced Ca(2+) release. Our data demonstrate that thalamocortical neurons are endowed with intrinsic dendritic Ca(2+) signaling properties that are spatially and temporally modified in a behavioral state-dependent manner and suggest that backpropagating action potentials faithfully inform proximal sensory but not distal corticothalamic synapses of neuronal output, whereas corticothalamic synapses only "detect" Ca(2+) signals associated with low-threshold spikes.
Prediction of thermal conductivity of rock through physico-mechanical properties
Energy Technology Data Exchange (ETDEWEB)
Singh, T.N. [Department of Earth Sciences, Indian Institute of Technology, Bombay 400 076 (India); Sinha, S.; Singh, V.K. [Institute of Technology, Banaras Hindu University, Varanasi 221 005 (India)
2007-01-15
The transfer of energy between two adjacent parts of rock mainly depends on its thermal conductivity. Present study supports the use of artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS) in the study of thermal conductivity along with other intrinsic properties of rock due to its increasing importance in many areas of rock engineering, agronomy and geo environmental engineering field. In recent years, considerable effort has been made to develop techniques to determine these properties. Comparative analysis is made to analyze the capabilities among six different models of ANN and ANFIS. ANN models are based on feedforward backpropagation network with training functions resilient backpropagation (RP), one step secant (OSS) and Powell-Beale restarts (CGB) and radial basis with training functions generalized regression neural network (GRNN) and more efficient design radial basis network (NEWRB). A data set of 136 has been used for training different models and 15 were used for testing purposes. A statistical analysis is made to show the consistency among them. ANFIS is proved to be the best among all the networks tried in this case with average absolute percentage error of 0.03% and regression coefficient of 1, whereas best performance shown by the FFBP (RP) with average absolute error of 2.26%. Thermal conductivity is predicted using P-wave velocity, porosity, bulk density, uniaxial compressive strength of rock as input parameters. (author)
Firearm Classification using Neural Networks on Ring of Firing Pin Impression Images
Directory of Open Access Journals (Sweden)
Abdul AZIZ JEMAIN
2013-07-01
Full Text Available This paper implements two layer neural networks with different feedforward backpropagation algorithms for better performance of firearm classification us-ing numerical features from the ring image. A total of 747 ring images which are extracted from centre of the firing pin impression have been captured from five different pistols of the Parabellum Vector SPI 9mm model. Then, based on finding from the previous studies, the six best geometric moments numerical fea-tures were extracted from those ring images. The elements of the dataset were further randomly divided into the training set (523 elements, testing set (112 el-ements and validation set (112 elements in accordance with the requirement of the supervised learning nature of the backpropagation neural network (BPNN. Empirical results show that a two layer BPNN with a 6-7-5 configura-tion and tansig/tansig transfer functions with ‘trainscg’ training algorithm has produced the best classification result of 98%. The classification result is an improvement compared to the previous studies as well as confirming that the ring image region contains useful information for firearm classification.
Directory of Open Access Journals (Sweden)
R. Murugadoss
2014-10-01
Full Text Available Neural networks are modeled on the way the human brain. They are capable of learning and can automatically recognize by skillfully training and design complex relationships and hidden dependencies based on historical example patterns and use this information for forecasting. The main difference, and at the same time is biggest advantage of the model of neural networks over statistical techniques seen that the forecaster the exact functional structure between input and Output variables need not be specified, but this by the system with certain Learning algorithms is "learned" using a kind of threshold logic. Goal of the learning procedure is to define the training phase while those parameters of the network, with Help the network has one of those adequate for the problem behavior. Mathematically, the training phase is an iterative, converging towards a minimum error value process. They identify the processors of the network, minimize the "total error". The currently the most popular and most widely for business applications algorithm is the backpropagation algorithm. This paper opens the black box of Backpropagation networks and makes the optimization process in the network over time and locally comprehensible.
Deep Learning with Dynamic Spiking Neurons and Fixed Feedback Weights.
Samadi, Arash; Lillicrap, Timothy P; Tweed, Douglas B
2017-03-01
Recent work in computer science has shown the power of deep learning driven by the backpropagation algorithm in networks of artificial neurons. But real neurons in the brain are different from most of these artificial ones in at least three crucial ways: they emit spikes rather than graded outputs, their inputs and outputs are related dynamically rather than by piecewise-smooth functions, and they have no known way to coordinate arrays of synapses in separate forward and feedback pathways so that they change simultaneously and identically, as they do in backpropagation. Given these differences, it is unlikely that current deep learning algorithms can operate in the brain, but we that show these problems can be solved by two simple devices: learning rules can approximate dynamic input-output relations with piecewise-smooth functions, and a variation on the feedback alignment algorithm can train deep networks without having to coordinate forward and feedback synapses. Our results also show that deep spiking networks learn much better if each neuron computes an intracellular teaching signal that reflects that cell's nonlinearity. With this mechanism, networks of spiking neurons show useful learning in synapses at least nine layers upstream from the output cells and perform well compared to other spiking networks in the literature on the MNIST digit recognition task.
Dong, Wenjiang; Ni, Yongnian; Kokot, Serge
2015-02-01
In this study, complex substances such as Mint (Mentha haplocalyx Briq.) samples from different growing regions in China were analyzed for phenolic compounds by high-performance liquid chromatography with diode array detection and for the volatile aroma compounds by gas chromatography with mass spectrometry. Chemometrics methods, e.g. principal component analysis, back-propagation artificial neural networks, and partial least squares discriminant analysis, were applied to resolve complex chromatographic profiles of Mint samples. A total of 49 aroma components and 23 phenolic compounds were identified in 79 Mint samples. Principal component analysis score plots from gas chromatography with mass spectrometry and high-performance liquid chromatography with diode array detection data sets showed a clear distinction among Mint from three different regions in China. Classification results showed that satisfactory performance of prediction ability for back-propagation artificial neural networks and partial least squares discriminant analysis. The major compounds that contributed to the discrimination were chlorogenic acid, unknown 3, kaempherol 7-O-rutinoside, salvianolic acid L, hesperidin, diosmetin, unknown 6 and pebrellin in Mint according to regression coefficients of the partial least squares discriminant analysis model. This study indicated that the proposed strategy could provide a simple and rapid technique to distinguish clearly complex profiles from samples such as Mint.
Neural net robot controller with guaranteed tracking performance.
Lewis, F L; Liu, K; Yesildirek, A
1995-01-01
A neural net (NN) controller for a general serial-link robot arm is developed. The NN has two layers so that linearity in the parameters holds, but the "net functional reconstruction error" and robot disturbance input are taken as nonzero. The structure of the NN controller is derived using a filtered error/passivity approach, leading to new NN passivity properties. Online weight tuning algorithms including a correction term to backpropagation, plus an added robustifying signal, guarantee tracking as well as bounded NN weights. The NN controller structure has an outer tracking loop so that the NN weights are conveniently initialized at zero, with learning occurring online in real-time. It is shown that standard backpropagation, when used for real-time closed-loop control, can yield unbounded NN weights if (1) the net cannot exactly reconstruct a certain required control function or (2) there are bounded unknown disturbances in the robot dynamics. The role of persistency of excitation is explored.
Koutsou, Achilleas; Bugmann, Guido; Christodoulou, Chris
2015-10-01
Biological systems are able to recognise temporal sequences of stimuli or compute in the temporal domain. In this paper we are exploring whether a biophysical model of a pyramidal neuron can detect and learn systematic time delays between the spikes from different input neurons. In particular, we investigate whether it is possible to reinforce pairs of synapses separated by a dendritic propagation time delay corresponding to the arrival time difference of two spikes from two different input neurons. We examine two subthreshold learning approaches where the first relies on the backpropagation of EPSPs (excitatory postsynaptic potentials) and the second on the backpropagation of a somatic action potential, whose production is supported by a learning-enabling background current. The first approach does not provide a learning signal that sufficiently differentiates between synapses at different locations, while in the second approach, somatic spikes do not provide a reliable signal distinguishing arrival time differences of the order of the dendritic propagation time. It appears that the firing of pyramidal neurons shows little sensitivity to heterosynaptic spike arrival time differences of several milliseconds. This neuron is therefore unlikely to be able to learn to detect such differences.
Belciug, Smaranda; Gorunescu, Florin
2014-12-01
Automated medical diagnosis models are now ubiquitous, and research for developing new ones is constantly growing. They play an important role in medical decision-making, helping physicians to provide a fast and accurate diagnosis. Due to their adaptive learning and nonlinear mapping properties, the artificial neural networks are widely used to support the human decision capabilities, avoiding variability in practice and errors based on lack of experience. Among the most common learning approaches, one can mention either the classical back-propagation algorithm based on the partial derivatives of the error function with respect to the weights, or the Bayesian learning method based on posterior probability distribution of weights, given training data. This paper proposes a novel training technique gathering together the error-correction learning, the posterior probability distribution of weights given the error function, and the Goodman-Kruskal Gamma rank correlation to assembly them in a Bayesian learning strategy. This study had two main purposes; firstly, to develop anovel learning technique based on both the Bayesian paradigm and the error back-propagation, and secondly,to assess its effectiveness. The proposed model performance is compared with those obtained by traditional machine learning algorithms using real-life breast and lung cancer, diabetes, and heart attack medical databases. Overall, the statistical comparison results indicate that thenovellearning approach outperforms the conventional techniques in almost all respects.
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.
Neuro-Knowledge-Based Expert System (NKBES)for Optimal Scheming of Die Casting Process
Institute of Scientific and Technical Information of China (English)
Qiaodan HU; Peng LUO; Yi YANG; Liliang CHEN
2004-01-01
We develop a neuro-knowledge-based expert system (NKBES) frame in this work. The system mainly concerns with decision of gating system and die casting machine based on a neuro-inference engine launched under the MATLAB software environment. For enhancement of reasoning agility, an error back-propagation neural network was applied.A rapidly convergent adaptive learning rate (ALR) and a momentum-based error back-propagation algorithm was used to conduct neuro-reasoning. The working effect of the system was compared to a conventional expert system that is based on a two-way (forward and backward) chaining inference mechanism. As the reference, the present paper provided the neural networks sum-squared error (SSE) and ALR vs iterative epoch curves of process planning case mentioned above. The study suggests that the neuro-modeling optimization application to die casting process design has good feasibility, and based on that a novel and effective intelligent expert system can be launched at low cost.
Neural networks and wavelet analysis in the computer interpretation of pulse oximetry data
Energy Technology Data Exchange (ETDEWEB)
Dowla, F.U.; Skokowski, P.G.; Leach, R.R. Jr.
1996-03-01
Pulse oximeters determine the oxygen saturation level of blood by measuring the light absorption of arterial blood. The sensor consists of red and infrared light sources and photodetectors. A method based on neural networks and wavelet analysis is developed for improved saturation estimation in the presence of sensor motion. Spectral and correlation functions of the dual channel oximetry data are used by a backpropagation neural network to characterize the type of motion. Amplitude ratios of red to infrared signals as a function of time scale are obtained from the multiresolution wavelet decomposition of the two-channel data. Motion class and amplitude ratios are then combined to obtain a short-time estimate of the oxygen saturation level. A final estimate of oxygen saturation is obtained by applying a 15 s smoothing filter on the short-time measurements based on 3.5 s windows sampled every 1.75 s. The design employs two backpropagation neural networks. The first neural network determines the motion characteristics and the second network determines the saturation estimate. Our approach utilizes waveform analysis in contrast to the standard algorithms that are based on the successful detection of peaks and troughs in the signal. The proposed algorithm is numerically efficient and has stable characteristics with a reduced false alarm rate with a small loss in detection. The method can be rapidly developed on a digital signal processing platform.
Using a binaural biomimetic array to identify bottom objects ensonified by echolocating dolphins
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.
Connectionist natural language parsing with BrainC
Mueller, Adrian; Zell, Andreas
1991-08-01
A close examination of pure neural parsers shows that they either could not guarantee the correctness of their derivations or had to hard-code seriality into the structure of the net. The authors therefore decided to use a hybrid architecture, consisting of a serial parsing algorithm and a trainable net. The system fulfills the following design goals: (1) parsing of sentences without length restriction, (2) soundness and completeness for any context-free language, and (3) learning the applicability of parsing rules with a neural network to increase the efficiency of the whole system. BrainC (backtracktacking and backpropagation in C) combines the well- known shift-reduce parsing technique with backtracking with a backpropagation network to learn and represent typical structures of the trained natural language grammars. The system has been implemented as a subsystem of the Rochester Connectionist Simulator (RCS) on SUN workstations and was tested with several grammars for English and German. The design of the system and then the results are discussed.
Natural language parsing in a hybrid connectionist-symbolic architecture
Mueller, Adrian; Zell, Andreas
1991-03-01
Most connectionist parsers either cannot guarantee the correctness of their derivations or have to simulate a serial flow of control. In the first case, users have to restrict the tasks (e.g. parse less complex or shorter sentences) of the parser or they need to believe in the soundness of the result. In the second case, the resulting network has lost most of its attractivity because seriality needs to be hard-coded into the structure of the net. We here present a hybrid symbolic connectionist parser, which was designed to fulfill the following goals: (1) parsing of sentences without length restriction, (2) soundness and completeness for any context-free grammar, and (3) learning the applicability of parsing rules with a neural network. Our hybrid architecture consists of a serial parsing algorithm and a trainable net. BrainC (Backtracking and Backpropagation in C) combines the well known shift-reduce parsing technique with backtracking with a backpropagation network to learn and represent the typical properties of the trained natural language grammars. The system has been implemented as a subsystem of the Rochester Connectionist Simulator (RCS) on SUN- Workstations and was tested with several grammars for English and German. We discuss how BrainC reached its design goals and what results we observed.
Early tube leak detection system for steam boiler at KEV power plant
Directory of Open Access Journals (Sweden)
Ismail Firas B.
2016-01-01
Full Text Available Tube leakage in boilers has been a major contribution to trips which eventually leads to power plant shut downs. Training of network and developing artificial neural network (ANN models are essential in fault detection in critically large systems. This research focusses on the ANN modelling through training and validation of real data acquired from a sub-critical boiler unit. The artificial neural network (ANN was used to develop a compatible model and to evaluate the working properties and behaviour of boiler. The training and validation of real data has been applied using the feed-forward with back-propagation (BP. The right combination of number of neurons, number of hidden layers, training algorithms and training functions was run to achieve the best ANN model with lowest error. The ANN was trained and validated using real site data acquired from a coal fired power plant in Malaysia. The results showed that the Neural Network (NN with one hidden layers performed better than two hidden layer using feed-forward back-propagation network. The outcome from this study give us the best ANN model which eventually allows for early detection of boiler tube leakages, and forecast of a trip before the real shutdown. This will eventually reduce shutdowns in power plants.
Yeşilkanat, Cafer Mert; Kobya, Yaşar
2015-09-01
In this study, radiological distribution of gross alpha, gross beta, (226)Ra, (232)Th, (40)K, and (137)Cs for a total of 40 natural spring water samples obtained from seven cities of the Eastern Black Sea Region was determined by artificial neural network (ANN) method. In the ANN method employed, the backpropagation algorithm, which estimates the backpropagation of the errors and results, was used. In the structure of ANN, five input parameters (latitude, longitude, altitude, major soil groups, and rainfall) were used for natural radionuclides and four input parameters (latitude, longitude, altitude, and rainfall) were used for artificial radionuclides, respectively. In addition, 75 % of the total data were used as the data of training and 25 % of them were used as test data in order to reveal the structure of each radionuclide. It has been seen that the results obtained explain the radiographic structure of the region very well. Spatial interpolation maps covering the whole region were created for each radionuclide including spots not measured by using these results. It has been determined that artificial neural network method can be used for mapping the spatial distribution of radioactivity with this study, which is conducted for the first time for the Black Sea Region.
Laidi, Maamar; Hanini, Salah; Rezrazi, Ahmed; Yaiche, Mohamed Redha; El Hadj, Abdallah Abdallah; Chellali, Farouk
2016-01-01
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.
Optimizing the De-Noise Neural Network Model for GPS Time-Series Monitoring of Structures
Directory of Open Access Journals (Sweden)
Mosbeh R. Kaloop
2015-09-01
Full Text Available The Global Positioning System (GPS is recently used widely in structures and other applications. Notwithstanding, the GPS accuracy still suffers from the errors afflicting the measurements, particularly the short-period displacement of structural components. Previously, the multi filter method is utilized to remove the displacement errors. This paper aims at using a novel application for the neural network prediction models to improve the GPS monitoring time series data. Four prediction models for the learning algorithms are applied and used with neural network solutions: back-propagation, Cascade-forward back-propagation, adaptive filter and extended Kalman filter, to estimate which model can be recommended. The noise simulation and bridge’s short-period GPS of the monitoring displacement component of one Hz sampling frequency are used to validate the four models and the previous method. The results show that the Adaptive neural networks filter is suggested for de-noising the observations, specifically for the GPS displacement components of structures. Also, this model is expected to have significant influence on the design of structures in the low frequency responses and measurements’ contents.
File access prediction using neural networks.
Patra, Prashanta Kumar; Sahu, Muktikanta; Mohapatra, Subasish; Samantray, Ronak Kumar
2010-06-01
One of the most vexing issues in design of a high-speed computer is the wide gap of access times between the memory and the disk. To solve this problem, static file access predictors have been used. In this paper, we propose dynamic file access predictors using neural networks to significantly improve upon the accuracy, success-per-reference, and effective-success-rate-per-reference by using neural-network-based file access predictor with proper tuning. In particular, we verified that the incorrect prediction has been reduced from 53.11% to 43.63% for the proposed neural network prediction method with a standard configuration than the recent popularity (RP) method. With manual tuning for each trace, we are able to improve upon the misprediction rate and effective-success-rate-per-reference using a standard configuration. Simulations on distributed file system (DFS) traces reveal that exact fit radial basis function (RBF) gives better prediction in high end system whereas multilayer perceptron (MLP) trained with Levenberg-Marquardt (LM) backpropagation outperforms in system having good computational capability. Probabilistic and competitive predictors are the most suitable for work stations having limited resources to deal with and the former predictor is more efficient than the latter for servers having maximum system calls. Finally, we conclude that MLP with LM backpropagation algorithm has better success rate of file prediction than those of simple perceptron, last successor, stable successor, and best k out of m predictors.
Prediction of geomagnetic storms from solar wind data with the use of a neural network
Directory of Open Access Journals (Sweden)
H. Lundstedt
Full Text Available An artificial feed-forward neural network with one hidden layer and error back-propagation learning is used to predict the geomagnetic activity index (D_{st} one hour in advance. The B_{z}-component and Σ_{Bz}, the density, and the velocity of the solar wind are used as input to the network. The network is trained on data covering a total of 8700 h, extracted from the 25-year period from 1963 to 1987, taken from the NSSDC data base. The performance of the network is examined with test data, not included in the training set, which covers 386 h and includes four different storms. Whilst the network predicts the initial and main phase well, the recovery phase is not modelled correctly, implying that a single hidden layer error back-propagation network is not enough, if the measured D_{st} is not available instantaneously. The performance of the network is independent of whether the raw parameters are used, or the electric field and square root of the dynamical pressure.
Singh, Mithun Kuniyil Ajith; Jaeger, Michael; Frenz, Martin; Steenbergen, Wiendelt
2016-08-01
Reflection artifacts caused by acoustic inhomogeneities are a critical problem in epi-mode biomedical photoacoustic imaging. High light fluence beneath the probe results in photoacoustic transients, which propagate into the tissue and reflect back from echogenic structures. These reflection artifacts cause problems in image interpretation and significantly impact the contrast and imaging depth. We recently proposed a method called PAFUSion (Photoacoustic-guided focused ultrasound) to identify such reflection artifacts in photoacoustic imaging. In its initial version, PAFUSion mimics the inward-travelling wavefield from small blood vessel-like PA sources by applying ultrasound pulses focused towards these sources, and thus provides a way to identify the resulting reflection artifacts. In this work, we demonstrate reduction of reflection artifacts in phantoms and in vivo measurements on human volunteers. In view of the spatially distributed PA sources that are found in clinical applications, we implemented an improved version of PAFUSion where photoacoustic signals are backpropagated to imitate the inward travelling wavefield and thus the reflection artifacts. The backpropagation is performed in a synthetic way based on the pulse-echo acquisitions after transmission on each single element of the transducer array. The results provide a direct confirmation that reflection artifacts are prominent in clinical epi-photoacoustic imaging, and that PAFUSion can strongly reduce these artifacts to improve deep-tissue photoacoustic imaging.
Ying, Yibin; Liu, Yande; Fu, Xiaping; Lu, Huishan
2005-11-01
The artificial neural networks (ANNs) have been used successfully in applications such as pattern recognition, image processing, automation and control. However, majority of today's applications of ANNs is back-propagate feed-forward ANN (BP-ANN). In this paper, back-propagation artificial neural networks (BP-ANN) were applied for modeling soluble solid content (SSC) of intact pear from their Fourier transform near infrared (FT-NIR) spectra. One hundred and sixty-four pear samples were used to build the calibration models and evaluate the models predictive ability. The results are compared to the classical calibration approaches, i.e. principal component regression (PCR), partial least squares (PLS) and non-linear PLS (NPLS). The effects of the optimal methods of training parameters on the prediction model were also investigated. BP-ANN combine with principle component regression (PCR) resulted always better than the classical PCR, PLS and Weight-PLS methods, from the point of view of the predictive ability. Based on the results, it can be concluded that FT-NIR spectroscopy and BP-ANN models can be properly employed for rapid and nondestructive determination of fruit internal quality.
Directory of Open Access Journals (Sweden)
Chung-Ta Li
2014-01-01
Full Text Available We propose a species-based hybrid of the electromagnetism-like mechanism (EM and back-propagation algorithms (SEMBP for an interval type-2 fuzzy neural system with asymmetric membership functions (AIT2FNS design. The interval type-2 asymmetric fuzzy membership functions (IT2 AFMFs and the TSK-type consequent part are adopted to implement the network structure in AIT2FNS. In addition, the type reduction procedure is integrated into an adaptive network structure to reduce computational complexity. Hence, the AIT2FNS can enhance the approximation accuracy effectively by using less fuzzy rules. The AIT2FNS is trained by the SEMBP algorithm, which contains the steps of uniform initialization, species determination, local search, total force calculation, movement, and evaluation. It combines the advantages of EM and back-propagation (BP algorithms to attain a faster convergence and a lower computational complexity. The proposed SEMBP algorithm adopts the uniform method (which evenly scatters solution agents over the feasible solution region and the species technique to improve the algorithm’s ability to find the global optimum. Finally, two illustrative examples of nonlinear systems control are presented to demonstrate the performance and the effectiveness of the proposed AIT2FNS with the SEMBP algorithm.
Artificial Neural Network Approach in Radar Target Classification
Directory of Open Access Journals (Sweden)
N. K. Ibrahim
2009-01-01
Full Text Available Problem statement: This study unveils the potential and utilization of Neural Network (NN in radar applications for target classification. The radar system under test is a special of it kinds and known as Forward Scattering Radar (FSR. In this study the target is a ground vehicle which is represented by typical public road transport. The features from raw radar signal were extracted manually prior to classification process using Neural Network (NN. Features given to the proposed network model are identified through radar theoretical analysis. Multi-Layer Perceptron (MLP back-propagation neural network trained with three back-propagation algorithm was implemented and analyzed. In NN classifier, the unknown target is sent to the network trained by the known targets to attain the accurate output. Approach: Two types of classifications were analyzed. The first one is to classify the exact type of vehicle, four vehicle types were selected. The second objective is to grouped vehicle into their categories. The proposed NN architecture is compared to the K Nearest Neighbor classifier and the performance is evaluated. Results: Based on the results, the proposed NN provides a higher percentage of successful classification than the KNN classifier. Conclusion/Recommendation: The result presented here show that NN can be effectively employed in radar classification applications.
Rozova, Vlada S; Khaydukov, Eugenyi V; Zvyagin, Andrei V
2016-07-20
A retroemission device (REM) is an incoherent holographic device that represents a lenslet array situated on a substrate containing fluorescent material. Each lenslet focuses each wavelet of an optical wavefront incident on the REM device into a diffraction-limited volume (voxel) in the fluorescent material, so that the voxel coordinates encode the angle of incidence and curvature of the wavelet. The back-propagating fraction of the excited fluorescence is collected by the lenslet and quasi-collimated into a back-propagating wavelet. All wavelets are combined to reconstruct the incident wavefront propagating in the backward direction. We present a theoretical model of REM based on Fresnel-Kirchhoff approximation describing the reconstructed 3D image characteristics versus the thickness of the fluorescence film at the focal plane of the lenslets. Results of the computer simulations of the REM-based images of a point source, two axially separated point sources and an extended object (a circular rim) situated in the sagittal plane are presented. These results speak in favor of using a fluorescence film of minimum diffraction-limited thickness at the lenslet back focal plane. This REM structure minimizes the fluorescence background and improves the 3D imaging resolution in virtue of the exclusion of out-of-voxel fluorescence contributions to the reconstructed wavefront.
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.
Directory of Open Access Journals (Sweden)
Lukas Falat
2016-01-01
Full Text Available 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.
Method and system for training dynamic nonlinear adaptive filters which have embedded memory
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.
Directory of Open Access Journals (Sweden)
Hacene MELLAH
2016-07-01
Full Text Available The objective of this paper is to develop an Artificial Neural Network (ANN model to estimate simultaneously, parameters and state of a brushed DC machine. The proposed ANN estimator is novel in the sense that his estimates simultaneously temperature, speed and rotor resistance based only on the measurement of the voltage and current inputs. Many types of ANN estimators have been designed by a lot of researchers during the last two decades. Each type is designed for a specific application. The thermal behavior of the motor is very slow, which leads to large amounts of data sets. The standard ANN use often Multi-Layer Perceptron (MLP with Levenberg-Marquardt Backpropagation (LMBP, among the limits of LMBP in the case of large number of data, so the use of MLP based on LMBP is no longer valid in our case. As solution, we propose the use of Cascade-Forward Neural Network (CFNN based Bayesian Regulation backpropagation (BRBP. To test our estimator robustness a random white-Gaussian noise has been added to the sets. The proposed estimator is in our viewpoint accurate and robust.
Laser ultrasound and simulated time reversal on bulk waves for non destructive control
Diot, G.; Walaszek, H.; Kouadri-David, A.; Guégan, S.; Flifla, J.
2014-06-01
Laser welding of aluminium generally creates embedded welding defects, such as porosities or cracks. Non Destructive Inspection (NDI) after processing may ensure an acceptable weld quality by defect detection. Nowadays, NDI techniques used to control the inside of a weld are mainly limited to X-Rays or ultrasonics. The current paper describes the use of a Laser Ultrasound (LU) technique to inspect porosities in 2 and 4-mm thick sheet lap welds. First experimentations resulted in the detection of 0.5-mm drilled holes in bulk aluminium sheets. The measurement of the depth of these defects is demonstrated too. Further experimentations shows the applicability of the LU technique to detect porosities in aluminium laser welds. However, as the interpretation of raw measures is limiting the detection capacity of this technique, we developed a signal processing using Time-Reversal capabilities to enhance detection capacities. Furthermore, the signal processing output is a geometrical image of the material's inner state, increasing the ease of interpretation. It is based on a mass-spring simulation which enables the back-propagation of the acquired ultrasound signal. The spring-mass simulation allows the natural generation of all the different sound waves and thus enables the back-propagation of a raw signal without any need of filtering or wave identification and extraction. Therefore the signal processing uses the information contained in the compression wave as well as in the shear wave.
Analysis of the experimental positron lifetime spectra by neural networks
Directory of Open Access Journals (Sweden)
Avdić Senada
2003-01-01
Full Text Available This paper deals with the analysis of experimental positron lifetime spectra in polymer materials by using various algorithms of neural networks. A method based on the use of artificial neural networks for unfolding the mean lifetime and intensity of the spectral components of simulated positron lifetime spectra was previously suggested and tested on simulated data [Pžzsitetal, Applied Surface Science, 149 (1998, 97]. In this work, the applicability of the method to the analysis of experimental positron spectra has been verified in the case of spectra from polymer materials with three components. It has been demonstrated that the backpropagation neural network can determine the spectral parameters with a high accuracy and perform the decomposi-tion of lifetimes which differ by 10% or more. The backpropagation network has not been suitable for the identification of both the parameters and the number of spectral components. Therefore, a separate artificial neural network module has been designed to solve the classification problem. Module types based on self-organizing map and learning vector quantization algorithms have been tested. The learning vector quantization algorithm was found to have better performance and reliability. A complete artificial neural network analysis tool of positron lifetime spectra has been constructed to include a spectra classification module and parameter evaluation modules for spectra with a different number of components. In this way, both flexibility and high resolution can be achieved.
Implementation of neural network hardware based on a floating point operation in an FPGA
Kim, Jeong-Seob; Jung, Seul
2007-12-01
This paper presents a hardware design and implementation of the radial basis function (RBF) neural network (NN) by the hardware description language. Due to its nonlinear characteristics, it is very difficult to implement for a system with integer-based operation. To develop nonlinear functions such sigmoid functions or exponential functions, floating point operations are required. The exponential function is designed based on the 32bit single-precision floating-point format. In addition, to update weights in the network, the back-propagation algorithm is also implemented in the hardware. Most operations are performed in the floating-point based arithmetic unit and accomplished sequentially by the instruction order stored in ROM. The NN is implemented and tested on the Altera FPGA "Cyclone2 EP2C70F672C8" for nonlinear classifications.
A DECISION SUPPORT SYSTEM FOR THE DIAGNOSIS OF HEART . V AL VE DISEASES
Directory of Open Access Journals (Sweden)
İbrahim Türkoğlu
2002-09-01
Full Text Available In this pa per, a decision s up port system is presented for interpretation of the Doppler signals of the heart valve diseases based on the pattern recognition. This paper especially deals with the feature extraction from measured Doppler signal waveforms at the heart valve using the Doppler Ultrasound. Wavelet transforms and power spectrum estimate by Yule-Walker AR method are used to feature extract from the Doppler signals on the timefrequency domain. Wavelet entropy method is applied to these features. The back-propagation neural network is used to classify the extracted features. The performance of the developed system has been evaluated in 215 samples. The test results showed that this system was effective to detect Doppler heart sounds. The correct classification rate was about 84°/o for normal subjects and 95.9°/o for abnormal subjects.
Qu, Wei-wei; Shang, Li-ping; Li, Xiao-xia; Liu, Jing
2010-10-01
The present paper used synthesized data from the experiment samples to replace partial basic experiments, and increased the training samples amount from 14 to 27. In principal component analysis (PCA), the dimensionality of multivariate data was reduced to n principal components and almost all data information was kept. The PCA reduced the network's input nodes from 60 to 3 to simplify the neural network's structure. Finally, back-propagation neural network was used to train and predict these samples. It had 27 training samples, the input layer had three nodes, the hidden layer had two nodes, and the output layer had two nodes. Its excitation function is variable learning rate method. The results show that the coefficient of recovery can reach 89.6-109.0. It has reached the expected purpose.
Artificial Neural Networks, Symmetries and Differential Evolution
Urfalioglu, Onay
2010-01-01
Neuroevolution is an active and growing research field, especially in times of increasingly parallel computing architectures. Learning methods for Artificial Neural Networks (ANN) can be divided into two groups. Neuroevolution is mainly based on Monte-Carlo techniques and belongs to the group of global search methods, whereas other methods such as backpropagation belong to the group of local search methods. ANN's comprise important symmetry properties, which can influence Monte-Carlo methods. On the other hand, local search methods are generally unaffected by these symmetries. In the literature, dealing with the symmetries is generally reported as being not effective or even yielding inferior results. In this paper, we introduce the so called Minimum Global Optimum Proximity principle derived from theoretical considerations for effective symmetry breaking, applied to offline supervised learning. Using Differential Evolution (DE), which is a popular and robust evolutionary global optimization method, we experi...
Massively parallel processing of remotely sensed hyperspectral images
Plaza, Javier; Plaza, Antonio; Valencia, David; Paz, Abel
2009-08-01
In this paper, we develop several parallel techniques for hyperspectral image processing that have been specifically designed to be run on massively parallel systems. The techniques developed cover the three relevant areas of hyperspectral image processing: 1) spectral mixture analysis, a popular approach to characterize mixed pixels in hyperspectral data addressed in this work via efficient implementation of a morphological algorithm for automatic identification of pure spectral signatures or endmembers from the input data; 2) supervised classification of hyperspectral data using multi-layer perceptron neural networks with back-propagation learning; and 3) automatic target detection in the hyperspectral data using orthogonal subspace projection concepts. The scalability of the proposed parallel techniques is investigated using Barcelona Supercomputing Center's MareNostrum facility, one of the most powerful supercomputers in Europe.
An MLP Neural Net with L1 and L2 Regularizers for Real Conditions of Deblurring
Directory of Open Access Journals (Sweden)
Bernués Emiliano
2010-01-01
Full Text Available Abstract Real conditions of deblurring involve a spatially nonlinear process since the borders are truncated, causing significant artifacts in the restored results. Typically, it is assumed to have boundary conditions to reduce ringing; in contrast, this paper proposes a restoration method which simply deals with null borders. We minimize a deterministic regularized function in a Multilayer Perceptron (MLP with no training and follow a back-propagation algorithm with the L1 and L2 norm-based regularizers. As a result, the truncated borders are regenerated while adapting the center of the image to the optimum linear solution. We report experimental results showing the good performance of our approach in a real model without borders. Even if using boundary conditions, the quality of restoration is comparable to other recent researches.
A Malaysian Vehicle License Plate Localization and Recognition System
Directory of Open Access Journals (Sweden)
Ganapathy Velappa
2008-02-01
Full Text Available Technological intelligence is a highly sought after commodity even in traffic-based systems. These intelligent systems do not only help in traffic monitoring but also in commuter safety, law enforcement and commercial applications. In this paper, a license plate localization and recognition system for vehicles in Malaysia is proposed. This system is developed based on digital images and can be easily applied to commercial car park systems for the use of documenting access of parking services, secure usage of parking houses and also to prevent car theft issues. The proposed license plate localization algorithm is based on a combination of morphological processes with a modified Hough Transform approach and the recognition of the license plates is achieved by the implementation of the feed-forward backpropagation artificial neural network. Experimental results show an average of 95% successful license plate localization and recognition in a total of 589 images captured from a complex outdoor environment.
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 R(2) = 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.
Institute of Scientific and Technical Information of China (English)
张长江; 付梦印; 金梅
2003-01-01
A kind of second-order algorithm--recursive approximate Newton algorithm was given by Karayiannis. The algorithm was simplified when it was formulated. Especially, the simplification to matrix Hessian was very reluctant, which led to the loss of valuable information and affected performance of the algorithm to certain extent. For multi-layer feed-forward neural networks, the second-order back-propagation recursive algorithm based generalized cost criteria was proposed. It is proved that it is equivalent to Newton recursive algorithm and has a second-order convergent rate. The performance and application prospect are analyzed. Lots of simulation experiments indicate that the calculation of the new algorithm is almost equivalent to the recursive least square multiple algorithm. The algorithm and selection of networks parameters are significant and the performance is more excellent than BP algorithm and the second-order learning algorithm that was given by Karayiannis.
Neurocontrol and neurobiology - New developments and connections
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.
Institute of Scientific and Technical Information of China (English)
徐继彭; 林柳兰; 胡庆夕; 方明伦
2006-01-01
Plasma surfacing is an important enabling technology in high-performance coating applications. Recently, it is applied to rapid prototyping/tooling to reduce development time and manufacturing cost for the development of new products. However, this technology is in its infancy, it is essential to understand clearly how process variables relate to deposit microstructure and properties for plasma deposition manufacturing process control. In this paper, layer appearance of single surfacing under different parameters such as plasma current, voltage, powder feedrate and travel speed is studied. Back-propagation neural networks are used to associate the depositing process variables with the features of the deposit layer shape. These networks can be effectively implemented to estimate the layer shape. The results indicate that neural networks can yield fairly accurate results and can be used as a practical tool in plasma deposition manufacturing process.
A method for predicting in-cylinder compound combustion emissions
Institute of Scientific and Technical Information of China (English)
苏石川; 严兆大; 元广杰; 曹韵华; 周重光
2002-01-01
This paper presents a method using a large steady-state engine operation data matrix to provide necessary information for successfully training a predictive network, while at the same time eliminating errors produced by the dispersive effects of the emissions measurement system. The steady-state training conditions of compound fuel allow for the correlation of time-averaged in-cylinder combustion variables to the engine-out NOx and HC emissions. The error back-propagation neural network (EBP) is then capable of learning the relationships between these variables and the measured gaseous emissions, and then interpolating between steady-state points in the matrix. This method for NOx and HC has been proved highly successful.
Institute of Scientific and Technical Information of China (English)
Chen Xi; Chen Cai; Hao Qingqing; Zhang Zhicai; Shi Peng
2008-01-01
Karstic aquifers in Southwest China are largely located in mountainous areas and groundwater level observation data are usually absent. Therefore, numerical groundwater models are inappropriate for simulation of groundwater flow and rainfall-underground outflow responses. In this study, an artificial neural network (ANN) model was developed to simulate underground stream discharge. The ANN model was applied to the Houzhai subterranean drainage in Guizhou Province of Southwest China, which is representative of karstic geomorphology in the humid areas of China. Correlation analysis between daily rainfall and the outflow series was used to determine the model inputs and time lags. The ANN model was trained using an error backpropagation algorithm and validated at three hydrological stations with different karstic features. Study results show that the ANN model performs well in the modeling of highly non-linear karstic aquifers.
Neural PID Control Strategy for Networked Process Control
Directory of Open Access Journals (Sweden)
Jianhua Zhang
2013-01-01
Full Text Available A new method with a two-layer hierarchy is presented based on a neural proportional-integral-derivative (PID iterative learning method over the communication network for the closed-loop automatic tuning of a PID controller. It can enhance the performance of the well-known simple PID feedback control loop in the local field when real networked process control applied to systems with uncertain factors, such as external disturbance or randomly delayed measurements. The proposed PID iterative learning method is implemented by backpropagation neural networks whose weights are updated via minimizing tracking error entropy of closed-loop systems. The convergence in the mean square sense is analysed for closed-loop networked control systems. To demonstrate the potential applications of the proposed strategies, a pressure-tank experiment is provided to show the usefulness and effectiveness of the proposed design method in network process control systems.
Adaptive Functional-Based Neuro-Fuzzy-PID Incremental Controller Structure
Directory of Open Access Journals (Sweden)
Ashraf Ahmed Fahmy
2014-03-01
Full Text Available This paper presents an adaptive functional-based Neuro-fuzzy-PID incremental (NFPID controller structure that can be tuned either offline or online according to required controller performance. First, differential membership functions are used to represent the fuzzy membership functions of the input-output space of the three term controller. Second, controller rules are generated based on the discrete proportional, derivative, and integral function for the fuzzy space. Finally, a fully differentiable fuzzy neural network is constructed to represent the developed controller for either offline or online controller parameter adaptation. Two different adaptation methods are used for controller tuning, offline method based on controller transient performance cost function optimization using Bees Algorithm, and online method based on tracking error minimization using back-propagation with momentum algorithm. The proposed control system was tested to show the validity of the controller structure over a fixed PID controller gains to control SCARA type robot arm.
100-Picometer Interferometry for EUVL
Energy Technology Data Exchange (ETDEWEB)
Sommargren, G E; Phillion, D W; Johnson, M A; Nguyen, N O; Barty, A; Snell, F J; Dillon, D R; Bradsher, L S
2002-03-18
Future extreme ultraviolet lithography (EWL) steppers will, in all likelihood, have six-mirror projection cameras. To operate at the diffraction limit over an acceptable depth of focus each aspheric mirror will have to be fabricated with an absolute figure accuracy approaching 100 pm rms. We are currently developing visible light interferometry to meet this need based on modifications of our present phase shifting diffraction interferometry (PSDI) methodology where we achieved an absolute accuracy of 250pm. The basic PSDI approach has been further simplified, using lensless imaging based on computational diffractive back-propagation, to eliminate auxiliary optics that typically limit measurement accuracy. Small remaining error sources, related to geometric positioning, CCD camera pixel spacing and laser wavelength, have been modeled and measured. Using these results we have estimated the total system error for measuring off-axis aspheric EUVL mirrors with this new approach to interferometry.
Directory of Open Access Journals (Sweden)
E O Omidiora
2012-05-01
Full Text Available The aim of this research is to analyze humans fingerprint texture in order to determine their Age & Gender, and correlation of RTVTR and Ridge Count on gender detection. The study is to analyze the effectiveness of physical biometrics (thumbprint in order to determine age and gender in humans. An application system was designed to capture the finger prints of sampled population through a fingerprint scanner device interfaced to the computer system via Universal Serial Bus (USB, and stored in Microsoft SQL Server database, while back-propagation neural network will be used to train the stored fingerprint. The specific Objectives of this research are to: Use fingerprint sensor to collect different individual fingerprint, alongside their age and gender, Formulate a model and develop a fingerprint based identification system to determine age and gender of individuals and evaluate the developed system.
Directory of Open Access Journals (Sweden)
Padmanaban Sanjeevikumar
2008-01-01
Full Text Available This paper presents an artificial neural network (ANN based approach to tune the parameters of the cascaded d-q axis controller for an AC-DC-AC converter without dc link capacitor. The proposed converter uses the cascaded d-q axis controller on the rectifier side and space vector pulse width modulation on the inverter side. The feed-forward ANN with the error back-propagation training is employed to tune the parameters of the cascaded d-q axis controller. The converter topology provides simple commutation procedure with reduced number of switches and has additional advantages such as good voltage transfer ratio, four quadrant operation, unity power factor, no DC link capacitor and less THD in both the line and load sides. Simulation results closely match with theoretical analysis.
Institute of Scientific and Technical Information of China (English)
杨京; 程建春
2001-01-01
A new inverse method based on the wavelet transform and artificial neural networks (ANN) is presented to recover elastic constants of a fibre-reinforced composite plate from laser-based ultrasonic Lamb waves. The transient waveforms obtained by numerical simulations under different elastic constants are taken as the input of the ANN for training and learning. The wavelet transform is employed for extracting the eigenvectors from the raw Lamb wave signals so as to simplify the structure of the ANN. Then these eigenvectors are input to a multi-layer internally recurrent neural network with a back-propagation algorithm. Finally, the experimental waveforms are used as the input in the whole system to inverse elastic constants of the experimental material.
Financial Time Series Prediction Using Elman Recurrent Random Neural Networks.
Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli
2016-01-01
In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices.
Synthesis of recurrent neural networks for dynamical system simulation.
Trischler, Adam P; D'Eleuterio, Gabriele M T
2016-08-01
We review several of the most widely used techniques for training recurrent neural networks to approximate dynamical systems, then describe a novel algorithm for this task. The algorithm is based on an earlier theoretical result that guarantees the quality of the network approximation. We show that a feedforward neural network can be trained on the vector-field representation of a given dynamical system using backpropagation, then recast it as a recurrent network that replicates the original system's dynamics. After detailing this algorithm and its relation to earlier approaches, we present numerical examples that demonstrate its capabilities. One of the distinguishing features of our approach is that both the original dynamical systems and the recurrent networks that simulate them operate in continuous time.
Energy Technology Data Exchange (ETDEWEB)
Lin, Whei-Min; Hong, Chih-Ming [Department of Electrical Engineering, National Sun Yat-Sen University, Kaohsiung 80424 (China); Cheng, Fu-Sheng [Department of Electrical Engineering, Cheng-Shiu University, Kaohsiung 83305 (China)
2011-02-15
This paper presents the design of an on-line training recurrent fuzzy neural network (RFNN) controller with a high-performance model reference adaptive system (MRAS) observer for the sensorless control of a induction generator (IG). The modified particle swarm optimization (MPSO) is adopted in this study to adapt the learning rates in the back-propagation process of the RFNN to improve the learning capability. By using the proposed RFNN controller with MPSO, the IG system can work for stand-alone power application effectively. The proposed output maximization control is achieved without mechanical sensors such as the wind speed or position sensor, and the new control system will deliver maximum electric power with light weight, high efficiency, and high reliability. The estimation of the rotor speed is based on the MRAS control theory. A sensorless vector-control strategy for an IG operating in a grid-connected variable speed wind energy conversion system can be achieved. (author)
Hayashi, Hideaki; Shima, Keisuke; Shibanoki, Taro; Kurita, Yuichi; Tsuji, Toshio
2013-01-01
This paper outlines a probabilistic neural network 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 that incorporates a Gaussian mixture model expressed in the reduced-dimensional space. The analysis can be incorporated into a neural network so that parameters can be obtained appropriately as network coefficients according to backpropagation-through-time-based training algorithm. The network is considered to enable high-accuracy classification of high-dimensional time-series patterns and to reduce the computation time taken for network training. In the experiments conducted during the study, the validity of the proposed network was demonstrated for EEG signals.
Directory of Open Access Journals (Sweden)
Hongze Li
2014-01-01
Full Text Available Short-term power load forecasting is one of the most important issues in the economic and reliable operation of electricity power system. Taking the characteristics of randomness, tendency, and periodicity of short-term power load into account, a new method (SSA-AR model which combines the univariate singular spectrum analysis and autoregressive model is proposed. Firstly, the singular spectrum analysis (SSA is employed to decompose and reconstruct the original power load series. Secondly, the autoregressive (AR model is used to forecast based on the reconstructed power load series. The employed data is the hourly power load series of the Mid-Atlantic region in PJM electricity market. Empirical analysis result shows that, compared with the single autoregressive model (AR, SSA-based linear recurrent method (SSA-LRF, and BPNN (backpropagation neural network model, the proposed SSA-AR method has a better performance in terms of short-term power load forecasting.
Multi-agent reinforcement learning using modular neural network Q-learning algorithms
Institute of Scientific and Technical Information of China (English)
YANG Yin-xian; FANG Kai
2005-01-01
Reinforcement learning is an excellent approach which is used in artificial intelligence,automatic control, etc. However, ordinary reinforcement learning algorithm, such as Q-learning with lookup table cannot cope with extremely complex and dynamic environment due to the huge state space. To reduce the state space, modular neural network Q-learning algorithm is proposed, which combines Q-learning algorithm with neural network and module method. Forward feedback neural network, Elman neural network and radius-basis neural network are separately employed to construct such algorithm. It is revealed that Elman neural network Q-learning algorithm has the best performance under the condition that the same neural network training method, i.e. gradient descent error back-propagation algorithm is applied.
Directory of Open Access Journals (Sweden)
Katarína Hiľovská
2011-09-01
Full Text Available To a degree the financial crisis influenced all European countries but the most affected are the PIGS (Portugal, Ireland, Greece and Spain. We investigated the effect of the financial crisis on the prediction accuracy of artificial neural networks on the Portuguese, Irish, Athens and Madrid Stock Exchange. We applied three-layered feed-forward neural networks with backpropagation algorithm to forecast the next day prices and we compared the paper returns achieved before and after the recent financial crisis. This method failed in forecasting the direction of the next day price movement but performed well in absolute price changes. However, it achieved better results than the strategy based on technical analysis in the period before the crisis. On the other hand, technical analysis performed better during the crisis.
Directory of Open Access Journals (Sweden)
Salim Lahmiri
2012-08-01
Full Text Available In this study, the backpropagation neural network (BPNN is tested for the ability to forecast the daily volatility of two stock market indices from the Middle East and North Africa (MENA region using volume; namely Morocco and Saudi Arabia. Volatility series were estimated using the Exponential Auto-Regressive Conditional Heteroskedasticity (EGARCH model. The simulation results show that trading volume helps improving the forecasting accuracy of BPNN in Morocco but not in Saudi Arabia. As a result, volume represents valuable information flow to be used in the modeling and prediction of volatility in Morocco. In addition, it is found that BPNN overpredicts volatility during high volatile periods. This finding is important in financial applications such as asset allocation and derivatives pricing.
Hybrid Neural Network Architecture for On-Line Learning
Chen, Yuhua; Wang, Lei
2008-01-01
Approaches to machine intelligence based on brain models have stressed the use of neural networks for generalization. Here we propose the use of a hybrid neural network architecture that uses two kind of neural networks simultaneously: (i) a surface learning agent that quickly adapt to new modes of operation; and, (ii) a deep learning agent that is very accurate within a specific regime of operation. The two networks of the hybrid architecture perform complementary functions that improve the overall performance. The performance of the hybrid architecture has been compared with that of back-propagation perceptrons and the CC and FC networks for chaotic time-series prediction, the CATS benchmark test, and smooth function approximation. It has been shown that the hybrid architecture provides a superior performance based on the RMS error criterion.
Effect of the size of an artificial neural network used as pattern identifier
Energy Technology Data Exchange (ETDEWEB)
Reynoso V, M.R.; Vega C, J.J. [ININ, 52045 Ocoyoacac, Estado de Mexico (Mexico)
2003-07-01
A novel way to extract relevant parameters associated with the outgoing ions from nuclear reactions, obtained by digitizing the signals provided by a Bragg curve spectrometer (BCS) is presented. This allowed the implementation of a more thorough pulse-shape analysis. Due to the complexity of this task, it was required to take advantage of new and more powerful computational paradigms. This was fulfilled using a back-propagation artificial neural network (ANN) as a pattern identifier. Over training of ANNs is a common problem during the training stage. In the performance of the ANN there is a compromise between its size and the size of the training set. Here, this effect will be illustrated in relation to the problem of Bragg Curve (BC) identification. (Author)
Control method for exoskeleton ankle with surface electromyography signals
Institute of Scientific and Technical Information of China (English)
ZHANG Zhen; WANG Zhen; JIANG Jia-xin; QIAN Jin-wu
2009-01-01
This paper is concerned with a control method for an exoskeleton ankle with clectromyography (EMG) signals.The EMG signals of human ankle and the exoskeleton ankle are introduced.Then a control method is proposed to control the exoskeleton ankle using the EMG signals.The feed-forward neural network model applied here is composed of four layers and uses the back-propagation training algorithm.The output signals from neural network are processed by the wavelet transform.Finally the control orders generated from the output signals are passed to the motor controller and drive the exoskeleton to move.Through experiments,the equality of neural network prediction of ankle movement is evaluated by giving the correlation coefficient.It is shown from the experimental results that the proposed method can accurately control the movement of ankle joint.
Zhang, Fan; Wang, Dan; Ding, Rui; Chen, Zhangyuan
2014-09-22
We propose a time domain structure of channel estimation for coherent optical communication systems, which employs training sequence based equalizer and is transparent to arbitrary quadrature amplitude modulation (QAM) formats. Enabled with this methodology, 1.02 Tb/s polarization division multiplexed 32 QAM Nyquist pulse shaping signal with a net spectral efficiency of 7.46 b/s/Hz is transmitted over standard single-mode fiber link with Erbium-doped fiber amplifier only amplification. After 1190 km transmission, the average bit-error rate is lower than the 20% hard-decision forward error correction threshold of 1.5 × 10(-2). The transmission distance can be extended to 1428 km by employing intra-subchannel nonlinear compensation with the digital back-propagation method.
Application of feedback connection artificial neural network to seismic data filtering
Djarfour, Noureddine; Baddari, Kamel; Mihoubi, Abdelhafid; Ferahtia, Jalal; 10.1016/j.crte.2008.03.003
2008-01-01
The Elman artificial neural network (ANN) (feedback connection) was used for seismic data filtering. The recurrent connection that characterizes this network offers the advantage of storing values from the previous time step to be used in the current time step. The proposed structure has the advantage of training simplicity by a back-propagation algorithm (steepest descent). Several trials were addressed on synthetic (with 10% and 50% of random and Gaussian noise) and real seismic data using respectively 10 to 30 neurons and a minimum of 60 neurons in the hidden layer. Both an iteration number up to 4000 and arrest criteria were used to obtain satisfactory performances. Application of such networks on real data shows that the filtered seismic section was efficient. Adequate cross-validation test is done to ensure the performance of network on new data sets.
Modeling and computing of stock index forecasting based on neural network and Markov chain.
Dai, Yonghui; Han, Dongmei; Dai, Weihui
2014-01-01
The stock index reflects the fluctuation of the stock market. For a long time, there have been a lot of researches on the forecast of stock index. However, the traditional method is limited to achieving an ideal precision in the dynamic market due to the influences of many factors such as the economic situation, policy changes, and emergency events. Therefore, the approach based on adaptive modeling and conditional probability transfer causes the new attention of researchers. This paper presents a new forecast method by the combination of improved back-propagation (BP) neural network and Markov chain, as well as its modeling and computing technology. This method includes initial forecasting by improved BP neural network, division of Markov state region, computing of the state transition probability matrix, and the prediction adjustment. Results of the empirical study show that this method can achieve high accuracy in the stock index prediction, and it could provide a good reference for the investment in stock market.
Comparison of biomass estimation techniques for a Bacillus thuringiensis fed-batch culture
Energy Technology Data Exchange (ETDEWEB)
Cunha, C.C.F. [University of Newcastle upon Tyne (United Kingdom). Dept. of Chemical and Process Engineering]. E-mail: C.C.F.Cunha@newcastle.ac.uk; Souza Junior, M.B. [Universidade Federal, Rio de Janeiro, RJ (Brazil). Escola de Quimica]. E-mail: mbsj@h2o.eq.ufrj.br
2001-03-01
In this work, the ability of artificial neural nets was investigated for the on-line biomass prediction of the simulated growth of a strain of Bacillus thuringiensis in fed-batch mode. For this purpose, multilayered backpropagation nets with sigmoid nodes were trained. The patterns were composed of input data on current values of biomass concentration, limiting substrate concentration and dilution rate, and output data on prediction of biomass concentration for the following step. The dilution rate was disturbed by a PRBS input, and simulations were conducted using a phenomenological experimentally validated model. The nets were able to predict the biomass concentration for different feeding techniques, and they were also compared with the variable estimation technique using the extended Kalman filter. (author)
Extracting Symbolic Rules for Medical Diagnosis Problem
Kamruzzaman, S M
2010-01-01
Neural networks (NNs) have been successfully applied to solve a variety of application problems involving classification and function approximation. Although backpropagation NNs generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions cannot be explained as those of decision trees. In many applications, it is desirable to extract knowledge from trained NNs for the users to gain a better understanding of how the networks solve the problems. An algorithm is proposed and implemented to extract symbolic rules for medical diagnosis problem. Empirical study on three benchmarks classification problems, such as breast cancer, diabetes, and lenses demonstrates that the proposed algorithm generates high quality rules from NNs comparable with other methods in terms of number of rules, average number of conditions for a rule, and predictive accuracy.
Medical diagnosis using neural network
Kamruzzaman, S M; Siddiquee, Abu Bakar; Mazumder, Md Ehsanul Hoque
2010-01-01
This research is to search for alternatives to the resolution of complex medical diagnosis where human knowledge should be apprehended in a general fashion. Successful application examples show that human diagnostic capabilities are significantly worse than the neural diagnostic system. This paper describes a modified feedforward neural network constructive algorithm (MFNNCA), a new algorithm for medical diagnosis. The new constructive algorithm with backpropagation; offer an approach for the incremental construction of near-minimal neural network architectures for pattern classification. The algorithm starts with minimal number of hidden units in the single hidden layer; additional units are added to the hidden layer one at a time to improve the accuracy of the network and to get an optimal size of a neural network. The MFNNCA was tested on several benchmarking classification problems including the cancer, heart disease and diabetes. Experimental results show that the MFNNCA can produce optimal neural networ...
A Constructive Algorithm for Feedforward Neural Networks for Medical Diagnostic Reasoning
Siddiquee, Abu Bakar; Kamruzzaman, S M
2010-01-01
This research is to search for alternatives to the resolution of complex medical diagnosis where human knowledge should be apprehended in a general fashion. Successful application examples show that human diagnostic capabilities are significantly worse than the neural diagnostic system. Our research describes a constructive neural network algorithm with backpropagation; offer an approach for the incremental construction of nearminimal neural network architectures for pattern classification. The algorithm starts with minimal number of hidden units in the single hidden layer; additional units are added to the hidden layer one at a time to improve the accuracy of the network and to get an optimal size of a neural network. Our algorithm was tested on several benchmarking classification problems including Cancer1, Heart, and Diabetes with good generalization ability.
PREDIKSI CUACA MENGGUNAKAN METODE CASE BASED REASONING DAN ADAPTIVE NEURO FUZZY INFERENCE SYSTEM
Directory of Open Access Journals (Sweden)
Ria Chaniago
2014-01-01
Full Text Available Weather is one of the nature elements that can influence decision making in human's life. Based on that issue, the author wants to make an application that is able to predict weather with good accuracy. The application is a weather forecasting system, using computer technology that implements expert system. The methods used are Adaptive Neuro Fuzzy Inference System (ANFIS and Case Based Reasoning (CBR, and a combination of both methods will applied to the system. The system also has learning methods like Backpropagation Error (BPE and Recursive Least Error (RLSE, to increase its accuracy. Clustering and data cleaning also done inside the system, as it needed by forecasting process to achieve a good result. K-Means is the clustering algorithm, while Box and Whisker Plot is the algorithm for data cleaning. The result from this project is to create a weather forecasting system with high accuracy.
Learning to train neural networks for real-world control problems
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.
Highly Accurate Multi-layer Perceptron Neural Network for Air Data System
Directory of Open Access Journals (Sweden)
H. S. Krishna
2009-11-01
Full Text Available The error backpropagation multi-layer perceptron algorithm is revisited. This algorithm is used to train and validate two models of three-layer neural networks that can be used to calibrate a 5-hole pressure probe. This paper addresses Occam's Razor problem as it describes the adhoc training methodology applied to improve accuracy and sensitivity. The trained outputs from 5-4-3 feed-forward network architecture with jump connection are comparable to second decimal digit (~0.05 accuracy, hitherto unreported in literature.Defence Science Journal, 2009, 59(6, pp.670-674, DOI:http://dx.doi.org/10.14429/dsj.59.1574
An intelligent power factor corrector for power system using artificial neural networks
Energy Technology Data Exchange (ETDEWEB)
Bayindir, R.; Colak, I. [Department of Electrical Education, Faculty of Technical Education, Gazi University, Besevler, 06500 Ankara (Turkey); Sagiroglu, S. [Department of Computer Engineering, Faculty of Engineering and Architecture, Celal Bayar Bulvari, Gazi University, Maltepe, 06570 Ankara (Turkey)
2009-01-15
An intelligent power factor correction approach based on artificial neural networks (ANN) is introduced. Four learning algorithms, backpropagation (BP), delta-bar-delta (DBD), extended delta-bar-delta (EDBD) and directed random search (DRS), were used to train the ANNs. The best test results obtained from the ANN compensators trained with the four learning algorithms were first achieved. The parameters belonging to each neural compensator obtained from an off-line training were then inserted into a microcontroller for on-line usage. The results have shown that the selected intelligent compensators developed in this work might overcome the problems occurred in the literature providing accurate, simple and low-cost solution for compensation. (author)
Institute of Scientific and Technical Information of China (English)
张春梅
2004-01-01
在对高技术项目投资风险因素分析的基础上,建立了能够预测项目投资风险的三层Levenberg-Marquardt Backpropagation Neural Network (LM-BP)人工神经网络模型.采用此人工神经网络模型,隐含层和输出层传输函数皆为purelin,各层内的所有权重相等,偏置也相等,模型避免了"过拟合"现象的发生.预测结果表明,该神经网络模型稳定可靠,所获得的结果是令人满意的.
Modeling and prediction of Turkey's electricity consumption using Artificial Neural Networks
Energy Technology Data Exchange (ETDEWEB)
Kavaklioglu, Kadir; Ozturk, Harun Kemal; Canyurt, Olcay Ersel [Pamukkale University, Mechanical Engineering Department, Denizli (Turkey); Ceylan, Halim [Pamukkale University, Civil Engineering Department, Denizli (Turkey)
2009-11-15
Artificial Neural Networks are proposed to model and predict electricity consumption of Turkey. Multi layer perceptron with backpropagation training algorithm is used as the neural network topology. Tangent-sigmoid and pure-linear transfer functions are selected in the hidden and output layer processing elements, respectively. These input-output network models are a result of relationships that exist among electricity consumption and several other socioeconomic variables. Electricity consumption is modeled as a function of economic indicators such as population, gross national product, imports and exports. It is also modeled using export-import ratio and time input only. Performance comparison among different models is made based on absolute and percentage mean square error. Electricity consumption of Turkey is predicted until 2027 using data from 1975 to 2006 along with other economic indicators. The results show that electricity consumption can be modeled using Artificial Neural Networks, and the models can be used to predict future electricity consumption. (author)
NEURON-CONTROL OF NONLINEAR SYSTEMS USING GENETIC ALGORITHMS%采用遗传网络算法实现非线性系统的神经网络控制
Institute of Scientific and Technical Information of China (English)
赵小兵; 赵贤燮
2002-01-01
In this thesis,we present a genetic algorithm neuron-control scheme for nonlinear systems.Our method is different from those using supervised learning algorithms,such as the backpropagation(BP) algorithm,that needs training information in each step.The contributions of this thesis are the new approach to constructing neural network architecture and its training.These improvements include: Optimizing connection weights and Optimizing network topology.%提出一种对于非线性系统遗传算法的神经网络控制模型,并给出了新的神经网络训练模型.该模型的主要优点是,优化网络连接权重,优化网络拓扑结构.
Image Binarization Using Multi-Layer Perceptron: A Semi-Supervised Approach
Directory of Open Access Journals (Sweden)
Amlan Raychaudhuri
2012-04-01
Full Text Available In this paper, we have discussed the Image Binarization technique using Multilayer Perceptron (MLP. The purpose of Image Binarization is to extract the lightness (brightness, density as a feature amount from the Image. It converts a gray-scale image of up to 256 gray levels to a black and white image. We use Backpropagation algorithm for training MLP. It is a supervised learning technique. Here Kmeans clustering algorithm has been used for clustering a 256 × 256 gray-level image. The dataset obtained by this is fed to the MLP and processed in a Semi-Supervised way where some training samples are taken as Known patterns (for training and others as Unknown patterns. Finally through this approach a Binarized image is produced.
RPROP算法在测井岩性识别中的应用%Application of RPROP Algorithm to Well Logging Lithologic Identification
Institute of Scientific and Technical Information of China (English)
张治国; 杨毅恒; 夏立显
2005-01-01
为了更好地解决测井岩性识别问题,引入一种快速实用的BP算法-Resilient Backpropagation (RPROP)算法.在说明RPROP算法的基础上,结合某地的实际测井资料,建立基于RPROP算法的BP网络岩性识别模型,进行岩性识别的应用研究.结果表明,应用RPROP算法进行测井资料岩性识别,识别的准确率较高,与基本BP算法及其一些改进算法相比,训练速度快,具有很好的应用前景.
Prediction of the heat transfer rate of a single layer wire-on-tube type heat exchanger using ANFIS
Energy Technology Data Exchange (ETDEWEB)
Hayati, Mohsen [Electrical Engineering Department, Faculty of Engineering, Razi University, Tagh-E-Bostan, Kermanshah 67149 (Iran); Computational Intelligence Research Center, Razi University, Tagh-E-Bostan, Kermanshah 67149 (Iran); Rezaei, Abbas; Seifi, Majid [Electrical Engineering Department, Faculty of Engineering, Razi University, Tagh-E-Bostan, Kermanshah 67149 (Iran)
2009-12-15
In this paper, we applied an Adaptive Neuro-Fuzzy Inference System (ANFIS) model for prediction of the heat transfer rate of the wire-on-tube type heat exchanger. Limited experimental data was used for training and testing ANFIS configuration with the help of hybrid learning algorithm consisting of backpropagation and least-squares estimation. The predicted values are found to be in good agreement with the actual values from the experiments with mean relative error less than 2.55%. Also, we compared the proposed ANFIS model to an ANN approach. Results show that the ANFIS model has more accuracy in comparison to ANN approach. Therefore, we can use ANFIS model to predict the performances of thermal systems in engineering applications, such as modeling heat exchangers for heat transfer analysis. (author)
基于LADT-BP算法的心电图快速分析%A NEW ALGORITHM FOR ECG ANALYSIS BASED ON LADT-BP NEURAL NETWORK
Institute of Scientific and Technical Information of China (English)
李刚; 叶天宇; 何峰
2001-01-01
本文提出了一种应用LADT(Linear Approximation Distance Thresholding)压缩算法进行预处理的BP(Backpropagation)网络算法(我们称为LADT-BP算法)。实验证明该算法与现有的算法相比，在运算速度及正确识别率等方面，均有大幅度的提高。%A new algorithm for ECG analysis was proposed, with combination of LADT compression technique and BP neural network method. The Basic principles of the algorithm and its applications were also discussed. The experiment result showed that the new algorithm was faster in convergence and more accurate in recognition than that of the others.
Wavelet based approach for facial expression recognition
Directory of Open Access Journals (Sweden)
Zaenal Abidin
2015-03-01
Full Text Available Facial expression recognition is one of the most active fields of research. Many facial expression recognition methods have been developed and implemented. Neural networks (NNs have capability to undertake such pattern recognition tasks. The key factor of the use of NN is based on its characteristics. It is capable in conducting learning and generalizing, non-linear mapping, and parallel computation. Backpropagation neural networks (BPNNs are the approach methods that mostly used. In this study, BPNNs were used as classifier to categorize facial expression images into seven-class of expressions which are anger, disgust, fear, happiness, sadness, neutral and surprise. For the purpose of feature extraction tasks, three discrete wavelet transforms were used to decompose images, namely Haar wavelet, Daubechies (4 wavelet and Coiflet (1 wavelet. To analyze the proposed method, a facial expression recognition system was built. The proposed method was tested on static images from JAFFE database.
Robust recurrent neural network modeling for software fault detection and correction prediction
Energy Technology Data Exchange (ETDEWEB)
Hu, Q.P. [Quality and Innovation Research Centre, Department of Industrial and Systems Engineering, National University of Singapore, Singapore 119260 (Singapore)]. E-mail: g0305835@nus.edu.sg; Xie, M. [Quality and Innovation Research Centre, Department of Industrial and Systems Engineering, National University of Singapore, Singapore 119260 (Singapore)]. E-mail: mxie@nus.edu.sg; Ng, S.H. [Quality and Innovation Research Centre, Department of Industrial and Systems Engineering, National University of Singapore, Singapore 119260 (Singapore)]. E-mail: isensh@nus.edu.sg; Levitin, G. [Israel Electric Corporation, Reliability and Equipment Department, R and D Division, Aaifa 31000 (Israel)]. E-mail: levitin@iec.co.il
2007-03-15
Software fault detection and correction processes are related although different, and they should be studied together. A practical approach is to apply software reliability growth models to model fault detection, and fault correction process is assumed to be a delayed process. On the other hand, the artificial neural networks model, as a data-driven approach, tries to model these two processes together with no assumptions. Specifically, feedforward backpropagation networks have shown their advantages over analytical models in fault number predictions. In this paper, the following approach is explored. First, recurrent neural networks are applied to model these two processes together. Within this framework, a systematic networks configuration approach is developed with genetic algorithm according to the prediction performance. In order to provide robust predictions, an extra factor characterizing the dispersion of prediction repetitions is incorporated into the performance function. Comparisons with feedforward neural networks and analytical models are developed with respect to a real data set.
Using Artificial Neural Networks and Function Points to Estimate 4GL Software Development Effort
Directory of Open Access Journals (Sweden)
G.E. Wittig
1994-05-01
Full Text Available Hie value of neural network modelling techniques in performing complicated pattern recognition and nonlinear estimation tasks has been demonstrated across an impressive spectrum of applications. Software development is a complex environment with many interrelated factors affecting development effort and productivity. Accurate forecasting has proved difficult since many of these interrelationships are not fully understood. An attempt to capture the significant attributes of the software development environment to enable improved accuracy in forecasting of development effort is made using backpropagation artificial neural networks. The data for this study was gathered from commercial 4GL software development projects, across a large range of sizes. As is typical of software developments, the range in productivity and other development factors in the data set is also large, accentuating the estimation problem. Despite these difficulties the neural network model predictions were reasonably accurate in comparison with other published results, indicating the potential of the use of this approach.
Institute of Scientific and Technical Information of China (English)
张韧
2001-01-01
基于前传式神经网络BP算法(Backpropagation Neural Network)和回归模型,探讨了西太平洋副高面积指数同赤道东太平洋海温及赤道纬向风之间非线性分类和映射逼近的建模方法和效果比较.结果表明,前传式网络,特别是回归网络预报模型具有较好拟合精度和预报效果及比较实用的预报时效.
Institute of Scientific and Technical Information of China (English)
朱京科; 苏云
2001-01-01
在应用人工神经网络预测有机反应产率中，由于结合了统计方法，使人工神经网络易产生的随机性和过拟合作用造成的不利影响减小，从而提高了预测可靠性。%This work presents a backpropagation neural network trained toreproduce the reaction yield of aryl fluorides by the halex technique. The work shows that a ten-dimensional input space is able to reproduce reasonably the observed reaction yields by employing statistics in artificial neural system. By means of a number of multilayer feedforward (MLF) networks rather than one, the disadvantages caused by network randomness are limited greatly, and therefore the prediction quality is improved. The combined approach is suitable for relatively small training set, which often causes overfitting and leads to unreliable prediction results.
Prediction of Double Layer Grids' Maximum Deflection Using Neural Networks
Directory of Open Access Journals (Sweden)
Reza K. Moghadas
2008-01-01
Full Text Available Efficient neural networks models are trained to predict the maximum deflection of two-way on two-way grids with variable geometrical parameters (span and height as well as cross-sectional areas of the element groups. Backpropagation (BP and Radial Basis Function (RBF neural networks are employed for the mentioned purpose. The inputs of the neural networks are the length of the spans, L, the height, h and cross-sectional areas of the all groups, A and the outputs are maximum deflections of the corresponding double layer grids, respectively. The numerical results indicate that the RBF neural network is better than BP in terms of training time and performance generality.
Evaluation of Starting Current of Induction Motors Using Artificial Neural Network
Directory of Open Access Journals (Sweden)
Iman Sadeghkhani
2014-07-01
Full Text Available Induction motors (IMs are widely used in industry including it be an electrical or not. However during starting period, their starting currents are so large that can damage equipment. Therefore, this current should be estimated accurately to prevent hazards caused by it. In this paper, the artificial neural network (ANN as an intelligent tool is used to evaluate starting current peak of IMs. Both Multilayer Perceptron (MLP and Radial Basis Function (RBF structures have been analyzed. Six learning algorithms, backpropagation (BP, delta-bar-delta (DBD, extended delta-bar-delta (EDBD, directed random search (DRS, quick propagation (QP, and levenberg marquardt (LM were used to train the MLP. The simulation results using MATLAB show that most developed ANNs can estimate the starting current peak of IMs with good accuracy. However, it is proven that LM and EDBD algorithms present better performance for starting current evaluation based on average of relative and absolute errors.
Energy Technology Data Exchange (ETDEWEB)
Junghui Chen; Kuan-Po Wang [Chung-Yuan Christian University (China). Dept. of Chemical Engineering; Ming-Tsai Liang [I-Shou University (China). Dept. of Chemical Engineering
2005-06-01
An overlapped type of local neural network is proposed to improve accuracy of the heat transfer coefficient estimation of the supercritical carbon dioxide. The idea of this work is to use the network to estimate the heat transfer coefficient for which there is no accurate correlation model due to the complexity of the thermo-physical properties involved around the critical region. Unlike the global approximation network (e.g. backpropagation network) and the local approximation network (e.g. the radial basis function network), the proposed network allows us to match the quick changes in the near-critical local region where the rate of heat transfer is significantly increased and to construct the global smooth perspective far away from that local region. Based on the experimental data for carbon dioxide flowing inside a heated tube at the supercritical condition, the proposed network significantly outperformed some the conventional correlation method and the traditional network models. (Author)
Application of BP neural networks in non-linearity correction of optical tweezers
Institute of Scientific and Technical Information of China (English)
Ziqiang WANG; Yinmei LI; Liren LOU; Henghua WEI; Zhong WANG
2008-01-01
The back-propagation (BP) neural network is proposed to correct nonlinearity and optimize the force measurement and calibration of an optical tweezer sys-tem. Considering the low convergence rate of the BP algo-rithm, the Levenberg-Marquardt (LM) algorithm is used to improve the BP network. The proposed method is experimentally studied for force calibration in a typical optical tweezer system using hydromechanics. The result shows that with the nonlinear correction using BP net-works, the range of force measurement of an optical tweezer system is enlarged by 30% and the precision is also improved compared with the polynomial fitting method. It is demonstrated that nonlinear correction by the neural network method effectively improves the per-formance of optical tweezers without adding or changing the measuring system.
FORECASTING NIKKEI 225 INDEX WITH SUPPORT VECTOR MACHINE
Institute of Scientific and Technical Information of China (English)
HUANG Wei; Yoshiteru Nakamori; WANG Shouyang; YU Lean
2003-01-01
Support Vector Machine (SVM) is a very specific type of learning algorithms characterized by the capacity control of the decision function, the use of the kernel functions and the sparsity of the solution. In this paper, we investigate the predictability of financial movement direction with SVM by forecasting the weekly movement direction of NIKKEI 225 index. To evaluate the forecasting ability of SVM, we compare the performance with those of Linear Discriminant Analysis, Quadratic Discriminant Analysis and Elman Backpropagation Neural Networks. The experiment results show that SVM outperforms other classification methods. Furthermore, we propose a combining model by integrating SVM with other classification methods. The combining model performs the best among the forecasting methods.
Sarkar, Sankho Turjo; Bhondekar, Amol P; Macaš, Martin; Kumar, Ritesh; Kaur, Rishemjit; Sharma, Anupma; Gulati, Ashu; Kumar, Amod
2015-11-01
The paper presents a novel encoding scheme for neuronal code generation for odour recognition using an electronic nose (EN). This scheme is based on channel encoding using multiple Gaussian receptive fields superimposed over the temporal EN responses. The encoded data is further applied to a spiking neural network (SNN) for pattern classification. Two forms of SNN, a back-propagation based SpikeProp and a dynamic evolving SNN are used to learn the encoded responses. The effects of information encoding on the performance of SNNs have been investigated. Statistical tests have been performed to determine the contribution of the SNN and the encoding scheme to overall odour discrimination. The approach has been implemented in odour classification of orthodox black tea (Kangra-Himachal Pradesh Region) thereby demonstrating a biomimetic approach for EN data analysis.
Dynamic Analysis of Structures Using Neural Networks
Directory of Open Access Journals (Sweden)
N. Ahmadi
2008-01-01
Full Text Available In the recent years, neural networks are considered as the best candidate for fast approximation with arbitrary accuracy in the time consuming problems. Dynamic analysis of structures against earthquake has the time consuming process. We employed two kinds of neural networks: Generalized Regression neural network (GR and Back-Propagation Wavenet neural network (BPW, for approximating of dynamic time history response of frame structures. GR is a traditional radial basis function neural network while BPW categorized as a wavelet neural network. In BPW, sigmoid activation functions of hidden layer neurons are substituted with wavelets and weights training are achieved using Scaled Conjugate Gradient (SCG algorithm. Comparison the results of BPW with those of GR in the dynamic analysis of eight story steel frame indicates that accuracy of the properly trained BPW was better than that of GR and therefore, BPW can be efficiently used for approximate dynamic analysis of structures.
Institute of Scientific and Technical Information of China (English)
无
2002-01-01
An adaptive learning control scheme intended to the on-line optimization of sculptured surface cutting process is presented. The scheme uses a back-propagation neural network to learn the relationships between process inputs and process states. The cutting parameters of the process model are optimized through a genetic algorithms(GA). The capacity of the proposed scheme for determining optimum process inputs under a variety of process conditions and optimization strategies is evaluated on the basis of milling of a sculptured surface using a ball-end mill. The experimental results show that the neural network could model the cutting process efficiently, and the cutting conditions such as spindle speed could be regulated for achieving high efficiency and high quality. Therefore the proposed approach can be well applied to the manufacturing of dies and molds.
An Artificial Neural Network for Data Forecasting Purposes
Directory of Open Access Journals (Sweden)
Catalina Lucia COCIANU
2015-01-01
Full Text Available Considering the fact that markets are generally influenced by different external factors, the stock market prediction is one of the most difficult tasks of time series analysis. The research reported in this paper aims to investigate the potential of artificial neural networks (ANN in solving the forecast task in the most general case, when the time series are non-stationary. We used a feed-forward neural architecture: the nonlinear autoregressive network with exogenous inputs. The network training function used to update the weight and bias parameters corresponds to gradient descent with adaptive learning rate variant of the backpropagation algorithm. The results obtained using this technique are compared with the ones resulted from some ARIMA models. We used the mean square error (MSE measure to evaluate the performances of these two models. The comparative analysis leads to the conclusion that the proposed model can be successfully applied to forecast the financial data.
Çebi, A.; Akdoğan, E.; Celen, A.; Dalkilic, A. S.
2016-06-01
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.
Ramadas, C; Balasubramaniam, Krishnan; Joshi, M; Krishnamurthy, C V
2011-07-01
In the present work, the interaction of the fundamental anti-symmetric guided Lamb mode (A(o)) with a structural discontinuity in a composite structure was studied through Finite Element numerical simulations and experiments. The structural component selected for this study was a T-joint section made from glass/epoxy material. This co-cured composite structure is made-up of an upper shell (skin) and a spar as the sub-components. It was observed that when A(o) mode interacts with the junction (structural discontinuity) of these sub-components, a mode-converted S(o) mode is generated. Experiments were conducted using air-coupled ultrasound to validate the numerical simulations. The back-propagating "Turning modes", which propagate from the thin region to the spar web and vice versa, were also numerically simulated and experimentally verified.
Chinea, Alejandro
2009-01-01
Recursive Neural Networks are non-linear adaptive models that are able to learn deep structured information. However, these models have not yet been broadly accepted. This fact is mainly due to its inherent complexity. In particular, not only for being extremely complex information processing models, but also because of a computational expensive learning phase. The most popular training method for these models is back-propagation through the structure. This algorithm has been revealed not to be the most appropriate for structured processing due to problems of convergence, while more sophisticated training methods enhance the speed of convergence at the expense of increasing significantly the computational cost. In this paper, we firstly perform an analysis of the underlying principles behind these models aimed at understanding their computational power. Secondly, we propose an approximate second order stochastic learning algorithm. The proposed algorithm dynamically adapts the learning rate throughout the tra...
Application of DEKF Algorithm in Training FANN%应用DEKF算法训练模糊化神经网络
Institute of Scientific and Technical Information of China (English)
乔士东; 沈振康
2004-01-01
模糊MLP网络的待定参数规模比确定性MLP网络的多几倍,急需找到高效的训练算法.本文尝试用DEKF训练模糊神经网络,这是DEKF算法新的应用.仿真表明,DEKF算法比经典BP算法的收敛速度更快,训练所得网络的精度更高.%Fuzzy neural network has much more parameters to be trained than conventional ANN. In this study, decoupled extended Kalman filter(DEKF) algorithm is applied to train FANN. Simulation indicates shorter training time and more accurate result can be obtained with DEKF algorithm than standard error back-propagation algorithm.
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.
Extended Mixture of MLP Experts by Hybrid of Conjugate Gradient Method and Modified Cuckoo Search
Salimi, Hamid; Soltanshahi, Mohammad Ali; Hatami, Javad
2012-01-01
This paper investigates a new method for improving the learning algorithm of Mixture of Experts (ME) model using a hybrid of Modified Cuckoo Search (MCS) and Conjugate Gradient (CG) as a second order optimization technique. The CG technique is combined with Back-Propagation (BP) algorithm to yield a much more efficient learning algorithm for ME structure. In addition, the experts and gating networks in enhanced model are replaced by CG based Multi-Layer Perceptrons (MLPs) to provide faster and more accurate learning. The CG is considerably depends on initial weights of connections of Artificial Neural Network (ANN), so, a metaheuristic algorithm, the so-called Modified Cuckoo Search is applied in order to select the optimal weights. The performance of proposed method is compared with Gradient Decent Based ME (GDME) and Conjugate Gradient Based ME (CGME) in classification and regression problems. The experimental results show that hybrid MSC and CG based ME (MCS-CGME) has faster convergence and better performa...
Institute of Scientific and Technical Information of China (English)
牛东晓; 刘达; 邢棉
2008-01-01
A combined model based on principal components analysis (PCA) and generalized regression neural network (GRNN) was adopted to forecast electricity price in day-ahead electricity market. PCA was applied to mine the main influence on day-ahead price, avoiding the strong correlation between the input factors that might influence electricity price, such as the load of the forecasting hour, other history loads and prices, weather and temperature; then GRNN was employed to forecast electricity price according to the main information extracted by PCA. To prove the efficiency of the combined model, a case from PJM (Pennsylvania-New Jersey-Maryland) day-ahead electricity market was evaluated. Compared to back-propagation (BP) neural network and standard GRNN, the combined method reduces the mean absolute percentage error about 3%.
Tian, Wenliang; Meng, Fandi; Liu, Li; Li, Ying; Wang, Fuhui
2017-01-01
A concept for prediction of organic coatings, based on the alternating hydrostatic pressure (AHP) accelerated tests, has been presented. An AHP accelerated test with different pressure values has been employed to evaluate coating degradation. And a back-propagation artificial neural network (BP-ANN) has been established to predict the service property and the service lifetime of coatings. The pressure value (P), immersion time (t) and service property (impedance modulus |Z|) are utilized as the parameters of the network. The average accuracies of the predicted service property and immersion time by the established network are 98.6% and 84.8%, respectively. The combination of accelerated test and prediction method by BP-ANN is promising to evaluate and predict coating property used in deep sea.
Jeong, Hyunjo; Zhang, Shuzeng; Li, Xiongbing
2017-02-01
In this work, we employ a focused beam theory to modify the phase reversal at the stress-free boundary, and consequently enhance the second harmonic generation during its back-propagation toward the initial source position. We first confirmed this concept through experiment by using a spherically focused beam at the water-air interface, and measuring the reflected second harmonic and comparing with a planar wave reflected from the same stress-free or a rigid boundary. In order to test the feasibility of this idea for measuring the nonlinearity parameter of solids in a reflection mode, a focused nonlinear ultrasonic beam is modeled for focusing at and reflection from a stress-free boundary. A nonlinearity parameter expression is then defined together with diffraction and attenuation corrections.
SPATIAL DATA MINING TOOLBOX FOR MAPPING SUITABILITY OF LANDFILL SITES USING NEURAL NETWORKS
Directory of Open Access Journals (Sweden)
S. K. M. Abujayyab
2016-09-01
Full Text Available Mapping the suitability of landfill sites is a complex field and is involved with multidiscipline. The purpose of this research is to create an ArcGIS spatial data mining toolbox for mapping the suitability of landfill sites at a regional scale using neural networks. The toolbox is constructed from six sub-tools to prepare, train, and process data. The employment of the toolbox is straightforward. The multilayer perceptron (MLP neural networks structure with a backpropagation learning algorithm is used. The dataset is mined from the north states in Malaysia. A total of 14 criteria are utilized to build the training dataset. The toolbox provides a platform for decision makers to implement neural networks for mapping the suitability of landfill sites in the ArcGIS environment. The result shows the ability of the toolbox to produce suitability maps for landfill sites.
Kaushik, Vikas; Lahiri, Tapobrata; Singha, Shantiswaroop; Dasgupta, Anjan Kumar; Mishra, Hrishikesh; Kumar, Upendra; Kumar, Rajeev
2011-01-01
Study on geometric properties of nanoparticles and their relation with biomolecular activities, especially protein is quite a new field to explore. This work was carried out towards this direction where images of gold nanoparticles obtained from transmission electron microscopy were processed to extract their size and area profile at different experimental conditions including and excluding a protein, citrate synthase. Since the images were ill-posed, texture of a context-window for each pixel was used as input to a back-propagation network architecture to obtain decision on its membership as nanoparticle. The segmented images were further analysed by k-means clustering to derive geometric properties of individual nanoparticles even from their assembled form. The extracted geometric information was found to be crucial to give a model featuring porous cage like configuration of nanoparticle assembly using which the chaperone like activity of gold nanoparticles can be explained. PMID:22355230
Partial-aperture array imaging in acoustic waveguides
Tsogka, Chrysoula; Mitsoudis, Dimitrios A.; Papadimitropoulos, Symeon
2016-12-01
We consider the problem of imaging extended reflectors in waveguides using partial-aperture array, i.e. an array that does not span the whole depth of the waveguide. For this imaging, we employ a method that back-propagates a weighted modal projection of the usual array response matrix. The challenge in this setup is to correctly define this projection matrix in order to maintain good energy concentration properties for the imaging method, which were obtained previously by Tsogka et al (2013 SIAM J. Imaging Sci. 6 2714-39) for the full-aperture case. In this paper we propose a way of achieving this and study the properties of the resulting imaging method.
Prediction of the plasma distribution using an artificial neural network
Institute of Scientific and Technical Information of China (English)
Li Wei; Chen JunFang; Wang Teng
2009-01-01
In this work, an artificial neural network (ANN) model is established using a back-propagation training algorithm in order to predict the plasma spatial distribution in an electron cyclotron resonance (ECR) - plasma-enhanced chemical vapor deposition (PECVD) plasma system. In our model, there are three layers: the input layer, the hidden layer and the output layer. The input layer is composed of five neurons: the radial position, the axial position, the gas pressure,the microwave power and the magnet coil current. The output layer is our target output neuron: the plasma density.The accuracy of our prediction is tested with the experimental data obtained by a Langmuir probe, and ANN results show a good agreement with the experimental data. It is concluded that ANN is a useful tool in dealing with some nonlinear problems of the plasma spatial distribution.
HYDRAULIC PRESSURE SIGNAL DENOISING USING THRESHOLD SELF-LEARNING WAVELET ALGORITHM
Institute of Scientific and Technical Information of China (English)
GUO Xin-lei; YANG Kai-lin; GUO Yong-xin
2008-01-01
A pre-filter combined with threshold self-learning wavelet algorithm is proposed for hydraulic pressure signals denoising. The denoising threshold is self-learnt in the steady flow state, and then modified under a given limit to make the mean square errors between reconstruction signals and desirable outputs minimum, so the corresponding optimal denoising threshold in a single operating case can be obtained. These optimal thresholds are used for the whole signal denoising and are different in various cases. Simulation results and comparative studies show that the present approach has an obvious effect of noise suppression and is superior to those of traditional wavelet algorithms and back-propagation neural networks. It also provides the precise data for the next step of pipeline leak detection using transient technique.
Directory of Open Access Journals (Sweden)
Einar Sørheim
1990-10-01
Full Text Available A neural network architecture called ART2/BP is proposed. Thc goal has been to construct an artificial neural network that learns incrementally an unknown mapping, and is motivated by the instability found in back propagation (BP networks: after first learning pattern A and then pattern B, a BP network often has completely 'forgotten' pattern A. A network using both supervised and unsupervised training is proposed, consisting of a combination of ART2 and BP. ART2 is used to build and focus a supervised backpropagation network consisting of many small subnetworks each specialized on a particular domain of the input space. The ART2/BP network has the advantage of being able to dynamically expand itself in response to input patterns containing new information. Simulation results show that the ART2/BP network outperforms a classical maximum likelihood method for the estimation of a discrete dynamic and nonlinear transfer function.
Chattopadhyay, Goutami; Chattopadhyay, Surajit; Chakraborthy, Parthasarathi
2012-07-01
The present study deals with daily total ozone concentration time series over four metro cities of India namely Kolkata, Mumbai, Chennai, and New Delhi in the multivariate environment. Using the Kaiser-Meyer-Olkin measure, it is established that the data set under consideration are suitable for principal component analysis. Subsequently, by introducing rotated component matrix for the principal components, the predictors suitable for generating artificial neural network (ANN) for daily total ozone prediction are identified. The multicollinearity is removed in this way. Models of ANN in the form of multilayer perceptron trained through backpropagation learning are generated for all of the study zones, and the model outcomes are assessed statistically. Measuring various statistics like Pearson correlation coefficients, Willmott's indices, percentage errors of prediction, and mean absolute errors, it is observed that for Mumbai and Kolkata the proposed ANN model generates very good predictions. The results are supported by the linearly distributed coordinates in the scatterplots.
Integrated software framework for processing of geophysical data
Chubak, Glenn; Morozov, Igor
2006-07-01
We present an integrated software framework for geophysical data processing, based on an updated seismic data processing program package originally developed at the Program for Crustal Studies at the University of Wyoming. Unlike other systems, this processing monitor supports structured multi-component seismic data streams, multi-dimensional data traces, and employs a unique backpropagation execution logic. This results in an unusual flexibility of processing, allowing the system to handle nearly any geophysical data. A modern and feature-rich graphical user interface (GUI) was developed for the system, allowing editing and submission of processing flows and interaction with running jobs. Multiple jobs can be executed in a distributed multi-processor networks and controlled from the same GUI. Jobs, in their turn, can also be parallelized to take advantage of parallel processing environments, such as local area networks and Beowulf clusters.
Biometric system for user authentication based on Hough transform and Neural Network
Directory of Open Access Journals (Sweden)
Rahul Dubey Dheeraj Agrawal
2011-10-01
Full Text Available Authentication of a person is the major concern in this era for security purposes. In biometric systems Signature is one of the behavioural features used for the authentication purpose. In this paper we work on the offline signature collected through different persons. Morphological operations are applied on these signature images with Hough transform to determine regular shape which assists in authentication process. The values extracted from this Hough space is used in the feed forward neural network which is trained using back-propagation algorithm. After the different training stages efficiency found above more than 95%. Application of this system will be in the security concerned fields, in the defence security, biometric authentication, as biometric computer protection or as
Institute of Scientific and Technical Information of China (English)
无
2010-01-01
By using of long-term monitoring data of Runyang Suspension Bridge,the improved back-propagation neural networks (BPNNs) are formulated for modeling the correlations between modal frequencies and environmental conditions including wind,temperature and vehicle load.Then,with the correlation models the environmental effects on modal frequencies are quantified and the abnormal changes of measured frequencies are detected by means of the hypothesis tests.Analysis results reveal that BPNN-based correlation models improved by both early stopping and Bayesian regularization techniques exhibit excellent generalization capability.And the developed correlation models can effectively reduce the environmental variability in modal frequencies.The t-test method provides a good capability to detect the damage-induced 0.16% and 0.12% abnormal changes of the 5th and 6th modal frequencies,respectively.Hence,the proposed method is suitable for real-time monitoring of suspension bridge conditions.
Artificial network prediction on degradable properties of coal-filled films
Institute of Scientific and Technical Information of China (English)
YANG Zhi-yuan; ZHOU An-ning; QU Jian-lin
2005-01-01
Utilized degradable data of coal-filled films from the accelerated UV chamber ageing degradation experiments, and on the basis of control factors' analysis, presented a predicting model on degradable properties of this film in photo-degradation according to back-propagation artificial neural network (BP ANN). 4 controlling factors in films degradation, including temperature, the time of UV irradiation, the concentration and the type of coals were used as input parameters in the ANN model. While the degradable properties after film degradation, including the mechanical properties and carbonyl index, were used as output parameters. It was carried out by the neural network toolbox of Matlab 6.5 software and Visual Basic 6.0. Discussed partition of sample data and model's parameters,and then selected the best configuration of ANN network. The accurate scope of predicting results was analyzed. This model has a high precision in predicting on properties of the coal-filled film degradation.
Automated Periodontal Diseases Classification System
Directory of Open Access Journals (Sweden)
Aliaa A. A. Youssif
2012-01-01
Full Text Available This paper presents an efficient and innovative system for automated classification of periodontal diseases, The strength of our technique lies in the fact that it incorporates knowledge from the patients' clinical data, along with the features automatically extracted from the Haematoxylin and Eosin (H&E stained microscopic images. Our system uses image processing techniques based on color deconvolution, morphological operations, and watershed transforms for epithelium & connective tissue segmentation, nuclear segmentation, and extraction of the microscopic immunohistochemical features for the nuclei, dilated blood vessels & collagen fibers. Also, Feedforward Backpropagation Artificial Neural Networks are used for the classification process. We report 100% classification accuracy in correctly identifying the different periodontal diseases observed in our 30 samples dataset.
Chen, Ying; Liu, Teng; Wang, Wenyue; Zhu, Qiguang; Bi, Weihong
2015-04-01
According to the band gap and photon localization characteristics, the single-arm notching and the double-arm notching Mach-Zehnder interferometer (MZI) structures based on 2D triangular lattice air hole-typed photonic crystal waveguide are proposed. The back-propagation (BP) neural network is introduced to optimize the structural parameters of the photonic crystal MZI structure, which results in the normalized transmission peak increasing from 85.3% to 97.1%. The sensitivity performances of the two structures are compared and analyzed using the Salmonella solution samples with different concentrations in the numerical simulation. The results show that the sensitivity of the double-arm notching structure is 4583 nm/RIU, which is about 6.4 times of the single-arm notching structure, which can provide some references for the optimization of the photonic devices and the design of high-sensitivity biosensors.
Using Artificial Bee Colony Algorithm for MLP Training on Earthquake Time Series Data Prediction
Shah, Habib; Nawi, Nazri Mohd
2011-01-01
Nowadays, computer scientists have shown the interest in the study of social insect's behaviour in neural networks area for solving different combinatorial and statistical problems. Chief among these is the Artificial Bee Colony (ABC) algorithm. This paper investigates the use of ABC algorithm that simulates the intelligent foraging behaviour of a honey bee swarm. Multilayer Perceptron (MLP) trained with the standard back propagation algorithm normally utilises computationally intensive training algorithms. One of the crucial problems with the backpropagation (BP) algorithm is that it can sometimes yield the networks with suboptimal weights because of the presence of many local optima in the solution space. To overcome ABC algorithm used in this work to train MLP learning the complex behaviour of earthquake time series data trained by BP, the performance of MLP-ABC is benchmarked against MLP training with the standard BP. The experimental result shows that MLP-ABC performance is better than MLP-BP for time se...
Directory of Open Access Journals (Sweden)
Małgorzata Pawul
2016-09-01
Full Text Available Recently, a lot of attention was paid to the improvement of methods which are used to air quality forecasting. Artificial neural networks can be applied to model these problems. Their advantage is that they can solve the problem in the conditions of incomplete information, without the knowledge of the analytical relationship between the input and output data. In this paper we applied artificial neural networks to predict the PM 10 concentrations as factors determining the occurrence of smog phenomena. To create these networks we used meteorological data and concentrations of PM 10. The data were recorded in 2014 and 2015 at three measuring stations operating in Krakow under the State Environmental Monitoring. The best results were obtained by three-layer perceptron with back-propagation algorithm. The neural networks received a good fit in all cases.
Round-robin multiple-source localization.
Mantzel, William; Romberg, Justin; Sabra, Karim G
2014-01-01
This paper introduces a round-robin approach for multi-source localization based on matched-field processing. Each new source location is estimated from the ambiguity function after nulling from the data vector the current source location estimates using a robust projection matrix. This projection matrix effectively minimizes mean-square energy near current source location estimates subject to a rank constraint that prevents excessive interference with sources outside of these neighborhoods. Numerical simulations are presented for multiple sources transmitting through a fixed (and presumed known) generic Pekeris ocean waveguide in the single-frequency and broadband-coherent cases that illustrate the performance of the proposed approach which compares favorably against other previously published approaches. Furthermore, the efficacy with which randomized back-propagations may also be incorporated for computational advantage is also presented.
A Novel Single Neuron Perceptron with Universal Approximation and XOR Computation Properties
Directory of Open Access Journals (Sweden)
Ehsan Lotfi
2014-01-01
Full Text Available 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.
Fault Diagnosis of Power System Based on Improved Genetic Optimized BP-NN
Directory of Open Access Journals (Sweden)
Yuan Pu
2015-01-01
Full Text Available BP neural network (Back-Propagation Neural Network, BP-NN is one of the most widely neural network models and is applied to fault diagnosis of power system currently. BP neural network has good self-learning and adaptive ability and generalization ability, but the operation process is easy to fall into local minima. Genetic algorithm has global optimization features, and crossover is the most important operation of the Genetic Algorithm. In this paper, we can modify the crossover of traditional Genetic Algorithm, using improved genetic algorithm optimized BP neural network training initial weights and thresholds, to avoid the problem of BP neural network fall into local minima. The results of analysis by an example, the method can efficiently diagnose network fault location, and improve fault-tolerance and grid fault diagnosis effect.
Directory of Open Access Journals (Sweden)
Vasios C.E.
2003-01-01
Full Text Available In the present work, a new method for the classification of Event Related Potentials (ERPs is proposed. The proposed method consists of two modules: the feature extraction module and the classification module. The feature extraction module comprises the implementation of the Multivariate Autoregressive model in conjunction with the Simulated Annealing technique, for the selection of optimum features from ERPs. The classification module is implemented with a single three-layer neural network, trained with the back-propagation algorithm and classifies the data into two classes: patients and control subjects. The method, in the form of a Decision Support System (DSS, has been thoroughly tested to a number of patient data (OCD, FES, depressives and drug users, resulting successful classification up to 100%.
Directory of Open Access Journals (Sweden)
Erdi Tosun
2016-12-01
Full Text Available This study deals with usage of linear regression (LR and artificial neural network (ANN modeling to predict engine performance; torque and exhaust emissions; and carbon monoxide, oxides of nitrogen (CO, NOx of a naturally aspirated diesel engine fueled with standard diesel, peanut biodiesel (PME and biodiesel-alcohol (EME, MME, PME mixtures. Experimental work was conducted to obtain data to train and test the models. Backpropagation algorithm was used as a learning algorithm of ANN in the multilayered feedforward networks. Engine speed (rpm and fuel properties, cetane number (CN, lower heating value (LHV and density (ρ were used as input parameters in order to predict performance and emission parameters. It was shown that while linear regression modeling approach was deficient to predict desired parameters, more accurate results were obtained with the usage of ANN.
Comparative analysis of regression and artificial neural network models for wind speed prediction
Bilgili, Mehmet; Sahin, Besir
2010-11-01
In this study, wind speed was modeled by linear regression (LR), nonlinear regression (NLR) and artificial neural network (ANN) methods. A three-layer feedforward artificial neural network structure was constructed and a backpropagation algorithm was used for the training of ANNs. To get a successful simulation, firstly, the correlation coefficients between all of the meteorological variables (wind speed, ambient temperature, atmospheric pressure, relative humidity and rainfall) were calculated taking two variables in turn for each calculation. All independent variables were added to the simple regression model. Then, the method of stepwise multiple regression was applied for the selection of the “best” regression equation (model). Thus, the best independent variables were selected for the LR and NLR models and also used in the input layer of the ANN. The results obtained by all methods were compared to each other. Finally, the ANN method was found to provide better performance than the LR and NLR methods.
Short Term Load Forecast Using Wavelet Neural Network
Institute of Scientific and Technical Information of China (English)
Gui Min; Rong Fei; Luo An
2005-01-01
This paper presents a wavelet neural network (WNN) model combining wavelet transform and artificial neural networks for short term load forecast (STLF). Both historical load and temperature data having important impacts on load level were used in the proposed forecasting model. The model used the three-layer feed forward network trained by the error back-propagation algorithm. To enhance the forecasting accuracy by neural networks, wavelet multi-resolution analysis method was introduced to pre-process these data and reconstruct the predicted output. The proposed model has been evaluated with actual data of electricity load and temperature of Hunan Province. The simulation results show that the model is capable of providing a reasonable forecasting accuracy in STLF.
Linear recursive distributed representations.
Voegtlin, Thomas; Dominey, Peter F
2005-09-01
Connectionist networks have been criticized for their inability to represent complex structures with systematicity. That is, while they can be trained to represent and manipulate complex objects made of several constituents, they generally fail to generalize to novel combinations of the same constituents. This paper presents a modification of Pollack's Recursive Auto-Associative Memory (RAAM), that addresses this criticism. The network uses linear units and is trained with Oja's rule, in which it generalizes PCA to tree-structured data. Learned representations may be linearly combined, in order to represent new complex structures. This results in unprecedented generalization capabilities. Capacity is orders of magnitude higher than that of a RAAM trained with back-propagation. Moreover, regularities of the training set are preserved in the new formed objects. The formation of new structures displays developmental effects similar to those observed in children when learning to generalize about the argument structure of verbs.
Parsing recursive sentences with a connectionist model including a neural stack and synaptic gating.
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.
Energy Technology Data Exchange (ETDEWEB)
Altran, A.B.; Lotufo, A.D.P.; Minussi, C.R. [Universidade Estadual Paulista Julio de Mesquita Filho (UNESP), Ilha Solteira, SP (Brazil). Dept. de Engenharia Eletrica], Emails: lealtran@yahoo.com.br, annadiva@dee.feis.unesp.br, minussi@dee.feis.unesp.br; Lopes, M.L.M. [Universidade Estadual Paulista Julio de Mesquita Filho (UNESP), Ilha Solteira, SP (Brazil). Dept. de Matematica], E-mail: mara@mat.feis.unesp.br
2009-07-01
This paper presents a methodology for electrical load forecasting, using radial base functions as activation function in artificial neural networks with the training by backpropagation algorithm. This methodology is applied to short term electrical load forecasting (24 h ahead). Therefore, results are presented analyzing the use of radial base functions substituting the sigmoid function as activation function in multilayer perceptron neural networks. However, the main contribution of this paper is the proposal of a new formulation of load forecasting dedicated to the forecasting in several points of the electrical network, as well as considering several types of users (residential, commercial, industrial). It deals with the MLF (Multimodal Load Forecasting), with the same processing time as the GLF (Global Load Forecasting). (author)
Development of a robust calibration model for nonlinear in-line process data
Despagne; Massart; Chabot
2000-04-01
A comparative study involving a global linear method (partial least squares), a local linear method (locally weighted regression), and a nonlinear method (neural networks) has been performed in order to implement a calibration model on an industrial process. The models were designed to predict the water content in a reactor during a distillation process, using in-line measurements from a near-infrared analyzer. Curved effects due to changes in temperature and variations between the different batches make the problem particularly challenging. The influence of spectral range selection and data preprocessing has been studied. With each calibration method, specific procedures have been applied to promote model robustness. In particular, the use of a monitoring set with neural networks does not always prevent overfitting. Therefore, we developed a model selection criterion based on the determination of the median of monitoring error over replicate trials. The back-propagation neural network models selected were found to outperform the other methods on independent test data.
Damage assessment in structure from changes in static parameter using neural networks
Indian Academy of Sciences (India)
Damodar Maity; Asish Saha
2004-06-01
Damage to structures may occur as a result of normal operations, accidents, deterioration or severe natural events such as earthquakes and storms. Most often the extent and location of damage may be determined through visual inspection. However, in some cases this may not be feasible. The basic strategy applied in this study is to train a neural network to recognize the behaviour of the undamaged structure as well as of the structure with various possible damaged states. When this trained network is subjected to the measured response, it should be able to detect any existing damage. This idea is applied on a simple cantilever beam. Strain and displacement are used as possible candidates for damage identiﬁcation by a back-propagation neural network. The superiority of strain over displacement for identiﬁcation of damage has been observed in this study.
Directory of Open Access Journals (Sweden)
Reza Rastiboroujeni
2015-06-01
Full Text Available In this paper, we propose a computer aided diagnosis (CAD system based on hierarchical convolutional neural networks (HCNNs to discriminate between malignant and benign tumors in breast DCE-MRIs. A HCNN is a hierarchical neural network that operates on two-dimensional images. A HCNN integrates feature extraction and classification processes into one single and fully adaptive structure. It can extract two-dimensional key features automatically, and it is relatively tolerant to geometric and local distortions in input images. We evaluate CNN implementation learning and testing processes based on gradient descent (GD and resilient back-propagation (RPROP approaches. We show that, proposed HCNN with RPROP learning approach provide an effective and robust neural structure to design a CAD base system for breast MRI, and has potential as a mechanism for the evaluation of different types of abnormalities in medical images.
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.
High-Performance Neural Networks for Visual Object Classification
Cireşan, Dan C; Masci, Jonathan; Gambardella, Luca M; Schmidhuber, Jürgen
2011-01-01
We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in a supervised way. Our deep hierarchical architectures achieve the best published results on benchmarks for object classification (NORB, CIFAR10) and handwritten digit recognition (MNIST), with error rates of 2.53%, 19.51%, 0.35%, respectively. Deep nets trained by simple back-propagation perform better than more shallow ones. Learning is surprisingly rapid. NORB is completely trained within five epochs. Test error rates on MNIST drop to 2.42%, 0.97% and 0.48% after 1, 3 and 17 epochs, respectively.
Identification of Jiangxi wines by three-dimensional fluorescence fingerprints
Wan, Yiqun; Pan, Fengqin; Shen, Mingyue
2012-10-01
A new assay of identifying wines was developed based on fingerprints of three-dimensional fluorescence spectra, and 30 samples from different manufacturers were analyzed. The techniques of principal component analysis (PCA) and hierarchical cluster analysis (HCA) were used to differentiate and evaluate the character parameters of wines' three-dimensional fluorescence spectra. At the same time, the back-propagation network (BPN) was applied to predict the attribution of unknown samples. The results of PCA and HCA showed that there was definite different information among the wine samples from different manufacturers. It was promising that the method could be applied to distinguish wine samples produced by different manufacturers. The proposed method could provide the criterion for the quality control of wines.
Virtual biopsy of rat tympanic membrane using higher harmonic generation microscopy
Lee, Wen-Jeng; Lee, Chia-Fone; Chen, Szu-Yu; Chen, Yuh-Shyang; Sun, Chi-Kuang
2010-07-01
Multiharmonic optical microscopy has been widely applied in biomedical research due to its unique capability to perform noninvasive studies of biomaterials. In this study, virtual biopsy based on back-propagating multiple optical harmonics, combining second and third harmonics, is applied in unfixed rat tympanic membrane. We show that third harmonic generation can provide morphologic information on the epithelial layers of rat tympanic membrane as well as radial collagen fibers in middle fibrous layers, and that second harmonic generation can provide information on both radial and circular collagen fibers in middle fibrous layers. Through third harmonic generation, the capillary and red blood cells in the middle fibrous layer are also noted. Additionally, the 3-D relationship to adjacent bony structures and spatial variations in thickness and curvature are obtained. Our study demonstrates the feasibility of using a noninvasive optical imaging system for comprehensive evaluation of the tympanic membrane.
Implementation of a Vision System for a Landmine Detecting Robot Using Artificial Neural Network
Directory of Open Access Journals (Sweden)
Roger Achkar
2012-09-01
Full Text Available Landmines, specifically anti-tank mines, cluster bombs, and unexploded ordnance form a serious problem in many countries. Several landmine sweeping techniques are used for minesweeping. This paper presents the design and the implementation of the vision system of an autonomous robot for landmines localization. The proposed work develops state-of-the-art techniques in digital image processing for pre-processing captured images of the contaminated area. After enhancement, Artificial Neural Network (ANN is used in order to identify, recognize and classify the landmines’ make and model. The Back-Propagation algorithm is used for training the network. The proposed work proved to be able to identify and classify different types of landmines under various conditions (rotated landmine, partially covered landmine with a success rate of up to 90%.
Implementation of a Vision System for a Landmine Detecting Robot Using Artificial Neural Network
Directory of Open Access Journals (Sweden)
Roger Achkar
2012-10-01
Full Text Available Landmines, specifically anti-tank mines, cluster bombs, and unexploded ordnance form a serious problemin many countries. Several landmine sweeping techniques are used for minesweeping. This paper presentsthe design and the implementation of the vision system of an autonomous robot for landmines localization.The proposed work develops state-of-the-art techniques in digital image processing for pre-processingcaptured images of the contaminated area. After enhancement, Artificial Neural Network (ANN is used inorder to identify, recognize and classify the landmines’ make and model. The Back-Propagation algorithmis used for training the network. The proposed work proved to be able to identify and classify different typesof landmines under various conditions (rotated landmine, partially covered landmine with a success rateof up to 90%.
Directory of Open Access Journals (Sweden)
Héliton Pandorfi
2016-06-01
Full Text Available ABSTRACT This study aimed to investigate the applicability of artificial neural networks (ANNs in the prediction of evapotranspiration of sweet pepper cultivated in a greenhouse. The used data encompass the second crop cycle, from September 2013 to February 2014, constituting 135 days of daily meteorological data, referring to the following variables: temperature and relative air humidity, wind speed and solar radiation (input variables, as well as evapotranspiration (output variable, determined using data obtained by load-cell weighing lysimeter. The recorded data were divided into three sets for training, testing and validation. The ANN learning model recognized the evapotranspiration patterns with acceptable accuracy, with mean square error of 0.005, in comparison to the data recorded in the lysimeter, with coefficient of determination of 0.87, demonstrating the best approximation for the 4-21-1 network architecture, with multilayers, error back-propagation learning algorithm and learning rate of 0.01.
Video Traffic Prediction Using Neural Networks
Directory of Open Access Journals (Sweden)
Miloš Oravec
2008-10-01
Full Text Available In this paper, we consider video stream prediction for application in services likevideo-on-demand, videoconferencing, video broadcasting, etc. The aim is to predict thevideo stream for an efficient bandwidth allocation of the video signal. Efficient predictionof traffic generated by multimedia sources is an important part of traffic and congestioncontrol procedures at the network edges. As a tool for the prediction, we use neuralnetworks – multilayer perceptron (MLP, radial basis function networks (RBF networksand backpropagation through time (BPTT neural networks. At first, we briefly introducetheoretical background of neural networks, the prediction methods and the differencebetween them. We propose also video time-series processing using moving averages.Simulation results for each type of neural network together with final comparisons arepresented. For comparison purposes, also conventional (non-neural prediction isincluded. The purpose of our work is to construct suitable neural networks for variable bitrate video prediction and evaluate them. We use video traces from [1].
Learning without local minima in radial basis function networks.
Bianchini, M; Frasconi, P; Gori, M
1995-01-01
Learning from examples plays a central role in artificial neural networks. The success of many learning schemes is not guaranteed, however, since algorithms like backpropagation may get stuck in local minima, thus providing suboptimal solutions. For feedforward networks, optimal learning can be achieved provided that certain conditions on the network and the learning environment are met. This principle is investigated for the case of networks using radial basis functions (RBF). It is assumed that the patterns of the learning environment are separable by hyperspheres. In that case, we prove that the attached cost function is local minima free with respect to all the weights. This provides us with some theoretical foundations for a massive application of RBF in pattern recognition.
Energy Technology Data Exchange (ETDEWEB)
Guia, Jose G.C. da; Araujo, Adevid L. de [Universidade Federal de Campina Grande, PB (Brazil). Dept. de Engenharia Mecanica; Irmao, Marcos A. da Silva [Universidade Federal de Campina Grande, PB (Brazil). Dept. de Engenharia de Processos; Silva, Antonio A. [Universidade Federal de Campina Grande, PB (Brazil). Dept. de Engenharia Mecanica
2003-07-01
The condition monitoring and diagnostic of structural faults in pipelines are an important problem for the petroleum's industry, being necessary to develop supervisory systems for detection, prediction and evaluation of a fault in the pipelines to avoid environmental and financial damages. In this work, three types of Artificial Neural Networks (ANNs) are reviewed and used to detect and locate a fault in a simulated pipe. The simulated pipe was modeled through the Finite Elements Method. In Neural Networks' analysis, the first six natural frequencies of the pipe are used as networks' inputs. The used ANNs were the Multi-Layer Perceptron Network with backpropagation, the Probabilistic Neural Network and the Generalized Regression Neural Network. After the analysis, it was concluded that the ANN are a good computational tool in problems of faults detection on pipelines with a great precision. In the localization of the faults were obtained errors smaller than 5%. (author)
Institute of Scientific and Technical Information of China (English)
JIN Zhe; SONG Zhi-huan; HE Jia-ming
2007-01-01
RF power amplifiers (PAs) are usually considered as memoryless devices in most existing predistortion techniques.Nevertheless, in wideband communication systems, PA memory effects can no longer be ignored and memoryless predistortion cannot linearize PAs effectively. After analyzing PA memory effects, a novel predistortion method based on wavelet networks (WNs) is proposed to linearize wideband RF power amplifiers. A complex wavelet network with tapped delay lines is applied to construct the predistorter and then a complex backpropagation algorithm is developed to train the predistorter parameters. The simulation results show that compared with the previously published feed-forward neural network predistortion method, the proposed method provides faster convergence rate and better performance in reducing out-of-band spectral regrowth.
Chen, Limin; Liang, Yin; Wan, Guojin
2012-04-01
An regularization approach is introduced into the online identification of inverse model for predistortion. It is based on a modified backpropagation Levenberg-Marquardt algorithm with sliding window. Adaptive predistorter with feedback was identified respectively based on direct learning and indirect learning architectures. Length of the sliding window was discussed. Compared with the Recursive Prediction Error Method (RPEM) algorithm and Nonlinear Filtered Least-Mean-Square (NFxLMS) algorithm, the algorithm is tested by identification of infinite impulse response Wiener predistorter. It is found that the proposed algorithm is much more efficient than either of the other techniques. The values of the parameters are also smaller than those extracted by the ordinary least-squares algorithm since the proposed algorithm constrains the L2-norm of the parameters.
A Tumor Growth Model with Unmolded Dynamics Based on an Online Feedback Neural Network Model
Directory of Open Access Journals (Sweden)
ArashPourhashemi
2014-01-01
Full Text Available In this study, we identify tumor growth system by an online feedback neural network model based on back-propagation method. The modeling and identification of nonlinear dynamic systems is the process of developing and improving a mathematical representation of a system using experimental data. So, it is a problem of considerable importance through the use of measured experimental data in biomedical modeling. As is obvious, in biomedical researches it is really difficult and in some cases impossible to implement research on real patient or such a system which is not possible to empirical tests. To deal with, we need sometime a model close to real system in order to forecast dynamic systems so as to perform researches on models and design controller for control of system.