1

Prediction of Parametric Roll Resonance by Multilayer Perceptron Neural Network

DEFF Research Database (Denmark)

Parametric roll resonance is a ship stability related phenomenon that generates sudden large amplitude oscillations up to 30-40 degrees of roll. This can cause severe damage, and it can put the crew in serious danger. The need for a parametric rolling real time prediction system has been acknowledged in the last few years. This work proposes a prediction system based on a multilayer perceptron (MP) neural network. The training and testing of the MP network is accomplished by feeding it with simulated data of a three degrees-of-freedom nonlinear model of a fishing vessel. The neural network is shown to be capable of forecasting the ship’s roll motion in realistic scenarios.

Míguez González, M; López Peña, F.

2011-01-01

2

Classification of fused face images using multilayer perceptron neural network

This paper presents a concept of image pixel fusion of visual and thermal faces, which can significantly improve the overall performance of a face recognition system. Several factors affect face recognition performance including pose variations, facial expression changes, occlusions, and most importantly illumination changes. So, image pixel fusion of thermal and visual images is a solution to overcome the drawbacks present in the individual thermal and visual face images. Fused images are projected into eigenspace and finally classified using a multi-layer perceptron. In the experiments we have used Object Tracking and Classification Beyond Visible Spectrum (OTCBVS) database benchmark thermal and visual face images. Experimental results show that the proposed approach significantly improves the verification and identification performance and the success rate is 95.07%. The main objective of employing fusion is to produce a fused image that provides the most detailed and reliable information. Fusion of multip...

Bhattacharjee, Debotosh; Nasipuri, Mita; Basu, Dipak Kumar; Kundu, Mahantapas

2010-01-01

3

An Analog Multilayer Perceptron Neural Network for a Portable Electronic Nose

Digital Repository Infrastructure Vision for European Research (DRIVER)

This study examines an analog circuit comprising a multilayer perceptron neural network (MLPNN). This study proposes a low-power and small-area analog MLP circuit to implement in an E-nose as a classifier, such that the E-nose would be relatively small, power-efficient, and portable. The analog MLP ...

Pan, Chih-Heng; Hsieh, Hung-Yi; Tang, Kea-Tiong

4

International Nuclear Information System (INIS)

[en] This paper deals with the controversial topic of the selection of the parameters of a genetic algorithm, in this case hierarchical, used for training of multilayer perceptron neural networks for the binary classification. The parameters to select are the crossover and mutation probabilities of the control and parametric genes and the permanency percent. The results can be considered as a guide for using this kind of algorithm.

2008-11-06

5

UK PubMed Central (United Kingdom)

Differentiation of silver, gold, aged and extra-aged tequila using 1-propanol, ethyl acetate, 2-methyl-1-propanol, 3-methyl-1-butanol and 2-methyl-1-butanol and furan derivatives like 5-(hydroxymethyl)-2-furaldehyde and 2-furaldehyde has been carried out. The content of 1-propanol, ethyl acetate, 2-methyl-1-propanol, 3-methyl-1-butanol and 2-methyl-1-butanol was determined by means of head space solid phase microextraction gas chromatography mass-spectrometry. 5-(Hydroxymethyl)-2-furaldehyde and 2-furaldehyde were determined by high performance liquid chromatography with diode array detection. Kruskal-Wallis test was used to highlight significant differences between types of tequila. Principal component analysis was applied as visualisation technique. Linear discriminant analysis and multilayer perceptron artificial neural networks were used to construct classification models. The best classification performance was obtained when multilayer perceptron model was applied.

Ceballos-Magaña SG; de Pablos F; Jurado JM; Martín MJ; Alcázar Á; Muñiz-Valencia R; Gonzalo-Lumbreras R; Izquierdo-Hornillos R

2013-02-01

6

ECG biometric using multilayer perceptron and radial basis function neural networks.

UK PubMed Central (United Kingdom)

This paper proposes a new method to identify people using Electrocardiogram (ECG), particularly the QRS complex which has been proven to be stable against heart rate variability and convenient to be used alone as a biometric feature. 324 QRS complexes are extracted from ECGs of 18 subjects in Physionet's MIT-BIH Normal Sinus Rhythm Database (NSRDB). Multilayer Perceptron (MLP) and Radial Basis Function (RBF) neural networks are used to classify those QRS complexes. If the training data are chosen carefully to cover a wide range of input values (i.e. QRS complexes), then the classification accuracy rates can reach above 98% using MLP and 97% using RBF.

Mai V; Khalil I; Meli C

2011-01-01

7

Learning multilayer perceptrons efficiently

A learning algorithm for multilayer perceptrons is presented which is based on finding the principal components of a correlation matrix computed from the example inputs and their target outputs. For large networks our procedure needs far fewer examples to achieve good generalization than traditional on-line algorithms.

Bunzmann, C; Urbanczik, R

2001-01-01

8

Directory of Open Access Journals (Sweden)

Full Text Available In this paper, the problem of predicting the exchange rate time series in the foreign exchange rate market is going to be solved using a time-delayed multilayer perceptron neural network with gold price as external factor. The input for the learning phase of the artificial neural network are the exchange rate data of the last five days plus the gold price in two different currencies of the exchange rate as the external factor for helping the artificial neural network improving its forecast accuracy. The five-day delay has been chosen because of the weekly cyclic behavior of the exchange rate time series with the consideration of two holidays in a week. The result of forecasts are then compared with using the multilayer peceptron neural network without gold price external factor by two most important evaluation techniques in the literature of exchange rate prediction. For the experimental analysis phase, the data of three important exchange rates of EUR/USD, GBP/USD, and USD/JPY are used.

Mohammad Fathian; Arash N.Kia

2012-01-01

9

Directory of Open Access Journals (Sweden)

Full Text Available This paper focuses on the segmentation of printed Bangla characters for efficient recognition of the characters. The segmentation of characters is an important step in the process of character recognitions because it allows the system to classify the characters more accurately and quickly. The system takes the scanned image file of the printed document as its input. A structural feature extraction method is used to extract the feature. In this case, each individual Bangla character is converted to a M × N feature matrix. A Multi-Layer Perceptron (MLP) neural network with back propagation algorithm is chosen to feed the feature matrix to train with the set of input patterns and to develop knowledge to classify the character. The effectiveness of the system has been tested with several printed documents and the success rates in all cases are over 90%.

Md. Musfique Anwar; Nasrin Sultana Shume; P. K. M. Moniruzzaman; Md. Al-Amin Bhuiyan

2010-01-01

10

An Analog Multilayer Perceptron Neural Network for a Portable Electronic Nose

This study examines an analog circuit comprising a multilayer perceptron neural network (MLPNN). This study proposes a low-power and small-area analog MLP circuit to implement in an E-nose as a classifier, such that the E-nose would be relatively small, power-efficient, and portable. The analog MLP circuit had only four input neurons, four hidden neurons, and one output neuron. The circuit was designed and fabricated using a 0.18 ?m standard CMOS process with a 1.8 V supply. The power consumption was 0.553 mW, and the area was approximately 1.36 × 1.36 mm2. The chip measurements showed that this MLPNN successfully identified the fruit odors of bananas, lemons, and lychees with 91.7% accuracy.

Pan, Chih-Heng; Hsieh, Hung-Yi; Tang, Kea-Tiong

2013-01-01

11

An Analog Multilayer Perceptron Neural Network for a Portable Electronic Nose

Directory of Open Access Journals (Sweden)

Full Text Available This study examines an analog circuit comprising a multilayer perceptron neural network (MLPNN). This study proposes a low-power and small-area analog MLP circuit to implement in an E-nose as a classifier, such that the E-nose would be relatively small, power-efficient, and portable. The analog MLP circuit had only four input neurons, four hidden neurons, and one output neuron. The circuit was designed and fabricated using a 0.18 ?m standard CMOS process with a 1.8 V supply. The power consumption was 0.553 mW, and the area was approximately 1.36 × 1.36 mm2. The chip measurements showed that this MLPNN successfully identified the fruit odors of bananas, lemons, and lychees with 91.7% accuracy.

Chih-Heng Pan; Hung-Yi Hsieh; Kea-Tiong Tang

2012-01-01

12

An analog multilayer perceptron neural network for a portable electronic nose.

UK PubMed Central (United Kingdom)

This study examines an analog circuit comprising a multilayer perceptron neural network (MLPNN). This study proposes a low-power and small-area analog MLP circuit to implement in an E-nose as a classifier, such that the E-nose would be relatively small, power-efficient, and portable. The analog MLP circuit had only four input neurons, four hidden neurons, and one output neuron. The circuit was designed and fabricated using a 0.18 ?m standard CMOS process with a 1.8 V supply. The power consumption was 0.553 mW, and the area was approximately 1.36 × 1.36 mm2. The chip measurements showed that this MLPNN successfully identified the fruit odors of bananas, lemons, and lychees with 91.7% accuracy.

Pan CH; Hsieh HY; Tang KT

2013-01-01

13

Geomagnetic Dst index forecast using a multilayer perceptrons artificial neural network

International Nuclear Information System (INIS)

[en] Complete text of publication follows. The best known manifestations of the impact of solar wind on the magnetosphere are the geomagnetic storms. The prediction of geomagnetic field behavior allows the alert of geomagnetic storms occurrence, as those phenomena can cause many damages in the planet. The Artificial Intelligence tools have been applied in many multidisciplinary studies, covering several areas of knowledge, as a choice of approach to the solution of problems with characteristics like non-linearity, imprecision, and other features that can not be easily solved with conventional computational models. Techniques such as Artificial Neural Networks, Expert Systems and Decision Trees have been used in the Space Weather studies to perform tasks such as forecasting geomagnetic storms and the investigation of rules and parameters related on its occurrence. The main focus of this work is on forecasting the geomagnetic field behavior, represented this time by the Dst index, using for that task, mainly, the interplanetary magnetic field components and solar wind data. The tool chosen here to solve the non-linear problem was a Multi-layer Perceptrons Artificial Neural Network, trained with the backpropagation algorithm. Unlike what was done in other studies, we chose to predict calm and disturbed periods like, for example, a full month of data, for application in a real time forecasting system. It was possible to predict the geomagnetic Dst index one or two hours before with great percentage efficiency.

2009-01-01

14

UK PubMed Central (United Kingdom)

Anaerobic treatability of synthetic sago wastewater was investigated in a laboratory anaerobic tapered fluidized bed reactor (ATFBR) with a mesoporous granular activated carbon (GAC) as a support material. The experimental protocol was defined to examine the effect of the maximum organic loading rate (OLR), hydraulic retention time (HRT), the efficiency of the reactor and to report on its steady-state performance. The reactor was subjected to a steady-state operation over a range of OLR up to 85.44 kg COD/(m3 x d). The COD removal efficiency was found to be 92% in the reactor while the biogas produced in the digester reached 25.38 m3/(m3 x d) of the reactor. With the increase of OLR from 83.7 kg COD/(m3 x d), the COD removal efficiency decreased. Also an artificial neural network (ANN) model using multilayer perceptron (MLP) has been developed for a system of two input variable and five output dependent variables. For the training of the input-output data, the experimental values obtained have been used. The output parameters predicted have been found to be much closer to the corresponding experimental ones and the model was validated for 30% of the untrained data. The mean square error (MSE) was found to be only 0.0146.

Parthiban R; Iyer PV; Sekaran G

2007-01-01

15

Cross Validation Evaluation for Breast Cancer Prediction Using Multilayer Perceptron Neural Networks

Directory of Open Access Journals (Sweden)

Full Text Available Problem statement: The presence of metastasis in the regional lymph nodes is the most important factor in predicting prognosis in breast cancer. Many biomarkers have been identified that appear to relate to the aggressive behaviour of cancer. However, the nonlinear relation of these markers to nodal status and also the existence of complex interaction between markers have prohibited an accurate prognosis. Approach: The aim of this study is to investigate the effectiveness of a Multilayer Perceptron (MLP) for predicting breast cancer progression using a set of four biomarkers of breast tumors. The biomarkers include DNA ploidy, cell cycle distribution (G0G1/G2M), steroid receptors (ER/PR) and S-Phase Fraction (SPF). A further objective of the study is to explore the predictive potential of these markers in defining the state of nodal involvement in breast cancer. Two methods of outcome evaluation viz. stratified and simple k-fold Cross Validation (CV) are studied in order to assess their accuracy and reliability for neural network validation. Criteria such as output accuracy, sensitivity and specificity are used for selecting the best validation technique besides evaluating the network outcome for different combinations of markers. Results: The results show that stratified 2-fold CV is more accurate and reliable compared to simple k-fold CV as it obtains a higher accuracy and specificity and also provides a more stable network validation in terms of sensitivity. Best prediction results are obtained by using an individual marker-SPF which obtains an accuracy of 65%. Conclusion/Recommendations: Our findings suggest that MLP-based analysis provides an accurate and reliable platform for breast cancer prediction given that an appropriate design and validation method is employed.

Shirin A. Mojarad; Satnam S. Dlay; Wai L. Woo; Gajanan V. Sherbet

2011-01-01

16

Multilayered perceptron neural networks to compute energy losses in magnetic cores

International Nuclear Information System (INIS)

This paper presents a new approach based on multilayered perceptrons (MLPs) to compute the specific energy losses of toroidal wound cores built from 3% SiFe 0.27 mm thick M4, 0.1 and 0.08 mm thin gauge electrical steel strips. The MLP has been trained by a back-propagation and extended delta-bar-delta learning algorithm. The results obtained by using the MLP model were compared with a commonly used conventional method. The comparison has shown that the proposed model improved loss estimation with respect to the conventional method.

2006-01-01

17

Multilayered perceptron neural networks to compute energy losses in magnetic cores

Energy Technology Data Exchange (ETDEWEB)

This paper presents a new approach based on multilayered perceptrons (MLPs) to compute the specific energy losses of toroidal wound cores built from 3% SiFe 0.27 mm thick M4, 0.1 and 0.08 mm thin gauge electrical steel strips. The MLP has been trained by a back-propagation and extended delta-bar-delta learning algorithm. The results obtained by using the MLP model were compared with a commonly used conventional method. The comparison has shown that the proposed model improved loss estimation with respect to the conventional method.

Kucuk, Ilker [Physics Department, Faculty of Arts and Sciences, Uludag University, Gorukle Campus 16059, Bursa (Turkey)]. E-mail: ikucuk@uludag.edu.tr

2006-12-15

18

Quaternionic Multilayer Perceptron with Local Analyticity

Directory of Open Access Journals (Sweden)

Full Text Available A multi-layered perceptron type neural network is presented and analyzed in this paper. All neuronal parameters such as input, output, action potential and connection weight are encoded by quaternions, which are a class of hypercomplex number system. Local analytic condition is imposed on the activation function in updating neurons’ states in order to construct learning algorithm for this network. An error back-propagation algorithm is introduced for modifying the connection weights of the network.

Teijiro Isokawa; Haruhiko Nishimura; Nobuyuki Matsui

2012-01-01

19

Energy Technology Data Exchange (ETDEWEB)

Critical heat flux (CHF) is an important parameter for the design of nuclear reactors. Although many experimental and theoretical researches have been performed, there is not a single correlation to predict CHF because it is influenced by many parameters. These parameters are based on fixed inlet, local and fixed outlet conditions. Artificial neural networks (ANNs) have been applied to a wide variety of different areas such as prediction, approximation, modeling and classification. In this study, two types of neural networks, radial basis function (RBF) and multilayer perceptron (MLP), are trained with the experimental CHF data and their performances are compared. RBF predicts CHF with root mean square (RMS) errors of 0.24%, 7.9%, 0.16% and MLP predicts CHF with RMS errors of 1.29%, 8.31% and 2.71%, in fixed inlet conditions, local conditions and fixed outlet conditions, respectively. The results show that neural networks with RBF structure have superior performance in CHF data prediction over MLP neural networks. The parametric trends of CHF obtained by the trained ANNs are also evaluated and results reported.

Vaziri, Nima [Department of Physics, Islamic Azad University, Karaj Branch, Moazen Blvd., Rajaee shahr (Iran, Islamic Republic of)]. E-mail: n.vaziri@gmail.com; Hojabri, Alireza [Department of Physics, Islamic Azad University, Karaj Branch, Moazen Blvd., Rajaee shahr (Iran, Islamic Republic of); Erfani, Ali [Department of Physics, Islamic Azad University, Karaj Branch, Moazen Blvd., Rajaee shahr (Iran, Islamic Republic of); Monsefi, Mehrdad [Department of Physics, Islamic Azad University, Karaj Branch, Moazen Blvd., Rajaee shahr (Iran, Islamic Republic of); Nilforooshan, Behnam [Department of Physics, Islamic Azad University, Karaj Branch, Moazen Blvd., Rajaee shahr (Iran, Islamic Republic of)

2007-02-15

20

Directory of Open Access Journals (Sweden)

Full Text Available Problem statement: The aim of the present study is to exemplify the use of Artificial Neural Networks (ANN) for parameter prediction. Missing value or unreal approach to some questions in scale is a problem for unbiased findings. To learn a real pattern with ANN provides robust and unbiased parameter estimation. Approach: To this end, data was collected from 906 students using ?Scale of student views about the expected situations and the current expectations from their families during learning process? for the study entitled ?Student views about the expected situations and the current expectations from their families during learning process?. In the study, first the initial data set gathered using the measurement tool and the new data set produced by Multi-Layer Receptors algorithm, which was considered as the highest predictive level of ANN for the research were individually analyzed by Chaid analysis and the results of the two analyses were compared. Results: The findings showed that as a result of Chaid analysis with the initial data set the variable ?education level of mother? had a considerable effect on total score dependent variable, while ?education level of father? was the influential variable on the attitude level in the data set predicted by ANN, unlike the previous model. Conclusion/Recommendations: The findings of the research show Artificial Neural Networks could be used for parameter estimation in cause-effect based studies. It is also thought the research will contribute to extensive use of advanced statistical methods.

Murat Kayri; Omay Cokluk

2010-01-01

21

A novel characterization method using artificial neural networks is presented. This method allows one to determine the intrinsic permeability tensor of ferrite thin-films from S-parameters measurements. Neural networks, efficient to solve inverse problems, are used to compute the permeability tensor components ? and k. This optimization technique is used to find extremely complex functions between inputs and outputs and can be successfully applied on our magnetic thin-film characterization problem. Results of our networks are compared to a theoretical model. A great number of both simulated and measured tests have been performed on many magnetic thin-films. Neural network processing leads to a rapid and robust method for predicting the magnetic characterization of thin-films in microwave range.

Djerfaf, F.; Vincent, D.; Robert, S.; Merzouki, A.

2011-12-01

22

Directory of Open Access Journals (Sweden)

Full Text Available This paper presents a multi-layered perceptronneural network (MLPNN) method to solve the combinedeconomic and emission dispatch (CEED) problem. The harmfulecological effects caused by the emission of particulate andgaseous pollutants like sulfur dioxide (SO2) and oxides ofnitrogen ( NOx ) can be reduced by adequate distribution ofload between the plants of a power system. However, this leadsto a noticeable increase in the operating cost of the plants. Thispaper presents the (MLPNN) method applied for the successfuloperation of the power system subject to economical andenvironmental constraints. The proposed MLP NN method istested for a three plant thermal power system and the results arecompared with the solutions obtained from the classical lambdaiterative technique and simple genetic algorithm (SGA) refinedgenetic algorithm (RGA) method.

Sarakhs branch; Sarakhs, Iran.

2012-01-01

23

Fourier-Lapped Multilayer Perceptron Method for Speech Quality Assessment

Directory of Open Access Journals (Sweden)

Full Text Available The paper introduces a new objective method for speech quality assessment called Fourier-lapped multilayer perceptron (FLMLP). This method uses an overcomplete transform based on the discrete Fourier transform (DFT) and modulated lapped transform (MLT). This transform generates the DFT and the MLT speech spectral domains from which several relevant perceptual parameters are extracted. The proposed method also employs a multilayer perceptron neural network trained by a modified version of the scaled conjugated gradient method. This neural network maps the perceptual parameters into a subjective score. The numerical results show that FLMLP is an effective alternative to previous methods. As a result, it is worth stating that the techniques here described may be potentially useful to other researches facing the same kind of problem.

Ribeiro MoisésVidal; Barbedo Jayme Garcia Arnal; Romano JoãoMarcosTravassos; Lopes Amauri

2005-01-01

24

DEFF Research Database (Denmark)

In this work, multilayered perceptron neural networks (MLPNNs) were presented for the computation of the gamma-ray energy absorption buildup factors (BA) of seven thermoluminescent dosimetric (TLD) materials [LiF, BeO, Na2B4O7, CaSO4, Li2B4O7, KMgF3, Ca3(PO4)2] in the energy region 0.015–15MeV, and for penetration depths up to 10 mfp (mean-free-path). The MLPNNs have been trained by a Levenberg–Marquardt learning algorithm. The developed model is in 99% agreement with the ANSI/ANS-6.4.3 standard data set. Furthermore, the model is fast and does not require tremendous computational efforts. The estimated BA data for TLD materials have been given with penetration depth and incident photon energy as comparative to the results of the interpolation method using the Geometrical Progression (G-P) fitting formula.

Kucuk, Nil; Manohara, S.R.

2013-01-01

25

A Choice of Input Variables for a Multilayer Perceptron

International Nuclear Information System (INIS)

In the paper some aspects of multilayer perceptron (MLP) application to the problem of classifying the events presented by empirical samples of a finite volume are considered. The results of the MLP learning for various forms of the input data are analyzed and the reasons leading to the effect of an instantaneous learning of the MLP and rise of the neural network are investigated for the case when the input data are presented in a form of variational series. The problem of hidden layer neuron reduction without raising the recognition error is discussed. (author). 13 refs., 6 figs., 1 tab.

1994-01-01

26

UK PubMed Central (United Kingdom)

The aim of the present study was to apply the simultaneous optimization method incorporating Artificial Neural Network (ANN) using Multi-layer Perceptron (MLP) model to the development of a metformin HCl 500 mg sustained release matrix tablets with an optimized in vitro release profile. The amounts of HPMC K15M and PVP K30 at three levels (-1, 0, +1) for each were selected as casual factors. In vitro dissolution time profiles at four different sampling times (1 h, 2 h, 4 h and 8 h) were chosen as output variables. 13 kinds of metformin matrix tablets were prepared according to a 2(3) factorial design (central composite) with five extra center points, and their dissolution tests were performed. Commercially available STATISTICA Neural Network software (Stat Soft, Inc., Tulsa, OK, U.S.A.) was used throughout the study. The training process of MLP was completed until a satisfactory value of root square mean (RSM) for the test data was obtained using feed forward back propagation method. The root mean square value for the trained network was 0.000097, which indicated that the optimal MLP model was reached. The optimal tablet formulation based on some predetermined release criteria predicted by MLP was 336 mg of HPMC K15M and 130 mg of PVP K30. Calculated difference (f(1) 2.19) and similarity (f(2) 89.79) factors indicated that there was no difference between predicted and experimentally observed drug release profiles for the optimal formulation. This work illustrates the potential for an artificial neural network with MLP, to assist in development of sustained release dosage forms.

Mandal U; Gowda V; Ghosh A; Bose A; Bhaumik U; Chatterjee B; Pal TK

2008-02-01

27

The aim of the present study was to apply the simultaneous optimization method incorporating Artificial Neural Network (ANN) using Multi-layer Perceptron (MLP) model to the development of a metformin HCl 500 mg sustained release matrix tablets with an optimized in vitro release profile. The amounts of HPMC K15M and PVP K30 at three levels (-1, 0, +1) for each were selected as casual factors. In vitro dissolution time profiles at four different sampling times (1 h, 2 h, 4 h and 8 h) were chosen as output variables. 13 kinds of metformin matrix tablets were prepared according to a 2(3) factorial design (central composite) with five extra center points, and their dissolution tests were performed. Commercially available STATISTICA Neural Network software (Stat Soft, Inc., Tulsa, OK, U.S.A.) was used throughout the study. The training process of MLP was completed until a satisfactory value of root square mean (RSM) for the test data was obtained using feed forward back propagation method. The root mean square value for the trained network was 0.000097, which indicated that the optimal MLP model was reached. The optimal tablet formulation based on some predetermined release criteria predicted by MLP was 336 mg of HPMC K15M and 130 mg of PVP K30. Calculated difference (f(1) 2.19) and similarity (f(2) 89.79) factors indicated that there was no difference between predicted and experimentally observed drug release profiles for the optimal formulation. This work illustrates the potential for an artificial neural network with MLP, to assist in development of sustained release dosage forms. PMID:18239298

Mandal, Uttam; Gowda, Veeran; Ghosh, Animesh; Bose, Anirbandeep; Bhaumik, Uttam; Chatterjee, Bappaditya; Pal, Tapan Kumar

2008-02-01

28

Scientific Electronic Library Online (English)

Full Text Available Abstract in portuguese Em termos computacionais, uma rede neural artificial (RNA) pode ser implementada em software ou em hardware, ou ainda de maneira híbrida, combinando ambos os recursos. O presente trabalho propõe uma arquitetura de hardware para a computação de uma rede neural do tipo perceptron com múltiplas camadas (MLP). Soluções em hardware tendem a ser mais eficientes do que soluções em software. O projeto em questão, além de explorar fortemente o paralelismo das redes neur (more) ais, permite alterações do número de entradas, número de camadas e de neurônios por camada, de modo que diversas aplicações de RNAs possam ser executadas no hardware proposto. Visando a uma redução de tempo do processamento aritmético, um número real é aproximado por uma fração de inteiros. Dessa forma, as operações aritméticas limitam-se a operações inteiras, executadas por circuitos combinacionais. Uma simples máquina de estados é demandada para controlar somas e produtos de frações. A função de ativação usada neste projeto é a sigmóide. Essa função é aproximada mediante o uso de polinômios, cujas operações são regidas por somas e produtos. Um teorema é introduzido e provado, permitindo a fundamentação da estratégia de cálculo da função de ativação. Dessa forma, reaproveita-se o circuito aritmético da soma ponderada para também computar a sigmóide. Essa re-utilização dos recursos levou a uma redução drástica de área total de circuito. Após modelagem e simulação para validação do bom funcionamento, a arquitetura proposta foi sintetizada utilizando recursos reconfiguráveis, do tipo FPGA. Os resultados são promissores. Abstract in english There are several neural network implementations using either software, hardware-based or a hardware/software co-design. This work proposes a hardware architecture to implement an artificial neural network (ANN), whose topology is the multilayer perceptron (MLP). In this paper, we explore the parallelism of neural networks and allow on-thefly changes of the number of inputs, number of layers and number of neurons per layer of the net. This reconfigurability characteristic (more) permits that any application of ANNs may be implemented using the proposed hardware. In order to reduce the processing time that is spent in arithmetic computation, a real number is represented using a fraction of integers. In this way, the arithmetics is limited to integer operations, performed by fast combinational circuits. A simple state machine is required to control sums and products of fractions. Sigmoid is used as the activation function in the proposed implementation. It is approximated by polynomials, whose underlying computation requires only sums and products. A theorem is introduced and proven so as to cover the arithmetic strategy of the computation of the activation function. Thus, the arithmetic circuitry used to implement the neuron weighted sum is reused for computing the sigmoid. this resource sharing decreased drastically the total area of the system. After modeling and simulation for functionality validation, the proposed architecture synthesized using reconfigurable hardware. The results are promising.

Silva, Rodrigo Martins da; Mourelle, Luiza de Macedo; Nedjah, Nadia

2011-12-01

29

Online learning dynamics of multilayer perceptrons with unidentifiable parameters

International Nuclear Information System (INIS)

In the over-realizable learning scenario of multilayer perceptrons, in which the student network has a larger number of hidden units than the true or optimal network, some of the weight parameters are unidentifiable. In this case, the teacher network consists of a union of optimal subspaces included in the parameter space. The optimal subspaces, which lead to singularities, are known to affect the estimation performance of neural networks. Using statistical mechanics, we investigate the online learning dynamics of two-layer neural networks in the over-realizable scenario with unidentifiable parameters. We show that the convergence speed strongly depends on the initial parameter conditions. We also show that there is a quasi-plateau around the optimal subspace, which differs from the well-known plateaus caused by permutation symmetry. In addition, we discuss the property of the final learning state, relating this to the singular structures

2003-11-28

30

Prediction of zenith tropospheric delay by multi-layer perceptron

The aim of the present study was to use the artificial neural network approach and specifically the multi-layer perceptron algorithm in order to predict total zenith tropospheric delay (ZTD) for various time spans of 1, 3 and 6 hours. The test data was ZTD values derived from the analysis centers of the EUREF Permanent tracking Network. The prediction process was applied to six EUREF permanent GPS stations for using period data of 2006 and 2007. The results obtained show an agreement at the order of few centimetres (2-3 cm) with those derived from EPN. Comparisons were also made with ZTD values calculated by other methods like the radiosonde observations and Saastamoinen model using ground measurements in order to confirm the final results and the feasibility of the neural network methodology.

Katsougiannopoulos, S.; Pikridas, C.

2009-12-01

31

A Parallel Framework for Multilayer Perceptron for Human Face Recognition

Directory of Open Access Journals (Sweden)

Full Text Available Artificial neural networks have already shown their success in face recognition and similar complex pattern recognition tasks. However, a major disadvantage of the technique is that it is extremely slow during training for larger classes and hence not suitable for real-time complex problems such as pattern recognition. This is an attempt to develop a parallel framework for the training algorithm of a perceptron. In this paper, two general architectures for a Multilayer Perceptron (MLP) have been demonstrated. The first architecture is All-Class-in-One-Network (ACON) where all the classes are placed in a single network and the second one is One-Class-in-One-Network (OCON) where an individual single network is responsible for each and every class. Capabilities of these two architectures were compared and verified in solving human face recognition, which is a complex pattern recognition task where several factors affect the recognition performance like pose variations, facial expression changes, occlusions, and most importantly illumination changes. Experimental results show that the proposed OCON structure performs better than the conventional ACON in terms of network training convergence speed and which can be easily exercised in a parallel environment.

Debotosh Bhattacharjee; Dipak Kumar Basu; Mahantapas Kundu; Mita Nasipuri; Mrinal Kanti Bhowmik

2010-01-01

32

Fourier-Lapped Multilayer Perceptron Method for Speech Quality Assessment

Digital Repository Infrastructure Vision for European Research (DRIVER)

The paper introduces a new objective method for speech quality assessment called Fourier-lapped multilayer perceptron (FLMLP). This method uses an overcomplete transform based on the discrete Fourier transform (DFT) and modulated lapped transform (MLT). This transform generates the DFT and the MLT s...

Moisés Vidal Ribeiro; Jayme Garcia Arnal Barbedo; João Marcos Travassos Romano; Amauri Lopes

33

Classification of glottic insufficiency and tension asymmetry using a multilayer perceptron.

UK PubMed Central (United Kingdom)

OBJECTIVE: Laryngeal function can be evaluated from multiple perspectives, including aerodynamic input, acoustic output, and mucosal wave vibratory characteristics. To determine the classifying power of each of these, we used a multilayer perceptron artificial neural network (ANN) to classify data as normal, glottic insufficiency, or tension asymmetry. STUDY DESIGN: Case series analyzing data obtained from excised larynges simulating different conditions. METHODS: Aerodynamic, acoustic, and videokymographic data were collected from excised canine larynges simulating normal, glottic insufficiency, and tension asymmetry. Classification of samples was performed using a multilayer perceptron ANN. RESULTS: A classification accuracy of 84% was achieved when including all parameters. Classification accuracy dropped below 75% when using only aerodynamic or acoustic parameters and below 65% when using only videokymographic parameters. CONCLUSIONS: Samples were classified with the greatest accuracy when using a wide range of parameters. Decreased classification accuracies for individual groups of parameters demonstrate the importance of a comprehensive voice assessment when evaluating dysphonia.

Hoffman MR; Surender K; Devine EE; Jiang JJ

2012-12-01

34

Efficient training of multilayer perceptrons using principal component analysis

International Nuclear Information System (INIS)

A training algorithm for multilayer perceptrons is discussed and studied in detail, which relates to the technique of principal component analysis. The latter is performed with respect to a correlation matrix computed from the example inputs and their target outputs. Typical properties of the training procedure are investigated by means of a statistical physics analysis in models of learning regression and classification tasks. We demonstrate that the procedure requires by far fewer examples for good generalization than traditional online training. For networks with a large number of hidden units we derive the training prescription which achieves, within our model, the optimal generalization behavior

2005-01-01

35

Error correcting code using tree-like multilayer perceptron

An error correcting code using tree-like multilayer perceptron is proposed. An original message $\\mbi{s}^0$ is encoded into a codeword $\\mbi{y}_0$ using tree-like committee machine (committee tree) or tree-like parity machine (parity tree) whose transfer functions are non-monotonic. The codeword $\\mbi{y}_0$ is then transmitted via a Binary Asymmetric Channel (BAC) where it is corrupted by noise. The analytical performance of these schemes is investigated using the replica method of statistical mechanics. Under some specific conditions, all the schemes are shown to saturate the Shannon bound at the infinite codeword length limit.

Cousseau, Florent; Okada, Masato

2008-01-01

36

Combining Self Organizing Maps and Multilayer Perceptrons to Learn

UK PubMed Central (United Kingdom)

Traditionally, the programming of bot behaviors for commercialcomputer games applies rule-based approaches. Buteven complex or fuzzyfied automatons cannot really challengeexperienced players. This contribution examineswhether bot programming can be treated as a pattern recognitionproblem and whether behaviors can be learned fromrecorded games. First, we sketch a technical computing interfaceto a commercial game that allows rapid prototyping ofclassifiers for bot programming. Then we discuss the use ofself organizing maps to represent manifolds of high dimensionalgame data and how multilayer perceptrons can modellocal characteristics of such manifolds. Finally, some experimentsin elementary behavior learning are presented.

C. Thurau; C. Bauckhage; G. Sagerer

37

Theoretical Properties of Projection Based Multilayer Perceptrons with Functional Inputs

Many real world data are sampled functions. As shown by Functional Data Analysis (FDA) methods, spectra, time series, images, gesture recognition data, etc. can be processed more efficiently if their functional nature is taken into account during the data analysis process. This is done by extending standard data analysis methods so that they can apply to functional inputs. A general way to achieve this goal is to compute projections of the functional data onto a finite dimensional sub-space of the functional space. The coordinates of the data on a basis of this sub-space provide standard vector representations of the functions. The obtained vectors can be processed by any standard method. In our previous work, this general approach has been used to define projection based Multilayer Perceptrons (MLPs) with functional inputs. We study in this paper important theoretical properties of the proposed model. We show in particular that MLPs with functional inputs are universal approximators: they can approximate to ...

Rossi, F; Rossi, Fabrice; Conan-Guez, Brieuc

2006-01-01

38

Missing value imputation on missing completely at random data using multilayer perceptrons.

UK PubMed Central (United Kingdom)

Data mining is based on data files which usually contain errors in the form of missing values. This paper focuses on a methodological framework for the development of an automated data imputation model based on artificial neural networks. Fifteen real and simulated data sets are exposed to a perturbation experiment, based on the random generation of missing values. These data set sizes range from 47 to 1389 records. A perturbation experiment was performed for each data set where the probability of missing value was set to 0.05. Several architectures and learning algorithms for the multilayer perceptron are tested and compared with three classic imputation procedures: mean/mode imputation, regression and hot-deck. The obtained results, considering different performance measures, not only suggest this approach improves the quality of a database with missing values, but also the best results are clearly obtained using the Multilayer Perceptron model in data sets with categorical variables. Three learning rules (Levenberg-Marquardt, BFGS Quasi-Newton and Conjugate Gradient Fletcher-Reeves Update) and a small number of hidden nodes are recommended.

Silva-Ramírez EL; Pino-Mejías R; López-Coello M; Cubiles-de-la-Vega MD

2011-01-01

39

FORECASTING ON FOREX MARKET WITH RBF AND PERCEPTRON NEURAL NETWORKS

Directory of Open Access Journals (Sweden)

Full Text Available This work deals with an alternative approach in financial modelling -artificial neural networks approach. The aim of this paper is to show that this type oftime series modelling is an excellent alternative to classical econometric modelling. Atfirst, neural networks using methods of supervised machine learning are discussed.After explaining theoretical basis of ANN, these models are then applied to specificexchange rate (AUD/USD). Finally, the comparison between statistical models andRBF and perceptron neural networks is made to illustrate the sense of using ANNmodels

LUKÁŠ FALÁT; ALEXANDRA KOTTILOVÁ

2012-01-01

40

Recognition of Epileptiform Patterns in the Human Electroencephalogram Using Multi-Layer Perceptron

Directory of Open Access Journals (Sweden)

Full Text Available Automatic detection of epileptiform patterns is highly desirable during continuous monitoring of patients with epilepsy. This paper describes an unconvential system for automatic off-line recognition of epileptic sharp transients in the human electroencephalogram (EEG), based on a standard neural network architecture - multi-layer perceptron (MLP), and implemented on a Silicon Graphics Indigo workstation. The system makes comprehensive use of wide spatial contextual information available on 12 channels of EEG and takes advantage of discrete dyadic wavelet transform (DDWT) for efficient parameterisation of EEG data. The EEG database consists of 12 patients, 7 of which are used in the process of training of MLP. The resulting MLP is presented with the testing data set consisting of all data vectors from all 12 patients, and is shown to be capable to recognise a wide variety of epileptic signals.

J. Magdolen; F. Zidek; V. Mokran

1995-01-01

41

Face Recognition through Multilayer Perceptron (MLP) and Learning Vector Quantization (LVQ)

Directory of Open Access Journals (Sweden)

Full Text Available Face recognition is challenging problems and there is still a lot of work that needs to be done in this area. Over the past ten years, face recognition has received substantial attention from researchers in biometrics, pattern recognition, computer vision, and cognitive psychology communities. This common interest in facial recognition technology among researchers working in diverse fields is motivated both by the remarkable ability to recognize people and by the increased attention being devoted to security applications. Applications of face recognition can be found in security, tracking, multimedia, and entertainment domains.This paper presents a face recognition system using artificial neural network. Here, we have designed a neural network with some own set network parameters. The results presented here have been obtained using two basic methods: multilayer perceptron (MLP), and learning vector quantization (LVQ). In both cases, two kinds of data have been fed to the classifiers: reduced resolution images (gray level or segmented), and feature vectors. The experimental results also show that, for the approaches considered here, analyzing gray level images produced better results than analyzing geometrical features, either because of the errors introduced during their extraction or because the original images have a richer information content. Furthermore, training times were much shorter for LVQ than for MLP. On the other hand, MLP achieved lower error rates when dealing with geometrical features.

Dr. Ikvinderpal Singh

2012-01-01

42

UK PubMed Central (United Kingdom)

Chemical descriptors are a way to define information concerning the physical, chemical and biological properties of a chemical compound. Machine learning methods such as the Artificial Neural Network (ANN) can be used to learn and predict such compounds by training on the compounds chemical descriptors. The motivation of our work is to predict odorant molecules for the development of an artificial biosensor. In this work, we demonstrate using a set of 32 optimized odorant descriptors how an assembly of MultiLayer Perceptrons (MLPs) can be successfully trained to differentiate among eight different chemical classes of odorant. In this communication, we demonstrate how it is possible to predict all 15/15 vectors from an unseen validation set with a high average prediction accuracy of 88.5% for the validation vectors. Furthermore, an introduction of a 10% noise injection level to the training set, increased the learning rate significantly as well as improve the average prediction accuracy of the MLPs to 92% for the validating vectors. Thus, this work indicates the promise of using odorant descriptor values to accurately predict chemical class and so move us forward to the realisation of an artificial odorant biosensor.

Bachtiar LR; Unsworth CP; Newcomb RD; Crampin EJ

2011-01-01

43

Analog Multilayer Perceptron Circuit with On-chip Learning: Portable Electronic Nose

This article presents an analog multilayer perceptron (MLP) neural network circuit with on-chip back propagation learning. This low power and small area analog MLP circuit is proposed to implement as a classifier in an electronic nose (E-nose). Comparing with the E-nose using microprocessor or FPGA as a classifier, the E-nose applying analog circuit as a classifier can be faster and much smaller, demonstrate greater power efficiency and be capable of developing a portable E-nose [1]. The system contains four inputs, four hidden neurons, and only one output neuron; this simple structure allows the circuit to have a smaller area and less power consumption. The circuit is fabricated using TSMC 0.18 ?m 1P6M CMOS process with 1.8 V supply voltage. The area of this chip is 1.353×1.353 mm2 and the power consumption is 0.54 mW. Post-layout simulations show that the proposed analog MLP circuit can be successively trained to identify three kinds of fruit odors.

Pan, Chih-Heng; Tang, Kea-Tiong

2011-09-01

44

k-nearest neighbors directed noise injection in multilayer perceptron training.

UK PubMed Central (United Kingdom)

The relation between classifier complexity and learning set size is very important in discriminant analysis. One of the ways to overcome the complexity control problem is to add noise to the training objects, increasing in this way the size of the training set. Both the amount and the directions of noise injection are important factors which determine the effectiveness for classifier training. In this paper the effect is studied of the injection of Gaussian spherical noise and -nearest neighbors directed noise on the performance of multilayer perceptrons. As it is impossible to provide an analytical investigation for multilayer perceptrons, a theoretical analysis is made for statistical classifiers. The goal is to get a better understanding of the effect of noise injection on the accuracy of sample-based classifiers. By both empirical as well as theoretical studies, it is shown that the -nearest neighbors directed noise injection is preferable over the Gaussian spherical noise injection for data with low intrinsic dimensionality.

Skurichina M; Raudys S; Duin RW

2000-01-01

45

K-Nearest Neighbours Directed Noise Injection in Multilayer Perceptron Training

UK PubMed Central (United Kingdom)

The relation between classifier complexity and learning set size is very important in discriminant analysis. One of theways to overcome the complexity control problem is to add noise to the training objects, increasing in this way thesize of the training set. Both, the amount and the directions of noise injection are important factors which determinethe effectiveness for classifier training. In this paper the effect is studied of the injection of Gaussian spherical noiseand k-nearest neighbours directed noise on the performance of multilayer perceptrons. As it is impossible to providean analytical investigation for multilayer perceptrons, a theoretical analysis is made for statistical classifiers. The goalis to get a better understanding of the effect of noise injection on the accuracy of sample based classifiers. By both,empirical as well as theoretical studies, it is shown that the k-nearest neighbours directed noise injection is preferableover the Gaussian spherical noise injection for data with low intrinsic dimensionality.

M. Skurichina

46

Directory of Open Access Journals (Sweden)

Full Text Available Prediction of highly non-linear behavior of suspended sediment flow in rivers has prime importance in environmental studies and watershed management. In this study, the predictive performance of two Artificial Neural Networks (ANNs), namely Radial Basis Function (RBF) and Multi-Layer Perceptron (MLP) were compared. Time series data of daily suspended sediment discharge and water discharge at the Langat River, Malaysia were used for training and testing the networks. Mean Square Error (MSE), Normalized Mean Square Error (NMSE) and correlation coefficient (r) were used for performance evaluation of the models. Using the testing data set, both models produced a similar level of robustness in sediment load simulation. The MLP network model showed a slightly better output than the RBF network model in predicting suspended sediment discharge, especially in the training process. However, both ANNs showed a weak robustness in estimating large magnitudes of sediment load.

Hadi Memarian; Siva Kumar Balasundram

2012-01-01

47

FPGA Implementation of Multilayer Perceptron for Modeling of Photovoltaic panel

International Nuclear Information System (INIS)

The Number of electronic applications using artificial neural network-based solutions has increased considerably in the last few years. However, their applications in photovoltaic systems are very limited. This paper introduces the preliminary result of the modeling and simulation of photovoltaic panel based on neural network and VHDL-language. In fact, an experimental database of meteorological data (irradiation, temperature) and output electrical generation signals of the PV-panel (current and voltage) has been used in this study. The inputs of the ANN-PV-panel are the daily total irradiation and mean average temperature while the outputs are the current and voltage generated from the panel. Firstly, a dataset of 4x364 have been used for training the network. Subsequently, the neural network (MLP) corresponding to PV-panel is simulated using VHDL language based on the saved weights and bias of the network. Simulation results of the trained MLP-PV panel based on Matlab and VHDL are presented. The proposed PV-panel model based ANN and VHDL permit to evaluate the performance PV-panel using only the environmental factors and involves less computational efforts, and it can be used for predicting the output electrical energy from the PV-panel.

2008-06-12

48

Experts Fusion and Multilayer Perceptron Based on Belief Learning for Sonar Image Classification

The sonar images provide a rapid view of the seabed in order to characterize it. However, in such as uncertain environment, real seabed is unknown and the only information we can obtain, is the interpretation of different human experts, sometimes in conflict. In this paper, we propose to manage this conflict in order to provide a robust reality for the learning step of classification algorithms. The classification is conducted by a multilayer perceptron, taking into account the uncertainty of the reality in the learning stage. The results of this seabed characterization are presented on real sonar images.

Martin, Arnaud

2008-01-01

49

Image Binarization Using Multi-Layer Perceptron: A Semi-Supervised Approach

Directory of Open Access Journals (Sweden)

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.

Amlan Raychaudhuri; Jayanta Dutta

2012-01-01

50

UK PubMed Central (United Kingdom)

An error correcting code using a treelike multilayer perceptron is proposed. An original message s0 is encoded into a codeword y0 using a treelike committee machine (committee tree) or a treelike parity machine (parity tree). Based on these architectures, several schemes featuring monotonic or nonmonotonic units are introduced. The codeword y0 is then transmitted via a binary asymmetric channel where it is corrupted by noise. The analytical performance of these schemes is investigated using the replica method of statistical mechanics. Under some specific conditions, some of the proposed schemes are shown to saturate the Shannon bound at the infinite codeword length limit. The influence of the monotonicity of the units on the performance is also discussed.

Cousseau F; Mimura K; Okada M

2010-02-01

51

A New Approach to Predicting Bankruptcy: Combining DEA and Multi-Layer Perceptron

Directory of Open Access Journals (Sweden)

Full Text Available The question of financial health and sustenance of a firm is so intriguing that it has spanned numerous studies. For investors,stakeholders and lenders, assessing the risk associated with an enterprise is vital. Several tools have been formulated to deal with predicting the solvency of a firm. This paper attempts to combine Data Envelopment Analysis and Multi-Layer Perceptron (MLP) to suggest a new method for prediction of bankruptcy that not only focusses on historical financial data of firms that filed for bankruptcy like other past studies but also takes into account the data of those firms that were likely to do so. This method thus identifies firms that have a high chance of facing bankruptcy along with those that have filed for bankruptcy. The performance of this procedure is compared with MLP. The suggested method outperforms MLP in prediction of bankruptcy.

Ayan Mukhopadhyay; Suman Tiwari; Ankit Narsaria; Bhaskar Roy Karmaker

2012-01-01

52

An error correcting code using a treelike multilayer perceptron is proposed. An original message s0 is encoded into a codeword y0 using a treelike committee machine (committee tree) or a treelike parity machine (parity tree). Based on these architectures, several schemes featuring monotonic or nonmonotonic units are introduced. The codeword y0 is then transmitted via a binary asymmetric channel where it is corrupted by noise. The analytical performance of these schemes is investigated using the replica method of statistical mechanics. Under some specific conditions, some of the proposed schemes are shown to saturate the Shannon bound at the infinite codeword length limit. The influence of the monotonicity of the units on the performance is also discussed. PMID:20365527

Cousseau, Florent; Mimura, Kazushi; Okada, Masato

2010-02-01

53

Learning times of neural networks: Exact solution for a perceptron algorithm

The performance of the optimal stability perceptron learning algorithm of Krauth and Mezard is studied for the learning of random unbiased patterns in neural networks. In the thermodynamic limit N, P-->?, ?=P/N finite, a replica approach is used to find the exact distribution for the number of time steps, which is required to stabilize a pattern. Remarkably for each neuron a finite fraction of the patterns do not contribute explicitly but are stabilized by other patterns.

Opper, M.

1988-10-01

54

Channel estimation for LTE Uplink system by Perceptron neural network

Directory of Open Access Journals (Sweden)

Full Text Available In this paper, a channel estimator using neural network is presented for Long Term Evolution (LTE)uplink. This paper considers multiuser SC-FDMA uplink transmissions with doubly selective channels.This channel estimation method uses knowledge of pilot channel properties to estimate the unknownchannel response at non-pilot sub-carriers. First, the neural network estimator learns to adapt to thechannel variations then it estimates the channel frequency response. Simulation results show that theproposed method has better performance, in terms of complexity and quality, compared to theconventional methods least square (LS), MMSE and decision feedback and it is more robust at high speedmobility.

A. Omri; R. Bouallegue; R. Hamila; M. Hasna

2010-01-01

55

UK PubMed Central (United Kingdom)

In this paper, we propose a wideband dynamic behavioral model for a bulk reflective semiconductor optical amplifier (RSOA) used as a modulator in colorless radio over fiber (RoF) systems using a tapped-delay multilayer perceptron (TDMLP). 64 quadrature amplitude modulation (QAM) signals with 20 Msymbol/s were used to train, validate and test the model. Nonlinear distortion and dynamic effects induced by the RSOA modulator are demonstrated. The parameters of the model such as the number of nodes in the hidden layer and memory depth were optimized to ensure the generality and accuracy. The normalized mean square error (NMSE) is used as a figure of merit. The NMSE was up to -44.33 dB when the number of nodes in the hidden layer and memory depth were set to 20 and 3, respectively. The TDMLP model can accurately approximate to the dynamic characteristics of the RSOA modulator. The dynamic AM-AM and dynamic AM-PM distortions of the RSOA modulator are drawn. The results show that the single hidden layer TDMLP can provide accurate approximation for behaviors of the RSOA modulator.

Liu Z; Violas MA; Carvalho NB

2013-02-01

56

In this paper, we propose a wideband dynamic behavioral model for a bulk reflective semiconductor optical amplifier (RSOA) used as a modulator in colorless radio over fiber (RoF) systems using a tapped-delay multilayer perceptron (TDMLP). 64 quadrature amplitude modulation (QAM) signals with 20 Msymbol/s were used to train, validate and test the model. Nonlinear distortion and dynamic effects induced by the RSOA modulator are demonstrated. The parameters of the model such as the number of nodes in the hidden layer and memory depth were optimized to ensure the generality and accuracy. The normalized mean square error (NMSE) is used as a figure of merit. The NMSE was up to -44.33 dB when the number of nodes in the hidden layer and memory depth were set to 20 and 3, respectively. The TDMLP model can accurately approximate to the dynamic characteristics of the RSOA modulator. The dynamic AM-AM and dynamic AM-PM distortions of the RSOA modulator are drawn. The results show that the single hidden layer TDMLP can provide accurate approximation for behaviors of the RSOA modulator. PMID:23481795

Liu, Zhansheng; Violas, Manuel Alberto; Carvalho, Nuno Borges

2013-02-11

57

Fast accurate MEG source localization using a multilayer perceptron trained with real brain noise

International Nuclear Information System (INIS)

Iterative gradient methods such as Levenberg-Marquardt (LM) are in widespread use for source localization from electroencephalographic (EEG) and magnetoencephalographic (MEG) signals. Unfortunately, LM depends sensitively on the initial guess, necessitating repeated runs. This, combined with LM's high per-step cost, makes its computational burden quite high. To reduce this burden, we trained a multilayer perceptron (MLP) as a real-time localizer. We used an analytical model of quasistatic electromagnetic propagation through a spherical head to map randomly chosen dipoles to sensor activities according to the sensor geometry of a 4D Neuroimaging Neuromag-122 MEG system, and trained a MLP to invert this mapping in the absence of noise or in the presence of various sorts of noise such as white Gaussian noise, correlated noise, or real brain noise. A MLP structure was chosen to trade off computation and accuracy. This MLP was trained four times, with each type of noise. We measured the effects of initial guesses on LM performance, which motivated a hybrid MLP-start-LM method, in which the trained MLP initializes LM. We also compared the localization performance of LM, MLPs, and hybrid MLP-start-LMs for realistic brain signals. Trained MLPs are much faster than other methods, while the hybrid MLP-start-LMs are faster and more accurate than fixed-4-start-LM. In particular, the hybrid MLP-start-LM initialized by a MLP trained with the real brain noise dataset is 60 times faster and is comparable in accuracy to random-20-start-LM, and this hybrid system (localization error: 0.28 cm, computation time: 36 ms) shows almost as good performance as optimal-1-start-LM (localization error: 0.23 cm, computation time: 22 ms), which initializes LM with the correct dipole location. MLPs trained with noise perform better than the MLP trained without noise, and the MLP trained with real brain noise is almost as good an initial guesser for LM as the correct dipole location. (author) )

2002-07-21

58

UK PubMed Central (United Kingdom)

BACKGROUND: Various methods can be applied to build predictive models for the clinical data with binary outcome variable. This research aims to explore the process of constructing common predictive models, Logistic regression (LR), decision tree (DT) and multilayer perceptron (MLP), as well as focus on specific details when applying the methods mentioned above: what preconditions should be satisfied, how to set parameters of the model, how to screen variables and build accuracy models quickly and efficiently, and how to assess the generalization ability (that is, prediction performance) reliably by Monte Carlo method in the case of small sample size. METHODS: All the 274 patients (include 137 type 2 diabetes mellitus with diabetic peripheral neuropathy and 137 type 2 diabetes mellitus without diabetic peripheral neuropathy) from the Metabolic Disease Hospital in Tianjin participated in the study. There were 30 variables such as sex, age, glycosylated hemoglobin, etc. On account of small sample size, the classification and regression tree (CART) with the chi-squared automatic interaction detector tree (CHAID) were combined by means of the 100 times 5-7 fold stratified cross-validation to build DT. The MLP was constructed by Schwarz Bayes Criterion to choose the number of hidden layers and hidden layer units, alone with levenberg-marquardt (L-M) optimization algorithm, weight decay and preliminary training method. Subsequently, LR was applied by the best subset method with the Akaike Information Criterion (AIC) to make the best used of information and avoid overfitting. Eventually, a 10 to 100 times 3-10 fold stratified cross-validation method was used to compare the generalization ability of DT, MLP and LR in view of the areas under the receiver operating characteristic (ROC) curves (AUC). RESULTS: The AUC of DT, MLP and LR were 0.8863, 0.8536 and 0.8802, respectively. As the larger the AUC of a specific prediction model is, the higher diagnostic ability presents, MLP performed optimally, and then followed by LR and DT in terms of 10-100 times 2-10 fold stratified cross-validation in our study. Neural network model is a preferred option for the data. However, the best subset of multiple LR would be a better choice in view of efficiency and accuracy. CONCLUSION: When dealing with data from small size sample, multiple independent variables and a dichotomous outcome variable, more strategies and statistical techniques (such as AIC criteria, L-M optimization algorithm, the best subset, etc.) should be considered to build a forecast model and some available methods (such as cross-validation, AUC, etc.) could be used for evaluation.

Li CP; Zhi XY; Ma J; Cui Z; Zhu ZL; Zhang C; Hu LP

2012-03-01

59

Directory of Open Access Journals (Sweden)

Full Text Available The algorithm of development of full set of tests for debugging of neural network expert systems based on threelayer perceptron is considered. The algo-rithm is based on rules extraction from neural network and using of the method of technical diagnostics PODEM. The use of algorithm for testing of expert sys-tem Glaukoma Complaint for prognosis of compliance of ophthalmologic patients is described.

Dolinina Olga Ni?kolaevna; Kuzmin Alexey Konstantinovich

2011-01-01

60

BaTiO3-based optical quadratic neural network implementing the perceptron algorithm

An optical quadratic neural network (OQNN) utilizing four-wave mixing in barium titanate (BaTiO3) has been developed. This network implements a feedback loop using a CCD camera, a microcomputer, two monochrome liquid crystal televisions (LCTVs), and various optical elements. For training, the network employs the supervised quadratic perceptron algorithm to associate binary-valued input vectors with specified training vectors. Using a spatial multiplexing scheme for two bipolar neurons, the quadratic network was able to associate an input vector with various target vectors. In addition, the network successfully associated two input vectors with two corresponding target vectors in the same training session. Both analytical and experimental results are presented.

Huynh, Alex V.; Walkup, John F.; Krile, Thomas F.

1992-05-01

61

The random initialization of weights of a multilayer perceptron makes it possible to model its training process as a Las Vegas algorithm, i.e. a randomized algorithm which stops when some required training error is obtained, and whose execution time is a random variable. This modelling is used to perform a case study on a well-known pattern recognition benchmark: the UCI Thyroid Disease Database. Empirical evidence is presented of the training time probability distribution exhibiting a heavy tail behavior, meaning a big probability mass of long executions. This fact is exploited to reduce the training time cost by applying two simple restart strategies. The first assumes full knowledge of the distribution yielding a 40% cut down in expected time with respect to the training without restarts. The second, assumes null knowledge, yielding a reduction ranging from 9% to 23%.

Cebrian, Manuel

2007-01-01

62

UK PubMed Central (United Kingdom)

A three-layer back-propagation network is used to implement a pattern association task in which four types of mapping are learned. These mappings, which are considered analogous to those which characterize the relationship between the stem and past tense forms of English verbs, include arbitrary mappings, identity mappings, vowel changes, and additions of a suffix. The degree of correspondence between parallel distributed processing (PDP) models which learn mappings of this sort (e.g., Rumelhart & McClelland, 1986, 1987) and children's acquisition of inflectional morphology has recently been at issue in discussions of the applicability of PDP models to the study of human cognition and language (Pinker & Mehler, 1989; Bever, in press). In this paper, we explore the capacity of a network to learn these types of mappings, focusing on three major issues. First, we compare the performance of a single-layered perceptron similar to the one used by Rumelhart and McClelland with a multi-layered perceptron. The results suggest that it is unlikely that a single-layered perceptron is capable of finding an adequate solution to the problem of mapping stems and past tense forms in input configurations that are sufficiently analogous to English. Second, we explore the input conditions which determine learning in these networks. Several factors that characterize linguistic input are investigated: (a) the nature of the mapping performed by the network (arbitrary, suffixation, identity, and vowel change); (b) the competition effects that arise when the task demands simultaneous learning of distinct mapping types; (c) the role of the type and token frequency of verb stems; and (d) the influence of phonological subregularities in the irregular verbs. Each of these factors is shown to have selective consequences on both successful and erroneous performance in the network. Third, we outline several types of systems which could result in U-shaped acquisition, and discuss the ways in which learning in multi-layered networks can be seen to capture several characteristics of U-shaped learning in children. In general, these models provide information about the role of input in determining the kinds of errors that a network will produce, including the conditions under which rule-like behavior and U-shaped learning will and will not emerge. The results from all simulations are discussed in light of behavioral data on children's acquisition of the past tense and the validity of drawing conclusions about the acquisition of language from models of this sort.

Plunkett K; Marchman V

1991-01-01

63

Noise robustness in multilayer neural network

Digital Repository Infrastructure Vision for European Research (DRIVER)

The training of multilayered neural networks in the presence of different types of noise is studied. We consider the learning of realizable rules in nonoverlapping architectures. Achieving optimal generalization depends on the knowledge of the noise level, however its misestimation may lead to parti...

Copelli, M.; Eichhorn, R.; Kinouchi, O.; Biehl, M.; Simonetti, R.; Riegler, P.; Caticha, N.

64

UK PubMed Central (United Kingdom)

In this letter, we use the firing rates from an array of olfactory sensory neurons (OSNs) of the fruit fly, Drosophila melanogaster, to train an artificial neural network (ANN) to distinguish different chemical classes of volatile odorants. Bootstrapping is implemented for the optimized networks, providing an accurate estimate of a network's predicted values. Initially a simple linear predictor was used to assess the complexity of the data and was found to provide low prediction performance. A nonlinear ANN in the form of a single multilayer perceptron (MLP) was also used, providing a significant increase in prediction performance. The effect of the number of hidden layers and hidden neurons of the MLP was investigated and found to be effective in enhancing network performance with both a single and a double hidden layer investigated separately. A hybrid array of MLPs was investigated and compared against the single MLP architecture. The hybrid MLPs were found to classify all vectors of the validation set, presenting the highest degree of prediction accuracy. Adjustment of the number of hidden neurons was investigated, providing further performance gain. In addition, noise injection was investigated, proving successful for certain network designs. It was found that the best-performing MLP was that of the double-hidden-layer hybrid MLP network without the use of noise injection. Furthermore, the level of performance was examined when different numbers of OSNs used were varied from the maximum of 24 to only 5 OSNs. Finally, the ideal OSNs were identified that optimized network performance. The results obtained from this study provide strong evidence of the usefulness of ANNs in the field of olfaction for the future realization of a signal processing back end for an artificial olfactory biosensor.

Bachtiar LR; Unsworth CP; Newcomb RD; Crampin EJ

2013-01-01

65

Speeding up a learning algorithm for multilayer perceptrons using the MAPS Environment

Digital Repository Infrastructure Vision for European Research (DRIVER)

Artificial neural networks, as non-linear adaptive elements, have been proposed for applications in adaptive control. Their ability to accurately approximate large classes of non-linear functions made them also a valuable tool for non-linear systems identification. However, in some cases, the parame...

Daniel, H.; Ruano, A. E.

66

This paper develops a primitive gas recognition system for discriminating between industrial gas species. The system under investigation consists of an array of eight micro-hotplate-based SnO2 thin film gas sensors with different selectivity patterns. The output signals are processed through a signal conditioning and analyzing system. These signals feed a decision-making classifier, which is obtained via a Field Programmable Gate Array (FPGA) with Very High-Speed Integrated Circuit Hardware Description Language. The classifier relies on a multilayer neural network based on a back propagation algorithm with one hidden layer of four neurons and eight neurons at the input and five neurons at the output. The neural network designed after implementation consists of twenty thousand gates. The achieved experimental results seem to show the effectiveness of the proposed classifier, which can discriminate between five industrial gases. PMID:23529119

Benrekia, Fayçal; Attari, Mokhtar; Bouhedda, Mounir

2013-03-01

67

UK PubMed Central (United Kingdom)

This paper develops a primitive gas recognition system for discriminating between industrial gas species. The system under investigation consists of an array of eight micro-hotplate-based SnO2 thin film gas sensors with different selectivity patterns. The output signals are processed through a signal conditioning and analyzing system. These signals feed a decision-making classifier, which is obtained via a Field Programmable Gate Array (FPGA) with Very High-Speed Integrated Circuit Hardware Description Language. The classifier relies on a multilayer neural network based on a back propagation algorithm with one hidden layer of four neurons and eight neurons at the input and five neurons at the output. The neural network designed after implementation consists of twenty thousand gates. The achieved experimental results seem to show the effectiveness of the proposed classifier, which can discriminate between five industrial gases.

Benrekia F; Attari M; Bouhedda M

2013-01-01

68

Directory of Open Access Journals (Sweden)

Full Text Available This paper develops a primitive gas recognition system for discriminating between industrial gas species. The system under investigation consists of an array of eight micro-hotplate-based SnO2 thin film gas sensors with different selectivity patterns. The output signals are processed through a signal conditioning and analyzing system. These signals feed a decision-making classifier, which is obtained via a Field Programmable Gate Array (FPGA) with Very High-Speed Integrated Circuit Hardware Description Language. The classifier relies on a multilayer neural network based on a back propagation algorithm with one hidden layer of four neurons and eight neurons at the input and five neurons at the output. The neural network designed after implementation consists of twenty thousand gates. The achieved experimental results seem to show the effectiveness of the proposed classifier, which can discriminate between five industrial gases.

Fayçal Benrekia; Mokhtar Attari; Mounir Bouhedda

2013-01-01

69

Supervised learning in multilayer spiking neural networks.

UK PubMed Central (United Kingdom)

We introduce a supervised learning algorithm for multilayer spiking neural networks. The algorithm overcomes a limitation of existing learning algorithms: it can be applied to neurons firing multiple spikes in artificial neural networks with hidden layers. It can also, in principle, be used with any linearizable neuron model and allows different coding schemes of spike train patterns. The algorithm is applied successfully to classic linearly nonseparable benchmarks such as the XOR problem and the Iris data set, as well as to more complex classification and mapping problems. The algorithm has been successfully tested in the presence of noise, requires smaller networks than reservoir computing, and results in faster convergence than existing algorithms for similar tasks such as SpikeProp.

Sporea I; Grüning A

2013-02-01

70

Directory of Open Access Journals (Sweden)

Full Text Available When investors decide to “adventure” through stock markets they search for a method to provide safety on making decision. In fact, there is no precise way to know which stocks will became a profitable investiment. Technical analysis is a discipline that support the investors on making decisions. Such a discipline uses a set of tools and statistical methods to forecast the market’s movement. Such a paper presents the develpment of a robotical Trade System, using a heuristic method. The system has a Neural Network multilayer perceptron, trained with an algorithm for back propagation error. Thus, approaching to the technical analysis without emotional aspects, using the Neural Network forecast on supporting the decisions of a investor on stock market. In analyzing the results of the neural network can be seen that the neural network got a result of 42.6% higher than the diagnostic of the technical analysis.Quando investidores decidem se “aventurar” pelo mercado de renda variável, como pelo mercado de ações, buscam um método de ter mais segurança na tomada de decisão. Na prática, não há como saber quais ativos tornar-se-ão um investimento lucrativo. No mercado acionário, a Análise Técnica procura auxiliar o investidor na tomada de decisão. Para isso, utiliza-se de ferramentas e de métodos estatísticos para tentar predizer os movimentos do mercado. Este artigo apresenta o desenvolvimento de um Trade System robótico, utilizando um método heurístico. O sistema conta com uma rede neural multilayer perceptron, treinada com o algoritmo de retro propagação de erro, aproximando-se da análise técnica sem o fator emoção. Ao avaliar os resultados da rede neural, pode ser visto que a mesma obteve um resultado de 42,6% maior do que o diagnóstico da análise técnica.

André Pacheco Miranda; Rodrigo Luiz Antoniazzi; Luis Felipe Dias Lopes; Marco Antonio Barbosa; Vânia Medianeira Flores Costa

2012-01-01

71

The design and analysis of effective and efficient neural networks and their applications

Energy Technology Data Exchange (ETDEWEB)

A complicated design issue of efficient Multilayer neural networks is addressed, and the perception and similar neural networks are examined. It shows that a three-layer perceptron neural network with specially designed learning algorithms provides an efficient framework to solve an exclusive OR problem using only n {minus} 1 processing elements in the second layer. Two efficient rapidly converging algorithms for any symmetric Boolean function were developed using only n {minus} 1 processing elements in the perceptron neural network and int(n/2) processing elements in the Adaline and perceptron neural network with the stepfunction transfer function. Similar results were obtained for the quasi-symmetric Boolean functions using a linear number of processing elements in perceptron neural networks, Adaline's, and perceptron neural networks with the stepfunction transfer functions. Generalized Boolean functions are discussed and two rapidly converging algorithms are shown for perceptron neural networks, Adaline's, and perceptron neural network with stepfunction transfer function. Many other interesting perceptron neural networks are discussed in the dissertation. Perceptron neural networks are applied to find the largest value of the n inputs. A new perceptron neural network is designed to find the largest value of the n inputs with the minimum number of inputs and the minimum number of layers. New perceptron neural networks are developed to sort n inputs. New, effective and efficient back-propagation Neural networks are designed to sort n inputs. The Sigmoid transfer function was discussed and a generalized Sigmoid function to improve Neural network performance was developed. A modified back-propagation learning algorithm was developed that builds any n input symmetric Boolean function using only int(n/2) processing elements in the second layer.

Makovoz, W.V.

1989-01-01

72

SOM-MLP Multi-Layered Neural Network with False-Alarming Nodes for Large Scale Pattern Recognition

Energy Technology Data Exchange (ETDEWEB)

In this paper, an SOM-MLP multi-layered neural network was studied for the large-scale pattern recognition problem such as the multilingual character recognition. The multi-layered neural network is made of the preclassification and the fine recognition modes. We constructed clusters for the preclassification mode using self-organizing map (SOM) learning and performed modifying steps for reducing the number of clusters. The clusters contain patterns that have the similar characteristics. We adopted the multi-layer perceptron(MLP) networks to the corresponding clusters for the fine recognition mode. And we proposed the use of false-alarming nodes in output layer of the MLP network, which could be constructed on error-prone negative examples quite similar to the patterns of the selected cluster but actually belonging to different nearby clusters through SOM`s topology-preserving mapping. The proposed system could be successfully adopted for recognizing the large number of printed Korean/Chinese characters database as well as IRIS database. (author). 14 refs., 13 figs., 2 tabs.

Kang, B.S.; Lim, K.T.; Chien, S.I. [Kyungpook National University, Taegu (Korea, Republic of)

1999-04-01

73

Entropic analysis and incremental synthesis of multilayered feedforward neural networks.

UK PubMed Central (United Kingdom)

Neural network architecture optimization is often a critical issue, particularly when VLSI implementation is considered. This paper proposes a new minimization method for multilayered feedforward ANNs and an original approach to their synthesis, both based on the analysis of the information quantity (entropy) flowing through the network. A layer is described as an information filter which selects the relevant characteristics until the complete classification is performed. The basic incremental synthesis method, including the supervised training procedure, is derived to design application-tailored neural paradigms with good generalization capability.

Pelagotti A; Piuri V

1997-10-01

74

Recognition of Tifinaghe Characters Using a Multilayer Neural Network

Directory of Open Access Journals (Sweden)

Full Text Available In this paper, we present an off line Tifinaghe characters recognition system. Texts are scannedusing a flatbed scanner. Digitized text are normalised, noise is reduced using a median filter,baseline skew is corrected by the use of the Hough transform, and text is segmented into line andlines into words. Features are extracted using the Walsh Transformation. Finally characters arerecognized by a multilayer neural network.

Rachid EL Ayachi; Mohamed Fakir; Belaid Bouikhalene

2011-01-01

75

Phase Transitions of Neural Networks

The cooperative behaviour of interacting neurons and synapses is studied using models and methods from statistical physics. The competition between training error and entropy may lead to discontinuous properties of the neural network. This is demonstrated for a few examples: Perceptron, associative memory, learning from examples, generalization, multilayer networks, structure recognition, Bayesian estimate, on-line training, noise estimation and time series generation.

Kinzel, W

1997-01-01

76

Bearing Fault Detection Using Artificial Neural Networks and Genetic Algorithm

Digital Repository Infrastructure Vision for European Research (DRIVER)

A study is presented to compare the performance of bearing fault detection using three types of artificial neural networks (ANNs), namely, multilayer perceptron (MLP), radial basis function (RBF) network, and probabilistic neural network (PNN). The time domain vibration signals of a rotating machine...

Saeed A. Al-Araimi; Khamis R. Al-Balushi; B. Samanta

77

Advances in Artificial Neural Networks – Methodological Development and Application

Digital Repository Infrastructure Vision for European Research (DRIVER)

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...

Yanbo Huang

78

A New Filter Design Method for Disturbed Multilayer Hopfield Neural Networks

Digital Repository Infrastructure Vision for European Research (DRIVER)

This paper investigates the passivity based filtering problem for multilayer Hopfield neural networks with external disturbance. A new passivity based filter design method for multilayer Hopfield neural networks is developed to ensure that the filtering error system is exponentially stable and pas...

AHN, C. K.

79

Dynamical optimization of the perceptron structure

International Nuclear Information System (INIS)

A complex method of the perceptron structure dynamic optimization is proposed. This method consists of two parts: the reduction of the input data dimension by means of a recirculative neural network and dynamic restructuring of the perceptron, as well as its structure optimization. The latter is realized by applying two dynamic procedures: adding new and removing faint neurons from network. This method was approved by applying it to a medical problem and demonstrated acceptable results. (author)

2002-01-01

80

Fast neural electron/pion discrimination with a fiber calorimeter

International Nuclear Information System (INIS)

A very fast neural electron/pion discriminator is introduced. It is based on a new training procedure that efficiently saturates each neuron output when applied on a multilayer network initially having hyperbolic tangent neurons. Thus, the network acts as a multilayer perceptron in the production phase. The neural discriminator can be implemented using fast comparators and resistor networks, which makes processing times of a few nanoseconds feasible. (author)

1996-01-01

81

Scientific Electronic Library Online (English)

Full Text Available Abstract in spanish En este trabajo se realizó un estudio estadístico de variables físico químicas asociadas al fenómeno de contaminación ambiental, en particular concentración media mensual de SO2 , medidas en la ciudad Salta Capital, Argentina, simultáneamente a concentraciones de NO2 y O3 . Las series bajo estudio presentaban comportamientos dinámicos no lineales, datos atípicos y cambios estructurales, lo que hizo imposible modelarlas con tipologías econométricas tradiciones (more) (AR, MA, ARMA, ARIMA, entre otras). Una solución eficiente que se encontró, hace uso de la teoría de los perceptrones multicapa. Mediante el modelo estructural de series de tiempo, esta solución se presenta como un proceso matemático iterativo que permite obtener un modelado final el cual tiene una muy alta confiabilidad (95%), para realizar pronoósticos a futuro sobre el comportamiento de la variable estudiada. Abstract in english In this paper a statistical study of phisical-chemistry variables connected with enviroment pollution, specifically SO2 monthly average concentration, measured in Salta Capital city, Argentina, together with NO2 and O3 concentrations, was made. Time series under study shown non linear dinamic behaviour, outliers and structural changes. Due to these it was impossible to use typical econometric typologies (AR, MA, ARMA, ARIMA, among others). An effective solution which uses (more) multistep perceptrons theory was found. By using structural time series modelling, this solution is presented by an iterative mathematical process that allows us to obtain a final model with a high confidence level (95%) in order to do the forecasting step on the studied variable.

Musso, Haydeé Elena; Ávila Blas, Orlando José

2013-01-01

82

Standard cell-based implementation of a digital optoelectronic neural-network hardware.

UK PubMed Central (United Kingdom)

A standard cell-based implementation of a digital optoelectronic neural-network architecture is presented. The overall structure of the multilayer perceptron network that was used, the optoelectronic interconnection system between the layers, and all components required in each layer are defined. The design process from VHDL-based modeling from synthesis and partly automatic placing and routing to the final editing of one layer of the circuit of the multilayer perceptrons are described. A suitable approach for the standard cell-based design of optoelectronic systems is presented, and shortcomings of the design tool that was used are pointed out. The layout for the microelectronic circuit of one layer in a multilayer perceptron neural network with a performance potential 1 magnitude higher than neural networks that are purely electronic based has been successfully designed.

Maier KD; Beckstein C; Blickhan R; Erhard W

2001-03-01

83

Function Approximation Performance of Fuzzy Neural Networks

Directory of Open Access Journals (Sweden)

Full Text Available In this paper we propose a Multilayer Perceptron Neural Network (MLP NN)consisting of fuzzy flip-flop neurons based on various fuzzy operations applied in order toapproximate a real-life application, two input trigonometric functions, and two and sixdimensional benchmark problems. The Bacterial Memetic Algorithm with ModifiedOperator Execution Order algorithm (BMAM) is proposed for Fuzzy Neural Networks(FNN) training. The simulation results showed that various FNN types delivered very goodfunction approximation results.

Rita Lovassy; László T. Kóczy; László Gál

2010-01-01

84

Optimization of High Order Perceptrons

UK PubMed Central (United Kingdom)

Neural networks are widely applied in research and industry. However, their broader applicationis hampered by various technical details. Among these details are several trainingparameters and the choice of the topology of the network. The subject of this dissertation istherefore the elimination and determination of usually user specified learning parameters.Furthermore, suitable application domains for neural networks are discussed.Among all training parameters, special attention is given to the learning rate, the gainof the sigmoidal function, and the initial weight range. A theorem is proven which permitsthe elimination of one of these parameters. Furthermore, it is shown that for high orderperceptrons, very small random initial weights are usually optimal in terms of training timeand generalization.Another important problem in the application of neural networks is to find a networktopology that suits a given data set. This favors high order perceptrons over several other...

Georg Thimm; Prof M. Kunt; Prof C. Pelligrini; Prof W. Gerstner; Prof L. C. Jain; E. Fiesler (ph. D

85

In this study, a hepatitis disease diagnosis study was realized using neural network structure. For this purpose, a multilayer neural network structure was used. Levenberg-Marquardt algorithm was used as training algorithm for the weights update of the neural network. The results of the study were compared with the results of the previous studies reported focusing on hepatitis disease diagnosis and using same UCI machine learning database. We obtained a classification accuracy of 91.87% via tenfold cross validation. PMID:20703548

Bascil, M Serdar; Temurtas, Feyzullah

2009-10-16

86

UK PubMed Central (United Kingdom)

In this study, a hepatitis disease diagnosis study was realized using neural network structure. For this purpose, a multilayer neural network structure was used. Levenberg-Marquardt algorithm was used as training algorithm for the weights update of the neural network. The results of the study were compared with the results of the previous studies reported focusing on hepatitis disease diagnosis and using same UCI machine learning database. We obtained a classification accuracy of 91.87% via tenfold cross validation.

Bascil MS; Temurtas F

2011-06-01

87

ESTIMATION OF INPUT IMPEDANCE OF MICROSTRIP PATCH ANTENNA USING FUZZY NEURAL NETWORK

Directory of Open Access Journals (Sweden)

Full Text Available The paper presents the use of fuzzy neural network (FNN) as a fast and better technique for the determination of input impedance of coaxial feed rectangular microstrip antenna. The fuzzy parameter ensures better performance as compared to three layer multilayered perceptron feed forward back propagation artificial neural network (MLPFFBP ANN) and radial basis function artificial neural network (RBF ANN) in the determination of input impedance of the coaxial feed microstrip antenna.

VANDANA VIKAS THAKARE; PRAMOD KUMAR SINGHAL

2010-01-01

88

Digital Repository Infrastructure Vision for European Research (DRIVER)

This paper presents the design of classifiers with neural network approach based on the method used Expectations Maximum (EM). The decision rule of Bayes classifier using the Minimum Error to the classification of a mixture of multitemporal imagery. In this particular, the multilayer perceptron neu...

Wawan Setiawan; Wiweka

89

A Hybrid Model based on Neural Network and Hybrid Genetic Algorithm for Automotive Price Forecasting

Digital Repository Infrastructure Vision for European Research (DRIVER)

In this paper, we introduce a new intelligent combination method based on Multilayer Perceptron Neural Network (MLP?NN) and Hybrid Genetic Algorithm (HGA) for automotive price forecasting. The combination of MLPNN and HGA lead us to accelerate convergence to the optimal weights and improve the forec...

M. Reza Peyghami; R. Khanduzi

90

Low latency and tight resources viseme recognition from speech using an artificial neural network

Digital Repository Infrastructure Vision for European Research (DRIVER)

We present a speech driven real-time viseme recognition system based on Artificial Neural Network (ANN). A Multi-Layer Perceptron (MLP) is used to provide a light and responsive framework, adapted to the final application (i.e., the animation of the lips of an avatar on multi-task platforms with emb...

Souviraà-Labastie, Nathan; Bimbot, Frédéric

91

Neural Network Revisited: Perception on Modified Poincare Map of Financial Time Series Data

Artificial Neural Network Model for prediction of time-series data is revisited on analysis of the Indonesian stock-exchange data. We introduce the use of Multi-Layer Perceptron to percept the modified Poincare-map of the given financial time-series data. The modified Poincare-map is believed to become the pattern of the data that transforms the data in time-t versus the data in time-t+1 graphically. We built the Multi-Layer Perceptron to percept and demonstrate predicting the data on specific stock-exchange in Indonesia.

Situngkir, H; Situngkir, Hokky; Surya, Yohanes

2004-01-01

92

A New Filter Design Method for Disturbed Multilayer Hopfield Neural Networks

Directory of Open Access Journals (Sweden)

Full Text Available This paper investigates the passivity based filtering problem for multilayer Hopfield neural networks with external disturbance. A new passivity based filter design method for multilayer Hopfield neural networks is developed to ensure that the filtering error system is exponentially stable and passive from the external disturbance vector to the output error vector. The unknown gain matrix is obtained by solving a linear matrix inequality (LMI), which can be easily facilitated by using some standard numerical packages. An illustrative example is given to demonstrate the effectiveness of the proposed filter.

AHN, C. K.

2011-01-01

93

Hybrid neural systems for pattern recognition in artificial noses.

UK PubMed Central (United Kingdom)

This work examines the use of Hybrid Intelligent Systems in the pattern recognition system of an artificial nose. The connectionist approaches Multi-Layer Perceptron and Time Delay Neural Networks, and the hybrid approaches Feature-Weighted Detector and Evolving Neural Fuzzy Networks were investigated. A Wavelet Filter is evaluated as a preprocessing method for odor signals. The signals generated by an artificial nose were composed by an array of conducting polymer sensors and exposed to two different odor databases.

Zanchettin C; Ludermir TB

2005-02-01

94

Digital Repository Infrastructure Vision for European Research (DRIVER)

In this study, the use of artificial neural network (ANN) based model, multi-layer perceptron (MLP) network, to compute the transfer capabilities in a multi-area power system was explored. The input for the ANN is load status and the outputs are the transfer capability among the system areas, volta...

Palukuru NAGENDRA; Sunita Halder NEE DEY; Tanaya DUTTA

95

Searching for risk factors using multilayer neural network as a classifier.

UK PubMed Central (United Kingdom)

A method to determine risk factors for particular outcomes using trained multilayer neural networks is proposed. The basic idea is to measure the partial differentials of the output with respect to input variables of the network. Differentiable activation functions and continuity of input variables is assumed.

Xue H; Tatsumi N; Park K; Shimizu M; Kyojima T; Sumiya Y; Kawabata S; Maeda N; Sakano D

1996-07-01

96

Applying Backpropagation Neural Networks to Bankruptcy Prediction

Directory of Open Access Journals (Sweden)

Full Text Available Bankruptcy prediction is an important classification problem for a business, and has become a major concern of managers. In this paper, two well-known backpropagation neural network models serving as data mining tools for classification problems are employed to perform bankruptcy forecasting: one is the backpropagation multi-layer perceptron, and the other is the radial basis function network. In particular, the radial basis function network can be treated as a fuzzy neural network. Through examining their classification generalization abilities, the empirical results from the data resources consisting of bankrupt and nonbankrupt firms in England, demonstrated that the radial basis function network outperforms the other classification methods, including the multi-layer perceptron, the multivariate discriminant analysis, and the probit method.

Yi-Chung Hu; Fang-Mei Tseng

2005-01-01

97

Growing Layers of Perceptrons: Introducing the Extentron Algorithm

UK PubMed Central (United Kingdom)

The ideas presented here are based on two observationsof perceptrons: (1) when the perceptronlearning algorithm cycles among hyperplanes, thehyperplanes may be compared to select one thatgives a best split of the examples, and (2) it is alwayspossible for the perceptron to build a hyperplanethat separates at least one example from allthe rest. We describe the Extentron which growsmulti-layer networks capable of distinguishing nonlinearly-separable data using the simple perceptronrule for linear threshold units. The resulting algorithmis simple, very fast, scales well to large problems,retains the convergence properties of the perceptron,and can be completely specified using onlytwo parameters. Results are presented comparingthe Extentron to other neural network paradigmsand to symbolic learning systems.1 IntroductionIt is well known that the simple perceptron algorithm(Rosenblatt, 1958) is unable to represent classificationswhich are not linearly separable (Minsky...

Paul T. Baffes; John M. Zelle

98

Comparision of Neural Algorithms for Funchtion Approximation

Directory of Open Access Journals (Sweden)

Full Text Available In this work, various neural network algorithms have been compared for function approximation problems. Multilayer Perceptron (MLP) structure with standard back propagation, MLP with fast back propagation (adaptive learning and momentum term added), MLP with Levenberg-Marquardt learning algorithms, Radial Basis Function (RBF) network structure trained by OLS algorithm and Conic Section Function Neural Network (CSFNN) with adaptive learning have been investigated for various functions. Results showed that the neural algorithms can be used for functional estimation as an alternative to classical methods.

Lale Ozyilmaz; Tulay Yildirim; Kevser Koklu

2002-01-01

99

Multilayer Neural Networks and Nearest Neighbor Classifier Performances for Image Annotation

Directory of Open Access Journals (Sweden)

Full Text Available The explosive growth of image data leads to the research and development of image content searching and indexing systems. Image annotation systems aim at annotating automatically animage with some controlled keywords that can be used for indexing and retrieval of images. This paper presents a comparative evaluation of the image content annotation system by using the multilayer neural networks and the nearest neighbour classifier. The region growing segmentation is used to separate objects, the Hu moments, Legendre moments and Zernike moments which are used in as feature descriptors for the image content characterization and annotation.The ETH-80 database image is used in the experiments here. The best annotation rate is achieved by using Legendre moments as feature extraction method and the multilayer neural network as a classifier

Mustapha OUJAOURA; Brahim MINAOUI; Mohammed FAKIR

2012-01-01

100

Nonlinear blind equalization schemes using complex-valued multilayer feedforward neural networks.

Among the useful blind equalization algorithms, stochastic-gradient iterative equalization schemes are based on minimizing a nonconvex and nonlinear cost function. However, as they use a linear FIR filter with a convex decision region, their residual estimation error is high. In this paper, four nonlinear blind equalization schemes that employ a complex-valued multilayer perceptron instead of the linear filter are proposed and their learning algorithms are derived. After the important properties that a suitable complex-valued activation function must possess are discussed, a new complex-valued activation function is developed for the proposed schemes to deal with QAM signals of any constellation sizes. It has been further proven that by the nonlinear transformation of the proposed function, the correlation coefficient between the real and imaginary parts of input data decreases when they are jointly Gaussian random variables. Last, the effectiveness of the proposed schemes is verified in terms of initial convergence speed and MSE in the steady state. In particular, even without carrier phase tracking procedure, the proposed schemes correct an arbitrary phase rotation caused by channel distortion. PMID:18255822

You, C; Hong, D

1998-01-01

101

Nonlinear blind equalization schemes using complex-valued multilayer feedforward neural networks.

UK PubMed Central (United Kingdom)

Among the useful blind equalization algorithms, stochastic-gradient iterative equalization schemes are based on minimizing a nonconvex and nonlinear cost function. However, as they use a linear FIR filter with a convex decision region, their residual estimation error is high. In this paper, four nonlinear blind equalization schemes that employ a complex-valued multilayer perceptron instead of the linear filter are proposed and their learning algorithms are derived. After the important properties that a suitable complex-valued activation function must possess are discussed, a new complex-valued activation function is developed for the proposed schemes to deal with QAM signals of any constellation sizes. It has been further proven that by the nonlinear transformation of the proposed function, the correlation coefficient between the real and imaginary parts of input data decreases when they are jointly Gaussian random variables. Last, the effectiveness of the proposed schemes is verified in terms of initial convergence speed and MSE in the steady state. In particular, even without carrier phase tracking procedure, the proposed schemes correct an arbitrary phase rotation caused by channel distortion.

You C; Hong D

1998-01-01

102

Generalized classifier neural network.

In this work a new radial basis function based classification neural network named as generalized classifier neural network, is proposed. The proposed generalized classifier neural network has five layers, unlike other radial basis function based neural networks such as generalized regression neural network and probabilistic neural network. They are input, pattern, summation, normalization and output layers. In addition to topological difference, the proposed neural network has gradient descent based optimization of smoothing parameter approach and diverge effect term added calculation improvements. Diverge effect term is an improvement on summation layer calculation to supply additional separation ability and flexibility. Performance of generalized classifier neural network is compared with that of the probabilistic neural network, multilayer perceptron algorithm and radial basis function neural network on 9 different data sets and with that of generalized regression neural network on 3 different data sets include only two classes in MATLAB environment. Better classification performance up to %89 is observed. Improved classification performances proved the effectivity of the proposed neural network. PMID:23298551

Ozyildirim, Buse Melis; Avci, Mutlu

2012-12-25

103

Generalized classifier neural network.

UK PubMed Central (United Kingdom)

In this work a new radial basis function based classification neural network named as generalized classifier neural network, is proposed. The proposed generalized classifier neural network has five layers, unlike other radial basis function based neural networks such as generalized regression neural network and probabilistic neural network. They are input, pattern, summation, normalization and output layers. In addition to topological difference, the proposed neural network has gradient descent based optimization of smoothing parameter approach and diverge effect term added calculation improvements. Diverge effect term is an improvement on summation layer calculation to supply additional separation ability and flexibility. Performance of generalized classifier neural network is compared with that of the probabilistic neural network, multilayer perceptron algorithm and radial basis function neural network on 9 different data sets and with that of generalized regression neural network on 3 different data sets include only two classes in MATLAB environment. Better classification performance up to %89 is observed. Improved classification performances proved the effectivity of the proposed neural network.

Ozyildirim BM; Avci M

2013-03-01

104

Directory of Open Access Journals (Sweden)

Full Text Available One of the essential factors that affect the performance of Artificial Neural Networks is the learning algorithm. The performance of Multilayer Feed Forward Artificial Neural Network performance in image compression using different learning algorithms is examined in this paper. Based on Gradient Descent, Conjugate Gradient, Quasi-Newton techniques three different error back propagation algorithms have been developed for use in training two types of neural networks, a single hidden layer network and three hidden layers network. The essence of this study is to investigate the most efficient and effective training methods for use in image compression and its subsequent applications. The obtained results show that the Quasi-Newton based algorithm has better performance as compared to the other two algorithms.

OMER MAHMOUD; FARHAT ANWAR; MOMOH JIMOH E. SALAMI

2007-01-01

105

Artificial Neural Network to predict mean monthly total ozone in Arosa, Switzerland

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

Chattopadhyay, S; Chattopadhyay, Surajit; Bandyopadhyay, Goutami

2006-01-01

106

One step ahead forecasting using Multilayered perceptron

UK PubMed Central (United Kingdom)

When dealing with time series, the one step ahead forecasting problembased on experimental data is the problem of estimating the autoregressionfunction of the underlying process. When minimizing the expected forecastingerror is the main goal the flexible approach has to be used to be able toadjust the complexity of the model to the complexity of the data. Multilayeredperceptrons are a popular example of such a flexible approach but notthe only one. Other methods such as kernel approximator (e.g. NaradayaWatson regressor), regression spline or wavelet regressor can also be used.But whatever flexible approach is, the main issue remains the control of thecomplexity of the flexible approximator. Noise injection in the inputs is anefficient technique to do so. The complexity of the regessor is then adjustedthanks to the quantity (variance) of injected noise. This quantity is tunedusing a bootstrap estimation of the forecasting error. One unexpected effectof this ap...

Yves Gr; Xia Ding; Centre De Recherches De Royallieu

107

A Comparative Study of RBF and MLP Neural Model for Seven Element Dynamic Phased Array Smart Antenna

Directory of Open Access Journals (Sweden)

Full Text Available In this paper we present the neural Modelling techniques for dynamic phased array smart antenna. Neural networks are mathematical and computation models that are used to optimize the smart antenna system, which are very much suitable for real time applications. Here we are optimizing the seven element dynamic phased array smart antenna using Radial basis function neural network (RBFNN) and Multilayer Perceptron neural network (MLPNN). The beam ship prediction of seven element DPA is done up to 60 deg scan angle and results of RBF and MLP are compared to find out the better neural network approach for smart antenna optimization.

Rahul Shrivastava; Abhishek Rawat; Yogendra Kumar Jain

2013-01-01

108

Weight decay induced phase transitions in multilayer neural networks

We investigate layered neural networks with differentiable activation function and student vectors without normalization constraint by means of equilibrium statistical physics. We consider the learning of perfectly realizable rules and find that the length of student vectors becomes infinite, unless a proper weight decay term is added to the energy. Then, the system undergoes a first order phase transition between states with very long student vectors and states where the lengths are comparable to those of the teacher vectors. Additionally in both configurations there is a phase transition between a specialized and an unspecialized phase. An anti-specialized phase with long student vectors exists in networks with a small number of hidden units.

Ahr, M; Schlösser, E

1999-01-01

109

Power Efficient Multilayer Neural Network for Image Compression

Directory of Open Access Journals (Sweden)

Full Text Available Multi layered neural network architecture is proposed for compression of high-resolution images. The architecture considered has 64-4-64 structures, which achieves 100% compression. The proposed network is initially trained with preselected data sets for accurate training. Feeding the scaled error back into the network at specific points, reduces the training time and reduces redundancy in weight storage. Results show the performance superiority of the network as compared with JPEG compression standard. Inserting noise on the compressed sets of data tests the network performance. Reconstructed image is compared with original image using SE and number of bits per pixel. The proposed architecture models array multipliers, carry save adders, global LUTs (Lookup Tables) for neuron construction. Calculated weights are stored in memory and read whenever required for signal processing. The control unit developed manages the data processing activity saving 20% of power when compared to direct form network structures. Power efficient architecture is developed for hardware implementation. A modification in the proposed architecture enhances the compression by 100% with sum-squared error of about 47.36.

K. Venkata Ramanaiah; K. Lal Kishore; P. Gopal Reddy

2007-01-01

110

A neural network combined to a neural classifier is used in a real time forecasting of hourly maximum ozone in the centre of France, in an urban atmosphere. This neural model is based on the MultiLayer Perceptron (MLP) structure. The inputs of the statistical network are model output statistics of the weather predictions from the French National Weather Service. With this neural classifier, the Success Index of forecasting is 78% whereas it is from 65% to 72% with the classical MLPs. During the validation phase, in the Summer of 2003, six ozone peaks above the threshold were detected. They actually were seven.

Dutot, A; Steiner, F; Rude, J

2008-01-01

111

Scientific Electronic Library Online (English)

Full Text Available Abstract in portuguese Estimativa do perfil de concentração de clorofila, em águas naturais, a partir da radiação emergente na superfície de um corpo d'agua, com o uso de rede neural artificial do tipo Perceptron de Múltiplas Camadas. A concentração de clorofila está relacionada com os coeficientes de absorção e espalhamento via modelos bio-ópticos. O treinamento da rede é formulado como um problema de otimização, no qual a atualização das variáveis livres da rede (pesos, viés e parâmetros de cada função de ativação) é feita através do método quasi-Newton. Abstract in english In this work the average profile of chlorophyll concentration is estimated from the emitted radiation at the surface of natural waters. This is performed through the use an Artificial Neural Network of Multilayer Perceptron type to act as the inverse operator. Bio-optical models are used to correlate the chlorophyll concentration with the absorption and scattering coefficients. The network training is formulated as an optimization problem, in which the update of the free (more) variables of network (weights, viéses and each slope of the activation functions) is performed through the quasi-Newton method.

Dall Cortivo, F.; Chalhoub, E. S.; Campos Velho, H. F.

2012-12-01

112

The use of Neural Networks in ... discrimination

UK PubMed Central (United Kingdom)

A Neural Network algorithm has been applied to the problem of discriminatingbetween photons and neutral pions using calorimetric informationfrom the ALEPH detector. Results are presented comparing theNeural Network with the existing ALEPH algorithms. In all cases theperformance of the Neural Network is comparable or superior to that ofthe conventional algorithms. In particular, at high energies, where thesealgorithms perform poorly, the Neural Network is still able to distinguishbetween the two particle types.1IntroductionThe application of software-implemented Neural Networks to high energy physicsproblems is now well established (see [1] for example). In particular, problemsinvolving pattern recognition, feature classification and combinatorial optimizationare well-suited to analysis using Neural Network paradigms. Here we use astandard back-propagated multi-layer perceptron network to study the problemof discriminating between photons and neutral pions in th...

Wayne S. Babbage; Lee F. Thompson

113

The Perceptron with Dynamic Margin

The classical perceptron rule provides a varying upper bound on the maximum margin, namely the length of the current weight vector divided by the total number of updates up to that time. Requiring that the perceptron updates its internal state whenever the normalized margin of a pattern is found not to exceed a certain fraction of this dynamic upper bound we construct a new approximate maximum margin classifier called the perceptron with dynamic margin (PDM). We demonstrate that PDM converges in a finite number of steps and derive an upper bound on them. We also compare experimentally PDM with other perceptron-like algorithms and support vector machines on hard margin tasks involving linear kernels which are equivalent to 2-norm soft margin.

Panagiotakopoulos, Constantinos

2011-01-01

114

Random noise effects in pulse-mode digital multilayer neural networks.

UK PubMed Central (United Kingdom)

A pulse-mode digital multilayer neural network (DMNN) based on stochastic computing techniques is implemented with simple logic gates as basic computing elements. The pulse-mode signal representation and the use of simple logic gates for neural operations lead to a massively parallel yet compact and flexible network architecture, well suited for VLSI implementation. Algebraic neural operations are replaced by stochastic processes using pseudorandom pulse sequences. The distributions of the results from the stochastic processes are approximated using the hypergeometric distribution. Synaptic weights and neuron states are represented as probabilities and estimated as average pulse occurrence rates in corresponding pulse sequences. A statistical model of the noise (error) is developed to estimate the relative accuracy associated with stochastic computing in terms of mean and variance. Computational differences are then explained by comparison to deterministic neural computations. DMNN feedforward architectures are modeled in VHDL using character recognition problems as testbeds. Computational accuracy is analyzed, and the results of the statistical model are compared with the actual simulation results. Experiments show that the calculations performed in the DMNN are more accurate than those anticipated when Bernoulli sequences are assumed, as is common in the literature. Furthermore, the statistical model successfully predicts the accuracy of the operations performed in the DMNN.

Kim YC; Shanblatt MA

1995-01-01

115

International Nuclear Information System (INIS)

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

2007-01-01

116

Scientific Electronic Library Online (English)

Full Text Available Abstract in english Neural Networks are a set of mathematical methods and computer programs designed to simulate the information process and the knowledge acquisition of the human brain. In last years its application in chemistry is increasing significantly, due the special characteristics for model complex systems. The basic principles of two types of neural networks, the multi-layer perceptrons and radial basis functions, are introduced, as well as, a pruning approach to architecture optim (more) ization. Two analytical applications based on near infrared spectroscopy are presented, the first one for determination of nitrogen content in wheat leaves using multi-layer perceptrons networks and second one for determination of BRIX in sugar cane juices using radial basis functions networks.

Cerqueira, Eduardo O. de; Andrade, João C. de; Poppi, Ronei J.; Mello, Cesar

2001-12-01

117

Generalization ability of a perceptron with nonmonotonic transfer function

We investigate the generalization ability of a perceptron with nonmonotonic transfer function of a reversed-wedge type in on-line mode. This network is identical to a parity machine, a multilayer network. We consider several learning algorithms. By the perceptron algorithm the generalization error is shown to decrease by the ?-1/3-law similarly to the case of a simple perceptron in a restricted range of the parameter a characterizing the nonmonotonic transfer function. For other values of a, the perceptron algorithm leads to the state where the weight vector of the student is just opposite to that of the teacher. The Hebbian learning algorithm has a similar property; it works only in a limited range of the parameter. The conventional AdaTron algorithm does not give a vanishing generalization error for any values of a. We thus introduce a modified AdaTron algorithm that yields a good performance for all values of a. We also investigate the effects of optimization of the learning rate as well as of the learning algorithm. Both methods give excellent learning curves proportional to ?-1. The latter optimization is related to the Bayes statistics and is shown to yield useful hints to extract maximum amount of information necessary to accelerate learning processes.

Inoue, Jun-Ichi; Nishimori, Hidetoshi; Kabashima, Yoshiyuki

1998-07-01

118

Design and FPGA-implementation of multilayer neural networks with on-chip learning

International Nuclear Information System (INIS)

Artificial Neural Networks (ANN) is used in many applications in the industry because of their parallel structure, high speed, and their ability to give easy solution to complicated problems. For example identifying the orange and apple in the sorting machine with neural network is easier than using image processing techniques to do the same thing. There are different software for designing, training, and testing the ANN, but in order to use the ANN in the industry, it should be implemented on hardware outside the computer. Neural networks are artificial systems inspired on the brain's cognitive behavior, which can learn tasks with some degree of complexity, such as signal processing, diagnosis, robotics, image processing, and pattern recognition. Many applications demand a high computing power and the traditional software implementation are not sufficient.This thesis presents design and FPGA implementation of Multilayer Neural Networks with On-chip learning in re-configurable hardware. Hardware implementation of neural network algorithm is very interesting due their high performance and they can easily be made parallel. The architecture proposed herein takes advantage of distinct data paths for the forward and backward propagation stages and a pipelined adaptation of the on- line backpropagation algorithm to significantly improve the performance of the learning phase. The architecture is easily scalable and able to cope with arbitrary network sizes with the same hardware. The implementation is targeted diagnosis of the Research Reactor accidents to avoid the risk of occurrence of a nuclear accident. The proposed designed circuits are implemented using Xilinx FPGA Chip XC40150xv and occupied 73% of Chip CLBs. It achieved 10.8 ?s to take decision in the forward propagation compared with current software implemented of RPS which take 24 ms. The results show that the proposed architecture leads to significant speed up comparing to high end software solutions. On-chip learning allows on line reconstruction of ANN. Re-configure ability and parallel structure of FPGA makes it possible to accomplish this task.

2008-01-01

119

Video Traffic Prediction Using Neural Networks

Directory of Open Access Journals (Sweden)

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 networks)and 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].

Miloš Oravec; Miroslav Petráš; Filip Pilka

2008-01-01

120

Ranking and Reranking with Perceptron

UK PubMed Central (United Kingdom)

This work is inspired by the so-called reranking tasks in natural language processing.In this paper, we first study the ranking, reranking, and ordinal regression algorithmsproposed recently in the context of ranks and margins. Then we propose a general frameworkfor ranking and reranking, and introduce a series of variants of the perceptron algorithm forranking and reranking in the new framework. Compared to the approach of using pairwiseobjects as training samples, the new algorithms reduces the data complexity and trainingtime. We apply the new perceptron algorithms to the parse reranking and machine translationreranking tasks, and study the performance of reranking by employing various definitions ofthe margins.

Libin Shen; Aravind K. Joshi

121

Classification of acoustic noise sources using artificial neural networks

Energy Technology Data Exchange (ETDEWEB)

Artificial neural networks (ANN) have been applied to the classification of acoustic noise sources. The aim of the analysis was to classify the signals collected by a passive sonar, using a set of registrations of ship noise. As available data were limited, car noise was also used. Several feature vectors were tested as input to multilayer perceptrons neural nets and their performances compared. The spectral samples of the signal, but using as feature-vector components a few linear combinations of spectral samples with noise-like vectors also gave good results.

Andreucci, F.; Arbolino, M.V. [Dune s.r.l., Rome (Italy); Garofalo, G. [CO.F.A.S. Consorzio Flegreo Attivita` Subacquee, Naples (Italy)

1997-01-01

122

A Second-Order Perceptron Algorithm

UK PubMed Central (United Kingdom)

We introduce a variant of the Perceptron algorithm called second-order Perceptron algorithm, which is able to exploit certain spectral properties of the data. We analyze the second-order Perceptron algorithm in the mistake bound model of on-line learning and prove bounds in terms of the eigenvalues of the Gram matrix created from the data.

Alex Conconi; Claudio Gentile

123

Directory of Open Access Journals (Sweden)

Full Text Available This paper describes artificial neural network (ANN) based prediction of theresponse of a fiber optic sensor using evanescent field absorption (EFA). The sensingprobe of the sensor is made up a bundle of five PCS fibers to maximize the interaction ofevanescent field with the absorbing medium. Different backpropagation algorithms areused to train the multilayer perceptron ANN. The Levenberg-Marquardt algorithm, aswell as the other algorithms used in this work successfully predicts the sensor responses.

ÃƒÂ–. Galip Saracoglu

2008-01-01

124

Higher-order probabilistic perceptrons as Bayesian inference engines

International Nuclear Information System (INIS)

This letter makes explicit a structural connection between the Bayes optimal classifier operating on K binary input variables and corresponding two-layer perceptron having normalized output activities and couplings from input to output units of all orders up to K. Given a large and unbiased training set and an effective learning algorithm, such a neural network should be able to learn the statistics of the classification problem and match the a posteriori probabilities given by the Bayes optimal classifier. (author). 18 refs.

1994-01-01

125

A Novel Channel Equalizer Using Large Margin Algebraic Perceptron Network

Directory of Open Access Journals (Sweden)

Full Text Available This paper proposes a novel control scheme for channel equalization for wireless communication system. The proposed scheme considers channel equalization as a classification problem. For efficient solution of the problem, this paper makes use of a neural network working on Algebraic Perceptron (AP) algorithm as a classifier. Also, this paper introduces a method of performance improvement by increasing margin of AP equalizers. Novelty of the proposed scheme is evidenced by its simulation results.

Priti R. Hathy; Sasmita K. Padhy; Siba P. Panigrahi; Prashant K. Patra

2010-01-01

126

a Statistical-Fuzzy Perceptron

An optimal statistical perceptron algorithm is derived using the Bayes classification theory. The described algorithm is able to construct an optimal classification hyperplane for separable and nonseparable classes. The described algorithm can be easily improved by imposing a simple fuzzyfication scheme of the training sets.

Andrecut, M.

127

A Novel Technique to Image Annotation using Neural Network

Directory of Open Access Journals (Sweden)

Full Text Available : Automatic annotation of digital pictures is a key technology for managing and retrieving images from large image collection. Traditional image semantics extraction and representation schemes were commonly divided into two categories, namely visual features and text annotations. However, visual feature scheme are difficult to extract and are often semantically inconsistent. On the other hand, the image semantics can be well represented by text annotations. It is also easier to retrieve images according to their annotations. Traditional image annotation techniques are time-consuming and requiring lots of human effort. In this paper we propose Neural Network based a novel approach to the problem of image annotation. These approaches are applied to the Image data set. Our main work is focused on the image annotation by using multilayer perceptron, which exhibits a clear-cut idea on application of multilayer perceptron with special features. MLP Algorithm helps us to discover the concealed relations between image data and annotation data, and annotate image according to such relations. By using this algorithm we can save more memory space, and in case of web applications, transferring of images and download should be fast. This paper reviews 50 image annotation systems using supervised machine learning Techniques to annotate images for image retrieval. Results obtained show that the multi layer perceptron Neural Network classifier outperforms conventional DST Technique.

Pankaj Savita

2013-01-01

128

Breast Fine Needle Tumor Classification using Neural Networks

Directory of Open Access Journals (Sweden)

Full Text Available The purpose of this study is to develop an intelligent diagnosis system for breast cancer classification. Artificial Neural Networks and Support Vector Machines were being developed to classify the benign and malignant of breast tumor in fine needle aspiration cytology. First the features were extracted from 92 FNAC image. Then these features were presented to several neural network architectures to investigate the most suitable network model for classifying the tumor effectively. Four classification models were used namely multilayer perceptron (MLP) using back-propagation algorithm, probabilistic neural networks (PNN), learning vector quantization (LVQ) and support vector machine (SVM). The classification results were obtained using 10-fold cross validation. The performance of the networks was compared based on resulted error rate, correct rate, sensitivity and specificity. The method was evaluated using six different datasets including four datasets related to our work and two other benchmark datasets for comparison. The optimum network for classification of breast cancer cells was found using probabilistic neural networks. This is followed in order by support vector machine, learning vector quantization and multilayer perceptron. The results showed that the predictive ability of probabilistic neural networks and support vector machine are stronger than the others in all evaluated datasets.

Yasmeen M. George; Bassant Mohamed Elbagoury; Hala H. Zayed; Mohamed I. Roushdy

2012-01-01

129

Using Artificial Neural Networks for ECG Signals Denoising

Directory of Open Access Journals (Sweden)

Full Text Available The authors have investigated some potential applications of artificial neural networks in electrocardiografic (ECG) signal prediction. For this, the authors used an adaptive multilayer perceptron structure to predict the signal. The proposed procedure uses an artificial neural network based learning structure to estimate the (n+1)th sample from n previous samples To train and adjust the network weights, the backpropagation (BP) algorithm was used. In this paper, prediction of ECG signals (as time series) using multi-layer feedforward neural networks will be described. The results are evaluated through approximation error which is defined as the difference between the predicted and the original signal.The prediction procedure is carried out (simulated) in MATLAB environment, using signals from MIT-BIH arrhythmia database. Preliminary results are encouraging enough to extend the proposed method for other types of data signals.

Zoltán Germán-Salló; Katalin György

2010-01-01

130

Controlling natural convection in a closed thermosyphon using neural networks

. The aim of this paper is to present a neural network-based approach to identification and control of a rectangular natural circulation loop. The first part of the paper defines a NARMAX model for the prediction of the experimental oscillating behavior characterizing the fluid temperature. The model has been generalized and implemented by means of a Multilayer Perceptron Neural Network that has been trained to simulate the system experimental dynamics. In the second part of the paper, the NARMAX model has been used to simulate the plant during the training of another neural network aiming to suppress the undesired oscillating behavior of the system. In order to define the neural controller, a cascade of several couples of neural networks representing both the system and the controller has been used, the number of couples coinciding with the number of steps in which the control action is exerted.

Cammarata, L.; Fichera, A.; Pagano, A.

131

Recurrent neural networks for diagnosis of carpal tunnel syndrome using electrophysiologic findings.

UK PubMed Central (United Kingdom)

This paper presents the use of recurrent neural networks (RNNs) for diagnosis of carpal tunnel syndrome (CTS) (normal, right CTS, left CTS, bilateral CTS). The RNN is trained with the Levenberg-Marquardt algorithm. The RNN is trained on the features of CTS (right median motor latency, left median motor latency, right median sensory latency, left median sensory latency). The multilayer perceptron neural network (MLPNN) is also implemented for comparison the performance of the classifiers on the same diagnosis problem. The total classification accuracy of the RNN is significantly high (94.80%). The obtained results confirmed the validity of the RNNs to help in clinical decision-making.

Ilbay K; Ubeyli ED; Ilbay G; Budak F

2010-08-01

132

APPLICATION OF NEURAL NETWORK ALGORITHMS FOR BPM LINEARIZATION

Energy Technology Data Exchange (ETDEWEB)

Stripline BPM sensors contain inherent non-linearities, as a result of field distortions from the pickup elements. Many methods have been devised to facilitate corrections, often employing polynomial fitting. The cost of computation makes real-time correction difficult, particulalry when integer math is utilized. The application of neural-network technology, particularly the multi-layer perceptron algorithm, is proposed as an efficient alternative for electrode linearization. A process of supervised learning is initially used to determine the weighting coefficients, which are subsequently applied to the incoming electrode data. A non-linear layer, known as an ?activation layer,? is responsible for the removal of saturation effects. Implementation of a perceptron in an FPGA-based software-defined radio (SDR) is presented, along with performance comparisons. In addition, efficient calculation of the sigmoidal activation function via the CORDIC algorithm is presented.

Musson, John C. [JLAB; Seaton, Chad [JLAB; Spata, Mike F. [JLAB; Yan, Jianxun [JLAB

2012-11-01

133

Advances in Artificial Neural Networks – Methodological Development and Application

Directory of Open Access Journals (Sweden)

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 engineering.

Yanbo Huang

2009-01-01

134

Aphasia Classification Using Neural Networks

DEFF Research Database (Denmark)

A web-based software model (http://fuzzy.iau.dtu.dk/aphasia.nsf) was developed as an example for classification of aphasia using neural networks. Two multilayer perceptrons were used to classify the type of aphasia (Broca, Wernicke, anomic, global) according to the results in some subtests of the Aachen Aphasia Test (AAT). First a coarse classification was achieved by using an assessment of spontaneous speech of the patient. This classifier produced correct results in 87% of the test cases. For a second test, data analysis tools were used to select four features out of the 30 available test features to yield a more accurate diagnosis. This second classifier produced correct results in 92% of the test cases. This test requires four AAT scores as input for the multilayer perceptron. In practice, the second test requires hours of work on behalf of the clinician, whereas the first test can be done in about half an hour in a free interview. The results of the classifiers were analyzed regarding their accuracy dependent on the diagnosis.

Axer, H.; Jantzen, Jan

2000-01-01

135

The No-Prop algorithm: a new learning algorithm for multilayer neural networks.

UK PubMed Central (United Kingdom)

A new learning algorithm for multilayer neural networks that we have named No-Propagation (No-Prop) is hereby introduced. With this algorithm, the weights of the hidden-layer neurons are set and fixed with random values. Only the weights of the output-layer neurons are trained, using steepest descent to minimize mean square error, with the LMS algorithm of Widrow and Hoff. The purpose of introducing nonlinearity with the hidden layers is examined from the point of view of Least Mean Square Error Capacity (LMS Capacity), which is defined as the maximum number of distinct patterns that can be trained into the network with zero error. This is shown to be equal to the number of weights of each of the output-layer neurons. The No-Prop algorithm and the Back-Prop algorithm are compared. Our experience with No-Prop is limited, but from the several examples presented here, it seems that the performance regarding training and generalization of both algorithms is essentially the same when the number of training patterns is less than or equal to LMS Capacity. When the number of training patterns exceeds Capacity, Back-Prop is generally the better performer. But equivalent performance can be obtained with No-Prop by increasing the network Capacity by increasing the number of neurons in the hidden layer that drives the output layer. The No-Prop algorithm is much simpler and easier to implement than Back-Prop. Also, it converges much faster. It is too early to definitively say where to use one or the other of these algorithms. This is still a work in progress.

Widrow B; Greenblatt A; Kim Y; Park D

2013-01-01

136

ERROR VS REJECTION CURVE FOR THE PERCEPTRON

Digital Repository Infrastructure Vision for European Research (DRIVER)

We calculate the generalization error epsilon for a > perceptron J, trained by a teacher perceptron T, on input patterns S that form a fixed angle arccos (J.S) with the student. We show that the error is reduced from a power law to an exponentially fast decay by rejecting input patterns th...

PARRONDO, JMR; VAN DEN BROECK, Christian

137

Neural network models for conditional distribution under bayesian analysis.

UK PubMed Central (United Kingdom)

We use neural networks (NN) as a tool for a nonlinear autoregression to predict the second moment of the conditional density of return series. The NN models are compared to the popular econometric GARCH(1,1) model. We estimate the models in a Bayesian framework using Markov chain Monte Carlo posterior simulations. The interlinked aspects of the proposed Bayesian methodology are identification of NN hidden units and treatment of NN complexity based on model evidence. The empirical study includes the application of the designed strategy to market data, where we found a strong support for a nonlinear multilayer perceptron model with two hidden units.

Miazhynskaia T; Frühwirth-Schnatter S; Dorffner G

2008-02-01

138

Neural network models for conditional distribution under bayesian analysis.

We use neural networks (NN) as a tool for a nonlinear autoregression to predict the second moment of the conditional density of return series. The NN models are compared to the popular econometric GARCH(1,1) model. We estimate the models in a Bayesian framework using Markov chain Monte Carlo posterior simulations. The interlinked aspects of the proposed Bayesian methodology are identification of NN hidden units and treatment of NN complexity based on model evidence. The empirical study includes the application of the designed strategy to market data, where we found a strong support for a nonlinear multilayer perceptron model with two hidden units. PMID:18045023

Miazhynskaia, Tatiana; Frühwirth-Schnatter, Sylvia; Dorffner, Georg

2008-02-01

139

Analysis and Prediction of Temperature using Statistical Artificial Neural Network

Directory of Open Access Journals (Sweden)

Full Text Available This paper is about producing a prediction system by usingartificial neural methods that will forecast temperature. Thispaper is based on three objectives. First, study of temperature andgathers all knowledge regarding the weather this is particularlystudied in analysis part of the paper. Second, gather allknowledge about artificial neural network methods. Implementmultilayer perceptron neural network with gradient descent(backpropagation), BFGS, conjugate gradient training algorithm andwill analyze the performance of all. Lastly, achieve an objectiveof developing a temperature prediction system. The generalfinding is that with BFGS algorithm, with multilayer perceptronmodel perform well with less prediction error and more accuracythan gradient descent and conjugate gradient, thus used fortemperature prediction. To implement this project we make useof statistica software which provides the functionality calledstatistica artificial neural network(SANN) which is used here fortemperature prediction and heavy weather software is used fordata gathering.

Parag Kadu; Kishor Wagh; Prashant Chatur

2012-01-01

140

On-line Learning with a Perceptron

UK PubMed Central (United Kingdom)

We study on--line learning of a linearly separable rule with a simpleperceptron. Training utilizes a sequence of uncorrelated, randomly drawnN--dimensional input examples. In the thermodynamic limit the generalizationerror after training with P such examples can be calculated exactly.For the standard perceptron algorithm it decreases like (N=P )1=3for largeP=N , in contrast to the faster (N=P )1=2--behavior of the so--called Hebbianlearning. Furthermore, we show that a specific parameter--free on--linescheme, the AdaTron algorithm, gives an asymptotic (N=P )--decay of thegeneralization error. This coincides (up to a constant factor) with thebound for any training process based on random examples, including off--line learning. Simulations confirm our results.PACS. 87.10, 02.50, 05.90A very important feature of Feedforward Neural Networks is their ability tolearn a rule from examples [1, 2]. Methods known from Statistical Mechanicshave been successfully used to s...

Michael Biehl; Peter Riegler

141

On--line Learning with a Perceptron

UK PubMed Central (United Kingdom)

We study on--line learning of a linearly separable rule with a simpleperceptron. Training utilizes a sequence of uncorrelated, randomly drawnN--dimensional input examples. In the thermodynamic limit the generalizationerror after training with P such examples can be calculated exactly.For the standard perceptron algorithm it decreases like (N=P )1=3for largeP=N , in contrast to the faster (N=P )1=2--behavior of the so--called Hebbianlearning. Furthermore, we show that a specific parameter--free on--linescheme, the AdaTron algorithm, gives an asymptotic (N=P )--decay of thegeneralization error. This coincides (up to a constant factor) with thebound for any training process based on random examples, including off--line learning. Simulations confirm our results.PACS. 87.10, 02.50, 05.90A very important feature of Feedforward Neural Networks is their ability tolearn a rule from examples [1, 2]. Methods known from Statistical Mechanicshave been successfully used to s...

Michael Biehl; Peter Riegler

142

Volterra models and three-layer perceptrons.

This paper proposes the use of a class of feedforward artificial neural networks with polynomial activation functions (distinct for each hidden unit) for practical modeling of high-order Volterra systems. Discrete-time Volterra models (DVMs) are often used in the study of nonlinear physical and physiological systems using stimulus-response data. However, their practical use has been hindered by computational limitations that confine them to low-order nonlinearities (i.e., only estimation of low-order kernels is practically feasible). Since three-layer perceptrons (TLPs) can be used to represent input-output nonlinear mappings of arbitrary order, this paper explores the basic relations between DVMs and TLPs with tapped-delay inputs in the context of nonlinear system modeling. A variant of TLP with polynomial activation functions-termed "separable Volterra networks" (SVNs)-is found particularly useful in deriving explicit relations with DVM and in obtaining practicable models of highly nonlinear systems from stimulus-response data. The conditions under which the two approaches yield equivalent representations of the input-output relation are explored, and the feasibility of DVM estimation via equivalent SVN training using backpropagation is demonstrated by computer-simulated examples and compared with results from the Laguerre expansion technique (LET). The use of SVN models allows practicable modeling of high-order nonlinear systems, thus removing the main practical limitation of the DVM approach. PMID:18255744

Marmarelis, V Z; Zhao, X

1997-01-01

143

Volterra models and three-layer perceptrons.

UK PubMed Central (United Kingdom)

This paper proposes the use of a class of feedforward artificial neural networks with polynomial activation functions (distinct for each hidden unit) for practical modeling of high-order Volterra systems. Discrete-time Volterra models (DVMs) are often used in the study of nonlinear physical and physiological systems using stimulus-response data. However, their practical use has been hindered by computational limitations that confine them to low-order nonlinearities (i.e., only estimation of low-order kernels is practically feasible). Since three-layer perceptrons (TLPs) can be used to represent input-output nonlinear mappings of arbitrary order, this paper explores the basic relations between DVMs and TLPs with tapped-delay inputs in the context of nonlinear system modeling. A variant of TLP with polynomial activation functions-termed "separable Volterra networks" (SVNs)-is found particularly useful in deriving explicit relations with DVM and in obtaining practicable models of highly nonlinear systems from stimulus-response data. The conditions under which the two approaches yield equivalent representations of the input-output relation are explored, and the feasibility of DVM estimation via equivalent SVN training using backpropagation is demonstrated by computer-simulated examples and compared with results from the Laguerre expansion technique (LET). The use of SVN models allows practicable modeling of high-order nonlinear systems, thus removing the main practical limitation of the DVM approach.

Marmarelis VZ; Zhao X

1997-01-01

144

A Study on Modeling of MIMO Channel by Using Different Neural Network Structures

Directory of Open Access Journals (Sweden)

Full Text Available Recognition of Radio Channel (channelParameters) is one of Main Challenges in SignalTransformation, and has important role in cognitive radioapproach. Goal of this paper is “Channel modeling” to estimatecoefficients of transmission functions affected on data beingtransformed in the channel. We use Multilayer perceptron(MLP)Neural Network with Back-propagation learning algorithm,block-structured Neural Network with Least Squares(LS)method(cost function) and a multilayer neural network withmultiple back-propagation(MBP) learning algorithm for errorestimation. These networks will be trained with received signalsto be compatible with channel, then give us an estimation of thesecoefficients. Simulation will show that this MBP method is betterthan the other two method in error estimation. It has goodperformance and also consume less execution time. Then, we willuse this network for estimating coefficients of non-lineartransmission functions of actual radio channel.

N. Prabhakar; Seyed Saeed Ayat

2012-01-01

145

Energy Technology Data Exchange (ETDEWEB)

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

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

1999-07-01

146

Online learning in a chemical perceptron.

UK PubMed Central (United Kingdom)

Autonomous learning implemented purely by means of a synthetic chemical system has not been previously realized. Learning promotes reusability and minimizes the system design to simple input-output specification. In this article we introduce a chemical perceptron, the first full-featured implementation of a perceptron in an artificial (simulated) chemistry. A perceptron is the simplest system capable of learning, inspired by the functioning of a biological neuron. Our artificial chemistry is deterministic and discrete-time, and follows Michaelis-Menten kinetics. We present two models, the weight-loop perceptron and the weight-race perceptron, which represent two possible strategies for a chemical implementation of linear integration and threshold. Both chemical perceptrons can successfully identify all 14 linearly separable two-input logic functions and maintain high robustness against rate-constant perturbations. We suggest that DNA strand displacement could, in principle, provide an implementation substrate for our model, allowing the chemical perceptron to perform reusable, programmable, and adaptable wet biochemical computing.

Banda P; Teuscher C; Lakin MR

2013-01-01

147

An oil fraction neural sensor developed using electrical capacitance tomography sensor data.

UK PubMed Central (United Kingdom)

This paper presents novel research on the development of a generic intelligent oil fraction sensor based on Electrical Capacitance Tomography (ECT) data. An artificial Neural Network (ANN) has been employed as the intelligent system to sense and estimate oil fractions from the cross-sections of two-component flows comprising oil and gas in a pipeline. Previous works only focused on estimating the oil fraction in the pipeline based on fixed ECT sensor parameters. With fixed ECT design sensors, an oil fraction neural sensor can be trained to deal with ECT data based on the particular sensor parameters, hence the neural sensor is not generic. This work focuses on development of a generic neural oil fraction sensor based on training a Multi-Layer Perceptron (MLP) ANN with various ECT sensor parameters. On average, the proposed oil fraction neural sensor has shown to be able to give a mean absolute error of 3.05% for various ECT sensor sizes.

Zainal-Mokhtar K; Mohamad-Saleh J

2013-01-01

148

Optimal exponential synchronization of general chaotic delayed neural networks: an LMI approach.

UK PubMed Central (United Kingdom)

This paper investigates the optimal exponential synchronization problem of general chaotic neural networks with or without time delays by virtue of Lyapunov-Krasovskii stability theory and the linear matrix inequality (LMI) technique. This general model, which is the interconnection of a linear delayed dynamic system and a bounded static nonlinear operator, covers several well-known neural networks, such as Hopfield neural networks, cellular neural networks (CNNs), bidirectional associative memory (BAM) networks, and recurrent multilayer perceptrons (RMLPs) with or without delays. Using the drive-response concept, time-delay feedback controllers are designed to synchronize two identical chaotic neural networks as quickly as possible. The control design equations are shown to be a generalized eigenvalue problem (GEVP) which can be easily solved by various convex optimization algorithms to determine the optimal control law and the optimal exponential synchronization rate. Detailed comparisons with existing results are made and numerical simulations are carried out to demonstrate the effectiveness of the established synchronization laws.

Liu M

2009-09-01

149

The Margitron: A Generalised Perceptron with Margin

We identify the classical Perceptron algorithm with margin as a member of a broader family of large margin classifiers which we collectively call the Margitron. The Margitron, (despite its) sharing the same update rule with the Perceptron, is shown in an incremental setting to converge in a finite number of updates to solutions possessing any desirable fraction of the maximum margin. Experiments comparing the Margitron with decomposition SVMs on tasks involving linear kernels and 2-norm soft margin are also reported.

Panagiotakopoulos, Constantinos

2008-01-01

150

Classifying epilepsy diseases using artificial neural networks and genetic algorithm.

UK PubMed Central (United Kingdom)

In this study, FFT analysis is applied to the EEG signals of the normal and patient subjects and the obtained FFT coefficients are used as inputs in Artificial Neural Network (ANN). The differences shown by the non-stationary random signals such as EEG signals in cases of health and sickness (epilepsy) were evaluated and tried to be analyzed under computer-supported conditions by using artificial neural networks. Multi-Layer Perceptron (MLP) architecture is used Levenberg-Marquardt (LM), Quickprop (QP), Delta-bar delta (DBD), Momentum and Conjugate gradient (CG) learning algorithms, and the best performance was tried to be attained by ensuring the optimization with the use of genetic algorithms of the weights, learning rates, neuron numbers of hidden layer in the training process. This study shows that the artificial neural network increases the classification performance using genetic algorithm.

Koçer S; Canal MR

2011-08-01

151

Radial Wavelet Neural Networks for Electroencephalographic Drug Detection

UK PubMed Central (United Kingdom)

Several samples of single-channel EEGs collected from 10 subjects under normalconditions, and under one of 3 antiepileptic drugs, were used to train 30 wavelet neural networks (WNNs)to perform 3 subject-specific recognition tasks. The recognition tasks were: (1) Detection of drug onsession 1 (B-S1), (2) Detection of drug on session 2 (B-S2), and (3) Drug separation (S1-S2). It is shownthat WNNs can improve average recognition scores by more than 10 percentage points over standard lineardiscriminant analysis, at the expense of considerable but clinically justified additional effort.I. IntroductionWavelet1neural networks (WNNs) represent a newclass of radial basis function (RBF) neural networks andwavelet networks [1-5]. The hallmark of WNNs issimply the fact that their neurons' nonlinear activationfunctions are neither completely local as in fuzzysystems and Gaussian RBFs, nor semi-infinitelyreceptive as in multilayer perceptrons, but a middleground obtained from loca...

Javier Echauz; George Vachtsevanos

152

Directory of Open Access Journals (Sweden)

Full Text Available In the article for solving the classification problem of the technical state of the object, proposed to use a hybrid neural network with a Kohonen layer and multilayer perceptron. The information-measuring system can be used for standardless diagnostics, cluster analysis and to classify the products which made from composite materials. The advantage of this architecture is flexibility, high performance, ability to use different methods for collecting diagnostic information about unit under test, high reliability of information processing?????????? ???????????? ??????? ????????? ????? ??? ???????????? ???????????????????? ???????. ??????? ???????? ???????? ?? ??????? ??? ??????? ???????????????????? ?? ?????? ????????? ????????? ??????. ???????? ?????????? ??????????????????????? ??????? ??? ??????????? ?????????? ????? ???????????? ???????.Use of artificial neural networks for classification of defects in cellular panels was introducedand investigated. Algorithm of construction and principles of operation demerit rating system whichbased on hybrid neural network is described. Results of practical use developed system fordiagnostics of a cellular panels’ technical condition was represented.??????????? ????????????? ????????????? ????????? ????? ??? ????????????? ??????????????? ???????. ??????? ???????? ?????????? ? ??????? ???????? ??????? ????????????????????? ?? ?????? ????????? ????????? c???. ????????? ?????????? ?????????????????????????? ??????? ??? ??????????? ???????????? ????????? ??????? ???????.??? ????????? ?????? ???????????? ?????????? ????? ??’???? ???????? ????????????? ??-????????????? ???????? ???????? ??????, ?? ??????????? ? ???? ???????? ?? ??????????-???? ???????????. ????????, ?? ?????????? ??????? ????? ??????????? ??? ????????? ????????????????? ???????????, ??????????? ??????? ?? ???????????? ????? ??????? ??????????????? ??????????. ???????? ???????? ???????: ????????? ?? ???????????, ???????????????, ?????????? ???????????? ? ??????? ???????? ????? ????????????? ????????????? ??’??? ????????, ?????? ????????????? ??????? ??????????

?. ????????; ?. ??????????; ?. ?????????

2011-01-01

153

Neural networks for process control and optimization: two industrial applications.

The two most widely used neural models, multilayer perceptron (MLP) and radial basis function network (RBFN), are presented in the framework of system identification and control. The main steps for building such nonlinear black box models are regressor choice, selection of internal architecture, and parameter estimation. The advantages of neural network models are summarized: universal approximation capabilities, flexibility, and parsimony. Two applications are described in steel industry and water treatment, respectively, the control of alloying process in a hot dipped galvanizing line and the control of a coagulation process in a drinking water treatment plant. These examples highlight the interest of neural techniques, when complex nonlinear phenomena are involved, but the empirical knowledge of control operators can be learned. PMID:12546467

Bloch, Gérard; Denoeux, Thierry

2003-01-01

154

Neural networks for process control and optimization: two industrial applications.

UK PubMed Central (United Kingdom)

The two most widely used neural models, multilayer perceptron (MLP) and radial basis function network (RBFN), are presented in the framework of system identification and control. The main steps for building such nonlinear black box models are regressor choice, selection of internal architecture, and parameter estimation. The advantages of neural network models are summarized: universal approximation capabilities, flexibility, and parsimony. Two applications are described in steel industry and water treatment, respectively, the control of alloying process in a hot dipped galvanizing line and the control of a coagulation process in a drinking water treatment plant. These examples highlight the interest of neural techniques, when complex nonlinear phenomena are involved, but the empirical knowledge of control operators can be learned.

Bloch G; Denoeux T

2003-01-01

155

Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia

Directory of Open Access Journals (Sweden)

Full Text Available Rainfall is considered as one of the major components of the hydrological process; it takes significant part in evaluating drought and flooding events. Therefore, it is important to have an accurate model for rainfall forecasting. Recently, several data-driven modeling approaches have been investigated to perform such forecasting tasks as multi-layer perceptron neural networks (MLP-NN). In fact, the rainfall time series modeling involves an important temporal dimension. On the other hand, the classical MLP-NN is a static and has a memoryless network architecture that is effective for complex nonlinear static mapping. This research focuses on investigating the potential of introducing a neural network that could address the temporal relationships of the rainfall series. Two different static neural networks and one dynamic neural network, namely the multi-layer perceptron neural network (MLP-NN), radial basis function neural network (RBFNN) and input delay neural network (IDNN), respectively, have been examined in this study. Those models had been developed for the two time horizons for monthly and weekly rainfall forecasting at Klang River, Malaysia. Data collected over 12 yr (1997–2008) on a weekly basis and 22 yr (1987–2008) on a monthly basis were used to develop and examine the performance of the proposed models. Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static and dynamic neural networks. Results showed that the MLP-NN neural network model is able to follow trends of the actual rainfall, however, not very accurately. RBFNN model achieved better accuracy than the MLP-NN model. Moreover, the forecasting accuracy of the IDNN model was better than that of static network during both training and testing stages, which proves a consistent level of accuracy with seen and unseen data.

A. El-Shafie; A. Noureldin; M. Taha; A. Hussain; M. Mukhlisin

2012-01-01

156

On PAC Learning Using Winnow, Perceptron, and a Perceptron-Like Algorithm

UK PubMed Central (United Kingdom)

In this paper we analyze the PAC learning abilitiesof several simple iterative algorithms for learninglinear threshold functions, obtaining both positiveand negative results. We show that Littlestone'sWinnow algorithm is not an efficient PAC learningalgorithm for the class of positive linear thresholdfunctions. We also prove that the Perceptron algorithmcannot efficiently learn the unrestricted classof linear threshold functions even under the uniformdistribution on boolean examples. However,we show that the Perceptron algorithm can efficientlyPAC learn the class of nested functions (aconcept class known to be hard for Perceptron underarbitrary distributions) under the uniform distributionon boolean examples. Finally, we givea very simple Perceptron-like algorithm for learningorigin-centered halfspaces under the uniformdistribution on the unit sphere in Rn: Unlike thePerceptron algorithm, which cannot learn in thepresence of classification nois...

Rocco A. Servedio

157

Artificial Neural Network Solutions of Slab-Geometry Neutron Diffusion Problems

Energy Technology Data Exchange (ETDEWEB)

Artificial neural network (ANN) methods have been researched extensively within the nuclear community for applications in systems control, diagnostics, and signal processing. We consider here the use of multilayer perceptron ANNs as an alternative to finite-difference and finite-element methods for obtaining solutions to neutron diffusion problems. This work is based on a method proposed by van Milligen et. al. to obtain solutions of the differential equations arising in plasma physics applications. This ANN method has the potential advantage of yielding an accurate, differentiable approximation to the solution of diffusion problems at all points in the spatial domain.

Brantley, P.S.

2000-06-12

158

Alternative sensor system and MLP neural network for vehicle pedal activity estimation.

UK PubMed Central (United Kingdom)

It is accepted that the activity of the vehicle pedals (i.e., throttle, brake, clutch) reflects the driver's behavior, which is at least partially related to the fuel consumption and vehicle pollutant emissions. This paper presents a solution to estimate the driver activity regardless of the type, model, and year of fabrication of the vehicle. The solution is based on an alternative sensor system (regime engine, vehicle speed, frontal inclination and linear acceleration) that reflects the activity of the pedals in an indirect way, to estimate that activity by means of a multilayer perceptron neural network with a single hidden layer.

Wefky AM; Espinosa F; Jiménez JA; Santiso E; Rodríguez JM; Fernández AJ

2010-01-01

159

A neural method for determining electromagnetic shower positions in laterally segmented calorimeters

Energy Technology Data Exchange (ETDEWEB)

A method based on a neural network technique is proposed to calculate the coordinates of an incident photon striking a laterally segmented calorimeter and depositing shower energies in different segments. The technique uses a multilayer perceptron trained by back-propagation implemented through standard gradient descent followed by conjugate gradient algorithms and has been demonstrated with GEANT simulations of a BAF2 detector array. The position resolution results obtained by using this method are found to be substantially better than the first moment method with logarithmic weighting. (orig.).

Roy, A. [Variable Energy Cyclotron Centre, Calcutta (India); Ray, A. [Variable Energy Cyclotron Centre, Calcutta (India); Mitra, T. [Dept. of Computer Science, Jadavpur University, Calcutta - 700 032 (India); Roy, A. [Dept. of Computer Science, Jadavpur University, Calcutta - 700 032 (India)

1995-10-15

160

Fast non-linear extraction of plasma equilibrium parameters using a neural network mapping

International Nuclear Information System (INIS)

The shaping of non-circular plasmas requires a non-linear mapping between the measured diagnostic signals and selected equilibrium parameters. The particular configuration of Neural Network known as the multi-layer perceptron provides a powerful and general technique for formulating an arbitrary continuous non-linear multi-dimensional mapping. This technique has been successfully applied to the extraction of equilibrium parameters from measurements of single-null diverted plasmas in the DIII-D tokamak; the results are compared with a purely linear mapping. The method is promising, and hardware implementation is straightforward. (author) 15 refs., 7 figs

1990-01-01

161

A Novel Approach to Speech Recognition by Using Generalized Regression Neural Networks

Directory of Open Access Journals (Sweden)

Full Text Available Speech recognition has been a subject of active research in the last few decades. In this paper, the applicability of a special model of Generalized Regression Neural Networks as a classifier is studied. A Generalized Regression Neural Network (GRNN) is often used for function approximation. It has a radial basis layer and a special linear layer. This network uses a competitive function for computing final result. The proposed network has been tested on one digit numbers dataset and produced significantly lower recognition error rate in comparison with common pattern classifiers. All of classifiers use Linear Predictive Cepstral Coefficients and Mel - Frequency Cepstral Coefficients. Results for proposed network shows that LPCC features yield better performance when compared to MFCC. It is found that the performance of Generalized Regression Neural Networks is superior to the other classifiers namely Linear and Multilayer Perceptron Neural Networks.

Lakshmi Kanaka Venkateswarlu Revada; Vasantha Kumari Rambatla; Koti Verra Nagayya Ande

2011-01-01

162

Neural Networks as Dynamical Bases in Function Space

UK PubMed Central (United Kingdom)

: We consider feedforward neural networks such as multi-layer perceptronsas non-orthogonal bases in a function space. The basis functions of that base are thefunctions computed by the neurons of the hidden layer. Projection Learning consistsin shifting the base in such a way that the distance between a function to be approximatedand its projection onto the manifold spanned by the base is minimized. Thatprojection is the approximation by the network. The basis functions to be used arearbitrary, except that they must be differentiable in some sense with regards to theirparameters/weights.We present the paradigm and learning rule using multi-layer perceptrons and bases ofmultivariate Gaussians, discuss some other potential applications, and present alternativesways to compute the projection.The resulting networks display graceful degradation, integrate gracefully further neurons/basis functions for an improved approximation, and adapt dynamically to changesin the environment....

Konrad Weigl; Marc Berthod; Programme Robotique; Projet Pastis

163

Parallel strategy for optimal learning in perceptrons

International Nuclear Information System (INIS)

We developed a parallel strategy for learning optimally specific realizable rules by perceptrons, in an online learning scenario. Our result is a generalization of the Caticha-Kinouchi (CK) algorithm developed for learning a perceptron with a synaptic vector drawn from a uniform distribution over the N-dimensional sphere, so called the typical case. Our method outperforms the CK algorithm in almost all possible situations, failing only in a denumerable set of cases. The algorithm is optimal in the sense that it saturates Bayesian bounds when it succeeds.

2010-03-26

164

The margitron: a generalized perceptron with margin.

UK PubMed Central (United Kingdom)

We identify the classical perceptron algorithm with margin as a member of a broader family of large margin classifiers, which we collectively call the margitron. The margitron, (despite its) sharing the same update rule with the perceptron, is shown in an incremental setting to converge in a finite number of updates to solutions possessing any desirable fraction of the maximum margin. We also report on experiments comparing the margitron with decomposition support vector machines, cutting-plane algorithms, and gradient descent methods on hard margin tasks involving linear kernels which are equivalent to 2-norm soft margin. Our results suggest that the margitron is very competitive.

Panagiotakopoulos C; Tsampouka P

2011-03-01

165

The margitron: a generalized perceptron with margin.

We identify the classical perceptron algorithm with margin as a member of a broader family of large margin classifiers, which we collectively call the margitron. The margitron, (despite its) sharing the same update rule with the perceptron, is shown in an incremental setting to converge in a finite number of updates to solutions possessing any desirable fraction of the maximum margin. We also report on experiments comparing the margitron with decomposition support vector machines, cutting-plane algorithms, and gradient descent methods on hard margin tasks involving linear kernels which are equivalent to 2-norm soft margin. Our results suggest that the margitron is very competitive. PMID:21216709

Panagiotakopoulos, Constantinos; Tsampouka, Petroula

2011-01-06

166

Scientific Electronic Library Online (English)

Full Text Available Abstract in portuguese Vinte variedades de soja (Glycine max), quatorze convencionais e seis variedades transgênicas (RR) foram analisadas quanto ao teor de proteína, ácido fítico, teor de óleo, fitosteróis, cinzas, minerais e ácidos graxos que foram tabelados e apresentados à rede neural do tipo perceptron de múltiplas camadas para a classificação e identificação quanto a região de plantio e quanto a variedade convencional ou transgênica. A rede neural utilizada classificou e te (more) stou corretamente 100% das amostras cultivadas por região. Para o banco de dados contendo informações sobre sojas transgênicas e convencionais foi obtido um desempenho de 94,43% no treinamento da rede, 83,30% no teste e 100% na validação. Abstract in english Twenty soybean (Glycine max) varieties, 14 conventional and 6 transgenic varieties were analyzed for protein content, phytic acid, oil content, phytosterols, ash, minerals and fatty acids. The data were tabled and presented to the multilayer perceptron neural network for classification and identification of their planting region and whether they were a conventional or transgenic. The neural network used correctly classified and tested 100% of the samples cultivated per re (more) gion. For the data bank containing information on transgenic and conventional soybean, a performance of 94.43% was obtained in the training of the neural network, 83.30% in the test and 100% in the validation.

Galão, Olívio F.; Borsato, Dionísio; Pinto, Jurandir P.; Visentainer, Jesuí V.; Carrão-Panizzi, Mercedes Concórdia

2011-01-01

167

Practical Application of Neural Networks in State Space Control

DEFF Research Database (Denmark)

In the present thesis we address some problems in discrete-time state space control of nonlinear dynamical systems and attempt to solve them using generic nonlinear models based on artificial neural networks. The main aim of the work is to examine how well such control algorithms perform when applied to a realistic process. The thesis therefore strives to provide a thorough treatment of two classes of neural network-based controllers, and to make a rigorous comparison between them and a classical linear controller. Thus, the thesis starts out with a short review of some relevant system theoretic notions followed by a detailed description of the topology, neuron functions and learning rules of the two types of neural networks treated in the thesis, the multilayer perceptron and the neurofuzzy networks. In both cases, a Least Squares second-order gradient method is used to train the networks, although some modifications are needed for the method to apply to the multilayer perceptron network. In connection with the multilayer perceptron networks it is also pointed out how instantaneous, sample-by-sample linearized state space models can be extracted from a trained network, thus opening up for application of linear theory at each sample instant. The case study addressed in this work is an attemporator for a high-temperature steam circuit situated in a Danish powerplant, I/S Vestkraft unit 3. The attemporator is fitted with a nonlinear and nonconstant valve, so nonlinear and adaptive control is desired to control the steam temperature tightly. A second-order nonlinear model of the attemporator based on system identification with a multilayer perceptron network is found from data collected from the actual process. It is shown to be a highly satisfying prediction and simulation model of the process. With this model in place, we turn to the control concepts. A pole placement controller based on the sample-by-sample linearizations extracted from a multilayer perceptron state observer is first derived, and it is shown how to make the control concept adaptive by continuing the training online. Then the controller is shown to work on a simulation example. We also address the potential problem of too rapidly fluctuating parameters by including regularization in the learning rule. Next we develop a direct adaptive certainty-equivalence controller based on neurofuzzy models. The control loop is proven to be stable under certain assumptions, and we address the question of how many basis functions are necessary. It is shown that basis functions with compact supports, whose supports are not entered by a system trajectory, do not need parameter updates. Therefore, a system with bounded trajectories can be controlled by a finite-dimensional model. We also introduce a modification to the algorithm which-if an upper bound on the nonlinearity growth is known-enables us to remove a sector-boundedness assumption on the nonlinearity. Finally the control concepts are applied to the nonlinear simulation model discussed above, and it is seen that the neural network -based control concepts outperform a classical linear controller.

Bendtsen, Jan Dimon

1999-01-01

168

Multi-Party Security System using Artificial Neural Networks

Directory of Open Access Journals (Sweden)

Full Text Available Multi-Party Security System is an improvised version of various security systems available using Artificial Neural Networks (ANN’s) as an Intelligent Agent for Intrusion Detection. This Paper focuses how inputs can be preserved to serve as a measure for securing communication protocol between two parties using privacy protocols at the hidden layer of Multi-layer Perceptron model. Various neural network structures are observed for evaluating the optimal network considering the number of hidden layers. Results depict that the generated system is capable of classifying records with about 90% of accuracy when two hidden layers are engulfed and the accuracy reduces to 87% with one hidden layer under observation.

Urvashi Rahul Saxena; S.P Singh

2012-01-01

169

Energy Technology Data Exchange (ETDEWEB)

Neural networks can be applied to the identification of nonlinear dynamic systems because powerful learning algorithms are available. In this contribution, the features of neural networks and traditional, parametric identification approaches are compared. The basis of this study are measurement data from an exhaust gas turbocharger of a truck Diesel engine. The least-squares estimation of time-discrete Hammerstein model is compared with two different neural network architectures. On the one side, a local linear model network trained with LOLIMOT (local linear model tree) is applied. On the other side, a DMLP network (dynamic multilayer perceptron) with internal dynamics is utilized. It turns out that for the turbocharger the Hammerstein model does not perform as well as both neural networks. (orig.) [Deutsch] Durch den Einsatz leistungsfaehiger Lernalgorithmen koennen neuronale Netze mittlerweile auch fuer die Identifikation von nichtlinearen, dynamischen Prozessen eingesetzt werden. Im vorliegenden Beitrag sollen die Eigenschaften von neuronalen Netzen mit denen traditioneller, parametrischer Identifikationsansaetze verglichen werden. Grundlage fuer die Untersuchung sind Messdaten des Abgasturboladers eines Lkw-Dieselmotors. Zur Identifikation wird die Least-Squares-Schaetzung eines zeitdiskreten Hammersteinmodells mit der Schaetzung zweier unterschiedlicher neuronaler Netze verglichen. Zum einen kommt ein extern dynamisches, neuronales Netz mit lokalen, linearen Modellen zum Einsatz, das mit dem LOLIMOT-Algorithmus (local linear model tree) trainiert wird. Zum anderen wird ein DMLP-Netz (dynamic multilayer perceptron) angewandt. Es stellt sich heraus, dass bei der untersuchten Anwendung die beiden neuronalen Netze dem klassischen Hammersteinmodell hinsichtlich Modellguete ueberlegen sind. (orig.)

Nelles, O.; Ernst, S. [Technische Univ. Darmstadt (Germany). Inst. fuer Regelungstechnik; Ayoubi, M. [BMW AG, Muenchen (Germany). Abt. Fahrdynamik-Simulation; Schumann, A. [Technische Univ. Darmstadt (Germany). Inst. fuer Regelungstechnik]|[Hoechst Research and Technology, Frankfurt am Main (Germany). Gruppe Integrierte Betriebsfuehrung; Lachmann, K.H. [HILGER und KERN GmbH, Mannheim (Germany). Sparte Dosiertechnik

1998-12-31

170

Control chart pattern recognition using K-MICA clustering and neural networks.

UK PubMed Central (United Kingdom)

Automatic recognition of abnormal patterns in control charts has seen increasing demands nowadays in manufacturing processes. This paper presents a novel hybrid intelligent method (HIM) for recognition of the common types of control chart pattern (CCP). The proposed method includes two main modules: a clustering module and a classifier module. In the clustering module, the input data is first clustered by a new technique. This technique is a suitable combination of the modified imperialist competitive algorithm (MICA) and the K-means algorithm. Then the Euclidean distance of each pattern is computed from the determined clusters. The classifier module determines the membership of the patterns using the computed distance. In this module, several neural networks, such as the multilayer perceptron, probabilistic neural networks, and the radial basis function neural networks, are investigated. Using the experimental study, we choose the best classifier in order to recognize the CCPs. Simulation results show that a high recognition accuracy, about 99.65%, is achieved.

Ebrahimzadeh A; Addeh J; Rahmani Z

2012-01-01

171

CONTROL OF NONLINEAR PROCESS USING NEURAL NETWORK BASED MODEL PREDICTIVE CONTROL

Directory of Open Access Journals (Sweden)

Full Text Available This paper presents a Neural Network based Model Predictive Control (NNMPC) strategy to control nonlinear process. Multilayer Perceptron Neural Network (MLP) is chosen to represent a Nonlinear Auto Regressive with eXogenous signal (NARX) model of a nonlinear system. NARX dynamic model is based on feed-forward architecture and offers good approximation capabilities along with robustness and accuracy. Based on the identified neural model, a generalized predictive control (GPC) algorithm is implemented to control the composition in acontinuous stirred tank reactor (CSTR), whose parameters are optimally determined by solving quadratic performance index using well known Levenberg-Marquardt and Quasi-Newton algorithm. NNMPC is tuned by selecting few horizon parameters and weighting factor. The tracking performance of the NNMPC is tested using different amplitude function as a reference signal on CSTR application. Also the robustness and performance is tested in the presence of disturbance on random reference signal.

PIYUSH SHRIVASTAVA,; Dr.A.TRIVEDI

2011-01-01

172

Neural Models for the Broadside-Coupled V-Shaped Microshield Coplanar Waveguides

This article presents a new approach based on multilayered perceptron neural networks (MLPNNs) to calculate the odd-and even-mode characteristic impedances and effective permittivities of the broadside-coupled V-shaped microshield coplanar waveguides (BC-VSMCPWs). Six learning algorithms, bayesian regulation (BR), Levenberg-Marquardt (LM), quasi-Newton (QN), scaled conjugate gradient (SCG), resilient propagation (RP), and conjugate gradient of Fletcher-Powell (CGF), are used to train the MLPNNs. The neural results are in very good agreement with the results reported elsewhere. When the performances of neural models are compared with each other, the best and worst results are obtained from the MLPNNs trained by the BR and CGF algorithms, respectively.

Guney, K.; Yildiz, C.; Kaya, S.; Turkmen, M.

2006-09-01

173

Control chart pattern recognition using K-MICA clustering and neural networks.

Automatic recognition of abnormal patterns in control charts has seen increasing demands nowadays in manufacturing processes. This paper presents a novel hybrid intelligent method (HIM) for recognition of the common types of control chart pattern (CCP). The proposed method includes two main modules: a clustering module and a classifier module. In the clustering module, the input data is first clustered by a new technique. This technique is a suitable combination of the modified imperialist competitive algorithm (MICA) and the K-means algorithm. Then the Euclidean distance of each pattern is computed from the determined clusters. The classifier module determines the membership of the patterns using the computed distance. In this module, several neural networks, such as the multilayer perceptron, probabilistic neural networks, and the radial basis function neural networks, are investigated. Using the experimental study, we choose the best classifier in order to recognize the CCPs. Simulation results show that a high recognition accuracy, about 99.65%, is achieved. PMID:22035774

Ebrahimzadeh, Ataollah; Addeh, Jalil; Rahmani, Zahra

2011-10-28

174

Classification of Five Mental Tasks Based on Two Methods of Neural Network

Directory of Open Access Journals (Sweden)

Full Text Available In this paper performance of two classifiers based on Neural Network were investigated for classification of five mental tasks from raw Electroencephalograph (EEG) signal. Aim of this research was to improve brain computer interface (BCI) system applications. For this study, Wavelet packet transform (WPT) was used for feature extraction of the relevant frequency bands from raw electroencephalogram (EEG) signals. The two classifiers used were Radial Basis Function Neural Network (RBFNN) and Multilayer Perceptron Back propagation Neural Network(MLP-BP NN) . In MLP-BP NN five training methods used were (a) Gradient Descent Back Propagation (b) Levenberg-Marquardt (c) Resilient Back Propagation (d) Conjugate Learning Gradient Back Propagation and (e) Gradient Descent Back Propagation with movementum.

Vijay Khare; Jayashree Santhosh; Sneh Anand; Manvir Bhatia

2010-01-01

175

An Approach to Neural Network Based Pattern Classifier for Printed Bengali Characters

Directory of Open Access Journals (Sweden)

Full Text Available In this paper, we have designed a Neural Network based pattern classifier for recognizing Bengali printed characters. Here view-based approach is used for extracting features from individual characters and a neural network based classifier is built to analyze the performance of the view-based approach in various experimental setups. Different Bengali character samples have been taken and whole image of individual character is considered for view based analysis. The characteristic points are extracted from the characters using left-right view based approach. These points are then used to form a feature vector which represents the given character. Multi-Layer Perceptrons Neural network has been used and it was trained by back propagation algorithm to create this recognition engine. Internal shape of each character has been considered to generate the feature vector for individual images.

sabyasachi samanta

2011-01-01

176

Effect of direction on wind speed estimation in complex terrain using neural networks

Energy Technology Data Exchange (ETDEWEB)

A method of estimating the annual average wind speed at a selected site using neural networks is presented. The method proposed uses only a few measurements taken at the selected site in a short time period and data collected at nearby fixed stations. The neural network used in this study is a multilayer perceptron with one hidden layer of 15 neurons, trained by the Bayesian regularization algorithm. The number of inputs that must be used in the neural network was analyzed in detail, and results suggest that only wind speed and direction data for a single station are required. In sites of complex terrain, direction is a very important input that can cause a decrease of 23% in root mean square (RMS). The results obtained by simulating the annual average wind speed at the selected site based on data from nearby stations are satisfactory, with errors below 2%. (author)

Lopez, P.; Velo, R.; Maseda, F. [Department of Agroforestry Engineering, Higher Polytechnic School. University of Santiago de Compostela, Campus Universitario, s/n, 27002, Lugo (Spain)

2008-10-15

177

Fuzzy Clustering Neural Networks for Real-Time Odor Recognition System

Directory of Open Access Journals (Sweden)

Full Text Available The aim of this study is to develop a novel fuzzy clustering neural network(FCNN) algorithm as pattern classifiers for real-time odor recognition system. In this type of FCNN, the input neurons activations are derived through fuzzy c mean clustering of the input data, so that the neural system could deal with the statistics of the measurement error directly. Then the performance of FCNN network is compared with the other network which is well-known algorithm, named multilayer perceptron (MLP), for the same odor recognition system. Experimental results show that both FCNN and MLP provided high recognition probability in determining various learn categories of odors, however, the FCNN neural system has better ability to recognize odors more than the MLP network.

Bekir Karl?k; Kemal Yüksek

2007-01-01

178

Morphological feature selection and neural classification

Directory of Open Access Journals (Sweden)

Full Text Available This paper presents the development procedure of the feature extraction and classification module of an intelligent sortingsystem for electronic components. This system was designed as a prototype to recognise six types of electronic componentsfor the needs of the educational electronics laboratories of the Kavala Institute of Technology. A list of features that describethe morphology of the outline of the components was extracted from the images. Two feature selection strategies were examinedfor the production of a powerful yet concise feature vector. These were correlation analysis and an implementationof support vector machines. Moreover, two types of neural classifiers were considered. The multilayer perceptron trainedwith the back-propagation algorithm and the radial basis function network trained with the K-means method. The best resultswere obtained with the combination of SVMs with MLPs, which successfully recognised 92.3% of the cases.

D. Lefkaditis; G. Tsirigotis

2009-01-01

179

A multi-layer neural-mass model for learning sequences using theta/gamma oscillations.

A neural mass model for the memorization of sequences is presented. It exploits three layers of cortical columns that generate a theta/gamma rhythm. The first layer implements an auto-associative memory working in the theta range; the second segments objects in the gamma range; finally, the feedback interactions between the third and the second layers realize a hetero-associative memory for learning a sequence. After training with Hebbian and anti-Hebbian rules, the network recovers sequences and accounts for the phase-precession phenomenon. PMID:23627655

Cona, Filippo; Ursino, Mauro

2013-03-26

180

A multi-layer neural-mass model for learning sequences using theta/gamma oscillations.

UK PubMed Central (United Kingdom)

A neural mass model for the memorization of sequences is presented. It exploits three layers of cortical columns that generate a theta/gamma rhythm. The first layer implements an auto-associative memory working in the theta range; the second segments objects in the gamma range; finally, the feedback interactions between the third and the second layers realize a hetero-associative memory for learning a sequence. After training with Hebbian and anti-Hebbian rules, the network recovers sequences and accounts for the phase-precession phenomenon.

Cona F; Ursino M

2013-06-01

181

Directory of Open Access Journals (Sweden)

Full Text Available Recently, Artificial Neural Networks (ANN), which is mathematical modelingtools inspired by the properties of the biological neural system, has been typically used inthe studies of hydrological time series modeling. These modeling studies generally includethe standart feed forward backpropagation (FFBP) algorithms such as gradient-descent,gradient-descent with momentum rate and, conjugate gradient etc. As the standart FFBPalgorithms have some disadvantages relating to the time requirement and slowconvergency in training, Newton and Levenberg-Marquardt algorithms, which arealternative approaches to standart FFBP algorithms, were improved and also used in theapplications. In this study, an application of Levenberg-Marquardt algorithm based ANN(LM-ANN) for the modeling of monthly inflows of Demirkopru Dam, which is located inthe Gediz basin, was presented. The LM-ANN results were also compared with gradientdescentwith momentum rate algorithm based FFBP model (GDM-ANN). When thestatistics of the long-term and also seasonal-term outputs are compared, it can be seen thatthe LM-ANN model that has been developed, is more sensitive for prediction of theinflows. In addition, LM-ANN approach can be used for modeling of other hydrologicalcomponents in terms of a rapid assessment and its robustness.

Umut Okkan

2011-01-01

182

Multifractal analysis of perceptron learning with errors

Random input patterns induce a partition of the coupling space of a perceptron into cells labeled by their output sequences. Learning some data with a maximal error rate leads to clusters of neighboring cells. By analyzing the internal structure of these clusters with the formalism of multifractals, we can handle different storage and generalization tasks for lazy students and absent-minded teachers within one unified approach. The results also allow some conclusions on the spatial distribution of cells.

Weigt, M

1998-01-01

183

Intelligent control of HVAC systems. Part II: perceptron performance analysis

Directory of Open Access Journals (Sweden)

Full Text Available This is the second part of a paper on intelligent type control of Heating, Ventilating, and Air-Conditioning (HVAC) systems. The whole study proposes a unified approach in the design of intelligent control for such systems, to ensure high energy efficiency and air quality improving. In the first part of the study it is considered as benchmark system a single thermal space HVAC system, for which it is assigned a mathematical model of the controlled system and a mathematical model(algorithm) of intelligent control synthesis. The conception of the intelligent control is of switching type, between a simple neural network, a perceptron, which aims to decrease (optimize) a cost index,and a fuzzy logic component, having supervisory antisaturating role for neuro-control. Based on numerical simulations, this Part II focuses on the analysis of system operation in the presence only ofthe neural control component. Working of the entire neuro-fuzzy system will be reported in a third part of the study.

Ioan URSU; Ilinca NASTASE; Sorin CALUIANU; Andreea IFTENE; George TECUCEANU; Adrian TOADER

2013-01-01

184

Directory of Open Access Journals (Sweden)

Full Text Available Introduction: We aimed to develop a classification method to discriminate ventricular septal defect and atrial septal defect by using severalhemodynamic parameters.Patients and Methods: Forty three patients (30 atrial septal defect, 13 ventricular septal defect; 26 female, 17 male) with documentedhemodynamic parameters via cardiac catheterization are included to study. Such parameters as blood pressure values of different areas,gender, age and Qp/Qs ratios are used for classification. Parameters, we used in classification are determined by divergence analysismethod. Those parameters are; i) pulmonary artery diastolic pressure, ii) Qp/Qs ratio, iii) right atrium pressure, iv) age, v) pulmonary arterysystolic pressure, vi) left ventricular sistolic pressure, vii) aorta mean pressure, viii) left ventricular diastolic pressure, ix) aorta diastolicpressure, x) aorta systolic pressure. Those parameters detected from our study population, are uploaded to multi-layered artificial neuralnetwork and the network was trained by genetic algorithm.Results: Trained cluster consists of 14 factors (7 atrial septal defect and 7 ventricular septal defect). Overall success ratio is 79.2%, andwith a proper instruction of artificial neural network this ratio increases up to 89%.Conclusion: Parameters, belonging to artificial neural network, which are needed to be detected by the investigator in classical methods,can easily be detected with the help of genetic algorithms. During the instruction of artificial neural network by genetic algorithms, boththe topology of network and factors of network can be determined. During the test stage, elements, not included in instruction cluster, areassumed as in test cluster, and as a result of this study, we observed that multi-layered artificial neural network can be instructed properly,and neural network is a successful method for aimed classification.

Mustafa Y?ld?z; Ayhan Yüksel; Mehmet Korürek; Ahmet Ça?r? Aykan; Banu ?ahin Y?ld?z; Alparslan ?ahin; Hakan Hasdemir; Mehmet Özkan

2012-01-01

185

GENES IV: A Bit-Serial Processing Element for a Multi-Model Neural-Network Accelerator

UK PubMed Central (United Kingdom)

Reprinted from Luigi Dadda and Benjamin Wah, editors, Proceedings of the International Conferenceon Application-Specific Array Processors, pages 345 -- 356, Venice, Italy, October 1993. Euromicro,IEEE, IEEE Computer Society Press. Copyright c fl 1993 by IEEE.A systolic array of dedicated processing elements (PEs) is presented as the heart of amulti-model neural-network accelerator. The instruction set of the PEs allows the implementationof several widely-used neural models, including multi-layer Perceptrons with thebackpropagation learning rule and Kohonen feature maps. Each PE holds an element of thesynaptic weight matrix. An instantaneous swapping mechanism of the weight matrix allowsthe implementation of neural networks larger than the physical PE array. A systolicallyflowinginstruction accompanies each input vector propagating in the array. This avoids theneed of emptying and refilling the array when the operating mode of the array is changed.Both the GENES IV chip, co...

Paolo Ienne; Marc A. Viredaz

186

UK PubMed Central (United Kingdom)

Electroactive scaffolds that are passively conductive and able to transmit applied electrical stimuli are of increasing importance for neural tissue engineering. Here, we report a process of rendering both 2D and 3D polymer scaffolds electrically conducting, while also enhancing neuron attachment. Graphene-heparin/poly-l-lysine polyelectrolytes were assembled via layer-by-layer (LbL) deposition onto 2D surfaces and 3D electrospun nanofibers. The employed LbL coating technique in this work enables the electro- and biofunctionalization of complex 3D scaffold structures. LbL assembly was characterized by a steady mass increase during the in situ deposition process in 2D, with regular step changes in hydrophobicity. Uniform coverage of the graphene/polyelectrolyte coatings was also achieved on nanofibers, with hydrodynamic flow and post-thermal annealing playing an important role in controlling sheet resistance of 2D surfaces and nanofibers. Cell culture experiments showed that both 2D and 3D graphene-PEMs supported neuron cell adhesion and neurite outgrowth, with no appreciable cell death. This electroactive scaffold modification may therefore assist in neuronal regeneration, for creating functional and biocompatible polymer scaffolds for electrical entrainment or biosensing applications.

Zhou K; Thouas GA; Bernard CC; Nisbet DR; Finkelstein DI; Li D; Forsythe JS

2012-09-01

187

PREDICTION OF BOD AND COD OF A REFINERY WASTEWATER USING MULTILAYER ARTIFICIAL NEURAL NETWORKS

Directory of Open Access Journals (Sweden)

Full Text Available In the recent past, artificial neural networks (ANNs) have shown the ability to learn and capture non-linear static or dynamic behaviour among variables based on the given set of data. Since the knowledge of internal procedure is not necessary, the modelling can take place with minimum previous knowledge about the process through proper training of the network. In the present study, 12 ANN based models were proposed to predict the Biochemical Oxygen Demand (BOD5) and Chemical Oxygen Demand (COD) concentrations of wastewater generated from the effluent treatment plant of a petrochemical industry. By employing the standard back error propagation (BEP) algorithm, the network was trained with 103 data points for water quality indices such as Total Suspended Solids (TSS), Total Dissolved Solids (TDS), Phenol concentration, Ammoniacal Nitrogen (AMN), Total Organic Carbon (TOC) and Kjeldahl’s Nitrogen (KJN) to predict BOD and COD. After appropriate training, the network was tested with a separate test data and the best model was chosen based on the sum square error (training) and percentage average relative error (% ARE for testing). The results from this study reveal that ANNs can be accurate and efficacious in predicting unknown concentrations of water quality parameters through its versatile training process.

Eldon Raj Rene; M. B. Saidutta

2008-01-01

188

Incorporating fuzzy membership functions into the perceptron algorithm.

UK PubMed Central (United Kingdom)

The perceptron algorithm, one of the class of gradient descent techniques, has been widely used in pattern recognition to determine linear decision boundaries. While this algorithm is guaranteed to converge to a separating hyperplane if the data are linearly separable, it exhibits erratic behavior if the data are not linearly separable. Fuzzy set theory is introduced into the perceptron algorithm to produce a ``fuzzy algorithm'' which ameliorates the convergence problem in the nonseparable case. It is shown that the fuzzy perceptron, like its crisp counterpart, converges in the separable case. A method of generating membership functions is developed, and experimental results comparing the crisp to the fuzzy perceptron are presented.

Keller JM; Hunt DJ

1985-06-01

189

Incorporating fuzzy membership functions into the perceptron algorithm.

The perceptron algorithm, one of the class of gradient descent techniques, has been widely used in pattern recognition to determine linear decision boundaries. While this algorithm is guaranteed to converge to a separating hyperplane if the data are linearly separable, it exhibits erratic behavior if the data are not linearly separable. Fuzzy set theory is introduced into the perceptron algorithm to produce a ``fuzzy algorithm'' which ameliorates the convergence problem in the nonseparable case. It is shown that the fuzzy perceptron, like its crisp counterpart, converges in the separable case. A method of generating membership functions is developed, and experimental results comparing the crisp to the fuzzy perceptron are presented. PMID:21869307

Keller, J M; Hunt, D J

1985-06-01

190

Data-driven automated acoustic analysis of human infant vocalizations using neural network tools.

UK PubMed Central (United Kingdom)

Acoustic analysis of infant vocalizations has typically employed traditional acoustic measures drawn from adult speech acoustics, such as f(0), duration, formant frequencies, amplitude, and pitch perturbation. Here an alternative and complementary method is proposed in which data-derived spectrographic features are central. 1-s-long spectrograms of vocalizations produced by six infants recorded longitudinally between ages 3 and 11 months are analyzed using a neural network consisting of a self-organizing map and a single-layer perceptron. The self-organizing map acquires a set of holistic, data-derived spectrographic receptive fields. The single-layer perceptron receives self-organizing map activations as input and is trained to classify utterances into prelinguistic phonatory categories (squeal, vocant, or growl), identify the ages at which they were produced, and identify the individuals who produced them. Classification performance was significantly better than chance for all three classification tasks. Performance is compared to another popular architecture, the fully supervised multilayer perceptron. In addition, the network's weights and patterns of activation are explored from several angles, for example, through traditional acoustic measurements of the network's receptive fields. Results support the use of this and related tools for deriving holistic acoustic features directly from infant vocalization data and for the automatic classification of infant vocalizations.

Warlaumont AS; Oller DK; Buder EH; Dale R; Kozma R

2010-04-01

191

A Multi-threaded Neural Network approach for Steganography

Directory of Open Access Journals (Sweden)

Full Text Available Steganographic techniques are being applied across a broad set of different modern digital technologies. Steganography is basically the process of hiding one medium of communication (Text, Sound, and Image) within another. It can work on JPEG 2000 compressed images & stir Mark images. The steganographic method will be used for internet/network security, watermarking and so on. „Steganalysis? is the field of detecting the covert messages. The new methods of steganalysis are based on neural network to get the statistics and features of images to identify the underlying hidden data. We first extract the features of image embedded information, and then input them into neural network to get the output. Experiment result indicates this method is valid in „Steganalysis?. Almost all steganalysis consist of hand-crafted tests or human visual inspection to detect whether a file contains a message hidden by a specific steganography algorithm. The neural network in images is used to overcome the hurdles by hiding the data indirectly into graphical image using neural network algorithm to get cipher bits. The generated cipher bits are then placed in the least significant bit position of the carrier image. A Multi threaded back propagation algorithm is used in the neural network. Multi threading in the back propagation algorithm increases the speed of processing in the neural layers and thereby significantly increases the efficiency. The XOR propagation network model is used which acts as a multilayer perceptron

Srinivasan SP

2011-01-01

192

Energy Technology Data Exchange (ETDEWEB)

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)

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

193

Evaluation of artificial neural network techniques for flow forecasting in the River Yangtze, China

Directory of Open Access Journals (Sweden)

Full Text Available While engineers have been quantifying rainfall-runoff processes since the mid-19th century, it is only in the last decade that artificial neural network models have been applied to the same task. This paper evaluates two neural networks in this context: the popular multilayer perceptron (MLP), and the radial basis function network (RBF). Using six-hourly rainfall-runoff data for the River Yangtze at Yichang (upstream of the Three Gorges Dam) for the period 1991 to 1993, it is shown that both neural network types can simulate river flows beyond the range of the training set. In addition, an evaluation of alternative RBF transfer functions demonstrates that the popular Gaussian function, often used in RBF networks, is not necessarily the ‘best’ function to use for river flow forecasting. Comparisons are also made between these neural networks and conventional statistical techniques; stepwise multiple linear regression, auto regressive moving average models and a zero order forecasting approach. Keywords: Artificial neural network, multilayer perception, radial basis function, flood forecasting

C. W. Dawson; C. Harpham; R. L. Wilby; Y. Chen

2002-01-01

194

Energy Technology Data Exchange (ETDEWEB)

Traditional neural networks like multi-layered perceptrons (MLP) use example patterns, i.e., pairs of real-valued observation vectors, ({rvec x},{rvec y}), to approximate function {cflx f}({rvec x}) = {rvec y}. To determine the parameters of the approximation, a special version of the gradient descent method called back-propagation is widely used. In many situations, observations of the input and output variables are not precise; instead, we usually have intervals of possible values. The imprecision could be due to the limited accuracy of the measuring instrument or could reflect genuine uncertainty in the observed variables. In such situation input and output data consist of mixed data types; intervals and precise numbers. Function approximation in interval domains is considered in this paper. We discuss a modification of the classical backpropagation learning algorithm to interval domains. Results are presented with simple examples demonstrating few properties of nonlinear interval mapping as noise resistance and finding set of solutions to the function approximation problem.

Patil, R.B.

1995-05-01

195

DEFF Research Database (Denmark)

The purpose of this study was to create an empirical model for assessing the landslide risk potential at Savadkouh Azad University, which is located in the rural surroundings of Savadkouh, about 5 km from the city of Pol-Sefid in northern Iran. The soil longitudinal profile of the city of Babol, located 25 km from the Caspian Sea, also was predicted with an artificial neural network (ANN). A multilayer perceptron neural network model was applied to the landslide area and was used to analyze specific elements in the study area that contributed to previous landsliding events. The ANN models were trained with geotechnical data obtained from an investigation of the study area. The quality of the modeling was improved further by the application of some controlling techniques involved in ANN. The observed >90% overall accuracy produced by the ANN technique in both cases is promising for future studies in landslide susceptibility zonation.

Farrokhzad, F.; Barari, Amin

2011-01-01

196

Bayesian Inference using Neural Net Likelihood Models for Protein Secondary Structure Prediction

Directory of Open Access Journals (Sweden)

Full Text Available Several techniques such as Neural Networks, Genetic Algorithms, Decision Trees and other statistical or heuristic methods have been used to approach the complex non-linear task of predicting Alpha-helicies, Beta-sheets and Turns of a proteins secondary structure in the past. This project introduces a new machine learning method by using an offline trained Multilayered Perceptrons (MLP) as the likelihood models within a Bayesian Inference framework to predict secondary structures proteins. Varying window sizes are used to extract neighboring amino acid information and passed back and forth between the Neural Net models and the Bayesian Inference process until there is a convergence of the posterior secondary structure probability.

Seong-Gon Kim; Yong-Gi Kim

2011-01-01

197

A hybrid Evolutionary Functional Link Artificial Neural Network for Data mining and Classification

Directory of Open Access Journals (Sweden)

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)

Faissal MILI; Manel HAMDI

2012-01-01

198

Prediction of slope stability using artificial neural network (case study: Noabad, Mazandaran, Iran)

International Nuclear Information System (INIS)

[en] Investigations of failures of soil masses are subjects touching both geology and engineering. These investigations call the joint efforts of engineering geologists and geotechnical engineers. Geotechnical engineers have to pay particular attention to geology, ground water, and shear strength of soils in assessing slope stability. Artificial neural networks (ANNs) are very sophisticated modeling techniques, capable of modeling extremely complex functions. In particular, neural networks are nonlinear. In this research, with respect to the above advantages, ANN systems consisting of multilayer perceptron networks are developed to predict slope stability in a specified location, based on the available site investigation data from Noabad, Mazandaran, Iran. Several important parameters, including total stress, effective stress, angle of slope, coefficient of cohesion, internal friction angle, and horizontal coefficient of earthquake, were used as the input parameters, while the slope stability was the output parameter. The results are compared with the classical methods of limit equilibrium to check the ANN model's validity. (author)

2009-01-01

199

Foreground removal from Planck Sky Model temperature maps using a MLP neural network

DEFF Research Database (Denmark)

Unfortunately, the Cosmic Microwave Background (CMB) radiation is contaminated by emission originating in the Milky Way (synchrotron, free-free and dust emission). Since the cosmological information is statistically in nature, it is essential to remove this foreground emission and leave the CMB with no systematic errors. To demonstrate the feasibility of a simple multilayer perceptron (MLP) neural network for extracting the CMB temperature signal, we have analyzed a specific data set, namely the Planck Sky Model maps, developed for evaluation of different component separation methods before including them in the Planck data analysis pipeline. It is found that a MLP neural network can provide a CMB map of about 80% of the sky to a very high degree uncorrelated with the foreground components. Also the derived power spectrum shows little evidence for systematic errors.

NØrgaard-Nielsen, Hans Ulrik; Hebert, K.

2009-01-01

200

Neural network model for a reactor subsystem using real time data

International Nuclear Information System (INIS)

Modern nuclear power plant is a very complex arrangement of machinery consisting of huge number of control and support systems. In real time it is possible to implement intelligent systems in the form of neural network, data mining, expert system etc. for modeling the power plant. This paper describes the development of an artificial neural network model for intermediate heat exchanger subsystem of fast breeder test reactor. Multilayer perceptron network using back propagation algorithm is implemented for training the safety critical, safety related real time data. It takes in to account the weight correction method. The results indicate a very good convergence of the algorithm. The model can be used as an operator support system for predictive measures of various parameters of the reactor subsystems. (author)

2010-01-01

201

Prediction of Force Measurements of a Microbend Sensor Based on an Artificial Neural Network

Directory of Open Access Journals (Sweden)

Full Text Available Artificial neural network (ANN) based prediction of the response of a microbend fiber optic sensor is presented. To the best of our knowledge no similar work has been previously reported in the literature. Parallel corrugated plates with three deformation cycles, 6 mm thickness of the spacer material and 16 mm mechanical periodicity between deformations were used in the microbend sensor. Multilayer Perceptron (MLP) with different training algorithms, Radial Basis Function (RBF) network and General Regression Neural Network (GRNN) are used as ANN models in this work. All of these models can predict the sensor responses with considerable errors. RBF has the best performance with the smallest mean square error (MSE) values of training and test results. Among the MLP algorithms and GRNN the Levenberg-Marquardt algorithm has good results. These models successfully predict the sensor responses, hence ANNs can be used as useful tool in the design of more robust fiber optic sensors.

Hasan S. Efendioglu; Tulay Yildirim; Kemal Fidanboylu

2009-01-01

202

Rolling bearing fault diagnostics using artificial neural networks based on Laplace wavelet analysis

Directory of Open Access Journals (Sweden)

Full Text Available A study is presented to explore the performance of bearing fault diagnosis using three types of artificial neural networks (ANNs), namely, Multilayer Perceptron (MLP) with BP algorithm, Radial Basis Function (RBF) network, and Probabilistic Neural Network (PNN). The time domain vibration signals of a rotating machine with normal and defective bearings are preprocessed using Lapalce wavelet analysis technique for feature extraction. The extracted features are used as inputs to all three ANN classifiers: MLP, RBF, and PNN for four-class: Healthy, outer, inner and roller faults identification. The procedure is illustrated using the experimental vibration data of a rotating machine with different bearing faults. The results show the relative effectiveness of three classifiers in detection of the bearing condition with different learning speeds and success rates.

Khalid F. Al-Raheem; Waleed Abdul-Karem

2010-01-01

203

Time-scale invariance as an emergent property in a perceptron with realistic, noisy neurons.

UK PubMed Central (United Kingdom)

In most species, interval timing is time-scale invariant: errors in time estimation scale up linearly with the estimated duration. In mammals, time-scale invariance is ubiquitous over behavioral, lesion, and pharmacological manipulations. For example, dopaminergic drugs induce an immediate, whereas cholinergic drugs induce a gradual, scalar change in timing. Behavioral theories posit that time-scale invariance derives from particular computations, rules, or coding schemes. In contrast, we discuss a simple neural circuit, the perceptron, whose output neurons fire in a clockwise fashion based on the pattern of coincidental activation of its input neurons. We show numerically that time-scale invariance emerges spontaneously in a perceptron with realistic neurons, in the presence of noise. Under the assumption that dopaminergic drugs modulate the firing of input neurons, and that cholinergic drugs modulate the memory representation of the criterion time, we show that a perceptron with realistic neurons reproduces the pharmacological clock and memory patterns, and their time-scale invariance, in the presence of noise. These results suggest that rather than being a signature of higher order cognitive processes or specific computations related to timing, time-scale invariance may spontaneously emerge in a massively connected brain from the intrinsic noise of neurons and circuits, thus providing the simplest explanation for the ubiquity of scale invariance of interval timing.

Buhusi CV; Oprisan SA

2013-05-01

204

Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia

Directory of Open Access Journals (Sweden)

Full Text Available Rainfall is considered as one of the major component of the hydrological process, it takes significant part of evaluating drought and flooding events. Therefore, it is important to have accurate model for rainfall forecasting. Recently, several data-driven modeling approaches have been investigated to perform such forecasting task such as Multi-Layer Perceptron Neural Networks (MLP-NN). In fact, the rainfall time series modeling involves an important temporal dimension. On the other hand, the classical MLP-NN is a static and memoryless network architecture that is effective for complex nonlinear static mapping. This research focuses on investigating the potential of introducing a neural network that could address the temporal relationships of the rainfall series. Two different static neural networks and one dynamic neural network namely; Multi-Layer Peceptron Neural network (MLP-NN), Radial Basis Function Neural Network (RBFNN) and Input Delay Neural Network (IDNN), respectively, have been examined in this study. Those models had been developed for two time horizon in monthly and weekly rainfall basis forecasting at Klang River, Malaysia. Data collected over 12 yr (1997–2008) on weekly basis and 22 yr (1987–2008) for monthly basis were used to develop and examine the performance of the proposed models. Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static and dynamic neural network. Results showed that MLP-NN neural network model able to follow the similar trend of the actual rainfall, yet it still relatively poor. RBFNN model achieved better accuracy over the MLP-NN model. Moreover, the forecasting accuracy of the IDNN model outperformed during training and testing stage which prove a consistent level of accuracy with seen and unseen data. Furthermore, the IDNN significantly enhance the forecasting accuracy if compared with the other static neural network model as they could memorize the sequential or time varying patterns.

A. El-Shafie; A. Noureldin; M. R. Taha; A. Hussain

2011-01-01

205

Hybrid Learning Algorithm in Neural Network System for Enzyme Classification

Directory of Open Access Journals (Sweden)

Full Text Available Nucleic acid and protein sequences store a wealth of informationwhich ultimately determines their functions and characteristics.Protein sequences classification deals with the assignment ofsequences to known categories based on homology detectionproperties. In this paper, we developed a hybrid learning algorithm inneural network system called Neural Network Enzyme Classification(NNEC) to classify an enzyme found in Protein Data Bank (PDB) to agiven family of enzymes. NNEC was developed based on MultilayerPerceptron with hybrid learning algorithm combining the geneticalgorithm (GA) and Backpropagation (BP), where one of them acts asan operator in the other. Here, BP is used as a mutation-like-operatorof the general GA search template. The proposed hybrid model wastested with different topologies of network architecture, especially indetermining the number of hidden nodes. The precision results arequite promising in classifying the enzyme accordingly.

Mohd Haniff Osman; Choong-Yeun Liong; Ishak Hashim

2010-01-01

206

Handwritten Farsi Character Recognition using Artificial Neural Network

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...

Ahangar, Reza Gharoie

2009-01-01

207

Artificial neural networks for load flow and external equivalents studies

Energy Technology Data Exchange (ETDEWEB)

In this paper an artificial neural network (ANN) based methodology is proposed for (a) solving the basic load flow, (b) solving the load flow considering the reactive power limits of generation (PV) buses, (c) determining a good quality load flow starting point for ill-conditioned systems, and (d) computing static external equivalent circuits. An analysis of the input data required as well as the ANN architecture is presented. A multilayer perceptron trained with the Levenberg-Marquardt second order method is used. The proposed methodology was tested with the IEEE 30- and 57-bus, and an ill-conditioned 11-bus system. Normal operating conditions (base case) and several contingency situations including different load and generation scenarios have been considered. Simulation results show the excellent performance of the ANN for solving problems (a)-(d). (author)

Mueller, Heloisa H.; Castro, Carlos A. [University of Campinas, DSEE/FEEC/UNICAMP, C.P. 6101, 13083-852 Campinas, SP (Brazil); Rider, Marcos J. [Universidade Estadual Paulista, DEE/FEIS/UNESP, C.P. 31, 15385-000 ILha Solteira, SP (Brazil)

2010-09-15

208

gamma/(pi)(sup 0) separation in shower maximum detector using neural network algorithm.

Procedure of gamma/pion neutral separation based on a multilayered perceptron algorithm are presented. Recognition capacities of these procedures and one of the CDF separation methods have been examined. The procedure were tested with the simulated data f...

N. G. Minaev

1994-01-01

209

Directory of Open Access Journals (Sweden)

Full Text Available An electrocardiogram (ECG) beat classification scheme based on multiple signal classification (MUSIC) algorithm, morphological descriptors, and neural networks is proposed for discriminating nine ECG beat types. These are normal, fusion of ventricular and normal, fusion of paced and normal, left bundle branch block, right bundle branch block, premature ventricular concentration, atrial premature contraction, paced beat, and ventricular flutter. ECG signal samples from MIT-BIH arrhythmia database are used to evaluate the scheme. MUSIC algorithm is used to calculate pseudospectrum of ECG signals. The low-frequency samples are picked to have the most valuable heartbeat information. These samples along with two morphological descriptors, which deliver the characteristics and features of all parts of the heart, form an input feature vector. This vector is used for the initial training of a classifier neural network. The neural network is designed to have nine sample outputs which constitute the nine beat types. Two neural network schemes, namely multilayered perceptron (MLP) neural network and a probabilistic neural network (PNN), are employed. The experimental results achieved a promising accuracy of 99.03% for classifying the beat types using MLP neural network. In addition, our scheme recognizes NORMAL class with 100% accuracy and never misclassifies any other classes as NORMAL.

Ahmad R. Naghsh-Nilchi; A. Rahim Kadkhodamohammadi

2009-01-01

210

Large Margin Classification Using the Perceptron Algorithm

UK PubMed Central (United Kingdom)

We introduce and analyze a new algorithm for linear classification which combines Rosenblatt's perceptron algorithm with Helmbold and Warmuth's leave-one-out method. Like Vapnik's maximal-margin classifier, our algorithm takes advantage of data that are linearly separablewith large margins. Compared to Vapnik's algorithm, however, ours is much simplerto implement, and much more efficient in terms of computation time. We also show that ouralgorithm can be efficiently used in very high dimensional spaces using kernel functions. Weperformed some experiments using our algorithm, and some variants of it, for classifying imagesof handwritten digits. The performance of our algorithm is close to, but not as good as, theperformance of maximal-margin classifiers on the same problem, while saving significantly oncomputation time and programming effort.1 IntroductionOne of the most influential developments in the theory of machine learning in the last few yearsis Vapnik's work on supp...

Yoav Freund; Robert E. Schapire

211

Learning from correlated patterns by simple perceptrons

Energy Technology Data Exchange (ETDEWEB)

Learning behavior of simple perceptrons is analyzed for a teacher-student scenario in which output labels are provided by a teacher network for a set of possibly correlated input patterns, and such that the teacher and student networks are of the same type. Our main concern is the effect of statistical correlations among the input patterns on learning performance. For this purpose, we extend to the teacher-student scenario a methodology for analyzing randomly labeled patterns recently developed in Shinzato and Kabashima 2008 J. Phys. A: Math. Theor. 41 324013. This methodology is used for analyzing situations in which orthogonality of the input patterns is enhanced in order to optimize the learning performance.

Shinzato, Takashi; Kabashima, Yoshiyuki [Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, Yokohama 226-8502 (Japan)], E-mail: shinzato@sp.dis.titech.ac.jp, E-mail: kaba@dis.titech.ac.jp

2009-01-09

212

Statistical Mechanics of Node-Perturbation Learning for Nonlinear Perceptron

Node-perturbation learning is a type of statistical gradient descent algorithm that can be applied to problems where the objective function is not explicitly formulated, including reinforcement learning. Node-perturbation learning with M linear perceptrons has previously been analyzed using the methods of statistical mechanics. It was shown that cross-talk noise, which originates from the error of the other outputs, increases the generalization error as the number of outputs increases. On the other hand, a nonlinear perceptron has several advantages over a linear perceptron, such as the ability to use nonlinear outputs, learnability, storage capacity, and so forth. However, node-perturbation for a nonlinear perceptron has yet to be analyzed theoretically. In this paper, we derive a learning rule of node-perturbation learning for a nonlinear perceptron within the framework of REINFORCE learning and analyze the learning behavior by using statistical mechanical methods. From the results, we found that the signal and cross-talk terms of the order parameter Q have different forms for a nonlinear perceptron. Moreover, the increase in the generalization error with increasing number of outputs is less than for a linear perceptron.

Hara, Kazuyuki; Katahira, Kentaro; Okanoya, Kazuo; Okada, Masato

2013-05-01

213

In the present research, possibility of predicting average summer-monsoon rainfall over India has been analyzed through Artificial Neural Network models. In formulating the Artificial Neural Network based predictive model, three layered networks have been constructed with sigmoid non-linearity. The models under study are different in the number of hidden neurons. After a thorough training and test procedure, neural net with three nodes in the hidden layer is found to be the best predictive model.

Chattopadhyay, S

2006-01-01

214

Scientific Electronic Library Online (English)

Full Text Available Abstract in spanish El presente artículo describe la implementación de un sistema de predicción de fallos en redes LAN (fallos de timeout y rechazo en las conexiones), utilizando redes neuronales artificiales Perceptrón Multicapa. Se describe como se implementó el sistema, las pruebas realizadas para la selección de los parámetros propios de la red neuronal, como del algoritmo de entrenamiento y los resultados de evaluación obtenidos. Abstract in english The paper presents the implementation of a system for predicting failures in LAN (timeout failure and rejection of connections), using neural networks (multilayer perceptron). It describes the implementation of the system, experiments conducted for the selection of specific parameters of the neural network, training algorithm and evaluation results.

García, Gustavo A.; Salcedo, Octavio

2010-06-01

215

Directory of Open Access Journals (Sweden)

Full Text Available In this study, the use of artificial neural network (ANN) based model, multi-layer perceptron (MLP) network, to compute the transfer capabilities in a multi-area power system was explored. The input for the ANN is load status and the outputs are the transfer capability among the system areas, voltage magnitudes and voltage angles at concerned buses of the areas under consideration. The repeated power flow (RPF) method is used in this paper for calculating the power transfer capability, voltage magnitudes and voltage angles necessary for the generation of input-output patterns for training the proposed MLP neural network. Preliminary investigations on a three area 30-bus system reveal that the proposed model is computationally faster than the conventional method.

Palukuru NAGENDRA; Sunita Halder NEE DEY; Tanaya DUTTA

2010-01-01

216

Selective Voting for Perceptron-like Online Learning

UK PubMed Central (United Kingdom)

The voting technique, which combines the predictions of several classifiers, can improve the generalization performance significantly by increasing the fraction of training examples with large margins. ROMMA (the Relaxed Online Maximum Margin Algorithm) is a perceptron-like online learning algorithm to approximate the optimal margin classifier, and aggressive ROMMA updates its prediction vectors whenever the output produced by the current prediction vector does not exceed the wanted threshold instead of just after a mistake. Alternatively, the voted perceptron algorithm improves the perceptron algorithm significantly based on a conversion from online learning to batch learning. However, the same voting method worsens the performance of aggressive ROMMA. In this paper, we describe a new voting method, called selective voting, for perceptron-like online learning algorithms. We provide theoretical and experimental evidence that selective voting is better than full voting, and the performance...

Yi Li

217

The Curse of Dimensionality and the Perceptron Algorithm

UK PubMed Central (United Kingdom)

We give an adversary strategy that forces the Perceptron algorithmto make (N Gamma k + 1)=2 mistakes when learning k-literal disjunctions overN variables. Experimentally we see that even for simple random data,the number of mistakes made by the Perceptron algorithm grows almostlinearly with N , even if the number k of relevant variable remains a smallconstant. Thus, the Perceptron algorithm suffers from the curse of dimensionalityeven when the target is extremely simple and almost all ofthe dimensions are irrelevant. In contrast, Littlestone's algorithm Winnowmakes at most O(k log N ) mistakes for the same problem. Both algorithmsuse linear threshold functions as their hypotheses. However, Winnow doesmultiplicative updates to its weight vector instead of the additive updatesof the Perceptron algorithm.Introduction 31 IntroductionThis paper addresses the familiar problem of predicting with a linear thresholdfunction. The instances are N-dimensional real vect...

Jyrki Kivinen; Manfred K. Warmuth

218

A canonical ensemble approach to graded-response perceptrons

Perceptrons with graded input-output relations and a limited output precision are studied within the Gardner-Derrida canonical ensemble approach. Soft non- negative error measures are introduced allowing for extended retrieval properties. In particular, the performance of these systems for a linear and quadratic error measure, corresponding to the perceptron respectively the adaline learning algorithm, is compared with the performance for a rigid error measure, simply counting the number of errors. Replica-symmetry-breaking effects are evaluated.

Bollé, D

1999-01-01

219

Catheter-manometer system damped blood pressures detected by neural nets.

UK PubMed Central (United Kingdom)

Degraded catheter-manometer systems cause distortion of blood pressure waveforms, often leading to erroneously resonant or damped waveforms, requiring waveforms quality control. We have tried multilayer perceptron back-propagation trained neural nets of varying architecture to detect damping on sets of normal and artificially damped brachial arterial pressure waves. A second-order digital simulation of a catheter-manometer system is used to cause waveform distortion. Each beat in the waveforms is represented by an 11 parameter input vector. From a group of normotensive or (borderline) hypertensive subjects, pressure waves are used to statistically test and train the neural nets. For each patient and category 5-10 waves are available. The best neural nets correctly classify about 75-85% of the individual beats as either adequate or damped. Using a single majority vote classification per subject per damped or adequate situation, the best neural nets correctly classify at least 16 of the 18 situations in nine test subjects (binomial P = 0.001). More importantly, these neural nets can always detect damping before clinically relevant parameters such as systolic pressure and computed stroke volume are reduced by more than 2%. Neural nets seem remarkably well adapted to solving such subtle problems as detecting a slight damping of arterial pressure waves before it affects waveforms to a clinically relevant degree.

Prentza A; Wesseling KH

1995-07-01

220

UK PubMed Central (United Kingdom)

Fourier transform infrared spectroscopy (FTIR) and artificial neural networks (ANN's) were used to identify species of Propionibacteria strains. The aim of the study was to improve the methodology to identify species of Propionibacteria strains, in which the differentiation index D, calculated based on Pearson's correlation and cluster analyses were used to describe the correlation between the Fourier transform infrared spectra and bacteria as molecular systems brought unsatisfactory results. More advanced statistical methods of identification of the FTIR spectra with application of artificial neural networks (ANN's) were used. In this experiment, the FTIR spectra of Propionibacteria strains stored in the library were used to develop artificial neural networks for their identification. Several multilayer perceptrons (MLP) and probabilistic neural networks (PNN) were tested. The practical value of selected artificial neural networks was assessed based on identification results of spectra of 9 reference strains and 28 isolates. To verify results of isolates identification, the PCR based method with the pairs of species-specific primers was used. The use of artificial neural networks in FTIR spectral analyses as the most advanced chemometric method supported correct identification of 93% bacteria of the genus Propionibacterium to the species level.

Dziuba B

2013-01-01

221

Applying Neural Network Architecture for Inverse Kinematics Problem in Robotics

Directory of Open Access Journals (Sweden)

Full Text Available One of the most important problems in robot kinematics and control is, finding the solution of Inverse Kinematics. Inverse kinematics computation has been one of the main problems in robotics research. As the Complexity of robot increases, obtaining the inverse kinematics is difficult and computationally expensive. Traditional methods such as geometric, iterative and algebraic are inadequate if the joint structure of the manipulator is more complex. As alternative approaches, neural networks and optimal search methods have been widely used for inverse kinematics modeling and control in robotics This paper proposes neural network architecture that consists of 6 sub-neural networks to solve the inverse kinematics problem for robotics manipulators with 2 or higher degrees of freedom. The neural networks utilized are multi-layered perceptron (MLP) with a back-propagation training algorithm. This approach will reduce the complexity of the algorithm and calculation (matrix inversion) faced when using the Inverse Geometric Models implementation (IGM) in robotics. The obtained results are presented and analyzed in order to prove the efficiency of the proposed approach.

Bassam Daya; Shadi Khawandi; Mohamed Akoum

2010-01-01

222

A NARX Neural Network Algorithm for Video Traffic Prediction

Directory of Open Access Journals (Sweden)

Full Text Available Multimedia services like video on demand, video broadcasting or videoconferencing became a major part of the internet network traffic. The bursty characteristics of the video traffic make it difficult to fulfill the Quality of Service (QoS) of the specificmultimedia applications. Therefore it is important to utilize congestion control procedures. One of the procedures can be traffic prediction and dynamic bandwidth allocation. Neural networks belong to vastly used methods for traffic prediction. In this paper, wepresent the results of the Nonlinear AutoRegressive model with eXogeneous inputs (NARX) neural network for video traffic prediction and propose a new algorithm for video traffic prediction using neuralnetworks based on the separation of different frames. At first we briefly describe the characteristics of the video traffic. Then we introduce theoretical fundamentals of the NARX neural network. In the last section we present the results of video traffic predictionusing NARX neural network and the new algorithm for video traffic prediction. For comparison purposes the prediction using the multilayer perceptron and the adaptive autoregressive integrated moving average (ARIMA) is included.

PILKA Filip; ORAVEC Miloš

2011-01-01

223

A novel algorithm for tunable compression to within the precision of reproduction targets, or storage, is proposed. The new algorithm is termed the `Perceptron Algorithm', which utilises simple existing concepts in a novel way, has multiple immediate commercial application aspects as well as it opens up a multitude of fronts in computational science and technology. The aims of this paper are to present the concepts underlying the algorithm, observations by its application to some example cases, and the identification of a multitude of potential areas of applications such as: image compression by orders of magnitude, signal compression including sound as well, image analysis in a multilayered detailed analysis, pattern recognition and matching and rapid database searching (e.g. face recognition), motion analysis, biomedical applications e.g. in MRI and CAT scan image analysis and compression, as well as hints on the link of these ideas to the way how biological memory might work leading to new points of view i...

Vassiliadis, V S

2006-01-01

224

Directory of Open Access Journals (Sweden)

Full Text Available In this study different approaches based on multilayer perceptron neural networks are proposed and evaluated with the aim to retrieve tropospheric profiles by using GPS radio occultation data. We employed a data set of 445 occultations covering the land surface within the Tropics, split into desert and vegetation zone. The neural networks were trained with refractivity profiles as input computed from geometrical occultation parameters provided by the FORMOSAT-3/COSMIC satellites, while the targets were the dry and wet refractivity profiles and the dry pressure profiles obtained from the contemporary European Centre for Medium-Range Weather Forecast data. Such a new retrieval algorithm was chosen to solve the atmospheric profiling problem without the constraint of an independent knowledge of one atmospheric parameter at each GPS occultation.

Stefania Bonafoni; Fabrizio Pelliccia; Roberta Anniballe

2009-01-01

225

UK PubMed Central (United Kingdom)

Fouling and cleaning in heat exchangers are severe and costly issues in food processing. In this study, a new pattern recognition method for detecting fouling on stainless steel is presented. It is based on a combination of ultrasonic parameters and a multilayer perceptron feed forward neural network. Chosen acoustic parameters change significantly with fouling compared with tap water as standard. When fouling is present echo energy of echo 2 increases up to 73.84%, characteristic acoustic impedance shows 1.802±0.169 MRayl (17.54% higher than impedance for water), and logarithmic decrement seems to decrease. These acoustic parameters have been combined in an artificial neural network (ANN) with one hidden layer and back propagation algorithm to disentangle error proneness of single parameters and increase detection stability. After training with 400 and validation of 250 of 1000 samples, the ANN displayed an accuracy of 98.58% for fouling presence/absence.

Wallhäußer E; Hussein WB; Hussein MA; Hinrichs J; Becker TM

2011-04-01

226

Energy and Carbon Flux Coupling: Multi-ecosystem Comparisons Using Artificial Neural Network

Directory of Open Access Journals (Sweden)

Full Text Available A multi-ecosystems carbon flux simulation from energy fluxes is presented. A new statistical learning technique based on Artificial Neural Network (ANN) back propagation algorithm and multi-layer perceptron architecture was used in the CO2 simulation. Four input layers (net radiation, soil heat flux, sensible and latent heat flux) were used for training (calibration) and testing (verification) of model outputs. The 15-days half-hourly (grassland) and hourly (forest and cropland) micrometeorological data from eddy covariance observations of AmeriFlux towers were divided into training (5-days) and testing (10-days) sets. Results show that the ANN-based technique predicts CO2 flux with testing R2 values of 0.86, 0.75 and 0.94 for forest, grassland and cropland ecosystems, respectively. The technique is reliable and efficient to estimate regional or global CO2 fluxes from point measurements and understand the spatiotemporal budget of the CO2 fluxes.

Assefa M. Melesse; Rodney S. Hanley

2005-01-01

227

Viscosity Calculation at Moderate Pressure for Nonpolar Gases via Neural Network

Directory of Open Access Journals (Sweden)

Full Text Available A new method, based on Artificial Neural Networks (ANN) of Multi-Layer Perceptron (MLP) type, has been developed to estimate the viscosity at moderate pressure for pure nonpolar gases over a wide range of temperatures. An ANN was trained, using four physicochemical properties: Molecular weight (M), boiling point (Tb), critical Temperature (Tc) and critical Pressure (Pc) combined with absolute Temperature (T) as its inputs, to correlate and predict viscosity. A group of 52 nonpolar gases were used to train and test the performance of the ANN. The viscosity and input data for each individual gas was compiled on average at fifty different temperatures, ranging from the boiling points for each of the chosen gases to 1100 K. The maximum absolute error in viscosity, predicted by the ANN, was approximately 15%.

A. Bouzidi; S. Hanini; F. Souahi; B. Mohammedi; M. Touiza

2007-01-01

228

Functional Link Artificial Neural Network for Classification Task in Data Mining

Directory of Open Access Journals (Sweden)

Full Text Available In solving classification task of data mining, the traditional algorithm such as multi-layer perceptron takes longer time to optimize the weight vectors. At the same time, the complexity of the network increases as the number of layers increases. In this study, we have used Functional Link Artificial Neural Networks (FLANN) for the task of classification. In contrast to multiple layer networks, FLANN architecture uses a single layer feed-forward network. Using the functionally expanded features FLANN overcomes the non-linearity nature of problems, which is commonly encountered in single layer networks. The features like simplicity of designing the architecture and low-computational complexity of the networks encourages us to use it in data mining task. An extensive simulation study is presented to demonstrate the effectiveness of the classifier.

B. B. Misra; S. Dehuri

2007-01-01

229

Use of artificial neural networks for prognosis of charcoal prices in Minas Gerais

Directory of Open Access Journals (Sweden)

Full Text Available Energy is an important factor of economic growth and is critical to the stability of a nation. Charcoal is a renewable energy resource and is a fundamental input to the development of the Brazilian forest-based industry. The objective of this study is to provide a prognosis of the charcoal price series for the year 2007 by using Artificial Neural Networks. A feedforward multilayer perceptron ANN was used, the results of which are close to reality. The main findings are that: real prices of charcoal dropped between 1975 and 2000 and rose from the early 21st century; the ANN with two hidden layers was the architecture making the best prediction; the most effective learning rate was 0.99 and 600 cycles, representing the most satisfactory and accurate ANN training. Prediction using ANN was found to be more accurate when compared by the mean squared error to other studies modeling charcoal price series in Minas Gerais state.

Luiz Moreira Coelho Junior; José Luiz Pereira de Rezende; André Luiz França Batista; Adriano Ribeiro de Mendonça; Wilian Soares Lacerda

2013-01-01

230

Comparison of Neural Network and K-Nearest Neighbor Methods in Daily Flow Forecasting

Directory of Open Access Journals (Sweden)

Full Text Available This study illustrates the application of Multilayer perceptron (MLP) Neural Network (NN) for flow prediction of a Bakhtiari River. Since measurement of variables is time consuming and defining the efficient variable is essential for better performance of NN, alternative method of flow forecasting is needed. The K-Nearest Neighbor (K-NN) method which is a non-parametric regression methodology as indicated by the absence of any parameterized analytical function of the input-output relationship is used in this study. The implementation of each time series technique is investigated and the performances of the models are then compared. It is concluded that discharge in one day-ahead and Antecedent Precipitation Index (API) for seven days-ahead are the most important inputs and NN model has little better result than nearest neighbor method.

Alireza Eskandarinia; Hadi Nazarpour; Mehdi Teimouri; Mirkhalegh Z. Ahmadi

2010-01-01

231

Prediction of Atmospheric Pressure at Ground Level using Artificial Neural Network

Directory of Open Access Journals (Sweden)

Full Text Available Prediction of Atmospheric Pressure is one important and challenging task that needs lot of attention and study for analyzing atmospheric conditions. Advent of digital computers and development of data driven artificial intelligence approaches like Artificial Neural Networks (ANN) have helped in numerical prediction of pressure. However, very few works have been done till now in this area. The present study developed an ANN model based on the past observations of several meteorological parameters like temperature, humidity, air pressure and vapour pressure as an input for training the model. The novel architecture of the proposed model contains several multilayer perceptron network (MLP) to realize better performance. The model is enriched by analysis of alternative hybrid model of k-means clustering and MLP. The improvement of the performance in the prediction accuracy has been demonstrated by the automatic selection of the appropriate cluster

Angshuman Ray; Sourav Mukhopadhyay; Bimal Datta

2013-01-01

232

Fast converging minimum probability of error neural network receivers for DS-CDMA communications.

UK PubMed Central (United Kingdom)

We consider a multilayer perceptron neural network (NN) receiver architecture for the recovery of the information bits of a direct-sequence code-division-multiple-access (DS-CDMA) user. We develop a fast converging adaptive training algorithm that minimizes the bit-error rate (BER) at the output of the receiver. The adaptive algorithm has three key features: i) it incorporates the BER, i.e., the ultimate performance evaluation measure, directly into the learning process, ii) it utilizes constraints that are derived from the properties of the optimum single-user decision boundary for additive white Gaussian noise (AWGN) multiple-access channels, and iii) it embeds importance sampling (IS) principles directly into the receiver optimization process. Simulation studies illustrate the BER performance of the proposed scheme.

Matyjas JD; Psaromiligkos IN; Batalama SN; Medley MJ

2004-03-01

233

Fast converging minimum probability of error neural network receivers for DS-CDMA communications.

We consider a multilayer perceptron neural network (NN) receiver architecture for the recovery of the information bits of a direct-sequence code-division-multiple-access (DS-CDMA) user. We develop a fast converging adaptive training algorithm that minimizes the bit-error rate (BER) at the output of the receiver. The adaptive algorithm has three key features: i) it incorporates the BER, i.e., the ultimate performance evaluation measure, directly into the learning process, ii) it utilizes constraints that are derived from the properties of the optimum single-user decision boundary for additive white Gaussian noise (AWGN) multiple-access channels, and iii) it embeds importance sampling (IS) principles directly into the receiver optimization process. Simulation studies illustrate the BER performance of the proposed scheme. PMID:15384536

Matyjas, John D; Psaromiligkos, Ioannis N; Batalama, Stella N; Medley, Michael J

2004-03-01

234

Directory of Open Access Journals (Sweden)

Full Text Available The main goal of the presented work is to analyse the performance of the Multi-Layer Perceptron (MLP) neural network for flow regime classification based on sets of simulated Electrical Capacitance Tomography (ECT) data. Normalised ECT data have been used to separately train several MLPs employing various commonly used back-propagation learning algorithms, namely the Levenberg-Marquardt (LM), Quasi-Newton (QN) and Resilient-Backpropagation (RP), to classify the gas-oil flow regimes. The performances of the MLPs have been analysed based on their correct classification percentage (CCP). The results demonstrate the feasibility of using MLP, and the superiority of LM algorithm for flow regime classification based on ECT data.

Khursiah Zainal-Mokhtar; Junita Mohamad-Saleh; Hafizah Talib; Najwan Osman-Ali

2009-01-01

235

We describe the development of artificial neural networks (ANN) for the prediction of the properties of ceramic materials. The ceramics studied here include polycrystalline, inorganic, non-metallic materials and are investigated on the basis of their dielectric and ionic properties. Dielectric materials are of interest in telecommunication applications where they are used in tuning and filtering equipment. Ionic and mixed conductors are the subjects of a concerted effort in the search for new materials that can be incorporated into efficient, clean electrochemical devices of interest in energy production and greenhouse gas reduction applications. Multi-layer perceptron ANNs are trained using the back-propagation algorithm and utilise data obtained from the literature to learn composition-property relationships between the inputs and outputs of the system. The trained networks use compositional information to predict the relative permittivity and oxygen diffusion properties of ceramic materials. The results sh...

Scott, D J; Kilner, J A; Rossiny, J C H; McAlford, N N

2007-01-01

236

Directory of Open Access Journals (Sweden)

Full Text Available In this contribution, human face as biometric is considered. Original method of feature extraction from image data is introduced using MLP (multilayer perceptron) and PCA (principal component analysis). This method is used in human face recognition system and results are compared to face recognition system using PCA directly, to a system with direct classification of input images by MLP and RBF (radial basis function) networks, and to a system using MLP as a feature extractor and MLP and RBF networks in the role of classifier. Also a two-stage method for face recognition is presented, in which Kohonen self-organizing map is used as a feature extractor. MLP and RBF network are used as classifiers. In order to obtain deeper insight into presented methods, also visualizations of internal representation of input data obtained by neural networks are presented.

M. Oravec; J. Pavlovicova

2007-01-01

237

Unfolding the neutron spectrum of a NE213 scintillator using artificial neural networks

International Nuclear Information System (INIS)

Artificial neural networks technology has been applied to unfold the neutron spectra from the pulse height distribution measured with NE213 liquid scintillator. Here, both the single and multi-layer perceptron neural network models have been implemented to unfold the neutron spectrum from an Am-Be neutron source. The activation function and the connectivity of the neurons have been investigated and the results have been analyzed in terms of the network's performance. The simulation results show that the neural network that utilizes the Satlins transfer function has the best performance. In addition, omitting the bias connection of the neurons improve the performance of the network. Also, the SCINFUL code is used for generating the response functions in the training phase of the process. Finally, the results of the neural network simulation have been compared with those of the FORIST unfolding code for both 241Am-Be and 252Cf neutron sources. The results of neural network are in good agreement with FORIST code.

2009-01-01

238

Unfolding the neutron spectrum of a NE213 scintillator using artificial neural networks

Energy Technology Data Exchange (ETDEWEB)

Artificial neural networks technology has been applied to unfold the neutron spectra from the pulse height distribution measured with NE213 liquid scintillator. Here, both the single and multi-layer perceptron neural network models have been implemented to unfold the neutron spectrum from an Am-Be neutron source. The activation function and the connectivity of the neurons have been investigated and the results have been analyzed in terms of the network's performance. The simulation results show that the neural network that utilizes the Satlins transfer function has the best performance. In addition, omitting the bias connection of the neurons improve the performance of the network. Also, the SCINFUL code is used for generating the response functions in the training phase of the process. Finally, the results of the neural network simulation have been compared with those of the FORIST unfolding code for both {sup 241}Am-Be and {sup 252}Cf neutron sources. The results of neural network are in good agreement with FORIST code.

Sharghi Ido, A. [Radiation Application Department, Shahid Beheshti University, Tehran (Iran, Islamic Republic of); Bonyadi, M.R. [Electrical and Computer Engineering Faculty, Shahid Beheshti University, Tehran (Iran, Islamic Republic of); Etaati, G.R. [Nuclear Engineering and Physics Faculty, Amir Kabir University of Technology, Tehran (Iran, Islamic Republic of); Shahriari, M. [Radiation Application Department, Shahid Beheshti University, Tehran (Iran, Islamic Republic of)], E-mail: m-shahriari@sbu.ac.ir

2009-10-15

239

Digital Hardware Implementation of a Neural System Used for Nonlinear Adaptive Prediction

Directory of Open Access Journals (Sweden)

Full Text Available Neural networks have been widely used for many applications in digital communications. They are able to give solutions to complex problems due to their nonlinear processing and their learning and generalization. Neural networks are one of the key technologies for the communication domain and accordingly a special effort may be expected to be paid to real time hardware implementation issues. In this study, it is proposed a digital hardware implementation of a neural system based on a multilayer perceptron (MLP). The neural system is used for the nonlinear adaptive prediction of nonstationary signals such as speech signals. The implemented architecture of the MLP is generated using a generic elementary neuron (EN). The polynomial approximation method is used to implement the sigmoidal activation function. The back-propagation algorithm is used to implant the prediction task. The circuit implementation architecture is detailed, for achieving real-time prediction for speech signals. The designed ASIC circuit includes a neural network block, an on-chip learning block and a memory used for storing the synaptic weights for updating.

HassÃ¨ne Faiedh; Chokri Souani; Kholdoun Torki; Kamel Besbes

2006-01-01

240

Unfolding the neutron spectrum of a NE213 scintillator using artificial neural networks.

Artificial neural networks technology has been applied to unfold the neutron spectra from the pulse height distribution measured with NE213 liquid scintillator. Here, both the single and multi-layer perceptron neural network models have been implemented to unfold the neutron spectrum from an Am-Be neutron source. The activation function and the connectivity of the neurons have been investigated and the results have been analyzed in terms of the network's performance. The simulation results show that the neural network that utilizes the Satlins transfer function has the best performance. In addition, omitting the bias connection of the neurons improve the performance of the network. Also, the SCINFUL code is used for generating the response functions in the training phase of the process. Finally, the results of the neural network simulation have been compared with those of the FORIST unfolding code for both (241)Am-Be and (252)Cf neutron sources. The results of neural network are in good agreement with FORIST code. PMID:19586776

Sharghi Ido, A; Bonyadi, M R; Etaati, G R; Shahriari, M

2009-06-09

241

Evaluation of pan evaporation modeling with two different neural networks and weather station data

This study evaluates neural networks models for estimating daily pan evaporation for inland and coastal stations in Republic of Korea. A multilayer perceptron neural networks model (MLP-NNM) and a cascade correlation neural networks model (CCNNM) are developed for local implementation. Five-input models (MLP 5 and CCNNM 5) are generally found to be the best for local implementation. The optimal neural networks models, including MLP 4, MLP 5, CCNNM 4, and CCNNM 5, perform well for homogeneous (cross-stations 1 and 2) and nonhomogeneous (cross-stations 3 and 4) weather stations. Statistical results of CCNNM are better than those of MLP-NNM during the test period for homogeneous and nonhomogeneous weather stations except for MLP 4 being better in BUS-DAE and POH-DAE, and MLP 5 being better in POH-DAE. Applying the conventional models for the test period, it is found that neural networks models perform better than the conventional models for local, homogeneous, and nonhomogeneous weather stations.

Kim, Sungwon; Singh, Vijay P.; Seo, Youngmin

2013-08-01

242

An Oil Fraction Neural Sensor Developed Using Electrical Capacitance Tomography Sensor Data

Directory of Open Access Journals (Sweden)

Full Text Available This paper presents novel research on the development of a generic intelligent oil fraction sensor based on Electrical Capacitance Tomography (ECT) data. An artificial Neural Network (ANN) has been employed as the intelligent system to sense and estimate oil fractions from the cross-sections of two-component flows comprising oil and gas in a pipeline. Previous works only focused on estimating the oil fraction in the pipeline based on fixed ECT sensor parameters. With fixed ECT design sensors, an oil fraction neural sensor can be trained to deal with ECT data based on the particular sensor parameters, hence the neural sensor is not generic. This work focuses on development of a generic neural oil fraction sensor based on training a Multi-Layer Perceptron (MLP) ANN with various ECT sensor parameters. On average, the proposed oil fraction neural sensor has shown to be able to give a mean absolute error of 3.05% for various ECT sensor sizes.

Khursiah Zainal-Mokhtar; Junita Mohamad-Saleh

2013-01-01

243

UK PubMed Central (United Kingdom)

This brief studies exponential H(infinity) synchronization of a class of general discrete-time chaotic neural networks with external disturbance. On the basis of the drive-response concept and H(infinity) control theory, and using Lyapunov-Krasovskii (or Lyapunov) functional, state feedback controllers are established to not only guarantee exponential stable synchronization between two general chaotic neural networks with or without time delays, but also reduce the effect of external disturbance on the synchronization error to a minimal H(infinity) norm constraint. The proposed controllers can be obtained by solving the convex optimization problems represented by linear matrix inequalities. Most discrete-time chaotic systems with or without time delays, such as Hopfield neural networks, cellular neural networks, bidirectional associative memory networks, recurrent multilayer perceptrons, Cohen-Grossberg neural networks, Chua's circuits, etc., can be transformed into this general chaotic neural network to be H(infinity) synchronization controller designed in a unified way. Finally, some illustrated examples with their simulations have been utilized to demonstrate the effectiveness of the proposed methods.

Qi D; Liu M; Qiu M; Zhang S

2010-08-01

244

Artificial neural network application for predicting soil distribution coefficient of nickel.

UK PubMed Central (United Kingdom)

The distribution (or partition) coefficient (K(d)) is an applicable parameter for modeling contaminant and radionuclide transport as well as risk analysis. Selection of this parameter may cause significant error in predicting the impacts of contaminant migration or site-remediation options. In this regards, various models were presented to predict K(d) values for different contaminants specially heavy metals and radionuclides. In this study, artificial neural network (ANN) is used to present simplified model for predicting K(d) of nickel. The main objective is to develop a more accurate model with a minimal number of parameters, which can be determined experimentally or select by review of different studies. In addition, the effects of training as well as the type of the network are considered. The K(d) values of Ni is strongly dependent on pH of the soil and mathematical relationships were presented between pH and K(d) of nickel recently. In this study, the same database of these presented models was used to verify that neural network may be more useful tools for predicting of K(d). Two different types of ANN, multilayer perceptron and redial basis function, were used to investigate the effect of the network geometry on the results. In addition, each network was trained by 80 and 90% of the data and tested for 20 and 10% of the rest data. Then the results of the networks compared with the results of the mathematical models. Although the networks trained by 80 and 90% of the data the results show that all the networks predict with higher accuracy relative to mathematical models which were derived by 100% of data. More training of a network increases the accuracy of the network. Multilayer perceptron network used in this study predicts better than redial basis function network.

Falamaki A

2013-01-01

245

Artificial Neural Network Approach in Radar Target Classification

Directory of Open Access Journals (Sweden)

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.

N. K. Ibrahim; R. S.A.R. Abdullah; M. I. Saripan

2009-01-01

246

A unified neural-network-based speaker localization technique.

Locating and tracking a speaker in real time using microphone arrays is important in many applications such as hands-free video conferencing, speech processing in large rooms, and acoustic echo cancellation. A speaker can be moving from the far field to the near field of the array, or vice versa. Many neural-network-based localization techniques exist, but they are applicable to either far-field or near-field sources, and are computationally intensive for real-time speaker localization applications because of the wide-band nature of the speech. We propose a unified neural-network-based source localization technique, which is simultaneously applicable to wide-band and narrow-band signal sources that are in the far field or near field of a microphone array. The technique exploits a multilayer perceptron feedforward neural network structure and forms the feature vectors by computing the normalized instantaneous cross-power spectrum samples between adjacent pairs of sensors. Simulation results indicate that our technique is able to locate a source with an absolute error of less than 3.5 degrees at a signal-to-noise ratio of 20 dB and a sampling rate of 8000 Hz at each sensor. PMID:18249826

Arslan, G; Sakarya, F A

2000-01-01

247

A unified neural-network-based speaker localization technique.

UK PubMed Central (United Kingdom)

Locating and tracking a speaker in real time using microphone arrays is important in many applications such as hands-free video conferencing, speech processing in large rooms, and acoustic echo cancellation. A speaker can be moving from the far field to the near field of the array, or vice versa. Many neural-network-based localization techniques exist, but they are applicable to either far-field or near-field sources, and are computationally intensive for real-time speaker localization applications because of the wide-band nature of the speech. We propose a unified neural-network-based source localization technique, which is simultaneously applicable to wide-band and narrow-band signal sources that are in the far field or near field of a microphone array. The technique exploits a multilayer perceptron feedforward neural network structure and forms the feature vectors by computing the normalized instantaneous cross-power spectrum samples between adjacent pairs of sensors. Simulation results indicate that our technique is able to locate a source with an absolute error of less than 3.5 degrees at a signal-to-noise ratio of 20 dB and a sampling rate of 8000 Hz at each sensor.

Arslan G; Sakarya FA

2000-01-01

248

An empirical evaluation of the fuzzy kernel perceptron.

J.-H. Chen and C.-S. Chen have recently proposed a nonlinear variant of Keller and Hunt's fuzzy perceptron algorithm, based on the now familiar "kernel trick." In this letter, we demonstrate experimentally that J.-H. Chen and C.-S. Chen's assertion that the fuzzy kernel perceptron (FKP) outperforms the support vector machine (SVM) cannot be sustained. A more thorough model comparison exercise, based on a much wider range of benchmark data sets, shows that the FKP algorithm is not competitive with the SVM. PMID:17526361

Cawley, Gavin C

2007-05-01

249

Smoothed Analysis of the Perceptron Algorithm for Linear Programming

UK PubMed Central (United Kingdom)

The smoothed complexity [1] of an algorithm is the expected running time of the algorithm on an arbitrary instance under a random perturbation. It was shown recently that the simplex algorithm has polynomial smoothed complexity. We show that a simple greedy algorithm for linear programming, the Perceptron algorithm, also has polynomial smoothed complexity, in a high probability sense: that is, the running time is polynomial with high probability over the random perturbation. While the bounds are not strictly comparable, for many choices of parameters the running time bound we show here for the Perceptron algorithm is much lower than the bound given in [1] for the Simplex algorithm.

Avrim Blum; John Dunagan

250

An empirical evaluation of the fuzzy kernel perceptron.

UK PubMed Central (United Kingdom)

J.-H. Chen and C.-S. Chen have recently proposed a nonlinear variant of Keller and Hunt's fuzzy perceptron algorithm, based on the now familiar "kernel trick." In this letter, we demonstrate experimentally that J.-H. Chen and C.-S. Chen's assertion that the fuzzy kernel perceptron (FKP) outperforms the support vector machine (SVM) cannot be sustained. A more thorough model comparison exercise, based on a much wider range of benchmark data sets, shows that the FKP algorithm is not competitive with the SVM.

Cawley GC

2007-05-01

251

Performance surfaces of a single-layer perceptron.

A perceptron learning algorithm may be viewed as a steepest-descent method whereby an instantaneous performance function is iteratively minimized. An appropriate performance function for the most widely used perceptron algorithm is described and it is shown that the update term of the algorithm is the gradient of this function. An example is given of the corresponding performance surface based on Gaussian assumptions and it is shown that there is an infinity of stationary points. The performance surfaces of two related performance functions are examined. Computer simulations that demonstrate the convergence properties of the adaptive algorithms are given. PMID:18282846

Shynk, J J

1990-01-01

252

Performance surfaces of a single-layer perceptron.

UK PubMed Central (United Kingdom)

A perceptron learning algorithm may be viewed as a steepest-descent method whereby an instantaneous performance function is iteratively minimized. An appropriate performance function for the most widely used perceptron algorithm is described and it is shown that the update term of the algorithm is the gradient of this function. An example is given of the corresponding performance surface based on Gaussian assumptions and it is shown that there is an infinity of stationary points. The performance surfaces of two related performance functions are examined. Computer simulations that demonstrate the convergence properties of the adaptive algorithms are given.

Shynk JJ

1990-01-01

253

Directory of Open Access Journals (Sweden)

Full Text Available Este artículo propone una red neuronal de tipo perceptron multicapas (MLP) que optimiza tanto su matriz de pesos como el número de neuronas ocultas. Inicialmente el sistema propuesto usa un número reducido de neuronas ocultas, optimizándose la matriz de pesos mediante un algoritmo de perturbación simultánea. Una vez que la red converge se analiza su funcionamiento y si este no es el esperado se agrega una neurona oculta. Este proceso se repite hasta obtener el funcionamiento deseado. Los resultados obtenidos muestran que el sistema propuesto presenta un funcionamiento muy similar al de un MLP convencional, cuando éste tiene un número óptimo de nodos en la capa oculta y disminuye la complejidad computacional durante la etapa de entrenamiento.This paper proposes a multilayer perceptron neural network (MLP) which optimizes both the matrix weights and the numbers of hidden neurons. Initially, the proposed system uses a reduced number of hidden neurons, optimizing the matrix weights by using a simultaneous perturbation algorithm. Once the network converges, its function is analyzed and if this is not as expected, a hidden neuron is added. This process is repeated until achieving the desired functioning. The results obtained show that the proposed system functions similarly to that of a conventional MLP when this has an optimal number of nodes in the hidden layer, decreasing the computational complexity during the training step.

G. Sánchez; H. Pérez; M. Nakano

2004-01-01

254

Scientific Electronic Library Online (English)

Full Text Available Abstract in spanish Este artículo propone una red neuronal de tipo perceptron multicapas (MLP) que optimiza tanto su matriz de pesos como el número de neuronas ocultas. Inicialmente el sistema propuesto usa un número reducido de neuronas ocultas, optimizándose la matriz de pesos mediante un algoritmo de perturbación simultánea. Una vez que la red converge se analiza su funcionamiento y si este no es el esperado se agrega una neurona oculta. Este proceso se repite hasta obtener el funci (more) onamiento deseado. Los resultados obtenidos muestran que el sistema propuesto presenta un funcionamiento muy similar al de un MLP convencional, cuando éste tiene un número óptimo de nodos en la capa oculta y disminuye la complejidad computacional durante la etapa de entrenamiento. Abstract in english This paper proposes a multilayer perceptron neural network (MLP) which optimizes both the matrix weights and the numbers of hidden neurons. Initially, the proposed system uses a reduced number of hidden neurons, optimizing the matrix weights by using a simultaneous perturbation algorithm. Once the network converges, its function is analyzed and if this is not as expected, a hidden neuron is added. This process is repeated until achieving the desired functioning. The resul (more) ts obtained show that the proposed system functions similarly to that of a conventional MLP when this has an optimal number of nodes in the hidden layer, decreasing the computational complexity during the training step.

Sánchez, G.; Pérez, H.; Nakano, M.

2004-01-01

255

Using the Perceptron Algorithm to Find Consistent Hypotheses

UK PubMed Central (United Kingdom)

The perceptron learning algorithm yields quite naturally an algorithm for finding a linearly separable boolean function consistent with a sample of such a function. Using the idea of a specifying sample, we give a simple proof that this algorithm is not efficient, in general.

Martin Anthony; John Shawe-taylor

256

Concentrations of outdoor radon-222 ((222)Rn) in temperate grazed peatland and deciduous forest in northwestern Turkey were measured, compared, and modeled using artificial neural networks (ANNs) and multiple nonlinear regression (MNLR) models. The best-performing multilayer perceptron model selected out of 28 ANNs considerably enhanced accuracy metrics in emulating (222)Rn concentrations relative to the MNLR model. The two ecosystems had similar diel patterns with the lowest (222)Rn concentrations in the afternoon and the highest ones near dawn. Mean level (5.1?+?2.5 Bq?m(-3) h(-1)) of (222)Rn in the forest was three times smaller than that (15.8?+?9.7 Bq?m(-3)) of (222)Rn in the peatland. Mean (222)Rn level had negative and positive relationships with air temperature and relative humidity, respectively. PMID:23096138

Evrendilek, Fatih; Denizli, Haluk; Yetis, Hakan; Karakaya, Nusret

2012-10-25

257

UK PubMed Central (United Kingdom)

Concentrations of outdoor radon-222 ((222)Rn) in temperate grazed peatland and deciduous forest in northwestern Turkey were measured, compared, and modeled using artificial neural networks (ANNs) and multiple nonlinear regression (MNLR) models. The best-performing multilayer perceptron model selected out of 28 ANNs considerably enhanced accuracy metrics in emulating (222)Rn concentrations relative to the MNLR model. The two ecosystems had similar diel patterns with the lowest (222)Rn concentrations in the afternoon and the highest ones near dawn. Mean level (5.1?+?2.5 Bq?m(-3) h(-1)) of (222)Rn in the forest was three times smaller than that (15.8?+?9.7 Bq?m(-3)) of (222)Rn in the peatland. Mean (222)Rn level had negative and positive relationships with air temperature and relative humidity, respectively.

Evrendilek F; Denizli H; Yetis H; Karakaya N

2013-07-01

258

UK PubMed Central (United Kingdom)

This paper presents a new approach for identifying and validating the F/A-18 aeroservoelastic model, based on flight flutter tests. The neural network (NN), trained with five different flight flutter cases, is validated using 11 other flight flutter test (FFT) data. A total of 16 FFT cases were obtained for all three flight regimes (subsonic, transonic, and supersonic) at Mach numbers ranging between 0.85 and 1.30 and at altitudes of between 5000 and 25 000 ft. The results obtained highlight the efficiency of the multilayer perceptron NN in model identification. Optimization of the NN requires mixing of two proprieties: the hidden layer size reduction and four-layered NN performances. This paper shows that a four-layer NN with only 16 neurons is enough to create an accurate model. The fit coefficients were higher than 92% for both the identification and the validation test data, thus demonstrating accuracy of the NN.

Boely N; Botez RM

2010-11-01

259

UK PubMed Central (United Kingdom)

This paper briefly introduces our numerical linear algebra approaches for solving structured nonlinear least squares problems arising from 'multiple-output' neural-network (NN) models. Our algorithms feature trust-region regularization, and exploit sparsity of either the 'block-angular' residual Jacobian matrix or the 'block-arrow' Gauss-Newton Hessian (or Fisher information matrix in statistical sense) depending on problem scale so as to render a large class of NN-learning algorithms 'efficient' in both memory and operation costs. Using a relatively large real-world nonlinear regression application, we shall explain algorithmic strengths and weaknesses, analyzing simulation results obtained by both direct and iterative trust-region algorithms with two distinct NN models: 'multilayer perceptrons' (MLP) and 'complementary mixtures of MLP-experts' (or neuro-fuzzy modular networks).

Mizutani E; Demmel JW

2003-06-01

260

Directory of Open Access Journals (Sweden)

Full Text Available This paper gives the definition of Transparent Neural Network “TNN” for the simulation of the global-local vision and its application to the segmentation of administrative document image. We have developed and have adapted a recognition method which models the contextual effects reported from studies in experimental psychology. Then, we evaluated and tested the TNN and the multi-layer perceptron “MLP”,which showed its effectiveness in the field of the recognition, in order to show that the TNN is clearer for the user and more powerful on the level of the recognition. Indeed, the TNN is the only system which makes it possible to recognize the document and its structure

Boulbaba Ben Ammar

2013-01-01

261

Foreground removal from WMAP 5 yr temperature maps using an MLP neural network

DEFF Research Database (Denmark)

Aims. One of the main obstacles for extracting the cosmic microwave background (CMB) signal from observations in the mm/sub-mm range is the foreground contamination by emission from Galactic component: mainly synchrotron, free-free, and thermal dust emission. The statistical nature of the intrinsic CMB signal makes it essential to minimize the systematic errors in the CMB temperature determinations. Methods. The feasibility of using simple neural networks to extract the CMB signal from detailed simulated data has already been demonstrated. Here, simple neural networks are applied to the WMAP 5 yr temperature data without using any auxiliary data. Results. A simple multilayer perceptron neural network with two hidden layers provides temperature estimates over more than 75 per cent of the sky with random errors significantly below those previously extracted from these data. Also, the systematic errors, i.e. errors correlated with the Galactic foregrounds, are very small. Conclusions. With these results the neural network method is well prepared for dealing with the high-quality CMB data from the ESA Planck Surveyor satellite. © ESO, 2010.

NØrgaard-Nielsen, Hans Ulrik

2010-01-01

262

Improved training of neural networks for the nonlinear active control of sound and vibration.

UK PubMed Central (United Kingdom)

Active control of sound and vibration has been the subject of a lot of research in recent years, and examples of applications are now numerous. However, few practical implementations of nonlinear active controllers have been realized. Nonlinear active controllers may be required in cases where the actuators used in active control systems exhibit nonlinear characteristics, or in cases when the structure to be controlled exhibits a nonlinear behavior. A multilayer perceptron neural-network based control structure was previously introduced as a nonlinear active controller, with a training algorithm based on an extended backpropagation scheme. This paper introduces new heuristical training algorithms for the same neural-network control structure. The objective is to develop new algorithms with faster convergence speed (by using nonlinear recursive-least-squares algorithms) and/or lower computational loads (by using an alternative approach to compute the instantaneous gradient of the cost function). Experimental results of active sound control using a nonlinear actuator with linear and nonlinear controllers are presented. The results show that some of the new algorithms can greatly improve the learning rate of the neural-network control structure, and that for the considered experimental setup a neural-network controller can outperform linear controllers.

Bouchard M; Paillard B; Le Dinh CT

1999-01-01

263

Prediction of the local power factor in BWR fuel cells by means of a multilayer neural network

International Nuclear Information System (INIS)

To the beginning of a new operation cycle in a BWR reactor the reactivity of this it increases by means of the introduction of fresh fuel, the one denominated reload fuel. The problem of the definition of the characteristics of this reload fuel represents a combinatory optimization problem that requires significantly a great quantity of CPU time for their determination. This situation has motivated to study the possibility to substitute the Helios code, the one which is used to generate the new cells of the reload fuel parameters, by an artificial neuronal network, with the purpose of predicting the parameters of the fuel reload cell of a BWR reactor. In this work the results of the one training of a multilayer neuronal net that can predict the local power factor (LPPF) in such fuel cells are presented. The prediction of the LPPF is carried out in those condition of beginning of the life of the cell (0.0 MWD/T, to 40% of holes in the one moderator, temperature of 793 K in the fuel and a moderator temperature of 560 K. The cells considered in the present study consist of an arrangement of 10x10 bars, of those which 92 contains U235, some of these bars also contain a concentration of Gd2O3 and 8 of them contain only water. The axial location inside the one assembles of recharge of these cells it is exactly up of the cells that contain natural uranium in the base of the reactor core. The training of the neuronal net is carried out by means of a retro-propagation algorithm that uses a space of training formed starting from previous evaluations of cells by means of the Helios code. They are also presented the results of the application of the neuronal net found for the prediction of the LPPF of some cells used in the real operation of the Unit One of the Laguna Verde Nuclear Power station. (Author)

2007-01-01

264

Bank Direct Marketing Based on Neural Network

Directory of Open Access Journals (Sweden)

Full Text Available All bank marketing campaigns are dependent on customers’ huge electronic data. The size of these data source is impossible for a human analyst to come up with interesting information that will help in the decision-making process. Data mining models are completely helping in performance of these campaigns. This paper introduces applications of recent and important models of data mining; Multilayer perceptron neural network (MLPNN) and Ross Quinlan new decision tree model (C5.0). The objective is to examine the performance of MLPNN and C5.0 models on a real-world data of bank deposit subscription. The purpose is increasing the campaign effectiveness by identifying the main characteristics that affect a success (the deposit subscribed by the client) based on MLPNN and C5.0. The experimental results demonstrate, with higher accuracies, the success of these models in predicting the best campaign contact with the clients for subscribing deposit. The performances are measured by three statistical measures; classification accuracy, sensitivity, and specificity.

Hany. A. Elsalamony,; Alaa. M. Elsayad,

2013-01-01

265

Bearing Fault Detection Using Artificial Neural Networks and Genetic Algorithm

Directory of Open Access Journals (Sweden)

Full Text Available A study is presented to compare the performance of bearing fault detection using three types of artificial neural networks (ANNs), namely, multilayer perceptron (MLP), radial basis function (RBF) network, and probabilistic neural network (PNN). The time domain vibration signals of a rotating machine with normal and defective bearings are processed for feature extraction. The extracted features from original and preprocessed signals are used as inputs to all three ANN classifiers: MLP, RBF, and PNN for two-class (normal or fault) recognition. The characteristic parameters like number of nodes in the hidden layer of MLP and the width of RBF, in case of RBF and PNN along with the selection of input features, are optimized using genetic algorithms (GA). For each trial, the ANNs are trained with a subset of the experimental data for known machine conditions. The ANNs are tested using the remaining set of data. The procedure is illustrated using the experimental vibration data of a rotating machine with and without bearing faults. The results show the relative effectiveness of three classifiers in detection of the bearing condition.

Saeed A. Al-Araimi; Khamis R. Al-Balushi; B. Samanta

2004-01-01

266

The Role of Weight Shrinking in Large Margin Perceptron Learning

We introduce into the classical perceptron algorithm with margin a mechanism that shrinks the current weight vector as a first step of the update. If the shrinking factor is constant the resulting algorithm may be regarded as a margin-error-driven version of NORMA with constant learning rate. In this case we show that the allowed strength of shrinking depends on the value of the maximum margin. We also consider variable shrinking factors for which there is no such dependence. In both cases we obtain new generalizations of the perceptron with margin able to provably attain in a finite number of steps any desirable approximation of the maximal margin hyperplane. The new approximate maximum margin classifiers appear experimentally to be very competitive in 2-norm soft margin tasks involving linear kernels.

Panagiotakopoulos, Constantinos

2012-01-01

267

Optical perceptron learning for binary classification with spatial light rebroadcasters

Binary classification of an object in a two-dimensional image is considered. A spatial light rebroadcaster is shown to be advantageous for learning in this case because it can store the weights and permit upward and downward adjustments. Two learning algorithms, based on the perceptron, are considered. A modification of the perceptron algorithm is developed so that only positive weights are needed. This is convenient because light intensity is positive only. The modified algorithm is shown to converge in a finite number of steps for positive linear separable classes. Optical experiments show the classification of four characters in two groups, in which alternative groupings are used to show robustness. In the second group of experiments the complements of the two-dimensional characters are used, and the convergence is equally fast. Adding the results from the original and complementary patterns provides a discrimination superior to that obtained using either on its own.

McAulay, Alastair D.; Wang, Junqing; Xu, Xin

1993-03-01

268

Optical perceptron learning for binary classification with spatial light rebroadcasters.

UK PubMed Central (United Kingdom)

Binary classification of an object in a two-dimensional image is considered. A spatial light rebroadcaster is shown to be advantageous for learning in this case because it can store the weights and permit upward and downward adjustments. Two learning algorithms, based on the perceptron, are considered. A modification of the perceptron algorithm is developed so that only positive weights are needed. This is convenient because light intensity is positive only. The modified algorithm is shown to converge in a finite number of steps for positive linear separable classes. Optical experiments show the classification of four characters in two groups, in which alternative groupings are used to show robustness. In the second group of experiments the complements of the two-dimensional characters are used, and the convergence is equally fast. Adding the results from the original and complementary patterns provides a discrimination superior to that obtained using either on its own.

McAulay AD; Wang J; Xu X

1993-03-01

269

Machine and component residual life estimation through the application of neural networks

International Nuclear Information System (INIS)

This paper concerns the use of neural networks for predicting the residual life of machines and components. In addition, the advantage of using condition-monitoring data to enhance the predictive capability of these neural networks was also investigated. A number of neural network variations were trained and tested with the data of two different reliability-related datasets. The first dataset represents the renewal case where the failed unit is repaired and restored to a good-as-new condition. Data were collected in the laboratory by subjecting a series of similar test pieces to fatigue loading with a hydraulic actuator. The average prediction error of the various neural networks being compared varied from 431 to 841 s on this dataset, where test pieces had a characteristic life of 8971 s. The second dataset were collected from a group of pumps used to circulate a water and magnetite solution within a plant. The data therefore originated from a repaired system affected by reliability degradation. When optimized, the multi-layer perceptron neural networks trained with the Levenberg-Marquardt algorithm and the general regression neural network produced a sum-of-squares error within 11.1% of each other for the renewal dataset. The small number of inputs and poorly mapped input space on the second dataset meant that much larger errors were recorded on some of the test data. The potential for using neural networks for residual life prediction and the advantage of incorporating condition-based data into the model was nevertheless proven for both examples.

2009-01-01

270

UK PubMed Central (United Kingdom)

A predictive model to determine the concentration of nickel and vanadium in vacuum residues of Colombian crude oils using laser-induced breakdown spectroscopy (LIBS) and artificial neural networks (ANNs) with nodes distributed in multiple layers (multilayer perceptron) is presented. ANN inputs are intensity values in the vicinity of the emission lines 300.248, 301.200 and 305.081 nm of the Ni(I), and 309.310, 310.229, and 311.070 nm of the V(II). The effects of varying number of nodes and the initial weights and biases in the ANNs were systematically explored. Average relative error of calibration/prediction (REC/REP) and average relative standard deviation (RSD) metrics were used to evaluate the performance of the ANN in the prediction of concentrations of two elements studied here.

Tarazona JL; Guerrero J; Cabanzo R; Mejía-Ospino E

2012-03-01

271

Directory of Open Access Journals (Sweden)

Full Text Available The article is devoted to the simulation of the influence of environmental osmotic pressure on the changes of the level of ?-amylase activity of mucous tunic of the intestine of Russian sturgeon (Acipenser güldenstädtii Brandt). For the solving of this problem the apparatus of neural networks is used. The designed model can be classified as multilayer perceptrone and has rather transparent structure. The conformities of this influence are examined and the model with high approximating and generalizing properties is created. The conclusion about high availability of application of the approach in the studies of adaptations of the digestive system of aquatic organisms to the influence of environmental factors with some qualifications about used rate of exactness of the simulation is made.

Martyanov Alexander Sergeevich; Bednyakov Dmitriy Andreevich

2012-01-01

272

Tagging b quark events in ALEPH with neural networks

International Nuclear Information System (INIS)

Comparison of different methods to tag b quark events are presented: multilayered perceptron (MLP), Learning Vector Quantization (LVQ), discriminant analysis, combination of any two of the above methods. The sample events come from the ALEPH Monte Carlo and data, from the 1990 ALEPH runs. (authors) 12 refs., 16 figs., 5 tabs

1991-01-01

273

?/?0 separation in shower maximum detector using neural network algorithm

International Nuclear Information System (INIS)

Procedure of gamma/pion neutral separation based on a multilayered perceptron algorithm are presented. Recognition capacities of these procedures and one of the CDF separation methods have been examined. The procedure were tested with the simulated data from one EMC+SMD tower of the STAR experiment. 10 refs., 1 tab., 9 figs.

1994-01-01

274

Directory of Open Access Journals (Sweden)

Full Text Available In this study, a method of artificial neural network applied for the solution of inverse kinematics of 2-link serial chain manipulator. The method is multilayer perceptrons neural network has applied. This unsupervised method learns the functional relationship between input (Cartesian) space and output (joint) space based on a localized adaptation of the mapping, by using the manipulator itself under joint control and adapting the solution based on a comparison between the resulting locations of the manipulator's end effectors in Cartesian space with the desired location. Even when a manipulator is not available; the approach is still valid if the forward kinematic equations are used as a model of the manipulator. The forward kinematic equations always have a unique solution, and the resulting Neural net can be used as a starting point for further refinement when the manipulator does become available. Artificial neural network especially MLP are used to learn the forward and the inverse kinematic equations of two degrees freedom robot arm. A set of some data sets were first generated as per the formula equation for this the input parameter X and Y coordinates in inches. Using these data sets was basis for the training and evaluation or testing the MLP model. Out of the sets data points, maximum were used as training data and some were used for testing for MLP. Backpropagation algorithm was used for training the network and for updating the desired weights. In this work epoch based training method was applied.

Satish Kumar; Kashif Irshad

2012-01-01

275

UK PubMed Central (United Kingdom)

UNLABELLED: An electronic nose (EN) based on an array of 10 metal oxide semiconductor sensors was used, jointly with an artificial neural network (ANN), to predict coffee roasting degree. The flavor release evolution and the main physicochemical modifications (weight loss, density, moisture content, and surface color: L*, a*), during the roasting process of coffee, were monitored at different cooking times (0, 6, 8, 10, 14, 19 min). Principal component analysis (PCA) was used to reduce the dimensionality of sensors data set (600 values per sensor). The selected PCs were used as ANN input variables. Two types of ANN methods (multilayer perceptron [MLP] and general regression neural network [GRNN]) were used in order to estimate the EN signals. For both neural networks the input values were represented by scores of sensors data set PCs, while the output values were the quality parameter at different roasting times. Both the ANNs were able to well predict coffee roasting degree, giving good prediction results for both roasting time and coffee quality parameters. In particular, GRNN showed the highest prediction reliability. PRACTICAL APPLICATION: Actually the evaluation of coffee roasting degree is mainly a manned operation, substantially based on the empirical final color observation. For this reason it requires well-trained operators with a long professional skill. The coupling of e-nose and artificial neural networks (ANNs) may represent an effective possibility to roasting process automation and to set up a more reproducible procedure for final coffee bean quality characterization.

Romani S; Cevoli C; Fabbri A; Alessandrini L; Dalla Rosa M

2012-09-01

276

Directory of Open Access Journals (Sweden)

Full Text Available Neural networks with the multi-layered perceptron architecture were trained on an autoassociation task to compress 2D seismic data. Networks with linear transfer functions outperformed nonlinear neural nets with single or multiple hidden layers. This indicates that the correlational structure of the seismic data is predominantly linear. A compression factor of 5 to 7 can be achieved if a reconstruction error of 10% is allowed. The performance on new test data was similar to that achieved with the training data. The hidden units developed feature-detecting properties that resemble oriented line, edge and more complex feature detectors. The feature detectors of linear neural nets are near-orthogonal rotations of the principal eigenvectors of the Karhunen-Loève transformation. Des réseaux neuronaux à architecture de perceptron multicouches ont été expérimentés en auto-association pour permettre la compression de données sismiques bidimensionnelles. Les réseaux neuronaux à fonctions de transfert linéaires s'avèrent plus performants que les réseaux neuronaux non linéaires, à une ou plusieurs couches cachées. Ceci indique que la structure corrélative des données sismiques est à prédominance linéaire. Un facteur de compression de 5 à 7 peut être obtenu si une erreur de reconstruction de 10 % est admise. La performance sur les données de test est très proche de celle obtenue sur les données d'apprentissage. Les unités cachées développent des propriétés de détection de caractéristiques ressemblant à des détecteurs de lignes orientées, de bords et de figures plus complexes. Les détecteurs de caractéristique des réseaux neuronaux linéaires sont des rotations quasi orthogonales des vecteurs propres principaux de la transformation de Karhunen-Loève.

Epping W. J. M.; L'istelle A. R.

2006-01-01

277

Directory of Open Access Journals (Sweden)

Full Text Available This paper presents the design of classifiers with neural network approach based on the method used Expectations Maximum (EM). The decision rule of Bayes classifier using the Minimum Error to the classification of a mixture of multitemporal imagery. In this particular, the multilayer perceptron neural network model with Probabilistic Neural Network (PNN) is used for nonparametric estimation of posterior class probabilities. Temporal image correlation calculated with the prior joint probabilities of each class that is automatically estimated by applying a special formula that is algorithm expectation maximum of multitemporal imagery. Experiments performed on two multitemporal image is the image of the Saguling taken at two different time. Based on experimental results on two test areas can be shown that the average accuracy rate PNN classifier is better than the Back Propagation (BP), and the Expectation Maximum (EM) increase the ability of classifiers. Multinomial PNN classifier by applying the maximum expected to have a consistent recognition capability for multitemporal imagery, and also consistent for each object class category. The proposed classification methodology can solve the problem multitemporal efectively.

Wawan Setiawan; Wiweka

2012-01-01

278

Artificial neural network as the tool in prediction rheological features of raw minced meat

Directory of Open Access Journals (Sweden)

Full Text Available Background. The aim of the study was to elaborate a method of modelling and forecasting rheological features which could be applied to raw minced meat at the stage of mixture preparation with a given ingredient composition. Material and methods. The investigated material contained pork and beef meat, pork fat, fat substitutes, ice and curing mixture in various proportions. Seven texture parameters were measured for each sample of raw minced meat. The data obtained were processed using the artificial neural network module in Statistica 9.0 software. Results. The model that reached the lowest training error was a multi-layer perceptron MLP with three neural layers and architecture 7:7-11-7:7. Correlation coefficients between the experimental and calculated values in training, verification and testing subsets were similar and rather high (around 0.65) which indicated good network performance. Conclusion. High percentage of the total variance explained in PCA analysis (73.5%) indicated that the percentage composition of raw minced meat can be successfully used in the prediction of its rheological features. Statistical analysis of the results revealed, that artificial neural network model is able to predict rheological parameters and thus a complete texture profile of raw minced meat.

Jerzy A. Balejko; Zbigniew Nowak; Edyta Balejko

2012-01-01

279

Selection of input parameters to model direct solar irradiance by using artificial neural networks

International Nuclear Information System (INIS)

A very important factor in the assessment of solar energy resources is the availability of direct irradiance data of high quality. However, this component of solar radiation is seldom measured and thus must be estimated from data of global solar irradiance, which is registered in most radiometric stations. In recent years, artificial neural networks (ANN) have shown to be a powerful tool for mapping complex and non-linear relationships. In this work, the Bayesian framework for ANN, named as automatic relevance determination method (ARD), was employed to obtain the relative relevance of a large set of atmospheric and radiometric variables used for estimating hourly direct solar irradiance. In addition, we analysed the viability of this novel technique applied to select the optimum input parameters to the neural network. For that, a multi-layer feedforward perceptron is trained on these data. The results reflect the relative importance of the inputs selected. Clearness index and relative air mass were found to be the more relevant input variables to the neural network, as it was expected, proving the reliability of the ARD method. Moreover, we show that this novel methodology can be used in unfavourable conditions, in terms of limited amount of available data, performing successful results

2005-01-01

280

UK PubMed Central (United Kingdom)

OBJECTIVE: The novel clinical prediction approach of Bayesian neural networks with fuzzy logic inferences is created and applied to derive prognostic decision rules in cerebral aneurysmal subarachnoid hemorrhage (aSAH). METHODS: The approach of Bayesian neural networks with fuzzy logic inferences was applied to data from five trials of Tirilazad for aneurysmal subarachnoid hemorrhage (3551 patients). RESULTS: Bayesian meta-analyses of observational studies on aSAH prognostic factors gave generalizable posterior distributions of population mean log odd ratios (ORs). Similar trends were noted in Bayesian and linear regression ORs. Significant outcome predictors include normal motor response, cerebral infarction, history of myocardial infarction, cerebral edema, history of diabetes mellitus, fever on day 8, prior subarachnoid hemorrhage, admission angiographic vasospasm, neurological grade, intraventricular hemorrhage, ruptured aneurysm size, history of hypertension, vasospasm day, age and mean arterial pressure. Heteroscedasticity was present in the nontransformed dataset. Artificial neural networks found nonlinear relationships with 11 hidden variables in 1 layer, using the multilayer perceptron model. Fuzzy logic decision rules (centroid defuzzification technique) denoted cut-off points for poor prognosis at greater than 2.5 clusters. DISCUSSION: This aSAH prognostic system makes use of existing knowledge, recognizes unknown areas, incorporates one's clinical reasoning, and compensates for uncertainty in prognostication.

Lo BW; Macdonald RL; Baker A; Levine MA

2013-01-01

281

Artificial neural network as the tool in prediction rheological features of raw minced meat.

UK PubMed Central (United Kingdom)

BACKGROUND: The aim of the study was to elaborate a method of modelling and forecasting rheological features which could be applied to raw minced meat at the stage of mixture preparation with a given ingredient composition. MATERIAL AND METHODS: The investigated material contained pork and beef meat, pork fat, fat substitutes, ice and curing mixture in various proportions. Seven texture parameters were measured for each sample of raw minced meat. The data obtained were processed using the artificial neural network module in Statistica 9.0 software. RESULTS: The model that reached the lowest training error was a multi-layer perceptron MLP with three neural layers and architecture 7:7-11-7:7. Correlation coefficients between the experimental and calculated values in training, verification and testing subsets were similar and rather high (around 0.65) which indicated good network performance. CONCLUSION: High percentage of the total variance explained in PCA analysis (73.5%) indicated that the percentage composition of raw minced meat can be successfully used in the prediction of its rheological features. Statistical analysis of the results revealed, that artificial neural network model is able to predict rheological parameters and thus a complete texture profile of raw minced meat.

Balejko JA; Nowak Z; Balejko E

2012-07-01

282

Objective. The novel clinical prediction approach of Bayesian neural networks with fuzzy logic inferences is created and applied to derive prognostic decision rules in cerebral aneurysmal subarachnoid hemorrhage (aSAH). Methods. The approach of Bayesian neural networks with fuzzy logic inferences was applied to data from five trials of Tirilazad for aneurysmal subarachnoid hemorrhage (3551 patients). Results. Bayesian meta-analyses of observational studies on aSAH prognostic factors gave generalizable posterior distributions of population mean log odd ratios (ORs). Similar trends were noted in Bayesian and linear regression ORs. Significant outcome predictors include normal motor response, cerebral infarction, history of myocardial infarction, cerebral edema, history of diabetes mellitus, fever on day 8, prior subarachnoid hemorrhage, admission angiographic vasospasm, neurological grade, intraventricular hemorrhage, ruptured aneurysm size, history of hypertension, vasospasm day, age and mean arterial pressure. Heteroscedasticity was present in the nontransformed dataset. Artificial neural networks found nonlinear relationships with 11 hidden variables in 1 layer, using the multilayer perceptron model. Fuzzy logic decision rules (centroid defuzzification technique) denoted cut-off points for poor prognosis at greater than 2.5 clusters. Discussion. This aSAH prognostic system makes use of existing knowledge, recognizes unknown areas, incorporates one's clinical reasoning, and compensates for uncertainty in prognostication.

Lo, Benjamin W. Y.; Macdonald, R. Loch; Baker, Andrew; Levine, Mitchell A. H.

2013-01-01

283

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

UK PubMed Central (United Kingdom)

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

Rasouli H; Rasouli C; Koohi A

2013-02-01

284

Use of the 'Perceptron' algorithm to distinguish translational initiation sites in E. coli.

UK PubMed Central (United Kingdom)

We have used a "Perceptron" algorithm to find a weighting function which distinguishes E. coli translational initiation sites from all other sites in a library of over 78,000 nucleotides of mRNA sequence. The "Perceptron" examined sequences as linear representations. The "Perceptron" is more successful at finding gene beginnings than our previous searches using "rules" (see previous paper). We note that the weighting function can find translational initiation sites within sequences that were not included in the training set.

Stormo GD; Schneider TD; Gold L; Ehrenfeucht A

1982-05-01

285

Data acquisition in modeling using neural networks and decision trees

Directory of Open Access Journals (Sweden)

Full Text Available The paper presents a comparison of selected models from area of artificial neural networks and decision trees in relation with actualconditions of foundry processes. The work contains short descriptions of used algorithms, their destination and method of data preparation,which is a domain of work of Data Mining systems. First part concerns data acquisition realized in selected iron foundry, indicating problems to solve in aspect of casting process modeling. Second part is a comparison of selected algorithms: a decision tree and artificial neural network, that is CART (Classification And Regression Trees) and BP (Backpropagation) in MLP (Multilayer Perceptron) networks algorithms.Aim of the paper is to show an aspect of selecting data for modeling, cleaning it and reducing, for example due to too strong correlationbetween some of recorded process parameters. Also, it has been shown what results can be obtained using two different approaches:first when modeling using available commercial software, for example Statistica, second when modeling step by step using Excel spreadsheetbasing on the same algorithm, like BP-MLP. Discrepancy of results obtained from these two approaches originates from a priorimade assumptions. Mentioned earlier Statistica universal software package, when used without awareness of relations of technologicalparameters, i.e. without user having experience in foundry and without scheduling ranks of particular parameters basing on acquisition, can not give credible basis to predict the quality of the castings. Also, a decisive influence of data acquisition method has been clearly indicated, the acquisition should be conducted according to repetitive measurement and control procedures. This paper is based on about 250 records of actual data, for one assortment for 6 month period, where only 12 data sets were complete (including two that were used for validation of neural network) and useful for creating a model. It is definitely too small portion in case of artificial neural networks, but it shows a scale of danger of unprofessional data acquisition.

R. Sika; Z. Ignaszak

2011-01-01

286

Synapse:neural network for predict power consumption: users guide

Energy Technology Data Exchange (ETDEWEB)

SYNAPSE is forecasting tool designed to predict power consumption in metropolitan France on the half hour time scale. Some characteristics distinguish this forecasting model from those which already exist. In particular, it is composed of numerous neural networks. The idea for using many neural networks arises from past tests. These tests showed us that a single neural network is not able to solve the problem correctly. From this result, we decided to perform unsupervised classification of the 24 consumption curves. From this classification, six classes appeared, linked with the weekdays: Mondays, Tuesdays, Wednesdays, Thursdays, Fridays, Saturdays, Sundays, holidays and bridge days. For each class and for each half hour, two multilayer perceptrons are built. The two of them forecast the power for one particular half hour, and for a day including one of the determined class. The input of these two network are different: the first one (short time forecasting) includes the powers for the most recent half hour and relative power of the previous day; the second (medium time forecasting) includes only the relative power of the previous day. A process connects the results of every networks and allows one to forecast more than one half-hour in advance. In this process, short time forecasting networks and medium time forecasting networks are used differently. The first kind of neural networks gives good results on the scale of one day. The second one gives good forecasts for the next predicted powers. In this note, the organization of the SYNAPSE program is detailed, and the user`s menu is described. This first version of synapse works and should allow the APC group to evaluate its utility. (authors). 6 refs., 2 appends.

Muller, C.; Mangeas, M.; Perrot, N.

1994-08-01

287

Neural Network Methods for Boundary Value Problems Defined in Arbitrarily Shaped Domains

Partial differential equations (PDEs) with Dirichlet boundary conditions defined on boundaries with simple geomerty have been succesfuly treated using sigmoidal multilayer perceptrons in previous works. This article deals with the case of complex boundary geometry, where the boundary is determined by a number of points that belong to it and are closely located, so as to offer a reasonable representation. Two networks are employed: a multilayer perceptron and a radial basis function network. The later is used to account for the satisfaction of the boundary conditions. The method has been succesfuly tested on two-dimensional and three-dimensional PDEs and has yielded accurate solutions.

Lagaris, I E; Papageorgiou, D G

1998-01-01

288

Artificial Neural Networks in the Assessment of Stand Parameters from an IKONOS Satellite Image

Directory of Open Access Journals (Sweden)

Full Text Available The paper explores the possibilities of assessing five stand parameters (tree number, volume, stocking, basal area and stand age) with the application of a multi-layer perceptron artificial neural network. An IKONOS satellite image (PAN 1 m x 1 m) was used to asses parts of stands in the sixth (121–140 yrs) and seventh (141–160 yrs) age class of pedunculate oak management class in the »Slavir« Management Unit of Otok Forest Office. Six features extracted from the first order histogram and five texture features extracted from the second order histogram were used as input data for neural network training. Data from the Management Plan were used as outputs of the neural network. An early stopping method and scaled conjugate gradient algorithm with error back propagation were used to improve generalization property of the neural network. Two neural network models were applied to assess the required stand parameters. The first model has one neuron in the output layer, where separate neuron network training was conducted for each stand parameter. The second model has five neurons in the output layer related to five assessed stand parameters. Both networks were trained and tested simultaneously. The conducted research showed that both of these neuron network models have good generalization properties. However, further analysis gave precedence to the second neural network model. Assessment of five quantitative stand parameters did not show any statistically significant differences between the Management Plan data and the neuron network model in terms of tree number, volume, stocking, basal area and stand age analysis.

Damir Klobu?ar; Renata Pernar; Sven Lon?ari?; Marko Subaši?

2008-01-01

289

Neural networks are capable of modeling any complex function and can be used in the poultry and animal production areas. The aim of this study was to investigate the possibility of using neural networks on an egg production data set and fitting models to the egg production curve by applying 2 approaches, one using a nonlinear logistic model and the other using 2 artificial neural network models [multilayer perceptron (MLP) and radial basis function]. Two data sets from 2 generations of a White Leghorn strain that had been selected mainly for egg production were used. In the first data set, the mean weekly egg-laying rate was ascertained over a 54-wk egg production period. This data set was used to adjust and test the logistic model and to train and test the neural networks. The second data set, covering 52 wk of egg production, was used to validate the models. The mean absolute deviation, mean square error, and R(2) were used to evaluate the fit of the models. The MLP neural network had the best fit in the test and validation phases. The advantage of using neural networks is that they can be fitted to any kind of data set and do not require model assumptions such as those required in the nonlinear methodology. The results confirm that MLP neural networks can be used as an alternative tool to fit to egg production. The benefits of the MLP are the great flexibility and their lack of a priori assumptions when estimating a noisy nonlinear model. PMID:21325246

Savegnago, R P; Nunes, B N; Caetano, S L; Ferraudo, A S; Schmidt, G S; Ledur, M C; Munari, D P

2011-03-01

290

UK PubMed Central (United Kingdom)

Neural networks are capable of modeling any complex function and can be used in the poultry and animal production areas. The aim of this study was to investigate the possibility of using neural networks on an egg production data set and fitting models to the egg production curve by applying 2 approaches, one using a nonlinear logistic model and the other using 2 artificial neural network models [multilayer perceptron (MLP) and radial basis function]. Two data sets from 2 generations of a White Leghorn strain that had been selected mainly for egg production were used. In the first data set, the mean weekly egg-laying rate was ascertained over a 54-wk egg production period. This data set was used to adjust and test the logistic model and to train and test the neural networks. The second data set, covering 52 wk of egg production, was used to validate the models. The mean absolute deviation, mean square error, and R(2) were used to evaluate the fit of the models. The MLP neural network had the best fit in the test and validation phases. The advantage of using neural networks is that they can be fitted to any kind of data set and do not require model assumptions such as those required in the nonlinear methodology. The results confirm that MLP neural networks can be used as an alternative tool to fit to egg production. The benefits of the MLP are the great flexibility and their lack of a priori assumptions when estimating a noisy nonlinear model.

Savegnago RP; Nunes BN; Caetano SL; Ferraudo AS; Schmidt GS; Ledur MC; Munari DP

2011-03-01

291

Crash Introduction to Artificial Neural Networks

The Crash Introduction to Artificial Neural Networks is not a comprehensive resource, but it provides a good overview of many aspects of the topic. Beginning with a discussion of biological processes in the brain, the site describes the function of neurons and how they are interconnected. Some historical events are mentioned, leading to the development of an artificial neural network. The famous perceptron configuration is the basis of subsequent discussions of training algorithms, prediction and classification functions, and data processing.

Galkin, Ivan

292

UK PubMed Central (United Kingdom)

Crying is the most noticeable behavior of infancy. Infant cry signals can be used to identify physical or psychological status of an infant. Recently, acoustic analysis of infant cry signal has shown promising results and it has been proven to be an excellent tool to investigate the pathological status of an infant. This paper proposes short-time Fourier transform (STFT) based time-frequency analysis of infant cry signals. Few statistical features are derived from the time-frequency plot of infant cry signals and used as features to quantify infant cry signals. General Regression Neural Network (GRNN) is employed as a classifier for discriminating infant cry signals. Two classes of infant cry signals are considered such as normal cry signals and pathological cry signals from deaf infants. To prove the reliability of the proposed features, two neural network models such as Multilayer Perceptron (MLP) and Time-Delay Neural Network (TDNN) trained by scaled conjugate gradient algorithm are also used as classifiers. The experimental results show that the GRNN classifier gives very promising classification accuracy compared to MLP and TDNN and the proposed method can effectively classify normal and pathological infant cries.

Hariharan M; Sindhu R; Yaacob S

2012-11-01

293

Directory of Open Access Journals (Sweden)

Full Text Available Direct measurement of soil hydraulic characteristics is costly and time-consuming. Also, the method is partly unreliable due to soil heterogeneity and laboratory errors. Instead, soil hydraulic characteristics can be predicted using readily available data such as soil texture and bulk density using pedotransfer functions (PTFs). Artificial neural networks (ANNs) and statistical regression are two methods which are used to develop PTFs. In this study, the multi-layer perceptron (MLP) neural network and backward and stepwise regression models were used to estimate saturated hydraulic conductivity using some soil characteristics including the percentage of particle size distribution, porosity, and bulk density. Data of 125 soil profiles were collected from the reports of basic soil science and land reclamation studies conducted by Khuzestan Water and Power Organization. The results showed that MLP neural network having Bayesian training algorithm with the greater coefficient of determination (R2=0.65) and the lower error (RMSE =0.04) had better performance than multiple linear regression model in predicting saturated hydraulic conductivity.

R. Rezae Arshad; GH. Sayyad; *, M. Mazloom; M. Shorafa; A. Jafarnejady

2012-01-01

294

The reactor safety study with help of artificial neuron networks (multilayer perceptrons)

International Nuclear Information System (INIS)

[en] One deals with deposition of insulation large amounts on settling tank components that may result in malfunction of residual heat removal systems. Paper describes briefly simulation of pressure drops in confinement systems by means of an artificial neuron nets and compares the simulation data with the experiment ones

2008-01-01

295

24-hours ahead global irradiation forecasting using Multi-Layer Perceptron

Digital Repository Infrastructure Vision for European Research (DRIVER)

The grid integration of variable renewable energy sources implies that their effective production could be predicted, at different times ahead. In the case of solar plants, the driving factor is the global solar irradiation (sum of direct and diffuse solar radiation projected on a plane (Wh/m²)). Th...

Voyant, Cyril; Randimbivololona, Prisca; Nivet, Marie Laure; Paoli, Christophe; Muselli, Marc

296

Scientific Electronic Library Online (English)

Full Text Available Abstract in spanish En este trabajo se presenta la aplicación de redes neuronales (RNs) en la reconstrucción tridimensional de objetos y su utilización en tareas de calibración en sistemas de proyección de luz estructurada. En una primer propuesta, se establece una red neuronal que utiliza funciones de base radial (RNFBR) útil para calibrar un sistema de proyección de franjas. En este caso la RNFBR es modelada para ajustar la información de fase, obtenida de los imágenes de franjas (more) a mediciones físicas reales. Se propone una segunda técnica que utiliza una red neuronal multicapas de perceptrones (RNMP) para la recuperación de fase y profundidad a partir de los patrones de franjas. En esta técnica se utiliza una ventana de análisis conteniendo subimágenes de los patrones de franjas. Esta subimagen es utilizada como entrada de la RNMP, obteniendo como salida las mediciones de los gradientes de fase o profundidad. Se presentan experimentos que aplican las técnicas propuestas para medir un objeto real. Abstract in english In this work the application of neural networks (NNs) in tridimensional object depth recovery and structured light projection system calibration tasks is presented. In a first approach, a NN using radial basis functions (RBFNN) is proposed to carry out fringe projection system calibration. In this case the RBFNN is modeled to fit the phase information (obtained from fringe images) to the real physical measurements. In a second approach, a Multilayer Perceptron Neural Netw (more) ork (MPNN) is applied to phase and depth recovery from the fringe patterns. A scanning window is used as the MPNN input and the phase or depth gradient measurements is obtained at the MPNN output. Experiments considering real object depth measurement are presented.

Cuevas de la Rosa, Francisco Javier; Servin Guirado, Manuel

2004-06-01

297

Handwritten Farsi Character Recognition using Artificial Neural Network

Directory of Open Access Journals (Sweden)

Full Text Available 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 error backpropagation algorithm are superior in recognition accuracy and memory usage. The result indicates that the backpropagation network provides good recognition accuracy of more than 80% of handwritten Farsi characters.

Reza Gharoie Ahangar; Mohammad Farajpoor Ahangar

2009-01-01

298

Weight Perturbation for Efficient Learning of Neural Networks

Energy Technology Data Exchange (ETDEWEB)

The Error Back-Propagation(EBP) algorithm is widely applied to train a multi-layer perceptron, which is a neural network model frequently employed in order to solve complex problems including pattern recognition and adaptive control. However, it suffers from two major problems: local minima and network structure design. This paper presents a modified error back-propagation algorithm which have the capability to solve the local minima problem and the network structure design in a unified and efficient way. Our algorithm is basically the same as the conventional EBP algorithm except application of stochastic perturbation in order to escape a local minimum. In our algorithm when a local minimum is detected weights associated with hidden units are probabilistically reinitialized and the normal EBP learning is continued with the new set of weights. Addition of a new hidden unit also can be viewed as a special case of stochastic perturbation, i.e., reinitializing all-zero weights of a virtually existing unit. The results of our experiments with several benchmark test problems, the parity problem and the two-spirals problem, including {sup c}redit-screening data, a practical problem of credit card approval, demonstrate that our algorithm is very efficient. (author). 11 refs., 4 figs., 3 tabs.

Kim, S.K. [Ansung National University, Ansung (Korea, Republic of); Min, C.W. [IBM Korea Inc., Seoul (Korea, Republic of); Kim, M.W. [Soongsil University, Seoul (Korea, Republic of)

1998-10-01

299

Identification and Prediction of Internet Traffic Using Artificial Neural Networks

Directory of Open Access Journals (Sweden)

Full Text Available This paper presents the development of an artificial neural network (ANN) model based on the multi-layer perceptron (MLP) for analyzing internet traffic data over IP networks. We applied the ANN to analyze a time series of measured data for network response evaluation. For this reason, we used the input and output data of an internet traffic over IP networks to identify the ANN model, and we studied the performance of some training algorithms used to estimate the weights of the neuron. The comparison between some training algorithms demonstrates the efficiency and the accu-racy of the Levenberg-Marquardt (LM) and the Resilient back propagation (Rp) algorithms in term of statistical crite-ria. Consequently, the obtained results show that the developed models, using the LM and the Rp algorithms, can successfully be used for analyzing internet traffic over IP networks, and can be applied as an excellent and fundamental tool for the management of the internet traffic at different times.

Samira Chabaa; Abdelouhab Zeroual; Jilali Antari

2010-01-01

300

QSO Selection and Photometric Redshifts with Neural Networks

Baryonic Acoustic Oscillations (BAO) and their effects on the matter power spectrum can be studied by using the Lyman-alpha absorption signature of the matter density field along quasar (QSO) lines of sight. A measurement sufficiently accurate to provide useful cosmological constraints requires the observation of ~100000 quasars in the redshift range 2.2

Yeche, Ch; Rich, J; Aubourg, E; Busca, N; Hamilton, J -Ch; Goff, J -M Le; Paris, I; Peirani, S; Pichon, Ch; Rollinde, E; Vargas-Magana, M

2009-01-01

301

Neural network diagnostic system for dengue patients risk classification.

UK PubMed Central (United Kingdom)

With the dramatic increase of the worldwide threat of dengue disease, it has been very crucial to correctly diagnose the dengue patients in order to decrease the disease severity. However, it has been a great challenge for the physicians to identify the level of risk in dengue patients due to overlapping of the medical classification criteria. Therefore, this study aims to construct a noninvasive diagnostic system to assist the physicians for classifying the risk in dengue patients. Systematic producers have been followed to develop the system. Firstly, the assessment of the significant predictors associated with the level of risk in dengue patients was carried out utilizing the statistical analyses technique. Secondly, Multilayer perceptron neural network models trained via Levenberg-Marquardt and Scaled Conjugate Gradient algorithms was employed for constructing the diagnostic system. Finally, precise tuning for the models' parameters was conducted in order to achieve the optimal performance. As a result, 9 noninvasive predictors were found to be significantly associated with the level of risk in dengue patients. By employing those predictors, 75% prediction accuracy has been achieved for classifying the risk in dengue patients using Scaled Conjugate Gradient algorithm while 70.7% prediction accuracy were achieved by using Levenberg-Marquardt algorithm.

Faisal T; Taib MN; Ibrahim F

2012-04-01

302

Hidden Conditional Neural Fields for Continuous Phoneme Speech Recognition

In this paper, we propose Hidden Conditional Neural Fields (HCNF) for continuous phoneme speech recognition, which are a combination of Hidden Conditional Random Fields (HCRF) and a Multi-Layer Perceptron (MLP), and inherit their merits, namely, the discriminative property for sequences from HCRF and the ability to extract non-linear features from an MLP. HCNF can incorporate many types of features from which non-linear features can be extracted, and is trained by sequential criteria. We first present the formulation of HCNF and then examine three methods to further improve automatic speech recognition using HCNF, which is an objective function that explicitly considers training errors, provides a hierarchical tandem-style feature and includes a deep non-linear feature extractor for the observation function. We show that HCNF can be trained realistically without any initial model and outperforms HCRF and the triphone hidden Markov model trained by the minimum phone error (MPE) manner using experimental results for continuous English phoneme recognition on the TIMIT core test set and Japanese phoneme recognition on the IPA 100 test set.

Fujii, Yasuhisa; Yamamoto, Kazumasa; Nakagawa, Seiichi

303

AN EFFICIENT NEURAL NETWORK FOR RECOGNIZING GESTURAL HINDI DIGITS

Directory of Open Access Journals (Sweden)

Full Text Available Handwritten Hindi digit recognition plays an important role in eastern Arab countries especially in the courtesy amounts of Arab bank checks, recognizing numbers in car plates, or in postal code for mail sorting. In our study, we proposed an efficient Hindi Digit Recognition System drawn by the mouse and developed using Multilayer Perceptron Neural Network (MLP) with backpropagation. The system has been designed, implemented and tested successfully. Analysis has been carried out to determine the number of hidden nodes that achieves high performance. The proposed system has been trained on samples of 800 images and tested on samples of 300 images written by different users selected from different ages. An experimental result shows high accuracy of about 91% on the testing samples and very close to 100% on the training samples. Experiments showed that our result is high in comparison with other Hindi digit recognition systems especially if we consider the way of writing (mouse and children) in our trained and tested results.

Nidal Fawzi Shilbayeh; Mohammad Mahmmoud Alwakeel; Maisa Mohy Naser

2013-01-01

304

Scientific Electronic Library Online (English)

Full Text Available Abstract in spanish En este artículo, se modela el precio promedio mensual del café colombiano en la Bolsa de Nueva York, usando varios modelos alternativos. El modelo final seleccionado está compuesto por una componente lineal autorregresiva más una red neuronal artificial tipo perceptron multicapa con dos neuronas en la capa oculta, que permite representar la dinámica que sigue el valor esperado de la serie de precios; mientras que la dinámica de los residuales es especificada usando (more) un proceso heterocedástico condicional autoregresivo de primer orden. Los residuales normalizados del modelo son incorrelacionados y homocedásticos, y siguen aproximadamente una distribución normal. Los resultados indican que el precio actual depende de los precios ocurridos en los últimos cuatro meses. Abstract in english In this paper, the monthly average price of the Colombian coffee in the New York Stock Exchange, is modelling by means of several alternative models. The preferred model is composed by a lineal autoregressive component plus a multilayer perceptron neural network with two neurons in the hidden layer, that allow us to representing the dynamic following by the expected value of the price time series; while, the dynamic of the residuals is specified by an autoregressive condi (more) tional heterocedastic model of first order. The normalized residuals of the preferred model are uncorrelated, homocedastic and are distributed following a normal distribution. The results indicate that the current price depend of the prices in the previous four months.

Velásquez Henao, Juan David; Aldana Dumar, Mario Alberto

2007-12-01

305

Using more than 1000 thin section photos of ancient (Phanerozoic) carbonates from different marine environments (pelagic to shallow-water) a new numerical methodology, based on digitized images of thin sections, is proposed here. In accordance with the Dunham classification, it allows the user to automatically identify carbonate textures unaffected by post-depositional modifications (recrystallization, dolomitization, meteoric dissolution and so on). The methodology uses, as input, 256 grey-tone digital image and by image processing gives, as output, a set of 23 values of numerical features measured on the whole image including the “white areas” (calcite cement). A multi-layer perceptron neural network takes as input this features and gives, as output, the estimated class. We used 532 images of thin sections to train the neural network, whereas to test the methodology we used 268 images taken from the same photo collection and 215 images from San Lorenzello carbonate sequence (Matese Mountains, southern Italy), Early Cretaceous in age. This technique has shown 93.3% and 93.5% of accuracy to classify automatically textures of carbonate rocks using digitized images on the 268 and 215 test sets, respectively. Therefore, the proposed methodology is a further promising application to the geosciences allowing carbonate textures of many thin sections to be identified in a rapid and accurate way. A MATLAB-based computer code has been developed for the processing and display of images.

Marmo, Roberto; Amodio, Sabrina; Tagliaferri, Roberto; Ferreri, Vittoria; Longo, Giuseppe

2005-06-01

306

A new approach for locating the minor apical foramen using an artificial neural network.

UK PubMed Central (United Kingdom)

AIM: To develop a new approach for locating the minor apical foramen (AF) using feature-extracting procedures from radiographs and then processing data using an artificial neural network (ANN) as a decision-making system. METHODOLOGY: Fifty straight single-rooted teeth were selected and placed in a socket within the alveolar bone of a dried skull. Access cavities were prepared and a file was place in the canals to determine the working length. A radiograph was taken to evaluate the location of the file in relation to the minor foramen and further checked after retrieving the tooth from the alveolar socket. The location of the file tip was categorized into: beyond the AF (long), within the root canal (short) and just at the minor AF (exact). Each radiograph was used to extract relevant features using K-means, Otsu method and Wavelet protocol. Thirty-six extracted features were used for training and the rest were used for evaluating the multi-layer Perceptron ANN model. RESULTS: Analysis of the images from radiographs (test samples) by ANN showed that in 93% of the samples, the location of the AF had been determined correctly by false rejection and acceptation error methods. CONCLUSION: Artificial neural networks can act as a second opinion to locate the AF on radiographs to enhance the accuracy of working length determination by radiography. In addition, ANN can function as a decision-making system in various similar clinical situations.

Saghiri MA; Asgar K; Boukani KK; Lotfi M; Aghili H; Delvarani A; Karamifar K; Saghiri AM; Mehrvarzfar P; Garcia-Godoy F

2012-03-01

307

UK PubMed Central (United Kingdom)

This study examined the potential of artificial neural network (ANN) modeling to infer timing, route and dose of contaminant exposure from biomarkers in a freshwater fish. Hepatic glutathione S-transferase (GST) activity and biliary concentrations of BaP, 1-OH BaP, 3-OH BaP and 7,8D BaP were quantified in juvenile Clarias gariepinus injected intramuscularly or intraperitoneally with 10-50 mg/kg benzo[a]pyrene (BaP) 1-3 d earlier. A feedforward multilayer perceptron (MLP) ANN resulted in more accurate prediction of timing, route and exposure dose than a linear neural network or a radial basis function (RBF) ANN. MLP sensitivity analyses revealed contribution of all five biomarkers to predicting route of exposure but no contribution of hepatic GST activity or one of the two hydroxylated BaP metabolites to predicting time of exposure and dose of exposure. We conclude that information content of biomarkers collected from fish can be extended by judicious use of ANNs.

Karami A; Christianus A; Bahraminejad B; Gagné F; Courtenay SC

2012-03-01

308

UK PubMed Central (United Kingdom)

OBJECTIVES: Artificial neural networks (ANNs) have been increasingly used in diagnosis and the prediction of outcome, mortality, and risk factors in ischemic stroke. Each model may have different accuracy, sensitivity, and specificity in processing the same clinical information. Thus, using only one model of ANNs may mislead the prediction. The present study aimed to predict symptomatic intracerebral hemorrhage (SICH) following thrombolysis in acute ischemic stroke based on clinical, laboratory, and imaging data using multiple ANN models. METHODS: Models for radial basis function (RBF), multilayer perceptron (MLP), probabilistic neural network (PNN), and support vector machine (SVM) were generated to analyze 194 datasets with 29 predictive variables. The relative importance of each predictor variable was calculated using sensitivity analysis. RESULTS: Comparison among the models based on the areas under the receiver operating characteristic curves (AUC) showed no significantly statistical difference in predictive performance among RBF, MLP, and PNN. PNN showed significantly better performance than SVM. With a minimum importance score of 50 together with an AUC value ?0·50, three models identified stroke subtype as an important predictive variable for SICH. Other potential predictors were stroke location, prothrombin time, low-density-lipoprotein cholesterol, diastolic blood pressure, International Normalized Ratio, and brain computed tomography findings. DISCUSSION: Although ANN models showed similar performance, the classification results were not totally alike, suggesting an advantage of using multiple classification models over a single model. The predictive results are supported by previous statistical studies on different datasets, suggesting generalizability of the utility of ANN analyses.

Dharmasaroja P; Dharmasaroja PA

2012-03-01

309

Artificial neural networks based predictive model for worker assignment into virtual cells

Directory of Open Access Journals (Sweden)

Full Text Available Virtual cellular manufacturing systems (VCMS) have come into existence, replacing traditional cellular manufacturing systems (CMS), to meet highly dynamic production conditions in terms of demand, processing times, product mix and processing sequence. While cell formation phase of VCMS has been dealt quite voluminously, worker assignments phase has gained momentum recently after researchers started realizing the importance of workers’ role during implementation of cell-based manufacturing. In the past, worker assignments have been analyzed with development of various heuristics/mathematical models in order to achieve reduced worker costs, improved productivity and quality, effective utilization of workforce and providing adequate levels of worker flexibility. In this paper, a new approach based on artificial neural networks (ANNs) has been proposed to assign workers into virtual cells since ANNs have the ability to model complex relationships between inputs and outputs and find similar patterns effectively. A framework of multilayered perceptron with feed forward (MLP-FF) neural network has been formulated on worker assignment for VCMS under dual resource constrained (DRC) context and its performance under two cell configurations with different time periods is analyzed. A worker assignment model has been developed and applied with cell formation solutions available in the literature in order to generate simulated datasets that drive the training process of proposed ANN framework.

R.V. Murali; A.B. Puri; G. Prabhakaran

2010-01-01

310

International Nuclear Information System (INIS)

A nuclear power plant's (NPP's) status is usually monitored by a human operator. Any classifier system used to enhance the operator's capability to diagnose a safety-critical system like an NPP should classify a novel transient as ''don't-know'' if it is not contained within its accumulated knowledge base. In particular, the classifier needs some kind of proximity measure between the new data and its training set. Artificial neural networks have been proposed as NPP classifiers, the most popular ones being the multilayered perceptron (MLP) type. However, MLPs do not have a proximity measure, while learning vector quantization, probabilistic neural networks (PNNs), and some others do. This proximity measure may also serve as an explanation to the classifier's decision in the way that case-based-reasoning expert systems do. The capability of a PNN network as a classifier is demonstrated using simulator data for the three-loop 436-MW(electric) Westinghouse San Onofre unit 1 pressurized water reactor. A transient's classification history is used in an ''evidence accumulation'' technique to enhance a classifier's accuracy as well as its consistency

1995-01-01

311

THYROID DISEASE DETECTION USING MODIFIED FUZZY HYPERLINE SEGMENT CLUSTERING NEURAL NETWORK

Directory of Open Access Journals (Sweden)

Full Text Available Two common diseases of the thyroid gland, which releases thyroid hormones for regulating the rate of body’s metabolism, are hyperthyroidism and hypothyroidism. The classification of these thyroid diseases is a one of the considerable tasks. In this work we propose modified fuzzy hyperline segment clustering neural network (MFHLSCNN) for classification of thyroid disease diagnosis. The MFHLSCNN algorithm is suitable for clustering and classification. This algorithm can learn ill-defined nonlinear cluster boundaries in a few passes and is suitable for on-line adaptation. The work is extension of fuzzy hyperline segment clustering neural network (FHLSCNN) proposed by Kulkarni U. V. and Sontakke T. R. Both the algorithms utilize fuzzy sets as pattern clusters in which each fuzzy set is an union of fuzzy set hyperline segments. The fuzzy set hyperline segment is an n-dimensional hyperline segment defined by two end points with a corresponding membership function. The modification of intersection test in the MFHLSCNN has resulted in improved performance. The thyroid dataset is taken from UCI machine learning repository. The results obtained with the proposed approach are compared with the multilayer perceptron (MLP) trained using error backpropagation and FHLSCNN. The experimental results show that performance of the proposed approach is superior as compared to MLP and FHLSCNN. Moreover training time and recall time per pattern of MFHLSCNN and FHLSCNN is very less as compared to MLP.

Satish N. Kulkarni; Dr. A. R. Karwankar

2012-01-01

312

The computer-aided diagnosis system we developed for the mass characterization is mainly based on a segmentation algorithm and on the neural classification of several features computed on the segmented mass. Mass segmentation plays a key role in most computerized systems. Our technique is a gradient-based one, showing the main characteristic that no free parameters have been evaluated on the dataset used in this analysis, thus it can directly be applied to datasets acquired in different conditions without any ad-hoc modification. A dataset of 226 masses (109 malignant and 117 benign) has been used in this study. The segmentation algorithm works with a comparable efficiency both on malignant and benign masses. Sixteen features based on shape, size and intensity of the segmented masses are analyzed by a multi-layered perceptron neural network. A feature selection procedure has been carried out on the basis of the feature discriminating power and of the linear correlations interplaying among them. The comparison...

Delogu, P; Kasae, P; Retico, A

2008-01-01

313

Creep Crack Growth Modeling of Low Alloy Steel using Artificial Neural Network

Directory of Open Access Journals (Sweden)

Full Text Available Prediction of crack growth under creep condition is prime requirement in order to avoid costly and time-consuming creep crack growth tests. To predict, in a reliable way, the growth of a major crack in a structural components operating at high temperatures, requires a fracture mechanics based approach. In this Study a novel technique, which uses Finite Element Method (FEM) together with Artificial Neural Networks (ANN) has been developed to predict the fracture mechanics parameter (C*) in a 1%Cr1%MoV low alloy rotor steel under wide range of loading and temperatures. After confirming the validity of the FEM model with experimental data, a collection of numerical and experimental data has been used for training the various neural networks models. Three networks have been used to simulate the process, the perceptron multilayer network with tangent transfer function that uses 9 neurons in the hidden layer, gives the best results. Finally, for validation three case studies at 538°C, 550°C and 594°C temperatures are employed. The proposed model has proved that a combinations of ANN and FEM simulation performs well in estimation of C* and it is a powerful designing tool for creep crack growth characterization.

F. Djavanroodi

2013-01-01

314

Artificial neural networks for simulating wind effects on sprinkler distribution patterns

Energy Technology Data Exchange (ETDEWEB)

A new approach based on Artificial Neural Networks (ANNs) is presented to simulate the effects of wind on the distribution pattern of a single sprinkler under a center pivot or block irrigation system. Field experiments were performed under various wind conditions (speed and direction). An experimental data from different distribution patterns using a Nelson R3000 Rotator sprinkler have been split into three and used for model training, validation and testing. Parameters affecting the distribution pattern were defined. To find an optimal structure, various networks with different architectures have been trained using an Early Stopping method. The selected structure produced R2 0.929 and RMSE = 6.69 mL for the test subset, consisting of a Multi-Layer Perceptron (MLP) neural network with a backpropagation training algorithm; two hidden layers (twenty neurons in the first hidden layer and six neurons in the second hidden layer) and a tangent-sigmoid transfer function. This optimal network was implemented in MATLAB to develop a model termed ISSP (Intelligent Simulator of Sprinkler Pattern). ISSP uses wind speed and direction as input variables and is able to simulate the distorted distribution pattern from a R3000 Rotator sprinkler with reasonable accuracy (R{sup 2} > 0.935). Results of model evaluation confirm the accuracy and robustness of ANNs for simulation of a single sprinkler distribution pattern under real field conditions. (Author) 41 refs.

Sayyadi, H.; Sadraddini, A. A.; Farsadi Zadeh, D.; Montero, J.

2012-07-01

315

Foreground removal from CMB temperature maps using an MLP neural network

DEFF Research Database (Denmark)

One of the main obstacles for extracting the Cosmic Microwave Background (CMB) signal from observations in the mm-submm range is the foreground contamination by emission from Galactic components: mainly synchrotron, free-free and thermal dust emission. Due to the statistical nature of the intrinsic CMB signal it is essential to minimize the systematic errors in the CMB temperature determinations. Following the available knowledge of the spectral behavior of the Galactic foregrounds simple power law-like spectra have been assumed. The feasibility of using a simple neural network for extracting the CMB temperature signal from the combined signal CMB and the foregrounds has been investigated. As a specific example, we have analysed simulated data, as expected from the ESA Planck CMB mission. A simple multilayer perceptron neural network with 2 hidden layers can provide temperature estimates over more than 80 per cent of the sky that are to a high degree uncorrelated with the foreground signals. A single network will be able to cover the dynamic range of the Planck noise level over the entire sky.

NØrgaard-Nielsen, Hans Ulrik; JØrgensen, H.E.

2008-01-01

316

A telemedicine system using communication and information technology to deliver medical signals such as ECG, EEG for long distance medical services has become reality. In either the urgent treatment or ordinary healthcare, it is necessary to compress these signals for the efficient use of bandwidth. This paper discusses a quality on demand compression of EEG signals using neural network predictors for telemedicine applications. The objective is to obtain a greater compression gains at a low bit rate while preserving the clinical information content. A two-stage compression scheme with a predictor and an entropy encoder is used. The residue signals obtained after prediction is first thresholded using various levels of thresholds and are further quantized and then encoded using an arithmetic encoder. Three neural network models, single-layer and multi-layer perceptrons and Elman network are used and the results are compared with linear predictors such as FIR filters and AR modeling. The fidelity of the reconstructed EEG signal is assessed quantitatively using parameters such as PRD, SNR, cross correlation and power spectral density. It is found from the results that the quality of the reconstructed signal is preserved at a low PRD thereby yielding better compression results compared to results obtained using lossless scheme.

Sriraam, N.

2011-01-01

317

Artificial Neural Network Simulation and Sensitivity Analysis of Heavy Oil Cracking Unit

Directory of Open Access Journals (Sweden)

Full Text Available This paper presents an artificial neural network (ANN) model of heavy oil catalytic cracking (HOC). The main feature of the model is to provide general and accurate and fast responding model for analysis of HOC unit. In this study, American petroleum institute index (API) , weight percentage of sulfur, Conradson carbon residue content (CCR), gas, coke, and liquid volume percent conversion (%LV) of reaction were considered as network inputs while the percentage of normal butane (N-C4), iso-butane (I-C4), butene (C4=), propane (C3), propene (C3=), heavy cycle oil (HCO), and light cycle oil (LCO) and gasoline (GASO) were considered as network outputs. 70% of all industrial collected data set were utilized to train and find the best neural network. Among the different networks, feed-forward multi-layer perceptron network with Levenberg Marquardt (LM) training algorithm with 10 neurons in hidden layer was found as the best network. The trained network showed good capability in anticipating the results of the unseen data (30% of the all data) of catalytic cracking unit with high accuracy. The obtained model can be used in optimization and process planning.

Sheikhattar L.; Hashim H.; Zahedi G.

2011-01-01

318

Neural and fuzzy computation techniques for playout delay adaptation in VoIP networks.

UK PubMed Central (United Kingdom)

Playout delay adaptation algorithms are often used in real time voice communication over packet-switched networks to counteract the effects of network jitter at the receiver. Whilst the conventional algorithms developed for silence-suppressed speech transmission focused on preserving the relative temporal structure of speech frames/packets within a talkspurt (intertalkspurt adaptation), more recently developed algorithms strive to achieve better quality by allowing for playout delay adaptation within a talkspurt (intratalkspurt adaptation). The adaptation algorithms, both intertalkspurt and intratalkspurt based, rely on short term estimations of the characteristics of network delay that would be experienced by up-coming voice packets. The use of novel neural networks and fuzzy systems as estimators of network delay characteristics are presented in this paper. Their performance is analyzed in comparison with a number of traditional techniques for both inter and intratalkspurt adaptation paradigms. The design of a novel fuzzy trend analyzer system (FTAS) for network delay trend analysis and its usage in intratalkspurt playout delay adaptation are presented in greater detail. The performance of the proposed mechanism is analyzed based on measured Internet delays. Index Terms-Fuzzy delay trend analysis, intertalkspurt, intratalkspurt, multilayer perceptrons (MLPs), network delay estimation, playout buffering, playout delay adaptation, time delay neural networks (TDNNs), voice over Internet protocol (VoIP).

Ranganathan MK; Kilmartin L

2005-09-01

319

Neural and fuzzy computation techniques for playout delay adaptation in VoIP networks.

Playout delay adaptation algorithms are often used in real time voice communication over packet-switched networks to counteract the effects of network jitter at the receiver. Whilst the conventional algorithms developed for silence-suppressed speech transmission focused on preserving the relative temporal structure of speech frames/packets within a talkspurt (intertalkspurt adaptation), more recently developed algorithms strive to achieve better quality by allowing for playout delay adaptation within a talkspurt (intratalkspurt adaptation). The adaptation algorithms, both intertalkspurt and intratalkspurt based, rely on short term estimations of the characteristics of network delay that would be experienced by up-coming voice packets. The use of novel neural networks and fuzzy systems as estimators of network delay characteristics are presented in this paper. Their performance is analyzed in comparison with a number of traditional techniques for both inter and intratalkspurt adaptation paradigms. The design of a novel fuzzy trend analyzer system (FTAS) for network delay trend analysis and its usage in intratalkspurt playout delay adaptation are presented in greater detail. The performance of the proposed mechanism is analyzed based on measured Internet delays. Index Terms-Fuzzy delay trend analysis, intertalkspurt, intratalkspurt, multilayer perceptrons (MLPs), network delay estimation, playout buffering, playout delay adaptation, time delay neural networks (TDNNs), voice over Internet protocol (VoIP). PMID:16252825

Ranganathan, Mohan Krishna; Kilmartin, Liam

2005-09-01

320

UK PubMed Central (United Kingdom)

In this paper, a novel heuristic structure optimization methodology for radial basis probabilistic neural networks (RBPNNs) is proposed. First, a minimum volume covering hyperspheres (MVCH) algorithm is proposed to select the initial hidden-layer centers of the RBPNN, and then the recursive orthogonal least square algorithm (ROLSA) combined with the particle swarm optimization (PSO) algorithm is adopted to further optimize the initial structure of the RBPNN. The proposed algorithms are evaluated through eight benchmark classification problems and two real-world application problems, a plant species identification task involving 50 plant species and a palmprint recognition task. Experimental results show that our proposed algorithm is feasible and efficient for the structure optimization of the RBPNN. The RBPNN achieves higher recognition rates and better classification efficiency than multilayer perceptron networks (MLPNs) and radial basis function neural networks (RBFNNs) in both tasks. Moreover, the experimental results illustrated that the generalization performance of the optimized RBPNN in the plant species identification task was markedly better than that of the optimized RBFNN.

Huang DS; Du JX

2008-12-01

321

Most real and engineered systems include multiple subsystems and layers of connectivity, and it is important to take such features into account to try to obtain a complete understanding of these systems. It is thus necessary to generalize "traditional" network theory by developing (and validating) a framework and associated tools to study multilayer systems in a comprehensive fashion. The origins of such efforts occurred several decades ago, but now the study of multilayer networks has become one of the major directions in network science. In this paper, we discuss the history of multilayer networks (and related concepts) and then review the exploding body of work on such networks. To unify the disparate terminology in the large body of recent work, we discuss a general framework for multilayer networks, construct a dictionary of terminology to relate the numerous existing concepts to each other, and provide a thorough discussion that compares, contrasts, and translates between related notions such as multila...

Kivelä, Mikko; Barthelemy, Marc; Gleeson, James P; Moreno, Yamir; Porter, Mason A

2013-01-01

322

Directory of Open Access Journals (Sweden)

Full Text Available Objetivando classificar terras para irrigação, faz-se necessário analisar e determinar alguns parâmetros, entre eles a produtividade do solo. A classificação de produtividade (comumente chamada fertilidade aparente) é delimitada em cinco classes: muito alta, alta, média, baixa e muito baixa, e em cada classe é preciso avaliar certos atributos do solo, como pH, CTC (capacidade de troca de cátions), V% (índice de saturação por bases), P (fósforo), Mg (magnésio) e K (potássio). Neste trabalho, objetivou-se identificar a produtividade na qual atributos do solo, da parte inicial da microbacia hidrográfica do Rio Pardo, localizada em Pardinho, SP, foram analisados e classificados nas classes que a delimitam, através de Redes Neurais Artificiais (RNAs) utilizandose Perceptron Múltiplas Camadas (Multilayers Perceptrons - MLP) com o algoritmo de treinamento "backpropagation"- classificador de padrões, obtendo-se um número ótimo de camadas intermediárias e de neurônios; resultando na classificação de produtividade, a situação ótima da rede obteve 78% dos resultados iguais aos desejados, com duas camadas de neurônios, uma das quais intermediária, com 5 neurônios, e uma camada de saída.Productivity data (commonly known as apparent fertility) of the initial part of the river Pardo-SP watershed was analyzed and classified with Artificial Neural Networks (ANNs), in order to classify lands for irrigation. Soil attributes as pH, CEC (cation exchange capacity), V% (base saturation index), P (phosphorus), Mg (magnesium) and K (potassium) were defined in five classes: very high, high, medium, low and very low. Apparent fertility classification taking into account the five classes was performed by using Multiple Layers Perceptron (MLP). Backpropagation algorithm was performed with the training set. One hidden layer with 5 neurons was the situation that best performed.

Luciana C. Bucene; Luiz H. A. Rodrigues

2004-01-01

323

Modeling of gamma-ray energy absorption buildup factors using neural network

Energy Technology Data Exchange (ETDEWEB)

This paper presents a new approach based on multilayered perceptrons (MLPs) to compute energy absorption buildup factors. The MLP has been trained by a Levenberg-Marquardt learning algorithm. The model is fast and does not require tremendous computational efforts. The results obtained by using the proposed model are in good agreement with the ANSI/ANS-6.4.3 standard data set.

Kucuk, Nil [Physics Department, Faculty of Arts and Sciences, Uludag University, Gorukle Campus, 16059 Bursa (Turkey)], E-mail: nilkoc@uludag.edu.tr

2008-10-15

324

Modeling of gamma-ray energy absorption buildup factors using neural network

International Nuclear Information System (INIS)

This paper presents a new approach based on multilayered perceptrons (MLPs) to compute energy absorption buildup factors. The MLP has been trained by a Levenberg-Marquardt learning algorithm. The model is fast and does not require tremendous computational efforts. The results obtained by using the proposed model are in good agreement with the ANSI/ANS-6.4.3 standard data set.

2008-01-01

325

Using Probabilistic Neural Networks for Handwritten Digit Recognition

Digital Repository Infrastructure Vision for European Research (DRIVER)

Artificial neural networks are well known in the field of pattern recognition and machine learning. Multi-layer neural networks are usually used as universal neural classifiers even though probabilistic neural networks represent a special type of artificial neural networks and have been designed to ...

Abdelhadi Lotfi; Abdelkader Benyettou

326

UK PubMed Central (United Kingdom)

We give an adversary strategy that forces the Perceptron algorithm to make OmegaGamma kN ) mistakes in learning monotone disjunctions over N variables with at most k literals. In contrast, Littlestone's algorithm Winnow makes at most O(k log N ) mistakes for the same problem. Both algorithms use thresholded linear functions as their hypotheses. However, Winnow does multiplicative updates to its weight vector instead of the additive updates of the Perceptron algorithm. The Perceptron algorithm is an example of additive algorithms, which have the property that their weight vector is always a sum of a fixed initial weight vector and some linear combination of already seen instances. We show that an adversary can force any additive algorithm to make (N + k Gamma 1)=2 mistakes in learning a monotone disjunction of at most k literals. Simple experiments show that for k N , Winnow clearly outperforms the Perceptron algorithm also on nonadversarial random data.

J. Kivinen; M. K. Warmuth; Peter Auer

327

Holographic implementation of a learning machine based on a multicategory perceptron algorithm.

UK PubMed Central (United Kingdom)

An optical learning machine that has multicategory classification capability is demonstrated. The system exactly implements the single-layer perceptron algorithm and is fully parallel and analog. Experimental results on the learning by examples obtained from the system are described.

Paek EG; Wullert Ii JR; Patel JS

1989-12-01

328

Identification of Non-Linear Structures using Recurrent Neural Networks

Digital Repository Infrastructure Vision for European Research (DRIVER)

Two different partially recurrent neural networks structured as Multi Layer Perceptrons (MLP) are investigated for time domain identification of a non-linear structure. , To be presented at the 13th Int. Modal Analysis Conference, Nashville, Tennessee, February 1995 PDF for print: 13 pp

Kirkegaard, Poul Henning; Nielsen, Søren R. K.; Hansen, H. I.

329

Ranking Algorithms for Named-Entity Extraction: Boosting and the Voted Perceptron

UK PubMed Central (United Kingdom)

We describe algorithms that rerank the top N hypotheses from a maximum-entropy tagger, the application being named-entity recognition in a corpus of web data. The first approach uses a boosting algorithm for ranking problems. The second approach uses the voted perceptron algorithm. Both algorithms give comparable, significant improvements over the maximum-entropy baseline. The voted perceptron algorithm can be considerably more efficient to train, at some cost in computation on test examples.

Michael Collins; Florham Park

330

Scientific Electronic Library Online (English)

Full Text Available Abstract in spanish En este trabajo se presenta una red neuronal perceptron multicapa combinada con el método Nelder-Mead Simplex para detectar daño en vigas. Los parámetros de entrada a la red se basan en frecuencias naturales y flexibilidad modal. Se considera que solo una cantidad específica de modos fueron identificados y que se dispone de mediciones en grados de libertad verticales. La confiabilidad de la metodología propuesta se evalúa a partir de escenarios de daño aleatorios y (more) de la definición de 3 tipos de error que la red puede cometer durante el proceso de detección del daño. Los resultados muestran que la metodología puede determinar confiablemente los escenarios de daño buscados. Sin embargo, su aplicación a vigas de gran tamaño puede verse limitada por el elevado costo computacional asociado al entrenamiento de la red. Abstract in english In this paper is presented a multilayer perceptron neural network combined with the Nelder-Mead Simplex method to detect damage in multiple support beams. The input parameters are based on natural frequencies and modal flexibility. It was considered that only a number of modes were available and that only vertical degrees of freedom were measured. The reliability of the proposed methodology is assessed from the generation of random damages scenarios and the definition of (more) three types of errors, which can be found during the damage identification process. Results show that the methodology can reliably determine the damage scenarios. However, its application to large beams may be limited by the high computational cost of training the neural network.

Villalba, Jesús D.; Gómez, Ivan D.; Laier, José E.

2012-06-01

331

Directory of Open Access Journals (Sweden)

Full Text Available Martine Ferguson1, Marc Boyer1, Robert Sprando21United States Food and Drug Administration, Center for Food Safety and Applied Nutrition, Office of Food Defense Communication and Emergency Response, Division of Public Health and Biostatistics, College Park, MD, USA; 2United States Food and Drug Administration, Center for Food Safety and Applied Nutrition, Office of Applied Research and Safety Assessment, Division of Toxicology, Laurel, MD, USAAbstract: Caenorhabditis elegans (L1s) were exposed to (in order of decreasing toxicity) sodium arsenite, sodium fluoride, caffeine, valproic acid, sodium borate, or dimethyl sulfoxide in C. elegans habitation medium (CeHM) for 72 consecutive hours. At this time point nematode growth and development were assessed using a Complex Object Parametric Analyzer and Sorter (COPAS™). The COPAS generated biomarkers of growth (time of flight [TOF] – a measure of axial length) and development (extinction [EXT] – a measure of optical density) were subsequently utilized to rank compounds according to their relative toxicity, as measured by the rat oral LD-50, using artificial neural network methods. Neural network methods were utilized to analyze this data because of their ability to model nonlinear endpoints and a multilayer perceptron neural network method was used because of its capability to function well in the presence of collinearity. Using a neural network approach we found that the LD-50 was correctly predicted 96% of the time. The present study demonstrates that neural network methods can be utilized to rank compounds according to their relative toxicity using COPAS-generated data (TOF and EXT) obtained from exposing a large number of nematodes to water-soluble compounds in axenic liquid culture.Keywords: neural network, TOF, EXT, COPAS, C. elegans, rat oral LD-50

Martine Ferguson; Marc Boyer; Robert Sprando

2010-01-01

332

The infamous soils of Adapazari, Turkey, that failed extensively during the 46-s long magnitude 7.4 earthquake in 1999 have since been the subject of a research program. Boreholes, piezocone soundings and voluminous laboratory testing have enabled researchers to apply sophisticated methods to determine the soil profiles in the city using the existing database. This paper describes the use of the artificial neural network (ANN) model to predict the complex soil profiles of Adapazari, based on cone penetration test (CPT) results. More than 3236 field CPT readings have been collected from 117 soundings spread over an area of 26 km2. An attempt has been made to develop the ANN model using multilayer perceptrons trained with a feed-forward back-propagation algorithm. The results show that the ANN model is fairly accurate in predicting complex soil profiles. Soil identification using CPT test results has principally been based on the Robertson charts. Applying neural network systems using the chart offers a powerful and rapid route to reliable prediction of the soil profiles.

Arel, Ersin

2012-06-01

333

A neural network structure has been used for unfolding neutron spectra measured by means of a Bonner Sphere Spectrometer set and a foil activation set using several neutron induced reactions. The present work used the SNNS (Stuttgart Neural Network Simulator) as the interface for designing, training and validation of the Multilayer Perceptron network. The back-propagation algorithm was applied. The Bonner Sphere set chosen has been calibrated at the National Physical Laboratory, United Kingdom, and uses gold activation foils as thermal neutron detectors. The neutron energy covered by the response functions goes from 0.0001 eV to 14 MeV. The foil activation set chosen has been irradiated at the IEA-R1 research reactor and measured at the Nuclear Metrology Laboratory of IPEN-CNEN/SP. Two types of neutron spectra were numerically investigated: monoenergetic and continuous The unfolded spectra were compared to a conventional method using code SAND-II as part of the neutron dosimetry system SAIPS. Good results wer...

Braga, C C

2001-01-01

334

Statistical Mechanical Analysis of the Dynamics of Learning in Perceptrons

We describe the application of tools from statistical mechanics to analyse the dynamics of various classes of supervised learning rules in perceptrons. The character of this paper is mostly that of a cross between a biased non-encyclopedic review and lecture notes: we try to present a coherent and self-contained picture of the basics of this field, to explain the ideas and tricks, to show how the predictions of the theory compare with (simulation) experiments, and to bring together scattered results. Technical details are given explicitly in an appendix. In order to avoid distraction we concentrate the references in a final section. In addition this paper contains some new results: (i) explicit solutions of the macroscopic equations that describe the error evolution for on-line and batch learning rules, (ii) an analysis of the dynamics of arbitrary macroscopic observables (for complete and incomplete trainingsets), leading to a general Fokker-Planck equation, and (iii) the macroscopic laws describing batch le...

Mace, C W H

1997-01-01

335

Learning processes in multilayer threshold nets.

UK PubMed Central (United Kingdom)

An algorithm of learning in multilayer threshold nets without feedbacks is proposed. The net is built of threshold elements with binary inputs. During a learning process each input vector chi is accompanied by a teacher's decision omega (omega epsilon(1,...,M)). The pairs (chi[n], omega[n]) appear in successive steps independently according to some unknown stationary distribution p(chi, omega). The problem of learning of a threshold net has been decomposed to a series of problems of learning of the threshold elements. The proposed learning algorithm of the threshold elements has a perceptron-like form. It was proven that a decision rule of the threshold net stabilizes after a finite number of steps. For definite classes (p(chi,omega))K of distributions p(chi, omega), an optimal decision rule stabilizes after a finite number of steps. These classes (p(chi, omega))K also contain distributions describing learning processes with perturbations.

Bobrowski L

1978-11-01

336

Scientific Electronic Library Online (English)

Full Text Available Abstract in portuguese Estudar modelagens através de dados geodésicos temporais com a possibilidade de predizer a posição de linha de costa é uma tarefa importante e pode auxiliar significativamente na gestão costeira. A área de estudo neste trabalho se refere ao município de Matinhos no estado do Paraná, Brasil. As linhas de costa temporais utilizadas para testar a modelagem preditiva são provenientes respectivamente da fotogrametria analógica para anos 1954, 1963, 1980, 1991 e 1997 (more) e de levantamentos geodésicos utilizando GPS (Global Position System) para 2001, 2002, 2005 e 2008 (como controle). Dois testes com as redes neurais artificiais foram organizados mudando alguns parâmetros como: arquitetura, número de neurônios nas camadas ocultas e algoritmos de treinamentos. Quando comparados o valor dos resíduos entre a predição e a linha de costa de controle, os melhores resultados estatísticos indicam que o MAPE (mean absolute percentage error) são 0,28% utilizando a rede neural parcialmente recorrente de Elman com o algoritmo de treinamento quase-Newton e 0,46% para o caso da rede neural perceptron multicamadas com o algoritmo de treinamento utilizando o método Bayesiano com regularização. Abstract in english The study of models using geodetic temporal data which can possibly predict the shoreline position is an important task and can significantly contribute to coastal management. The studied area is located at municipality of Matinhos in the Paraná State, Brazil. The temporal shoreline used to test the prediction model is respectively from analog photogrammetric data, related to the years 1954, 1963, 1980, 1991 and 1997, and GPS (Global Position System) geodetic surveys for (more) 2001, 2002, 2005 and 2008 (as control). Two different tests with artificial neural network were organized setting the parameters like: architecture, number of neuron in hidden layers and the training algorithms. Comparing the residuals between the prediction to the shoreline of control, the best statistical results show the MAPE (Mean Absolute Percentage Error) is 0,28% using the Elman partially recurrent network with quasi-Newton training function and 0,46% using the neural network multilayer perceptron with Bayesian regulation training function.

Gonçalves, Rodrigo Mikosz; Coelho, Leandro dos Santos; Krueger, Claudia Pereira; Heck, Bernhard

2010-09-01

337

Energy Technology Data Exchange (ETDEWEB)

The analysis of openhole wireline logs is of great importance for the subsurface mapping of geological layers and the identification and quantification of hydrocarbon and mineral deposits. An important aspects to construct a geological model of the reservoir is the well-to-well log correlation, which can be a tedious and time-consuming task for the geologist. Automating this procedure is complicated but potentially rewarding because it may save the production geologist and log analyst substantial amount of time. Artificial neural networks have been shown to handle this task efficiently including in cases where sequential algorithms have problems. We show in this paper that a neural networks can be used to perform the well-to-well log correlation to provide first approximation od the geological model of the reservoir. This procedure is shown on actual field data. (author)

Andrade, Andre J.N. [Para Univ., Belem, PA (Brazil); Luthi, Stefan M. [Schlumberger Wireline Service, Montrouge (France)

1997-07-01

338

Statistical Mechanics of On-line Ensemble Teacher Learning through a Novel Perceptron Learning Rule

In ensemble teacher learning, ensemble teachers have only uncertain information about the true teacher, and this information is given by an ensemble consisting of an infinite number of ensemble teachers whose variety is sufficiently rich. In this learning, a student learns from an ensemble teacher that is iteratively selected randomly from a pool of many ensemble teachers. An interesting point of ensemble teacher learning is the asymptotic behavior of the student to approach the true teacher by learning from ensemble teachers. The student performance is improved by using the Hebbian learning rule in the learning. However, the perceptron learning rule cannot improve the student performance. On the other hand, we proposed a perceptron learning rule with a margin. This learning rule is identical to the perceptron learning rule when the margin is zero and identical to the Hebbian learning rule when the margin is infinity. Thus, this rule connects the perceptron learning rule and the Hebbian learning rule continuously through the size of the margin. Using this rule, we study changes in the learning behavior from the perceptron learning rule to the Hebbian learning rule by considering several margin sizes. From the results, we show that by setting a margin of ?>0, the effect of an ensemble appears and becomes significant when a larger margin ? is used.

Hara, Kazuyuki; Miyoshi, Seiji

2012-06-01

339

Birch pollen is one of the main causes of allergy during spring and early summer in northern and central Europe. The aim of this study was to create a forecast model that can accurately predict daily average concentrations of Betula sp. pollen grains in the atmosphere of Szczecin, Poland. In order to achieve this, a novel data analysis technique—artificial neural networks (ANN)—was used. Sampling was carried out using a volumetric spore trap of the Hirst design in Szczecin during 2003-2009. Spearman's rank correlation analysis revealed that humidity had a strong negative correlation with Betula pollen concentrations. Significant positive correlations were observed for maximum temperature, average temperature, minimum temperature and precipitation. The ANN resulted in multilayer perceptrons 366 8: 2928-7-1:1, time series prediction was of quite high accuracy (SD Ratio between 0.3 and 0.5, R > 0.85). Direct comparison of the observed and calculated values confirmed good performance of the model and its ability to recreate most of the variation.

Puc, Ma?gorzata

2012-03-01

340

Here, the temperature performance of a two-phase closed thermosyphon (TPCT) was investigated using two synthesized nanofluids, including carbon nano-tube (CNT)/water and CNT-Ag/water. In order to determine the temperature performance of a TPCT, the experiments were performed for various values of weight fraction and input power. To predict the other experimental conditions, a reliable and accurate tool should be applied. Therefore Artificial Neural Network (ANN) was applied to predict the process performance. Using ANN, the operating parameters, including distribution of wall temperature (T) and the temperature difference between the input and the output water streams of condenser section (?T) were determined. To achieve this goal, the multi-layer perceptron network was employed. The Levenberg-Marquardt algorithm was chosen as learning algorithm of this network. The results of simulation showed an excellent agreement with the data resulted from the experiments. Therefore it is possible to say that ANN is a powerful tool to predict the performance of different processes.

Shanbedi, Mehdi; Jafari, Dariush; Amiri, Ahmad; Heris, Saeed Zeinali; Baniadam, Majid

2013-01-01

341

Prediction of Natural Frequency of Laminated Composite Plates Using Artificial Neural Networks

Directory of Open Access Journals (Sweden)

Full Text Available The paper is focused on the application of artificial neural networks (ANN) in predicting the natural frequency of laminated composite plates under clamped boundary condition. For training and testing of the ANN model, a number of finite element analyses have been carried out using D-optimal design in the design of experiments (DOE) by varying the fibre orientations, –45?, 0?, 45? and 90?. The composite plate is modeled using linear layered structural shell element. The natural frequencies were found by analyses which were done by finite element (FE) analysis software. The ANN model has been developed using multilayer perceptron (MLP) back propagation algorithm. The adequacy of the developed model is verified by coefficient of determination (R). It was found that the R2 (R: coefficient of determination) values are 1 and 0.998 for train and test data respectively. The results showed that, the training algorithm of back propagation was sufficient enough in predicting the natural frequency of laminated composite plates. To judge the ability and efficiency of the developed ANN model, absolute relative error has been used. The results predicted by ANN are in very good agreement with the finite element (FE) results. Consequently, the D-optimal design and ANN are shown to be effective in predicting the natural frequency of laminated composite plates.

Mutra Raja Sekhara Reddy; Bathini Sidda Reddy; Vanguru Nageswara Reddy; Surisetty Sreenivasulu

2012-01-01

342

The use of concentrators implies that CPV systems only work with the Direct Normal Irradiance (DNI). So it is necessary to know DNI data in order to estimate the energy that will be produced by the system, perform economic analysis, supervise plant operation, etc. However, DNI Typical Meteorological Year datasets are expensive and rarely available due to the cost and sophistication of measurement devices and data processing requirements. Particularly, there is a lack of data on the Sunbelt countries, which are more favorable for the use of CPV. In this work, an artificial neural network is used for the generation of DNI hourly time series for some Spanish locations. The model was trained and tested with different locations and different year's data. Although several authors have proposed different methods for the generation of solar radiation synthetic series, these methods are for global radiation and flat panel, nevertheless, we calculate them for direct normal solar radiation and used for CPV systems. A Multilayer Perceptron is explained, looking over the first rudimentary initial version and the last more elaborated final version. Finally, an application of this methodology is presented.

Rodrigo, J.; Hontoria, L.; Almonacid, F.; Fernández, Eduardo F.; Rodrigo, P. M.; Pérez-Higueras, P. J.

2012-10-01

343

A novel neural network approach to cDNA microarray image segmentation.

UK PubMed Central (United Kingdom)

Microarray technology has become a great source of information for biologists to understand the workings of DNA which is one of the most complex codes in nature. Microarray images typically contain several thousands of small spots, each of which represents a different gene in the experiment. One of the key steps in extracting information from a microarray image is the segmentation whose aim is to identify which pixels within an image represent which gene. This task is greatly complicated by noise within the image and a wide degree of variation in the values of the pixels belonging to a typical spot. In the past there have been many methods proposed for the segmentation of microarray image. In this paper, a new method utilizing a series of artificial neural networks, which are based on multi-layer perceptron (MLP) and Kohonen networks, is proposed. The proposed method is applied to a set of real-world cDNA images. Quantitative comparisons between the proposed method and commercial software GenePix(®) are carried out in terms of the peak signal-to-noise ratio (PSNR). This method is shown to not only deliver results comparable and even superior to existing techniques but also have a faster run time.

Wang Z; Zineddin B; Liang J; Zeng N; Li Y; Du M; Cao J; Liu X

2013-07-01

344

Comparative Study of Artificial Neural Network and ARIMA Models in Predicting Exchange Rate

Directory of Open Access Journals (Sweden)

Full Text Available Capital market as an organized market has an effective role in mobilizing financial resources due to have growth and economic development of countries and many countries now in the finance firms is responsible for the required credits. In the stock market, shareholders are always seeking the highest efficiency, so the stock price prediction is important for them. Since the stock market is a nonlinear system under conditions of political, economic and psychological, it is difficult to predict the correct stock price. Thus, in the present study artificial intelligence and ARIMA method has been used to predict stock prices. Multilayer Perceptron neural network and radial basis functions are two methods used in this research. Evaluation methods, selection methods and exponential smoothing methods are compared to random walk. The results showed that AI-based methods used in predicting stock performance are more accurate. Between two methods used in artificial intelligence, a method based on radial basis functions is capable to estimate stock prices in the future with higher accuracy.

karamollah Bagherifard; Mehrbakhsh Nilashi; Othman Ibrahim; Nasim Janahmadi; Leila Ebrahimi

2012-01-01

345

A novel neural network approach to cDNA microarray image segmentation.

Microarray technology has become a great source of information for biologists to understand the workings of DNA which is one of the most complex codes in nature. Microarray images typically contain several thousands of small spots, each of which represents a different gene in the experiment. One of the key steps in extracting information from a microarray image is the segmentation whose aim is to identify which pixels within an image represent which gene. This task is greatly complicated by noise within the image and a wide degree of variation in the values of the pixels belonging to a typical spot. In the past there have been many methods proposed for the segmentation of microarray image. In this paper, a new method utilizing a series of artificial neural networks, which are based on multi-layer perceptron (MLP) and Kohonen networks, is proposed. The proposed method is applied to a set of real-world cDNA images. Quantitative comparisons between the proposed method and commercial software GenePix(®) are carried out in terms of the peak signal-to-noise ratio (PSNR). This method is shown to not only deliver results comparable and even superior to existing techniques but also have a faster run time. PMID:23669179

Wang, Zidong; Zineddin, Bachar; Liang, Jinling; Zeng, Nianyin; Li, Yurong; Du, Min; Cao, Jie; Liu, Xiaohui

2013-05-11

346

Directory of Open Access Journals (Sweden)

Full Text Available The prediction accuracy and generalization of fermentation process modeling on exopolysaccharide (EPS) production from Lactobacillus are often deteriorated by noise existing in the corresponding experimental data. In order to circumvent this problem, a novel entropy-based criterion is proposed as the objective function of several commonly used modeling methods, i.e. Multi-Layer Perceptron (MLP) network, Radial Basis Function (RBF) neural network, Takagi-Sugeno-Kang (TSK) fuzzy system, for fermentation process model in this study. Quite different from the traditional Mean Square Error (MSE) based criterion, the novel entropy-based criterion can be used to train the parameters of the adopted modeling methods from the whole distribution structure of the training data set, which results in the fact that the adopted modeling methods can have global approximation capability. Compared with the MSE- criterion, the advantage of this novel criterion exists in that the parameter learning can effectively avoid the over-fitting phenomenon, therefore the proposed criterion based modeling methods have much better generalization ability and robustness. Our experimental results confirm the above virtues of the proposed entropy-criterion based modeling methods.

Zuo-Ping Tan; Shi-Tong Wang; Zhao-Hong Deng; Guo-Cheng Du

2010-01-01

347

Optimization of bending sequence in roll forming using neural network and genetic algorithm

International Nuclear Information System (INIS)

In the roll forming process, the bending sequence plays a major role in the product quality. The optimal bending sequence results in the smallest number of passes and the flawless process. This paper presents a new optimization procedure of bending sequence in a roll forming process. The multilayer perceptron is used to build the neural network (NN), which models the variation of longitudinal strain in process while the genetic algorithm (GA) is employed to optimize the bending sequence. The data used for training the network is automatically obtained by the integration between CAD and CAE. The values of peak longitudinal strains are maximized while the number of passes is reduced to the smallest and the constraint conditions being set on the maximal longitudinal strain to avoid buckling. The overbending at final pass after spring back is also considered in this paper. Two roll forming processes are optimized in order to prove applicability and efficiency of the optimization procedure. This method maintains the longitudinal strain less than the buckling limit, whereas reducing the number of passes to the smallest. Thus, the advantages of the proposed method show the high applicability in designing and optimizing the bending sequence in the roll forming process

2011-01-01

348

Optimization of bending sequence in roll forming using neural network and genetic algorithm

Energy Technology Data Exchange (ETDEWEB)

In the roll forming process, the bending sequence plays a major role in the product quality. The optimal bending sequence results in the smallest number of passes and the flawless process. This paper presents a new optimization procedure of bending sequence in a roll forming process. The multilayer perceptron is used to build the neural network (NN), which models the variation of longitudinal strain in process while the genetic algorithm (GA) is employed to optimize the bending sequence. The data used for training the network is automatically obtained by the integration between CAD and CAE. The values of peak longitudinal strains are maximized while the number of passes is reduced to the smallest and the constraint conditions being set on the maximal longitudinal strain to avoid buckling. The overbending at final pass after spring back is also considered in this paper. Two roll forming processes are optimized in order to prove applicability and efficiency of the optimization procedure. This method maintains the longitudinal strain less than the buckling limit, whereas reducing the number of passes to the smallest. Thus, the advantages of the proposed method show the high applicability in designing and optimizing the bending sequence in the roll forming process.

Park, Hong Seok; Anh, Tran Viet [University of Ulsan, Ulsan (Korea, Republic of)

2011-08-15

349

Energy Technology Data Exchange (ETDEWEB)

Polycyclic aromatic hydrocarbon formation in combustion systems has received considerable attention because of its health effects. The feed-forward, multi-layer perceptron type artificial neural networks with back-propagation learning were used to predict the total PAH amount in atmospheric pressure, premixed n-heptane and n-heptane/oxygenate flames. MTBE and ethanol were used as fuel oxygenates. The total fifty-four data sets were divided into three groups: training, cross-validation, and testing. The different network architectures were tested and the best predictions were obtained for a network of one hidden layer with five neurons. The transfer function was sigmoid function. The mean square and mean absolute errors were 10.52 and 2.60 ppm for the testing set, respectively. The correlation coefficient (R{sup 2}) was 0.98. The results also showed that the total PAH amount was significantly influenced by the changes in equivalence ratio, presence of fuel oxygenates, and mole fractions of C{sub 4} species. (author)

Inal, Fikret [Department of Chemical Engineering, Izmir Institute of Technology, Gulbahce-Urla, 35430 Izmir (Turkey)

2006-11-15

350

Energy Technology Data Exchange (ETDEWEB)

Overvoltages are one of the most frequently encountered problems during line energization. At the time of restoration transmission line switching is also one of the major causes, which creates overvoltage. The magnitude and shape of the switching overvoltages vary with the system parameters and network configuration and the point-on-wave where the switching operation takes place. Though detailed electromagnetic transient studies carried out for the design of transmission systems, such studies are not common in a day-to-day operation of power system. However it is important for the operator to ensure that peak overvoltages resulting from the switching operations are well within safe limits. This paper presents an Artificial Neural Network (ANN)-based approach to estimate the peak overvoltage generated by switching transients during line energization. In proposed methodology Levenberg-Marquardt method is used to train the multilayer perceptron. The developed ANN is trained with the extensive simulated results, and tested for typical cases. The simulated results presented clearly show that the proposed technique can estimate the peak values of switching overvoltages with good accuracy. (author)

Thukaram, D.; Khincha, H.P.; Khandelwal, Sulabh [Department of Electrical Engineering, Indian Institute of Science, Bangalore 560012 (India)

2006-01-15

351

NEURAL NETWORKS FOR THE SIMULATION OF MICROCLIMATIC PARAMETERS IN DAIRY HOUSES

Directory of Open Access Journals (Sweden)

Full Text Available The aim of the present paper is to study natural ventilation in a dairy house by means of a parametric analysis relating wind speed and direction to the air flows through the ridge vent of the building. This analysis was carried out by means of an artificial neural network (ANN) which capability in modelling and simulating some climatic parameters inside a dairy house has been validated using the data collected in a trial carried out during summer 2005. The results show that modelling a Generalized feed-forward Multi-Layer Perceptron ANN allowed to obtain satisfactory results in the simulation of air speed and direction and air temperature and humidity inside a dairy house, using as input the values of wind speed and direction and outdoor air temperature and humidity. The adequate accuracy in the simulation of the air motion across the ridge vent allowed to perform a parametric analysis of the ventilation, which provided the values of air speed and direction in function of a fixed range of values of wind speed and direction.

Alessandro D'Emilio; Rosari Mazzarella; Simona M.C. Porto

2009-01-01

352

UK PubMed Central (United Kingdom)

In this letter, we demonstrate that the generalization properties of a neural network (NN) can be extended to encompass objects that obscure or segment the original image in its foreground or background. We achieve this by piloting an extension of the noise injection training technique, which we term excessive noise injection (ENI), on a simple feedforward multilayer perceptron (MLP) network with vanilla backward error propagation to achieve this aim. Six tests are reported that show the ability of an NN to distinguish six similar states of motion of a simplified human figure that has become obscured by moving vertical and horizontal bars and random blocks for different levels of obscuration. Four more extensive tests are then reported to determine the bounds of the technique. The results from the ENI network were compared to results from the same NN trained on clean states only. The results pilot strong evidence that it is possible to track a human subject behind objects using this technique, and thus this technique lends itself to a real-time markerless tracking system from a single video stream.

Unsworth CP; Coghill G

2006-09-01

353

UK PubMed Central (United Kingdom)

An artificial neural network (ANN) can help in the prediction of advanced water treatment effluent and thus facilitate design practices. In this study, sets of 225 experimental data were obtained from a wastewater treatment process for the removal of phosphorus using oven-dried alum residuals in fixed-bed adsorbers. Five input variables (pH, initial phosphorus concentration, wastewater flow rate, porosity, and time) were used to test the efficiency of phosphorus removal at different times, and ANNs were then used to predict the effluent phosphorus concentration. Results of experiments that were conducted for different values of the input parameters made up the data used to train and test a multilayer perceptron using the back-propagation algorithm of the ANN. Values predicted by the ANN and the experimentally measured values were compared, and the accuracy of the ANN was evaluated. When ANN results were compared to the experimental results, it was concluded that the ANN results were accurate, especially during conditions of high phosphorus concentration. While the ANN model was able to predict the breakthrough point with good accuracy, the conventional advection-diffusion equation was not as accurate. A parametric study conducted to examine the effect of the initial pH and initial phosphorus concentration on the effluent phosphorus concentration at different times showed that lower influent pH values are the most suitable for this advanced treatment system.

Mortula MM; Abdalla J; Ghadban AA

2012-07-01

354

Statistical downscaling of extreme rainfall events in Romania using artificial neural networks

The main purpose of statistical downscaling methods is to model the relationship between large-scale atmospheric circulation and climatic variables on a regional and subregional scale. Downscaling is an important area of research as it bridges the gap between predictions of future circulation generated by General Circulation Models (GCMs) and the effects of climate change on smaller areas. In this study we present the first results of a statistical downscaling model, using a neural network-based approach by means of multi-layer perceptron networks. As predictands, various indices associated to temperature and precipitation extremes in Romania are used over the entire country (for temperature extremes) and on selected homogenous areas (for precipitation extremes). Several large-scale predictors (sea-level pressure, temperature at 850 / 700 hPa, specific humidity at 850 / 700 hPa) are tested, in order to select the optimum statistical model for each predictand. Predictands are considered separately or in various combinations. This work has been realised within the research project "Changes in climate extremes and associated impact in hydrological events in Romania" (CLIMHYDEX), code PN II-ID-2011-2-0073, financed by the Romanian Executive Agency for Higher Education Research, Development and Innovation Funding (UEFISCDI).

Birsan, Marius-Victor; Busuioc, Aristita; Dumitrescu, Alexandru

2013-04-01

355

UK PubMed Central (United Kingdom)

This paper proposes a multiclassification algorithm using multilayer perceptron neural network models. It tries to boost two conflicting main objectives of multiclassifiers: a high correct classification rate level and a high classification rate for each class. This last objective is not usually optimized in classification, but is considered here given the need to obtain high precision in each class in real problems. To solve this machine learning problem, we use a Pareto-based multiobjective optimization methodology based on a memetic evolutionary algorithm. We consider a memetic Pareto evolutionary approach based on the NSGA2 evolutionary algorithm (MPENSGA2). Once the Pareto front is built, two strategies or automatic individual selection are used: the best model in accuracy and the best model in sensitivity (extremes in the Pareto front). These methodologies are applied to solve 17 classification benchmark problems obtained from the University of California at Irvine (UCI) repository and one complex real classification problem. The models obtained show high accuracy and a high classification rate for each class.

Fernández Caballero JC; Martínez FJ; Hervás C; Gutiérrez PA

2010-05-01

356

Directory of Open Access Journals (Sweden)

Full Text Available Considering the significance of the Sodium Adsorption Ratio (SAR) for growing plants, its prediction is essential for water quality management for irrigation. The SAR prediction in Chelghazy River in Kurdistan, northwest of Iran, using an Artificial Neural Network (ANN) was studied. The study applied the Multilayer Perceptron (MLP) of the ANN to average monthly data, which was collected by the water authority of the Kurdistan province for the period of 1998-2009. The input parameters of the MLP network was pH, discharge, sulfate, sodium, calcium, chloride, magnesium and bicarbonate, and output was predictive of the SAR. The results showed a correlation coefficient 0.976 between actual and predicted SAR, which means the accuracy of the model is acceptable. The model uses the input parameters to predict the SAR at the same month. The sensitivity analysis indicated the prediction of the SAR was affected by merely pH and calcium. As a whole, the MLP of the ANN may be applicable for prediction of the SAR which is necessary parameter ration for agriculture.

Gholamreza Asadollahfardi; Azadeh Hemati; Saber Moradinejad; Rashin Asadollahfardi

2013-01-01

357

UK PubMed Central (United Kingdom)

We give an adversary strategy that forces thePerceptron algorithm to make (N Gamma k + 1)=2mistakes when learning k-literal disjunctionsover N variables. Experimentally we see thateven for simple random data, the number ofmistakes made by the Perceptron algorithmgrows almost linearly with N , even if the numberk of relevant variable remains a small constant.In contrast, Littlestone's algorithmWinnow makes at most O(k log N ) mistakesfor the same problem. Both algorithms uselinear threshold functions as their hypotheses.However, Winnow does multiplicative updatesto its weight vector instead of the additive updatesof the Perceptron algorithm.1 IntroductionThis paper addresses the familiar problem of predictingwith a linear threshold function. The instances are N -dimensional real vectors, and a threshold function isgiven by an N-dimensional real weight vector w anda real threshold `. The linear threshold function hasthe value 1 on an instance x if w Delta x `, a...

Jyrki Kivinen; Manfred K. Warmuth

358

UK PubMed Central (United Kingdom)

We give an adversary strategy that forces the Perceptron algorithm to makeOmegaGamma kN) mistakes in learning monotone disjunctions over N variables with at mostk literals. In contrast, Littlestone's algorithm Winnow makes at most O(k log N)mistakes for the same problem. Both algorithms use thresholded linear functionsas their hypotheses. However, Winnow does multiplicative updates to its weightvector instead of the additive updates of the Perceptron algorithm. In general, wecall an algorithm additive if its weight vector is always a sum of a fixed initial weightvector and some linear combination of already seen instances. Thus, the Perceptronalgorithm is an example of an additive algorithm. We show that an adversary canforce any additive algorithm to make (N +k Gamma 1)=2 mistakes in learning a monotonedisjunction of at most k literals. Simple experiments show that for k ø N , Winnowclearly outperforms the Perceptron algorithm also on nonadversarial random data.Keywo...

J. Kivinen; M. K. Warmuth; P. Auer

359

Using an Easy Calculable Complexity Measure to Introduce Complexity in the Artificial Neuron Model

Directory of Open Access Journals (Sweden)

Full Text Available This study introduces an approach to simulate neural complexity by changing the McCulloch and Pitts neuron model. The new approach was tested by comparing the classification performance of a multilayer perceptron with complexity measurement capability to a traditional multilayer perceptron with McCulloch and Pitts neuron model The results showed that the multilayer perceptron implemented with the complexity measurement approach achieved best classification performance (worst score of 94%) when compared with multilayer perceptron without the complexity approach (best score of 51%) in task of classifier large time series generated by a logistic map with different generator parameter.

Ana Carolina Sousa Silva; Sergio Souto; Euvaldo Ferreira Cabral Jr.; Ernane Jose Xavier Costa

2007-01-01

360

UK PubMed Central (United Kingdom)

To solve the complicated problem of water-stage predictions under the interaction of upstream flows and tidal effects during typhoon attacks, this article presents a novel approach to river-stage predictions. The proposed CART-ANN model combines both the decision trees (classification and regression trees [CART]) and the artificial neural network (ANN) techniques, which comprise the multilayer perceptron (MLP) and radial basis function (RBFNN). The combined CART-ANN model involves a two-step predicting process. First, the CART stage-level classifier can classify the river stages into higher, middle, and lower levels. Then, the ANN-based water-stage predictors are employed to predict the water stages. The proposed model was applied to the Tanshui River Basin in Taiwan. The Taipei Bridge, which is close to the estuary and affected by tidal effects, was taken as the study gauge. The mean square error and the mean absolute error were used for evaluating the variance and bias performances of the models. This study makes two contributions. First, the CART-MLP and CART-RBF were modeled to predict river stages under tidal effects during typhoons, and they were compared with three benchmark models, CART, back-propagation neural network, and RBFNN. Second, the CART-RBF successfully demonstrated that it achieved more accurate prediction than CART-MLP and three benchmark models.

Tsai CC; Lu MC; Wei CC

2012-02-01

361

Directory of Open Access Journals (Sweden)

Full Text Available This paper outlines the application of the multi-layer perceptron artificial neural network (ANN), ordinary kriging (OK), and inverse distance weighting (IDW) models in the estimation of local scour depth around bridge piers. As part of this study, bridge piers were installed with bed sills at the bed of an experimental flume. Experimental tests were conducted under different flow conditions and varying distances between bridge pier and bed sill. The ANN, OK and IDW models were applied to the experimental data and it was shown that the artificial neural network model predicts local scour depth more accurately than the kriging and inverse distance weighting models. It was found that the ANN with two hidden layers was the optimum model to predict local scour depth. The results from the sixth test case showed that the ANN with one hidden layer and 17 hidden nodes was the best model to predict local scour depth. Whereas the results from the fifth test case found that the ANN with three hidden layers was the best model to predict local scour depth.

Homayoon Seyed Rahman; Keshavarzi Alireza; Gazni Reza

2010-01-01

362

UK PubMed Central (United Kingdom)

Human neural stem/precursor cells (hNSC/hNPC) have been targeted for application in a variety of research models and as prospective candidates for cell-based therapeutic modalities in central nervous system (CNS) disorders. To this end, the successful derivation, expansion, and sustained maintenance of undifferentiated hNSC/hNPC in vitro, as artificial expandable neurogenic micro-niches, promises a diversity of applications as well as future potential for a variety of experimental paradigms modeling early human neurogenesis, neuronal migration, and neurogenetic disorders, and could also serve as a platform for small-molecule drug screening in the CNS. Furthermore, hNPC transplants provide an alternative substrate for cellular regeneration and restoration of damaged tissue in neurodegenerative disorders such as Parkinson's disease and Alzheimer's disease. Human somatic neural stem/progenitor cells (NSC/NPC) have been derived from a variety of cadaveric sources and proven engraftable in a cytoarchitecturally appropriate manner into the developing and adult rodent and monkey brain while maintaining both functional and migratory capabilities in pathological models of disease. In the following unit, we describe a new procedure that we have successfully employed to maintain operationally defined human somatic NSC/NPC from developing fetal, pre-term post-natal, and adult cadaveric forebrain. Specifically, we outline the detailed methodology for in vitro expansion, long-term maintenance, manipulation, and transplantation of these multipotent precursors.

Wakeman DR; Hofmann MR; Redmond DE Jr; Teng YD; Snyder EY

2009-05-01

363

Human neural stem/precursor cells (hNSC/hNPC) have been targeted for application in a variety of research models and as prospective candidates for cell-based therapeutic modalities in central nervous system (CNS) disorders. To this end, the successful derivation, expansion, and sustained maintenance of undifferentiated hNSC/hNPC in vitro, as artificial expandable neurogenic micro-niches, promises a diversity of applications as well as future potential for a variety of experimental paradigms modeling early human neurogenesis, neuronal migration, and neurogenetic disorders, and could also serve as a platform for small-molecule drug screening in the CNS. Furthermore, hNPC transplants provide an alternative substrate for cellular regeneration and restoration of damaged tissue in neurodegenerative disorders such as Parkinson's disease and Alzheimer's disease. Human somatic neural stem/progenitor cells (NSC/NPC) have been derived from a variety of cadaveric sources and proven engraftable in a cytoarchitecturally appropriate manner into the developing and adult rodent and monkey brain while maintaining both functional and migratory capabilities in pathological models of disease. In the following unit, we describe a new procedure that we have successfully employed to maintain operationally defined human somatic NSC/NPC from developing fetal, pre-term post-natal, and adult cadaveric forebrain. Specifically, we outline the detailed methodology for in vitro expansion, long-term maintenance, manipulation, and transplantation of these multipotent precursors. PMID:19455542

Wakeman, Dustin R; Hofmann, Martin R; Redmond, D Eugene; Teng, Yang D; Snyder, Evan Y

2009-05-01

364

COCOMO Estimates Using Neural Networks

Directory of Open Access Journals (Sweden)

Full Text Available Software cost estimation is an important phase in software development. It predicts the amount of effort and development time required to build a software system. It is one of the most critical tasks and an accurate estimate provides a strong base to the development procedure. In this paper, the most widely used software cost estimation model, the Constructive Cost Model (COCOMO) is discussed. The model is implemented with the help of artificial neural networks and trained using the perceptron learning algorithm. The COCOMO dataset is used to train and to test the network. The test results from the trained neural network are compared with that of the COCOMO model. The aim of our research is to enhance the estimation accuracy of the COCOMO model by introducing the artificial neural networks to it.

Anupama Kaushik; Ashish Chauhan; Deepak Mittal; Sachin Gupta

2012-01-01

365

Novel maximum-margin training algorithms for supervised neural networks.

This paper proposes three novel training methods, two of them based on the backpropagation approach and a third one based on information theory for multilayer perceptron (MLP) binary classifiers. Both backpropagation methods are based on the maximal-margin (MM) principle. The first one, based on the gradient descent with adaptive learning rate algorithm (GDX) and named maximum-margin GDX (MMGDX), directly increases the margin of the MLP output-layer hyperplane. The proposed method jointly optimizes both MLP layers in a single process, backpropagating the gradient of an MM-based objective function, through the output and hidden layers, in order to create a hidden-layer space that enables a higher margin for the output-layer hyperplane, avoiding the testing of many arbitrary kernels, as occurs in case of support vector machine (SVM) training. The proposed MM-based objective function aims to stretch out the margin to its limit. An objective function based on Lp-norm is also proposed in order to take into account the idea of support vectors, however, overcoming the complexity involved in solving a constrained optimization problem, usually in SVM training. In fact, all the training methods proposed in this paper have time and space complexities O(N) while usual SVM training methods have time complexity O(N (3)) and space complexity O(N (2)) , where N is the training-data-set size. The second approach, named minimization of interclass interference (MICI), has an objective function inspired on the Fisher discriminant analysis. Such algorithm aims to create an MLP hidden output where the patterns have a desirable statistical distribution. In both training methods, the maximum area under ROC curve (AUC) is applied as stop criterion. The third approach offers a robust training framework able to take the best of each proposed training method. The main idea is to compose a neural model by using neurons extracted from three other neural networks, each one previously trained by MICI, MMGDX, and Levenberg-Marquard (LM), respectively. The resulting neural network was named assembled neural network (ASNN). Benchmark data sets of real-world problems have been used in experiments that enable a comparison with other state-of-the-art classifiers. The results provide evidence of the effectiveness of our methods regarding accuracy, AUC, and balanced error rate. PMID:20409990

Ludwig, Oswaldo; Nunes, Urbano

2010-04-19

366

Novel maximum-margin training algorithms for supervised neural networks.

UK PubMed Central (United Kingdom)

This paper proposes three novel training methods, two of them based on the backpropagation approach and a third one based on information theory for multilayer perceptron (MLP) binary classifiers. Both backpropagation methods are based on the maximal-margin (MM) principle. The first one, based on the gradient descent with adaptive learning rate algorithm (GDX) and named maximum-margin GDX (MMGDX), directly increases the margin of the MLP output-layer hyperplane. The proposed method jointly optimizes both MLP layers in a single process, backpropagating the gradient of an MM-based objective function, through the output and hidden layers, in order to create a hidden-layer space that enables a higher margin for the output-layer hyperplane, avoiding the testing of many arbitrary kernels, as occurs in case of support vector machine (SVM) training. The proposed MM-based objective function aims to stretch out the margin to its limit. An objective function based on Lp-norm is also proposed in order to take into account the idea of support vectors, however, overcoming the complexity involved in solving a constrained optimization problem, usually in SVM training. In fact, all the training methods proposed in this paper have time and space complexities O(N) while usual SVM training methods have time complexity O(N (3)) and space complexity O(N (2)) , where N is the training-data-set size. The second approach, named minimization of interclass interference (MICI), has an objective function inspired on the Fisher discriminant analysis. Such algorithm aims to create an MLP hidden output where the patterns have a desirable statistical distribution. In both training methods, the maximum area under ROC curve (AUC) is applied as stop criterion. The third approach offers a robust training framework able to take the best of each proposed training method. The main idea is to compose a neural model by using neurons extracted from three other neural networks, each one previously trained by MICI, MMGDX, and Levenberg-Marquard (LM), respectively. The resulting neural network was named assembled neural network (ASNN). Benchmark data sets of real-world problems have been used in experiments that enable a comparison with other state-of-the-art classifiers. The results provide evidence of the effectiveness of our methods regarding accuracy, AUC, and balanced error rate.

Ludwig O; Nunes U

2010-06-01

367

Arabic Vowels Fuzzy Neural Network Recognition

Directory of Open Access Journals (Sweden)

Full Text Available In this study, We propose a fuzzy neural system containing inferred rules which are modelled separately by a three layer perceptron neural network giving the conclusion part according to the premise of the rule. Such a system is applied to different morphology words for Arabic vowels recognition as a two-dimensional fuzzy implication presented in the form of linguistic features values. The system has been implemented on a real-time mini-computer and is now operational, the results concerning a multi-speaker corpus of continuous speech are also promising.

A. Taleb; A. Benyettou

2010-01-01

368

Directory of Open Access Journals (Sweden)

Full Text Available The succinic acid is a microorganism common metabolite used in the food market which is produced exclusively by fermentation, and great attention has been given to the use of renewable raw materials for this purpose. This study aimed to determine the variables that influence the production of succinic acid by fermentation using Actinobacillussuccinogenes strain (CIP 106512) through a fractional factorial design and to test different architectures of artificialneural networks to model this process. Artificial neural networks are madeof three layers and were the MultilayerPerceptron (MLP) type, with Backpropagation learning algorithm. Experimental data for learning and testing ofnetworks were used, 13 and 6, respectively. The number of neurons in the hidden layer, learning rate and activationfunctions was varied. After evaluation of architectures, it was found that the sigmoidal activation function showed abetter performance than the hyperbolic tangent and that the number of neurons and learning rate directly influencethe error. The neural model with the lowest squared error was the network with the sigmoid function, learning rate0,1 and 5 neurons in the intermediate layer. This work allowed to determine which variables most influence in thesuccinic acid production and in the construction of the neural model for this process.

Flaviana Diuk Andrade; Tatiane Gonzales; Ranulfo Monte Alegre; Elis Regina Duarte

2010-01-01

369

Holographic implementation of a learning machine based on a multicategory perceptron algorithm.

An optical learning machine that has multicategory classification capability is demonstrated. The system exactly implements the single-layer perceptron algorithm and is fully parallel and analog. Experimental results on the learning by examples obtained from the system are described. PMID:19759665

Paek, E G; Wullert Ii, J R; Patel, J S

1989-12-01

370

Ranking Algorithms for Named-Entity Extraction: Boosting and the Voted Perceptron

UK PubMed Central (United Kingdom)

This paper describes algorithms whichrerank the top N hypotheses from amaximum-entropy tagger, the applicationbeing the recovery of named-entityboundaries in a corpus of web data. Thefirst approach uses a boosting algorithmfor ranking problems. The second approachuses the voted perceptron algorithm.

Michael Collins

371

Artificial Neural Network Model for Forecasting Foreign Exchange Rate

Directory of Open Access Journals (Sweden)

Full Text Available The present statistical models used for forecasting cannot effectively handle uncertainty and instability nature of foreign exchange data. In this work, an artificial neural network foreign exchange rate forecasting model (AFERFM) was designed for foreign exchange rate forecasting to correct some of these problems. The design was divided into two phases, namely: training and forecasting. In the training phase, back propagation algorithm was used to train the foreign exchange rates and learn how to approximate input. Sigmoid Activation Function (SAF) was used to transform the input into a standard range [0, 1]. The learning weights were randomly assigned in the range [-0.1, 0.1] to obtain the output consistent with the training. SAF was depicted using a hyperbolic tangent in order to increase the learning rate and make learning efficient. Feed forward Network was used to improve the efficiency of the back propagation. Multilayer Perceptron Network was designed for forecasting. The datasets from oanda website were used as input in the back propagation for the evaluation and forecasting of foreign exchange rates. The design was implemented using matlab7.6 and visual studio because of their supports for implementing forecasting system. The system was tested using mean square error and standard deviation with learning rate of 0.10, an input layer, 3 hidden layers and an output layer. The best known related work, Hidden Markov foreign exchange rate forecasting model (HFERFM) showed an accuracy of 69.9% as against 81.2% accuracy of AFERFM. This shows that the new approach provided an improved technique for carrying out foreign exchange rate forecasting.

Adewole Adetunji Philip; Akinwale Adio Taofiki; Akintomide Ayo Bidem

2011-01-01

372

Scientific Electronic Library Online (English)

Full Text Available Abstract in portuguese Após 1991, a literatura sobre previsão de carga passou a ser dominada por propostas baseadas em modelos neurais. Entretanto, um empecilho na aplicação destes modelos reside na possibilidade do ajuste excessivo dos dados, i.e, overfitting. O excesso de não-linearidade disponibilizado pelos modelos neurais de previsão de carga, que depende da representação do espaço de entrada, vem sendo ajustado de maneira heurística. Modelos autônomos incluindo técnicas autom? (more) ?ticas e acopladas para seleção de entradas e controle de complexidade dos modelos foram propostos recentemente para previsão de carga em curto prazo. Entretanto, estas técnicas necessitam da especificação do conjunto inicial de entradas que será processado pelo modelo visando determinar aquelas mais relevantes. Este trabalho explora a teoria do caos como ferramenta de análise não-linear de séries temporais na definição automática do conjunto de atrasos de uma dada série de carga a serem utilizados como entradas de modelos neurais autônomos. Neste trabalho, inferência Bayesiana aplicada a perceptrons de múltiplas camadas e máquinas de vetores relevantes são utilizadas no desenvolvimento de modelos neurais autônomos. Abstract in english After 1991, the literature on load forecasting has been dominated by neural network based proposals. However, one major risk in using neural models is the possibility of excessive training, i.e., data overfitting. The extent of nonlinearity provided by neural network based load forecasters, which depends on the input space representation, has been adjusted using heuristic procedures. The empirical nature of these procedures makes their application cumbersome and time cons (more) uming. Autonomous modeling including automatic input selection and model complexity control has been proposed recently for short-term load forecasting. However, these techniques require the specification of an initial input set that will be processed by the model in order to select the most relevant variables. This paper explores chaos theory as a tool from non-linear time series analysis to automatic select the lags of the load series data that will be used by the neural models. In this paper, Bayesian inference applied to multi-layered perceptrons and relevance vector machines are used in the development of autonomous neural models.

Ferreira, Vitor Hugo; Silva, Alexandre Pinto Alves da

2011-12-01

373

Competing neural networks Finding a strategy for the game of matching pennies

The ability of a deterministic, plastic system to learn to imitate stochasticbehavior is analyzed. Two neural networks -actually, two perceptrons- are putto play a zero-sum game one against the other. The competition, by acting as akind of mutually supervised learning, drives the networks to produce anapproximation to the optimal strategy, that is to say, a random signal.

Samengo, I

2000-01-01

374

Modeling of the radioactive contamination of the Techa river by artificial neural networks

International Nuclear Information System (INIS)

This study examines the applicability of using artificial neural network in modeling radioactive contamination features for the Techa River. A multi layer perceptron trained with error back propagation algorithm was used to model processes of filtration of radioactive isotopes from the Techa Reservoirs to the Techa River and their migration in the river system. (authors)

2006-01-01

375

UK PubMed Central (United Kingdom)

Object constancy, the ability to recognize objects despite changes in orientation, has not been well studied in the auditory modality. Dolphins use echolocation for object recognition, and objects ensonified by dolphins produce echoes that can vary significantly as a function of orientation. In this experiment, human listeners had to classify echoes from objects varying in material, shape, and size that were ensonified with dolphin signals. Participants were trained to discriminate among the objects using an 18-echo stimulus from a 10° range of aspect angles, then tested with novel aspect angles across a 60° range. Participants were typically successful recognizing the objects at all angles (M = 78 %). Artificial neural networks were trained and tested with the same stimuli with the purpose of identifying acoustic cues that enable object recognition. A multilayer perceptron performed similarly to the humans and revealed that recognition was enabled by both the amplitude and frequency of echoes, as well as the temporal dynamics of these features over the course of echo trains. These results provide insight into representational processes underlying echoic recognition in dolphins and suggest that object constancy perceived through the auditory modality is likely to parallel what has been found in the visual domain in studies with both humans and animals.

Delong CM; Heberle AL; Wisniewski MG; Mercado E 3rd

2013-09-01

376

Energy Technology Data Exchange (ETDEWEB)

Voltage stability is one of the challenges facing electric utilities, particularly since modern day power systems are being operated close to their limits. Artificial neural networks (ANNs) have been used in recent years as a tool for online voltage stability assessment. In order to successfully use ANN, the potential inputs must be selected. This study proposed a regression-based method of computing sensitivities of the voltage stability margin with respect to different parameters. Important features were then chosen selectively to train separate Multilayer Perceptron Networks (MLP) to monitor voltage stability for different contingencies. An enhanced Radial Basis Function Network (RBFN) was then proposed for online monitoring of voltage stability. The proposed RBFN had important features, most notably, the same network was trained for multiple contingencies; the number of neurons in the hidden layers was decided automatically using a sequential learning strategy; it could be adapted online with changing operating scenarios; and, the growth of the network size was limited using a network pruning strategy. A sensitivity-based voltage stability enhancement method was also proposed, in which multiple contingencies were considered. Sensitivity information was used to find the correct amounts of generation rescheduling using linear optimization. The application of the proposed methods were demonstrated with case studies.

Chakrabarti, S.

2008-07-01

377

DEFF Research Database (Denmark)

Animal welfare is an issue of great importance in modern food production systems. Because animal behavior provides reliable information about animal health and welfare, recent research has aimed at designing monitoring systems capable of measuring behavioral parameters and transforming them into their corresponding behavioral modes. However, network unreliability and high-energy consumption have limited the applicability of those systems. In this study, a 2.4-GHz ZigBee-based mobile ad hoc wireless sensor network (MANET) that is able to overcome those problems is presented. The designed MANET showed high communication reliability, low energy consumption and low packet loss rate (14.8%) due to the deployment of modern communication protocols (e.g. multi-hop communication and handshaking protocol). The measured behavioral parameters were transformed into the corresponding behavioral modes using a multilayer 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 rate of behavior classification into five classes (i.e. grazing, lying down, walking, standing and others) was 76.2% (?mean=1.06)(?mean=1.06) on average. The results of this study showed an important improvement regarding the performance of the designed MANET and behavior classification compared to the results of other similar studies.

S. Nadimi, Esmaeil; Nyholm JØrgensen, Rasmus

2012-01-01

378

UK PubMed Central (United Kingdom)

Cardiac auscultatory proficiency of physicians is crucial for accurate diagnosis of many heart diseases. Plenty of diverse abnormal heart sounds with identical main specifications and different details representing the ambient noise are indispensably needed to train, assess and improve the skills of medical students in recognizing and distinguishing the primary symptoms of the cardiac diseases. This paper proposes a versatile multiresolution wavelet-based algorithm to first extract the main statistical characteristics of three well-known heart valve disorders, namely the aortic insufficiency, the aortic stenosis, and the pulmonary stenosis sounds as well as the normal ones. An artificial neural network (ANN) and statistical classifier are then applied alternatively to choose proper exclusive features. Both classification approaches suggest using Daubechies wavelet filter with four vanishing moments within five decomposition levels for the most prominent distinction of the diseases. The proffered ANN is a multilayer perceptron structure with one hidden layer trained by a back-propagation algorithm (MLP-BP) and it elevates the percentage classification accuracy to 94.42. Ultimately, the corresponding main features are manipulated in wavelet domain so as to sequentially regenerate the individual counterparts of the underlying signals.

Babaei S; Geranmayeh A

2009-01-01

379

Cardiac auscultatory proficiency of physicians is crucial for accurate diagnosis of many heart diseases. Plenty of diverse abnormal heart sounds with identical main specifications and different details representing the ambient noise are indispensably needed to train, assess and improve the skills of medical students in recognizing and distinguishing the primary symptoms of the cardiac diseases. This paper proposes a versatile multiresolution wavelet-based algorithm to first extract the main statistical characteristics of three well-known heart valve disorders, namely the aortic insufficiency, the aortic stenosis, and the pulmonary stenosis sounds as well as the normal ones. An artificial neural network (ANN) and statistical classifier are then applied alternatively to choose proper exclusive features. Both classification approaches suggest using Daubechies wavelet filter with four vanishing moments within five decomposition levels for the most prominent distinction of the diseases. The proffered ANN is a multilayer perceptron structure with one hidden layer trained by a back-propagation algorithm (MLP-BP) and it elevates the percentage classification accuracy to 94.42. Ultimately, the corresponding main features are manipulated in wavelet domain so as to sequentially regenerate the individual counterparts of the underlying signals. PMID:19081085

Babaei, Sepideh; Geranmayeh, Amir

2008-12-09

380

Accurate knowledge of the spatial extents and distributions of an oil spill is very impor-tant for efficient response. This is because most petroleum products spread rapidly on the water surface when released into the ocean, with the majority of the affected area becoming covered by very thin sheets. This article presents a study for examining the feasibility of Landsat ETM+ images in order to detect oil spills pollutions. The Landsat ETM+ images for 1st, 10th, 17th May 2010 were used to study the oil spill in Gulf of Mexico. In this article, an attempt has been made to perform ratio operations to enhance the feature. The study concluded that the bands difference between 660 and 560 nm, division at 660 and 560 and division at 825 and 560 nm, normalized by 480 nm provide the best result. Multilayer perceptron neural network classifier is used in order to perform a pixel-based supervised classification. The result indicates the potential of Landsat ETM+ data in oil spill detection. The promising results achieved encourage a further analysis of the potential of the optical oil spill detection approach.

Taravat, Alireza; Del Frate, Fabio

2012-12-01

381

International Nuclear Information System (INIS)

A technique for level measurement in pressure vessels was developed using thermal probes with internal cooling and artificial neural networks (ANN's). This new concept of thermal probes was experimentally tested in an experimental facility (BETSNI) with two test sections, ST1 and ST2. Two different thermal probes were designed and constructed: concentric tubes probe and U tube probe. A data acquisition system (DAS) was assembled to record the experimental data during the tests. Steady state and transient level tests were carried out and the experimental data obtained were used as learning and recall data sets in the ANN's program RETRO-05 that simulate a multilayer perceptron with backpropagation. The results of the analysis show that the technique can be applied for level measurements in pressure vessel. The technique is applied for a less input temperature data than the initially designed to the probes. The technique is robust and can be used in case of lack of some temperature data. Experimental data available in literature from electrically heated thermal probe were also used in the ANN's analysis producing good results. The results of the ANN's analysis show that the technique can be improved and applied to level measurements in pressure vessels. (author)

2008-01-01

382

Energy Technology Data Exchange (ETDEWEB)

Electric utilities perform economic dispatch (ED) procedures on a daily basis to satisfy the total system load at minimum operating cost. The procedure involves obtaining information on the available generating units for dispatch. In this study, an artificial neural network (ANN) was used to model the economic load dispatch (ELD) behaviour of generators in the Jamaican power system. A multilayered perceptron (MLP) ANN was used to model the function that relates the generators' outputs and total system demand at a time t to the output of a particular generator at time (t+T), where T is the dispatch period. This paper provided an overview of the ED problem and how it can be described mathematically using the Levenberg-Marquardt training algorithm. The architecture of the implemented ANN was also presented along with simulation design and results obtained using historical ELD data. This study represents the first step in ED prediction where not only the system demand is predicted but also the economic outputs of the system generators with inherent knowledge of systems constraints and operating policies. 16 refs., 4 figs.

Watt, V.H.C.; Darmand, A.B.; Reid, D. [Univ. of Technology, Kingston (Jamaica). School of Engineering

2007-07-01

383

Adopting the use of real-time odour monitoring in the smart home has the potential to alert the occupant of unsafe or unsanitary conditions. In this paper, we measured (with a commercial metal-oxide sensor-based electronic nose) the odours of five household foods that had been left out at room temperature for a week to spoil. A multilayer perceptron (MLP) neural network was trained to recognize the age of the samples (a quantity related to the degree of spoilage). For four of these foods, median correlation coefficients (between target values and MLP outputs) of R > 0.97 were observed. Fuzzy C-means clustering (FCM) was applied to the evolving odour patterns of spoiling milk, which had been sampled more frequently (4h intervals for 7 days). The FCM results showed that both the freshest and oldest milk samples had a high degree of membership in "fresh" and "spoiled" clusters, respectively. In the future, as advancements in electronic nose development remove the present barriers to acceptance, signal processing methods like those explored in this paper can be incorporated into odour monitoring systems used in the smart home. PMID:19965227

Green, Geoffrey C; Chan, Adrian D C; Goubran, Rafik A

2009-01-01

384

UK PubMed Central (United Kingdom)

Adopting the use of real-time odour monitoring in the smart home has the potential to alert the occupant of unsafe or unsanitary conditions. In this paper, we measured (with a commercial metal-oxide sensor-based electronic nose) the odours of five household foods that had been left out at room temperature for a week to spoil. A multilayer perceptron (MLP) neural network was trained to recognize the age of the samples (a quantity related to the degree of spoilage). For four of these foods, median correlation coefficients (between target values and MLP outputs) of R > 0.97 were observed. Fuzzy C-means clustering (FCM) was applied to the evolving odour patterns of spoiling milk, which had been sampled more frequently (4h intervals for 7 days). The FCM results showed that both the freshest and oldest milk samples had a high degree of membership in "fresh" and "spoiled" clusters, respectively. In the future, as advancements in electronic nose development remove the present barriers to acceptance, signal processing methods like those explored in this paper can be incorporated into odour monitoring systems used in the smart home.

Green GC; Chan AD; Goubran RA

2009-01-01

385

UK PubMed Central (United Kingdom)

The olfactory system detects volatile chemical compounds, known as odour molecules or odorants. Such odorants have a diverse chemical structure which in turn interact with the receptors of the olfactory system. The insect olfactory system provides a unique opportunity to directly measure the firing rates that are generated by the individual olfactory sensory neurons (OSNs) which have been stimulated by odorants in order to use this data to inform their classification. In this work, we demonstrate that it is possible to use the firing rates from an array of OSNs of the vinegar fly, Drosophila melanogaster, to train an Artificial Neural Network (ANN), as a series of a Multi-Layer Perceptrons (MLPs), to differentiate between eight distinct chemical classes. We demonstrate that the MLPs when trained on 108 odorants, for both clean and 10% noise injected data, can reliably identify 87% of an unseen validation set of chemicals using noise injection. In addition, the noise injected MLPs provide a more accurate level of identification. This demonstrates that a 10% noise injected series of MLPs provides a robust method for classifying chemicals from the firing rates of OSNs and paves the way to a future realisation of an artificial olfactory biosensor.

Bachtiar LR; Unsworth CP; Newcomb RD; Crampin EJ

2011-01-01

386

Directory of Open Access Journals (Sweden)

Full Text Available Thanks to the built in intelligence (deployment of new intelligent devices and sensors in places where historically they were not present), the Smart Grid and Microgrid paradigms are able to take advantage from aggregated load forecasting, which opens the door for the implementation of new algorithms to seize this information for optimization and advanced planning. Therefore, accuracy in load forecasts will potentially have a big impact on key operation factors for the future Smart Grid/Microgrid-based energy network like user satisfaction and resource saving, and new methods to achieve an efficient prediction in future energy landscapes (very different from the centralized, big area networks studied so far). This paper proposes different improved models to forecast next day’s aggregated load using artificial neural networks, taking into account the variables that are most relevant for the aggregated. In particular, seven models based on the multilayer perceptron will be proposed, progressively adding input variables after analyzing the influence of climate factors on aggregated load. The results section presents the forecast from the proposed models, obtained from real data.

Luis Hernández; Carlos Baladrón; Javier M. Aguiar; Lorena Calavia; Belén Carro; Antonio Sánchez-Esguevillas; Pablo García; Jaime Lloret

2013-01-01

387

Scientific Electronic Library Online (English)

Full Text Available Abstract in portuguese Ao longo dos últimos anos, diversos trabalhos têm sido desenvolvidos a fim de se modelar quantitativamente o efeito GMI (Magnetoimpedância Gigante). No entanto, esses modelos adotam simplificações que afetam significativamente seu desempenho teórico-experimental e sua generalidade, e ainda são raros os modelos quantitativos que incorporam parâmetros geradores de assimetria - AGMI (GMI assimétrica) - como, por exemplo, o nível CC da corrente de excitação das am (more) ostras GMI. Este trabalho objetiva o desenvolvimento de um novo modelo, suficientemente geral, que incorpore inclusive a assimetria induzida pelo nível CC da corrente de excitação, capaz de guiar os procedimentos experimentais de caracterização das amostras GMI. Assim, este artigo propõe, apresenta e discute a utilização de um modelo computacional baseado em Redes Neurais feedforward Multilayer Perceptron na modelagem da sensibilidade de módulo e fase da impedância do efeito GMI em função do campo magnético, para ligas ferromagnéticas amorfas de composição Co70Fe5Si15B10. O modelo proposto permite a obtenção da sensibilidade a partir de alguns dos principais parâmetros que a afetam: comprimento das amostras, nível CC e frequência da corrente de excitação e campo magnético externo. Abstract in english Over the past few years, several studies have been developed in order to quantitatively model the GMI effect (Giant Magnetoimpedance). However, these models adopt simplifications that significantly affect its theoretical-experimental performance and its generalization capability, and models that incorporate parameters that generate asymmetry - AGMI (asymmetric GMI) - such as the DC level of the excitation current of the GMI samples are still rare. This work aims to develo (more) p a new model, sufficiently general, which also incorporates the asymmetry induced by the DC level of the excitation current, capable of guiding the experimental procedures of characterization of the GMI samples. Thus, this paper proposes, presents and discusses the use of a computational model based on feedforward Multilayer Perceptron Neural Networks to model the impedance magnitude sensitivity and impedance phase sensitivity, of the GMI effect, as functions of the magnetic field, for Co70Fe5Si15B10 ferromagnetic amorphous alloys. The proposed model allows obtaining these sensitivities based on some of the main parameters that affect it: length of the samples, DC level and frequency of the excitation current and the external magnetic field.

Silva, Eduardo Costa da; Vellasco, Marley M. B. R.; Barbosa, Carlos R. Hall; Monteiro, Elisabeth Costa; Gusmão, Luiz A. P. de

2012-10-01

388

Application of Artificial Neural Networks Model as Analytical Tool for Groundwater Salinity

Directory of Open Access Journals (Sweden)

Full Text Available The main source of water in Gaza Strip is the shallow coastal aquifer. It is extremely deteriorated in terms of salinity which influenced by many variables. Studying the relation between these variables and salinity is often a complex and nonlinear process, making it suitable to model by Artificial Neural Networks (ANN). Initially, it is assumed that the salinity (represented by chloride concentration, mg/l) may be affected by some variables as: recharge rate, abstraction, abstraction average rate, life time and aquifer thickness. Data were extracted from 56 municipal wells, covering the area of Gaza Strip. After a number of modeling trials, the best neural network was determined to be Multilayer Perceptron network (MLP) with four layers: an input layer of 6 neurons, first hidden layer with 10 neurons, second hidden layer with 7 neurons and the output layer with 1 neuron which gives the final chloride concentration. The ANN model generated very good results depending on the high correlation between the observed and simulated values of chloride concentration. The correlation coefficient (r) was 0.9848. The high value of (r) showed that the simulated chloride concentration values using the ANN model were in very good agreement with the observed chloride concentration which mean that ANN model is useful and applicable for groundwater salinity modeling. ANN model was successfully utilized as analytical tool to study influence of the input variables on chloride concentration. It proved that chloride concentration in groundwater is reduced by decreasing abstraction, abstraction average rate and life time. Furthermore, it is reduced by increasing recharge rate and aquifer thickness.

Mohamed Seyam; Yunes Mogheir

2011-01-01

389

A Neural Network Based Hybrid Mixture Model to Extract Information from Non-linear Mixed Pixels

Directory of Open Access Journals (Sweden)

Full Text Available Signals acquired by sensors in the real world are non-linear combinations, requiring non-linear mixture models to describe the resultant mixture spectra for the endmember’s (pure pixel’s) distribution. This communication discusses inferring class fraction through a novel hybrid mixture model (HMM). HMM is a three-step process, where the endmembers are first derived from the images themselves using the N-FINDR algorithm. These endmembers are used by the linear mixture model (LMM) in the second step that provides an abundance estimation in a linear fashion. Finally, the abundance values along with the training samples representing the actual ground proportions are fed into neural network based multi-layer perceptron (MLP) architecture as input to train the neurons. The neural output further refines the abundance estimates to account for the non-linear nature of the mixing classes of interest. HMM is first implemented and validated on simulated hyper spectral data of 200 bands and subsequently on real time MODIS data with a spatial resolution of 250 m. The results on computer simulated data show that the method gives acceptable results for unmixing pixels with an overall RMSE of 0.0089 ± 0.0022 with LMM and 0.0030 ± 0.0001 with the HMM when compared to actual class proportions. The unmixed MODIS images showed overall RMSE with HMM as 0.0191 ± 0.022 as compared to the LMM output considered alone that had an overall RMSE of 0.2005 ± 0.41, indicating that individual class abundances obtained from HMM are very close to the real observations.

Uttam Kumar; Kumar S. Raja; Chiranjit Mukhopadhyay; T.V. Ramachandra

2012-01-01

390

Neural Networks and Photometric Redshifts

We present a neural network based approach to the determination of photometric redshift. The method was tested on the Sloan Digital Sky Survey Early Data Release (SDSS-EDR) reaching an accuracy comparable and, in some cases, better than SED template fitting techniques. Different neural networks architecture have been tested and the combination of a Multi Layer Perceptron with 1 hidden layer (22 neurons) operated in a Bayesian framework, with a Self Organizing Map used to estimate the accuracy of the results, turned out to be the most effective. In the best experiment, the implemented network reached an accuracy of 0.020 (interquartile error) in the range 0

Tagliaferri, R; Andreon, S; Capozziello, S; Donalek, C; Giordano, G; Tagliaferri, Roberto; Longo, Giuseppe; Andreon, Stefano; Capozziello, Salvatore; Donalek, Ciro; Giordano, Gerardo

2002-01-01

391

Gamma spectral analysis via neural networks

Energy Technology Data Exchange (ETDEWEB)

A system combining a portable gamma-ray spectrometer with a neural network is discussed. In this system, the neural network is used to automatically identify radioactive isotopes in real-time from their gamma-ray spectra. Two neural network paradigms are examined: the linear perceptron and the optimal linear associative memory (OLAM). A comparison of the two paradigms shows that OLAM is superior to linear perceptron for this application. Both networks have a linear response and are useful in determining the composition of an unknown sample when the spectrum of the unknown is a linear superposition of known spectra. One feature of this technique is that it uses the whole spectrum in the identification process instead of only the individual photo-peaks. For this reason, it is potentially more useful for processing data from lower resolution gamma-ray spectrometers. This approach has been successfully tested with data generated by Monte Carlo simulations and with field data from both sodium iodide and germanium detectors. With the neural network approach, the intense computation takes place during the training process. Once the network is trained, normal operation consists of propagating the data through the network, which results in rapid identification of samples in the field. This approach is useful in situations that require fast response but where precise quantification is less important.

Keller, P.E.; Kouzes, R.T.

1994-10-01

392

UK PubMed Central (United Kingdom)

We present a new security technology called theMultilayer Firewall. We argue that it is useful in somesituations for which other approaches, such ascryptographically protected communications, presentoperational or economic difficulties. In othercircumstances a Multilayer Firewall can complimentsuch security technology by providing additionalprotection against intruder attacks. We first present theoperational theory behind the Multilayer Firewall andthen describe a prototype that we designed andimplemented.

Dan Nessett; Polar Humenn

393

UK PubMed Central (United Kingdom)

This paper introduces new learning algorithms for natural language processing based onthe perceptron algorithm. We show how the algorithms can be efficiently applied toexponential sized representations of parse trees, such as the "all subtrees" (DOP)representation described by (Bod 98), or a representation tracking all sub-fragments of atagged sentence. We give experimental results showing significant improvements on twotasks: parsing Wall Street Journal text, and named-entity extraction from web data.

Michael Collinsy; Nigel Duffyz; Florham Park

394

UK PubMed Central (United Kingdom)

This paper introduces new learning algorithmsfor natural language processingbased on the perceptron algorithm. Weshow how the algorithms can be efficientlyapplied to exponential sized representationsof parse trees, such as the "all subtrees" (DOP) representation described by(Bod 1998), or a representation trackingall sub-fragments of a tagged sentence.We give experimental results showing significantimprovements on two tasks: parsingWall Street Journal text, and namedentityextraction from web data.1

Michael Collins; Florham Park; Nigel Duffy

395

Digital Repository Infrastructure Vision for European Research (DRIVER)

This paper develops a primitive gas recognition system for discriminating between industrial gas species. The system under investigation consists of an array of eight micro-hotplate-based SnO2 thin film gas sensors with different selectivity patterns. The output signals are processed through a signa...

Fayçal Benrekia; Mokhtar Attari; Mounir Bouhedda

396

Directory of Open Access Journals (Sweden)

Full Text Available Nowadays, with regard to environmental issues, proper operation of wastewater treatment plants is of particular importance that in the case of inappropriate utilization, they will cause serious problems. Processes that exist in environmental systems and environmental engineers are dealing with them mostly have two major characteristics: they are dependent on many variables; and there are complex relationships between its components which make them very difficult to analyze. Being familiar with characteristics of industrial town effluents from various wastewater treatment units, which have high qualitative and quantitative variations and more uncertainties compared to urban wastewaters, plays very effective role in governing them. In order to achieve a better and efficient control over the operation of an industrial wastewater treatment plant, powerful mathematical tool can be used that is based on recorded data from some basic parameters of wastewater during a period of treatment plant operation. In this study, the multilayer perceptron (MLP) feed forward neural network with a hidden layer and stop training method was used to predict quality parameters of the industrial effluent. Data of this study are related to the Fajr Industrial Wastewater Treatment Plant located in Mahshahr—Iran that qualitative and quantitative characteristics of its units were used for training, calibration and evaluation of the neural model. Also, Principal Component Analysis technique was applied to modify and improve performance of generated models of neural networks. The results of this model showed good accuracy of the model in estimating qualitative pro- file of wastewater. This model facilitates evaluating the performance of each treatment plant units through comparing the results of prediction model with the standard amount of output.

Hamed Hasanlou; Naser Mehrdadi; Mohammad Taghi Jafarzadeh; Hamidreza Hasanlou

2012-01-01

397

Directory of Open Access Journals (Sweden)

Full Text Available Being familiar with characteristics of industrial town effluents from various wastewater treatment units, which have high qualitative and quantitative variations and more uncertainties compared to urban wastewaters, plays very effective role in governing them. With regard to environmental issues, proper operation of wastewater treatment plants is of par- ticular importance that in the case of inappropriate utilization, they will cause serious problems. Processes that exist in environmental systems mostly have two major characteristics: they are dependent on many variables; and there are complex relationships between its components which make them very difficult to analyze. In order to achieve a better and efficient control over the operation of an industrial wastewater treatment plant (WWTP), powerful mathematical tool can be used that is based on recorded data from some basic parameters of wastewater during a period of treatment plant operation. In this study, the treatment plant was divided into two main subsystems including: Low TDS (Total Dissolved Solids) treatment unit and Biological unit (extended aeration). The multilayer perceptron feed forward neural network with a hidden layer and stop training method was used to predict quality parameters of the industrial effluent. Data of this study are related to the Fajr Industrial Wastewater Treatment Plant, located in Mahshahr—Iran that qualita- tive and quantitative characteristics of its units were used for training, calibration and validation of the neural model. Also, Principal Component Analysis (PCA) technique was applied to improve performance of generated models of neural networks. The results of L-TDS unit showed good accuracy of the models in estimating qualitative profile of wastewater but results of biological unit did not have sufficient accuracy to being used. This model facilitates evaluating the performance of each treatment plant units through comparing the results of prediction model with the standard amount of outputs.

Naser Mehrdadi; Hamed Hasanlou; Mohammad Taghi Jafarzadeh; Hamidreza Hasanlou; Hamid Abdolabadi

2012-01-01

398

International Nuclear Information System (INIS)

Background: In breast MRI (bMRI), prediction of lymph node metastases (N+) on the basis of dynamic and morphologic descriptors of breast cancers remains a complex task. Purpose: To predict N+ using an artificial neural network (ANN) on the basis of 17 previously published descriptors of breast lesions in bMRI. Material and Methods: Standardized protocol and study design were applied in this study (T1w-FLASH; 0.1 mmol/kg body weight Gd-DTPA; T2w-TSE; histological verification after bMRI). All lesions were evaluated by two experienced radiologists in consensus. In every lesion 17 previously published descriptors were assessed. Matched subgroups with (N+; n=97) and without N+ were created (N-; n=97), forming the dataset of this study (n=194). An ANN was constructed ('Multilayer Perceptron'; training: 'Batch'; activation function of hidden/output layer: 'Hyperbolic Tangent'/'Softmax') to predict N+ using all descriptors in combination on a randomly chosen training sample (n=123/194) and optimized on the corresponding test sample (n=71/194) using dedicated software. The discrimination power of this ANN was quantified by area under the curve (AUC) comparison (vs AUC=0.5). Training and testing cycles were repeated 20 times to quantify the robustness of the ANN (median-AUC; confidence intervals, CIs). Results: The ANN demonstrated highly significant discrimination power to classify N+ vs N- (P

2010-01-01

399

In typical case 2 waters an accurate remote sensing retrieval of chlorophyll a (chla) is still challenging. There is a widespread understanding that universally applicable water constituent retrieval algorithms are currently not feasible, shifting the research focus to regionally specific implementations of powerful inversion methods. This study takes advantage of regionally specific chlorophyll a (chla) algorithms, which were developed by the authors of this abstract in previous works, and the characteristics of Medium Resolution Imaging Spectrometer (MERIS) in order to study harmful algal events in the optically complex waters of the Galician Rias (NW). Harmful algal events are a frequent phenomenon in this area with direct and indirect impacts to the mussel production that constitute a very important economic activity for the local community. More than 240 106 kg of mussel per year are produced in these highly primary productive upwelling systems. A MERIS archive from nine years (2003-2012) was analysed using regionally specific chla algorithms. The latter were developed based on Multilayer perceptron (MLP) artificial neural networks and fuzzy c-mean clustering techniques (FCM). FCM specifies zones (based on water leaving reflectances) where the retrieval algorithms normally provide more reliable results. Monthly chla anomalies and other statistics were calculated for the nine years MERIS archive. These results were then related to upwelling indices and other associated measurements to determine the driver forces for specific phytoplankton blooms. The distribution and changes of chla are also discussed.

Gonzalez Vilas, L.; Castro Fernandez, M.; Spyrakos, E.; Torres Palenzuela, J.

2013-08-01

400

Characterisation of the plasma density with two artificial neural network models

This paper establishes two artificial neural network models by using a multi layer perceptron algorithm and radial based function algorithm in order to predict the plasma density in a plasma system. In this model, 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 the target output neuron: the plasma density. The accuracy of prediction is tested with the experimental data obtained by the Langmuir probe. The effectiveness of two artificial neural network models are demonstrated, the results show good agreements with corresponding experimental data. The ability of the artificial neural network model to predict the plasma density accurately in an electron cyclotron resonance-plasma enhanced chemical vapour deposition system can be concluded, and the radial based function is more suitable than the multi layer perceptron in this work.

Wang, Teng; Gao, Xiang-Dong; Li, Wei

2010-07-01

401

Directory of Open Access Journals (Sweden)

Full Text Available This paper focuses on an automated ANN classification system consisting of two modules: an unsupervised Kohonen’s Self-Organizing Mapping (SOM) neural network module, and a supervised Multilayer Perceptron (MLP) neural network module using the Backpropagation (BP) training algorithm. Two training algorithms were provided for the SOM network module: the standard SOM, and a refined SOM learning algorithm which incorporated Simulated Annealing (SA). The ability of our automated ANN system to perform Land-Use/Land-Cover (LU/LC) classifications of a Landsat Thematic Mapper (TM) image was tes