Search results for: independent component analysis and neural networks.

Authors: K. Ben Khalifa, M.H. Bédoui, M. Dogui, F. Alexandre

Abstract:

Several studies have been carried out, using various techniques, including neural networks, to discriminate vigilance states in humans from electroencephalographic (EEG) signals, but we are still far from results satisfactorily useable results. The work presented in this paper aims at improving this status with regards to 2 aspects. Firstly, we introduce an original procedure made of the association of two neural networks, a self organizing map (SOM) and a learning vector quantization (LVQ), that allows to automatically detect artefacted states and to separate the different levels of vigilance which is a major breakthrough in the field of vigilance. Lastly and more importantly, our study has been oriented toward real-worked situation and the resulting model can be easily implemented as a wearable device. It benefits from restricted computational and memory requirements and data access is very limited in time. Furthermore, some ongoing works demonstrate that this work should shortly results in the design and conception of a non invasive electronic wearable device.

Keywords: Electroencephalogram interpretation, artificialneural networks, vigilance states, hardware implementation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1476

Authors: Hossein Sahoolizadeh, Davood Sarikhanimoghadam, Hamid Dehghani

Abstract:

This paper proposes new hybrid approaches for face recognition. Gabor wavelets representation of face images is an effective approach for both facial action recognition and face identification. Perform dimensionality reduction and linear discriminate analysis on the down sampled Gabor wavelet faces can increase the discriminate ability. Nearest feature space is extended to various similarity measures. In our experiments, proposed Gabor wavelet faces combined with extended neural net feature space classifier shows very good performance, which can achieve 93 % maximum correct recognition rate on ORL data set without any preprocessing step.

Keywords: Face detection, Neural Networks, Multi-layer Perceptron, Gabor wavelets.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2162

Authors: Akram M. Othman, May H. Riadh

Abstract:

This research work is aimed at speech recognition using scaly neural networks. A small vocabulary of 11 words were established first, these words are “word, file, open, print, exit, edit, cut, copy, paste, doc1, doc2". These chosen words involved with executing some computer functions such as opening a file, print certain text document, cutting, copying, pasting, editing and exit. It introduced to the computer then subjected to feature extraction process using LPC (linear prediction coefficients). These features are used as input to an artificial neural network in speaker dependent mode. Half of the words are used for training the artificial neural network and the other half are used for testing the system; those are used for information retrieval. The system components are consist of three parts, speech processing and feature extraction, training and testing by using neural networks and information retrieval. The retrieve process proved to be 79.5-88% successful, which is quite acceptable, considering the variation to surrounding, state of the person, and the microphone type.

Keywords: Feature extraction, Liner prediction coefficients, neural network, Speech Recognition, Scaly ANN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1737

Authors: H. Kiani, S. Moradi, B. Soltani Soulgani, S. Mousavian

Abstract:

Desalting/dehydration plants (DDP) are often installed in crude oil production units in order to remove water-soluble salts from an oil stream. In order to optimize this process, desalting unit should be modeled. In this research, artificial neural network is used to model efficiency of desalting unit as a function of input parameter. The result of this research shows that the mentioned model has good agreement with experimental data.

Keywords: Desalting unit, Crude oil, Neural Networks, Simulation, Recovery, Separation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4250

Authors: Ahmad M. Sarhan, Omar I. Al Helalat

Abstract:

In this paper, an Arabic letter recognition system based on Artificial Neural Networks (ANNs) and statistical analysis for feature extraction is presented. The ANN is trained using the Least Mean Squares (LMS) algorithm. In the proposed system, each typed Arabic letter is represented by a matrix of binary numbers that are used as input to a simple feature extraction system whose output, in addition to the input matrix, are fed to an ANN. Simulation results are provided and show that the proposed system always produces a lower Mean Squared Error (MSE) and higher success rates than the current ANN solutions.

Keywords: ANN, Backpropagation, Gaussian, LMS, MSE, Neuron, standard deviation, Widrow-Hoff rule.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2014

Authors: Parvinder S. Sandhu, Roma Jaswal, Sandeep Khimta, Shailendra Singh

Abstract:

As the majority of faults are found in a few of its modules so there is a need to investigate the modules that are affected severely as compared to other modules and proper maintenance need to be done in time especially for the critical applications. As, Neural networks, which have been already applied in software engineering applications to build reliability growth models predict the gross change or reusability metrics. Neural networks are non-linear sophisticated modeling techniques that are able to model complex functions. Neural network techniques are used when exact nature of input and outputs is not known. A key feature is that they learn the relationship between input and output through training. In this present work, various Neural Network Based techniques are explored and comparative analysis is performed for the prediction of level of need of maintenance by predicting level severity of faults present in NASA-s public domain defect dataset. The comparison of different algorithms is made on the basis of Mean Absolute Error, Root Mean Square Error and Accuracy Values. It is concluded that Generalized Regression Networks is the best algorithm for classification of the software components into different level of severity of impact of the faults. The algorithm can be used to develop model that can be used for identifying modules that are heavily affected by the faults.

Keywords: Neural Network, Software faults, Software Metric.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1575

Authors: Kyu Chul Lee, Sung Hyun Yoo, Choon Ki Ahn, Myo Taeg Lim

Abstract:

Recent experimental evidences have shown that because of a fast convergence and a nice accuracy, neural networks training via extended kalman filter (EKF) method is widely applied. However, as to an uncertainty of the system dynamics or modeling error, the performance of the method is unreliable. In order to overcome this problem in this paper, a new finite impulse response (FIR) filter based learning algorithm is proposed to train radial basis function neural networks (RBFN) for nonlinear function approximation. Compared to the EKF training method, the proposed FIR filter training method is more robust to those environmental conditions. Furthermore , the number of centers will be considered since it affects the performance of approximation.

Keywords: Extended kalmin filter (EKF), classification problem, radial basis function networks (RBFN), finite impulse response (FIR)filter.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2399

Authors: Zongyan Li, Matt Best

Abstract:

This paper presents an optimization method for reducing the number of input channels and the complexity of the feed-forward NARX neural network (NN) without compromising the accuracy of the NN model. By utilizing the correlation analysis method, the most significant regressors are selected to form the input layer of the NN structure. An application of vehicle dynamic model identification is also presented in this paper to demonstrate the optimization technique and the optimal input layer structure and the optimal number of neurons for the neural network is investigated.

Keywords: Correlation analysis, F-ratio, Levenberg-Marquardt, MSE, NARX, neural network, optimisation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2188

Authors: H. Khorashadi-Zadeh, M. R. Aghaebrahimi

Abstract:

A novel application of neural network approach to fault classification and fault location of Medium voltage cables is demonstrated in this paper. Different faults on a protected cable should be classified and located correctly. This paper presents the use of neural networks as a pattern classifier algorithm to perform these tasks. The proposed scheme is insensitive to variation of different parameters such as fault type, fault resistance, and fault inception angle. Studies show that the proposed technique is able to offer high accuracy in both of the fault classification and fault location tasks.

Keywords: Artificial neural networks, cable, fault location andfault classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1851

Authors: Ali Hussian Ali AlTimemy, Fawzi M. Al Naima

Abstract:

This paper presents the prediction of kidney dysfunction using different neural network (NN) approaches. Self organization Maps (SOM), Probabilistic Neural Network (PNN) and Multi Layer Perceptron Neural Network (MLPNN) trained with Back Propagation Algorithm (BPA) are used in this study. Six hundred and sixty three sets of analytical laboratory tests have been collected from one of the private clinical laboratories in Baghdad. For each subject, Serum urea and Serum creatinin levels have been analyzed and tested by using clinical laboratory measurements. The collected urea and cretinine levels are then used as inputs to the three NN models in which the training process is done by different neural approaches. SOM which is a class of unsupervised network whereas PNN and BPNN are considered as class of supervised networks. These networks are used as a classifier to predict whether kidney is normal or it will have a dysfunction. The accuracy of prediction, sensitivity and specificity were found for each type of the proposed networks .We conclude that PNN gives faster and more accurate prediction of kidney dysfunction and it works as promising tool for predicting of routine kidney dysfunction from the clinical laboratory data.

Keywords: Kidney Dysfunction, Prediction, SOM, PNN, BPNN, Urea and Creatinine levels.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1931

Authors: Shu Lü, Shouming Zhong, Zixin Liu

Abstract:

In this paper, the robust exponential stability problem of discrete-time uncertain stochastic neural networks with timevarying delays is investigated. By introducing a new augmented Lyapunov function, some delay-dependent stable results are obtained in terms of linear matrix inequality (LMI) technique. Compared with some existing results in the literature, the conservatism of the new criteria is reduced notably. Three numerical examples are provided to demonstrate the less conservatism and effectiveness of the proposed method.

Keywords: Robust exponential stability, delay-dependent stability, discrete-time neural networks, stochastic, time-varying delays.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1436

Authors: Takaaki Ishibashi

Abstract:

Independent component analysis can estimate unknown source signals from their mixtures under the assumption that the source signals are statistically independent. However, in a real environment, the separation performance is often deteriorated because the number of the source signals is different from that of the sensors. In this paper, we propose an estimation method for the number of the sources based on the joint distribution of the observed signals under two-sensor configuration. From several simulation results, it is found that the number of the sources is coincident to that of peaks in the histogram of the distribution. The proposed method can estimate the number of the sources even if it is larger than that of the observed signals. The proposed methods have been verified by several experiments.

Keywords: blind source separation, independent component analysys, estimation for the number of the blind sources, voice activity detection, target extraction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1302

Authors: Hazem M. El-Bakry

Abstract:

Neural processors have shown good results for detecting a certain character in a given input matrix. In this paper, a new idead to speed up the operation of neural processors for character detection is presented. Such processors are designed based on cross correlation in the frequency domain between the input matrix and the weights of neural networks. This approach is developed to reduce the computation steps required by these faster neural networks for the searching process. The principle of divide and conquer strategy is applied through image decomposition. Each image is divided into small in size sub-images and then each one is tested separately by using a single faster neural processor. Furthermore, faster character detection is obtained by using parallel processing techniques to test the resulting sub-images at the same time using the same number of faster neural networks. In contrast to using only faster neural processors, the speed up ratio is increased with the size of the input image when using faster neural processors and image decomposition. Moreover, the problem of local subimage normalization in the frequency domain is solved. The effect of image normalization on the speed up ratio of character detection is discussed. Simulation results show that local subimage normalization through weight normalization is faster than subimage normalization in the spatial domain. The overall speed up ratio of the detection process is increased as the normalization of weights is done off line.

Keywords: Fast Character Detection, Neural Processors, Cross Correlation, Image Normalization, Parallel Processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1537

Authors: C. N. Vanitha, M. Usha

Abstract:

In a real world scenario, the viability of the sensor networks has been proved by standardizing the technologies. Wireless sensor networks are vulnerable to both electronic and physical security breaches because of their deployment in remote, distributed, and inaccessible locations. The compromised sensor nodes send malicious data to the base station, and thus, the total network effectiveness will possibly be compromised. To detect and seclude the Route modifiers, a neural network based Pattern Learning predictor (PLP) is presented. This algorithm senses data at any node on present and previous patterns obtained from the en-route nodes. The eminence of any node is upgraded by their predicted and reported patterns. This paper propounds a solution not only to detect the route modifiers, but also to seclude the malevolent nodes from the network. The simulation result proves the effective performance of the network by the presented methodology in terms of energy level, routing and various network conditions.

Keywords: Neural networks, pattern learning, security, wireless sensor networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1303

Authors: Sachin Man Bajimaya, SangChul Park, Gi-Nam Wang

Abstract:

The objective of this paper is to estimate realistic principal extrusion process parameters by means of artificial neural network. Conventionally, finite element analysis is used to derive process parameters. However, the finite element analysis of the extrusion model does not consider the manufacturing process constraints in its modeling. Therefore, the process parameters obtained through such an analysis remains highly theoretical. Alternatively, process development in industrial extrusion is to a great extent based on trial and error and often involves full-size experiments, which are both expensive and time-consuming. The artificial neural network-based estimation of the extrusion process parameters prior to plant execution helps to make the actual extrusion operation more efficient because more realistic parameters may be obtained. And so, it bridges the gap between simulation and real manufacturing execution system. In this work, a suitable neural network is designed which is trained using an appropriate learning algorithm. The network so trained is used to predict the manufacturing process parameters.

Keywords: Artificial Neural Network (ANN), Indirect Extrusion, Finite Element Analysis, MES.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2367

Authors: Kamaldeep Kaur, Arvinder Kaur, Ruchika Malhotra

Abstract:

The aim of this paper is to rank the impact of Object Oriented(OO) metrics in fault prediction modeling using Artificial Neural Networks(ANNs). Past studies on empirical validation of object oriented metrics as fault predictors using ANNs have focused on the predictive quality of neural networks versus standard statistical techniques. In this empirical study we turn our attention to the capability of ANNs in ranking the impact of these explanatory metrics on fault proneness. In ANNs data analysis approach, there is no clear method of ranking the impact of individual metrics. Five ANN based techniques are studied which rank object oriented metrics in predicting fault proneness of classes. These techniques are i) overall connection weights method ii) Garson-s method iii) The partial derivatives methods iv) The Input Perturb method v) the classical stepwise methods. We develop and evaluate different prediction models based on the ranking of the metrics by the individual techniques. The models based on overall connection weights and partial derivatives methods have been found to be most accurate.

Keywords: Artificial Neural Networks (ANNS), Backpropagation, Fault Prediction Modeling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1757

Authors: Anupama Pande, Ashok Kumar Thakur, Swapnoneel Roy

Abstract:

A complex valued neural network is a neural network which consists of complex valued input and/or weights and/or thresholds and/or activation functions. Complex-valued neural networks have been widening the scope of applications not only in electronics and informatics, but also in social systems. One of the most important applications of the complex valued neural network is in signal processing. In Neural networks, generalized mean neuron model (GMN) is often discussed and studied. The GMN includes a new aggregation function based on the concept of generalized mean of all the inputs to the neuron. This paper aims to present exhaustive results of using Generalized Mean Neuron model in a complex-valued neural network model that uses the back-propagation algorithm (called -Complex-BP-) for learning. Our experiments results demonstrate the effectiveness of a Generalized Mean Neuron Model in a complex plane for signal processing over a real valued neural network. We have studied and stated various observations like effect of learning rates, ranges of the initial weights randomly selected, error functions used and number of iterations for the convergence of error required on a Generalized Mean neural network model. Some inherent properties of this complex back propagation algorithm are also studied and discussed.

Keywords: Complex valued neural network, Generalized Meanneuron model, Signal processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1730

Authors: Amany M. Alshawi, Khaled Alduhaiman

Abstract:

This paper proposes a technique to protect against email bombing. The technique employs a statistical approach, Naïve Bayes (NB), and Neural Networks to show that it is possible to differentiate between good and bad traffic to protect against email bombing attacks. Neural networks and Naïve Bayes can be trained by utilizing many email messages that include both input and output data for legitimate and non-legitimate emails. The input to the model includes the contents of the body of the messages, the subject, and the headers. This information will be used to determine if the email is normal or an attack email. Preliminary tests suggest that Naïve Bayes can be trained to produce an accurate response to confirm which email represents an attack.

Keywords: Email bombing, Legitimate email, Naïve Bayes, Neural networks, Non-legitimate email.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1420

Authors: Xiaomei Wang, Shouming Zhong

Abstract:

In this paper, a class of generalized bi-directional associative memory (BAM) neural networks with mixed delays is investigated. On the basis of Lyapunov stability theory and contraction mapping theorem, some new sufficient conditions are established for the existence and uniqueness and globally exponential stability of equilibrium, which generalize and improve the previously known results. One example is given to show the feasibility and effectiveness of our results.

Keywords: Bi-directional associative memory (BAM) neural networks, mixed delays, Lyapunov stability theory, contraction mapping theorem, existence, equilibrium, globally exponential stability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1482

Authors: Sotirios Raptis

Abstract:

Linking social needs to social classes using different criteria may lead to social services misuse. The paper discusses using ML and Neural Networks (NNs) in linking public services in Scotland in the long term and advocates, this can result in a reduction of the services cost connecting resources needed in groups for similar services. The paper combines typical regression models with clustering and cross-correlation as complementary constituents to predict the demand. Insurance companies and public policymakers can pack linked services such as those offered to the elderly or to low-income people in the longer term. The work is based on public data from 22 services offered by Public Health Services (PHS) Scotland and from the Scottish Government (SG) from 1981 to 2019 that are broken into 110 years series called factors and uses Linear Regression (LR), Autoregression (ARMA) and 3 types of back-propagation (BP) Neural Networks (BPNN) to link them under specific conditions. Relationships found were between smoking related healthcare provision, mental health-related health services, and epidemiological weight in Primary 1(Education) Body Mass Index (BMI) in children. Primary component analysis (PCA) found 11 significant factors while C-Means (CM) clustering gave 5 major factors clusters.

Keywords: Probability, cohorts, data frames, services, prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 460

Authors: K. Kamalanand, S. Srinivasan

Abstract:

Analysis of blood vessel mechanics in normal and diseased conditions is essential for disease research, medical device design and treatment planning. In this work, 3D finite element models of normal vessel and atherosclerotic vessel with 50% plaque deposition were developed. The developed models were meshed using finite number of tetrahedral elements. The developed models were simulated using actual blood pressure signals. Based on the transient analysis performed on the developed models, the parameters such as total displacement, strain energy density and entropy per unit volume were obtained. Further, the obtained parameters were used to develop artificial neural network models for analyzing normal and atherosclerotic blood vessels. In this paper, the objectives of the study, methodology and significant observations are presented.

Keywords: Blood vessel, atherosclerosis, finite element model, artificial neural networks

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2308

Authors: Mohammad Namazi, Mohammad Sadeghzadeh Maharluie

Abstract:

Predicting earnings management is vital for the capital market participants, financial analysts and managers. The aim of this research is attempting to respond to this query: Is there a significant difference between the regression model and neural networks’ models in predicting earnings management, and which one leads to a superior prediction of it? In approaching this question, a Linear Regression (LR) model was compared with two neural networks including Multi-Layer Perceptron (MLP), and Generalized Regression Neural Network (GRNN). The population of this study includes 94 listed companies in Tehran Stock Exchange (TSE) market from 2003 to 2011. After the results of all models were acquired, ANOVA was exerted to test the hypotheses. In general, the summary of statistical results showed that the precision of GRNN did not exhibit a significant difference in comparison with MLP. In addition, the mean square error of the MLP and GRNN showed a significant difference with the multi variable LR model. These findings support the notion of nonlinear behavior of the earnings management. Therefore, it is more appropriate for capital market participants to analyze earnings management based upon neural networks techniques, and not to adopt linear regression models.

Keywords: Earnings management, generalized regression neural networks, linear regression, multi-layer perceptron, Tehran stock exchange.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2104

Authors: Poramate Manoonpong, Frank Pasemann, Florentin Wörgötter

Abstract:

This paper describes reactive neural control used to generate phototaxis and obstacle avoidance behavior of walking machines. It utilizes discrete-time neurodynamics and consists of two main neural modules: neural preprocessing and modular neural control. The neural preprocessing network acts as a sensory fusion unit. It filters sensory noise and shapes sensory data to drive the corresponding reactive behavior. On the other hand, modular neural control based on a central pattern generator is applied for locomotion of walking machines. It coordinates leg movements and can generate omnidirectional walking. As a result, through a sensorimotor loop this reactive neural controller enables the machines to explore a dynamic environment by avoiding obstacles, turn toward a light source, and then stop near to it.

Keywords: Recurrent neural networks, Walking robots, Modular neural control, Phototaxis, Obstacle avoidance behavior.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1729

Authors: Rami El-Hajj Mohamad, Mahmoud Skafi, Ali Massoud Haidar

Abstract:

Several meteorological parameters were used for the  prediction of monthly average daily global solar radiation on  horizontal using recurrent neural networks (RNNs). Climatological  data and measures, mainly air temperature, humidity, sunshine  duration, and wind speed between 1995 and 2007 were used to design  and validate a feed forward and recurrent neural network based  prediction systems. In this paper we present our reference system  based on a feed-forward multilayer perceptron (MLP) as well as the  proposed approach based on an RNN model. The obtained results  were promising and comparable to those obtained by other existing  empirical and neural models. The experimental results showed the  advantage of RNNs over simple MLPs when we deal with time series  solar radiation predictions based on daily climatological data.

Keywords: Recurrent Neural Networks, Global Solar Radiation, Multi-layer perceptron, gradient, Root Mean Square Error.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2561

Authors: M. Sinecen, M. Makinacı

Abstract:

The purpose of this paper is to assess the value of neural networks for classification of cancer and noncancer prostate cells. Gauss Markov Random Fields, Fourier entropy and wavelet average deviation features are calculated from 80 noncancer and 80 cancer prostate cell nuclei. For classification, artificial neural network techniques which are multilayer perceptron, radial basis function and learning vector quantization are used. Two methods are utilized for multilayer perceptron. First method has single hidden layer and between 3-15 nodes, second method has two hidden layer and each layer has between 3-15 nodes. Overall classification rate of 86.88% is achieved.

Keywords: Artificial neural networks, texture classification, cancer diagnosis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1591

Authors: A. Junaid, M. A. Z. Raja, I. M. Qureshi

Abstract:

An evolutionary computing technique for solving initial value problems in Ordinary Differential Equations is proposed in this paper. Neural network is used as a universal approximator while the adaptive parameters of neural networks are optimized by genetic algorithm. The solution is achieved on the continuous grid of time instead of discrete as in other numerical techniques. The comparison is carried out with classical numerical techniques and the solution is found with a uniform accuracy of MSE ≈ 10-9 .

Keywords: Neural networks, Unsupervised learning, Evolutionary computing, Numerical methods, Fitness evaluation function.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1780

Authors: Marina Velikova, Hennie Daniels, Ad Feelders

Abstract:

In many data mining applications, it is a priori known that the target function should satisfy certain constraints imposed by, for example, economic theory or a human-decision maker. In this paper we consider partially monotone prediction problems, where the target variable depends monotonically on some of the input variables but not on all. We propose a novel method to construct prediction models, where monotone dependences with respect to some of the input variables are preserved by virtue of construction. Our method belongs to the class of mixture models. The basic idea is to convolute monotone neural networks with weight (kernel) functions to make predictions. By using simulation and real case studies, we demonstrate the application of our method. To obtain sound assessment for the performance of our approach, we use standard neural networks with weight decay and partially monotone linear models as benchmark methods for comparison. The results show that our approach outperforms partially monotone linear models in terms of accuracy. Furthermore, the incorporation of partial monotonicity constraints not only leads to models that are in accordance with the decision maker's expertise, but also reduces considerably the model variance in comparison to standard neural networks with weight decay.

Keywords: mixture models, monotone neural networks, partially monotone models, partially monotone problems.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1246

Authors: H. Shayeghi, H. A. Shayanfar, G. Azimi

Abstract:

Short-Term Load Forecasting (STLF) plays an important role for the economic and secure operation of power systems. In this paper, Continuous Genetic Algorithm (CGA) is employed to evolve the optimum large neural networks structure and connecting weights for one-day ahead electric load forecasting problem. This study describes the process of developing three layer feed-forward large neural networks for load forecasting and then presents a heuristic search algorithm for performing an important task of this process, i.e. optimal networks structure design. The proposed method is applied to STLF of the local utility. Data are clustered due to the differences in their characteristics. Special days are extracted from the normal training sets and handled separately. In this way, a solution is provided for all load types, including working days and weekends and special days. We find good performance for the large neural networks. The proposed methodology gives lower percent errors all the time. Thus, it can be applied to automatically design an optimal load forecaster based on historical data.

Keywords: Feed-forward Large Neural Network, Short-TermLoad Forecasting, Continuous Genetic Algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1830

Authors: Zukisa Nante, Wang Zenghui

Abstract:

Face recognition is the problem of identifying or recognizing individuals in an image. This paper investigates a possible method to bring a solution to this problem. The method proposes an amalgamation of Principal Component Analysis (PCA), K-Means clustering, and Convolutional Neural Network (CNN) for a face recognition system. It is trained and evaluated using the ORL dataset. This dataset consists of 400 different faces with 40 classes of 10 face images per class. Firstly, PCA enabled the usage of a smaller network. This reduces the training time of the CNN. Thus, we get rid of the redundancy and preserve the variance with a smaller number of coefficients. Secondly, the K-Means clustering model is trained using the compressed PCA obtained data which select the K-Means clustering centers with better characteristics. Lastly, the K-Means characteristics or features are an initial value of the CNN and act as input data. The accuracy and the performance of the proposed method were tested in comparison to other Face Recognition (FR) techniques namely PCA, Support Vector Machine (SVM), as well as K-Nearest Neighbour (kNN). During experimentation, the accuracy and the performance of our suggested method after 90 epochs achieved the highest performance: 99% accuracy F1-Score, 99% precision, and 99% recall in 463.934 seconds. It outperformed the PCA that obtained 97% and KNN with 84% during the conducted experiments. Therefore, this method proved to be efficient in identifying faces in the images.

Keywords: Face recognition, Principal Component Analysis, PCA, Convolutional Neural Network, CNN, Rectified Linear Unit, ReLU, feature extraction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 505

Authors: Abdelhadi Lotfi, Abdelkader Benyettou

Abstract:

In this work, a training algorithm for probabilistic neural networks (PNN) is presented. The algorithm addresses one of the major drawbacks of PNN, which is the size of the hidden layer in the network. By using a cross-validation training algorithm, the number of hidden neurons is shrunk to a smaller number consisting of the most representative samples of the training set. This is done without affecting the overall architecture of the network. Performance of the network is compared against performance of standard PNN for different databases from the UCI database repository. Results show an important gain in network size and performance.

Keywords: Classification, probabilistic neural networks, network optimization, pattern recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1223