The work presents the results of an investigation conducted to compare the performances of the Multi Layer Perceptron (MLP) and the Nearest Neighbor (NN) classifier for handwritten numeral recognition problem. The comparison is drawn in terms of the recognition performance and the computational requirements of the individual classifiers. The results show that a two-layer perceptron performs com...

With regard to the importance of behavioral factors on stock price, which has been mentioned by researchers, this study includes four behavioral factors (overconfidence, representativeness, over reaction and under reaction) in addition to fundamental and technical factors as inputs for neural network models to evaluate the effectiveness of these behavioral factors on stock price prediction accu...

Deviating from the conventional Hidden Markov ModelMulti-Layer Perceptron (HMM-MLP) hybrid paradigm of using MLP for classi cation, the proposed discriminative MLP technique uses MLP as a mapping module for feature extraction for conventional HMM-based systems. The MLP is discriminatively trained on the phonetically labeled training data to generate the phoneme posterior probabilities. We achie...

In this work, we propose a novel Deep Convolutional Neural Network (DCNN) tailored for gas classification. Inspired by the great success of DCNN in the field of computer vision, we designed a DCNN with up to 38 layers. In general, the proposed gas neural network, named GasNet, consists of: six convolutional blocks, each block consist of six layers; a pooling layer; and a fully-connected layer. ...

Dryer system is a controlled plant which is normally used in chemical industry. The proper modeling of this system facilitates its maintenance and keeping. Normally this is not an easy task, unless having a complete model of the process, due to sudden and nonlinear events. In this paper the linear identification of dryer plant in Arak petroleum, is introduced according to the Autoregressive wit...

This work addresses a fuzzy set based evolving modeling (FBeM) approach and the task of trading strategies performance. FBeM is a granular computing technique that uses fuzzy information granules to model nonstationary functions providing functional and linguistic approximations. As an application, we consider the BRL/USD exchange rate for the period from January 2000 to October 2012. Caparison...

This study deals with estimation of electricity demand of Iran on the basis of economic criteria using a genetic-based approach called Gene Expression Programming (GEP) as an expression-driven approach. The GEP-based mathematical model is provided based on population, gross domestic product, exports, and imports. The proposed model is derived based on available data obtained from 1992 to 2006. ...

In this paper we present a training method and a network achitecture for the estimation of context-dependent observation probabilities in the framework of a hybrid Hidden Markov Model (HMM) / Multi Layer Perceptron (MLP) speaker independent continuous speech recognition system. The context-dependent modeling approach we present here computes the HMM context-dependent observation probabilities u...

An modification of the Approximate Internal Modelbased Neural Control (AIMNC), using Multi Layer Perceptron (MLP) neural networks is proposed. A necessary condition that the system provides zero steady-state error for a constant reference and constant disturbances is derived. In the proposed control strategy only one neural network, which is the neural model of the plant, needs to be trained of...