Automation and Autonomous Systems

S. Santhosh Baboo ¹, I. Kadar Shereef ²

Affiliations
1 Postgraduate and Research, Department of Computer Science at Dwaraka Doss Goverdhan Doss Vaishnav College, IN
2 Sree Saraswathi Thyagaraja College of Arts and Science, Pollachi, IN

Abstract

In this paper, primarily hybrid network is illustrated, which integrates a Self-Organizing Feature Map (SOFM) and a Multilayer Perceptron Network (MLP) to understand a much better prediction system. Then, it is demonstrated that the use of appropriate features can not only reduce the number of features, but also can improve the prediction accuracy. A feature selection MLP selects significant features online while learning the prediction task. Moreover, in this proposed approach, MLP is trained using Modified Levenberg-Marquardt algorithm for better convergence and performance. The experimental results show that the proposed approach provides significant prediction result with very less error rates.

Keywords

SOFM, MLP, Modified Levenberg-Marquardt, Prediction.

Full Text