Strathprints Home | Open Access | Browse | Search | User area | Copyright | Help | Library Home | SUPrimo

Multi-classify hybrid multilayered perceptron (HMLP) network for pattern recognition applications

Bin Hashim, Fakroul Ridzuan and Soraghan, John and Petropoulakis, Lykourgos (2012) Multi-classify hybrid multilayered perceptron (HMLP) network for pattern recognition applications. IFIP Advances in Information and Communication Technology, 381. pp. 19-27. ISSN 1868-4238

Full text not available in this repository. (Request a copy from the Strathclyde author)

Abstract

This paper introduces a Hybrid Multilayered Perceptron (HMLP) based classifier known as the Multi-Classify HMLP network (MCHMLP). This network is shown to be able to enhance the performance accuracy when compared to the conventional HMLP network. The Multi-Classify HMLP network architecture is trained using a Modified Recursive Prediction Error (MRPE). This study uses three benchmark datasets in order to measure the capability of the network. The results show that the proposed Multi-Classify HMLP network provides a significant improvement over the conventional HMLP network for pattern recognition applications.

Item type: Article
ID code: 41880
Keywords: multi-classify, hybrid multilayered perceptron , HMLP, network , pattern recognition applications, Electrical engineering. Electronics Nuclear engineering, Information Systems and Management
Subjects: Technology > Electrical engineering. Electronics Nuclear engineering
Department: Faculty of Engineering > Electronic and Electrical Engineering
Technology and Innovation Centre > Sensors and Asset Management
Related URLs:
Depositing user: Pure Administrator
Date Deposited: 02 Nov 2012 05:46
Last modified: 27 Mar 2014 10:36
URI: http://strathprints.strath.ac.uk/id/eprint/41880

Actions (login required)

View Item