IIUM Repository (IREP)

Higher-order statistics and neural network based multi-classifier system for gene identification

Gunawan, Teddy Surya and Ambikairajah, Eliathamby and Epps, Julien (2007) Higher-order statistics and neural network based multi-classifier system for gene identification. In: 1st International Conference on Signal Processing and Communication Systems (ICSPCS 2007), 17-19 Dec 2007, Gold Coast, Australia.

[img] PDF (Higher-order statistics and neural network based multi-classifier system for gene identification)
Restricted to Registered users only

Download (371kB) | Request a copy
[img] PDF (Higher-order statistics and neural network based multi-classifier system for gene identification)
Restricted to Registered users only

Download (182kB) | Request a copy

Abstract

This paper presents the use of higher order statistics and a neural network based multi-classifier system for gene and exon identification of a DNA sequence. Newly proposed higher order statistics features, combined with frequency domain analysis, are used to train three different neural networks. Classification results of the three individual neural networks are combined through an aggregation function, of which five variants are compared herein. An evaluation of the multi-classifier system on 117 sequences from the HMR195 database shows that when different opinions of more classifiers on the same input data are integrated within a multi-classifier system, a relative improvement in precision of 5% over the individual performances of the neural networks can be obtained.

Item Type: Conference or Workshop Item (Full Paper)
Additional Information: 5588/2341
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Kulliyyahs/Centres/Divisions/Institutes: Kulliyyah of Engineering > Department of Electrical and Computer Engineering
Depositing User: Dr Teddy Surya Gunawan
Date Deposited: 22 Nov 2013 12:21
Last Modified: 22 Nov 2013 12:21
URI: http://irep.iium.edu.my/id/eprint/2341

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year