Neuro fuzzy classification and detection technique for bioinformatics problems

Bioinformatics is an emerging science and technology which has lots of research potential in the future. It involves multi-interdisciplinary approaches such as mathematics, physics, computer science and engineering, biology, and behavioral science. Computers are used to gather, store, analyze as wel...

Full description

Bibliographic Details
Main Authors: Othman, Mohd. Fauzi, Moh, Thomas Shan Yau
Format: Book Section
Language:English
Published: Institute of Electrical and Electronics Engineering (IEEE) 2007
Subjects:
Online Access:http://eprints.utm.my/9597/1/MohdFauziOthman2007NeuroFuzzyClassificationandDetection.pdf
Description
Summary:Bioinformatics is an emerging science and technology which has lots of research potential in the future. It involves multi-interdisciplinary approaches such as mathematics, physics, computer science and engineering, biology, and behavioral science. Computers are used to gather, store, analyze as well as integration of patterns and biological data information which can then be applied to discover new useful diagnosis or information. In this study, the focus was directed to the classification or clustering techniques which can be applied in the bioinformatics fields based on the Sugeno type neuro fuzzy model or ANFIS (adaptive neuro fuzzy inference system). It is very important to identify new integration of classification or clustering algorithm especially in neuro fuzzy domain as compared to conventional or traditional method. This paper explores the suitability and performance of recurrent classification technique, fuzzy c means (FCM) act as classifier in neuro fuzzy system compared to subclustering method. A package of software based on neuro fuzzy model (ANFIS) has been developed using MATLAB software and optimization were done with the help from WEKA. A set diabetes data based on real diagnosis of patient was used.