Ema-Qpso Based Feature Selection and Weighted Classification by Ls-Svm for Diabetes Diagnosis
Fawzi Elias Bekri1, A. Govardhan2
1Fawzi Elias Bekri, Department of Computer Science & Engineering JNTU, Hyderabad- 500 085, Andhra Pradesh, India.
2A. Govardhan, Professor of Computer Science & Engineering Principal College of engineering, JNTUH, Jagityal.
Manuscript received on may 27, 2012. | Revised Manuscript received on June 22, 2012. | Manuscript published on June 30, 2012. | PP: 44-52 | Volume-1 Issue-5, June 2012 | Retrieval Number: E0407051512/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In accordance to the fast developing technology now a days, every field is gaining it’s benefit through machines other than human involvement. Many changes are being made much advancement is possible by this developing technology. Likewise this technology is too gaining its importance in bioinformatics especially to analyse data. As we all know that diabetes is one of the present day deadly diseases prevailing. With the motivation of our earlier model OFW-ITS-LSSVM, here in this paper we introduce weighted classification with LSSVM to diagnose the diabetes in given blood sample datasets. We derived and proposed a swarm intelligence technique called Escalated Mediocre Agent based Quantum Particle Swarm Optimization EMA-QPSO for feature selection. The feature weights will be identified using a technique DFWQ (dynamic feature weight quantization) that derived from HITS algorithm, which uses in web mining. In contrast to our earlier model OFW-ITS-LSSVM the proposed model is not using pre defined ontology. Further, considering the patient’s details we can predict where he has a chance to get diabetes, if so measures to cure or stop it.
Keywords: machine learning, SVM, Feature reduction, feature optimization, tabu search, Tabu search.