Path: news.mathworks.com!not-for-mail
From: <HIDDEN>
Newsgroups: comp.soft-sys.matlab
Subject: Classification using SVM
Date: Thu, 21 Mar 2013 23:24:09 +0000 (UTC)
Organization: Oklahoma State University
Lines: 7
Message-ID: <kig4qp$jug$1@newscl01ah.mathworks.com>
Reply-To: <HIDDEN>
NNTP-Posting-Host: www-00-blr.mathworks.com
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
X-Trace: newscl01ah.mathworks.com 1363908249 20432 172.30.248.45 (21 Mar 2013 23:24:09 GMT)
X-Complaints-To: news@mathworks.com
NNTP-Posting-Date: Thu, 21 Mar 2013 23:24:09 +0000 (UTC)
X-Newsreader: MATLAB Central Newsreader 3958516
Xref: news.mathworks.com comp.soft-sys.matlab:791738

Hi 

I am using MATLAB 'svmtrain' and 'svmclassify' in Bioinformatics toolbox to do a classification task. Everytime I run the code, I am getting different results (accuracy)eventhough I put the same sigma and boxconstraint parameters in svmtrain.
Can anybody suggest how to get a stable result?

thanks
Sitanshu