OpenViBE forum

The OpenViBE community
It is currently Fri Oct 19, 2018 6:20 pm

All times are UTC




Post new topic Reply to topic  [ 2 posts ] 
Author Message
PostPosted: Fri Jul 03, 2015 7:32 am 
Offline

Joined: Sun Nov 23, 2014 5:32 am
Posts: 21
I build a system, gives a 88.7% test data accuracy(when building the classification model), But when I run the data on the classifier model and measure the accuracy with "classifier Accuracy measure" Box, the accuracy decreases to 40% ! Is that normal?


Top
 Profile  
Reply with quote  
PostPosted: Tue Jul 21, 2015 1:32 am 
Offline

Joined: Sun Mar 14, 2010 12:58 pm
Posts: 108
you used the classifier accuracy measure on the same data in which you trained your classifier is that right?
If so, the fact you obtained decreased accuracy may come from the fact that you gave all your data (including the non-control state - i.e., the data between trial that do not correspond to one of the class the classifier has been trained on) to the classifier accuracy measure, and not only the data corresponding to one of the classes the classifier has been optimized to classify. Could that be the case? If so you need to use something like a stimulation based epoching to only use as input to the classifier accuracy measure box data that actually can be (and need to be) classified.

I hope this helps,
Fabien


Top
 Profile  
Reply with quote  
Display posts from previous:  Sort by  
Post new topic Reply to topic  [ 2 posts ] 

All times are UTC


Who is online

Users browsing this forum: No registered users and 1 guest


You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot post attachments in this forum

Search for:
Jump to:  
Powered by phpBB® Forum Software © phpBB Group
Americanized by Maƫl Soucaze.