5.0

5.0 | 2 ratings Rate this file 17 Downloads (last 30 days) File Size: 5.49 KB File ID: #6320

Gaussian and Nearest Mean Classifiers

by Himanshu Ray

 

17 Nov 2004 (Updated 29 Nov 2004)

Estimating probability of Classification error for Gaussian and Nearest Mean Classifiers

| Watch this File

File Information
Description

This M-file focuses on a 3-class pattern classification problem. It generates hundred random samples for each pattern class using given parameters for the class-conditional densities. Further the Gaussian classifier is implemented to classify test samples of each class using equal prior class probabilities and specified probabilities. Also the nearest mean classifier is implemented to classify the test samples of each class using equal prior class probabilities. The probability of classification error is estimated for each case. See M-File for details.

MATLAB release MATLAB 6.5 (R13)
Tags for This File  
Everyone's Tags
Tags I've Applied
Add New Tags Please login to tag files.
Comments and Ratings (4)
14 Feb 2005 Alpa Bhesania

This file is great help to me in my research.
Thank you for posting it.

09 May 2008 mohammed mohammed

Please hilp me i wont code for nearest mean classify for my project

13 May 2008 mohamed mohamed

This file help me very well in my research it is great.
Think you

12 May 2009 durrani nukman

Can this code used for 2-class problem. Is there any suggestion for me to run 62x2000 input data. Thank you.

Please login to add a comment or rating.
Updates
23 Nov 2004

(1)Spelling mistakes
(2)Will modify M-File soon as special characters are not "evident"

29 Nov 2004

(1)Change special characters in M-file

Tag Activity for this File
Tag Applied By Date/Time
statistics Himanshu Ray 22 Oct 2008 07:35:58
probability Himanshu Ray 22 Oct 2008 07:35:58
gaussian Himanshu Ray 22 Oct 2008 07:35:58
nearest mean Himanshu Ray 22 Oct 2008 07:35:58
3 class pattern classification problem Cristina McIntire 15 Jan 2009 13:46:42
gaussian Ahmed Jawwad 13 Jul 2010 19:03:04

Contact us at files@mathworks.com