Research
   Home
   Computational Finance
   ICA
   Hybrid Systems
   Recurrent Networks
   Support Vector Machines
   Input Variable Selection
   Classification Methods
   

Publications
   Book Chapters
   Journal Papers
   Conference Papers
   BibTex
  

Software
   Windale Technologies
  

Conferences
   NIPS*96
   NIPS*95
   NIPS*94


Information
   Biography
   Contact Me
  
View Andrew Back's profile on LinkedIn

   A Classification Scheme for Applications with Ambiguous Data

We propose a scheme for pattern classifications in applications, which include ambiguous data, that is, where pattern occupy overlapping areas in the feature space. Such situations frequently occur with noisy data and/or where some features are unknown. We demonstrate that it is advantageous to first detect those ambiguous areas with the help of training data and then to re-classify those data in these areas as ambiguous before making class predictions on test sets. This scheme is demonstrated with a simple example and benchmarked on two real world applications. Keywords: data classification, ambiguous data, probabilistic ANN, k-NN algorithm
 

 

 

Home   Research  Contact Me  Feedback  Publications

Copyright 1989-2008 Andrew Back. All Rights Reserved.