Classification using normalized compression distance

Uri Shaham, Yael Edan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Classification algorithms that use the NCD (Normalized Compression Distance) as a similarity metric are proposed. This way of measuring similarity allows either skipping the feature selection and feature extraction phases or extracting features in a more objective way than common feature extraction methods, and so makes the classification algorithms less biased This work consists of several classification experiments of images, voice samples and ECG signals using a weighted k nearest neighbor algorithm and support vector machines. Our results are comparative to those achieved by more complicated, parameter laden learning algorithms that do use feature selection and extraction.

Original languageEnglish
Title of host publicationInternational Conference on Artificial Intelligence and Pattern Recognition 2008, AIPR 2008
Pages63-69
Number of pages7
StatePublished - 1 Dec 2008
Event2008 International Conference on Artificial Intelligence and Pattern Recognition 2008, AIPR 2008 - Orlando, FL, United States
Duration: 7 Jul 200810 Jul 2008

Publication series

NameInternational Conference on Artificial Intelligence and Pattern Recognition 2008, AIPR 2008

Conference

Conference2008 International Conference on Artificial Intelligence and Pattern Recognition 2008, AIPR 2008
Country/TerritoryUnited States
CityOrlando, FL
Period7/07/0810/07/08

Keywords

  • Classification
  • Compression
  • Feature selection
  • Similarity

Fingerprint

Dive into the research topics of 'Classification using normalized compression distance'. Together they form a unique fingerprint.

Cite this