Machine learning classifiers for clumps in binary sequences

Hojung Lim, Amrit L. Goel, Miyoung Shin

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

Abstract

In this paper we develop a set of classification models for clumps that are subsequences of 1's in a binary sequence of O's and 1's. The models we consider use Gaussian basis functions and the newly developed SG algorithm [1] for their design. We present models for two cases based on how training and test data are created. Then we compare their performance (classification error on training and test data) with the reported results [2] from C4.5 and CART algorithms and the MLP network. We conclude by observing that the new models outperform the other classifiers for the cases considered here.

Original languageEnglish
Title of host publicationProceedings of the IASTED International Conference on Intelligent Systems and Control
EditorsM.H. Hamza, M.H. Hamza
Pages323-326
Number of pages4
StatePublished - 2003
EventProceedings of the IASTED International Conference on Intelligent Systems and Control - Salzburg, Austria
Duration: 25 Jun 200327 Jun 2003

Publication series

NameProceedings of the IASTED International Conference on Intelligent Systems and Control

Conference

ConferenceProceedings of the IASTED International Conference on Intelligent Systems and Control
Country/TerritoryAustria
CitySalzburg
Period25/06/0327/06/03

Keywords

  • Classification
  • Clumps
  • Machine learning
  • Radial Basis Functions

Fingerprint

Dive into the research topics of 'Machine learning classifiers for clumps in binary sequences'. Together they form a unique fingerprint.

Cite this