THEORETICAL FOUNDATIONS AND EXPERIMENTAL RESULTS FOR A HIERARCHICAL CLASSIFIER WITH OVERLAPPING CLUSTERS
Article first published online: 11 SEP 2012
© 2012 Wiley Periodicals, Inc.
Volume 29, Issue 2, pages 357–388, May 2013
How to Cite
Podolak, I. T. and Roman, A. (2013), THEORETICAL FOUNDATIONS AND EXPERIMENTAL RESULTS FOR A HIERARCHICAL CLASSIFIER WITH OVERLAPPING CLUSTERS. Computational Intelligence, 29: 357–388. doi: 10.1111/j.1467-8640.2012.00469.x
- Issue published online: 7 MAY 2013
- Article first published online: 11 SEP 2012
- Received 7 December 2010; Revised 7 February 2012; Accepted 28 February 2012.
- hierarchical clustering;
- classification framework;
- hierarchical classifier;
- weak classifier
This paper proposes a classification framework based on simple classifiers organized in a tree-like structure. It is observed that simple classifiers, even though they have high error rate, find similarities among classes in the problem domain. The authors propose to trade on this property by recognizing classes that are mistaken and constructing overlapping subproblems. The subproblems are then solved by other classifiers, which can be very simple, giving as a result a hierarchical classifier (HC). It is shown that HC, together with the proposed training algorithm and evaluation methods, performs well as a classification framework. It is also proven that such constructs give better accuracy than the root classifier it is built upon.