Volume : II, Issue : II, February - 2013

Review paper on Error Correcting Output Code Based on Multiclass Classification

Irfan Poladi, Hitesh Ishwardas

Abstract :

A common way to model multiclass classification problem is to design a set of binary classifiers and to combine them. Error-Correcting Output Codes (ECOC) represents a successful framework to deal with these types of problems. Recent works in the ECOC framework showed significant performance improvements. The ECOC framework is a powerful tool to deal with multi-class categorization problems. As the error correcting output codes have error correcting ability and improve the generalization ability of the base classifiers. This paper describe both state-of-the-art coding (one-versus-one, one-versus all, dense-random, sparse-random, DECOC, forest- ECOC, and ECOC-ONE) and decoding designs (hamming, Euclidean, inverse hamming, laplacian, β-density, attenuated, loss-based, probabilistic kernel-based, and loss weighted). This paper also contains the empirical study on ECOC.

Keywords :

Article: Download PDF   DOI : 10.36106/ijsr  

Cite This Article:

Irfan Poladi, Hitesh Ishwardas Review paper on Error Correcting Output Code Based on Multiclass Classification International Journal of Scientific Research, Vol.II, Issue.II February 2013

Number of Downloads : 364

References :