System evaluation of construction methods for multi-class problems using binary classifiers

Shigeichi Hirasawa, Gendo Kumoi, Manabu Kobayashi, Masayuki Goto, Hiroshige Inazumi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Construction methods for multi-valued classification (multi-class) systems using binary classifiers are discussed and evaluated by a trade-off model for system evaluation based on rate-distortion theory. Suppose the multi-class systems consisted of M(≥3) categories and N(≥M-1) binary classifiers, then they can be represented by a matrix W, where the matrix W is given by a table of M code words with length N, called a code word table. For a document classification task, the relationship between the probability of classification error Pe and the number of binary classifiers N for given M is investigated, and we show that our constructed systems satisfy desirable properties such as “Flexible”, and “Elastic”. In particular, modified Reed Muller codes perform well: they are shown to be “Effective elastic”. As a second application we consider a hand-written character recognition task, and we show that the desirable properties are also satisfied.

Original languageEnglish
Title of host publicationTrends and Advances in Information Systems and Technologies
PublisherSpringer-Verlag
Pages909-919
Number of pages11
ISBN (Print)9783319777115
DOIs
Publication statusPublished - 2018 Jan 1
Event6th World Conference on Information Systems and Technologies, WorldCIST 2018 - Naples, Italy
Duration: 2018 Mar 272018 Mar 29

Publication series

NameAdvances in Intelligent Systems and Computing
Volume746
ISSN (Print)2194-5357

Other

Other6th World Conference on Information Systems and Technologies, WorldCIST 2018
CountryItaly
CityNaples
Period18/3/2718/3/29

    Fingerprint

Keywords

  • Binary classifier
  • ECOC
  • Error correcting codes
  • Exhaustive code
  • Multi-valued classification
  • Trade-off model

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Hirasawa, S., Kumoi, G., Kobayashi, M., Goto, M., & Inazumi, H. (2018). System evaluation of construction methods for multi-class problems using binary classifiers. In Trends and Advances in Information Systems and Technologies (pp. 909-919). (Advances in Intelligent Systems and Computing; Vol. 746). Springer-Verlag. https://doi.org/10.1007/978-3-319-77712-2_86