Feature ordering and stopping rule based on maximizing mutual information

Joe Suzuki, Toshiyasu Matsushima, Hiroshige Inazumi, Shigeichi Hirasawa

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

    Abstract

    Summary form only given. The problem of feature ordering and stopping rule for sequential Bayesian classification is considered. A criterion that maximizes mutual information has been developed and compared with conventional strategies. At each stage the feature that maximizes mutual information gain from the observed data is selected, and the sequential procedure is terminated if its maximum value is less than a positive constant C. The advantages of the scheme are outlined. Numerical results have shown the good behavior of the proposed technique if the number of patterns or the allowable average number of used features is large. It has been shown that this scheme reduces the misallocation error rate, especially in the early stage, with the same mean number of used features.

    Original languageEnglish
    Title of host publicationIEEE 1988 Int Symp on Inf Theory Abstr of Pap
    Place of PublicationNew York, NY, USA
    PublisherPubl by IEEE
    Pages12
    Number of pages1
    Volume25 n 13
    Publication statusPublished - 1988

    ASJC Scopus subject areas

    • Engineering(all)

    Cite this

    Suzuki, J., Matsushima, T., Inazumi, H., & Hirasawa, S. (1988). Feature ordering and stopping rule based on maximizing mutual information. In IEEE 1988 Int Symp on Inf Theory Abstr of Pap (Vol. 25 n 13, pp. 12). New York, NY, USA: Publ by IEEE.

    Feature ordering and stopping rule based on maximizing mutual information. / Suzuki, Joe; Matsushima, Toshiyasu; Inazumi, Hiroshige; Hirasawa, Shigeichi.

    IEEE 1988 Int Symp on Inf Theory Abstr of Pap. Vol. 25 n 13 New York, NY, USA : Publ by IEEE, 1988. p. 12.

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

    Suzuki, J, Matsushima, T, Inazumi, H & Hirasawa, S 1988, Feature ordering and stopping rule based on maximizing mutual information. in IEEE 1988 Int Symp on Inf Theory Abstr of Pap. vol. 25 n 13, Publ by IEEE, New York, NY, USA, pp. 12.
    Suzuki J, Matsushima T, Inazumi H, Hirasawa S. Feature ordering and stopping rule based on maximizing mutual information. In IEEE 1988 Int Symp on Inf Theory Abstr of Pap. Vol. 25 n 13. New York, NY, USA: Publ by IEEE. 1988. p. 12
    Suzuki, Joe ; Matsushima, Toshiyasu ; Inazumi, Hiroshige ; Hirasawa, Shigeichi. / Feature ordering and stopping rule based on maximizing mutual information. IEEE 1988 Int Symp on Inf Theory Abstr of Pap. Vol. 25 n 13 New York, NY, USA : Publ by IEEE, 1988. pp. 12
    @inproceedings{dbcf892e096a4561bd8bc27da878329b,
    title = "Feature ordering and stopping rule based on maximizing mutual information",
    abstract = "Summary form only given. The problem of feature ordering and stopping rule for sequential Bayesian classification is considered. A criterion that maximizes mutual information has been developed and compared with conventional strategies. At each stage the feature that maximizes mutual information gain from the observed data is selected, and the sequential procedure is terminated if its maximum value is less than a positive constant C. The advantages of the scheme are outlined. Numerical results have shown the good behavior of the proposed technique if the number of patterns or the allowable average number of used features is large. It has been shown that this scheme reduces the misallocation error rate, especially in the early stage, with the same mean number of used features.",
    author = "Joe Suzuki and Toshiyasu Matsushima and Hiroshige Inazumi and Shigeichi Hirasawa",
    year = "1988",
    language = "English",
    volume = "25 n 13",
    pages = "12",
    booktitle = "IEEE 1988 Int Symp on Inf Theory Abstr of Pap",
    publisher = "Publ by IEEE",

    }

    TY - GEN

    T1 - Feature ordering and stopping rule based on maximizing mutual information

    AU - Suzuki, Joe

    AU - Matsushima, Toshiyasu

    AU - Inazumi, Hiroshige

    AU - Hirasawa, Shigeichi

    PY - 1988

    Y1 - 1988

    N2 - Summary form only given. The problem of feature ordering and stopping rule for sequential Bayesian classification is considered. A criterion that maximizes mutual information has been developed and compared with conventional strategies. At each stage the feature that maximizes mutual information gain from the observed data is selected, and the sequential procedure is terminated if its maximum value is less than a positive constant C. The advantages of the scheme are outlined. Numerical results have shown the good behavior of the proposed technique if the number of patterns or the allowable average number of used features is large. It has been shown that this scheme reduces the misallocation error rate, especially in the early stage, with the same mean number of used features.

    AB - Summary form only given. The problem of feature ordering and stopping rule for sequential Bayesian classification is considered. A criterion that maximizes mutual information has been developed and compared with conventional strategies. At each stage the feature that maximizes mutual information gain from the observed data is selected, and the sequential procedure is terminated if its maximum value is less than a positive constant C. The advantages of the scheme are outlined. Numerical results have shown the good behavior of the proposed technique if the number of patterns or the allowable average number of used features is large. It has been shown that this scheme reduces the misallocation error rate, especially in the early stage, with the same mean number of used features.

    UR - http://www.scopus.com/inward/record.url?scp=17944385675&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=17944385675&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:17944385675

    VL - 25 n 13

    SP - 12

    BT - IEEE 1988 Int Symp on Inf Theory Abstr of Pap

    PB - Publ by IEEE

    CY - New York, NY, USA

    ER -