An Investigation of the Performance of Informative Samples Preservation Methods

Jianlin Xiong, Yuhua Li

    Research output: Chapter in Book/Report/Conference proceeding › Chapter

    Abstract

    Instance-based learning algorithms make prediction/generalization based on the stored instances. Storing all instances of large data size applications causes huge memory requirements and slows program execution speed; it may make the prediction process impractical or even impossible. Therefore researchers have made great efforts to reduce the data size of instance-based learning algorithms by selecting informative samples. This paper has two main purposes. First, it investigates recent developments in informative sample preservation methods and identifies five representative methods for use in this study. Second, the five selected methods are implemented in a standardized input-output interface so that the programs can be used by other researchers, their performance in terms of accuracy and reduction rates are compared on ten benchmark classification problems. K-nearest neighbor is employed as the classifier in the performance comparison.
    LanguageEnglish
    Title of host publicationLecture Notes in Electrical Engineering: Recent Advances in Computer Science and Information Engineering
    Pages13-18
    Volume124
    DOIs
    Publication statusPublished - 2012

    Fingerprint

    Learning algorithms
    Classifiers
    Data storage equipment

    Cite this

    Xiong, J., & Li, Y. (2012). An Investigation of the Performance of Informative Samples Preservation Methods. In Lecture Notes in Electrical Engineering: Recent Advances in Computer Science and Information Engineering (Vol. 124, pp. 13-18) https://doi.org/10.1007/978-3-642-25781-0_3
    Xiong, Jianlin ; Li, Yuhua. / An Investigation of the Performance of Informative Samples Preservation Methods. Lecture Notes in Electrical Engineering: Recent Advances in Computer Science and Information Engineering. Vol. 124 2012. pp. 13-18
    @inbook{36e7d4460ffe4d2b967ded3eb04947b6,
    title = "An Investigation of the Performance of Informative Samples Preservation Methods",
    abstract = "Instance-based learning algorithms make prediction/generalization based on the stored instances. Storing all instances of large data size applications causes huge memory requirements and slows program execution speed; it may make the prediction process impractical or even impossible. Therefore researchers have made great efforts to reduce the data size of instance-based learning algorithms by selecting informative samples. This paper has two main purposes. First, it investigates recent developments in informative sample preservation methods and identifies five representative methods for use in this study. Second, the five selected methods are implemented in a standardized input-output interface so that the programs can be used by other researchers, their performance in terms of accuracy and reduction rates are compared on ten benchmark classification problems. K-nearest neighbor is employed as the classifier in the performance comparison.",
    author = "Jianlin Xiong and Yuhua Li",
    year = "2012",
    doi = "10.1007/978-3-642-25781-0_3",
    language = "English",
    isbn = "na",
    volume = "124",
    pages = "13--18",
    booktitle = "Lecture Notes in Electrical Engineering: Recent Advances in Computer Science and Information Engineering",

    }

    Xiong, J & Li, Y 2012, An Investigation of the Performance of Informative Samples Preservation Methods. in Lecture Notes in Electrical Engineering: Recent Advances in Computer Science and Information Engineering. vol. 124, pp. 13-18. https://doi.org/10.1007/978-3-642-25781-0_3

    An Investigation of the Performance of Informative Samples Preservation Methods. / Xiong, Jianlin; Li, Yuhua.

    Lecture Notes in Electrical Engineering: Recent Advances in Computer Science and Information Engineering. Vol. 124 2012. p. 13-18.

    Research output: Chapter in Book/Report/Conference proceeding › Chapter

    TY - CHAP

    T1 - An Investigation of the Performance of Informative Samples Preservation Methods

    AU - Xiong, Jianlin

    AU - Li, Yuhua

    PY - 2012

    Y1 - 2012

    N2 - Instance-based learning algorithms make prediction/generalization based on the stored instances. Storing all instances of large data size applications causes huge memory requirements and slows program execution speed; it may make the prediction process impractical or even impossible. Therefore researchers have made great efforts to reduce the data size of instance-based learning algorithms by selecting informative samples. This paper has two main purposes. First, it investigates recent developments in informative sample preservation methods and identifies five representative methods for use in this study. Second, the five selected methods are implemented in a standardized input-output interface so that the programs can be used by other researchers, their performance in terms of accuracy and reduction rates are compared on ten benchmark classification problems. K-nearest neighbor is employed as the classifier in the performance comparison.

    AB - Instance-based learning algorithms make prediction/generalization based on the stored instances. Storing all instances of large data size applications causes huge memory requirements and slows program execution speed; it may make the prediction process impractical or even impossible. Therefore researchers have made great efforts to reduce the data size of instance-based learning algorithms by selecting informative samples. This paper has two main purposes. First, it investigates recent developments in informative sample preservation methods and identifies five representative methods for use in this study. Second, the five selected methods are implemented in a standardized input-output interface so that the programs can be used by other researchers, their performance in terms of accuracy and reduction rates are compared on ten benchmark classification problems. K-nearest neighbor is employed as the classifier in the performance comparison.

    U2 - 10.1007/978-3-642-25781-0_3

    DO - 10.1007/978-3-642-25781-0_3

    M3 - Chapter

    SN - na

    VL - 124

    SP - 13

    EP - 18

    BT - Lecture Notes in Electrical Engineering: Recent Advances in Computer Science and Information Engineering

    ER -

    Xiong J, Li Y. An Investigation of the Performance of Informative Samples Preservation Methods. In Lecture Notes in Electrical Engineering: Recent Advances in Computer Science and Information Engineering. Vol. 124. 2012. p. 13-18 https://doi.org/10.1007/978-3-642-25781-0_3

    Access to Document