English  |  正體中文  |  简体中文  |  Items with full text/Total items : 88295/117812 (75%)
Visitors : 23397884      Online Users : 84
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    政大機構典藏 > 理學院 > 資訊科學系 > 期刊論文 >  Item 140.119/70680
    Please use this identifier to cite or link to this item: http://nccur.lib.nccu.edu.tw/handle/140.119/70680

    Title: On Adjustment Functions for Weight-Adjusted Voting-Based Ensembles of Classifiers
    Authors: 徐國偉
    Hsu, Kuo-Wei
    Contributors: 資科系
    Keywords: Classificatio;ensemble;voting
    Date: 2014.07
    Issue Date: 2014-10-20 18:21:29 (UTC+8)
    Abstract: An ensemble of classifiers is a system consisting of multiple member classifiers which are trained individually and whose outcomes are aggregated into an overall outcome for a testing data instance. Voting is a common approach used to aggregate outcomes generated by member classifiers. Ensembles based on weighted voting have been studied for some time. However, the focus of most studies is more on weight assignment rather than on weight adjustment, whose basic idea is to increase the weights of votes from member classifiers performing better on data instances of higher difficulty. In this paper, we present our study on adjustment functions in each of which both the performance of a member classifier and the difficulty of a data set are determined nonlinearly. We report results from experiments conducted on several data sets, demonstrating the potential of the studied functions.
    Relation: Journal of Computers (JCP), 9(7), 1547-1552
    Data Type: article
    DOI 連結: http://dx.doi.org/10.4304/jcp.9.7.1547-1552
    DOI: 10.4304/jcp.9.7.1547-1552
    Appears in Collections:[資訊科學系] 期刊論文

    Files in This Item:

    File Description SizeFormat
    1547-1552.pdf381KbAdobe PDF642View/Open

    All items in 政大典藏 are protected by copyright, with all rights reserved.

    社群 sharing

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback