Effective classification of noisy data streams with attribute-oriented dynamic classifier selection

被引:25
|
作者
Zhu, XQ [1 ]
Wu, XD
Yang, Y
机构
[1] Univ Vermont, Dept Comp Sci, Burlington, VT 05405 USA
[2] Monash Univ, Sch Comp Sci & Software Engn, Melbourne, Vic 3004, Australia
关键词
stream data mining; classification; dynamic classifier selection; classifier ensemble; multiple classifier systems; class noise;
D O I
10.1007/s10115-005-0212-y
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recently, mining from data streams has become an important and challenging task for many real-world applications such as credit card fraud protection and sensor networking. One popular solution is to separate stream data into chunks, learn a base classifier from each chunk, and then integrate all base classifiers for effective classification. In this paper, we propose a new dynamic classifier selection (DCS) mechanism to integrate base classifiers for effective mining from data streams. The proposed algorithm dynamically selects a single "best" classifier to classify each test instance at run time. Our scheme uses statistical information from attribute values, and uses each attribute to partition the evaluation set into disjoint subsets, followed by a procedure that evaluates the classification accuracy of each base classifier on these subsets. Given a test instance, its attribute values determine the subsets that the similar instances in the evaluation set have constructed, and the classifier with the highest classification accuracy on those subsets is selected to classify the test instance. Experimental results and comparative studies demonstrate the efficiency and efficacy of our method. Such a DCS scheme appears to be promising in mining data streams with dramatic concept drifting or with a significant amount of noise, where the base classifiers are likely conflictive or have low confidence.
引用
收藏
页码:339 / 363
页数:25
相关论文
共 50 条
  • [1] Effective classification of noisy data streams with attribute-oriented dynamic classifier selection
    Xingquan Zhu
    Xindong Wu
    Ying Yang
    [J]. Knowledge and Information Systems, 2006, 9 : 339 - 363
  • [2] Dynamic classifier selection for effective mining from noisy data streams
    Zhu, XQ
    Wu, XD
    Yang, Y
    [J]. FOURTH IEEE INTERNATIONAL CONFERENCE ON DATA MINING, PROCEEDINGS, 2004, : 305 - 312
  • [3] An evolutionary and attribute-oriented ensemble classifier
    Lee, Chien-I
    Tsai, Cheng-Jung
    Ku, Chih-Wei
    [J]. COMPUTATIONAL SCIENCE AND ITS APPLICATIONS - ICCSA 2006, PT 2, 2006, 3981 : 1210 - 1218
  • [4] Enhancing classification performance using attribute-oriented functionally expanded data
    Bertini Junior, Joao Roberto
    Nicoletti, Maria do Carmo
    [J]. PATTERN RECOGNITION LETTERS, 2017, 89 : 39 - 45
  • [5] An attribute-oriented ensemble classifier based on Niche Gene Expression Programming
    Wu, Jiang
    Tang, Changjie
    Zhu, Jun
    Li, Taiyong
    Duan, Lei
    Li, Chuan
    Dai, Li
    [J]. ICNC 2007: THIRD INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 3, PROCEEDINGS, 2007, : 525 - +
  • [6] Incorporating domain knowledge into attribute-oriented data mining
    McClean, S
    Scotney, B
    Shapcott, M
    [J]. INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2000, 15 (06) : 535 - 547
  • [7] A framework for dynamic classifier selection oriented by the classification problem difficulty
    Brun, Andre L.
    Britto, Alceu S., Jr.
    Oliveira, Luiz S.
    Enernbreck, Fabricio
    Sabourin, Robert
    [J]. PATTERN RECOGNITION, 2018, 76 : 175 - 190
  • [8] Efficient Rule-Based Attribute-Oriented Induction for Data Mining
    David W. Cheung
    H.Y. Hwang
    Ada W. Fu
    Jiawei Han
    [J]. Journal of Intelligent Information Systems, 2000, 15 : 175 - 200
  • [9] Efficient rule-based attribute-oriented induction for data mining
    Cheung, DW
    Hwang, HY
    Fu, AW
    Han, JW
    [J]. JOURNAL OF INTELLIGENT INFORMATION SYSTEMS, 2000, 15 (02) : 175 - 200
  • [10] Distributed data mining: An attribute-oriented key-preserving method
    Muyeba, MK
    Keane, JA
    [J]. DATA MINING AND KNOWLEDGE DISCOVERY: THEORY, TOOLS, AND TECHNOLOGY II, 2000, 4057 : 163 - 172