Multiple k-NN classifiers fusion based on evidence theory

被引:2
|
作者
Han, Deqiang [1 ]
Han, Chongzhao [1 ]
Yang, Yi [1 ]
机构
[1] Xi An Jiao Tong Univ, Inst Integrated Automat, Xian 710049, Shaanxi, Peoples R China
关键词
k-NN; multiple classifiers fusion; evidence theory; classification;
D O I
10.1109/ICAL.2007.4338932
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Multiple Classifiers Fusion is a powerful solution to the difficult and complex classification problems, which can improve performance and generalization capability. This paper presents a multiple k-Nearest Neighbor classifiers fusion approach based on evidence theory. Independent k-NN classifiers are established based on heterogeneous features. The novel approach to generating mass functions of a given sample for each member classifiers are based on the class distributions on the k-Nearest Neighbors over heterogeneous features. Based on Dempster rule of combination, we can obtain the combined mass functions. Then the corresponding belief functions can be derived and the classification decisions of the fused classifier can be done. The approach proposed is promising because it takes full advantage of the simplicity of k-NN classifier and the better performance based on classifiers fusion. Experimental results provided show the efficacy and rationality of the approach proposed.
引用
收藏
页码:2155 / 2159
页数:5
相关论文
共 50 条
  • [1] Voting over multiple k-NN classifiers
    Grabowski, S
    [J]. MODERN PROBLEMS OF RADIO ENGINEERING, TELECOMMUNICATIONS AND COMPUTER SCIENCE, PROCEEDINGS, 2002, : 223 - 225
  • [2] Moderating k-NN classifiers
    Alkoot, FM
    Kittler, J
    [J]. PATTERN ANALYSIS AND APPLICATIONS, 2002, 5 (03) : 326 - 332
  • [3] Moderating k-NN Classifiers
    Fuad M. Alkoot
    Josef Kittler
    [J]. Pattern Analysis & Applications, 2002, 5 : 326 - 332
  • [4] Experiments with soft fusion methods when bagging k-NN classifiers
    Alkoot, Fuad M.
    [J]. PROCEEDINGS OF THE EIGHTH IASTED INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING, 2006, : 40 - 44
  • [5] Reducing computational complexity in k-NN based adaptive classifiers
    Alippi, Cesare
    Roveri, Manuel
    [J]. 2007 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE FOR MEASUREMENT SYSTEMS AND APPLICATIONS, 2007, : 68 - +
  • [6] Sensor based on k-NN classifiers in Agricultural Pest Control
    Penaloza, Elmer A. G.
    Mercaldi, Heitor V.
    Oliveira, Vilma A.
    Cruvinel, Paulo E.
    [J]. 2019 18TH EUROPEAN CONTROL CONFERENCE (ECC), 2019, : 3286 - 3291
  • [7] Fusion of Granular Computing and k-NN Classifiers for Medical Data Support System
    Bernas, Marcin
    Orczyk, Tomasz
    Porwik, Piotr
    [J]. INTELLIGENT INFORMATION AND DATABASE SYSTEMS, PT II, 2015, 9012 : 62 - 71
  • [8] Fast multistage algorithm for K-NN classifiers
    Soraluze, I
    Rodriguez, C
    Boto, F
    Cortes, A
    [J]. PROGRESS IN PATTERN RECOGNITION, SPEECH AND IMAGE ANALYSIS, 2003, 2905 : 448 - 455
  • [9] k-NN classifiers: investigating the k = k (n) relationship
    Alippi, C.
    Fuhrman, M.
    Roveri, M.
    [J]. 2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8, 2008, : 3676 - +
  • [10] Ambient Intelligence Assistant for Running Sports Based on k-NN Classifiers
    Lopez-Matencio, P.
    Vales Alonso, J.
    Gonzalez-Castano, F. J.
    Sieiro, J. L.
    Alcaraz, J. J.
    [J]. 3RD INTERNATIONAL CONFERENCE ON HUMAN SYSTEM INTERACTION, 2010, : 605 - 611