Selecting Informative Variables in the Identification Problem

被引：12
|
作者：
Mihov, Eugene D. [1 ]
Nepomnyashchiy, Oleg V. [1 ]
机构：
[1] Siberian Fed Univ, Inst Space & Informat Technol, Kirensky 26, Krasnoyarsk 660074, Russia
来源：
JOURNAL OF SIBERIAN FEDERAL UNIVERSITY-MATHEMATICS & PHYSICS | 2016年 / 9卷 / 04期
基金：
俄罗斯科学基金会;
关键词：
classification; small training sample; informative variable; optimization of the coefficient vector of the kernel fuzziness;
D O I：
10.17516/1997-1397-2016-9-4-473-480
中图分类号：
O1 [数学];
学科分类号：
0701 ; 070101 ;
摘要：
The problem of multidimensional object classification with small training sample is considered. The following algorithms of estimating variable informativeness are considered:Ad, Del, AdDel. A new algorithm for selecting informative variables is proposed. It is based on the optimization of the coefficient vector of the kernel fuzziness. Some modification of this algorithm is also discussed. The comparative analysis of existing methods for selecting informative variables is presented.
引用
收藏
页码：473 / 480
页数：8
相关论文
共 50 条
  • [31] EFFECTS OF INFORMATIVE AND JUSTIFICATORY VARIABLES UPON IMITATION
    FLANDERS, JP
    THISTLET.DL
    JOURNAL OF EXPERIMENTAL SOCIAL PSYCHOLOGY, 1970, 6 (03) : 316 - &
  • [32] Identification of errors-in-variables models as a quadratic eigenvalue problem
    Diversi, Roberto
    Soverini, Umberto
    2013 EUROPEAN CONTROL CONFERENCE (ECC), 2013, : 1896 - 1901
  • [33] Direct integration of microarrays for selecting informative genes and phenotype classification
    Yoon, Youngrai
    Lee, Jongchan
    Park, Sanghyun
    Bien, Sangjay
    Chung, Hyun Cheol
    Rha, Sun Young
    INFORMATION SCIENCES, 2008, 178 (01) : 88 - 105
  • [34] Integer programming for selecting set of informative markers in paternity inference
    Soichiro Nishiyama
    Kengo Sato
    Ryutaro Tao
    BMC Bioinformatics, 23
  • [35] SELECTING AN INFORMATIVE SIGNAL PAIR IN A 2-CHANNEL DEVICE
    ONISHCHENKO, AM
    INDUSTRIAL LABORATORY, 1994, 60 (10): : 627 - 630
  • [36] Selecting Informative Features for Post-hoc Community Explanation
    Sadler, Sophie
    Greene, Derek
    Archambault, Daniel
    COMPLEX NETWORKS & THEIR APPLICATIONS X, VOL 1, 2022, 1015 : 297 - 308
  • [37] Integer programming for selecting set of informative markers in paternity inference
    Nishiyama, Soichiro
    Sato, Kengo
    Tao, Ryutaro
    BMC BIOINFORMATICS, 2022, 23 (01)
  • [38] Selecting Informative Universum Sample for Semi-Supervised Learning
    Chen, Shuo
    Zhang, Changshui
    21ST INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI-09), PROCEEDINGS, 2009, : 1016 - 1021
  • [39] Selecting maximally informative sibships for QTL linkage and association analysis
    Purcell, S
    Cherny, SS
    Sham, PC
    MOLECULAR PSYCHIATRY, 1999, 4 : S11 - S11
  • [40] Selecting Most Informative Contributors with Unknown Costs for Budgeted Crowdsensing
    Yang, Shuo
    Wu, Fan
    Tang, Shaojie
    Luo, Tie
    Gao, Xiaofeng
    Kong, Linghe
    Chen, Guihai
    2016 IEEE/ACM 24TH INTERNATIONAL SYMPOSIUM ON QUALITY OF SERVICE (IWQOS), 2016,
12345