MAHALANOBIS DISTANCE-BASED 2 NEW FEATURE EVALUATION CRITERIA

被引：5
|
作者：
RAY, S
TURNER, LF
机构：
[1] INDIAN STAT INST,ELECTR & COMMUN SCI UNIT,CALCUTTA 700035,W BENGAL,INDIA
[2] IMPERIAL COLL SCI TECHNOL & MED,DEPT ELECT ENGN,COMMUN SECT,LONDON SW7 2BT,ENGLAND
来源：
INFORMATION SCIENCES | 1992年 / 60卷 / 03期
关键词：
D O I：
10.1016/0020-0255(92)90012-W
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper two Mahalanobis distance-based criteria are proposed for feature evaluation. Because of certain theoretical properties of these two criteria which are discussed in the paper, they are expected to perform better than the direct use of the Mahalanobis distance in a multiclass pattern recognition problem. Experimental results also suggest their superiority.
引用
收藏
页码：217 / 245
页数：29
相关论文
共 50 条
  • [31] Feature Extraction for Distance-Based Classification of Signal Sources
    Birleanu, Florin-Marian
    Iana, Vasile-Gabriel
    Oproescu, Mihai
    Ionita, Silvia
    PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON ELECTRONICS, COMPUTERS AND ARTIFICIAL INTELLIGENCE - ECAI 2017, 2017,
  • [32] Feature-rich distance-based terrain synthesis
    Brennan Rusnell
    David Mould
    Mark Eramian
    The Visual Computer, 2009, 25 : 573 - 579
  • [33] Distance-Based Network Recovery under Feature Correlation
    Adametz, David
    Roth, Volker
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014), 2014, 27
  • [34] Distance-based test feature classifiers and its applications
    Lashkia, V
    Kaneko, S
    Aleshin, S
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2000, E83D (04): : 904 - 913
  • [35] Autoencoder and Mahalanobis distance-based monitoring indicator estimation for early clinkering detection in boiler
    Sinha, Aparna
    Das, Debanjan
    Kumar Palavalasa, Suneel
    Singh Bugga, Jaspreet
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2025, 36 (01)
  • [36] Evolutionary Mahalanobis Distance-Based Oversampling for Multi-Class Imbalanced Data Classification
    Yao, Leehter
    Lin, Tung-Bin
    SENSORS, 2021, 21 (19)
  • [37] A Mahalanobis Distance-Based Automatic Threshold Selection Method for Peaks Over Threshold Model
    Kiran, K. G.
    Srinivas, V. V.
    WATER RESOURCES RESEARCH, 2021, 57 (01)
  • [38] l2,p-Norm and Mahalanobis Distance-Based Robust Fuzzy C-Means
    Chen, Qiang
    Nie, Feiping
    Yu, Weizhong
    Li, Xuelong
    IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2023, 31 (09) : 2904 - 2916
  • [39] Feature Selection for Steganalysis using the Mahalanobis Distance
    Davidson, Jennifer L.
    Jalan, Jaikishan
    MEDIA FORENSICS AND SECURITY II, 2010, 7541
  • [40] Understanding Mahalanobis Distance Criterion for Feature Selection
    Masnan, Maz Jamilah
    Mahat, Nor Idayu
    Shakaff, Ali Yeon Md
    Abdullah, Abu Hassan
    Zakaria, Nur Zawatil Ishqi
    Yusuf, Nurlisa
    Subari, Norazian
    Zakaria, Ammar
    Aziz, Abdul Hallis Abdul
    INTERNATIONAL CONFERENCE ON MATHEMATICS, ENGINEERING AND INDUSTRIAL APPLICATIONS 2014 (ICOMEIA 2014), 2015, 1660
12345