A new unsupervised outlier detection method

被引:1
|
作者
Zheng, Lina [1 ]
Chen, Lijun [2 ]
Wang, Yini [3 ]
机构
[1] Guangxi Univ, Sch Econ, Nanning, Peoples R China
[2] Yulin Normal Univ, Ctr Appl Math Guangxi, Yulin, Guangxi, Peoples R China
[3] Guangxi Univ Finance & Econ, Guangxi Key Lab Seaward Econ Intelligent Syst Ana, Nanning, Guangxi, Peoples R China
关键词
Outlier detection; CIS; Information amount; IAOF; ALGORITHMS; DENSITY;
D O I
10.3233/JIFS-236518
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Information amount has been shown to be one of the most efficient methods for measuring uncertainty. However, there has been little research on outlier detection using information amount. To fill this void, this paper provides a new unsupervised outlier detection method based on the amount of information. First, the information amount in a given information system is determined, which offers a thorough estimate of the uncertainty of this information system. Then, the relative information amount and the relative cardinality are proposed. Following that, the degree of outlierness and weight function are shown. Furthermore, the information amount-based outlier factor is constructed, which determines whether an object is an outlier by its rank. Finally, a new unsupervised outlier detection method called the information amount-based outlier factor (IAOF) is developed. To validate the effectiveness and advantages of IAOF, it is compared to five existing outlier identification methods. The experimental results on real-world data sets show that this method is capable of addressing the problem of outlier detection in categorical information systems.
引用
收藏
页码:1713 / 1734
页数:22
相关论文
共 50 条
  • [1] A new unsupervised clustering method based on outlier information
    Lv, TY
    Wang, ZX
    Zuo, WL
    [J]. PROCEEDINGS OF THE 2004 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2004, : 1540 - 1544
  • [2] RDPOD: an unsupervised approach for outlier detection
    Abhaya Abhaya
    Bidyut Kr. Patra
    [J]. Neural Computing and Applications, 2022, 34 : 1065 - 1077
  • [3] Unsupervised outlier detection in multidimensional data
    Atiq ur Rehman
    Samir Brahim Belhaouari
    [J]. Journal of Big Data, 8
  • [4] On the Internal Evaluation of Unsupervised Outlier Detection
    Marques, Henrique O.
    Campello, Ricardo J. G. B.
    Zimek, Arthur
    Sander, Jorg
    [J]. PROCEEDINGS OF THE 27TH INTERNATIONAL CONFERENCE ON SCIENTIFIC AND STATISTICAL DATABASE MANAGEMENT, 2015,
  • [5] Internal Evaluation of Unsupervised Outlier Detection
    Marques, Henrique O.
    Campello, Ricardo J. G. B.
    Sander, Jorg
    Zimek, Arthur
    [J]. ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2020, 14 (04)
  • [6] Unsupervised outlier detection in multidimensional data
    Ur Rehman, Atiq
    Belhaouari, Samir Brahim
    [J]. JOURNAL OF BIG DATA, 2021, 8 (01)
  • [7] Bagged Subspaces for Unsupervised Outlier Detection
    Pasillas-Diaz, Jose Ramon
    Ratte, Sylvie
    [J]. COMPUTATIONAL INTELLIGENCE, 2017, 33 (03) : 507 - 523
  • [8] RDPOD: an unsupervised approach for outlier detection
    Abhaya, Abhaya
    Patra, Bidyut Kr
    [J]. NEURAL COMPUTING & APPLICATIONS, 2022, 34 (02): : 1065 - 1077
  • [9] Interpretable Single-dimension Outlier Detection (ISOD): An Unsupervised Outlier Detection Method Based on Quantiles and Skewness Coefficients
    Huang, Yuehua
    Liu, Wenfen
    Li, Song
    Guo, Ying
    Chen, Wen
    [J]. APPLIED SCIENCES-BASEL, 2024, 14 (01):
  • [10] Tax evasion risk management using a Hybrid Unsupervised Outlier Detection method
    Savic, Milos
    Atanasijevic, Jasna
    Jakovetic, Dusan
    Krejic, Natasa
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2022, 193