Calibration of One-Class SVM for MV set estimation

被引:0
|
作者
Thomas, Albert [1 ,2 ]
Feuillard, Vincent [1 ]
Gramfort, Alexandre [2 ]
机构
[1] Airbus Grp Innovat, 12 Rue Pasteur, F-92150 Suresnes, France
[2] Univ Paris Saclay, Telecom Paris Tech, CNRS, LTCI, F-75013 Paris, France
关键词
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A general approach for anomaly detection or novelty detection consists in estimating high density regions or Minimum Volume (MV) sets. The One-Class Support Vector Machine (OCSVM) is a state-of-the-art algorithm for estimating such regions from high dimensional data. Yet it suffers from practical limitations. When applied to a limited number of samples it can lead to poor performance even when picking the best hyperparameters. Moreover the solution of OCSVM is very sensitive to the selection of hyperparameters which makes it hard to optimize in an unsupervised setting. We present a new approach to estimate MV sets using the OCSVM with a different choice of the parameter controlling the proportion of outliers. The solution function of the OCSVM is learnt on a training set and the desired probability mass is obtained by adjusting the offset on a test set to prevent overfitting. Models learnt on different train/test splits are then aggregated to reduce the variance induced by such random splits. Our approach makes it possible to tune the hyperparameters automatically and obtain nested set estimates. Experimental results show that our approach outperforms the standard OCSVM formulation while suffering less from the curse of dimensionality than kernel density estimates. Results on actual data sets are also presented.
引用
收藏
页码:75 / 83
页数:9
相关论文
共 50 条
  • [31] One-class SVM based segmentation for SAR image
    Yan, Jianjun
    Zheng, Jianrong
    ADVANCES IN NEURAL NETWORKS - ISNN 2007, PT 3, PROCEEDINGS, 2007, 4493 : 959 - +
  • [32] Nearest Mean Classification via One-Class SVM
    Shin, Donghyuk
    Kim, Saejoon
    INTERNATIONAL JOINT CONFERENCE ON COMPUTATIONAL SCIENCES AND OPTIMIZATION, VOL 1, PROCEEDINGS, 2009, : 593 - 596
  • [33] Multi-task learning with one-class SVM
    He, Xiyan
    Mourot, Gilles
    Maquin, Didier
    Ragot, Jose
    Beauseroy, Pierre
    Smolarz, Andre
    Grall-Maes, Edith
    NEUROCOMPUTING, 2014, 133 : 416 - 426
  • [34] Brain activation detection by neighborhood one-class SVM
    Yang, Jian
    Zhong, Ning
    Liang, Peipeng
    Wang, Jue
    Yao, Yiyu
    Lu, Shengfu
    COGNITIVE SYSTEMS RESEARCH, 2010, 11 (01): : 16 - 24
  • [35] One-class SVM in multi-task learning
    He, Xiyan
    Mourot, Gilles
    Maquin, Didier
    Ragot, Jose
    Beauseroy, Pierre
    Smolarz, Andre
    Grall-Maes, Edith
    ADVANCES IN SAFETY, RELIABILITY AND RISK MANAGEMENT, 2012, : 486 - 494
  • [36] Evolving training model method for one-class SVM
    Tran, QA
    Zhang, QL
    Li, X
    2003 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOLS 1-5, CONFERENCE PROCEEDINGS, 2003, : 2388 - 2393
  • [37] Efficient Data Point Pruning for One-Class SVM
    Fujiwara, Yasuhiro
    Kanai, Sekitoshi
    Arai, Junya
    Ida, Yasutoshi
    Ueda, Naonori
    THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 3590 - 3597
  • [38] On feature selection with principal component analysis for one-class SVM
    Lian, Heng
    PATTERN RECOGNITION LETTERS, 2012, 33 (09) : 1027 - 1031
  • [39] Fall detection by wearable sensor and one-class SVM algorithm
    Zhang, Tong
    Wang, Jue
    Xu, Liang
    Liu, Ping
    INTELLIGENT COMPUTING IN SIGNAL PROCESSING AND PATTERN RECOGNITION, 2006, 345 : 858 - 863
  • [40] Antinoise Texture Retrieval Based on PCNN and One-Class SVM
    Tian, Le
    Ma, Yi-De
    Liu, Li
    Zhan, Kun
    ADVANCES IN COMPUTATIONAL INTELLIGENCE, PT I, 2013, 7902 : 291 - 298