Average Localised Proximity: A new data descriptor with good default one-class classification performance

作者：

Highlights：

• A new algorithm for performing one-class classification.

• First large-scale evaluation of one-class classification without tuning.

• Identification of recommended hyperparameter values for range of algorithms.

摘要

•A new algorithm for performing one-class classification.•First large-scale evaluation of one-class classification without tuning.•Identification of recommended hyperparameter values for range of algorithms.

论文关键词：Data descriptors,Hyperparameters,Localised distance,Nearest neighbours,Novelty detection,One-class classification,OWA operators,Semi-supervised outlier detection

论文评审过程：Received 30 June 2020, Revised 10 March 2021, Accepted 6 April 2021, Available online 22 April 2021, Version of Record 29 May 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107991