A hybrid prototype selection-based deep learning approach for anomaly detection in industrial machines

作者：

Highlights：

• Learning features for anomaly detection problems may be a challenging task.

• Prototype selection improves the training of feature extractors for anomaly detection.

• It helps mapping normal instances to a more restricted region of the feature space.

• It makes the anomaly detection via one-class classification easier.

摘要

•Learning features for anomaly detection problems may be a challenging task.•Prototype selection improves the training of feature extractors for anomaly detection.•It helps mapping normal instances to a more restricted region of the feature space.•It makes the anomaly detection via one-class classification easier.

论文关键词：Anomaly detection,Deep learning,Prototype selection,Rotating machinery

论文评审过程：Received 15 August 2021, Revised 4 April 2022, Accepted 5 May 2022, Available online 14 May 2022, Version of Record 27 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117528