CPDGA: Change point driven growing auto-encoder for lifelong anomaly detection

作者：

Highlights：

• A Change Point Driven Growing Autoencoder (CPDGA) for lifelong anomaly detection.

• Unsupervised concept formation and memory organization in a forest structure.

• Hierarchical knowledge is continually updated and exploited for anomaly detection.

• Competitive high anomaly detection performance in complex real-world domains.

摘要

•A Change Point Driven Growing Autoencoder (CPDGA) for lifelong anomaly detection.•Unsupervised concept formation and memory organization in a forest structure.•Hierarchical knowledge is continually updated and exploited for anomaly detection.•Competitive high anomaly detection performance in complex real-world domains.

论文关键词：Anomaly detection,Lifelong learning,Auto-encoders,Neural networks,Unsupervised learning

论文评审过程：Received 27 June 2021, Revised 8 February 2022, Accepted 5 April 2022, Available online 13 April 2022, Version of Record 20 April 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.108756