DyD2: Dynamic Double anomaly Detection Application to on-board space radiation faults. Issue 6 (2022)

• Record Type: Journal Article
• Authors: Dorise, Adrien; Travé-Massuyès, Louise; Subias, Audine; Alonso, Corinne
• Is Part Of: IFAC-PapersOnLine. Volume 55:Issue 6(2022)
• Page Start: 205
• Page End: 210
• Publication Date: 2022
• Subjects: Anomaly detection -- Machine learning -- One-class classification -- Embedded applications -- Aerospace engineering -- Space Radiations; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2022.07.130
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: Anomaly detection is a crucial aspect of embedded applications. However, limited computational power, evolving environments, and lack of training data are difficulties that can limit anomaly detection algorithms. One class classification algorithms are often used for this task to circumvent the need of anomalous data in the training set. This paper presents a new machine learning algorithm for anomaly detection called Dynamic Double anomaly Detection DyD 2 that is suited to evolving environments and on-board requirements. The contributions made by DyD 2 are thoroughly presented and an experimental evaluation is set up to compare DyD 2 to state-of-the-art algorithms.