We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Unsupervised and scalable subsequence anomaly detection in large data series.
- Authors
Boniol, Paul; Linardi, Michele; Roncallo, Federico; Palpanas, Themis; Meftah, Mohammed; Remy, Emmanuel
- Abstract
Subsequence anomaly (or outlier) detection in long sequences is an important problem with applications in a wide range of domains. However, the approaches that have been proposed so far in the literature have severe limitations: they either require prior domain knowledge or become cumbersome and expensive to use in situations with recurrent anomalies of the same type. In this work, we address these problems and propose NormA, a novel approach, suitable for domain-agnostic anomaly detection. NormA is based on a new data series primitive, which permits to detect anomalies based on their (dis)similarity to a model that represents normal behavior. The experimental results on several real datasets demonstrate that the proposed approach correctly identifies all single and recurrent anomalies of various types, with no prior knowledge of the characteristics of these anomalies (except for their length). Moreover, it outperforms by a large margin the current state-of-the art algorithms in terms of accuracy, while being orders of magnitude faster.
- Subjects
ANOMALY detection (Computer security); MAGNITUDE (Mathematics); INTRUSION detection systems (Computer security); PRIOR learning; DATABASES; ALGORITHMS
- Publication
VLDB Journal International Journal on Very Large Data Bases, 2021, Vol 30, Issue 6, p909
- ISSN
1066-8888
- Publication type
Article
- DOI
10.1007/s00778-021-00655-8