Email this article Time Series Anomaly Searching Based on DBSCAN Ensembles
- Authors: Chesnokov M.Y.1
-
Affiliations:
- Department of Theoretical and Applied Problems of Innovation, Moscow Institute of Physics and Technology (State University)
- Issue: Vol 46, No 5 (2019)
- Pages: 299-305
- Section: Article
- URL: https://journals.rcsi.science/0147-6882/article/view/175520
- DOI: https://doi.org/10.3103/S0147688219050010
- ID: 175520
Cite item
Open Access
Access granted
Subscription Access
Abstract
This article suggests a technique for building an ensemble based on the DBSCAN algorithm. This technique uses the internal structure of a time series for adaptively selecting input parameters. When used in experiments, it shows a narrower variance and higher levels of anomaly detection using real and synthetic data compared with a number of popular approaches.
Keywords
About the authors
M. Yu. Chesnokov
Department of Theoretical and Applied Problems of Innovation, Moscow Institute of Physics and Technology (State University)
Author for correspondence.
Email: mikhail.chesnokov@psytech.edu
Russian Federation, Moscow, 117303
Supplementary files
