A novel unsupervised method for anomaly detection in time series based on statistical features for industrial predictive maintenance.
Jesimar da Silva ArantesMárcio da Silva ArantesHerberth Birck FröhlichLaure SiretRenan BonnardPublished in: Int. J. Data Sci. Anal. (2021)
Keyphrases
- anomaly detection
- unsupervised learning
- network security
- similarity measure
- machine learning
- correlation analysis
- network intrusion detection
- network traffic
- one class support vector machines
- anomalous behavior
- network intrusion
- detect anomalies
- computer security
- intrusion detection
- pairwise
- bayesian networks
- genetic algorithm