Learning Multi-Pattern Normalities in the Frequency Domain for Efficient Time Series Anomaly Detection.
Feiyi ChenYingying ZhangZhen QinLunting FanRenhe JiangYuxuan LiangQingsong WenShuiguang DengPublished in: ICDE (2024)
Keyphrases
- anomaly detection
- frequency domain
- fourier transform
- intrusion detection
- connectionist systems
- spatial domain
- learning process
- unsupervised learning
- detecting anomalies
- feature extraction
- anomalous behavior
- network intrusion detection
- active learning
- detect anomalies
- power spectrum
- network traffic
- image sequences
- intrusion detection system
- subband
- training data
- preprocessing
- supervised learning
- network anomaly detection
- learning algorithm