Distribution Agnostic Symbolic Representations for Time Series Dimensionality Reduction and Online Anomaly Detection.
Konstantinos BountrogiannisGeorge TzagkarakisPanagiotis TsakalidesPublished in: CoRR (2021)
Keyphrases
- anomaly detection
- symbolic representation
- dimensionality reduction
- intrusion detection
- detect anomalies
- network intrusion detection
- detecting anomalies
- anomalous behavior
- real valued
- unsupervised learning
- intrusion detection system
- feature extraction
- detecting anomalous
- network anomaly detection
- network traffic
- real valued time series
- high dimensional
- one class support vector machines
- high dimensional data
- original data
- low dimensional
- normal behavior
- data sets
- negative selection algorithm
- principal component analysis
- random variables
- data points
- data analysis
- pattern recognition
- training data
- image segmentation
- data mining