Distribution Agnostic Symbolic Representations for Time Series Dimensionality Reduction and Online Anomaly Detection.
Konstantinos BountrogiannisGeorge TzagkarakisPanagiotis TsakalidesPublished in: IEEE Trans. Knowl. Data Eng. (2023)
Keyphrases
- anomaly detection
- symbolic representation
- dimensionality reduction
- intrusion detection
- detecting anomalies
- real valued
- detect anomalies
- network traffic
- anomalous behavior
- unsupervised learning
- network intrusion detection
- one class support vector machines
- network anomaly detection
- low dimensional
- high dimensional data
- feature extraction
- original data
- databases
- intrusion detection system
- detecting anomalous
- high dimensional
- real valued time series
- data points
- neural network
- nearest neighbor
- feature vectors
- object recognition
- negative selection algorithm
- pattern recognition
- cumulative sum
- symbolic aggregate approximation