Representative sequence selection in unsupervised anomaly detection using spectrum kernel with theoretical parameter setting.
Stefan SkludarekHirosuke YamamotoPublished in: ICMLC (2010)
Keyphrases
- parameter settings
- unsupervised anomaly detection
- anomaly detection
- parameter values
- parameter tuning
- intrusion detection
- genetic algorithm ga
- semi supervised
- support vector
- parameter optimization
- feature space
- neural network
- theoretical analysis
- kernel function
- parameter set
- pre selected
- knowledge discovery
- model selection
- feature extraction
- image sequences
- computer vision