On the Selection of Time-Frequency Features for Improving the Detection and Classification of Newborn EEG Seizure Signals and Other Abnormalities.
Boualem BoashashLarbi BoubchirPublished in: ICONIP (4) (2012)
Keyphrases
- eeg signals
- epileptic seizures
- signal processing
- eeg data
- event related potentials
- extracted features
- motor imagery
- brain computer interface
- brain activity
- feature extraction
- feature set
- pattern recognition
- signal analysis
- classification method
- brain signals
- classification accuracy
- feature extraction and classification
- classification process
- false positives
- selected features
- feature selection
- feature vectors
- features extraction
- gabor filters
- spectral features
- medical images
- support vector machine classifier
- image features
- decision trees
- sleep stage
- machine learning
- selecting relevant features