A methodology for time-frequency image processing applied to the classification of non-stationary multichannel signals using instantaneous frequency descriptors with application to newborn EEG signals.
Boualem BoashashLarbi BoubchirGhasem AzemiPublished in: EURASIP J. Adv. Signal Process. (2012)
Keyphrases
- instantaneous frequency
- eeg signals
- empirical mode decomposition
- non stationary
- signal processing
- image processing
- signal analysis
- frequency modulation
- motor imagery
- intrinsic mode functions
- pattern recognition
- brain computer interface
- brain activity
- multi component
- classification accuracy
- eeg data
- feature selection
- kernel density estimators
- neural network
- linear discriminant classifier
- feature vectors
- machine learning
- white noise
- extracted features
- independent component analysis
- multiresolution
- electrical activity
- change point detection
- multiscale
- computer vision