Multi-Band CNN With Band-Dependent Kernels and Amalgamated Cross Entropy Loss for Motor Imagery Classification.
Jinhyo ShinWonzoo ChungPublished in: IEEE J. Biomed. Health Informatics (2023)
Keyphrases
- motor imagery
- cross entropy
- multi band
- eeg signals
- frequency band
- support vector
- feature space
- classification accuracy
- brain computer interface
- pattern recognition
- log likelihood
- neural network
- image classification
- maximum likelihood
- feature vectors
- eeg data
- feature selection
- density estimation
- supervised learning
- image data
- high resolution
- image segmentation