EEG signal classification and segmentation by means of Hidden Markov Models

The article describes the optimization of off-line classification of simple movements using a system based on Hidden Markov Models (HMM). Movements of the proximal arm (shoulder) and distal arm (finger) were classified using scalp EEG signals and reached classification score was typically about 80%. The classification of movement-related EEG data based on HMM yielded higher recognition scores than previously reported classification scores based on artificial neural networks (NaN). Next we tested the stability of the training algorithm and tried to utilize the trained models for the automatic segmentation of EEG realizations. We also tested the classification of brisk right index finger extensions and fexions.