In this paper, we propose an automated computer platform for the purpose ofclassifying Electroencephalography (EEG) signals associated with left and righthand movements using a hybrid system that uses advanced feature extractiontechniques and machine learning algorithms. It is known that EEG represents thebrain activity by the electrical voltage fluctuations along the scalp, andBrain-Computer Interface (BCI) is a device that enables the use of the brainneural activity to communicate with others or to control machines, artificiallimbs, or robots without direct physical movements. In our research work, weaspired to find the best feature extraction method that enables thedifferentiation between left and right executed fist movements through variousclassification algorithms. The EEG dataset used in this research was createdand contributed to PhysioNet by the developers of the BCI2000 instrumentationsystem. Data was preprocessed using the EEGLAB MATLAB toolbox and artifactsremoval was done using AAR. Data was epoched on the basis of Event-Related (De)Synchronization (ERD/ERS) and movement-related cortical potentials (MRCP)features. Mu/beta rhythms were isolated for the ERD/ERS analysis and deltarhythms were isolated for the MRCP analysis. The Independent Component Analysis(ICA) spatial filter was applied on related channels for noise reduction andisolation of both artifactually and neutrally generated EEG sources. The finalfeature vector included the ERD, ERS, and MRCP features in addition to themean, power and energy of the activations of the resulting independentcomponents of the epoched feature datasets. The datasets were inputted into twomachine-learning algorithms: Neural Networks (NNs) and Support Vector Machines(SVMs). Intensive experiments were carried out and optimum classificationperformances of 89.8 and 97.1 were obtained using NN and SVM, respectively.
展开▼
