Brain Computer Interfaces (BCI) provide the opportunity to control external devices using the brainudElectroEncephaloGram (EEG) signals. In this paper we propose two software framework in order toudcontrol a 5 degree of freedom robotic and prosthetic hand. Results are presented where an EmotivudCognitive Suite (i.e. the 1st framework) combined with an embedded software system (i.e. an open sourceudArduino board) is able to control the hand through character input associated with the taught actions ofudthe suite. This system provides evidence of the feasibility of brain signals being a viable approach toudcontrolling the chosen prosthetic. Results are then presented in the second framework. This latter oneudallowed for the training and classification of EEG signals for motor imagery tasks. When analysing theudsystem, clear visual representations of the performance and accuracy are presented in the results using audconfusion matrix, accuracy measurement and a feedback bar signifying signal strength. Experiments withudvarious acquisition datasets were carried out and with a critical evaluation of the results given. Finallyuddepending on the classification of the brain signal a Python script outputs the driving command to theudArduino to control the prosthetic. The proposed architecture performs overall good results for the designudand implementation of economically convenient BCI and prosthesis.
展开▼
