Regresar

Study of the Influences of Stimuli Characteristics in the Implementation of Steady State Visual Evoked Potentials Based Brain Computer Interface Systems

Abstract:

The characteristics of the stimulus can influence the strength of the SSVEP responses. However, a complete study of the influence of different characteristics of SSVEP stimuli was not considered in previous works. The present work has performed different experiments including the most important characteristics of a visual stimulus that can affect the results of a BCI system based on SSVEP. For the present study, we have used a methodology called action research to perform different experiments and get new learnings in each experiment. At the end of the experimentation, it was possible to find the optimal combination of stimulus’ characteristics that can allow us to implement a more precise SSVEP systems. For the experimentation, the traditional CCA algorithm and the proposed algorithm called RCA were used for signal classification. The results indicated that a white color circular visual stimulus of 7 to 10 Hz generated by an LED with a diffuser filter reaching 6 lx delivered the best SSVEP responses. With this combination of characteristics, it was possible to build CCA based BCI prototypes having up to 4 simultaneous stimuli with a precision higher than 82% and a response time of 0.5 s. In a similar way, it was also possible to generate an RCA based systems of up to 7 simultaneous stimuli with a precision higher than 90% and a response time of 2.5 s.