Time-frequency analysis of EEG signals from healthy subjects allocated by gender for a subject-independent BCI-based on motor imagery

Most of the recent brain-computer interfaces (BCI) based on motor imagery are designed by taking into account a single user. A BCI system designed for multiple users without the need of extensive training sessions could be a viable solution for the system's implementation outside research centers. The present work explores the design of an independent-subject BCI. In order to accomplish this, Linear Discriminant Analysis classifiers were designed with the data of a sample of 30 healthy volunteers as a whole group and separated by gender. Three different methods were employed to compute power spectrum features from the volunteer's electroencephalographic recordings. The results show that it is possible to design an independent-subject BCI for the classification of right or left hand motor imagery with respect of a reference interval with classification accuracies above 70%. The female gender could benefit more from a subject-independent classifier, than the male gender.