A novel approach to steady-state visual evoked potential (SSVEP) based brain-computer interface (BCI) is presented in the paper. To minimize possible side-effects of the monochromatic light SSVEP-based BCI we propose to utilize chromatic green-blue flicker stimuli in higher, comparing to the traditionally used, frequencies. The developed safer SSVEP responses are processed an classified with features drawn from EEG power spectra. Results obtained from healthy users support the research hypothesis of the chromatic and higher frequency SSVEP. The feasibility of proposed method is evaluated in a comparison of monochromatic versus chromatic SSVEP responses. We also present preliminary results with empirical mode decomposition (EMD) adaptive filtering which resulted with improved classification accuracies.