Development of low-cost event marker for EEG-based emotion recognition

Abstract

The study of changes in physiological signals for emotion recognition in human subjects has generated immense interest in medical instrumentation. One of the effective ways of classifying emotions is by the use of the event-related potentials (ERPs) of electroencephalogram (EEG) signals. This requires projection of an image on one computer system while simultaneously putting a marker on another computer system acquiring the EEG. This is achieved using costly modules to synchronize the stimulus presentation system with the data acquisition system. This paper describes an innovative low-cost technique to achieve this simultaneous triggering on the second computer system using the parallel operation of mechanical keyboards. The latency aspect of both USB and PS/2 keyboards with their two keys galvanically connected have been experimentally analysed and compared. It has been found experimentally that the USB keyboards, if used in cognition research, would give better latency results compared with the PS/2 keyboards. The synchronization error between the two USB keyboards has been found to be lower than or equal to 1 ms for the maximum number of keystrokes. The horizon of applications of this technique is unlimited and it can be used in almost every sphere of cognition enhancement and research, where a perfect synchronization of the brain stimulus with the corresponding physiological signals being acquired is required.