Classification of sensorimotor cortex signals based on the task durations: an fNIRS-BCI study

Abstract

To date, several studies have utilized brain stimulation to evoke particular brain activity. One of the most critical questions that remain unaddressed is how long the stimulation should last. To address this issue, this paper investigates two different stimulation durations for braincomputer interface (BCI) with functional near-infrared spectroscopy (fNIRS). To do so, this paper investigates the influence of the stimulation duration on the hemodynamic response (HR) signal in the sensorimotor cortex of the human brain. fNIRS is used for the measurement of HRs. For brain stimulation, right-hand index finger tapping and poking tasks are utilized, and the HR signals are acquired. Two different stimulation durations, i.e., 10 and 15 secs, were utilized in this study, and a total of 5 subjects participated in the experiment. After acquiring the signals, signals are filtered, leading to classification. From the study results, it is concluded that the classification accuracy does not increase with the increase in the stimulation duration among the tested stimulation durations. So, the use of longer stimulation durations, i.e., 15 secs, can't serve the purpose well and make the subjects tired. In contrast, 10-sec stimulation yielded a higher classification accuracy in a comparatively shorter time, which is the BCI's core objective.