Three class classification of fNIRS signals for the detection of RGB color stimuli in the visual cortex

In this study, we have used functional near-infrared spectroscopy (fNIRS) to measure the hemodynamic response in the visual cortex. We concurrently measure and discriminate the fNIRS signals evoked by three different color stimuli: red, green, and blue (RGB) colors. Seven healthy subjects were asked to perform the RGB color stimuli experiment during a 10 s task and 25 s rest period. Using a continuous-wave fNIRS system, brain signals were acquired concurrently from the visual cortex. Multiclass linear discriminant analysis was utilized to classify RGB stimuli, which resulted in an average classification accuracy of 66.67% across the 7 subjects. A 3~8 s time window during a 10 s task period provided the best result in classification.