Single-Trial NIRS Data Classification for Brain–Computer Interfaces Using Graph Signal Processing

Near-infrared spectroscopy (NIRS)-based brain-computer interface (BCI) systems use feature extraction methods relying mainly on the slope characteristics and mean changes of the hemodynamic responses in respect to certain mental tasks. Nevertheless, spatial patterns across the measurement channels have been detected and should be considered during the feature vector extraction stage of the BCI realization. In this paper, a graph signal processing (GSP) approach for feature extraction is adopted in order to capture the aforementioned spatial information of the NIRS signals. The proposed GSP-based methodology for feature extraction in NIRS-based BCI systems, namely graph NIRS (GNIRS), is applied on a publicly available dataset of NIRS recordings during a mental arithmetic task. GNIRS exhibits higher classification rates (CRs), up to 92.52%, as compared to the CRs of two state-of-the-art feature extraction methodologies related to slope and mean values of hemodynamic response, i.e., 90.35% and 82.60%, respectively. In addition, GNIRS leads to the formation of feature vectors with reduced dimensionality in comparison with the baseline approaches. Moreover, it is shown to facilitate high CRs even from the first second after the onset of the mental task, paving the way for faster NIRS-based BCI systems.

I. Introduction

Brain-Computer Interfaces (BCI) have received increased attention the last two decades as alternative means of communication and rehabilitation of people with motor impairments [1]–[4]. A typical BCI system enables a human to interact with surroundings without the involvement of peripheral nervous system or muscles, using only the activity of the brain. A variety of signal processing and classification methods have been developed to translate brain activity to control-commands to move a screen cursor, to manage neuroprosthetics, or to engage in a neurohabilitation infrastructure [5]–[10].