An integrated EEG-fNIRS-based Vector-Phase Analysis for early hemodynamic response: Applications to BCI

Abstract

Objective. In this thesis, a novel methodology for better hemodynamic response detection, has been developed using multimodal brain-computer interface (BCI). Methodology Used. A novel classifier has been developed for achieving better classification accuracy using two modalities. An integrated EEG-fNIRS based Vector phase analysis (VPA) has been conducted. An online available dataset assembled at the Technische Universität Berlin; comprising of simultaneous fNIRS and EEG signals of 26 physically and mentally fit persons during n-back tasks has been used for this research. Instrumental and physiological noise removal has been done using preprocessing techniques followed by detection of activity in both modalities individually. VPA, with resting state threshold circle, is used for detection of hemodynamic response in functional near-infrared spectroscopy (fNIRS) data whereas phase plots for electroencephalography (EEG) signals have been constructed using Hilbert Transform to detect the activity in each trial. Multiple threshold circles are drawn in the vector plane, where each circle is drawn after task completion in each trial of EEG signal. Finally, both processes are integrated in one vector phase plot to get combined detection of hemodynamic response for activity. Main Results. Results of this study illustrates that the combined EEG-fNIRS VPA yields considerably higher average classification accuracy, that is 91.35%, as compared to other techniques that are Convolutional neural network (CNN), Support vector machine(SVM) and VPA (with dual threshold circles) with classification accuracies 89%, 82% and 86% respectively. Significance. Outcomes of this research demonstrate that improved classification performance can be feasibly achieved using multimodal VPA for EEG-fNIRS hybrid data.