Bispectrum Analysis of Noninvasive EEG Signals Discriminates Complex and Natural Grasp Types

TL;DR

This study demonstrates that bispectrum analysis of EEG signals can effectively distinguish complex and natural grasp types, achieving high classification accuracy and revealing neural activity related to different movements.

Contribution

The paper introduces the use of bispectrum analysis combined with classifiers to decode complex grasp movements from EEG data, a novel approach in neural signal analysis.

Findings

Achieved 97% accuracy in binary classification of power grasp.

Attained 94.93% accuracy in multiclass grasp classification.

Bispectrum effectively captures phase information for movement differentiation.

Abstract

The bispectrum stands out as a revolutionary tool in frequency domain analysis, leaping the usual power spectrum by capturing crucial phase information between frequency components. In our innovative study, we have utilized the bispectrum to analyze and decode complex grasping movements, gathering EEG data from five human subjects. We put this data through its paces with three classifiers, focusing on both magnitude and phase-related features. The results highlight the bispectrum's incredible ability to delve into neural activity and differentiate between various grasping motions with the Support Vector Machine (SVM) classifier emerging as a standout performer. In binary classification, it achieved a remarkable 97\% accuracy in identifying power grasp, and in the more complex multiclass tasks, it maintained an impressive 94.93\% accuracy. This finding not only underscores the bispectrum's analytical strength but also showcases the SVM's exceptional capability in classification, opening new doors in our understanding of movement and neural dynamics.