Estimating the Relationship Between EMG Signals and EEG Signal Connections Using Convolutional Neural Networks

Abstract

Discovering the functional connections between human body parts can be beneficial for better control of brain-computer interface (BCI) systems. The brain, as the decision-making organ, controls all body parts to perform activities. In this study, the main objective is to investigate the relation of hand muscles and the effect of each muscle on another using electroencephalogram (EEG) signals. To this end, brain connections are extracted as influential components, and a convolutional network is used to calculate the effect of EEG signals on the connections between hand muscles. The relationships between EEG signal channels are computed using correlation methods, coherence, directed transfer function, Granger causality, and phase delay index. The relationships between electromyogram (EMG) signal channels are also calculated using Granger causality. Signals are recorded in two phases: rest and activity, and ultimately, the EMG signal activity is estimated solely using EEG signals.Simulation results estimate the correlation between the estimated and actual patterns for test data to be around 0.949, indicating a high correlation between the estimated outputs and actual values. According to the researches reviewed, there has been a lack of investigation into the EEG signal graph with muscular Discussions and its correlation with the EMG signal. Given that muscle actions necessitate input from multiple brain regions, it is anticipated that several areas of the brain will be engaged during this process. Therefore, employing graph theory may yield more profound insights into this interaction than traditional approaches, such as analyzing brain connectivity.

Keywords

Vital signal connections, brain-computer interface, regression, convolutional networks