Continuous Decoding of Hand Movement From EEG Signals Using Phase-Based Connectivity Features

Abstract

The principal goal of the brain-computer interface (BCI) is to translate brain signals into meaningful commands to control external devices or neuroprostheses to restore lost functions of patients with severe motor disabilities. The invasive recording of brain signals involves numerous health issues. Therefore, BCIs based on non-invasive recording modalities such as electroencephalography (EEG) are safer and more comfortable for the patients. The BCI requires reconstructing continuous movement parameters such as position or velocity for practical application of neuroprostheses. The BCI studies in continuous decoding have extensively relied on extracting features from the amplitude of brain signals, whereas the brain connectivity features have rarely been explored. This study aims to investigate the feasibility of using phase-based connectivity features in decoding continuous hand movements from EEG signals. To this end, the EEG data were collected from seven healthy subjects performing a 2D center-out hand movement task in four orthogonal directions. The phase-locking value (PLV) and magnitude-squared coherence (MSC) are exploited as connectivity features along with multiple linear regression (MLR) for decoding hand positions. A brute-force search approach is employed to find the best channel pairs for extracting features related to hand movements. The results reveal that the regression models based on PLV and MSC features achieve the average Pearson correlations of 0.43 ± 0.03 and 0.42 ± 0.06, respectively, between predicted and actual trajectories over all subjects. The delta and alpha band features have the most contribution in regression analysis. The results also demonstrate that both PLV and MSC decoding models lead to superior results on our data compared to two recently proposed feature extraction methods solely based on the amplitude or phase of recording signals (p < 0.05). This study verifies the ability of PLV and MSC features in the continuous decoding of hand movements with linear regression. Thus, our findings suggest that extracting features based on brain connectivity can improve the accuracy of trajectory decoder BCIs.

Applying Common Spatial Pattern and Convolutional Neural Network to Classify Movements via EEG Signals

“…They suggested that the timing of hemodynamic responses to both tasks in this region was very similar. Several articles have classified MI tasks or ME tasks 46 ; however, some of them have compared the performance of both tasks. 47 Shuqfa et al 48 investigated the classification of four-class bilateral and unilateral MI and ME tasks of 109 subjects.…”

The Easy and Versatile Neural Recording Platform (T-REX): Design and Development Study

“…For a movement experiment [19][20][21][22][23], the streams recorded could be the neural amplifier and experimental triggers. Additionally, a movement tracker [24][25][26] or a force sensor [27] could be added. For speech perception [28][29][30] or auditory perception [31,32], the audio stream, experiment triggers, and neural data need to be recorded.…”

Interhemispheric neural characteristics of noxious mechano-nociceptive stimulation in the anterior cingulate cortex

“…To evaluate the synchronization between two hemispheres, the connectivity measure of phase locking value (PLV) was exploited (Bastos and Schoffelen, 2016;Hosseini and Shalchyan, 2022). The mathematical calculation of PLV is described as follows.…”