PreMovNet: Premovement EEG-Based Hand Kinematics Estimation for Grasp-and-Lift Task

Kinematics decoding from brain activity helps in developing rehabilitation or power-augmenting brain–computer interface (BCI) devices. Low-frequency signals recorded from noninvasive electroencephalography (EEG) are associated with the neural motor correlation utilized for motor trajectory decoding (MTD). In this communication, the ability to decode motor kinematics trajectory from premovement delta-band (0.5–3 Hz) EEG is investigated for the healthy participants. In particular, two deep learning-based neural decoders called PreMovNet-I and PreMovNet-II are proposed that make use of motor-related neural information existing in the premovement EEG data. EEG data segments with various time lags of 150, 200, 250, 300, and 350 ms before the movement onset are utilized for the same. The MTD is presented for grasp-and-lift task (WAY-EEG-GAL dataset) using EEG with the various lags taken as input to the neural decoders. The performance of the proposed decoders is compared with the state-of-the-art multivariable linear regression model. Pearson correlation coefficient and hand trajectory are utilized as performance metric. The results demonstrate the viability of decoding 3-D hand kinematics using premovement EEG data, enabling better control of BCI-based external devices such as exoskeleton/exosuit.