BiCurNet: Pre-Movement EEG based Neural Decoder for Biceps Curl Trajectory Estimation

TL;DR

This paper introduces BiCurNet, a deep learning model that accurately estimates biceps curl trajectories from early EEG signals, enabling improved wearable robot control through efficient and robust brain signal decoding.

Contribution

The study presents a novel lightweight deep learning architecture utilizing EEG features in spherical and harmonics domains for early kinematic parameter estimation.

Findings

Achieved a Pearson correlation coefficient of 0.7 for trajectory estimation.

Demonstrated robustness in both subject-dependent and subject-independent scenarios.

Utilized computationally efficient EEG features in novel domains.

Abstract

Kinematic parameter (KP) estimation from early electroencephalogram (EEG) signals is essential for positive augmentation using wearable robot. However, work related to early estimation of KPs from surface EEG is sparse. In this work, a deep learning-based model, BiCurNet, is presented for early estimation of biceps curl using collected EEG signal. The model utilizes light-weight architecture with depth-wise separable convolution layers and customized attention module. The feasibility of early estimation of KPs is demonstrated using brain source imaging. Computationally efficient EEG features in spherical and head harmonics domain is utilized for the first time for KP prediction. The best Pearson correlation coefficient (PCC) between estimated and actual trajectory of $0.7$ is achieved when combined EEG features (spatial and harmonics domain) in delta band is utilized. Robustness of the proposed network is demonstrated for subject-dependent and subject-independent training, using EEG signals with artifacts.