EEGForceFusion: Joint Tokenised-Continuous Representation Learning for Subject-Independent Grasp Force Decoding

2026-07-27

AI Summary

This study addresses the challenge of limited cross-subject generalization in EEG-based continuous grip force decoding, which stems from complex temporal dynamics and high inter-individual variability. To overcome this, the authors propose a hybrid decoding framework that integrates continuous and discrete representations. Specifically, the method jointly models continuous neural features extracted by a convolutional-recurrent network and discrete tokenized representations derived through quantization, while leveraging a Transformer architecture to capture long-range temporal dependencies. The entire system is optimized end-to-end within a unified regression framework. Evaluated on the WAY-EEG-GAL dataset, the model achieves an offline R² of 0.817 and a simulated real-time R² of 0.793, demonstrating both low latency and strong cross-subject generalization, thereby offering a promising solution for assistive robotics and neurorehabilitation applications.

Abstract

Brain-machine interfaces provide a link between neural activity and external devices, enabling restoration of motor function and advancing human-machine interaction using non-invasive electroencephalography (EEG). However, continuous grasp force decoding remains challenging due to complex temporal dynamics, high inter-subject variability, and limited generalisation of existing approaches. To address this, we propose a hybrid EEG decoding framework that jointly models continuous and tokenised representations, enabling capture of both fine-grained neural structure and long-range temporal dependencies. The proposed approach integrates convolutional-recurrent representation learning, quantisation-based tokenisation, and transformer-based temporal modelling within a unified fusion-based regression architecture. Experimental evaluation on the WAY-EEG-GAL dataset under strict leave-one-subject-out conditions achieves $R^2$ = 0.817 in offline settings and $R^2$ = 0.793 in simulated real-time evaluation, with latency suitable for real-time deployment. These results demonstrate strong cross-subject generalisation and highlight the practicality of hybrid continuous-tokenised representations for real-time EEG-based force decoding in assistive robotics, neuro-rehabilitation, and human-machine interaction.

Problem

• grasp force decoding
• subject-independent
• EEG
• continuous decoding
• inter-subject variability

Innovation

• hybrid representation learning
• tokenised-continuous fusion
• subject-independent EEG decoding
• transformer-based temporal modeling
• grasp force prediction