Enhancing Interpretability of AR-SSVEP-Based Motor Intention Recognition via CNN-BiLSTM and SHAP Analysis on EEG Data

TL;DR

This paper introduces an augmented reality BCI system using CNN-BiLSTM with attention and SHAP analysis to improve motor intention recognition from EEG data, aiming to enhance rehabilitation for motor-impaired patients.

Contribution

It develops a novel AR-SSVEP system with an advanced neural network architecture and interpretability analysis, improving real-time motor intention recognition in BCI applications.

Findings

Enhanced recognition accuracy with the MACNN-BiLSTM model

Improved interpretability of EEG features via SHAP analysis

Potential for real-time application in motor rehabilitation

Abstract

Patients with motor dysfunction show low subjective engagement in rehabilitation training. Traditional SSVEP-based brain-computer interface (BCI) systems rely heavily on external visual stimulus equipment, limiting their practicality in real-world settings. This study proposes an augmented reality steady-state visually evoked potential (AR-SSVEP) system to address the lack of patient initiative and the high workload on therapists. Firstly, we design four HoloLens 2-based EEG classes and collect EEG data from seven healthy subjects for analysis. Secondly, we build upon the conventional CNN-BiLSTM architecture by integrating a multi-head attention mechanism (MACNN-BiLSTM). We extract ten temporal-spectral EEG features and feed them into a CNN to learn high-level representations. Then, we use BiLSTM to model sequential dependencies and apply a multi-head attention mechanism to highlight motor-intention-related patterns. Finally, the SHAP (SHapley Additive exPlanations) method is applied to visualize EEG feature contributions to the neural network's decision-making process, enhancing the model's interpretability. These findings enhance real-time motor intention recognition and support recovery in patients with motor impairments.