DCAF-Net: Dual-Channel Attentive Fusion Network for Lower Limb Motion Intention Prediction in Stroke Rehabilitation Exoskeletons

TL;DR

This paper introduces DCAF-Net, a novel deep learning model that combines electromyography and inertial data to accurately predict lower limb movement intentions in stroke rehabilitation, enhancing exoskeleton assistance.

Contribution

The paper presents a dual-channel attention-based neural network that effectively fuses sEMG and IMU data for improved intention prediction in stroke patients.

Findings

Achieved 97.19% accuracy for stroke patients

Achieved 93.56% accuracy for healthy subjects

Demonstrated effectiveness on 11 participants

Abstract

Rehabilitation exoskeletons have shown promising results in promoting recovery for stroke patients. Accurately and timely identifying the motion intentions of patients is a critical challenge in enhancing active participation during lower limb exoskeleton-assisted rehabilitation training. This paper proposes a Dual-Channel Attentive Fusion Network (DCAF-Net) that synergistically integrates pre-movement surface electromyography (sEMG) and inertial measurement unit (IMU) data for lower limb intention prediction in stroke patients. First, a dual-channel adaptive channel attention module is designed to extract discriminative features from 48 time-domain and frequency-domain features derived from bilateral gastrocnemius sEMG signals. Second, an IMU encoder combining convolutional neural network (CNN) and attention-based long short-term memory (attention-LSTM) layers is designed to decode temporal-spatial movement patterns. Third, the sEMG and IMU features are fused through concatenation to enable accurate recognition of motion intention. Extensive experiment on 11 participants (8 stroke subjects and 3 healthy subjects) demonstrate the effectiveness of DCAF-Net. It achieved a prediction accuracies of 97.19% for patients and 93.56% for healthy subjects. This study provides a viable solution for implementing intention-driven human-in-the-loop assistance control in clinical rehabilitation robotics.