Luo Mingxiang, Yin Meng, Li Jinke, Li Ying, Kobsiriphat Worawarit, Yu Hongliu, Xu Tiantian, Wu Xinyu, Cao Wujing
Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
Department of Mechanical and Electrical Engineering, Shenzhen Polytechnic University, Shenzhen, China.
Cyborg Bionic Syst. 2025 May 1;6:0250. doi: 10.34133/cbsystems.0250. eCollection 2025.
Lateral walking exercise is beneficial for the hip abductor enhancement. Accurate gait recognition and continuous hip joint angle prediction are essential for the control of exoskeletons. We propose a dual-task learning framework, the "Twin Brother" model, which fuses convolutional neural network (CNN), long short-term memory (LSTM), neural networks (NNs), and the squeezing-elicited attention mechanism to classify the lateral gait stage and estimate the hip angle from electromyography (EMG) signals. The EMG signals of 6 muscles from 10 subjects during lateral walking were collected. Four gait phases were recognized, and the hip angles of both legs were continuously estimated. The sliding window length of 250 ms and the sliding increment of 3 ms were determined by the requirements of response time and recognition accuracy of the real-time system. We compared the performance of CNN-LSTM, CNN, LSTM, support vector machine, NN, K-nearest neighbor, and the "Twin Brother" models. The "Twin Brother" model achieved a recognition accuracy (mean ± SD) of 98.81% ± 0.14%. The model's predicted root mean square error (RMSE) for the left and right hip angles are 0.9183° ± 0.024° and 1.0511° ± 0.027°, respectively, where the are 0.9853 ± 0.006 and 0.9808 ± 0.008. The accuracy of recognition and estimation are both better than comparative models. For gait phase percentage prediction, RMSE and predicted by the model can reach 0.152° ± 0.014° and 0.986 ± 0.011, respectively. These results demonstrate that the method can be applied to lateral walking gait recognition and hip joint angle prediction.
横向行走运动有助于增强髋外展肌。准确的步态识别和连续的髋关节角度预测对于外骨骼的控制至关重要。我们提出了一种双任务学习框架，即“孪生兄弟”模型，该模型融合了卷积神经网络（CNN）、长短期记忆网络（LSTM）、神经网络（NN）和挤压激发注意力机制，用于对横向步态阶段进行分类，并从肌电图（EMG）信号中估计髋关节角度。收集了10名受试者在横向行走过程中6块肌肉的EMG信号。识别出四个步态阶段，并连续估计双腿的髋关节角度。根据实时系统的响应时间和识别精度要求，确定了250 ms的滑动窗口长度和3 ms的滑动增量。我们比较了CNN-LSTM、CNN、LSTM、支持向量机、NN、K近邻和“孪生兄弟”模型的性能。“孪生兄弟”模型的识别准确率（均值±标准差）达到了98.81%±0.14%。该模型对左右髋关节角度的预测均方根误差（RMSE）分别为0.9183°±0.024°和1.0511°±0.027°，其中相关系数分别为0.9853±0.006和0.9808±0.008。识别和估计的准确率均优于对比模型。对于步态阶段百分比预测，该模型预测的RMSE和相关系数分别可达0.152°±0.014°和0.986±0.011。这些结果表明，该方法可应用于横向行走步态识别和髋关节角度预测。
