School of Mechanical and Aerospace Engineering, Jilin University, Changchun 130025, China.
Sensors (Basel). 2023 Jun 26;23(13):5905. doi: 10.3390/s23135905.
Gait phase recognition is of great importance in the development of rehabilitation devices. The advantages of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) are combined (LSTM-CNN) in this paper, then a gait phase recognition method based on LSTM-CNN neural network model is proposed. In the LSTM-CNN model, the LSTM layer is used to process temporal sequences and the CNN layer is used to extract features A wireless sensor system including six inertial measurement units (IMU) fixed on the six positions of the lower limbs was developed. The difference in the gait recognition performance of the LSTM-CNN model was estimated using different groups of input data collected by seven different IMU grouping methods. Four phases in a complete gait were considered in this paper including the supporting phase with the right hill strike (SU-RHS), left leg swimming phase (SW-L), the supporting phase with the left hill strike (SU-LHS), and right leg swimming phase (SW-R). The results show that the best performance of the model in gait recognition appeared based on the group of data from all the six IMUs, with the recognition precision and macro-F1 unto 95.03% and 95.29%, respectively. At the same time, the best phase recognition accuracy for SU-RHS and SW-R appeared and up to 96.49% and 95.64%, respectively. The results also showed the best phase recognition accuracy (97.22%) for SW-L was acquired based on the group of data from four IMUs located at the left and right thighs and shanks. Comparably, the best phase recognition accuracy (97.86%) for SU-LHS was acquired based on the group of data from four IMUs located at left and right shanks and feet. Ulteriorly, a novel gait recognition method based on Data Pre-Filtering Long Short-Term Memory and Convolutional Neural Network (DPF-LSTM-CNN) model was proposed and its performance for gait phase recognition was evaluated. The experiment results showed that the recognition accuracy reached 97.21%, which was the highest compared to Deep convolutional neural networks (DCNN) and CNN-LSTM.
步态相位识别在康复设备的发展中具有重要意义。本文将长短时记忆 (LSTM) 和卷积神经网络 (CNN) 的优势相结合（LSTM-CNN），提出了一种基于 LSTM-CNN 神经网络模型的步态相位识别方法。在 LSTM-CNN 模型中，使用 LSTM 层处理时间序列，使用 CNN 层提取特征。开发了一个包括六个惯性测量单元 (IMU) 的无线传感器系统，这些 IMU 固定在下肢的六个位置上。通过使用七种不同的 IMU 分组方法采集的不同组输入数据来估计 LSTM-CNN 模型的步态识别性能差异。本文考虑了一个完整步态的四个阶段，包括右侧足趾触地的支撑阶段 (SU-RHS)、左腿游泳阶段 (SW-L)、左侧足趾触地的支撑阶段 (SU-LHS) 和右腿游泳阶段 (SW-R)。结果表明，模型在步态识别方面的最佳性能出现在基于来自所有六个 IMU 的数据组，识别精度和宏观 F1 分别达到 95.03%和 95.29%。同时，SU-RHS 和 SW-R 的最佳相位识别精度分别达到 96.49%和 95.64%。结果还表明，基于位于左大腿和小腿及右大腿和小腿的四个 IMU 的数据组，SW-L 的最佳相位识别精度（97.22%）。相比之下，基于位于左小腿和脚以及右小腿和脚的四个 IMU 的数据组，SU-LHS 的最佳相位识别精度（97.86%）。此外，提出了一种基于数据预滤波长短时记忆和卷积神经网络（DPF-LSTM-CNN）模型的新型步态识别方法，并对其步态相位识别性能进行了评估。实验结果表明，与深度卷积神经网络 (DCNN) 和 CNN-LSTM 相比，识别精度达到 97.21%，是最高的。
Sensors (Basel). 2023-6-26
Sensors (Basel). 2023-1-11
Biosensors (Basel). 2020-8-27
Sensors (Basel). 2020-3-10
Int J Environ Res Public Health. 2020-8-5
Sensors (Basel). 2021-4-19
IEEE Trans Neural Syst Rehabil Eng. 2025
Sensors (Basel). 2024-4-13
Sensors (Basel). 2021-1-25
Biosensors (Basel). 2020-8-27
Front Neurorobot. 2019-7-24
J Orthop Translat. 2015-10-17
Zotero 插件
