A CNN-LSTM model for six human ankle movements classification on different loads.
A CNN-LSTM model for six human ankle movements classification on different loads.
复制标题
DOI：
10.3389/fnhum.2023.1101938
复制
发表时间：
2023
影响因子：
2.9
通讯作者：
中科院分区：
文献类型：
--
作者：
本研究旨在解决目前研究中存在的三个问题：(1)为了提供更好的训练，只能识别最多4个踝关节运动，而需要对6个踝关节运动进行分类；(2)直接将原始的表面肌电信号输入神经网络会导致较高的计算代价；(3)负荷变化对分类精度有很大影响。为此，提出了卷积神经网络(CNN)-长短期记忆(LSTM)模型、表面肌电信号的时域特征选择方法和两步法。首次将Boruta算法用于表面肌电信号的时域特征提取。选择的特征而不是原始的表面肌电信号被馈送到CNN-LSTM模型中。因此，模型的参数数量从331,938个减少到155,042个，减半。通过实验验证了该方法的有效性。结果表明，该方法能够较好地对六种踝关节动作进行分类，准确率为95.73%。以表面肌电信号为输入的CNN-LSTM、CNN和LSTM模型的准确率均高于以原始表面肌电信号为输入的相应模型。采用两步法识别不同负荷下的踝关节运动，总体准确率从73.23%提高到93.50%。与CNN、LSTM和支持向量机相比，我们提出的CNN-LSTM模型对踝关节运动的分类准确率最高。
This study aims to address three problems in current studies in decoding the ankle movement intention for robot-assisted bilateral rehabilitation using surface electromyogram (sEMG) signals: (1) only up to four ankle movements could be identified while six ankle movements should be classified to provide better training; (2) feeding the raw sEMG signals directly into the neural network leads to high computational cost; and (3) load variation has large influence on classification accuracy. To achieve this, a convolutional neural network (CNN)—long short-term memory (LSTM) model, a time-domain feature selection method of the sEMG, and a two-step method are proposed. For the first time, the Boruta algorithm is used to select time-domain features of sEMG. The selected features, rather than raw sEMG signals are fed into the CNN-LSTM model. Hence, the number of model’s parameters is reduced from 331,938 to 155,042, by half. Experiments are conducted to validate the proposed method. The results show that our method could classify six ankle movements with relatively good accuracy (95.73%). The accuracy of CNN-LSTM, CNN, and LSTM models with sEMG features as input are all higher than that of corresponding models with raw sEMG as input. The overall accuracy is improved from 73.23% to 93.50% using our two-step method for identifying the ankle movements with different loads. Our proposed CNN-LSTM model have the highest accuracy for ankle movements classification compared with CNN, LSTM, and Support Vector Machine (SVM).
登录
查看更多内容
DOI：
10.3389/fneng.2014.00030
发表时间：
2014
期刊：
Frontiers in neuroengineering
影响因子：
--
作者：
Ang KK;Guan C;Phua KS;Wang C;Zhou L;Tang KY;Ephraim Joseph GJ;Kuah CW;Chua KS
通讯作者：
Chua KS
影响因子：
8.1
作者：
Chen, Rung-Ching;Dewi, Christine;Caraka, Rezzy Eko
通讯作者：
Caraka, Rezzy Eko
影响因子：
6.4
作者：
Jamwal, Prashant K.;Xie, Sheng Q.;Parsons, John G.
通讯作者：
Parsons, John G.
通过深度循环神经网络进行实时预期膝关节运动预测
影响因子：
4.3
作者：
Huang, Yongchuang;He, Zexia;Liu, Tao
通讯作者：
Liu, Tao
影响因子：
5.8
作者：
Kursa, Miron B.;Rudnicki, Witold R.
通讯作者：
Rudnicki, Witold R.