LSTM-AE for Domain Shift Quantification in Cross-Day Upper-Limb Motion Estimation Using Surface Electromyography
LSTM-AE for Domain Shift Quantification in Cross-Day Upper-Limb Motion Estimation Using Surface Electromyography
复制标题
DOI：
10.1109/tnsre.2023.3281455
复制
发表时间：
2023-05
影响因子：
4.9
通讯作者：
Tianzhe Bao;Chao Wang;Pengfei Yang;Shengquan Xie;Zhiqiang Zhang;Ping Zhou
中科院分区：
文献类型：
--
作者：
Tianzhe Bao;Chao Wang;Pengfei Yang;Shengquan Xie;Zhiqiang Zhang;Ping Zhou
尽管深度学习技术在上肢肌电控制中已经得到了广泛的研究，但系统在交叉应用中的鲁棒性仍然非常有限。这在很大程度上是由于表面肌电信号的非平稳和时变特性，导致了域移对DL模型的影响。为此，提出了一种基于重构的域移量化方法。这里，选择了一种流行的结合卷积神经网络(CNN)和长短期记忆网络(LSTM)的混合框架，即CNN-LSTM作为主干。提出了将自动编码器(AE)与LSTM配对(简称LSTM-AE)来重建CNN特征。基于LSTM-AE的重建误差(REROR)，可以量化域移对CNN-LSTM的影响。为了进行深入的研究，在手势分类和手腕运动学回归两个方面进行了实验，其中sEMG数据都是在多天内收集的。实验结果表明，当估计精度在日间测试集中显著下降时，REROR相应地增加，并且可能与在日内数据集中得到的结果不同。根据数据分析，CNN-LSTM分类/回归结果与LSTM-AE错误密切相关。平均皮尔逊相关系数分别为-0.986美元、0.014美元和-0.992美元、0.011美元。
Although deep learning (DL) techniques have been extensively researched in upper-limb myoelectric control, system robustness in cross-day applications is still very limited. This is largely caused by non-stable and time-varying properties of surface electromyography (sEMG) signals, resulting in domain shift impacts on DL models. To this end, a reconstruction-based method is proposed for domain shift quantification. Herein, a prevalent hybrid framework that combines a convolutional neural network (CNN) and a long short-term memory network (LSTM), i.e. CNN-LSTM, is selected as the backbone. The paring of auto-encoder (AE) and LSTM, abbreviated as LSTM-AE, is proposed to reconstruct CNN features. Based on reconstruction errors (RErrors) of LSTM-AE, domain shift impacts on CNN-LSTM can be quantified. For a thorough investigation, experiments were conducted in both hand gesture classification and wrist kinematics regression, where sEMG data were both collected in multi-days. Experiment results illustrate that, when the estimation accuracy degrades substantially in between-day testing sets, RErrors increase accordingly and can be distinct from those obtained in within-day datasets. According to data analysis, CNN-LSTM classification/regression outcomes are strongly associated with LSTM-AE errors. The average Pearson correlation coefficients could reach $-0.986\,\,\pm $ 0.014 and $-0.992\,\,\pm $ 0.011, respectively.