LSTM-AE for Domain Shift Quantification in Cross-Day Upper-Limb Motion Estimation Using Surface Electromyography

• Main Authors: Tianzhe Bao (Author), Chao Wang (Author), Pengfei Yang (Author), Sheng Quan Xie (Author), Zhi-Qiang Zhang (Author), Ping Zhou (Author)
• Format: Book
• Published: IEEE, 2023-01-01T00:00:00Z.
• Subjects: article
• Online Access: Connect to this object online.

Summary

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 <inline-formula> <tex-math notation="LaTeX">$-0.986\,\,\pm $ </tex-math></inline-formula> 0.014 and <inline-formula> <tex-math notation="LaTeX">$-0.992\,\,\pm $ </tex-math></inline-formula> 0.011, respectively.

Item Description

1558-0210
10.1109/TNSRE.2023.3281455