Journal
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
Volume 31, Issue -, Pages 2570-2580Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNSRE.2023.3281455
Keywords
sEMG; deep learning; long short-term memory network; auto-encoder; domain shift quantification
Categories
Ask authors/readers for more resources
Although DL techniques have been extensively researched in upper-limb myoelectric control, the robustness of cross-day applications is limited due to non-stable and time-varying properties of sEMG signals. To address this, a reconstruction-based method is proposed for domain shift quantification using a hybrid framework of CNN-LSTM. Experiments show that the estimation accuracy degrades substantially in between-day testing sets, and the RErrors of LSTM-AE can quantify the domain shift impacts on CNN-LSTM.
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 +/- 0.014 and -0.992 +/- 0.011, respectively.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available