An Extended Spatial Transformer Convolutional Neural Network for Gesture Recognition and Self-Calibration Based on Sparse sEMG Electrodes

Chen, Wei; Feng, Lihui; Lu, Jihua; Wu, Bing-Fei

doi:10.1109/tbcas.2022.3222196

Cited by 8 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…External influences, such as muscle fatigue, electrode displacement, and the impact of arm posture, can easily affect the features of sEMG ( Hill et al, 2016 ; Kusche and Ryschka, 2019 ). Chen et al (2022) proposed an extended spatial transformer convolutional neural network (EST-CNN) model, which automatically learns electrode displacement relationships through feature enhancement preprocessing and spatial transformation layers, further micro-adjusts rotation angles through tuning layers, can simultaneously achieve gesture recognition and autonomous motion calibration, and effectively improve recognition accuracy under electrode movement. Especially, sEMG signals have user-specific characteristics, resulting in large differences in amplitude and frequency between subjects even when collected from the same position with the same movement ( De Luca, 2002 ).…”

Section: Introductionmentioning

confidence: 99%

A rotary transformer cross-subject model for continuous estimation of finger joints kinematics and a transfer learning approach for new subjects

Lin,

2024

Front. Neurosci.

View full text Add to dashboard Cite

IntroductionSurface Electromyographic (sEMG) signals are widely utilized for estimating finger kinematics continuously in human-machine interfaces (HMI), and deep learning approaches are crucial in constructing the models. At present, most models are extracted on specific subjects and do not have cross-subject generalizability. Considering the erratic nature of sEMG signals, a model trained on a specific subject cannot be directly applied to other subjects. Therefore, in this study, we proposed a cross-subject model based on the Rotary Transformer (RoFormer) to extract features of multiple subjects for continuous estimation kinematics and extend it to new subjects by adversarial transfer learning (ATL) approach.MethodsWe utilized the new subject’s training data and an ATL approach to calibrate the cross-subject model. To improve the performance of the classic transformer network, we compare the impact of different position embeddings on model performance, including learnable absolute position embedding, Sinusoidal absolute position embedding, and Rotary Position Embedding (RoPE), and eventually selected RoPE. We conducted experiments on 10 randomly selected subjects from the NinaproDB2 dataset, using Pearson correlation coefficient (CC), normalized root mean square error (NRMSE), and coefficient of determination (R2) as performance metrics.ResultsThe proposed model was compared with four other models including LSTM, TCN, Transformer, and CNN-Attention. The results demonstrated that both in cross-subject and subject-specific cases the performance of RoFormer was significantly better than the other four models. Additionally, the ATL approach improves the generalization performance of the cross-subject model better than the fine-tuning (FT) transfer learning approach.DiscussionThe findings indicate that the proposed RoFormer-based method with an ATL approach has the potential for practical applications in robot hand control and other HMI settings. The model’s superior performance suggests its suitability for continuous estimation of finger kinematics across different subjects, addressing the limitations of subject-specific models.

show abstract

Section: Introductionmentioning

confidence: 99%