Continuous motion finger joint angle estimation utilizing hybrid sEMG-FMG modality driven transformer-based deep learning model

Chen, Zhouping; Wang, Hong; Chen, Haonan; Tao, Wei

doi:10.1016/j.bspc.2023.105030

Cited by 6 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, HD-sEMG exhibits inherent advantages over sEMG in extracting MU features and predictive performance. Regarding multi-sensor fusion, as discussed in studies [21], [55], [79], [114], [140], [151], [160], integrating sEMG sensors with EEG, IMU, FMG, and MMG sensors can further enhance the performance and robustness, especially in scenarios of isometric contractions and under external force interference.…”

Section: A Significant Findings 1) Advantages Of Hd-semg Sensors and ...mentioning

confidence: 99%

Continuous Motion Intention Prediction Using sEMG for Upper-Limb Rehabilitation: A Systematic Review of Model-Based and Model-Free Approaches

Wei,

Zhang,

Xie

2024

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Upper limb functional impairments persisting after stroke significantly affect patients' quality of life. Precise adjustment of robotic assistance levels based on patients' motion intention using sEMG signals is crucial for active rehabilitation. This paper systematically reviews studies over the past decade on continuous prediction of upper limb single joint and multi-joint combinations motion intention using Model-Based (MB) and Model-Free (MF) approaches, based on 186 relevant studies screened from six major electronic databases. The findings indicate ongoing challenges in terms of subject composition, algorithm robustness and generalization, and feasibility for practical applications. Moreover, it suggests integrating the strengths of both MB and MF approaches to improve existing algorithms. Therefore, future research should further explore personalized MB-MF combination methods incorporating deep learning, attention mechanisms, muscle synergy features, motor unit features, and closed-loop feedback to achieve precise, real-time, and long-duration prediction of multi-joint complex movements, while further refining the transfer learning strategy for rapid algorithm deployment across days and subjects. In summary, this review summarizes the current state and challenges of research, aiming to provide inspiration for future research on predicting upper limb motion intention based on sEMG.

show abstract

Section: A Significant Findings 1) Advantages Of Hd-semg Sensors and ...mentioning

confidence: 99%

Continuous Motion Intention Prediction Using sEMG for Upper-Limb Rehabilitation: A Systematic Review of Model-Based and Model-Free Approaches

Wei,

Zhang,

Xie

2024

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

“…Bai et al (2021) employed long short term memory networks (LSTM) (Hochreiter and Schmidhuber, 1997) and CNN models to recognize sEMG signals through a multimodal approach in combination with EMG imagery. Guo et al (2021) proposed a long exposure mechanism for training a convolutional LSTM neural network to predict 10 joint angles with an average PCC accuracy of 0.82 Chen et al (2023) used a decoding scheme that combined two different modalities of information, surface electromyography and force electromyography, and achieved higher accuracy than using a single modality of information.…”

Section: Introductionmentioning

confidence: 99%

Fusion inception and transformer network for continuous estimation of finger kinematics from surface electromyography

Lin,

Zhang

2024

Front. Neurorobot.

View full text Add to dashboard Cite

Decoding surface electromyography (sEMG) to recognize human movement intentions enables us to achieve stable, natural and consistent control in the field of human computer interaction (HCI). In this paper, we present a novel deep learning (DL) model, named fusion inception and transformer network (FIT), which effectively models both local and global information on sequence data by fully leveraging the capabilities of Inception and Transformer networks. In the publicly available Ninapro dataset, we selected surface EMG signals from six typical hand grasping maneuvers in 10 subjects for predicting the values of the 10 most important joint angles in the hand. Our model’s performance, assessed through Pearson’s correlation coefficient (PCC), root mean square error (RMSE), and R-squared (R2) metrics, was compared with temporal convolutional network (TCN), long short-term memory network (LSTM), and bidirectional encoder representation from transformers model (BERT). Additionally, we also calculate the training time and the inference time of the models. The results show that FIT is the most performant, with excellent estimation accuracy and low computational cost. Our model contributes to the development of HCI technology and has significant practical value.

show abstract

A Dual‐Mode, Scalable, Machine‐Learning‐Enhanced Wearable Sensing System for Synergetic Muscular Activity Monitoring

Wang,

Jiang,

et al. 2024

Adv Materials Technologies

View full text Add to dashboard Cite

Simultaneously detecting muscular deformation and biopotential signals provides comprehensive insights of the muscle activity. However, the substantial size and weight of detecting equipment result in reduced wearer benefits and comfort. It remains a challenge to establish a flexible and lightweight wearable system for mapping muscular morphological parameters while collecting biopotentials. Herein, a fully integrated dual‐mode wearable system for monitoring lower‐extremity muscular activity is introduced. The system utilizes an iontronic pressure sensing matrix (16 channels) for precise mapping of force myography (FMG) within a single muscle, while simultaneously capturing the muscular electrophysiological signals using a self‐customized electromyography (EMG) sensing module. Experimental results show that the bimodal sensing system is capable of capturing complementary and comprehensive aspects of muscular activity, which reflect activation and architectural changes of the muscle. By leveraging machine learning techniques, the integrated system significantly (p < 0.05) enhances the average gait phase recognition accuracy to 96.35%, and reduces the average ankle joint angle estimation error to 1.44°. This work establishes a foundation for lightweight and bimodal muscular sensing front‐ends, which is promising in applications of human–machine interfaces and wearable robotics.

show abstract

Continuous motion finger joint angle estimation utilizing hybrid sEMG-FMG modality driven transformer-based deep learning model

Cited by 6 publications

References 36 publications

Continuous Motion Intention Prediction Using sEMG for Upper-Limb Rehabilitation: A Systematic Review of Model-Based and Model-Free Approaches

Continuous Motion Intention Prediction Using sEMG for Upper-Limb Rehabilitation: A Systematic Review of Model-Based and Model-Free Approaches

Fusion inception and transformer network for continuous estimation of finger kinematics from surface electromyography

A Dual‐Mode, Scalable, Machine‐Learning‐Enhanced Wearable Sensing System for Synergetic Muscular Activity Monitoring

Contact Info

Product

Resources

About