Estimation of Joint Angle From sEMG and Inertial Measurements Based on Deep Learning Approach

Delgado, Alfredo Lobaina; Rocha, Adson Ferreira da; León, Alexander Suárez; Ruiz-Olaya, Andres F.; Montero, Klaus Ribeiro; Delis, Alberto López

doi:10.1109/embc46164.2021.9630609

Cited by 5 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although previous studies have confirmed that end-to-end deep learning models can extract representative features from sEMG signals [40][41][42], after all, deep learning models are like a black box with poor interpretability. In our experiment, we therefore first manually selected a large number of features, filtered them through EFS, and then fed them into a deep learning model for training.…”

Section: Discussionmentioning

confidence: 94%

Continuous Estimation of Human Knee Joint Angles by Fusing Kinematic and Myoelectric Signals

Sun

Cao

Chen

et al. 2022

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Exoskeleton robot is an essential tool in active rehabilitation training for patients with lower limb motor dysfunctions. Accurate and real-time recognition in human motion intention is a great challenge in exoskeleton robot, which can be implemented by continues estimation of human joint angles. In this study, we innovatively proposed a novel feature-based convolutional neural network-bidirectional long-short term memory network (CNN-BiLSTM) model to predict the knee joint angles more accurately and in real time. We validated our method on a public dataset, including surface electromyography(sEMG) and inertial measurement unit (IMU) data of 10 healthy subjects during normal walking. Initially, features extraction from each modal data achieved feature-level fusion. Then the importance of each sEMG and IMU signal feature for knee joint angle prediction was quantified by ensemble feature scorer (EFS) and the number of features required for prediction while ensuring accuracy was simplified by profile likelihood maximization (PLM) algorithm. Finally, the CNN-BiLSTM model was created by using the determined simplest features to further fuse the spatio-temporal correlation of signals. The results indicated that the EFS and PLM algorithm could remove the feature redundancy perfectly and estimation performance would become better when bi-modal gait data were fused. For the estimation performance, the average root mean square error (RMSE), adjusted R 2 and pearson correlation coefficient (CC) of our algorithm were 4.07, 0.95, and 0.98, respectively, which was better than CNN 、 BiLSTM and other three traditional machine learning methods. In addition, the model test time was 62.47 ± 0.29 ms, which was less than the predicted horizon of 100 ms. The real-time performance and accuracy are satisfactory. Compared with previous works, our method has great advantages in feature selection and model design, which further improves the prediction accuracy. These promising results demonstrate that the proposed method has considerable potential to be applied to exoskeleton robot control.

show abstract

Section: Discussionmentioning

confidence: 94%

Continuous Estimation of Human Knee Joint Angles by Fusing Kinematic and Myoelectric Signals

Sun

Cao

Chen

et al. 2022

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

“…The RNNs encompass NARX [135], LSTM [13], [131], [132], [136]- [139], and GRU [131], [132]. The hybrid category includes CNN-LSTM [140], Long Exposure Convolutional Memory Network (LE-ConvMN) [141], and Attention-ConvGRU [142].…”

Section: D) Deep Learningmentioning

confidence: 99%

“…CNN-RNN Hybrids: [140]'s CNN-LSTM combines the advantages of CNN and RNN, and similar to [30], it can employ transfer learning by merely retraining the fully connected layer. To address LSTM's drawback of flattening multi-dimensional inputs into 1D vectors, which leads to spatial information loss when processing spatiotemporal data, [141]'s LE-ConvMN replaces the LSTM's fully connected layer with the 2D-CNN.…”

Section: D) Deep Learningmentioning

confidence: 99%

“…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%

“…Moreover, RNNbased models like LSTM [98] and Bi-LSTM [179] can improve robustness to load and movement speed variations as well as multi-joint simultaneous prediction accuracy through long-term contextual dependencies. Therefore, combining CNN and RNN strengths to extract spatiotemporal information simultaneously, such as CNN-LSTM [80], [140] and LE-ConvMN [141], can outperform the methods using only CNNs and RNNs. As for the attention mechanisms, studies [11], [62], [177] using GFWSVM, LightGBM, and SE-Net have already proven the significance of adjusting key feature weight distributions.…”

Section: ) Closed-loop Feedbackmentioning

confidence: 99%

See 2 more Smart Citations

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

Characterizations on Knee Movement Estimation from Surface EMG Using Composited Approaches

Guan

2023

J. Electr. Eng. Technol.

View full text Add to dashboard Cite

Estimation of Joint Angle From sEMG and Inertial Measurements Based on Deep Learning Approach

Cited by 5 publications

References 16 publications

Continuous Estimation of Human Knee Joint Angles by Fusing Kinematic and Myoelectric Signals

Continuous Estimation of Human Knee Joint Angles by Fusing Kinematic and Myoelectric Signals

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

Characterizations on Knee Movement Estimation from Surface EMG Using Composited Approaches

Contact Info

Product

Resources

About