A novel sEMG-based force estimation method using deep-learning algorithm

Hua, Shaoyang; Wang, Congqing; Wu, Xuewei

doi:10.1007/s40747-021-00338-5

Cited by 8 publications

(5 citation statements)

References 43 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, with the rapid development of computer technology, artificial intelligence has been applied in a wide range of fields, and many studies have applied neural networks to muscle force estimation based on the sEMG. Hua et al combined linear regression (LR) and LSTM to estimate muscle forces from sEMG signals [20], and the experiment results showed that the LR-LSTM performed well in muscle force estimation. Xu et al compared the performance of CNN, LSTM, and CNN-LSTM in estimating muscle forces from sEMG signals [21], and the experiment results showed that CNN-LSTM performed best.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Muscle Forces of Lower Limbs Based on CNN–LSTM Neural Network and Wearable Sensor System

Liu,

et al. 2024

Sensors

View full text Add to dashboard Cite

Estimation of vivo muscle forces during human motion is important for understanding human motion control mechanisms and joint mechanics. This paper combined the advantages of the convolutional neural network (CNN) and long-short-term memory (LSTM) and proposed a novel muscle force estimation method based on CNN–LSTM. A wearable sensor system was also developed to collect the angles and angular velocities of the hip, knee, and ankle joints in the sagittal plane during walking, and the collected kinematic data were used as the input for the neural network model. In this paper, the muscle forces calculated using OpenSim based on the Static Optimization (SO) method were used as the standard value to train the neural network model. Four lower limb muscles of the left leg, including gluteus maximus (GM), rectus femoris (RF), gastrocnemius (GAST), and soleus (SOL), were selected as the studying objects in this paper. The experiment results showed that compared to the standard CNN and the standard LSTM, the CNN–LSTM performed better in muscle forces estimation under slow (1.2 m/s), medium (1.5 m/s), and fast walking speeds (1.8 m/s). The average correlation coefficients between true and estimated values of four muscle forces under slow, medium, and fast walking speeds were 0.9801, 0.9829, and 0.9809, respectively. The average correlation coefficients had smaller fluctuations under different walking speeds, which indicated that the model had good robustness. The external testing experiment showed that the CNN–LSTM also had good generalization. The model performed well when the estimated object was not included in the training sample. This article proposed a convenient method for estimating muscle forces, which could provide theoretical assistance for the quantitative analysis of human motion and muscle injury. The method has established the relationship between joint kinematic signals and muscle forces during walking based on a neural network model; compared to the SO method to calculate muscle forces in OpenSim, it is more convenient and efficient in clinical analysis or engineering applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Estimation of Muscle Forces of Lower Limbs Based on CNN–LSTM Neural Network and Wearable Sensor System

Liu,

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Although the training of deep neural networks may be lengthy, as the inference only involves a relatively simple forward pass through the network, it is computationally inexpensive and thus very quick. For instance, Hua et al [23] proposed a linear regression (LR) and long short-term memory (LSTM)integrated method (LR-LSTM) to predict the muscle force under the isometric contraction state. Tang et al [24] developed a modified framework to accurately predict muscle forces based on encoder-decoder networks.…”

Section: Introductionmentioning

confidence: 99%

Physics-Informed Deep Learning for Muscle Force Prediction With Unlabeled sEMG Signals

Ma,

Zhang,

Shi

et al. 2024

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Computational biomechanical analysis plays a pivotal role in understanding and improving human movements and physical functions. Although physics-based modeling methods can interpret the dynamic interaction between the neural drive to muscle dynamics and joint kinematics, they suffer from high computational latency. In recent years, data-driven methods have emerged as a promising alternative due to their fast execution speed, but label information is still required during training, which is not easy to acquire in practice. To tackle these issues, this paper presents a novel physics-informed deep learning method to predict muscle forces without any label information during model training. In addition, the proposed method could also identify personalized muscle-tendon parameters. To achieve this, the Hill muscle model-based forward dynamics is embedded into the deep neural network as the additional loss to further regulate the behavior of the deep neural network. Experimental validations on the wrist joint from six healthy subjects are performed, and a fully connected neural network (FNN) is selected to implement the proposed method. The predicted results of muscle forces show comparable or even lower root mean square error (RMSE) and higher coefficient of determination com-Manuscript

show abstract

“…Furthermore, related traditional methods include linear discriminant analysis (LDA) [22], principal component analysis (PCA) [23], decision tree [24][25][26][27]. Deep learning algorithms have also been widely used in sEMG processing and behavioral intention recognition due to their ability to automatically learn data-representing features [28][29][30][31][32]. For instance, Wang et al proposed an sEMG Gesture recognition network by improving the multi-stream convolutional attention module, and achieved good results on the Ninapro DB1 dataset [31].…”

Section: Introductionmentioning

confidence: 99%

An Efficient Method for Identifying Lower Limb Behavior Intentions Based on Surface Electromyography

Ling,

Wang,

Ding

et al. 2023

CMC

View full text Add to dashboard Cite

Surface electromyography (sEMG) is widely used for analyzing and controlling lower limb assisted exoskeleton robots. Behavior intention recognition based on sEMG is of great significance for achieving intelligent prosthetic and exoskeleton control. Achieving highly efficient recognition while improving performance has always been a significant challenge. To address this, we propose an sEMG-based method called Enhanced Residual Gate Network (ERGN) for lower-limb behavioral intention recognition. The proposed network combines an attention mechanism and a hard threshold function, while combining the advantages of residual structure, which maps sEMG of multiple acquisition channels to the lower limb motion states. Firstly, continuous wavelet transform (CWT) is used to extract signals features from the collected sEMG data. Then, a hard threshold function serves as the gate function to enhance signals quality, with an attention mechanism incorporated to improve the ERGN's performance further. Experimental results demonstrate that the proposed ERGN achieves extremely high accuracy and efficiency, with an average recognition accuracy of 98.41% and an average recognition time of only 20 ms-outperforming the state-ofthe-art research significantly. Our research provides support for the application of lower limb assisted exoskeleton robots.

show abstract

A novel sEMG-based force estimation method using deep-learning algorithm

Cited by 8 publications

References 43 publications

Estimation of Muscle Forces of Lower Limbs Based on CNN–LSTM Neural Network and Wearable Sensor System

Estimation of Muscle Forces of Lower Limbs Based on CNN–LSTM Neural Network and Wearable Sensor System

Physics-Informed Deep Learning for Muscle Force Prediction With Unlabeled sEMG Signals

An Efficient Method for Identifying Lower Limb Behavior Intentions Based on Surface Electromyography

Contact Info

Product

Resources

About