Hierarchical Motion Segmentation Through sEMG for Continuous Lower Limb Motions

Park, Seong‐Sik; Lee, Donghyeon; Chung, Wan Kyun; Kim, Kee Hoon

doi:10.1109/lra.2019.2932343

Cited by 9 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adaptive segmentation technology was utilized to find potential segments of actions and complete classification, the segmentation method depended on the signal features of the action, which need to be extracted manually, for our research, due to the complexity of the object, it is difficult to extract features manually, and machine learning approach is more appropriate. Park Seongsik's [10] method used a hierarchical hidden Markov model (HHMM). The authors employed sEMG to process the continuous movement of human lower limbs.…”

Section: Introductionmentioning

confidence: 99%

End‐to‐end motion segmentation and recognition with high accuracy using wearable devices

Zhou

Cheng

Xiang

2022

Electronics Letters

View full text Add to dashboard Cite

An important research direction in applying wearable devices in sports is motion recognition and segmentation. The authors propose an endto-end motion recognition-segmentation method in basketball. First, data are collected using an arm guard with an inertial measurement unit (IMU) module. Next, a sliding window is used to extract the data features. The feature extraction method is a multi-model long short-term memory (LSTM) network. After feature extraction, a label vector is obtained and a result vector is formed after temporal matrix processing. The results of the experiment on the accuracy, precision and recall were 97.1% ± 1.6%, 94.4% ± 0.7% and 96.4% ± 1.1%, respectively, showing better performance among similar studies.

show abstract

Section: Introductionmentioning

confidence: 99%

End‐to‐end motion segmentation and recognition with high accuracy using wearable devices

Zhou

Cheng

Xiang

2022

Electronics Letters

View full text Add to dashboard Cite

show abstract

“…sEMG signals have been proved to improve the accuracy of intention prediction in [ 8 , 12 , 13 , 14 ]. However, the non-stationary of sEMG signal increases the uncertainty of the motion recognition algorithm [ 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

Online Adaptive Prediction of Human Motion Intention Based on sEMG

Ding

Yang

Wang

et al. 2021

Sensors

View full text Add to dashboard Cite

Accurate and reliable motion intention perception and prediction are keys to the exoskeleton control system. In this paper, a motion intention prediction algorithm based on sEMG signal is proposed to predict joint angle and heel strike time in advance. To ensure the accuracy and reliability of the prediction algorithm, the proposed method designs the sEMG feature extraction network and the online adaptation network. The feature extraction utilizes the convolution autoencoder network combined with muscle synergy characteristics to get the high-compression sEMG feature to aid motion prediction. The adaptation network ensures the proposed prediction method can still maintain a certain prediction accuracy even the sEMG signals distribution changes by adjusting some parameters of the feature extraction network and the prediction network online. Ten subjects were recruited to collect surface EMG data from nine muscles on the treadmill. The proposed prediction algorithm can predict the knee angle 101.25 ms in advance with 2.36 degrees accuracy. The proposed prediction algorithm also can predict the occurrence time of initial contact 236±9 ms in advance. Meanwhile, the proposed feature extraction method can achieve 90.71±3.42% accuracy of sEMG reconstruction and can guarantee 73.70±5.01% accuracy even when the distribution of sEMG is changed without any adjustment. The online adaptation network enhances the accuracy of sEMG reconstruction of CAE to 87.65±3.83% and decreases the angle prediction error from 4.03∘ to 2.36∘. The proposed method achieves effective motion prediction in advance and alleviates the influence caused by the non-stationary of sEMG.

show abstract

“…To recognize the common hand motions accurately, various classical classifiers such as Neural Network [9]- [11], Support Vector Machine [12]- [14], and Hidden Markov Model [15]- [17] have been used to process SEMG signals. The experimental results show that these classifiers can achieve relatively high accuracy in motion classification, but may increase the time and space complexity of training and testing owing to complex structures.…”

Section: Introductionmentioning

confidence: 99%

SEMG-Based Human In-Hand Motion Recognition Using Nonlinear Time Series Analysis and Random Forest

Xue

Zhou

et al. 2019

IEEE Access

View full text Add to dashboard Cite

As a novel and non-invasive sensing technology, surface electromyography (SEMG) can record the bioelectrical signals on the skin surface quickly and effectively, and thus has been widely used in human motion assessment in fields like medical rehabilitation and human-computer interaction. In this paper, an SEMG-based in-hand motion recognition system is proposed to recognize ten kinds of popular hand motions. According to the human common movements in performing in-hand object manipulations, ten sets of in-hand motions, including translation, transfer, and rotation, are designed, and then a nonlinear time series analysis method of SEMG signal processing is proposed to better capture the nonlinearity of these motions. The detailed analysis method of the nonlinear data is presented, and the experimental results, including human in-hand motion recognition result, motion recognition results of different subjects, and comparison results of different algorithms performance, are analyzed and discussed in detail. Experimental results illustrate that the human in-hand motion recognition system proposed in this paper can effectively recognize these different in-hand movements with a better performance than other popular methods.INDEX TERMS Empirical mode decomposition, maximal Lyapunov exponent, random forest, surface electromyography.

show abstract

Hierarchical Motion Segmentation Through sEMG for Continuous Lower Limb Motions

Cited by 9 publications

References 22 publications

End‐to‐end motion segmentation and recognition with high accuracy using wearable devices

End‐to‐end motion segmentation and recognition with high accuracy using wearable devices

Online Adaptive Prediction of Human Motion Intention Based on sEMG

SEMG-Based Human In-Hand Motion Recognition Using Nonlinear Time Series Analysis and Random Forest

Contact Info

Product

Resources

About