Evaluation of Feature Extraction and Classification for Lower Limb Motion Based on sEMG Signal

Qin, Pengjie; Shi, Xin

doi:10.3390/e22080852

Cited by 35 publications

(17 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of this study show that even though the feature search space was greatly increased, the combined results of the genetic algorithm still outperformed the state-of-the-art feature sets. Other than the work by Phinyomark et al (2017) or Qin and Shi (2020) , we decided not to investigate the individual impact of each feature, as features combined may show added benefit in terms of performance. In our case, we wanted to have the genetic algorithm come up with a feature set, without looking into the groups features could belong to, to not restrict the genetic algorithm in its search.…”

Section: Discussionmentioning

confidence: 99%

Genetic Algorithm for Feature Selection in Lower Limb Pattern Recognition

et al. 2021

View full text Add to dashboard Cite

Choosing the right features is important to optimize lower limb pattern recognition, such as in prosthetic control. EMG signals are noisy in nature, which makes it more challenging to extract useful information. Many features are used in the literature, which raises the question which features are most suited for use in lower limb myoelectric control. Therefore, it is important to find combinations of best performing features. One way to achieve this is by using a genetic algorithm, a meta-heuristic capable of searching vast feature spaces. The goal of this research is to demonstrate the capabilities of a genetic algorithm and come up with a feature set that has a better performance than the state-of-the-art feature set. In this study, we collected a dataset containing ten able-bodied subjects who performed various gait-related activities while measuring EMG and kinematics. The genetic algorithm selected features based on the performance on the training partition of this dataset. The selected feature sets were evaluated on the remaining test set and on the online benchmark dataset ENABL3S, against a state-of-the-art feature set. The results show that a feature set based on the selected features of a genetic algorithm outperforms the state-of-the-art set. The overall error decreased up to 0.54% and the transitional error by 2.44%, which represent a relative decrease in overall errors up to 11.6% and transitional errors up to 14.1%, although these results were not significant. This study showed that a genetic algorithm is capable of searching a large feature space and that systematic feature selection shows promising results for lower limb myoelectric control.

show abstract

Section: Discussionmentioning

confidence: 99%

Genetic Algorithm for Feature Selection in Lower Limb Pattern Recognition

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Here absolutely twelve features are extricated from the preprocessed EMG signals; dependent on all features the development of the exoskeleton orthosis is analyzed. Nevertheless, a large portion of the features is repetitive, and consequently joins a portion of the characteristics which does not bring about critical betterment in the precision of forecast than utilizing a signal portion [25]. These features don't just really consider the present worth, and yet can be determined over a window.…”

Section: Extracted Features For Proposed Emg Signalsmentioning

confidence: 99%

Design of Human Adaptive Mechatronics Controller for Upper Limb Motion Intention Prediction

Hwang¹,

Kim²,

Kim³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Human Adaptive Mechatronics (HAM) includes human and computer system in a closed loop. Elderly person with disabilities, normally carry out their daily routines with some assistance to move their limbs. With the short fall of human care takers, mechatronics devices are used with the likes of exoskeleton and exosuits to assist them. The rehabilitation and occupational therapy equipments utilize the electromyography (EMG) signals to measure the muscle activity potential. This paper focuses on optimizing the HAM model in prediction of intended motion of upper limb with high accuracy and to increase the response time of the system. Limb characteristics extraction from EMG signal and prediction of optimal controller parameters are modeled. Time and frequency based approach of EMG signal are considered for feature extraction. The models used for estimating motion and muscle parameters from EMG signal for carrying out limb movement predictions are validated. Based on the extracted features, optimal parameters are selected by Modified Lion Optimization (MLO) for controlling the HAM system. Finally, supervised machine learning makes predictions at different points in time for individual sensing using Support Vector Neural Network (SVNN). This model is also evaluated based on optimal parameters of motion estimation and the accuracy level along with different optimization models for various upper limb movements. The proposed model of human adaptive controller predicts the limb movement by 96% accuracy.

show abstract

“…The commonly used models for solving classification problems are K-nearest neighbor (KNN) [14], multilayer perceptron (MLP) [15] and artificial neural network (ANN) [16]. Qin et al [17] used the Gaussian kernel linear discriminant analysis (GK-LDA) with wilson amplitude (WAMP) to classify four sport modes of the lower limbs. The recognition accuracy was as high as 96%.…”

Section: Introductionmentioning

confidence: 99%

LS-SVM Combined with ZNN for Predicting the Continuous Motion Joint Angle of Lower Limb

Zhang

Liu

et al. 2021

2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)

View full text Add to dashboard Cite

In this paper, a method fusing least squares support vector machine (LS-SVM) with Gaussian kernel function and zeroing neural network (ZNN) is proposed to forecast the continuous motion of lower limb. The surface electromyography (sEMG) signal contains human behavior information and directly reflects the movement intention. In the experiment, the sEMG signal of the lower limbs when the tester is doing leg extension exercise is collected and the real knee joint angle is recorded at the same time. Then the raw sEMG is subjected to a series of preprocessing, and the corresponding muscle activation is gained by calculation. The muscle activation is used as input to the LS-SVM model, and the output to the model is the knee joint angle. LS-SVM transforms the original problem into solving linear equations. When the amount of data is relatively large, the traditional solution method is very time-consuming, and the proposed ZNN method is able to solve the problem, thus speeding up the convergence speed and greatly reducing the learning time. Finally, the back propagation neural network (BPNN) model is utilized to form a comparative experiment. The numerical results indicate that a more stable and better performance is reflected in the raised method, which provides a valuable reference for the research of joint continuous estimation.

show abstract

Evaluation of Feature Extraction and Classification for Lower Limb Motion Based on sEMG Signal

Cited by 35 publications

References 42 publications

Genetic Algorithm for Feature Selection in Lower Limb Pattern Recognition

Genetic Algorithm for Feature Selection in Lower Limb Pattern Recognition

Design of Human Adaptive Mechatronics Controller for Upper Limb Motion Intention Prediction

LS-SVM Combined with ZNN for Predicting the Continuous Motion Joint Angle of Lower Limb

Contact Info

Product

Resources

About