Transfer Learning-Based Muscle Activity Decoding Scheme by Low-frequency sEMG for Wearable Low-cost Application

Li, Yurong; Zhang, Wenxuan; Zhang, Qian; Zheng, Nan

doi:10.1109/access.2021.3056412

Cited by 17 publications

(8 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neurophysiological activity is considered in physical measurements for muscle data. Muscle activation, extension, relaxation, muscle force, and strength are considered parameters for HSD under quantitative data collection [62].…”

Section: A Types Of Data For Detecting Human Status (Rq1)mentioning

confidence: 99%

See 1 more Smart Citation

A Systematic Literature Review on Machine Learning Algorithms for Human Status Detection

2022

View full text Add to dashboard Cite

Human status detection (HSD) is important to understand the status of users when interacting with various systems under different conditions. Recently, although various machine learning algorithms have been applied to analyze and detect human status, there are no guidelines to utilize machine learning algorithms to analyze physical, cognitive, and emotional aspects of human status. Therefore, this study aimed to investigate measures, tools, and machine learning algorithms for HSD by applying a systematic literature review method. We followed the preferred reporting items for systematic reviews and metaanalysis (PRISMA) model to answer three research questions related to the research objective. A total of 76 articles were identified using two hundred keyword combinations addressing topics under HSD in the fields of human factors and human-computer interaction (HCI). The results showed that research on HSD becomes important in industrial systems, focusing on how intelligent systems based on machine learning (ML) differ from earlier generations of automated systems, and what these differences necessarily imply for HCI to design and evaluation. The tools used to collect data for HSD on different parameters are broadly discussed. Recent HSD studies seem to focus on cognitive load and emotion, whereas prior studies have focused on the detection of physical effort. This research assists domain researchers in identifying HSD approaches using different ML algorithms that are suitable for use in their research.

show abstract

Section: A Types Of Data For Detecting Human Status (Rq1)mentioning

confidence: 99%

“…The ActiveTwo system [103] is also utilized mostly to gather data for the emotion category. Tobii Eye Tracker [86] is used for eye tracking and Myo armband [62] is used to get muscle data. The Shimmer3 [52] unit connects to one channel of galvanic skin response (GSR) data gathering and offers preamplification.…”

Section: B Tools Used To Collect Data For Hsd (Rq2)mentioning

confidence: 99%

A Systematic Literature Review on Machine Learning Algorithms for Human Status Detection

2022

View full text Add to dashboard Cite

show abstract

“…erefore, MYO EMG data contains characteristics of few samples and high dimensions. SVM is an effective classifier in solving small sample, nonlinear, and high-dimensional pattern recognition problems [33,34]. erefore, SVM and the obtained feature sample have a good combination.…”

Section: Recognition Modelmentioning

confidence: 99%

A Novel Adaptive Mutation PSO Optimized SVM Algorithm for sEMG-Based Gesture Recognition

Cao

Zhang

Kan

et al. 2021

Scientific Programming

View full text Add to dashboard Cite

In the field of noncontact human-computer interaction, it is of crucial importance to distinguish different surface electromyography (sEMG) gestures accurately for intelligent prosthetic control. Gesture recognition based on low sampling frequency sEMG signal can extend the application of wearable low-cost EMG sensor (for example, MYO bracelet) in motion control. In this paper, a combination of sEMG gesture recognition consisting of feature extraction, genetic algorithm (GA), and support vector machine (SVM) model is proposed. Particularly, a novel adaptive mutation particle swarm optimization (AMPSO) algorithm is proposed to optimize the parameters of SVM; moreover, a new calculation method of mutation probability is also defined. The AMPSO-SVM model based on combination processing is successfully applied to MYO bracelet dataset, and four gesture classifications are carried out. Furthermore, AMPSO-SVM is compared with PSO-SVM, GS-SVM, and BP. The sEMG gesture recognition rate of AMPSO-SVM is 0.975, PSO-SVM is 0.9463, GS-SVM is 0.9093, and BP is 0.9019. The experimental results show that AMPSO-SVM is effective for low-frequency sEMG signals of different gestures.

show abstract

“…In terms of EMG pattern recognition, many classifiers have been used in recent studies. ese are convolutional neural networks (CNNs) [49,50], linear discriminant analysis (LDA) [51], artificial neural networks (ANNs) [52], fuzzy methods [53], support vector machines (SVMs) [54,55], and k-nearest neighbours (KNNs) [56]. Among these methods, the CNN provides very strong EMG recognition performance but is impossible to implement in cheap hardware for real-time operation [57].…”

Section: Introductionmentioning

confidence: 99%

Myoelectric Pattern Recognition Performance Enhancement Using Nonlinear Features

Islam

Ahmad

Haque

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The multichannel electrode array used for electromyogram (EMG) pattern recognition provides good performance, but it has a high cost, is computationally expensive, and is inconvenient to wear. Therefore, researchers try to use as few channels as possible while maintaining improved pattern recognition performance. However, minimizing the number of channels affects the performance due to the least separable margin among the movements possessing weak signal strengths. To meet these challenges, two time-domain features based on nonlinear scaling, the log of the mean absolute value (LMAV) and the nonlinear scaled value (NSV), are proposed. In this study, we validate the proposed features on two datasets, the existing four feature extraction methods, variable window size, and various signal-to-noise ratios (SNR). In addition, we also propose a feature extraction method where the LMAV and NSV are grouped with the existing 11 time-domain features. The proposed feature extraction method enhances accuracy, sensitivity, specificity, precision, and F1 score by 1.00%, 5.01%, 0.55%, 4.71%, and 5.06% for dataset 1, and 1.18%, 5.90%, 0.66%, 5.63%, and 6.04% for dataset 2, respectively. Therefore, the experimental results strongly suggest the proposed feature extraction method, for taking a step forward with regard to improved myoelectric pattern recognition performance.

show abstract

Transfer Learning-Based Muscle Activity Decoding Scheme by Low-frequency sEMG for Wearable Low-cost Application

Cited by 17 publications

References 47 publications

A Systematic Literature Review on Machine Learning Algorithms for Human Status Detection

A Systematic Literature Review on Machine Learning Algorithms for Human Status Detection

A Novel Adaptive Mutation PSO Optimized SVM Algorithm for sEMG-Based Gesture Recognition

Myoelectric Pattern Recognition Performance Enhancement Using Nonlinear Features

Contact Info

Product

Resources

About