Article
Engineering, Biomedical
Hui Wang, Pingao Huang, Tinghan Xu, Guanglin Li, Yong Hu
Summary: This paper presents a novel approach for myoelectric control by designing a fabric myoelectric armband to reduce electrode shifts. A fully unsupervised adaptive method called hybrid serial classifier (HSC) is proposed to eliminate the need for retraining. The performance of the approach is investigated using a dataset of forearm motion and compared with other algorithms, showing higher classification accuracy.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2022)
Article
Engineering, Biomedical
Daniele D'Accolti, Katarina Dejanovic, Leonardo Cappello, Enzo Mastinu, Max Ortiz-Catalan, Christian Cipriani
Summary: The design of prosthetic controllers using neurophysiological signals remains a significant challenge for bioengineers. Existing electromyographic (EMG) continuous pattern recognition controllers rely on assumptions of stable EMG patterns, which we challenge. We propose an algorithm that decodes wrist and hand movements based on transient EMG signals. Our offline evaluations show promising results with non-amputees achieving a median accuracy of around 96%, while amputees achieved a median accuracy of around 89%. Further assessments with domain-adaptation strategies may be needed for amputees. Overall, our results support the hypothesis that decoding transient EMG signals can be a viable pattern recognition strategy for prosthetic controllers.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Article
Engineering, Biomedical
Bo Xue, Le Wu, Aiping Liu, Xu Zhang, Xiang Chen, Xun Chen
Summary: Due to individual differences, myoelectric interfaces trained by multiple users cannot adapt to the hand movement patterns of new users. A few-shot supervised domain adaptation framework is proposed in this paper to address this issue. The proposed method aligns the distributions of different domains and achieves high recognition accuracy with a small number of samples, reducing the user burden and facilitating the development of myoelectric pattern recognition techniques.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Hanadi A. Jaber, Mofeed T. Rashid, Hisham Mahmood, Luigi Fortuna
Summary: This paper proposes a set of robust features to improve the performance of the myoelectric control system for upper limb prostheses. These features significantly increase the classification accuracy in online setups and are more resistant to noise compared to time-domain features. The results confirm the robustness of the features extracted from the high-density surface electromyography map.
IEEE SENSORS JOURNAL
(2022)
Article
Computer Science, Information Systems
Ethan Eddy, Evan Campbell, Angkoon Phinyomark, Scott Bateman, Erik Scheme
Summary: The article introduces an open-source Python library, LibEMG, which can be used for offline EMG analysis and online EMG-based interaction development. By eliminating the barriers that require substantial domain expertise, the library provides researchers with an accessible tool to accelerate research and improve reproducibility. By combining expertise from the prosthetics and human-computer interaction communities, it aims to facilitate the exploration of myoelectric control technology.
Article
Engineering, Biomedical
Jena L. Nawfel, Kevin B. Englehart, Erik J. Scheme
Summary: Research indicates that the standard offline metric, classification accuracy, is not a good indicator of usability and other metrics are needed for prediction. Combining offline metrics leads to more accurate predictions, with feature efficiency being the best indicator for predicting usability metric throughput.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2021)
Article
Engineering, Biomedical
Hanadi Abbas Jaber, Mofeed Turky Rashid, Luigi Fortuna
Summary: The study integrates high-density surface electromyography (HD-sEMG) electrodes technology with robust hybrid spatial features to improve the performance of myoelectric prostheses. Proposed spatial features and SVM classifier evaluation demonstrate the significant impact of robust spatial features on classification accuracy.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Engineering, Electrical & Electronic
Hanadi Abbas Jaber, Mofeed Turky Rashid, Luigi Fortuna
Summary: The study proposes three types of spatial features based on the HOG algorithm to improve myoelectric performance, overcoming the challenge of nonstationary properties of EMG signals.
IRANIAN JOURNAL OF SCIENCE AND TECHNOLOGY-TRANSACTIONS OF ELECTRICAL ENGINEERING
(2021)
Article
Engineering, Electrical & Electronic
Long Wang, Xiaoling Li, Zhangyi Chen, Zhipeng Sun, Jingyi Xue
Summary: This study proposes an electrode shift correction method and an online updating framework to improve the performance and robustness of myoelectric recognition models. Results from offline and online experiments demonstrate the effectiveness of the proposed methods and their potential for practical applications.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Biomedical
Xuan Zhang, Xu Zhang, Le Wu, Chang Li, Xiang Chen, Xun Chen
Summary: This article introduces a gesture recognition method based on unsupervised domain adaptation, which utilizes a self-guided adaptive sampling strategy to improve the feature representation consistency of myoelectric patterns across users. Experimental results demonstrate the excellent performance of this method in cross-user classification.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2022)
Article
Chemistry, Analytical
Bingbin Wang, Levi Hargrove, Xinqi Bao, Ernest N. Kamavuako
Summary: This study compared the statistical properties of surface electromyography signals used in home and laboratory settings for prosthesis calibration, finding differences in between-calibration classification errors but not within-calibration classification errors.
Article
Computer Science, Information Systems
Md. Johirul Islam, Shamim Ahmad, Fahmida Haque, Mamun Bin Ibne Reaz, Mohammad A. S. Bhuiyan, Md. Rezaul Islam
Summary: The authors proposed a scheme to normalize EMG signals across channels before feature extraction, significantly enhancing force invariant EMG-PR performance compared to previous studies. The proposed method achieved the highest F1 scores when using different classifiers, suggesting its potential for practical application.
Article
Engineering, Biomedical
Ulysse Cote-Allard, Gabriel Gagnon-Turcotte, Angkoon Phinyomark, Kyrre Glette, Erik Scheme, Francois Laviolette, Benoit Gosselin
Summary: Disparities exist between offline accuracy and real-time usability in electromyography-based gesture recognition, due to the absence of a controller and the difficulty in including dynamic factors. A new type of dataset recorded in virtual reality using an EMG-independent controller serves as an intermediate benchmark. This dataset is leveraged to evaluate different recalibration techniques for long-term gesture recognition, showing the novel algorithm TADANN outperforms fine-tuning.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2021)
Article
Neurosciences
Mojisola Grace Asogbon, Oluwarotimi Williams Samuel, Ejay Nsugbe, Yongcheng Li, Frank Kulwa, Deogratias Mzurikwao, Shixiong Chen, Guanglin Li
Summary: This article investigates the impact of myoelectric signal recording duration on finger gesture recognition and finds that a recording duration of 5 to 10 seconds can achieve good decoding accuracy. It also provides guidance for selecting appropriate recording durations.
FRONTIERS IN NEUROSCIENCE
(2023)
Article
Engineering, Manufacturing
Fei Cheng, Jingyan Dong
Summary: This study proposed an online statistical pattern recognition method using an incremental adaptive support vector machine to detect severe tip wear in nanomachining. By analyzing the nanomachining force data, the method achieved accurate detection and monitoring of tip wear, showing promising results for online damage detection in the nanomachining process.
JOURNAL OF MANUFACTURING PROCESSES
(2021)