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, Biomedical
Xiangxin Li, Lan Tian, Yue Zheng, Oluwarotimi Williams Samuel, Peng Fang, Lin Wang, Guanglin Li
Summary: Surface electromyogram pattern recognition (EMG-PR) is a promising approach for predicting amputees' motion intentions to control myoelectric prostheses. In this study, a feature filtering strategy was proposed and applied to improve the performance of EMG-PR. Experimental results showed that the proposed strategy significantly increased motion classification accuracy and real-time motion completion rate.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Engineering, Biomedical
Jianan Li, Ziling Zhu, William J. Boyd, Carlos Martinez-Luna, Chenyun Dai, Haopeng Wang, He Wang, Xinming Huang, Todd R. Farrell, Edward A. Clancy
Summary: Most transradial prosthesis users have limited function with conventional Sequential myoelectric control, as they can only control one degree of freedom at a time. However, our regression-based EMG control method allows simultaneous and proportional control of two degrees of freedom in a virtual task. Using a short calibration period and automated electrode site selection, we achieved better target matching performance than Sequential control.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Rami N. Khushaba, Erik Scheme, Ali H. Al-Timemy, Angkoon Phinyomark, Ahmed Al-Taee, Adel Al-Jumaily
Summary: This paper introduces a novel approach using Fusion of Time Domain Descriptors and Range Spatial Filtering for processing EMG signals, achieving superior performance compared to traditional methods and other state-of-the-art models.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
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
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
Computer Science, Artificial Intelligence
Akira Furui, Takuya Igaue, Toshio Tsuji
Summary: This study proposes an EMG pattern classification method that incorporates a scale mixture-based generative model and trains the model using variational Bayesian learning. An information-based method is introduced to optimize the hyperparameters of the proposed method. Experimental results demonstrate the superiority of the proposed method on public datasets and validate its effectiveness.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Engineering, Biomedical
Ziling Zhu, Jianan Li, William J. Boyd, Carlos Martinez-Luna, Chenyun Dai, Haopeng Wang, He Wang, Xinming Huang, Todd R. Farrell, Edward A. Clancy
Summary: Recent research has made progress in achieving simultaneous, independent, and proportional control of hand-wrist prostheses using surface electromyogram signals. Two regression-based controllers were evaluated and compared with a conventional sequential controller, with the regression controllers performing better in certain tasks.
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
Medicine, General & Internal
Md. Johirul Islam, Shamim Ahmad, Fahmida Haque, Mamun Bin Ibne Reaz, Mohammad Arif Sobhan Bhuiyan, Md. Rezaul Islam
Summary: The improved force-invariant feature extraction method proposed in the study uses nonlinear transformation, changes in amplitude, signal amplitude, and spatial correlation coefficients to extract information from electromyogram signals across different force levels. This method shows higher pattern recognition performance, robustness, and efficiency compared to existing feature extraction methods.
Article
Chemistry, Analytical
Giulio Marano, Cristina Brambilla, Robert Mihai Mira, Alessandro Scano, Henning Mueller, Manfredo Atzori
Summary: This study investigates the challenge of training complex models to control robotic hand prostheses using transfer learning. The results suggest that traditional transfer learning algorithms do not improve performance significantly when proper hyperparameter optimization is applied.
Article
Engineering, Biomedical
Xinhui Li, Xu Zhang, Xiang Chen, Xun Chen, Liwei Zhang
Summary: The paper proposes a novel method, MAT-DGA, for addressing the cross-user variability problem in myoelectric pattern recognition. This method integrates domain generalization and unsupervised domain adaptation into a unified framework, utilizing mix-up and adversarial training strategies to enhance the integration. Experimental results show that the proposed method achieves a high accuracy of 95.71%±4.17% under cross-user testing scenarios, outperforming other UDA methods significantly.
IEEE TRANSACTIONS ON BIOMEDICAL 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)
Review
Chemistry, Analytical
Federico Mereu, Francesca Leone, Cosimo Gentile, Francesca Cordella, Emanuele Gruppioni, Loredana Zollo
Summary: The evolution of technological and surgical techniques allows for more intuitive control of multiple joints with advanced prosthetic systems. Targeted Muscle Reinnervation (TMR) is considered an innovative surgical technique for improving prosthetic control for people with different levels of limb amputation.
Article
Engineering, Biomedical
Oluwarotimi Williams Samuel, Mojisola Grace Asogbon, Rami Khushaba, Frank Kulwa, Guanglin Li
Summary: Surface electromyogram (sEMG) is widely used in biomedical applications, especially in miniaturized rehabilitation robots. Due to its rich motor information content and non-invasiveness, sEMG is commonly used to drive pattern recognition (PR)-based control schemes. However, sEMG recordings have non-linear and non-uniform properties, and there are interferences that distort the signal's intrinsic characteristics, making existing signal processing methods unable to provide the required motor control information. Therefore, a multiresolution decomposition driven by dual-polynomial interpolation (MRDPI) technique is proposed for denoising and reconstruction of multi-class EMG signals to enhance signal quality and preserve motor information.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2023)
Article
Engineering, Biomedical
Alexander T. Belyea, Kevin B. Englehart, Erik J. Scheme
JOURNAL OF NEURAL ENGINEERING
(2018)
Article
Computer Science, Information Systems
Asim Waris, Imran K. Niazi, Mohsin Jamil, Kevin Englehar, Winnie Jensen, Ernest Nlandu Kamavuako
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2019)
Article
Engineering, Biomedical
Asim Waris, Irene Mendez, Kevin Englehart, winnie Jensen, Ernest Nlandu Kamavuako
JOURNAL OF NEURAL ENGINEERING
(2019)
Article
Biochemical Research Methods
Daniel Blustein, Ahmed Shehata, Kevin Englehart, Jonathon Sensinger
PLOS COMPUTATIONAL BIOLOGY
(2018)
Article
Engineering, Biomedical
Ali Ameri, Mohammad Ali Akhaee, Erik Scheme, Kevin Englehart
JOURNAL OF NEURAL ENGINEERING
(2019)
Article
Computer Science, Information Systems
Jason W. Robertson, Kevin B. Englehart, Erik J. Scheme
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2019)
Article
Engineering, Biomedical
Alex Belyea, Kevin Englehart, Erik Scheme
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2019)
Article
Engineering, Biomedical
Ali Ameri, Mohammad Ali Akhaee, Erik Scheme, Kevin Englehart
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2020)
Article
Chemistry, Analytical
Asim Waris, Muhammad Zia Ur Rehman, Imran Khan Niazi, Mads Jochumsen, Kevin Englehart, Winnie Jensen, Heidi Haavik, Ernest Nlandu Kamavuako
Article
Multidisciplinary Sciences
Daniel H. Blustein, Ahmed W. Shehata, Erin S. Kuylenstierna, Kevin B. Englehart, Jonathon W. Sensinger
Summary: This study focuses on error adaptation during unperturbed and naturalistic movements, showing an increase in trial-by-trial adaptation with increasing motor noise. By relying on stochastic signal processing, a reduced bias estimate of motor adaptation is obtained, improving upon conventional methods. The effectiveness of the new method is demonstrated in analyzing simulated and empirical movement data under different noise conditions.
SCIENTIFIC REPORTS
(2021)
Article
Computer Science, Information Systems
Kimia Dinashi, Ali Ameri, Mohammad Ali Akhaee, Kevin Englehart, Erik Scheme
Summary: This study proposes a new method for efficient compression of EMG data using deep convolutional autoencoders (CAE), achieving significant results in experiments. The CAE architecture can generate a highly compressed abstract data representation without significantly affecting the accuracy of data classification. Additionally, the method demonstrates excellent inter-subject performance and high generalizability.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Engineering, Biomedical
Jena L. Nawfel, Kevin B. Englehart, Erik J. Scheme
Summary: Studies have shown that closed-loop myoelectric control schemes can impact user performance and behavior compared to open-loop systems. Visual feedback provided during user training can influence the quality and predictability of a myoelectric classification-based control system. The commonly used screen guided training protocol may not represent online use effectively, suggesting the need for better training protocols that mimic real-time control.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2022)
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)
Proceedings Paper
Engineering, Biomedical
Nitin Seth, Rafaela C. de Freitas, Mitchell Chaulk, Colleen O'Connell, Kevin Englehart, Erik Scheme
2019 IEEE 16TH INTERNATIONAL CONFERENCE ON REHABILITATION ROBOTICS (ICORR)
(2019)
Proceedings Paper
Engineering, Biomedical
Anjana Gayathri Arunachalam, Kevin B. Englehart, Jon W. Sensinger
2019 IEEE 16TH INTERNATIONAL CONFERENCE ON REHABILITATION ROBOTICS (ICORR)
(2019)