Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Xiaodong Lv et al.
Summary: This article proposes a remote hand gesture recognition system based on a deep learning framework of multi-attention mechanism convolutional neural network using sEMG energy. The system enhances the recognition accuracy by improving the feature maps and shortcuts, and achieves high accuracy on multiple datasets.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Engineering, Biomedical
Chen Chen et al.
Summary: This study proposed a real-time hand gesture recognition method by decoding motor unit (MU) discharges across multiple motor tasks in a motion-wise way. The results showed that the proposed method is feasible and superior in motion tasks and gesture recognition, expanding the potential applications of neural decoding in human-machine interfaces.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2023)
Review
Engineering, Electrical & Electronic
Md. Maruf Hossain Shuvo et al.
Summary: The successful integration of deep neural networks has led to breakthroughs in various fields, but deploying these accurate models for practical machine learning solutions remains challenging. Deep learning algorithms are often computationally expensive, power-hungry, and require large memory. Edge devices, such as mobile phones and IoT devices, have limited resources but can reduce cloud transmission cost.
PROCEEDINGS OF THE IEEE
(2023)
Article
Computer Science, Artificial Intelligence
Yansheng Wu et al.
Summary: The movement of the human limb is generated by muscle contraction, and surface electromyography (sEMG) reflects muscle activation information. This study aims to investigate the difference in muscle activation during force increase and decrease using sEMG signals and establish a relationship model between sEMG and force. A synchronous data acquisition device is used to collect force and sEMG signals, and a new method based on spectrogram is introduced for sEMG signal feature extraction. The experimental results show that the sEMG signal differs between force increase and decrease processes, with a more significant difference at weaker muscle contraction strength.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Jian-Hong Gao et al.
Summary: This study proposes a novel diagnostic approach for high-impedance faults (HIF) based on the semantic segmentation of the signal envelope (SE) and Hilbert marginal spectrum (HMS). The approach uses 1DUNet to identify the transient process of potential fault events in zero-sequence voltage, and then extracts SE and HMS from longer timescale zero-sequence voltage to represent HIF characteristics. These features are transformed into images, and ResNet18 is employed for HIF detection. An industrial prototype of the proposed approach has been implemented and validated in a 10 kV test system. The experimental results show that the proposed approach outperforms the comparison by a significant margin, especially in resonant distribution networks.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Gongfa Li et al.
Summary: This paper explores the integration of blockchain technology in the Internet of Medical Things (IoMT) and its impact on user security, convenience, and interoperability. It presents a novel approach to continuous dynamic gesture recognition by improving filters and models for surface electromyography (EMG) signals. The experimental results demonstrate the effectiveness of the proposed method in reducing false recognition rates and achieving accurate gesture recognition.
INFORMATION SCIENCES
(2023)
Article
Robotics
Xuhui Hu et al.
Summary: This study proposes a novel human-robot co-adaptation framework to improve robust and accurate user intent recognition in assistance robots. By incorporating user adaptability early in the training phase and applying biofeedback-based user adaptive behavior, this framework enables the machine to adapt to changes through online learning.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Engineering, Biomedical
Yurong Li et al.
Summary: The proposed EMG-filtering method combines adaptive wavelet-Wiener filter and adaptive moving average filter to effectively reduce noise in ECG signals. By improving SNR and preserving clinical information, the method shows promising results in filtering EMG interference in dynamic ECG signals.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Review
Engineering, Electrical & Electronic
Mingde Zheng et al.
Summary: Surface electromyography (sEMG) is a non-invasive method for measuring neuromuscular potentials. This technique has been extensively studied and has applications in both medical field and human-machine interfaces. This article provides an overview of the physical basis and hardware development of sEMG signals, discusses signal processing and machine learning methods for extracting information from sEMG signals, and explores future trends and challenges in the field.
IEEE SENSORS JOURNAL
(2022)
Article
Computer Science, Artificial Intelligence
Noemi Gozzi et al.
Summary: This study applies explainable artificial intelligence algorithms to EMG hand gesture classification in order to understand the results of machine learning models in relation to physiological processes. The findings show that AI models recognize hand gestures by mapping and fusing high amplitude activity of synergic muscles, and that classification performance can be improved by reducing the number of electrodes and selecting key features.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Zhi-Hui Zhan et al.
Summary: Deep learning has achieved great success in solving learning problems, and evolutionary computation has been applied to optimize deep learning. Given the rapid development of evolutionary deep learning, it is necessary to review and summarize existing research to provide references for future studies and applications.
Article
Robotics
Tianyun Sun et al.
Summary: In this study, a deep network approach is proposed to decode high-density surface electromyography (HD-sEMG) signals, aiming at estimating dynamic temporal dependencies and identifying transient intentions. The introduction of heterogeneous temporal dilation and dilation foci enhances the spatiotemporal resolution and modeling capability. The experimental results demonstrate the state-of-the-art performance in terms of accuracy and training time.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Pedro J. Freire et al.
Summary: This article examines the use of predictive modeling, classification, and regression based on neural networks for soft-demapping in coherent optical communications. The study finds that regression-based learning is superior to classification-based learning in terms of Q-factor and achievable information rates. Additionally, the use of cross-entropy loss function may not always be the most suitable option due to learning problems.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Ping Shi et al.
Summary: Pattern recognition based on surface electromyography (sEMG) can improve the quality of life for amputees, but the lack of robustness and adaptability has hindered its practical application. To address this issue, a novel multi-task dual-stream supervised domain adaptation network based on convolutional neural network (CNN) was proposed, and its performance was validated through long-term multi-subject sEMG signal acquisition.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Environmental Sciences
Qing Yan et al.
Summary: This paper proposes a novel cloud detection algorithm based on multi-scale input and dual-channel attention mechanisms. The method achieves excellent results in terms of pixel accuracy, category pixel accuracy, recall, F1 score, and visual effects, surpassing existing semantic segmentation methods.
Article
Computer Science, Information Systems
Tianzhe Bao et al.
Summary: This article provides a systematic review of recent achievements in the field of multi-functional human-machine interfaces. By exploring the fusion of multi-modal sensors, transfer learning methods, and post-processing approaches, the aim is to enhance the robustness, adaptability, and reliability of the models. Additionally, research challenges and emerging opportunities in hardware development, public resources, and decoding strategies are analyzed to provide perspectives for future developments.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Engineering, Biomedical
Bin Fang et al.
Summary: This paper proposes a method for simultaneous recognition of gestures and forces for interaction with a prosthetic hand, and validates the effectiveness of this method through offline and online experiments. It demonstrates that gesture classification tasks with different force levels can be accurately recognized based on sEMG signals, improving the operation ability and comfortable interaction for amputees.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2022)
Article
Computer Science, Information Systems
Shihan Ma et al.
Summary: In this study, a novel filter is proposed to effectively remove three types of noise components from electromyography (EMG) signals. The method decomposes noisy EMG signals into band-limited modes using variational mode decomposition (VMD) and removes each category of noise within specific modes. Experimental results show that the proposed method achieves the best performance in removing baseline wandering and white Gaussian noise.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2021)
Article
Computer Science, Information Systems
Xiang Chen et al.
Summary: This paper introduces an effective transfer learning strategy to improve gesture recognition accuracy and decrease training burden. The strategy performs well on different datasets, significantly enhancing recognition accuracy and greatly reducing training time.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2021)
Review
Neurosciences
Wei Li et al.
Summary: Amputation of the upper limb has a negative impact on amputees' quality of life and daily performance, highlighting the importance of achieving natural control for prosthetic hands. Deep learning has shown great potential in improving accuracy of sEMG pattern recognition and reducing interference, indicating promising future prospects for clinical application.
FRONTIERS IN NEUROSCIENCE
(2021)
Article
Engineering, Biomedical
Leobardo E. Sanchez-Velasco et al.
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2020)
Article
Engineering, Biomedical
Md Ferdous Wahid et al.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2020)
Article
Computer Science, Hardware & Architecture
Shu Shen et al.
MOBILE NETWORKS & APPLICATIONS
(2020)
Review
Chemistry, Analytical
Nawadita Parajuli et al.
Article
Multidisciplinary Sciences
Yu Hu et al.
Article
Chemistry, Multidisciplinary
Nurhazimah Nazmi et al.
APPLIED SCIENCES-BASEL
(2017)
Article
Mathematics, Applied
Roberto Bilato et al.
ADVANCES IN COMPUTATIONAL MATHEMATICS
(2014)
Review
Sport Sciences
JL Durstine et al.
