Continuous Intention Prediction of Lifting Motions Using EMG-Based CNN-LSTM DOI Creative Commons
Min-Seong Gwon,

Jong-Ha Woo,

Karur Krishna Sahithi

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 42453 - 42464

Published: Jan. 1, 2024

Industrial exoskeletons is a field of ongoing research for improving human safety and conveniences. However, the adoption industrial exoskeleton robots still remains challenging. One problem that needs to be solved control delay inevitably occurs due data transmission processing issues. Recently, there has been active employing deep learning address by leveraging diverse information extracted from motion. crucial source electromyography (EMG) signals, known their quicker activation compared actual This study specifically focused on predicting changing motion intentions within squat, representative lifting in contexts. In an experimental setup involving 24 participants utilizing 7 EMG electrodes, we categorized during squat into four types. We developed CNN-LSTM model capable 300 milliseconds ahead using signals. The model's prediction performance was assessed comparing them with existing models. findings propose methodology signals lower extremity movements, facilitating feedforward robots. anticipated contribute advancement acceptance realm

Language: Английский

sEMG-Based Lower Limb Motion Prediction Using CNN-LSTM with Improved PCA Optimization Algorithm DOI
Meng Zhu, Xiaorong Guan, Zhong Li

et al.

Journal of Bionic Engineering, Journal Year: 2022, Volume and Issue: 20(2), P. 612 - 627

Published: Oct. 31, 2022

Language: Английский

Citations

55
Neuromorphic Edge Computing for Biomedical Applications: Gesture Classification Using EMG Signals DOI
Antonio Vitale, Elisa Donati, Roger Germann

et al.

IEEE Sensors Journal, Journal Year: 2022, Volume and Issue: 22(20), P. 19490 - 19499

Published: Aug. 3, 2022

With the emergence of edge-computing platforms, applications smart wearable devices are immense. This technology can be incorporated in consumer products such as smartwatches and activity trackers, for continuous health monitoring, well medical myoelectric prosthetics, to interpret electric residual limb achieve fast precise control. However, technologies require a lightweight, energy-efficient, low-latency processing system order extend devices’ autonomy while maintaining realistic user-feedback interaction. Neuromorphic processing, thanks its event-based asynchronous nature, presents ideal characteristics compact brain-inspired low-power ultra-fast computing systems that enable new generation devices. article two spiking neural networks (SNNs) electromyography (EMG) gesture recognition their evaluation on Intel’s research neuromorphic chip Loihi. Specifically, is done Kapoho Bay platform which embeds Loihi processor Universal Serial Bus (USB) form factor device allowing closed-loop edge computation. accurate experimental evaluation, this demonstrates proposed method able discriminate 12 different hand gestures using an eight-channel EMG sensor exceeds state-of-the-art results. We obtained accuracy 74% commonly used NinaPro DB5 dataset, latency 5.7 ms 300-ms samples consuming only 41 mW.

Language: Английский

Citations

39
Consensus for experimental design in electromyography (CEDE) project: Checklist for reporting and critically appraising studies using EMG (CEDE-Check) DOI Creative Commons
Manuela Besomi, Valter Devecchi, Deborah Falla

et al.

Journal of Electromyography and Kinesiology, Journal Year: 2024, Volume and Issue: 76, P. 102874 - 102874

Published: March 13, 2024

The diversity in electromyography (EMG) techniques and their reporting present significant challenges across multiple disciplines research clinical practice, where EMG is commonly used. To address these augment the reproducibility interpretation of studies using EMG, Consensus for Experimental Design Electromyography (CEDE) project has developed a checklist (CEDE-Check) to assist researchers thoroughly report methodologies. Development involved multi-stage Delphi process with seventeen experts from various disciplines. After two rounds, consensus was achieved. final CEDE-Check consists forty items that four critical areas demand precise when employed: task investigated, electrode placement, recording characteristics, acquisition pre-processing signals. This aims guide accurately critically appraise studies, thereby promoting standardised evaluation, greater scientific rigor uses approach not only facilitate study results comparisons between but it also expected contribute advancing quality other practical applications knowledge generated through use EMG.

Language: Английский

Citations

11
EMG Dataset for Gesture Recognition with Arm Translation DOI Creative Commons
Iris Kyranou,

Katarzyna Szymaniak,

Kianoush Nazarpour

et al.

Scientific Data, Journal Year: 2025, Volume and Issue: 12(1)

Published: Jan. 17, 2025

Myoelectric control has emerged as a promising approach for wide range of applications, including controlling limb prosthetics, teleoperating robots and enabling immersive interactions in the Metaverse. However, accuracy robustness myoelectric systems are often affected by various factors, muscle fatigue, perspiration, drifts electrode positions changes arm position. The latter received less attention despite its significant impact on signal quality decoding accuracy. To address this gap, we present novel dataset surface electromyographic (EMG) signals captured from multiple positions. This dataset, comprising EMG hand kinematics data 8 participants performing 6 different gestures, provides comprehensive resource investigating position-invariant algorithms. We envision to serve valuable both training benchmark Additionally, expand publicly available capturing variability across diverse positions, propose acquisition protocol that can be utilized future collection.

Language: Английский

Citations

1
Machine Learning- and Deep Learning-Based Myoelectric Control System for Upper Limb Rehabilitation Utilizing EEG and EMG Signals: A Systematic Review DOI Creative Commons

Tala Zaim,

Sara Abdel-Hadi,

R. bin Mahmoud

et al.

Bioengineering, Journal Year: 2025, Volume and Issue: 12(2), P. 144 - 144

Published: Feb. 3, 2025

Upper limb disabilities, often caused by conditions such as stroke or neurological disorders, severely limit an individual’s ability to perform essential daily tasks, leading a significant reduction in quality of life. The development effective rehabilitation technologies is crucial restoring motor function and improving patient outcomes. This systematic review examines the application machine learning deep techniques myoelectric-controlled systems for upper rehabilitation, focusing on use electroencephalography electromyography signals. By integrating non-invasive signal acquisition methods with advanced computational models, highlights how these can enhance accuracy efficiency devices. A comprehensive search literature published between January 2015 July 2024 led selection fourteen studies that met inclusion criteria. These showcase various approaches decoding intentions controlling assistive devices, models Long Short-Term Memory Networks, Support Vector Machines, Convolutional Neural Networks showing notable improvements control precision. However, challenges remain terms model robustness, complexity, real-time applicability. aims provide researchers deeper understanding current advancements this field, guiding future research efforts overcome barriers facilitate transition from experimental settings practical, real-world applications.

Language: Английский

Citations

1
Myoelectric Control Systems for Upper Limb Wearable Robotic Exoskeletons and Exosuits—A Systematic Review DOI Creative Commons
Jirui Fu, Renoa Choudhury, Saba M. Hosseini

et al.

Sensors, Journal Year: 2022, Volume and Issue: 22(21), P. 8134 - 8134

Published: Oct. 24, 2022

In recent years, myoelectric control systems have emerged for upper limb wearable robotic exoskeletons to provide movement assistance and/or restore motor functions in people with disabilities and augment human performance able-bodied individuals. control, electromyographic (EMG) signals from muscles are utilized implement strategies exosuits, improving adaptability human-robot interactions during various motion tasks. This paper reviews the state-of-the-art designed upper-limb highlights key focus areas future research directions. Here, different modalities of existing were described detail, their advantages disadvantages summarized. Furthermore, design aspects (i.e., supported degrees freedom, portability, intended application scenario) type experiments conducted validate efficacy proposed controllers also discussed. Finally, challenges limitations current analyzed, directions suggested.

Language: Английский

Citations

36
Wearable upper limb robotics for pervasive health: a review DOI Creative Commons
Chukwuemeka Ochieze, Soroush Zare, Ye Sun

et al.

Progress in Biomedical Engineering, Journal Year: 2023, Volume and Issue: 5(3), P. 032003 - 032003

Published: March 23, 2023

Abstract Wearable robotics, also called exoskeletons, have been engineered for human-centered assistance decades. They provide assistive technologies maintaining and improving patients’ natural capabilities towards self-independence enable new therapy solutions rehabilitation pervasive health. Upper limb exoskeletons can significantly enhance human manipulation with environments, which is crucial to independence, self-esteem, quality of life. For long-term use in both in-hospital at-home settings, there are still needs high comfort, biocompatibility, operability. The recent progress soft robotics has initiated (also exosuits), based on controllable compliant materials structures. Remarkable literature reviews performed rigid ranging from robot design different practical applications. Due the emerging state, few focused upper exoskeletons. This paper aims a systematic review wearable including focus their designs applications various healthcare settings. technical robots carefully reviewed that be enhanced by particularly discussed. knowledge may experience inspire ideas exoskeleton designs. We discuss challenges opportunities

Language: Английский

Citations

21
Interaction with a Hand Rehabilitation Exoskeleton in EMG-Driven Bilateral Therapy: Influence of Visual Biofeedback on the Users’ Performance DOI Creative Commons
Ana Cisnal, Paula Gordaliza, Javier Pérez Turiel

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(4), P. 2048 - 2048

Published: Feb. 11, 2023

The effectiveness of EMG biofeedback with neurorehabilitation robotic platforms has not been previously addressed. present work evaluates the influence an EMG-based visual on user performance when performing EMG-driven bilateral exercises a hand exoskeleton. Eighteen healthy subjects were asked to perform 1-min randomly generated sequences gestures (rest, open and close) in four different conditions resulting from combination using or (1) (2) kinesthetic feedback exoskeleton movement. each test was measured by computing similarity between target recognized L2 distance. Statistically significant differences subject found type provided (p-value 0.0124). Pairwise comparisons showed that distance statistically significantly lower only (2.89 ± 0.71) than presence alone (3.43 0.75, p-value = 0.0412) both (3.39 0.70, 0.0497). Hence, enables increase their control over movement platform assessing muscle activation real time. This could benefit patients learning more quickly how activate robot functions, increasing motivation towards rehabilitation.

Language: Английский

Citations

19
Estimating finger joint angles by surface EMG signal using feature extraction and transformer-based deep learning model DOI
Nur Achmad Sulistyo Putro, Cries Avian, Setya Widyawan Prakosa

et al.

Biomedical Signal Processing and Control, Journal Year: 2023, Volume and Issue: 87, P. 105447 - 105447

Published: Sept. 21, 2023

Language: Английский

Citations

16
A Review of Hand Function Rehabilitation Systems Based on Hand Motion Recognition Devices and Artificial Intelligence DOI Creative Commons

Yuexing Gu,

Yuanjing Xu,

Yuling Shen

et al.

Brain Sciences, Journal Year: 2022, Volume and Issue: 12(8), P. 1079 - 1079

Published: Aug. 15, 2022

The incidence of stroke and the burden on health care society are expected to increase significantly in coming years, due increasing aging population. Various sensory, motor, cognitive psychological disorders may remain patient after survival from a stroke. In hemiplegic patients with movement disorders, impairment upper limb function, especially hand dramatically limits ability perform activities daily living (ADL). Therefore, one essential goals post-stroke rehabilitation is restore function. recovery motor function achieved chiefly through compensatory strategies, such as robots, which have been available since end last century. This paper reviews current research status devices based various types motion recognition technologies analyzes their advantages disadvantages, application artificial intelligence summarizes limitations discusses future directions.

Language: Английский

Citations

22