High-density electromyography for effective gesture-based control of physically assistive mobile manipulators

npj Robotics, Journal Year: 2025, Volume and Issue: 3(1)

Published: Jan. 27, 2025

Language: Английский

---

A survey of motor rehabilitation for hemiplegic upper limbs based on the brain–apparatus interaction

Published: Jan. 1, 2025

Language: Английский

---

Optimizing the impact of time domain segmentation techniques on upper limb EMG decoding using multimodal features

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(5), P. e0322580 - e0322580

Published: May 8, 2025

Neurological disorders, such as stroke, spinal cord injury, and amyotrophic lateral sclerosis, result in significant motor function impairments, affecting millions of individuals worldwide. To address the need for innovative effective interventions, this study investigates efficacy electromyography (EMG) decoding improving outcomes. While existing literature has extensively explored classifier selection feature set optimization, choice preprocessing technique, particularly time-domain windowing techniques, remains understudied posing a knowledge gap. This presents upper limb movement classification by providing comprehensive comparison eight techniques. For purpose, EMG data from volunteers is recorded involving fifteen distinct movements fingers. The rectangular window technique among others emerged most effective, achieving accuracy 99.98% while employing 40 features L-SVM classifier, other classifiers. optimal combination implications development more accurate reliable myoelectric control systems. achieved high demonstrates feasibility using surface signals classification. study’s results have potential to improve reliability prosthetic limbs wearable sensors inform personalized rehabilitation programs. findings can contribute advancement human-computer interaction brain-computer interface technologies.

Language: Английский

---

A review on EMG/EEG based control scheme of upper limb rehabilitation robots for stroke patients

Heliyon, Journal Year: 2023, Volume and Issue: 9(8), P. e18308 - e18308

Published: July 20, 2023

Stroke is a common worldwide health problem and crucial contributor to gained disability. The abilities of people, who are subjected stroke, live independently significantly affected since upper limbs' functions essential for our daily life. This review article focuses on emerging trends in BCI-controlled rehabilitation techniques based EMG, EEG, or EGM + EEG signals the last few years. Working developing robotics, considered wealthy scientific area researchers period. There significant advantage that human acquires from interaction between machine his body, patient's limb very important get body recovery, this what provided mostly by applying robotic devices.

Language: Английский

---

Wearable high-density EMG sleeve for complex hand gesture classification and continuous joint angle estimation

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Aug. 9, 2024

Abstract High-density electromyography (HD-EMG) can provide a natural interface to enhance human–computer interaction (HCI). This study aims demonstrate the capability of novel HD-EMG forearm sleeve equipped with up 150 electrodes capture high-resolution muscle activity, decode complex hand gestures, and estimate continuous position via joint angle predictions. Ten able-bodied participants performed 37 movements grasps while EMG was recorded using sleeve. Simultaneously, an 18-sensor motion glove calculated 23 angles from fingers across all for training regression models. For classifying our decoding algorithm able differentiate between sequential $$97.3 \pm 0.3\%$$ 97.3±0.3% accuracy on 100 ms bin-by-bin basis. In separate mixed dataset consisting 19 randomly interspersed, performance achieved average bin-wise $$92.8 0.8\%$$ xmlns:mml="http://www.w3.org/1998/Math/MathML">92.8±0.8% . When evaluating decoders use in real-time scenarios, we found that reliably both movement transitions, achieving $$93.3 0.9\%$$ xmlns:mml="http://www.w3.org/1998/Math/MathML">93.3±0.9% set $$88.5 xmlns:mml="http://www.w3.org/1998/Math/MathML">88.5±0.9% set. Furthermore, estimated data, $$R^2$$ xmlns:mml="http://www.w3.org/1998/Math/MathML">R2 $$0.884 0.003$$ xmlns:mml="http://www.w3.org/1998/Math/MathML">0.884±0.003 $$0.750 0.008$$ xmlns:mml="http://www.w3.org/1998/Math/MathML">0.750±0.008 Median absolute error (MAE) kept below 10° joints, grand MAE $$1.8 0.04^\circ$$ xmlns:mml="http://www.w3.org/1998/Math/MathML">1.8±0.04∘ $$3.4 0.07^\circ$$ xmlns:mml="http://www.w3.org/1998/Math/MathML">3.4±0.07∘ datasets, respectively. We also assessed two modifications address specific challenges EMG-driven HCI applications. To minimize decoder latency, used method accounts reaction time by dynamically shifting cue labels time. reduce requirements, show pretraining models historical data provided increase compared were not pretrained when reducing in-session only one attempt each movement. The sleeve, combined sophisticated machine learning algorithms, be powerful tool gesture recognition estimation. technology holds significant promise applications HCI, such as prosthetics, assistive technology, rehabilitation, human–robot collaboration.

Language: Английский

---

Deep Learning Based Post-stroke Myoelectric Gesture Recognition: From Feature Construction to Network Design

IEEE Transactions on Neural Systems and Rehabilitation Engineering, Journal Year: 2024, Volume and Issue: 33, P. 191 - 200

Published: Dec. 23, 2024

Recently, robot-assisted rehabilitation has emerged as a promising solution to increase the training intensity of stroke patients while reducing workload on therapists, whilst surface electromyography (sEMG) is expected serve viable control source. In this paper, we delve into potential deep learning (DL) for post-stroke hand gesture recognition by collecting sEMG signals eight chronic subjects, focusing three primary aspects: feature domains (time, frequency, and wavelet), data structures (one or two-dimensional images), neural network architectures (CNN, CNN-LSTM, CNN-LSTM-Attention). A total 18 DL models were comprehensively evaluated in both intra-subject testing inter-subject transfer tasks, with two post-processing algorithms (Model Voting Bayesian Fusion) analysed subsequently. Experiment results infer that testing, average accuracy CNN-LSTM using frequency features highest, reaching 72.95%. For learning, CNN-LSTM-Attention one-dimensional 68.38%. Through these experiments, it was found had significant advantages over other after stroke. Moreover, algorithm can further improve accuracy, effect be increased 2.03% through model voting algorithm.

Language: Английский

---

Benchtop Performance of Novel Mixed Ionic–Electronic Conductive Electrode Form Factors for Biopotential Recordings

Sensors, Journal Year: 2024, Volume and Issue: 24(10), P. 3136 - 3136

Published: May 15, 2024

Background: Traditional gel-based (wet) electrodes for biopotential recordings have several shortcomings that limit their practicality real-world measurements. Dry may improve usability, but they often suffer from reduced signal quality. We sought to evaluate the recording properties of a novel mixed ionic–electronic conductive (MIEC) material improved performance. Methods: fabricated four MIEC electrode form factors and compared two control electrodes, which are commonly used (Ag-AgCl stainless steel). an agar synthetic skin characterize impedance each factor. An electrical phantom setup allowed us compare quality simulated biopotentials with ground-truth sources. Results: All yielded impedances in similar range (all <80 kΩ at 100 Hz). Three samples produced signal-to-noise ratios interfacial charge transfers as electrodes. Conclusions: The demonstrated and, some cases, better characteristics than current state-of-the-art can also be into myriad factors, underscoring great potential this has across wide applications.

Language: Английский

---

Identifying alterations in hand movement coordination from chronic stroke survivors using a wearable high-density EMG sleeve

Journal of Neural Engineering, Journal Year: 2024, Volume and Issue: 21(4), P. 046040 - 046040

Published: July 15, 2024

Abstract Objective. Non-invasive, high-density electromyography (HD-EMG) has emerged as a useful tool to collect range of neurophysiological motor information. Recent studies have demonstrated changes in EMG features that occur after stroke, which correlate with functional ability, highlighting their potential use biomarkers. However, previous largely explored these isolation individual electrodes assess gross movements, limiting clinical utility. This study aims predict hand function stroke survivors by combining interpretable extracted from wearable HD-EMG forearm sleeve. Approach. Here, able-bodied ( N = 7) and chronic subjects performed 12 wrist movements while was recorded using A variety features, or views, were decomposed alterations coordination. Main Results. Stroke subjects, on average, had higher co-contraction reduced muscle coupling when attempting open actuate thumb. Additionally, synergies the population relatively preserved, large spatial overlap composition matched synergies. Alterations synergy between digit extensors muscles thumb, well an increase flexor activity group. Average activations during revealed differences coordination, overactivation antagonist compensatory strategies. When first principal component strongly correlated upper-extremity Fugl Meyer sub-score participants R 2 0.86). Principal embeddings measures coordination alterations. Significance. These results demonstrate feasibility predicting through sleeve, could be leveraged improve research care.

Language: Английский

---

Proportional myoelectric control of a virtual bionic arm in participants with hemiparesis, muscle spasticity, and impaired range of motion

Journal of NeuroEngineering and Rehabilitation, Journal Year: 2024, Volume and Issue: 21(1)

Published: Dec. 21, 2024

Abstract Background This research aims to improve the control of assistive devices for individuals with hemiparesis after stroke by providing intuitive and proportional motor control. Stroke is leading cause disability in United States, 80% stroke-related coming form hemiparesis, presented as weakness or paresis on half body. Current exoskeletonscontrolled via electromyography do not allow fine force regulation. strategies provide only binary, all-or-nothing based a linear threshold muscle activity. Methods In this study, we demonstrate ability participants finely regulate their activity proportionally position virtual bionic arm. Ten survivors ten healthy, aged-matched controls completed target-touching task We compared signal-to-noise ratio (SNR) recorded (EMG) signals used train algorithms performance using root mean square error, percent time target, maximum hold within target window. Additionally, looked at correlation between EMG SNR, performance, clinical spasticity scores. Results All were able achieve despite limited no physical movement (i.e., modified Ashworth scale 3). SNR was significantly lower paretic arm than contralateral nonparetic healthy arms, but similar across conditions hand grasp. contrast, extension worse arms arms. The participants’ age, since stroke, rate, history botulinum toxin injections had impact Conclusions It possible from survivor’s Importantly, information regulating output still present activity, even extreme cases where there visible movement. Future work should incorporate into upper-limb exoskeletons enhance dexterity survivors.

Language: Английский

---

Recent Trends in Soft Robotics for Assistive Technologies

Advances in medical technologies and clinical practice book series, Journal Year: 2024, Volume and Issue: unknown, P. 119 - 144

Published: Nov. 29, 2024

Wearable healthcare devices have transformed personal health management through continuous monitoring. Soft robotics, with its emphasis on compliant and adaptable systems, offers a new paradigm for human-machine interaction. This emerging field holds immense potential developing wearable that seamlessly integrate the human body. By employing soft robotic technologies, we can create innovative tools assessing physical ergonomics informing lifestyle medical interventions. integration of robotics monitoring promises to revolutionize preventive personalized medicine. work provides comprehensive overview applications aging population mobility impaired. examining various techniques, aim establish solid foundation understanding current landscape this field.

Language: Английский

---