Exoskeletons in Intermittent Bending Tasks: Assessing Muscle Demands, Endurance, and User Perspectives

Human Factors The Journal of the Human Factors and Ergonomics Society, Год журнала: 2025, Номер unknown

Опубликована: Март 13, 2025

Objective We investigated effects of a Back-support industrial exoskeleton (BSIE) across intermittently performed unloaded trunk bending task cycles. Background Industrial tasks are often in the form cycles with varying activities and rest breaks after each cycle. Investigating BSIEs during such intermittent is crucial to understand translation their benefits real-world environments. Method Twelve participants ∼709 (sustained bending, retraction, standing still, relaxation activities) with/without BSIE (E/NE) 45° asymmetry (S/A) towards left until fatigue. Evaluated measures included muscle activity (LES)/right (RES) erector spinae (LBF)/right (RBF) biceps femoris muscles, endurance, user perspectives. Temporal fatigue were examined by categorizing based on perceived exertion level Borg scale. Results reduced low-back (LES, RES), leg (LBF, RBF) mean amplitude ∼ 18–24% ∼10–17% respectively. Benefits ∼11–15% at medium versus low Overall, led 50% more completed was favorably rated reducing physical demands, most especially sustained portion Conclusion Using can not only provide demands but also delay region increase endurance enabling wearers perform Application Findings from this study may be beneficial practitioners for setting guidelines implementation tasks.

Язык: Английский

---

Machine Learning-Based Fatigue Level Prediction for Exoskeleton-Assisted Trunk Flexion Tasks Using Wearable Sensors

Applied Sciences, Год журнала: 2024, Номер 14(11), С. 4563 - 4563

Опубликована: Май 26, 2024

Monitoring physical demands during task execution with exoskeletons can be instrumental in understanding their suitability for industrial tasks. This study aimed at developing a fatigue level prediction model Back-Support Industrial Exoskeletons (BSIEs) using wearable sensors. Fourteen participants performed set of intermittent trunk-flexion cycles consisting static, sustained, and dynamic activities, until they reached medium-high levels, while wearing BSIEs. Three classification algorithms, Support Vector Machine (SVM), Random Forest (RF), XGBoost (XGB), were implemented to predict perceived the back leg regions features from four wireless Electromyography (EMG) sensors integrated Inertial Measurement Units (IMUs). We examined best grouping sensor combinations by comparing performance. The findings showed performance binary 95% (2 EMG + IMU sensors) 82% (single sensor) accuracy, respectively. Tertiary required setups both measures perform 79% 67% efforts presented our article demonstrate feasibility an accessible detection system, which beneficial objective assessment, design selection, implementation BSIEs real-world scenarios.

Язык: Английский

---

IPTGNet: an adaptive multi-task recognition strategy for human locomotion modes

Computer Methods in Biomechanics & Biomedical Engineering, Год журнала: 2025, Номер unknown, С. 1 - 19

Опубликована: Апрель 4, 2025

Complexities in processing human motion are possessed by lower limb exoskeletons. In this paper, a multi-task recognition model, IPTGNet, is proposed for the locomotion modes. Temporal convolutional network and gated recurrent unit parallelly fused through dynamic tuning of hyperparameters using improved particle swarm optimization algorithm. The experimental results demonstrate that faster more stable convergence achieved IPTGNet with rate 99.47% standard deviation 0.42%. Furthermore, finite state machine utilized incorrection transition states. An innovative exoskeleton provided paper.

Язык: Английский

---

Training and Familiarization with Industrial Exoskeletons: A Review of Considerations, Protocols, and Approaches for Effective Implementation

Biomimetics, Год журнала: 2024, Номер 9(9), С. 520 - 520

Опубликована: Авг. 30, 2024

Effective training programs are essential for safely integrating exoskeletons (EXOs) in industrial workplaces. Since the effects of wearable systems depend highly upon their proper use, lack end-users may cause adverse on users. We reviewed articles that incorporated and familiarization protocols to train novices operation/use EXOs. Findings showed variation methods were implemented study participants EXO evaluation studies. Studies also indicate multiple (up four) sessions be needed novice wearers match movement patterns experts, can offer benefits enhancing motor learning novices. Biomechanical assessments ergonomic evaluations helpful developing EXO-specific by determining parameters (duration/number task difficulty). Future directions include development personalized approaches assessing user behavior/performance through integration emerging sensing technologies. Application simulators use data-driven customizing individuals, tasks, design provided along with a comprehensive framework. Discussed elements this article exoskeleton researchers familiarizing users EXOs prior evaluation, practitioners workforce.

Язык: Английский

---

Investigating Spatiotemporal Effects of Back-Support Exoskeletons Using Unloaded Cyclic Trunk Flexion–Extension Task Paradigm

Applied Sciences, Год журнала: 2024, Номер 14(13), С. 5564 - 5564

Опубликована: Июнь 26, 2024

Back-Support Industrial Exoskeletons (BSIEs) are designed to reduce muscle effort during repetitive tasks that involve trunk bending. We recruited twelve participants perform 30 cycles of 45° bending with/without the assistance BSIEs and postural asymmetry, first without any back fatigue, then at medium–high level perceived fatigue. To study benefits BSIEs, effects being in a fatigued state were assessed by comparing demands, kinematics, stability measures bending, retraction, their transition portions per cycle across conditions. Overall, caused minimal decrease lower-back activity (0–1.8%), increased demands retraction portion. A substantial leg was observed (10–18%). Asymmetry right-lower-back demands. Medium–high fatigue an increase (8–12%) retraction. The slower movements improved lowering maximum distance Center Pressure (COP) portion, as well mean velocity COP bending/retraction portions. This controlled demonstrated use cyclic flexion–extension paradigm outcomes can help with understanding temporal using on physiological measures, ultimately benefiting proper implementation.

Язык: Английский

---

Predicting Perceived Back Fatigue During Exoskeleton Supported Trunk Bending Tasks using Machine Learning

Proceedings of the Human Factors and Ergonomics Society Annual Meeting, Год журнала: 2024, Номер unknown

Опубликована: Авг. 10, 2024

Repetitive trunk flexion tasks performed over long durations can increase low-back injury risk, where Back Support Industrial Exoskeletons (BSIEs) be beneficial. While BSIEs have shown effectiveness in lab assessments, real-world outcomes variation based on task complexity, necessitating monitoring of physical demands. Fourteen participants repetitive BSIE-assisted forward bending and return, without fatigue then at medium-high fatigue. We recorded muscle activity thigh muscles using Electromyography (EMG) whole-body stability force plates. Classification algorithms, namely, Vector Machine (SVM), Random Forest (RF), XGBoost (XGB) were utilized to predict perceived back sensor data. Highest performance was observed with XGB algorithm data from a single EMG (Accuracy: 86.1%, Recall: 86%), plate (93.5, 94.1%). Outcomes our study helpful developing novel detection products, benefiting ergonomists properly implementing industrial scenarios.

Язык: Английский

---

A comprehensive review on lower limb exoskeleton: from origin to future expectations

International Journal on Interactive Design and Manufacturing (IJIDeM), Год журнала: 2024, Номер unknown

Опубликована: Сен. 19, 2024

Язык: Английский

---

Enhanced Predictive Modeling for Neuromuscular Disease Classification: A Comparative Assessment Using Gaussian Copula Denoising on Electromyographic Data

Bionatura journal :, Год журнала: 2024, Номер 1(4), С. 1 - 28

Опубликована: Ноя. 21, 2024

This study presents a methodology for automatically detecting neuromuscular diseases through prepro-cessing and classifying electromyography (EMG) signals. The presented approach integrates Gaussian Copula-based denoising techniques with feature extraction Random Forest classification. To assess the performance, performs comprehensive evaluation of various techniques, including Empirical Mode Decomposition (EMD), Variational (VMD), Wavelet Thresholding Denoising (WTD), Copula (GCD). also compares effectiveness several classification algorithms, such as (RF), Convolutional Neural Networks (CNN), Multilayer Perceptron (MLP), Decision Tree (DT). demonstrated exceptional per-formance, achieving an overall accuracy greater than 99% in distinguishing between healthy, myopathic, neuropathic EMG proposed method's is attributed to its noise reduction ca-pabilities, selection focusing on mean amplitude range, al-gorithm's adeptness data. study's findings underscore ac-curacy highlight potential revolutionize clinical diagnostics disorders, offering powerful tool more precise timely interventions. Keywords: Electromyography; Denoising; Classification; Neuromuscular Diseases; Copula; Forest; EMG; CNN.

Язык: Английский

---