The Spine Journal, Journal Year: 2023, Volume and Issue: 23(7), P. 929 - 944
Published: March 7, 2023
Language: Английский
Nature, Journal Year: 2022, Volume and Issue: 610(7931), P. 277 - 282
Published: Oct. 12, 2022
Abstract Personalized exoskeleton assistance provides users with the largest improvements in walking speed 1 and energy economy 2–4 but requires lengthy tests under unnatural laboratory conditions. Here we show that optimization can be performed rapidly real-world We designed a portable ankle based on insights from versatile testbed. developed data-driven method for optimizing outdoors using wearable sensors found it was equally effective as methods, identified optimal parameters four times faster. data collected during many short bouts of at varying speeds. Assistance optimized one hour naturalistic public setting increased self-selected by 9 ± 4% reduced used to travel given distance 17 5% compared normal shoes. This metabolic consumption 23 8% when participants walked treadmill standard 1.5 m s −1 . Human movements encode information personalize assistive devices enhance performance.
Language: Английский
Citations
143
Sensors, Journal Year: 2024, Volume and Issue: 24(4), P. 1058 - 1058
Published: Feb. 6, 2024
E-textiles have emerged as a fast-growing area in wearable technology for sports and fitness due to the soft comfortable nature of textile materials capability smart functionality be integrated into familiar clothing. This review paper presents roles technologies sport monitoring movement biosignals used assess performance, reduce injury risk, motivate training/exercise. The drivers research e-textiles are discussed after reviewing existing non-textile textile-based commercial products. Different sensing components/materials (e.g., inertial measurement units, electrodes biosignals, piezoresistive sensors), manufacturing processes, their applications published literature were reviewed discussed. Finally, current challenges achieve practical at scale future perspectives development.
Language: Английский
Citations
17
Applied Ergonomics, Journal Year: 2021, Volume and Issue: 98, P. 103574 - 103574
Published: Sept. 20, 2021
To determine the applications of machine learning (ML) techniques used for primary prevention work-related musculoskeletal disorders (WMSDs), a scoping review was conducted using seven literature databases. Of 4,639 initial results, 130 research studies were deemed relevant inclusion. Studies reviewed and classified as contribution to one six steps within WMSD framework by van der Beek et al. (2017). ML provided greatest contributions development interventions (48 studies), followed risk factor identification (33 underlying mechanisms (29 incidence WMSDs (14 evaluation (6 implementation effective (0 studies). Nearly quarter (23.8%) all included published in 2020. These findings provide insight into breadth can help identify areas future development.
Language: Английский
Citations
80
Applied Ergonomics, Journal Year: 2021, Volume and Issue: 99, P. 103619 - 103619
Published: Nov. 2, 2021
Language: Английский
Citations
68
Diagnostics, Journal Year: 2022, Volume and Issue: 12(12), P. 3048 - 3048
Published: Dec. 5, 2022
Physical ergonomics has established itself as a valid strategy for monitoring potential disorders related, example, to working activities. Recently, in the field of physical ergonomics, several studies have also shown improvement experimental methods ergonomic analysis, through combined use artificial intelligence, and wearable sensors. In this regard, review intends provide first account investigations carried out using these methods, considering period up 2021. The method that combines information obtained on worker sensors (IMU, accelerometer, gyroscope, etc.) or biopotential (EMG, EEG, EKG/ECG), with analysis intelligence systems (machine learning deep learning), offers interesting perspectives from both diagnostic, prognostic, preventive points view. particular, signals, recognition categorization postural biomechanical load worker, can be processed formulate algorithms applications (especially respect musculoskeletal disorders), high statistical power. For Ergonomics, but Occupational Medicine, improve knowledge limits human organism, helping definition sustainability thresholds, design environments, tools, work organization. growth prospects research area are refinement procedures detection processing signals; expansion study assisted (assistive robots, exoskeletons), categories workers suffering pathologies disabilities; well development risk assessment exceed those currently used precision agility.
Language: Английский
Citations
40
Biosensors, Journal Year: 2024, Volume and Issue: 14(11), P. 560 - 560
Published: Nov. 18, 2024
Wearable biosensors are a fast-evolving topic at the intersection of healthcare, technology, and personalized medicine. These sensors, which frequently integrated into clothes accessories or directly applied to skin, provide continuous, real-time monitoring physiological biochemical parameters such as heart rate, glucose levels, hydration status. Recent breakthroughs in downsizing, materials science, wireless communication have greatly improved functionality, comfort, accessibility wearable biosensors. This review examines present status biosensor with an emphasis on advances sensor design, fabrication techniques, data analysis algorithms. We analyze diverse applications clinical diagnostics, chronic illness management, fitness tracking, emphasizing their capacity transform health facilitate early disease diagnosis. Additionally, this seeks shed light future healthcare wellness by summarizing existing trends new advancements.
Language: Английский
Citations
11
Applied Sciences, Journal Year: 2024, Volume and Issue: 14(9), P. 3563 - 3563
Published: April 23, 2024
Back-Support Industrial Exoskeletons (BSIEs) can be beneficial in reducing the risk of injury due to overexertion during trunk flexion tasks. Most real-world tasks include complex body movements, leading mixed outcomes that necessitate field-based methods for detecting overall physical demands. Monitoring fatigue this regard ensure benefits BSIEs are translated real world. Our experiment included 14 participants, who performed 30 repetitions 45° trunk-flexion while assisted by a BSIE, first without and then at medium-high back (7/10 Borg scale). We extracted 135 features from recorded muscle activity, motion, whole-body stability across bending, transition, retraction portions each cycle. Four classification algorithms, namely Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), XGBoost (XGB), were implemented assess prediction. XGB (Accuracy: 86.1%, Recall: 86%, Specificity: 86.3%) was effective classifying with data obtained single EMG sensor located on lower (erector spinae) muscle. Meanwhile, measures showed high predictability both RF (92.9%, 91.9%, 94.1%) (93.5, 94.1%, 93.1%). Findings demonstrate success force plates, when replaced pressure insoles, they facilitate detection BSIE-assisted
Language: Английский
Citations
8
Sensors, Journal Year: 2021, Volume and Issue: 21(8), P. 2593 - 2593
Published: April 7, 2021
Many activities may elicit a biomechanical overload. Among these, lifting loads can cause work-related musculoskeletal disorders. Aspiring to improve risk prevention, the National Institute for Occupational Safety and Health (NIOSH) established methodology assessing actions by means of quantitative method based on intensity, duration, frequency other geometrical characteristics lifting. In this paper, we explored machine learning (ML) feasibility classify according revised NIOSH equation. Acceleration angular velocity signals were collected using wearable sensor during tasks performed seven subjects further segmented extract time-domain features: root mean square, minimum, maximum standard deviation. The features fed several ML algorithms. Interesting results obtained in terms evaluation metrics binary risk/no-risk classification; specifically, tree-based algorithms reached accuracies greater than 90% Area under Receiver operating curve curves 0.9. conclusion, study indicates proposed combination represents valuable approach automatically work two groups. These data confirm potential assess which are exposed their activity.
Language: Английский
Citations
52
Sensors, Journal Year: 2022, Volume and Issue: 22(7), P. 2507 - 2507
Published: March 25, 2022
In biomechanics, joint kinetics has an important role in evaluating the mechanical load of and understanding its motor function. Although optical motion capture (OMC) system mainly been used to evaluate combination with force plates, inertial (IMC) systems have recently emerging kinetic analysis due their wearability ubiquitous measurement capability. this regard, numerous studies conducted estimate using IMC-based wearable systems. However, these not comprehensively addressed yet. Thus, aim review is explore methodology current on estimating variables by means IMC system. From a systematic search literature, 48 were selected. This paper summarizes content selected literature terms (i) study characteristics, (ii) methodologies, (iii) results. The estimation methods are categorized into two types: inverse dynamics-based method machine learning-based method. While presented different characteristics variables, it was demonstrated that both could be applied good performance for joints daily activities.
Language: Английский
Citations
30
Archives of Computational Methods in Engineering, Journal Year: 2024, Volume and Issue: unknown
Published: May 4, 2024
Abstract In the past three decades, biomedical engineering has emerged as a significant and rapidly growing field across various disciplines. From an perspective, biomaterials, biomechanics, biofabrication play pivotal roles in interacting with targeted living biological systems for diverse therapeutic purposes. this context, silico modelling stands out effective efficient alternative investigating complex interactive responses vivo. This paper offers comprehensive review of swiftly expanding machine learning (ML) techniques, empowering to develop cutting-edge treatments addressing healthcare challenges. The categorically outlines different types ML algorithms. It proceeds by first assessing their applications covering such aspects data mining/processing, digital twins, data-driven design. Subsequently, approaches are scrutinised studies on mono-/multi-scale biomechanics mechanobiology. Finally, extends techniques bioprinting biomanufacturing, encompassing design optimisation situ monitoring. Furthermore, presents typical ML-based implantable devices, including tissue scaffolds, orthopaedic implants, arterial stents. challenges perspectives illuminated, providing insights academia, industry, professionals further apply strategies future studies.
Language: Английский
Citations
5