Optimal Sensor Placement and Multimodal Fusion for Human Activity Recognition in Agricultural Tasks DOI Creative Commons
Lefteris Benos, Dimitrios Tsaopoulos, Aristotelis C. Tagarakis

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(18), P. 8520 - 8520

Published: Sept. 21, 2024

This study examines the impact of sensor placement and multimodal fusion on performance a Long Short-Term Memory (LSTM)-based model for human activity classification taking place in an agricultural harvesting scenario involving human-robot collaboration. Data were collected from twenty participants performing six distinct activities using five wearable inertial measurement units placed at various anatomical locations. The signals sensors first processed to eliminate noise then input into LSTM neural network recognizing features sequential time-dependent data. Results indicated that chest-mounted provided highest F1-score 0.939, representing superior over other placements combinations them. Moreover, magnetometer surpassed accelerometer gyroscope, highlighting its ability capture crucial orientation motion data related investigated activities. However, accelerometer, showed benefit integrating different types improve accuracy. emphasizes effectiveness strategic optimizing recognition, thus minimizing requirements computational expenses, resulting cost-optimal system configuration. Overall, this research contributes development more intelligent, safe, cost-effective adaptive synergistic systems can be integrated variety applications.

Language: Английский

Exploring Human–AI Dynamics in Enhancing Workplace Health and Safety: A Narrative Review DOI Open Access
Jakub Fiegler-Rudol, Karolina Lau,

Alina Mroczek

et al.

International Journal of Environmental Research and Public Health, Journal Year: 2025, Volume and Issue: 22(2), P. 199 - 199

Published: Jan. 30, 2025

Background: Artificial intelligence (AI) is revolutionizing occupational health and safety (OHS) by addressing workplace hazards enhancing employee well-being. This review explores the broader context of increasing automation digitalization, focusing on role human–AI interaction in improving health, safety, productivity while considering associated challenges. Methods: A narrative methodology was employed, involving a comprehensive literature search PubMed, Embase, Scopus for studies published within last 25 years. After screening relevance eligibility, total 52 articles were included final analysis. These publications examined various AI applications OHS, such as wearable technologies, predictive analytics, ergonomic tools, with focus their contributions limitations. Results: Key findings demonstrate that enhances hazard detection, enables real-time monitoring, improves training through immersive simulations, significantly contributing to safer more efficient workplaces. However, challenges data privacy concerns, algorithmic biases, reduced worker autonomy identified significant barriers adoption OHS. Conclusions: holds great promise transforming OHS practices, but its integration requires ethical frameworks human-centric collaboration models ensure transparency, equity, empowerment. Addressing these will allow workplaces harness full potential creating safer, healthier, sustainable environments.

Language: Английский

Citations

0

Computer vision syndrome: a comprehensive literature review DOI Creative Commons
Fares Kahal,

Ahmad Al Darra,

André Torbey

et al.

Future Science OA, Journal Year: 2025, Volume and Issue: 11(1)

Published: March 8, 2025

Computer Vision Syndrome is a growing health concern in the digital age, with reported prevalence of 69.0%. It caused by screen-related, environmental, ergonomic, and physiological factors, affecting diverse demographics. The COVID-19 pandemic significantly amplified CVS due to increased screen time for remote work, online learning, social media use, studies reporting symptoms up 74% individuals. Unique visual challenges from screens, including reduced clarity glare, exacerbate like dry eyes discomfort, especially those uncorrected vision. Understanding crucial mitigating its impact through effective prevention management strategies. This study explores causes, diagnosis, management, strategies synthesizing recent findings optometry, occupational health, ergonomics. also highlights emerging trends such as AI, wearables, augmented reality while providing practical A narrative review literature 2014 2024 was conducted, focusing on PubMed-indexed, peer-reviewed articles, meta-analyses systematic reviews, priority given recent, highly cited studies.

Language: Английский

Citations

0

Muscle Strength Assistance of a Shape Memory Alloy Exoskeleton During Lifting and Lowering Tasks DOI

Kwang Hee Lee,

Mi Yu, Young Min Kim

et al.

International Journal of Precision Engineering and Manufacturing, Journal Year: 2025, Volume and Issue: unknown

Published: March 11, 2025

Language: Английский

Citations

0

Neurosciences and Sports Rehabilitation in ACLR: A Narrative Review on Winning Alliance Strategies and Connecting the Dots DOI Creative Commons
Rocco Salvatore Calabrò, Andrea Calderone,

Nicola Fiorente

et al.

Journal of Functional Morphology and Kinesiology, Journal Year: 2025, Volume and Issue: 10(2), P. 119 - 119

Published: April 2, 2025

This narrative review explores the significant evolution of sports rehabilitation, tracing its trajectory from basic exercise therapies early 20th century to advanced, neuroplasticity-driven approaches 21st century, with a specific focus on anterior cruciate ligament reconstruction (ACLR). The primary aim is understand how neuroplasticity, motor control, and sensorimotor retraining can optimize recovery, reduce reinjury risk, enhance long-term athletic performance, synthesize current rehabilitation strategies that integrate innovative technologies, such as robotics, virtual reality (VR), biofeedback systems, address neurocognitive deficits contribute alarmingly high rates (9–29%) observed in young athletes post-ACLR. These include impaired proprioception, psychological factors like fear reinjury. methodology employed involves peer-reviewed literature databases including PubMed, Scopus, Web Science. synthesis findings underscores importance holistic approaches, targeted proprioceptive exercises, dual-task drills, immersive VR training, enhancing integration, decision-making, athlete confidence. Furthermore, this highlights critical need for monitoring interdisciplinary collaboration between neuroscientists, physiotherapists, engineers refine protocols ensure sustained recovery. By leveraging neuroplasticity advanced field shift purely physical restoration comprehensive recovery models significantly risks performance.

Language: Английский

Citations

0

ERGONOMİ BİLİMİ İLE YAPAY ZEKÂ ARASINDAKİ İLİŞKİ: BİBLİYOMETRİK BİR İNCELEME DOI Open Access
Sevil ÇIRAKOĞLU KELLECİ, Abdullah Ragıp Ersöz

Ergonomi, Journal Year: 2025, Volume and Issue: 8(1), P. 45 - 57

Published: April 15, 2025

Yapay zekâ, ergonomi uygulamalarını derinden etkileyen ve en yaygın kullanılan teknolojilerden biri olarak öne çıkmaktadır. Bu çalışma, endüstriyel dönüşümün merkezinde yer alan yapay zekâ ile bilimi arasındaki ilişkiyi bibliyometrik analiz yoluyla inceleyerek, alanında gelişmiş teknolojilerin entegrasyonu için mevcut eğilimleri, akademik işbirliklerini araştırma önceliklerini ortaya koymayı amaçlamaktadır. Scopus veri tabanında "Ergonomics" "Artificial Intelligence" anahtar kelimeleriyle elde edilen, 1977-2024 yılları arasında yayınlanmış 267 makale, yöntem kullanılarak incelenmiştir. Analiz kapsamında edilen veriler, R Studio yazılımındaki bibliometrix kütüphanesi değerlendirilmiştir. Bulgulara göre, yıllık %8,63 büyüme oranıyla düzenli artış gösteren yayınlar, ortalama 21,18 atıf yüksek etki düzeyine sahiptir. En sık kelimeler (230 kez) (225 olmuş, çalışmalarda insan merkezli yaklaşımlar teknolojik çözümler ön plana çıkmıştır. Alana fazla katkı sağlayan ülke 200 yayınla ABD olurken, Birleşik Krallık Çin de önemli katkılarda bulunmuştur. Ergonomics dergisi 17 makale yayına sahip kaynak

Citations

0

Wearable sensors for classification of load-handling tasks with machine learning algorithms in occupational safety and health: a systematic literature review DOI Creative Commons
Markus Peters, Wolfgang Potthast, Sascha Wischniewski

et al.

Ergonomics, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 21

Published: April 17, 2025

Ergonomic assessments are critical to preventing work-related musculoskeletal disorders. The integration of machine learning with wearable sensor technology offers new approaches risk assessment by capturing external forces and non-ergonomic working conditions. We conducted a systematic literature search, reviewing 851 studies from PubMed, Web Science Embase, included 15 in our analysis. This review summarises critically discusses these studies, which focus on posture classification, activity duration weight estimation load handling tasks. Although the results promising, current research covers only few aspects, limited emphasis measurement forces. Furthermore, many faced fundamental issues such as small sample sizes access data algorithms. Future advances this area could greatly benefit sharing datasets algorithms, thereby increasing comparability robustness findings.

Language: Английский

Citations

0

Wearables and Sustainable Development: Exploring Future Implications for the Green Jobs and Green Labor Market DOI Open Access
Adam Sulich, Łukasz Jarosław Kozar

Procedia Computer Science, Journal Year: 2023, Volume and Issue: 225, P. 279 - 288

Published: Jan. 1, 2023

This article analyzes the subject of wearables and Sustainable Development (SD) in scientific literature is an attempt to present possible implications for Green Jobs (GJs) green labor market. There a growing trend toward purchasing new wearable devices among consumers, which are more interested SD. These combine functions many other using smart technology connectivity. They can communicate with or equipment, such as vehicles, machines, buildings. Wearables have wide range applications. allow monitoring vital functions, behavior, display information, improve communication, help plan daily activities, aid decision-making. Therefore, these becoming increasingly important life business. Wearable uses Internet Things (IoT) connectivity synchronize data between devices. From perspective, it interesting explore how related SD transitioning economy areas. The main goal this demonstrate relevance literature. Additionally, paper aims outline future GJs, self-employment, competencies, method adopted study was bibliometric review conducted Scopus database VOSviewer software support. results presented form maps keyword tables. study's suggest that been rarely addressed context managing employees workplace from perspective.

Language: Английский

Citations

9

Digital and Virtual Technologies for Work-Related Biomechanical Risk Assessment: A Scoping Review DOI Creative Commons
Paulo C. Anacleto Filho, Ana Colim, Cristiano Jesus

et al.

Safety, Journal Year: 2024, Volume and Issue: 10(3), P. 79 - 79

Published: Sept. 12, 2024

The field of ergonomics has been significantly shaped by the advent evolving technologies linked to new industrial paradigms, often referred as Industry 4.0 (I4.0) and, more recently, 5.0 (I5.0). Consequently, several studies have reviewed integration advanced for improved in different industry sectors. However, evaluate specific technologies, such extended reality (XR), wearables, artificial intelligence (AI), and collaborative robot (cobot), their advantages problems. In this sense, there is a lack research exploring state art I4.0 I5.0 virtual digital evaluating work-related biomechanical risks. Addressing gap, study presents comprehensive review 24 commercial tools 10 academic focusing on risk assessment using technologies. analysis reveals that AI human modelling (DHM) are most commonly utilised tools, followed motion capture (MoCap) (VR). Discrepancies were found between studies. acknowledges limitations, including potential biases sample selection search methodology. Future directions include enhancing transparency tool validation processes, examining broader impact emerging ergonomics, considering human-centred design principles technology integration. These findings contribute deeper understanding landscape assessment.

Language: Английский

Citations

3

sEMG Spectral Analysis and Machine Learning Algorithms Are Able to Discriminate Biomechanical Risk Classes Associated with Manual Material Liftings DOI Creative Commons
Leandro Donisi, Deborah Jacob, Lorena Guerrini

et al.

Bioengineering, Journal Year: 2023, Volume and Issue: 10(9), P. 1103 - 1103

Published: Sept. 20, 2023

Manual material handling and load lifting are activities that can cause work-related musculoskeletal disorders. For this reason, the National Institute for Occupational Safety Health proposed an equation depending on following parameters: intensity, duration, frequency, geometric characteristics associated with lifting. In paper, we explore feasibility of several Machine Learning (ML) algorithms, fed frequency-domain features extracted from electromyographic (EMG) signals back muscles, to discriminate biomechanical risk classes defined by Revised NIOSH Lifting Equation. The EMG multifidus erector spinae muscles were acquired means a wearable device surface then segmented extract relating Total Power Spectrum signal. These ML algorithms assess their prediction power. produced interesting results in classification task, Support Vector algorithm outperforming others accuracy Area under Receiver Operating Characteristic Curve values up 0.985. Moreover, correlation between muscular fatigue risky was found. showed methodology-based sensors artificial intelligence-to predict A future investigation enriched study population additional scenarios could confirm potential methodology its applicability field occupational ergonomics.

Language: Английский

Citations

8

An overview on human-centred technologies, measurements and optimisation in assembly systems DOI
Rim Slama,

Ilhem Slama,

Houda Tlahig

et al.

International Journal of Production Research, Journal Year: 2023, Volume and Issue: 62(14), P. 5336 - 5358

Published: Nov. 30, 2023

This paper offers an in-depth examination of the ergonomics human-centred assembly systems in Industry 4.0, where manual tasks remain essential. The use advanced technologies such as motion capture (MOCAP) and virtual reality (VR) is analysed ways to enhance system efficiency improve worker well-being. highlights importance optimising performance while considering both economic human factors. Metrics assess ergonomic risk productivity are discussed based on technologies, existing operational research models explored analyse how factors could be considered performance. Additionally, explores potential future directions they play a role 4.0.

Language: Английский

Citations

8