Compensation Method for Missing and Misidentified Skeletons in Nursing Care Action Assessment by Improving Spatial Temporal Graph Convolutional Networks

Bioengineering, Год журнала: 2024, Номер 11(2), С. 127 - 127

Опубликована: Янв. 29, 2024

With the increasing aging population, nursing care providers have been facing a substantial risk of work-related musculoskeletal disorders (WMSDs). Visual-based pose estimation methods, like OpenPose, are commonly used for ergonomic posture assessment. However, these methods face difficulty when identifying overlapping and interactive tasks, resulting in missing misidentified skeletons. To address this, we propose skeleton compensation method using improved spatial temporal graph convolutional networks (ST-GCN), which integrates kinematic chain action features to assess integrity compensate it. The results verified effectiveness our approach optimizing skeletal loss misidentification leading accuracy calculating both joint angles REBA scores. Moreover, comparative analysis against other demonstrated superior performance approach, achieving an 87.34% score. Collectively, might hold promising potential tasks.

Язык: Английский

---

Lumbo-Pelvic Rhythm Monitoring Using Wearable Technology with Sensory Biofeedback: A Systematic Review

Healthcare, Год журнала: 2024, Номер 12(7), С. 758 - 758

Опубликована: Март 30, 2024

As an essential lower-back movement pattern, lumbo-pelvic rhythm (LPR) during forward trunk flexion and backward return has been investigated on a large scale. It suggested that abnormalities in coordination are related to the risk of developing low back disorders. However, considerable differences approaches used monitor LPR make it challenging integrate findings from those investigations for future research. Therefore, aim this systematic review was summarize use wearable technology kinematic measurement with sensory biofeedback monitoring by assessing these technologies’ specific capabilities capacities exploring their practical viability based sensor outcomes. The developed following PRISMA guidelines, bias analyzed using PREDro STROBE scales. PubMed, Web Science, Scopus, IEEEXPLORE databases were searched relevant studies, initially returning total 528 articles. Finally, we included eight articles featuring devices audio or vibration biofeedback. Differences protocols limitations also observed. This novel study presents tracking motion-mediated purpose correcting lower posture. More research is needed determine long-term effectiveness devices, as well most appropriate corresponding methodologies.

Язык: Английский

---

Large Language Models for Wearable Sensor-Based Human Activity Recognition, Health Monitoring, and Behavioral Modeling: A Survey of Early Trends, Datasets, and Challenges

Sensors, Год журнала: 2024, Номер 24(15), С. 5045 - 5045

Опубликована: Авг. 4, 2024

The proliferation of wearable technology enables the generation vast amounts sensor data, offering significant opportunities for advancements in health monitoring, activity recognition, and personalized medicine. However, complexity volume these data present substantial challenges modeling analysis, which have been addressed with approaches spanning time series to deep learning techniques. latest frontier this domain is adoption large language models (LLMs), such as GPT-4 Llama, modeling, understanding, human behavior monitoring through lens data. This survey explores current trends applying LLMs sensor-based recognition modeling. We discuss nature capabilities limitations them, their integration traditional machine also identify key challenges, including quality, computational requirements, interpretability, privacy concerns. By examining case studies successful applications, we highlight potential enhancing analysis interpretation Finally, propose future directions research, emphasizing need improved preprocessing techniques, more efficient scalable models, interdisciplinary collaboration. aims provide a comprehensive overview intersection between LLMs, insights into state prospects emerging field.

Язык: Английский

---

A human-centric system combining smartwatch and LiDAR data to assess the risk of musculoskeletal disorders and improve ergonomics of Industry 5.0 manufacturing workers

Computers in Industry, Год журнала: 2023, Номер 155, С. 104042 - 104042

Опубликована: Ноя. 24, 2023

Язык: Английский

---

Wearables for Monitoring and Postural Feedback in the Work Context: A Scoping Review

Sensors, Год журнала: 2024, Номер 24(4), С. 1341 - 1341

Опубликована: Фев. 19, 2024

Wearables offer a promising solution for simultaneous posture monitoring and/or corrective feedback. The main objective was to identify, synthesise, and characterise the wearables used in workplace monitor postural feedback workers. PRISMA-ScR guidelines were followed. Studies included between 1 January 2000 22 March 2023 Spanish, French, English, Portuguese without geographical restriction. databases selected research PubMed®, Web of Science®, Scopus®, Google Scholar®. Qualitative studies, theses, reviews, meta-analyses excluded. Twelve studies included, involving total 304 workers, mostly health professionals (n = 8). remaining covered workers industry 2), construction 1), welders 1). For assessment purposes, most one 5) or two sensors characterised as accelerometers 7), sixaxial 2) nonaxialinertial measurement units 3). common source sensor itself 6) smartphones 4). Haptic prevalent 6), followed by auditory visual Most employed prototype emphasising kinematic variables human movement. Healthcare primary focus study along with haptic that proved be effective method correcting during work activities.

Язык: Английский

---

Combining inertial-based ergonomic assessment with biofeedback for posture correction: A narrative review

Computers & Industrial Engineering, Год журнала: 2024, Номер 190, С. 110037 - 110037

Опубликована: Март 12, 2024

Work-related musculoskeletal disorders (WRMSDs) are the most reported work-related health problem in European Union, representing an economic burden equivalent to 2% of its gross domestic product. Awkward postures one main risk factors. Several postural assessment tools try identify ergonomic exposure factors for evaluating WRMSD risk, yet these commonly based on observation. Replacing observations with objective measurements can bring more accuracy and reproducibility this analysis, hence a direct measurement approach is desired. This review looks two-fold solutions, able not only monitor workers' posture using inertial sensors but also return that information user, biofeedback loop. It presents systems assessment, regarding methods, sensors' actuators' characteristics, validation protocols. In particular, advances previous manuscripts by exploring literature different strategies ways encode meaningful cues, i.e., deliver intuitive guidance so user becomes aware changes into neutral posture. The combination vibrotactile motors stood out, due effectiveness reducing risk. Directional feedback guide users' segments individually was found be promising strategy, although still limited. results reviewed pointed out relevant practices, potentialities, limitations existing allowing identification future challenges.

Язык: Английский

---

A Rapid Review on the Effectiveness and Use of Wearable Biofeedback Motion Capture Systems in Ergonomics to Mitigate Adverse Postures and Movements of the Upper Body

Sensors, Год журнала: 2024, Номер 24(11), С. 3345 - 3345

Опубликована: Май 23, 2024

Work-related diseases and disorders remain a significant global health concern, necessitating multifaceted measures for mitigation. One potential measure is work technique training utilizing augmented feedback through wearable motion capture systems. However, there exists research gap regarding its current effectiveness in both real environments controlled settings, as well ability to reduce postural exposure retention effects over short, medium, long durations. A rapid review was conducted, two databases three previous literature reviews identify relevant studies published within the last twenty years, including recent up end of 2023. Sixteen met inclusion criteria, which 14 were high or moderate quality. These summarized descriptively, strength evidence assessed. Among included studies, six rated quality, while eight considered Notably, reporting participation rates, blinding assessors, a-priori power calculations infrequently performed. Four conducted environments, ten settings. Vibration most common type utilized (n = 9), followed by auditory 7) visual 1). All employed corrective initiated system. In from systems ranged strong no evidence, depending on time elapsed after administration. Conversely, very limited evidence. Future reach needs are identified discussed.

Язык: Английский

---

What have we learned about risk assessment and interventions to prevent work-related musculoskeletal disorders and support work participation?

Scandinavian Journal of Work Environment & Health, Год журнала: 2024, Номер 50(5), С. 317 - 328

Опубликована: Май 29, 2024

The Scandinavian Journal of Work, Environment & Health (SJWEH) was established half a century ago. This paper provides an overview research on musculoskeletal disorders (MSD) published over these 50 years. Three themes are described: risk assessment, interventions to prevent work-related MSD, and support work participation. Finally, implications for future highlighted.

Язык: Английский

---

Reliability and Accuracy of Standard Reference Procedures for Measurements of Trunk and Arm Postures in Ergonomics

Bioengineering, Год журнала: 2025, Номер 12(1), С. 50 - 50

Опубликована: Янв. 9, 2025

Adequate reference procedures for obtaining the zero-angle position are important precise and accurate posture measurements, but few studies have systematically investigated these. A limited number of previous suggest differences in accuracy between procedures, with some causing an underestimation true arm elevation angle when sensors taped to skin. The reliability commonly used measurement trunk is also not well explored, alternative may improve precision. Based on this identified gap, study evaluated test–retest N-position (I-pose), i.e., standard procedure recording postures, compared it two new procedures. Additionally, measuring angles was one procedure. total 40 participants (22 women 18 men) aged 26–70 years performed a laboratory setting. Postures were recorded using smart workwear system equipped inertial units (IMUs) embedded pockets within workwear. For posture, showed slight lack reliability, while demonstrated better reliability. N-position, which does include lateral inclination, resulted substantial approximately 15°, novel finding. In contrast, involving inclination closely matched targeted reference, difference less than 2°. This underscores importance selecting appropriate ensure measurements.

Язык: Английский

---

A fatigue failure framework for the assessment of highly variable low back loading using inertial motion capture – a case study

Ergonomics, Год журнала: 2025, Номер unknown, С. 1 - 17

Опубликована: Фев. 16, 2025

Workers in manufacturing settings experience highly variable musculoskeletal loading, which current risk assessment methods often fail to fully capture. This study evaluated a Fatigue Failure-Based framework for estimating continuous lumbar loading from occupational loads. Worker movements and postures were recorded using Inertial Motion Capture technologies, L5/S1 joint history was estimated through inverse dynamics. Stress cycles analysed Rainflow analysis, adjusted with Goodman's method, summed Palmgren-Miner rule estimate cumulative damage. The tested live industrial eight automotive workers across 108 trials. Logistic regression models demonstrated significant correlations between damage estimates self-reported low-back pain (OR = 2.16, 95% CI: 1.30, 3.57). provides novel method analysing exposure ergonomics, offering starting point future research potential applications assessing low back injury risks similar settings.

Язык: Английский

---