Enhancing Security in CPS Industry 5.0 Using Lightweight MobileNetV3 with Adaptive Optimization Technique DOI Creative Commons
Mohammed A. Aleisa

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Ноя. 5, 2024

Abstract The Industrial Revolution of technologies such as the Internet Things (IIoT), cloud and Artificial Intelligence (AI) is breaking new frontiers in industrial process automation. Under Industry 5.0 revolution, AI based manufacturing units are more sophisticated Cyber-Physical Systems (CPS) that allow interaction people, objects machines at any given supply chain level. One key advantages this transformation it enables implementing individual-focused adaptable systems. However, interconnection poses various threats, especially phenomenon referred to attacks nature sometimes known distributed denial service (Ddos) attacks. In quest prevent cyber security challenges CPS 5.0, paper proposes a simple effective System on Deep Learning architecture. very first stage concerns data acquisition which entails careful monitoring collection raw from inbuilt sensors for real time performance. case, also processed further order clean data, handle missing values within set fix errors present set, improving it. next step involves Normalization feature extraction takes shape reducing into shapes acceptable by features; flow-based, time-based statistical features well deep using ResNet-101. To models, MobileNetV3 light weight models learning, predicted be utilized edge devices low resources through quantization pruning methods. This going reduce model or data. efficient local search method CTPOA applied adjustment parameters, optimization performance improvement model. Finally, safeguarded use AES encryption Discretionary Access Control policies.

Язык: Английский

Safety-efficiency integrated assembly: The next-stage adaptive task allocation and planning framework for human–robot collaboration DOI
Ruihan Zhao, Sichen Tao, Pengzhong Li

и другие.

Robotics and Computer-Integrated Manufacturing, Год журнала: 2025, Номер 94, С. 102942 - 102942

Опубликована: Янв. 7, 2025

Язык: Английский

Процитировано

2
Techniques and Models for Addressing Occupational Risk Using Fuzzy Logic, Neural Networks, Machine Learning, and Genetic Algorithms: A Review and Meta-Analysis DOI Creative Commons

Christos Mitrakas,

Alexandros Xanthopoulos, D.E. Koulouriotis

и другие.

Applied Sciences, Год журнала: 2025, Номер 15(4), С. 1909 - 1909

Опубликована: Фев. 12, 2025

This article aims to present a structured literature review that utilizes computational intelligence techniques, specifically fuzzy logic, neural networks, genetic algorithms, and machine learning, assist in the assessment of workplace risk from human factors. The general aim is highlight existing on subject, while specific goal research attempt answer questions emerge after classification literature, which are aspects have not previously been addressed. methodology for retrieving relevant articles involved keyword search Scopus database. results were filtered based selected criteria. spans 40-year period, 1984 2024. After filtering, 296 topic identified. Statistical analysis highlights systems as technique with highest representation (163 articles), followed by networks (81 learning algorithms ranking next (25 20 articles, respectively). main conclusions indicate primary sectors utilizing these techniques industry, transportation, construction, cross-sectoral models applicable multiple occupational fields. An additional finding reasoning behind researchers’ preference over primarily due availability or lack accident databases. also highlighted gaps requiring further research. continues numerous challenges, future trend suggests may be prominent.

Язык: Английский

Процитировано

1
Human Factors and Ergonomics in Industry 5.0—A Systematic Literature Review DOI Creative Commons
Maja Trstenjak, Andrea Benešová, Tihomir Opetuk

и другие.

Applied Sciences, Год журнала: 2025, Номер 15(4), С. 2123 - 2123

Опубликована: Фев. 17, 2025

Human-centricity, sustainability, and resilience are the core pillars of Industry 5.0 concept. The human-centric perspective emphasizes development socio-technical systems designed to enhance human health, safety, well-being while fostering sustainable practices that benefit society at large. This paper presents a systematic literature review identify key characteristics human-centered work environments. findings reveal growing interest in factors ergonomics, with notable gaps cognitive ergonomics requiring further attention. Beyond ensuring safety must address workload maintain productivity, efficiency, motivation, which closely tied company’s market performance. study provides valuable insights for both scientific industrial stakeholders, outlining principles requirements essential effective implementation systems.

Язык: Английский

Процитировано

0
Industrial application of multi-robot destructive disassembly line balancing under component non-disassemblability for multi-product scenarios DOI
Zeqiang Zhang, Lei Guo, Yu Zhang

и другие.

International Journal of Production Research, Год журнала: 2025, Номер unknown, С. 1 - 26

Опубликована: Апрель 10, 2025

Язык: Английский

Процитировано

0
Future Research Directions on Human-Centric Smart Manufacturing DOI
Baicun Wang, Pai Zheng, Song Ci

и другие.

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Uncertainties of supply chain transition and integration for Industry 5.0: a review of operations management literature DOI
Christopher Durugbo

International Journal of Production Research, Год журнала: 2025, Номер unknown, С. 1 - 23

Опубликована: Апрель 14, 2025

Язык: Английский

Процитировано

0
Digital and Virtual Technologies for Work-Related Biomechanical Risk Assessment: A Scoping Review DOI Creative Commons
Paulo C. Anacleto Filho, Ana Colim, Cristiano Jesus

и другие.

Safety, Год журнала: 2024, Номер 10(3), С. 79 - 79

Опубликована: Сен. 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.

Язык: Английский

Процитировано

3
Digital Transformation Towards Human-Centricity: A Systematic Literature Review DOI
Jelena Crnobrnja, Danijela Ćirić Lalić, David Romero

и другие.

IFIP advances in information and communication technology, Год журнала: 2024, Номер unknown, С. 89 - 102

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

1
Electromyographic analysis of bilateral upper trapezius muscles at different levels of work-pace among sewing machine operators DOI Creative Commons
Iqra Javed, Y. Nukman, Raja Ariffin Raja Ghazilla

и другие.

BMC Musculoskeletal Disorders, Год журнала: 2024, Номер 25(1)

Опубликована: Окт. 1, 2024

Язык: Английский

Процитировано

1
NLP-based ergonomics MSD risk root cause analysis and risk controls recommendation DOI Creative Commons
Pulkit Parikh, Julia Penfield, Richard Barker

и другие.

Ergonomics, Год журнала: 2024, Номер unknown, С. 1 - 13

Опубликована: Авг. 27, 2024

An ergonomics assessment of the physical risk factors in workplace is instrumental predicting and preventing musculoskeletal disorders (MSDs). Using Artificial Intelligence (AI) has become increasingly popular for assessments because time savings improved accuracy. However, most effort this area starts ends with producing scores, without providing guidance to reduce risk. This paper proposes a holistic job improvement process that performs automatic root cause analysis control recommendations reducing MSD We apply deep learning-based Natural Language Processing (NLP) techniques such as Part Speech (PoS) tagging dependency parsing on textual descriptions actions performed (e.g. pushing) along object cart) being acted upon. The action-object inferences provide entry point an expert-based Machine Learning (ML) system automatically identifies targeted work-related causes cart movement forces are too high, due caster size small) identified excessive shoulder forces). proposed framework utilises recommend strategies larger diameter casters, minimum 8" or 203 mm) likely mitigate risk, resulting more efficient effective process.

Язык: Английский

Процитировано

0