[go: up one dir, main page]
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.5
Journals
Applied Sciences
Special Issues
Leveraging Digital Transformation for Enhanced Occupational Health and Safety in...
applsci-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Applied Sciences Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Leveraging Digital Transformation for Enhanced Occupational Health and Safety in Manufacturing

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 20 June 2025 | Viewed by 2067

Special Issue Editors

Prof. Dr. Francesco Costantino

E-Mail Website
Guest Editor
Department of Computer, Control and Management Engineering “Antonio Ruberti”, Sapienza University of Rome, Via Ariosto 25, 00185 Rome, Italy
Interests: safety; resilience; smart factory; supply chain; digitalization
Special Issues, Collections and Topics in MDPI journals
Dr. Silvia Colabianchi

E-Mail Website
Guest Editor
Department of Computer, Control and Management Engineering “Antonio Ruberti”, Sapienza University of Rome, Via Ariosto 25, 00185 Rome, Italy
Interests: smart factory; Industry 4.0; Industry 5.0; large language models; safety; cybersecurity
Dr. Margherita Bernabei

E-Mail Website
Co-Guest Editor
Department of Mechanical and Aerospace Engineering, Sapienza University of Rome, Via Eudossiana 18, 00184 Rome, Italy
Interests: technological introduction on health and safety in the workplace within manufacturing sectors; methodologies to guide adaptive automation

Special Issue Information

Dear Colleagues,

The integration of digital technologies is revolutionizing the field of occupational health and safety. This Special Issue explores the industrial impact of enabling technologies such as virtual reality, augmented reality, and generative artificial intelligence, focusing on occupational health and safety (OHS). In high-risk, complex manufacturing environments, the use of innovative tools can significantly improve safety standards, reduce hazards, and promote a culture of preventive maintenance and risk management. Here, the use of digital technologies—such those cited—enables the development of novel tools that promote learning through actions, storytelling, and a first-person experiences-based approach. Furthermore, it permits the integration of non-traditional training content and modes, thereby addressing the inherent variability in digitized industrial contexts. In such a context, it is not sufficient to learn rules and behaviors that are required. Ad-hoc adaptation and response to unpredictable conditions must also be learned. Therefore, in the field of safety management, a new level of expertise is needed. The Skill–Rule–Knowledge framework contains an exemplary level of knowledge. This framework helps one to understand the different levels of conscious effort that workers must apply to industrial tasks and how this affects decision-making. In the event of a unique and unfamiliar situation, the decision is not automatic and reflexive (skill-based), and there are no rules to guide the decision maker (rule-based). So, it is evident that a knowledge-based decision is needed, i.e., the creation of plans and responses based on personal knowledge and experience. In the pursuit of a sustainable working environment, all these concerns must be addressed. So, this Special Issue explores how these technologies can support training, enhance safety protocols, and improve incident management processes. Submissions are invited to present frameworks, models, experimental studies, and practical applications that integrate technologies to support OHS and enhance the social, economic, and environmental sustainability of industrial environments.

Topics of interest include but are not limited to the following: Innovative uses of immersive technologies for safety training, demonstrating impacts on workers' skills and capabilities; Development and application of AI models for the analysis of safety incident narratives and protocols to identify trends and preventive measures; Comparative analyses of industrial safety performance before and after the adoption of technologies, highlighting their effectiveness and potential improvement.

Prof. Dr. Francesco Costantino
Dr. Silvia Colabianchi
Dr. Margherita Bernabei
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • training
  • safety management
  • smart manufacturing
  • sustainable digitization
  • virtual reality
  • augmented reality
  • generative artificial intelligence

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

31 pages, 7146 KiB  
Article
Resilience Analysis Grid–Rasch Rating Scale Model for Measuring Organizational Resilience Potential
by Andrea Falegnami, Andrea Tomassi, Giuseppe Corbelli and Elpidio Romano
Appl. Sci. 2025, 15(4), 1695; https://doi.org/10.3390/app15041695 - 7 Feb 2025
Viewed by 495
Abstract
This paper presents a novel method for measuring organizational resilience by integrating the Rasch model into the Resilience Analysis Grid (RAG), providing a robust and objective tool for cross-sectional resilience studies. By treating the four cornerstones of resilience as abilities, Rasch’s model allows [...] Read more.
This paper presents a novel method for measuring organizational resilience by integrating the Rasch model into the Resilience Analysis Grid (RAG), providing a robust and objective tool for cross-sectional resilience studies. By treating the four cornerstones of resilience as abilities, Rasch’s model allows for an assessment that positions both the difficulty of the items and the organizations’ ability along a common scale. The requirement is the availability of a number of different organizations to be assessed. We employ a dataset generated through an artificial simulation and analyzed in a controlled environment, demonstrating the potential of Rasch-based resilience assessments to provide accurate, comparable, and scalable results in different organizational contexts. The traditional RAG is designed without a normative reference group, which makes it challenging to evaluate its results. The proposed model overcomes this limitation by offering a measurement scale on which different organizations can be placed without the need to use a normative group, facilitating the more consistent and timely monitoring of systems. This novel approach to quantifying resilience potentials highlights the transformative role of digital technologies in improving workplace safety and resilience. It advances resilience engineering and occupational health and safety practices in complex environments like manufacturing and industrial sectors. Full article
(This article belongs to the Special Issue Leveraging Digital Transformation for Enhanced Occupational Health and Safety in Manufacturing)
►▼ Show Figures

Figure 1

Figure 1
<p>Organizational resilience potential estimates for eight synthetic organizations: (<b>a</b>) organization 1; (<b>b</b>) organization 2; (<b>c</b>) organization 3; (<b>d</b>) organization 4; (<b>e</b>) organization 5; (<b>f</b>) organization 6; (<b>g</b>) organization 7; (<b>h</b>) organization 8.</p> Full article ">Figure 2
<p>Organization ability estimates for responding (error bars represent standard error).</p> Full article ">Figure 3
<p>Organization ability estimates for monitoring (error bars represent standard error).</p> Full article ">Figure 4
<p>Organization ability estimates for learning (error bars represent standard error).</p> Full article ">Figure 5
<p>Organization ability estimates for anticipating (error bars represent standard error).</p> Full article ">Figure A1
<p>Responding item characteristic curves for Items 1 and 2.</p> Full article ">Figure A2
<p>Responding item characteristic curves for Items 3 and 4.</p> Full article ">Figure A3
<p>Responding item characteristic curves for Items 5 and 6.</p> Full article ">Figure A4
<p>Responding item characteristic curves for Items 7 and 8.</p> Full article ">Figure A5
<p>Responding item characteristic curves for Items 9 and 10.</p> Full article ">
21 pages, 2265 KiB  
Article
A Generative Artificial-Intelligence-Based Workbench to Test New Methodologies in Organisational Health and Safety
by Andrea Falegnami, Andrea Tomassi, Giuseppe Corbelli, Francesco Saverio Nucci and Elpidio Romano
Appl. Sci. 2024, 14(24), 11586; https://doi.org/10.3390/app142411586 - 11 Dec 2024
Viewed by 783
Abstract
This paper introduces a novel generative artificial intelligence workbench specifically tailored to the field of safety sciences. Utilizing large language models (LLMs), this innovative approach significantly diverges from traditional methods by enabling the rapid development, refinement, and preliminary testing of new safety methodologies. [...] Read more.
This paper introduces a novel generative artificial intelligence workbench specifically tailored to the field of safety sciences. Utilizing large language models (LLMs), this innovative approach significantly diverges from traditional methods by enabling the rapid development, refinement, and preliminary testing of new safety methodologies. Traditional techniques in this field typically depend on slow, iterative cycles of empirical data collection and analysis, which can be both time-intensive and costly. In contrast, our LLM-based workbench leverages synthetic data generation and advanced prompt engineering to simulate complex safety scenarios and generate diverse, realistic data sets on demand. This capability allows for more flexible and accelerated experimentation, enhancing the efficiency and scalability of safety science research. By detailing an application case, we demonstrate the practical implementation and advantages of our framework, such as its ability to adapt quickly to evolving safety requirements and its potential to significantly cut down development time and resources. The introduction of this workbench represents a paradigm shift in safety methodology development, offering a potent tool that combines the theoretical rigor of traditional methods with the agility of modern AI technologies. Full article
(This article belongs to the Special Issue Leveraging Digital Transformation for Enhanced Occupational Health and Safety in Manufacturing)
►▼ Show Figures

Figure 1

Figure 1
<p>Diagram showing the step-by-step interaction between a human user and an LLM-based system through structured prompt engineering. Initially, in phase (<b>a</b>), “Provide framework”, the user defines a general structure for the LLM, setting broad guidelines. In phase (<b>b</b>), “Give feedback”, the LLM generates initial outputs, which the user refines through feedback, enhancing precision. Phase (<b>c</b>), “Make requests about a context”, involves the user specifying details to tailor the framework to the task’s unique needs. Finally, in phase (<b>d</b>), “Provide answers”, the LLM delivers detailed solutions aligned with both general principles and specific task requirements, illustrating a responsive and adaptive workflow that enhances the LLM’s effectiveness. The entire process can be subject to continuous feedback loops at each intermediate stage and can virtually extend indefinitely, as summarised by the curved arrows between the two agents and the dashed box, respectively.</p> Full article ">Figure 2
<p>Synthetic data generation workflow depicting each stage of the process. In (<b>a</b>), yellow box, “Identify the test’s operating conditions”, initial conditions and requirements are set, establishing the data generation foundation, including scope and constraints. In (<b>b</b>), cyan box, “Identify the typology of needed data,” the necessary data type for the research is specified, distinguishing between structured and unstructured formats. In (<b>c</b>), green box, “Identify the experimental data parameters”, key parameters such as data distribution and consistency levels are defined. In (<b>d</b>), orange box, “Select the proper synthetic generator”, the appropriate tool for data generation is chosen based on the data type and parameters, such as using a language model for text or parametric tools for statistical data. In (<b>e</b>), grey box, “Generate synthetic data according to params”, data are produced according to the specified characteristics. Finally, in (<b>f</b>), white box, “Implement synthetic data in the methods”, the generated data are integrated into research methods for testing and validation. This streamlined approach ensures robust, tailored data generation for effective testing under controlled conditions. All the boxes, except the grey one, correspond to actions performed by human agents.</p> Full article ">Figure 3
<p>Step-by-step workflow illustrates the interaction between a human user and an LLM-based system within a structured prompt engineering and synthetic data generation framework. The two blocks constituting the proposed methodology are clearly highlighted. Initially, the user sets a basic framework based on Hollnagel’s RAG general questionnaire for OHS relevance. The LLM then provides feedback to refine its model interpretation. Next, the user requests contextual adaptations to tailor the questionnaire for OHS in manufacturing, leading to the LLM adjusting questions to reflect four core OHS competencies. Further, the user requests Likert scale responses, specifies the type of data required, and sets test conditions to fit a Rasch model, including specifying data parameters like the number of responses and Cronbach’s alpha for consistency. The “LikertMakeR” R package is chosen to generate data fitting these criteria, producing a data set that mimics real-world OHS scenarios in manufacturing. These data are then implemented within the RAG-Rasch framework for testing and validation, completing a robust, context-specific methodological workflow for early-stage OHS methodology testing. The colour code in use corresponds to that in <a href="#applsci-14-11586-f002" class="html-fig">Figure 2</a>.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop