Final DAI-DSS Research Collection – D3.3
Lucas Paletta, Herwig Zeiner, Gustavo Vieira, Sylwia Olbrych, Alexander Nasuta, Johanna Werz, Johannes Zysk, Noushin Qeybi, Stefan Böschen, Marlene Mayr, Christian Muck
This deliverable shows the “Final DAI-DSS Research Collection” as part of the Horizon Europe project FAIRWork. The deliverable aims to describe guidelines, methods and tools for democratising the production process in the light of their flexibilization utilizing artificial intelligence (AI), Optimisation, Human Factors Analytics, and multi-agent systems (MAS) as mediators in the form of prototypes, physical experiments in laboratories, implemented questionnaires, modelling tools or semantic model of criteria catalogues. Importantly, this collection is published in the FARIWork Innovation Shop and represents the key support features for the Democratic AI-based Decision Support System Support System (DAI-DSS). The FAIRWork Innovation shop is accessible online as Deliverable 3.3. This document is considered the accompanying document of the deployed online version.
https://innovationshop.fairwork-project.eu/
This deliverable also presents the scientific basis for the FAIRWork project across seven research tracks: The “Democratization of Decision-Making in Socio-Technical Settings” examines the dynamics of democratization in industry through MAS by exploring the contextual conditions for implementing a DSS within socio-technical frameworks. The “Decision-Making Using Multi Agent Systems” explores the potential of MAS for decentralized, adaptive decision-making in industry. By balancing technical, human-centric, and ethical aspects, MAS enhances efficiency, inclusivity, and scalability in complex systems. The “Digital Human Factors Analytics” outlines the use of wearable sensors to capture critical information on human physiological, cognitive-emotional, and resilience states, including the intelligent sensor box (ISB). It also details a novel framework using Personas as Human Digital Twins for Decision Making in Industry 5.0. The “Optimization in Decision Support Systems” is crucial for defining clear goals in AI-driven manufacturing, addressing challenges such as process optimisation, automation, and resource allocation. Various techniques, including AI, new algorithms and heuristics, support decision-making and efficiency in manufacturing companies. The “AI-Enriched Decision Support Systems” explores how AI methodologies, particularly machine learning (ML), can optimise decision-making in manufacturing, with an emphasis on dynamic tasks. It also addresses the gap between industry and developers by proposing a structured categorisation of DSS, enabling developers to select appropriate AI methods for industrial applications. The “Model-based Knowledge Engineering for Decision Support” presents a structured approach to AI adoption in enterprises by proposing a three-layered framework: Identification, Specification, and Configuration. It highlights the role of conceptual and technical models from the identification of the problem setting to the configuration of AI to ensure the alignment with business needs. Furthermore, it also reflects the integration of different AI techniques, such as retrieval-augmented generation (RAG) and large language models (LLMs), within use-case-specific prototypes, demonstrating how model-based methodologies can support AI configuration. It also investigates how such design models can be reused to support the explanation of decision scenarios on a high abstraction level using OMiLAB’s Scene2Model tool. The “Reliable and Trustworthy AI” demonstrates the importance of transparency for trusting AI systems and that transparency needs to be adapted to the target group. AI systems have to be understandable, which is why a system-dependent approach that sets the user in the center is recommended. A developed transparency matrix with additional individual consulting workshops for the developers has shown to be successful in implementing transparency and accuracy communication into AI services.
https://innovationshop.fairwork-project.eu/
This deliverable also presents the scientific basis for the FAIRWork project across seven research tracks: The “Democratization of Decision-Making in Socio-Technical Settings” examines the dynamics of democratization in industry through MAS by exploring the contextual conditions for implementing a DSS within socio-technical frameworks. The “Decision-Making Using Multi Agent Systems” explores the potential of MAS for decentralized, adaptive decision-making in industry. By balancing technical, human-centric, and ethical aspects, MAS enhances efficiency, inclusivity, and scalability in complex systems. The “Digital Human Factors Analytics” outlines the use of wearable sensors to capture critical information on human physiological, cognitive-emotional, and resilience states, including the intelligent sensor box (ISB). It also details a novel framework using Personas as Human Digital Twins for Decision Making in Industry 5.0. The “Optimization in Decision Support Systems” is crucial for defining clear goals in AI-driven manufacturing, addressing challenges such as process optimisation, automation, and resource allocation. Various techniques, including AI, new algorithms and heuristics, support decision-making and efficiency in manufacturing companies. The “AI-Enriched Decision Support Systems” explores how AI methodologies, particularly machine learning (ML), can optimise decision-making in manufacturing, with an emphasis on dynamic tasks. It also addresses the gap between industry and developers by proposing a structured categorisation of DSS, enabling developers to select appropriate AI methods for industrial applications. The “Model-based Knowledge Engineering for Decision Support” presents a structured approach to AI adoption in enterprises by proposing a three-layered framework: Identification, Specification, and Configuration. It highlights the role of conceptual and technical models from the identification of the problem setting to the configuration of AI to ensure the alignment with business needs. Furthermore, it also reflects the integration of different AI techniques, such as retrieval-augmented generation (RAG) and large language models (LLMs), within use-case-specific prototypes, demonstrating how model-based methodologies can support AI configuration. It also investigates how such design models can be reused to support the explanation of decision scenarios on a high abstraction level using OMiLAB’s Scene2Model tool. The “Reliable and Trustworthy AI” demonstrates the importance of transparency for trusting AI systems and that transparency needs to be adapted to the target group. AI systems have to be understandable, which is why a system-dependent approach that sets the user in the center is recommended. A developed transparency matrix with additional individual consulting workshops for the developers has shown to be successful in implementing transparency and accuracy communication into AI services.
Links
Cite as
BibTeX (Download)
@techreport{fairwork_d3.3,
title = {Final DAI-DSS Research Collection - D3.3},
author = {Lucas Paletta, Herwig Zeiner, Gustavo Vieira, Sylwia Olbrych, Alexander Nasuta, Johanna Werz, Johannes Zysk, Noushin Qeybi, Stefan Böschen, Marlene Mayr, Christian Muck},
editor = {Stefan Böschen},
url = {https://fairwork-project.eu/deliverables/D3.3%20DAI-DSS%20Research%20Collection%20v1.0-preliminary.pdf},
year = {2025},
date = {2025-02-28},
urldate = {2025-02-28},
abstract = {This deliverable shows the “Final DAI-DSS Research Collection” as part of the Horizon Europe project FAIRWork. The deliverable aims to describe guidelines, methods and tools for democratising the production process in the light of their flexibilization utilizing artificial intelligence (AI), Optimisation, Human Factors Analytics, and multi-agent systems (MAS) as mediators in the form of prototypes, physical experiments in laboratories, implemented questionnaires, modelling tools or semantic model of criteria catalogues. Importantly, this collection is published in the FARIWork Innovation Shop and represents the key support features for the Democratic AI-based Decision Support System Support System (DAI-DSS). The FAIRWork Innovation shop is accessible online as Deliverable 3.3. This document is considered the accompanying document of the deployed online version.
https://innovationshop.fairwork-project.eu/
This deliverable also presents the scientific basis for the FAIRWork project across seven research tracks: The “Democratization of Decision-Making in Socio-Technical Settings” examines the dynamics of democratization in industry through MAS by exploring the contextual conditions for implementing a DSS within socio-technical frameworks. The “Decision-Making Using Multi Agent Systems” explores the potential of MAS for decentralized, adaptive decision-making in industry. By balancing technical, human-centric, and ethical aspects, MAS enhances efficiency, inclusivity, and scalability in complex systems. The “Digital Human Factors Analytics” outlines the use of wearable sensors to capture critical information on human physiological, cognitive-emotional, and resilience states, including the intelligent sensor box (ISB). It also details a novel framework using Personas as Human Digital Twins for Decision Making in Industry 5.0. The “Optimization in Decision Support Systems” is crucial for defining clear goals in AI-driven manufacturing, addressing challenges such as process optimisation, automation, and resource allocation. Various techniques, including AI, new algorithms and heuristics, support decision-making and efficiency in manufacturing companies. The “AI-Enriched Decision Support Systems” explores how AI methodologies, particularly machine learning (ML), can optimise decision-making in manufacturing, with an emphasis on dynamic tasks. It also addresses the gap between industry and developers by proposing a structured categorisation of DSS, enabling developers to select appropriate AI methods for industrial applications. The “Model-based Knowledge Engineering for Decision Support” presents a structured approach to AI adoption in enterprises by proposing a three-layered framework: Identification, Specification, and Configuration. It highlights the role of conceptual and technical models from the identification of the problem setting to the configuration of AI to ensure the alignment with business needs. Furthermore, it also reflects the integration of different AI techniques, such as retrieval-augmented generation (RAG) and large language models (LLMs), within use-case-specific prototypes, demonstrating how model-based methodologies can support AI configuration. It also investigates how such design models can be reused to support the explanation of decision scenarios on a high abstraction level using OMiLAB’s Scene2Model tool. The “Reliable and Trustworthy AI” demonstrates the importance of transparency for trusting AI systems and that transparency needs to be adapted to the target group. AI systems have to be understandable, which is why a system-dependent approach that sets the user in the center is recommended. A developed transparency matrix with additional individual consulting workshops for the developers has shown to be successful in implementing transparency and accuracy communication into AI services.},
howpublished = {https://fairwork-project.eu/deliverables/D3.3%20DAI-DSS%20Research%20Collection%20v1.0-preliminary.pdf},
keywords = {deliverable},
pubstate = {published},
tppubtype = {techreport}
}