Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Dec 11:6:1264372.
doi: 10.3389/frai.2023.1264372. eCollection 2023.

Explainability as the key ingredient for AI adoption in Industry 5.0 settings

Carlos Agostinho  1   2 , Zoumpolia Dikopoulou  3 , Eleni Lavasa  4 , Konstantinos Perakis  5 , Stamatis Pitsios  5 , Rui Branco  2 , Sangeetha Reji  6 , Jonas Hetterich  6 , Evmorfia Biliri  7 , Fenareti Lampathaki  7 , Silvia Rodríguez Del Rey  8 , Vasileios Gkolemis  4
Affiliations

Explainability as the key ingredient for AI adoption in Industry 5.0 settings

Carlos Agostinho et al. Front Artif Intell. .

Abstract

Explainable Artificial Intelligence (XAI) has gained significant attention as a means to address the transparency and interpretability challenges posed by black box AI models. In the context of the manufacturing industry, where complex problems and decision-making processes are widespread, the XMANAI platform emerges as a solution to enable transparent and trustworthy collaboration between humans and machines. By leveraging advancements in XAI and catering the prompt collaboration between data scientists and domain experts, the platform enables the construction of interpretable AI models that offer high transparency without compromising performance. This paper introduces the approach to building the XMANAI platform and highlights its potential to resolve the "transparency paradox" of AI. The platform not only addresses technical challenges related to transparency but also caters to the specific needs of the manufacturing industry, including lifecycle management, security, and trusted sharing of AI assets. The paper provides an overview of the XMANAI platform main functionalities, addressing the challenges faced during the development and presenting the evaluation framework to measure the performance of the delivered XAI solutions. It also demonstrates the benefits of the XMANAI approach in achieving transparency in manufacturing decision-making, fostering trust and collaboration between humans and machines, improving operational efficiency, and optimizing business value.

Keywords: Fuzzy Cognitive Maps; XMANAI platform; business value; decision-making; explainable AI; manufacturing industry.

PubMed Disclaimer

Conflict of interest statement

CA was employed by UNINOVA and Knowledgebiz Consulting. ZD was employed by AiDEAS. KP and SP were employed by Ubitech. RB was employed by Knowledgebiz Consulting. SRe and JH were employed by Fraunhofer FOKUS. EB and FL were employed by Suite5 Data Intelligence Solutions. SRo was employed by Innovalia Association. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
XMANAI data model overview.
Figure 2
Figure 2
XMANAI platform menu page.
Figure 3
Figure 3
XMANAI Reference Architecture-Services Bundles Perspective. The star symbol (*) indicates that data anonymizer is based on a standalone tool (AMNESIA) developed by ATHENA RC.
Figure 4
Figure 4
Demonstrators in XMANAI project that will test and validate the XMANAI solution.
Figure 5
Figure 5
Indicative screenshots-FORD manufacturing application.
Figure 6
Figure 6
Indicative screenshots-WHIRLPOOL manufacturing application.
Figure 7
Figure 7
Indicative screenshots-CNH mobile manufacturing application.
Figure 8
Figure 8
Indicative screenshots-UNIMETRIK manufacturing application.
Figure 9
Figure 9
6Ps digital transformation tool-the six pillars.
Figure 10
Figure 10
6Ps-the people dimension.
Figure 11
Figure 11
6Ps overall radar chart-an example.
Figure 12
Figure 12
The Process pillar radar chart-an example.
Figure 13
Figure 13
The simulation procedure of the FCM graph model activating in the initial vector one input concepts (C2-MAPE).
See this image and copyright information in PMC

References

    1. Adadi A., Berrada M. (2018). Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access. 6, 52138–52160. 10.1109/ACCESS.2018.2870052 - DOI
    1. Ahmed I., Jeon G., Piccialli F. (2022). From artificial intelligence to explainable artificial intelligence in industry 4.0: a survey on what, how, and where. IEEE Trans. Industr. Inf. 18, 5031–5042. 10.1109/TII.2022.3146552 - DOI
    1. Barredo Arrieta A., Díaz-Rodríguez N., Del Ser J., Bennetot A., Tabik S., Barbado A. F., et al. F. (2020). Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82–115. 10.1016/j.inffus.2019.12.012 - DOI
    1. Betancourt M. (2017). A Conceptual Introduction to Hamiltonian Monte Carlo. arXiv [preprint]. arXiv:1701.02434
    1. Bharti S., Kurian D. S., Pillai V. M. (2020). “Reinforcement learning for inventory management,” in Innovative Product Design and Intelligent Manufacturing Systems. Lecture Notes in Mechanical Engineering, eds B. Deepak, D. Parhi, and P. Jena (Singapore: Springer; ), 877–85.

LinkOut - more resources