liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Towards Visual Analytics for Explainable AI in Industrial Applications
Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering. (iVis, INV)ORCID iD: 0000-0002-1907-7820
Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering. (iVis, INV)ORCID iD: 0000-0001-6741-4337
Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering. (iVis, INV)ORCID iD: 0000-0002-0646-0388
2025 (English)In: Analytics, E-ISSN 2813-2203, Vol. 4, no 1, article id 7Article in journal (Refereed) Published
Abstract [en]

As the levels of automation and reliance on modern artificial intelligence (AI) approaches increase across multiple industries, the importance of the human-centered perspective becomes more evident. Various actors in such industrial applications, including equipment operators and decision makers, have their needs and preferences that often do not align with the decisions produced by black-box models, potentially leading to mistrust and wasted productivity gain opportunities. In this paper, we examine these issues through the lenses of visual analytics and, more broadly, interactive visualization, and we argue that the methods and techniques from these fields can lead to advances in both academic research and industrial innovations concerning the explainability of AI models. To address the existing gap within and across the research and application fields, we propose a conceptual framework for visual analytics design and evaluation for such scenarios, followed by a preliminary roadmap and call to action for the respective communities.

Place, publisher, year, edition, pages
MDPI, 2025. Vol. 4, no 1, article id 7
Keywords [en]
explainable artificial intelligence, XAI, human-centered artificial intelligence, visual analytics, industrial applications, human–automation collaboration, information visualization, data visualization
National Category
Human Computer Interaction Computer Sciences
Identifiers
URN: urn:nbn:se:liu:diva-211647DOI: 10.3390/analytics4010007OAI: oai:DiVA.org:liu-211647DiVA, id: diva2:1937048
Projects
EXPLAIN
Funder
Vinnova, 2021-04336
Note

The present study is partially funded by VINNOVA Sweden (2021-04336), Bundesministerium für Bildung und Forschung (BMBF; 01IS22030), and Rijksdienst voor Ondernemend Nederland (AI2212001) under the project Explanatory Artificial Interactive Intelligence for Industry (EXPLAIN).

The authors would like to thank Emmanuel Brorsson and Gianluca Manca for providing a new, original figure illustrating the visual interface from the respective paper by Manca et al.

Available from: 2025-02-12 Created: 2025-02-12 Last updated: 2025-05-15

Open Access in DiVA

fulltext(1939 kB)225 downloads
File information
File name FULLTEXT01.pdfFile size 1939 kBChecksum SHA-512
e750080390527abf5f366cd1a8f57d7024fe1273fc02d32e1221d2216912ca10b3b0c9b0e525573af52df04ddb6df71ce7f0a342ca892479ea9443f1adb51047
Type fulltextMimetype application/pdf

Other links

Publisher's full texthttps://www.mdpi.com/2813-2203/4/1/7

Authority records

Kucher, KostiantynZohrevandi, ElmiraWestin, Carl

Search in DiVA

By author/editor
Kucher, KostiantynZohrevandi, ElmiraWestin, Carl
By organisation
Media and Information TechnologyFaculty of Science & Engineering
Human Computer InteractionComputer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 225 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 284 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf