ORCID
- Jan Stodt: 0000-0001-9115-7668
- Nathan Clarke: 0000-0002-3595-3800
Abstract
This paper investigates the usability of XAI (Explainable Artificial Intelligence) in AI-based image classification, particularly for non-experts like medical professionals. XAI provides the user of AI systems with an explanation for a particular decision. But the usability of such explanations remains an open point of discussion. The investigation highlights that there is a need for integrating explainability in the design of the classification approach. This paper will present an approach to classify the parts of an object separately and then utilize a white box model (decision tree) for the final classification. This is enriched by additional information, achieving understandability of the classification.
DOI Link
DOI
10.1016/j.ifacol.2024.11.064
Publication Date
2024-09-01
Publication Title
IFAC-PapersOnLine
Volume
58
Issue
24
ISSN
2405-8963
Keywords
AI-based Image processing, Investigation, Non-AI Experts, Usability, XAI
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
First Page
362
Last Page
367
Recommended Citation
Stodt, J., Reich, C., & Clarke, N. (2024) 'Investigating the Usability of XAI in AI-based Image Classification', IFAC-PapersOnLine, 58(24), pp. 362-367. Available at: 10.1016/j.ifacol.2024.11.064
