Investigating the Usability of XAI in AI-based Image Classification
- 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.
Download full text files
Additional Services
Statistics
| Document Type: | Article (peer-reviewed) |
|---|---|
| Author: | Jan StodtORCiDGND, Christoph ReichORCiDGND, Nathan Clarke |
| URN: | https://urn:nbn:de:bsz:fn1-opus4-111384 |
| DOI: | https://doi.org/10.1016/j.ifacol.2024.11.064 |
| ISSN: | 2405-8963 |
| Parent Title (English): | IFAC-PapersOnLine |
| Subtitle (English): | 12th IFAC Symposium on Biological and Medical Systems BMS 2024, September 11-13, 2024, Villingen-Schwenningen, Germany |
| Language: | English |
| Year of Completion: | 2024 |
| Release Date: | 2024/12/16 |
| Tag: | Peer-reviewed conference AI-based image processing; Investigation; Non-AI experts; Usability; XAI |
| Volume: | 58.2024 |
| Issue: | 24 |
| First Page: | 362 |
| Last Page: | 367 |
| Open-Access-Status: | Open Access |
| Diamond | |
| Licence (German): |  Creative Commons - CC BY-NC-ND - Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International |