DEVELOPMENT OF FUZZY ONTOLOGY FOR EXPLAINABLE ARTIFICIAL INTELLIGENCE FOR DECISION-MAKING IN FUZZY ENVIRONMENT

Authors

Pavel Kosov, Azerbaijan State Oil and Industry University. Address: Azadliq Avenue 34, AZ1010, Baku, Azerbaijan. E-mail: pavel_kosov@asoiu.edu.az.Follow

Abstract

In modern artificial intelligence systems, there is an acute need to understand the decision-making logic of "black box" algorithms. Our research proposes an innovative method for increasing the transparency of such systems through the formalization of fuzzy explanatory mechanisms. We have developed an extension of existing ontological approaches by introducing the concept of fuzziness into the structure of explanatory properties, which allows overcoming the fundamental limitations of traditional XAI methods. The proposed formalization is based on the theory of collective mental models and principles of fuzzy logic, providing a more accurate reflection of uncertainty and subjectivity in expert knowledge. Our approach establishes quantitative indicators of explanation credibility through degrees of fuzzy membership in OWL2 ontology, allowing users to evaluate the reliability of each element in the logical inference chain. Application of the developed methodology to the student performance assessment task demonstrates its practical value. An important component of our work was the development of criteria for the effectiveness of explanatory properties, covering aspects of accessibility, flexibility, and compatibility with the open world assumption. The system architecture is based on specialized models for each property, ensuring precise identification of relevant characteristics. The developed approach is particularly effective in areas where binary logic cannot express the complexity of domain knowledge. The proposed evaluation methods include analysis of semantic consistency and representational adequacy. Promising research directions include adapting the system to visual data and integration with neuro-symbolic computations.

First Page

19

Last Page

26

References

1. Kosov, P., El Kadhi, N., Zanni-Merk, C., Gardashova, L. (2024). Advancing XAI: new properties to broaden semantic-based explanations of black-box learning models. Procedia Computer Science, 246, 2292-2301.
2. Panigutti, C., Perotti, A., Pedreschi, D. (2020). Doctor XAI: an ontology-based approach to black-box sequential data classification explanations. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, ACM, 629-639.
3. Bellucci, M., Delestre, N., Malandain, N., Zanni-Merk, C. (2020). Combining an explainable model based on ontologies with an explanation interface to classify images. Procedia Computer Science, 207, 2395-2403.
4. W3C. (2012). OWL 2 Web Ontology Language Document Overview (Second Edition). [Online, Accessed: February 10, 2025]. Available: https://www.w3.org/TR/owl2-overview/.
5. Kosov, P., Kadhi, N. E., Zanni-Merk, C., Gardashova, L. (2024). Semantic-Based XAI: Leveraging Ontology Properties to Enhance Explainability. In 2024 International Conference on Decision Aid Sciences and Applications, IEEE, 1-5.
6. Zadeh, L. A. (1965). Fuzzy sets. Information and Control, 8(3), 338-353.
7. Jonker, C.M., Van Riemsdijk, M.B., Vermeulen, B. (2011). Shared Mental Models. In Coordination, Organizations, Institutions, and Norms in Agent Systems VI (Lecture Notes in Computer Science, vol. 6541), De Vos, M., Fornara, N., Pitt, J. V., Vouros, G. (Eds.), Springer Berlin Heidelberg, 132-151.
8. Cortez, P. (2008). Student Performance. UCI Machine Learning Repository.
9. Gunning, D., Aha, D.W. (2019). DARPA’s Explainable Artificial Intelligence Program. AI Magazine, 40(2), 44-58.
10. Jones, N.A., Ross, H., Lynam, T., Perez, P., Leitch, A. (2011). Mental Models: An Interdisciplinary Synthesis of Theory and Methods. Ecology and Society, 16(1).
11. Burtscher, M.J., Manser, T. (2012). Team mental models and their potential to improve teamwork and safety: A review and implications for future research in healthcare. Safety Science, 50(5), 1344-1354.
12. Westli, H., Johnsen, B., Eid, J., Rasten, I., Brattebø, G. (2010). Teamwork skills, shared mental models, and performance in simulated trauma teams: an independent group design. Scand J Trauma Resusc Emerg Med, 18(1), 47.
13. Bobillo, F., Straccia, U. (2011). Fuzzy ontology representation using OWL 2. International Journal of Approximate Reasoning, 52, 1073-1094.
14. Huitzil, I., Bobillo, F. (2023). Fuzzy ontology datatype learning using Datil. Expert Systems with Applications, 228, 120299.
15. Bobillo, F., Straccia, U. (2018). Reasoning within Fuzzy OWL 2 EL revisited. Fuzzy Sets and Systems, 351, 1-40.
16. Bobillo, F., Straccia, U. (2016). The fuzzy ontology reasoner fuzzyDL. Knowledge-Based Systems, 95, 12-34.
17. Bobillo, F., Delgado, M., Gómez-Romero, J. (2012). DeLorean: A reasoner for fuzzy OWL 2. Expert Systems with Applications, 39(1), 258-272.

Recommended Citation

Kosov, Pavel (2025) "DEVELOPMENT OF FUZZY ONTOLOGY FOR EXPLAINABLE ARTIFICIAL INTELLIGENCE FOR DECISION-MAKING IN FUZZY ENVIRONMENT," Chemical Technology, Control and Management: Vol. 2025: Iss. 2, Article 3.
DOI: https://doi.org/10.59048/2181-1105.1682