Methodology of interpretable fuzzy classifiers design for explainable artificial intelligence systems
DOI: 10.21293/1818-0442-2025-28-2-73-87
Abstract: The use of artificial intelligence systems based on machine learning methods in critical problem areas is associated with high risks and requires an explanation of the obtained result to a person. Predictive models with this property are called inter-pretable. The absence of such an opportunity reduces the level of trust in the result and may be the reason for slowing down the public acceptance and implementation of such systems. Artificial intelligence systems based on fuzzy systems make it possible to explain the result of their decision. Due to the pres-ence of a base of production rules, they are able to express knowledge in a human-oriented form, using natural language terms. The paper proposes a technique for constructing fuzzy classifiers aimed at improving interpretability, taking into ac-count the shortcomings of known construction methods. The technique includes the use of mixed multiobjective optimization algorithms, discrete optimization, gradient descent, and the data separation method. An experiment was conducted on 38 public-ly available data sets from various problem areas to evaluate the effectiveness of classifiers built using the proposed technique. A statistical comparison with known interpretable classifiers – genetic fuzzy systems FARC-HD and decision trees CART – was carried out. The application of the technique made it possi-ble, with comparable accuracy, to achieve a statistically signifi-cant increase of the interpretability of classifiers by reducing the number of rules, the number of features and the total number of fuzzy terms compared to genetic systems FARC-HD, and the number of rules and the number of conditions in a rule com-pared to classifiers based on decision trees CART. The achieved results indicate a high level of interpretability of classi-fiers constructed using the proposed technique.
Keywords: explainable artificial intelligence, machine learning, classification, fuzzy systems, interpretability, learning algorithms, metaheuristic algorithms, optimization
Funding: The study was supported by the Russian Science Foundation grant No. 24-21-00168, https://rscf.ru/project/24-21-00168/.
For citation:
Sarin K. S. Methodology of interpretable fuzzy classifiers design for explainable artificial intelligence systems. Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radioelektroniki, 2025, vol. 28, no. 2, pp. 73–87. DOI: 10.21293/1818-0442-2025-28-2-73-87
Authors and copyright holders:
- Sarin K. S. , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)
- 1. Wiese T. Predictive Maintenance Using Artificial Intelligence in Critical Infrastructure: A Decision-Making Framework. International Journal of Engineering, Business and Management, 2024, vol. 8, no 4, pp. 1–4.
- 2. Goodman B., Flaxman S. European union regulations on algorithmic decision making and a «right to explanation». AI Magazine, 2017, vol. 38, no. 3. pp. 50–57.
- 3. Zhu J., Liapis A., Risi S., Bidarra R., Youngblood G.M. Explainable AI for designers: A human-centered perspective on mixed-initiative co-creation. 2018 IEEE Conference on Computational Intelligence and Games (CIG), Maastricht, The Netherlands, 2018, pp. 1–8.
- 4. Woodruff A., Fox S., Rousso-Schindler S., Warshaw J. A qualitative exploration of perceptions of algorithmic fairness. Proceedings Conference on Human Factors in Computing Systems, Montreal, QC, Canada, 2018, pp. 1–14.
- 5. Hodashinsky I.A., Shurygin Yu.A., Sarin K.S. Kuzmina E.A. Eticheskie problemy iskusstvennogo intellekta [Ethical Issues of Artificial Intelligence]. Sovremennoe obrazovanie: integraciya obrazovaniya, nauki, biznesa i vlasti. Transformaciya obrazovaniya, nauki i proizvodstva - osnova tekhnologicheskogo proryva: materialy mezhdunarodnoj nauchnometodicheskoj konferencii [Modern education: integration of education, science, business and government. Transformation of education, science and production - the basis of technological breakthrough: materials of the international scientific and methodological conference]. Tomsk, 26–27 January 2023, vol. 2, Tomsk: Tomsk State University of Control Systems and Radioelectronics, 2023, pp. 125–129 (in Russ.).
- 6. Borisov V., Leemann T., Sesler K., Haug J., Pawelczyk M., Kasneci J. Deep Neural Networks and Tabular Data: A Survey. IEEE Transactions on Neural Networks and Learning Systems, 2024, vol. 35, no. 6, pp. 7499–7519.
- 7. Castelvecchi D. Can we open the black box of AI? Nature, 2016, vol. 538, pp. 20–23.
- 8. Lipton Z.C. The mythos of model interpretability. Communications of the ACM, 2016, vol. 61, pp. 36-43.
- 9. Gunning D., Aha W. DARPA's Explainable Artificial Intelligence (XAI) Program. AI Magazine, 2019, vol. 40, pp. 44–58.
- 10. Ahmed I., Jeon G., Piccialli F. From Artificial Intelligence to Explainable Artificial Intelligence in Industry 4.0: A Survey on What, How, and Where. IEEE Transactions on Industrial Informatics, 2022, vol. 18, pp. 5031–5042.
- 11. Moral J.M.A., Castiello C., Magdalena L., Mencar C. Explainable Fuzzy Systems. Studies in Computational Intelligence, 2021, vol. 970, 232 p.
- 12. Carvalho D.V., Pereira E.M., Cardoso J.S. Machine Learning Interpretability: A Survey on Methods and Metrics. Electronics, 2019, vol. 8, pp. 832.
- 13. Zadeh L.A. From computing with numbers to computing with words. From manipulation of measurements to manipulation of perception. IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, 1999, vol. 46, no. 1, pp. 105–119.
- 14. Zadeh L.A. Toward human-level machine intelligence: is it achievable? The need for a paradigm shift. IEEE Computational Intelligence Magazine, 2008, vol.3, no. 3, pp. 11–22.
- 15. Casalino G., Castellano G., Castiello C., Mencar C. Effect of fuzziness in fuzzy rule-based classifiers defined by strong fuzzy partitions and winner-takes-all inference. Soft Computing, 2022, vol. 26, pp. 6519–6527.
- 16. Cao J., Zhou T., Zhi S., Lam S., Ren G., Zhang Y., Wang Y., Dong Y., Cai J. Fuzzy inference system with interpretable fuzzy rules: Advancing explainable artificial intelligence for disease diagnosis - A comprehensive review. Information Science, 2024, vol. 662, pp. 120212.
- 17. Gacto M.J., Alcala R., Herrera F. Interpretability of linguistic fuzzy rule-based systems: An overview of interpretability measures. Information Science, 2011, vol. 181, pp. 4340–4360.
- 18. Duda R., Hart P. Pattern classification and scene analysis, New York, Wiley, 1973, 482 p.
- 19. Sarin K.S. Nechetkij klassifikator tipa Min-Max: obzor [Fuzzy Min-Max classifier: review]. Proceedings of TUSUR University, 2024, vol. 26, no. 1, pp. 65–75 (in Russ).
- 20. Sarin K.S., Kolomnikov R.E., Svetlakov M.O., Hodashinsky I.A. Nechetkij klassifikator inkrementnogo obucheniya tipa Min-Max dlya resheniya zadach kiberbezopasnosti [Fuzzy Min-Max Classifier in Cybersecurity Applications.] Automatic Documentation and Mathematical Linguistics, 2024, vol. 58, no. 5, pp. 299–309.
- 21. Herrera F. Genetic fuzzy systems: taxonomy, current research trends and prospects. Evolution Intelligence, 2008, vol. 1, no. 1, pp. 27–46.
- 22. Alcala-Fdez J., Alcala R., Herrera F. A Fuzzy Association Rule-Based Classification Model for High-Dimensional Problems With Genetic Rule Selection and Lateral Tuning. IEEE Transactions on Fuzzy Systems, 2011, vol. 19, no. 5, pp. 857–872.
- 23. Elkano M., Galar M., Sanz J., Barrenechea E., Herrera F., Bustince H. Improving the Performance of FARC-HD in Multi-class Classification Problems Using the One-VersusOne Strategy and an Adaptation of the Inference System. Communications in Computer and Information Science, 2014, vol. 444, pp. 296–306.
- 24. Omozaki Y., Masuyama N., Nojima Y., Ishibuchi H. Evolutionary Multi-Objective Multi-Tasking for Fuzzy Genetics-Based Machine Learning in Multi-Label Classification. 2022 IEEE International Conference on Fuzzy Systems (FUZZIEEE), Padova, Italy, 2022, pp. 1–8.
- 25. Fazzolari M., Alcala R., Herrera F. Multi-objective evolutionary method for learning granularities based on fuzzy discretization to improve the accuracy-complexity trade-off of fuzzy rule-based classification systems: D-MOFARC algorithm. Applied Soft Computing, 2014, vol. 24, pp. 470–481.
- 26. Alcala R., Nojima Y., Herrera F., Ishibuchi H. Multiobjective genetic fuzzy rule selection of single granularitybased fuzzy classification rules and its interaction with the lateral tuning of membership functions. Soft Computing, 2011, vol. 15, pp. 2303–2318.
- 27. Jang R. ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man and Cybernetics, 1993, vol. 23, pp. 665–685.
- 28. Cui Y., Wu D., Huang J. Optimize TSK Fuzzy Systems for Classification Problems: Minibatch Gradient Descent With Uniform Regularization and Batch Normalization. IEEE Transactions on Fuzzy Systems, 2020, vol. 28, no. 12, pp. 3065–3075.
- 29. Haque F., Reaz M., Chowdhury M.E., Hashim F.H., Arsad N., Ali S. Diabetic Sensorimotor Polyneuropathy Severity Classification Using Adaptive Neuro Fuzzy Inference System. IEEE Access, 2021, vol. 9, pp. 7618–7631.
- 30. Kanwal S., Jiriwibhakorn S. Advanced Fault Detection, Classification, and Localization in Transmission Lines: A Comparative Study of ANFIS, Neural Networks, and Hybrid Methods. IEEE Access, 2024, vol. 12, pp. 49017–49033.
- 31. Sarin K., Bardamova M., Svetlakov M., Koryshev N., Ostapenko R., Hodashinskaya A., Hodashinsky I. A three-stage fuzzy classifier method for Parkinson’s disease diagnosis using dynamic handwriting analysis. Decision Analytics Journal, 2023, vol. 8, pp. 100274.
- 32. Bardamova M.B., Buymov A.G., Tarasenko V.F. Sposoby adaptatsii algoritma prygayushchih lyagushek k binarnomu prostranstvu poiska pri reshenii zadachi otbora priznakov [Methods for adapting the leaping frog algorithm to the binary search space when solving the feature selection problem]. Proceedings of TUSUR University, 2020, vol. 23, no. 4, pp. 57–62 (in Russ).
- 33. Bardamova M.B., Hodashinsky I.A., Shurygin Yu.A., Sarin K.S., Svetlakov M.O. Generatsiya bazy pravil nechetkogo klassifikatora dlya diagnostiki bolezni Parkinsona po rukopisnym dannym [Generation of a Fuzzy Classifier Rule Base for Diagnosing Parkinson's Disease from Handwritten Data]. Artificial Intelligence and Decision Making, 2023, no. 2, pp. 31–44 (in Russ).
- 34. Bardamova M.B., Hodashinsky I.A. Formirovanie struktury nechyotkogo klassifikatora kombinatsiej algoritma ekstremumov klassov i algoritma "prygayushchih lyagushek" dlya nesbalansirovannyh dannyh s dvumya klassami [Formation of Fuzzy Classifier Structure by a Combination of the Class Extremum Algorithm and the Shuffled Frog Leaping Algorithm for Imbalanced Data with Two Classes]. Optoelectronics, Instrumentation and Data Processing, 2021, vol. 57, no. 4, pp. 378–387.
- 35. Koryshev N.P., Hodashinsky I.A. Algoritm formirovaniya bazy pravil nechyotkogo klassifikatora na osnove algoritma klasterizatsii K-srednih i metaevristicheskogo algoritma "kitov"[Algorithm to forming a rule base for a fuzzy classifier designed on the basis of the K-means clustering algorithm and the whale optimization algorithm]. Proceedings of TUSUR University, 2021, vol. 24, no 1, pp. 42–47 (in Russ).
- 36. Ostapenko R.O., Hodashinsky I.A., Shurygin Yu.A. Postroenie nechyotkogo klassifikatora na osnove metaevristicheskogo algoritma «saranchi» [Using the Grasshopper Optimization Algorithm for Fuzzy Classifier Design]. Automatic Documentation and Mathematical Linguistics, 2023, vol. 57, no. 6, pp. 333–349.
- 37. Ishibuchi H., Nozaki K., Tanaka H. Distributed representation of fuzzy rules and its application to pattern classification. Fuzzy Sets and Systems, 1992, vol. 52, no. 1, pp. 2–132.
- 38. Sarin K.S. Metod razdeleniya dannyh dlya postroeniya prognosticheskih modelej mashinnogo obucheniya [Data splitting method for building machine learning models]. Proceedings of TUSUR University, 2024, vol. 27, no. 4, pp. 88–96 (in Russ).
- 39. Sarin K.S. Diskretnyj algoritm optimizatsii na osnove raspredeleniya veroyatnostej s transformatsiej tselevyh znachenij [Discrete Optimization Algorithm Based on Probability Distribution with Transformation of Target Values]. Programming and Computer Software, 2024, vol. 50, no. 6, pp. 445-456.
- 40. Sarin K.S. Gibridnyj algoritm smeshannoj mnogokriterial'noj optimizatsii «kukushkin poisk» s geneticheskim operatorom skreshchivaniya [Mixed-integer multiobjective optimization algorithm based on cuckoo search methaheuristic with genetic crossover operator]. Artificial Intelligence and Decision Making, 2024, no. 2, pp. 87–105 (in Russ.).
- 41. Hastie T., Tibshirani R., Friedman J.H. The Elements of Statistical Learning. New York, Springer, 2009, 745 p.
- 42. Herrera F., Martinez-Lopez L. A 2-tuple fuzzy linguistic representation model for computing with words. IEEE Transactions on Fuzzy Systems. 2000, vol. 8, pp. 746–752.
- 43. Ishibuchi H., Nakashima T., Nii M. Classification and Modeling with Linguistic Information Granules. Berlin, Springer, 2005, 308 p.
- 44. Coppersmith D., Hong S.J., Hosking J.R.M. Partitioning Nominal Attributes in Decision Trees. Data Mining and Knowledge Discovery, 1999, vol. 3, pp. 197–217.
- 45. Triguero I., Gonzalez S., Moyano J. M., Garcia S., Alcala-Fdez J., Luengo J., Fernandez A., del Jesus L., Sanchez L., Herrera F. KEEL 3.0: An Open Source Software for Multi-Stage Analysis in Data Mining. International Journal of Computational Intelligence Systems, 2017, no. 10, pp. 1238–1249.
- 46. Wu J., Chen X., Zhang H., Xiong L-D., Lei H., Deng S. Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimization. Journal of Electronic Science and Technology, 2019, vol. 17, pp. 26–40.
Last issue
-2026-1_%D0%BA%D0%BE%D0%BF%D0%B8%D1%8F.jpg)
Editorial office address
Executive Secretary of the Editor’s Office
Editor’s Office: 40 Lenina Prospect, Tomsk, 634050, Russia
Phone / Fax: + 7 (3822) 701-582
Viktor N. Maslennikov
Executive Secretary of the Editor’s Office
Editor’s Office: 40 Lenina Prospect, Tomsk, 634050, Russia
Phone / Fax: + 7 (3822) 51-21-21 / 51-43-02
Subscription for updates
