N.A. Khamidullina1, S.Ya. Grodzenskiy2

1,2 D.I. Zgirskis Russian State Social University (Moscow, Russia)
1 Efremka@list.ru, 2 grodzenskys@yandex.ru

This text explores the integration of fuzzy logic and artificial intelligence (AI) to enhance objectivity and efficiency in evaluating practical skills within educational systems. Fuzzy logic, introduced by Lotfi Zadeh in 1965, addresses the inherent subjectivity and uncertainty in expert assessments by translating qualitative judgments into mathematical models. The methodology combines fuzzy aggregation techniques, such as fuzzification and defuzzification, with AI tools like neural networks to automate data processing and improve decision-making. This hybrid approach mitigates biases, handles multidimensional qualitative data, and generates interpretable results, bridging the gap between human expertise and computational precision.

The proposed framework emphasizes four key stages: forming expert groups, aggregating evaluations using fuzzy operators, analyzing consensus via cluster methods, AI integration to optimize the process.

Case studies demonstrate improved accuracy in pedagogical assessments, while fuzzy-neural networks optimize real-world applications like consumer behavior prediction. Despite challenges–including computational complexity and interpretability barriers – the synergy of fuzzy logic and AI offers scalable solutions for dynamic educational environments, balancing flexibility with analytical rigor.

Current trends highlight the growing role of fuzzy logic in managing uncertainty within machine learning systems, enabling adaptive models that mirror human cognition. Future advancements aim to refine interpretability, reduce resource demands, and expand applications in competency-based education.

Khamidullina N.A., Grodzenskiy S.Ya. Fuzzy logic and artificial intelligence in the evaluation system: prospects of integration. Nonlinear World. 2025. V. 23. № 4. P. 43–49. DOI: https:// doi.org/10. 18127/j20700970-202504-05 (In Russian)

1. Zadeh L.A. Fuzzy sets. Information and Control.1965.V. 8. № 3. P. 338–353.
2. Mamdani E. Application of fuzzy algorithms for control of simple dynamic plant. Proceedings of the Institution of Electrical Engineers.1974. V. 121. № 12. P. 1585–1588.
3. Grodzenskij S.Ya., Kalacheva E.A. Informacionnye tekhnologii: istoriya razvitiya i stanovleniya. Nelinejnyj mir. 2016. T. 14. № 5. S. 74–79 (In Russian).
4. Grodzenskij S.Ya., Chesalin A.N. Ispol'zovanie apparata nechetkoj logiki dlya ocenki nadezhnosti avtomatizirovannyh sistem. Nelinejnyj mir. 2017. T. 15. № 4. S. 17–24 (In Russian).
5. Suhih I.I. Modeli i algoritmy sistemy povysheniya kachestva podgotovki IT-specialistov na osnove garmonizacii uchebnogo plana. Nelinejnyj mir. 2025. T. 23. № 1. S. 35–45 (In Russian).
6. Chesalin A.N., Ushkova N.N., Grodzenskij S.Ya., Ovchinnikov S.A., Stavcev A.V., Bolotin K.V. Formirovanie IT-kompetencij v obrazovatel'nyh programmah vysshego obrazovaniya. Nelinejnyj mir. 2025. T. 23. № 1. S. 46–58 (In Russian).
7. Savchenko D.V., Reznikova K.M., Smyshlyaeva A.A. Nechetkaya logika i nechetkie informacionnye tekhnologii. Othody i resursy. 2021. T. 8. № 1. S. 1–12. URL: https://resources.today/PDF/10ECOR121.pdf. (data obrashcheniya: 06.05.2025) (In Russian).
8. Vorob'eva A.Yu., Sukmanova Ya.A., Brusencev N.S. Primenenie gibridnyh intellektual'nyh sistem. Materialy 10-j Vseros. nauch.-tekhn. konf. Kursk: Yugo-Zapadnyj gosudarstvennyj universitet. 2024. 25–26 sentyabrya. S. 61–65 (In Russian).
9. Roden B., Lusher D., Spurling T.H., Simpson G.W., Klein T., Brailly J., Hogan B. Avoiding GIGO: Learnings from data collection in innovation research. Social Networks. 2020. V. 63. P. 193–204.
10. Grodzenskij S.Ya., Chesalin A.N. Ot statisticheskogo myshleniya k intellektual'nomu. Standarty i kachestvo. 2020. № 10(1000). S. 94–97.
11. Skvorcov S.V., Hryukin V.I., Skvorcova T.S. Analiz soglasovannosti mnenij specialistov v usloviyah protivorechivosti ekspertnyh ocenok proektnyh al'ternativ. Vestnik RGRTU. 2021. № 76. S. 53–63 (In Russian).
12. Levkina I.A., Ledeneva T.M. Agregirovanie interval'noj informacii. Mezhdunarodnyj nauchno-issledovatel'skij zhurnal. 2022. № 6 (120). Ch. 1. S. 78–88 (In Russian).
13. Ngossaha J.M., Fonkoua Tatang K.N., Ntjam Ngamby L.B., Mfopou A., Tsakou S.B. Integrating fuzzy multicriteria decision making approach for improving the quality of urban mobility services in developing countries. Journal of Infrastructure Policy and Development. 2024. V. 8. № 8. Article ID: 6183
14. Hackevich V.L. Nechetkie usrednyayushchie operatory v zadache agregirovaniya nechetkoj informacii. Informatika i ee primeneniya. 2022. T. 16. № 4. S. 51–56 (In Russian).
15. Qian J., Zhou G., He W., Cui Y., Deng H. Optimization of teacher evaluation indicator system based on fuzzy-DEMATEL-BP.Heliyon. 2024. V. 10. № 13. e34034. P. 1–16.
16. Cheng M. Fuzzy Neural Network Algorithm Applied to the Construction of a Prediction Model for Online Buying Behavior. Applied Mathematics and Nonlinear Sciences. 2023. V. 9. № 1. P. 1–19.