Gradient-based and evolutionary tuning of membership functions for a fuzzy classifier based on a compression function: a comparative analysis
In decision support systems for medical image analysis, a rule-based fuzzy classifier provides interpretability of decisions; however, its accuracy depends significantly on the parameters of the membership functions. This paper examines a fuzzy classifier in which Łukasiewicz operators and trapezoidal membership functions are approximated using a compression function based on a sigmoid function, while the rule structure is generated via a genetic algorithm. Because the compression function is differentiable, the parameters of the membership functions can be tuned using an analytical gradient. Three tuning methods—gradient-based, differential evolution, and a genetic algorithm with real-valued encoding (using BLX-α crossover)—were compared under strictly identical conditions: the same rule structure, initial parameters, objective function, and a computational budget of 3,000 evaluations. The experiments were conducted using the Iris, Wine, Pima, and WDBC datasets; the features for the WDBC dataset were derived from digital images of fine-needle breast aspirates. Gradient-based tuning across all datasets yields a statistically significantly lower mean squared error during training, reaches the final performance level of evolutionary algorithms using only 3–23% of the allocated budget, and requires 16–31% less time; the accuracy on test data is comparable across all three methods. The influence of the steepness parameter β for the squashing function was also investigated. These results justify the use of gradient-based tuning within the fuzzy component of a hybrid system for mammogram analysis.
Authors
- Yuri Yurievich Gromov (ORCID: https://orcid.org/0000-0003-3313-2731)
- Pavel Karasev (ORCID: https://orcid.org/0009-0009-3628-6980)
- Z. Al-Sudani
- I Safin
Institutions
- Tambov State Technical University (RU)
- MIREA - Russian Technological University (RU)
Publication Details
- Journal
- Modeling of systems and processes
- Published
- 2026-11-13
- DOI
- https://doi.org/10.12737/2219-0767-2026-19-3-7-14
- Primary Topic
- Fuzzy Logic and Control Systems
- Type
- article
- Field-Weighted Citation Impact
- 0.00