<![CDATA[Complex decision-making systems increasingly face uncertainty, nonlinearity, incomplete information, and dynamic data streams, making conventional rule-based and statistical approaches less reliable for adaptive and consistent decision support. Fuzzy logic offers interpretability for imprecise reasoning, whereas machine learning contributes predictive strength and optimization capability. This study develops and evaluates fuzzy logic-based hybrid models that integrate fuzzy inference systems with neural learning and evolutionary optimization. Benchmark datasets and simulation-based case studies were used to test model performance under uncertain and nonlinear conditions. The models were assessed using prediction accuracy, decision consistency, computational efficiency, error reduction, scalability, and adaptability, followed by comparison with conventional fuzzy, statistical, and standalone machine learning models. The main objective is to evaluate the effectiveness, reliability, scalability, and adaptability of hybrid fuzzy models for complex decision-making systems. The findings show that the proposed hybrid fuzzy models outperform conventional single model approaches across different scenarios. The models improve prediction precision, stabilize decision outputs under uncertainty, reduce error rates, and enhance adaptability to nonlinear data patterns. Neural learning strengthens predictive capability, while evolutionary optimization improves rule refinement, parameter tuning, and adaptive decision processing. This study concludes that fuzzy logic-based hybrid models provide a robust, interpretable, and scalable framework for intelligent decision support in uncertain and dynamic environments. The findings support the development of adaptive hybrid artificial intelligence systems for healthcare, energy management, smart cities, finance, and industrial automation. This structure also promotes transparent reasoning, reproducible evaluation, and practical deployment in high-stakes environments requiring explainability and resilience simultaneously.]]>
Copyrights © 2026
