This research presents a comparative analysis of traditional AI models and fuzzy logic-enhanced AI
systems in decision support applications, particularly focusing on disaster management, healthcare,
and autonomous systems. Traditional AI models, while effective, often struggle to handle uncertainty
and imprecise data, which are inherent in real-world scenarios such as predicting flood risks,
diagnosing diseases, and guiding autonomous drones. By integrating fuzzy logic into AI frameworks,
this study demonstrates significant improvements in key performance metrics, including accuracy,
precision, recall, and decision robustness. The results show that fuzzy logic-enhanced AI models provide
a more flexible and adaptive approach to decision-making, offering superior handling of ambiguous
and incomplete information. These findings highlight the potential of hybrid AI-fuzzy logic systems
in enhancing decision support under uncertain conditions, contributing to more reliable and robust
solutions in critical sectors.
