IoT-based fuzzy logic system for real-time flooded road detection and decision support

Flooding remains a critical challenge in urbanenvironments, often disrupting transportation systems andendangering drivers who must decide whether to cross inundatedroads without precise knowledge of water depth. Existing IoTbasedflood monitoring systems primarily emphasize dataacquisition and remote alerts but rarely support localized, realtimedecision-making for road safety. This study proposes an IoTbasedflood detection and decision-support system that integratesSugeno-type fuzzy logic inference directly into distributed edgenodes to evaluate flooded road conditions in real time. The systememploys multiple JSN-SR04T ultrasonic sensors and WeMos D1microcontrollers interconnected via a wireless network to measurewater levels across multiple road segments. Each nodeautonomously processes sensor inputs to classify road conditionsinto three categories—Safe, Caution, and Not Safe—and displaysresults locally via OLED SSD1306 and RYG (Red-Yellow-Green)LED indicators. Experimental results demonstrate that theproposed system achieves an average sensor error of 2.2 cmcompared to calibrated measurements and maintains wirelesscommunication stability up to 25 meters with an average systemresponse time of 1.19 seconds. Furthermore, the fuzzy inferenceoutputs from the embedded system closely matched MATLABbasedsimulations, validating computational consistency andinference reliability. The integration of edge-level fuzzy decisionmakingwithin distributed IoT nodes represents a key innovation,enabling autonomous flood assessment with minimal latency. Thisstudy contributes a low-cost, scalable, and intelligent frameworkfor enhancing road safety and smart city flood resilience,particularly in developing urban regions prone to recurrentinundation.