<![CDATA[Flood is a natural disaster that frequently occurs and causes significant material and social losses. Conventional flood monitoring systems are generally reactive and rely on threshold-based approaches, which limits their effectiveness in supporting early detection. This study proposes an Internet of Things (IoT)-based early flood detection system using the Random Forest algorithm. The developed system collects hydrological data, including water level and flow velocity, through IoT sensors that periodically transmit data to a server for further processing. The collected data are then aggregated and classified into flood and non-flood conditions using a Random Forest model. Model performance is evaluated using accuracy, precision, recall, f1-score, confusion matrix, and 5-fold cross-validation. Experimental results indicate that the proposed model achieves an accuracy of 97.26% with a mean cross-validation score of 0.9863. However, the recall for flood events remains limited due to data imbalance and the relatively small number of flood occurrences. Despite these limitations, the proposed system demonstrates potential to support the development of early flood warning systems and can be further improved by incorporating longer and more diverse historical datasets.]]>
Copyrights © 2026
