<![CDATA[Purpose of the study: This study aims to develop an intelligent indoor fire detection system by integrating low-cost Internet of Things (IoT) sensors with machine learning-based multi-sensor data fusion to improve early fire hazard detection accuracy while reducing false alarms compared to conventional single-sensor fire detection systems. Methodology: The system is implemented using an ESP32 microcontroller connected to temperature, humidity, flame, and sound sensors for real-time data acquisition. A dataset of 1,500 sensor samples is collected and labeled into Normal, Fire-Risk, and Fire classes. Decision Tree, Support Vector Machine, and Random Forest classifiers are trained and evaluated using Python-based machine learning libraries. Main Findings: Experimental results indicate that the Random Forest model outperforms the other classifiers, achieving 95% overall accuracy, perfect recall for fire events, and a Macro ROC-AUC score of 0.993. Feature importance analysis reveals that humidity and temperature are the most influential parameters for early fire detection in indoor environments. Novelty/Originality of this study: This study proposes a lightweight intelligent fire detection framework that integrates multi-sensor Internet of Things data including temperature, humidity, flame, and sound signals with machine learning–based classification for indoor environments. Unlike conventional systems that rely on single-sensor or threshold-based detection, the proposed approach utilizes multi-sensor data fusion and ensemble learning to improve early fire-risk identification while remaining computationally efficient for low-cost platforms such as the ESP32 microcontroller.]]>
Copyrights © 2026
