Data Fusion and Real- Time Monitoring of Intelligent Fire Protection System Based on Internet of Things

This paper proposes a data fusion framework combined with machine learning algorithm, aiming to improve the real-time response capability of intelligent fire protection system in fire monitoring and disaster prediction. The system design adopts a multi-level data processing architecture, which reduces redundant information and improves the accuracy and timeliness of data by fusing data from different sensors. The system first collects environmental monitoring data through the sensor network and transmits it to the central processing unit. The central unit uses the data fusion algorithm to synthesize and optimize the information from different data sources to ensure that the obtained data is more accurate and has high timeliness. Then, the historical data is trained in combination with the machine learning model to build a fire risk prediction model, and generate warning information based on real-time data. The simulation results show that the system can accurately identify fire events and respond within 0.5 seconds under various disaster scenarios. Data analysis shows that the fusion algorithm improves the system accuracy and shortens the fire response time by about 30%, from an average of 7 seconds to 5 seconds. At the same time, the false alarm rate is reduced from 12.5% of the traditional method to 3.8%, effectively reducing the risk of false alarms and missed alarms. In addition, the accuracy of fire identification is improved by 15% compared with the traditional algorithm, from 78.2% to 93.5%.