Intelligent Multi-Sensor Detection System for Monitoring Indoor Building Fires

This paper presents a novel fire detection system to monitor various types of indoor building fires. While conventional studies mainly focus on developing fire sensing systems or detection algorithms, the proposed fire detection system integrates both sensing and detection phases to effectively utilize diverse sensor signals in real-time and detect fire outbreak at an early stage. The proposed fire sensing system gathers sensor data from multiple sensor types that are sensitive to measuring various components emitted from fires. Then, the collected sensor data are utilized by a similarity matching-based fire detection algorithm that captures diverse shape patterns that exist in the sensor signals under various fire scenarios, and detects the outbreak of fires at an early stage, with low false alarms. The real-life sensor data collected by the newly developed sensing system and experimental results conducted by the proposed fire detection algorithm show the effectiveness of the proposed fire detection system.

Automated summary

This paper presents a novel fire detection system that integrates fire sensing and detection phases to effectively monitor and detect indoor building fires at an early stage using diverse sensor signals. The system gathers sensor data from various sensor types sensitive to measuring components emitted from fires, and utilizes a similarity matching-based detection algorithm to capture shape patterns in sensor signals and reduce false alarms. Real-life sensor data and experimental results demonstrate the effectiveness of the proposed fire detection system.