A team of South Korean researchers has developed an advanced fire detection system that significantly reduces false alarms—also known as “unwanted alarms”—which occur even in the absence of an actual fire. The technology is now nearing commercialization and is expected to greatly reduce the social and financial costs associated with these incidents.
False Alarm Prevention. Image Credit: Electronics and Telecommunications Research Institute (ETRI)
The Electronics and Telecommunications Research Institute (ETRI) has created an AI-powered sensor that prevents false alarms by distinguishing between smoke from actual fires and non-fire aerosols. It does this by analyzing how different wavelengths of light scatter when interacting with various particles.
Traditional photoelectric smoke detectors work by placing an infrared light source and a photodiode inside the detector. When smoke particles enter, they scatter the infrared light, which the photodiode captures. If the scattered light reaches a certain intensity, the alarm is triggered.
However, the problem with current detectors is that they can’t differentiate between smoke from a real fire and harmless airborne particles. Everyday activities—such as cooking, smoking, or even humidity—can generate aerosols that trigger false alarms.
According to the National Fire Agency, between 2021 and July 2022, South Korea recorded 258,220 fire engine dispatches—96.6 % of which were due to false alarms.
ETRI’s AI-powered sensor eliminates this issue by measuring how different aerosol particles scatter light at multiple wavelengths. By analyzing these unique scattering patterns, the system can accurately determine whether the detected particles are from a fire or not.
ETRI plans to first integrate this technology into aspirating smoke detectors, which actively draw in air using a fan for faster smoke detection. These detectors are commonly used in semiconductor clean rooms and server rooms, where early smoke detection is critical. However, they are also more prone to false alarms due to dust and moisture.
Most aspirating smoke detectors currently on the market are expensive imported products that lack the ability to distinguish between fire-related and non-fire aerosols. If a domestic version equipped with this AI-based false alarm prevention system is introduced, it could be highly competitive in both South Korean and international markets.
After it is commercialized, this technology will significantly reduce the number of false alarms caused by non-fire incidents, thus reducing the cost of fire engine dispatches and wasteful use of firefighting resources that are estimated at KRW 20 billion annually.
Kang Bok Lee, Director, Defense & Safety Intelligence Research Section, Electronics and Telecommunications Research Institute
Beyond fire detection, this light-scattering spectrum measurement technology has promising applications in cosmetics, medical diagnostics, environmental monitoring, and industrial safety. ETRI is currently in discussions with companies about bringing the technology to market.