A technology has been developed that allows indoor air quality measurement, which used to take more than 48 hours, to be completed in just 3 hours.
Professor Jeong Jae-hee from the Department of Mechanical Engineering at Sejong University noted on the 5th that he, along with Research Institute Ko Hyun-sik and Professor Heo Gi-joon from Chonnam National University, has developed a technology for rapidly detecting the concentration of bacteria in the air using artificial intelligence (AI). The time required for indoor air quality measurement has been reduced from over 48 hours to 3 hours, while maintaining an accuracy of over 95%.
Korea's indoor air quality management law utilizes the 'cultivation microorganism colony counting method' recommended by the World Health Organization (WHO) as the standard testing method. This method involves collecting microorganisms from the air onto a semi-solid nutrient medium and then incubating them for over 48 hours to visually count the concentration of the colonies that have multiplied. Although this method has the advantage of providing accurate counts, it takes more than two days to measure indoor air quality and requires manual participation for each task.
The research team developed a system that drastically shortens the detection time by combining various technologies while basing it on the standard cultivation method. First, to accurately detect the extremely low concentrations of microorganisms in the air, they implemented a technology that continuously concentrates bacteria in the air up to 10 million times by utilizing the inertia of particles.
Through a process where primary concentration occurs in the air and secondary particle concentration takes place in a liquid phase, they achieved world-class concentration performance. As a result, they were able to measure the bacterial colony count concentration in the air at a level of 30 CFU/㎥ with an accuracy of over 95% within 3 hours.
Professor Jeong Jae-hee stated, "This technology is an automated system that covers the entire process from sample collection to data analysis, incorporating various technologies such as aerosol particle sampling technology, a microscope platform capable of large-area observation, and machine learning-based image analysis technology," and added, "It lays the foundation for developing equipment that can overcome the shortcomings of the existing standard cultivation method."
References
Sensors and Actuators B: Chemical(2025), DOI : https://doi.org/10.1016/j.snb.2024.137084