News

PhD Candidate Seohyun Yoo's Research Team Wins Excellence Award in 'Women Graduate Students Engineering Research Team Program'

  • 12/31/2025
  • Views 12

A research team led by PhD candidate Seohyun Yoo (Department of Software Engineering, College of Engineering) at Jeonbuk National University (JBNU) received the Excellence Award in the 2025 Women Graduate Students Engineering Research Team Support Program organized by the Korea Foundation for the Advancement of Women in Science and Technology (WISET). 

 

The research team was led by PhD candidate Seohyun Yoo as the Principal Investigator (PI), with undergraduates Kwon Ye-won and Kim Yun-su participating. Students from Jeonju Solnae High School and Daejeon Science High School also joined the hands-on research, forming an integrated research team linking graduate, undergraduate, and high school levels. The project was carried out under the supervision of Professor Jae-hyeok Cho of JBNU's Department of Software Engineering.

 

To address the recurring missing-data problem in IoT environmental sensor data, the team developed an AI-based missing-data imputation model that combines multi-layer stacking with a scoring method.

 

Experimental results using fine dust (particulate matter), carbon dioxide (CO₂), and temperature and humidity sensor data collected from five locations in the Seoul metropolitan area showed that the proposed model achieved 20–30% improved reconstruction performance in terms of RMSE and MAE compared with conventional mean-imputation and KNN methods.

 

The study received high evaluation not only for its outcomes but also for its educational value. High school mentees performed data preprocessing, visualization, and basic model training themselves, gaining hands-on experience across the AI research process. They reported that they "felt more deeply the importance of the process than the results."

 

PhD candidate Seohyun Yoo stated, "Building on this achievement, we are developing a lightweight AI model for small-scale environmental monitoring that can be used by schools, research institutes, and public agencies," and added, "In the future, we plan to expand the research into an environment–health correlation analysis platform that integrates environmental and health data."



미리보기

Loading