SNU Civil Engineering Ph.D. Student Soyeon Park Wins First Place at ASCE EMI Student Paper Competition
- Proposes cutting-edge deep learning technique for vibration-based damage detection
- Demonstrates outstanding research capabilities at the world’s top conference in engineering mechanics


▲ Soyeon Park, Ph.D. student in the Department of Civil and Environmental Engineering at Seoul National University, receives the first-place award from the President and Judging Chair of EMI

Seoul National University College of Engineering announced that Soyeon Park, a doctoral student in the Department of Civil and Environmental Engineering, has won first place at the student paper competition hosted by the Structural Health Monitoring and Control Committee of the Engineering Mechanics Institute (EMI), under the American Society of Civil Engineers (ASCE).

The ASCE EMI Conference, which features around 1,000 presenters across more than 150 sessions annually, is considered the most prestigious international academic conference in the field of engineering mechanics. The student paper competition, held concurrently, selects five finalists through preliminary reviews of all 18 submitted papers. The final round includes live presentations and Q&A evaluations, with one top prize awarded.

In this year’s competition, So-Yeon Park won first place for her paper titled “Vibration-based Damage Assessment Enhanced by Integrating Deep Support Vector Description with Convolutional Autoencoder.” Her research was recognized for its significant contributions to the field of structural health monitoring. The paper was co-advised by Professor Sun-Joong Kim from the Department of Civil Engineering at the University of Seoul and Professor Junho Song from the Department of Civil and Environmental Engineering at Seoul National University.

Notably, Park’s paper proposes a novel deep learning-based hybrid model that enables early detection of structural damage using vibration data. By combining Convolutional Autoencoder and Deep Support Vector Data Description (Deep-SVDD) into an innovative framework, the model simultaneously performs unsupervised feature extraction and boundary-aware anomaly detection. This allows for the sensitive identification of even subtle structural damage without requiring extensive data labeling.

Park commented, “I am honored that my research was recognized at such a prestigious international conference. I hope this technology will be implemented in real-world structural health monitoring systems and contribute to the maintenance and management of critical infrastructure.”

Looking ahead, Park plans to expand this research with her advisor Professor Song by applying the methodology to large-scale infrastructure. They aim to integrate the system with real-time monitoring platforms to develop a resilience-based maintenance and decision support system.


[Reference Materials]
- Official Announcement of 2025 ASCE EMI Student Paper Competition Winners:
https://www.asce.org/communities/institutes-and-technical-groups/engineering-mechanics-institute/news/2025-emi-student-competition-winners

[Contact Information]
Prof. Junho Song, Department of Civil and Environmental Engineering, Seoul National University / +82-2-880-8397 / junhosong@snu.ac.kr