Publications International Journal Visual Defect Obfuscation Based Self-Supervised Anomaly Detection YeongHyeon Park, Sungho Kang, Myung Jin Kim, Yeonho Lee, Hyeong Seok Kim, Juneho Yi Scientific Reports, 2024 [paper] [poster] Boost-up Efficiency of Defective Solar Panel Detection with Pre-trained Attention Recycling YeongHyeon Park, Myung Jin Kim, Uju Gim, Juneho Yi IEEE Transactions on Industry Applications, 2023 [paper] [slide] Efficient Non-Compression Auto-Encoder for Driving Noise-Based Road Surface Anomaly Detection YeongHyeon Park, JongHee Jung IEEJ Transactions on Electrical and Electronic Engineering, 2022 [paper] Anomaly Detection in Particulate Matter Sensor using Hypothesis Pruning Generative Adversarial Network YeongHyeon Park, Won Seok Park, Yeong Beom Kim ETRI Journal, 2020 [paper] The CNN-based Coronary Occlusion Site Localization with Effective Preprocessing Method YeongHyeon Park, Il Dong Yun, Si-Hyuck Kang IEEJ Transactions on Electrical and Electronic Engineering, 2020 [paper] Preprocessing Method for Performance Enhancement in CNN-based STEMI Detection from 12-lead ECG YeongHyeon Park, Il Dong Yun, Si-Hyuck Kang IEEE Access, 2019 [paper] Arrhythmia detection in electrocardiogram based on recurrent neural network encoder–decoder with Lyapunov exponent YeongHyeon Park, Il Dong Yun IEEJ Transactions on Electrical and Electronic Engineering, 2019 [paper] Fast Adaptive RNN Encoder–Decoder for Anomaly Detection in SMD Assembly Machine YeongHyeon Park, Il Dong Yun Sensors, 2018 [paper] International Conference Feature Attenuation of Defective Representation Can Resolve Incomplete Masking on Anomaly Detection YeongHyeon Park, Sungho Kang, Myung Jin Kim, Hyeong Seok Kim, Juneho Yi IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPR 2025 VAND3.0 workshop) (Accepted) [arXiv] [poster] [2025] Contrastive Language Prompting to Ease False Positives in Medical Anomaly Detection YeongHyeon Park, Myung Jin Kim, Hyeong Seok Kim IEEE International Symposium on Biomedical Imaging (ISBI 2025) [arXiv] [poster] [2025] Encouraging LLM Thought Improvements for Medical Diagnosis Consistency Myung Jin Kim YeongHyeon Park IEEE International Symposium on Biomedical Imaging (ISBI 2025, 1-Page Paper) [poster] Exploiting Connection-Switching U-Net for Enhancing Surface Anomaly Detection YeongHyeon Park, Sungho Kang, Myung Jin Kim, Yeonho Lee, Juneho Yi IEEE International Conference on Electrical, Control and Instrumentation Engineering (ICECIE 2024) [paper] [slide] Neural Network Training Strategy to Enhance Anomaly Detection Performance: A Perspective on Reconstruction Loss Amplification YeongHyeon Park, Sungho Kang, Myung Jin Kim, Hyeonho Jeong, Hyunkyu Park, Hyeong Seok Kim, Juneho Yi IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024) [paper] [poster] Enhancing Defective Solar Panel Detection with Attention-guided Statistical Features using Pre-trained Neural Networks Hanbyul Lee*, YeongHyeon Park*, Juneho Yi (* Equal contribution) IEEE International Conference on Big Data and Smart Computing (BigComp 2024) [paper] Edge Storage Management Recipe with Zero-Shot Data Compression for Road Anomaly Detection YeongHyeon Park, Uju Gim, Myung Jin Kim IEEE International Conference on Information and Communication Technology Convergence (ICTC 2023) [paper] [slide] Exploiting Monocular Depth Estimation for Style Harmonization in Landscape Painting Sungho Kang, Hyunkyu Park, YeongHyeon Park, Yeonho Lee, Hanbyul Lee, Seho Bae, Juneho Yi IEEE International Conference on Knowledge Innovation and Invention (ICKII 2023) [paper] Unsupervised Image-to-Image Translation Based on Bidirectional Style Transfer Hyunkyu Park, Sungho Kang, YeongHyeon Park, Yeonho Lee, Hanbyul Lee, Seho Bae, Juneho Yi IEEE International Conference on Knowledge Innovation and Invention (ICKII 2023) [paper] Recycling for Recycling: RoI Cropping by Recycling a Pre-trained Attention Mechanism for Accurate Classification of Recyclables YeongHyeon Park, Myung Jin Kim, Won Seok Park, Juneho Yi IEEE International Conference on Smart Information Systems and Technologies (SIST 2023) [paper] [slide] Frequency of Interest-based Noise Attenuation Method to Improve Anomaly Detection Performance YeongHyeon Park, Myung Jin Kim, Won Seok Park IEEE International Conference on Big Data and Smart Computing (BigComp 2023) [paper] [slide] Attention! Is Recycling Artificial Neural Network Effective for Maintaining Renewable Energy Efficiency? YeongHyeon Park, Myung Jin Kim, Uju Gim IEEE Texas Power and Energy Conference (TPEC 2022) [paper] [slide] Non-Compression Auto-Encoder for Detecting Road Surface Abnormality via Vehicle Driving Noise YeongHyeon Park, JongHee Jung IEEE International Conference on Architecture, Construction, Environment and Hydraulics (ICACEH 2021) Best Conference Paper Award [paper] [award] Design of Cost-Effective Auto-Encoder for Electric Motor Anomaly Detection in Resource Constrained Edge Device YeongHyeon Park, Myung Jin Kim IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE 2021) [paper] Preprints Empirical Analysis of Anomaly Detection on Hyperspectral Imaging Using Dimension Reduction Methods Dongeon Kim, YeongHyeon Park arXiv:2401.04437 [arXiv] Concise Logarithmic Loss Function for Robust Training of Anomaly Detection Model YeongHyeon Park arXiv:2201.05748 [arXiv] Comparison of RNN Encoder-Decoder Models for Anomaly Detection YeongHyeon Park, Il Dong Yun arXiv:1807.06576 [arXiv] Patents Management Method of Foreign Matter for Liquid Products based on a Graph and an Device Supporting the Same KR Patent 1027374770000, Nov.2024. [link] Management Method of Foreign Matter for Liquid Products and an Device Supporting the Same KR Patent 1027374760000, Nov.2024. [link] ECG preprocessing method and STEMI detection method KR Patent 1024517510000, Sep.2022. [link] Road condition detection device and system, road condition detection method using the same KR Patent 1023465330000, Dec.2021. [link] Apparatus and Method for Anomaly Detection of SMD Assembly Device Operation based on Deeplearnig KR Patent 1021790400000, Nov.2020. [link]