Publications
My research focuses on AI and Machine Learning with applications in feature selection, model compression, efficient AI systems, and generative models. Below are my published works, organized by type, along with papers currently under review.
Journal Articles
Published in MDPI Symmetry, 2025
A neural network–based missing value imputation method that incrementally builds a cumulative feature set during training, avoiding reliance on naively imputed data and achieving superior performance across 25 benchmark datasets compared to conventional methods.
Recommended citation: Seo, Wangduk, et al. "ChainImputer: A Neural Network-Based Iterative Imputation Method Using Cumulative Features." Symmetry 17.6 (2025): 869.
Download Paper
Conference Papers
Published in IEEE International Conference on Consumer Electronics (ICCE), 2025
We present an approach that leverages natural language processing and diffusion-based generative models to automatically create music videos for children’s songs from lyrics, with experiments on 20 prompts showing that the Cascade SD model outperforms four alternatives across multiple evaluation metrics.
Recommended citation: Lee, Sanghyuck, Timur Khairulov, and Jaesung Lee. "Diffusion Model-Based Generative Pipeline for Children Song Video." 2025 IEEE International Conference on Consumer Electronics (ICCE). IEEE, 2025.
Download Paper
Published in Institute of Electronics and Information Engineers (IEIE), 2024
This survey reviews and classifies object detection methods for autonomous driving, highlights state-of-the-art approaches, and presents a taxonomy diagram to capture current research trends and challenges, particularly in ensuring reliability under adverse weather conditions.
Recommended citation: Khairulov, Timur, Sanghyuck Lee, and Jaesung Lee. "Review of current approaches in the area of object detection for autonomous vehicles." 대한전자공학회 학술대회 (2024): 2836-2839.
Download Paper
Theses
Published in Chung-Ang University Master Thesis, 2025
Master thesis exploring advanced methods for automated feature selection using joint entropy maximization and pattern discrimination techniques.
Published in Electrotechnical University "LETI" Bachelor Thesis, 2023
Bachelor thesis focusing on traffic sign recognition using deep learning approaches for autonomous driving applications.
Under Review
Information-Theoretic Unsupervised Feature Selection for Constructing Taxonomy Tree
Status: Under Review
Abstract: A novel approach to unsupervised feature selection leveraging information-theoretic principles for constructing hierarchical taxonomy structures.
BAGen: Background Animation Generation for LLM-Generated Lyric Towards Children's Songs
Status: Under Review
Abstract: An automated system for generating background animations synchronized with LLM-generated lyrics specifically designed for children's educational content.
Efficient Multi-Scale Network for Real-Time Crack Segmentation: Achieving High Accuracy-Speed Trade-off
Status: Under Review
Abstract: A multi-scale neural network architecture optimized for real-time crack detection and segmentation, balancing computational efficiency with segmentation accuracy.
Efficient Cheap All-Layer Aggregation Network for Time-Sensitive Time Series Classification
Status: Under Review
Abstract: A computationally efficient network architecture for time-sensitive time series classification tasks, utilizing all-layer aggregation techniques for improved performance.
