Dae-Yeong is a graduate student conducting interdisciplinary research at the intersection of animal welfare, computer vision, and data science. His primary focus lies in developing predictive and monitoring algorithms for livestock environments and animal health using time-series analysis and deep learning models such as LSTM. He integrates multimodal data—including environmental sensor readings, video footage, and audio signals—to build practical and scalable smart farming systems. His work spans multiple applications, including greenhouse climate forecasting, automated obstacle detection in agricultural machinery, and real-time animal behavior recognition. In addition, he is actively involved in planning and executing government-funded R&D projects aimed at enhancing sustainability and efficiency in agriculture.