About Me

I have been actively involved as a wireless communication and AI researcher Smart Networking Lab (SNL) for approximately four years, beginning from my undergraduate studies and continuing through my Master’s degree in Computer Science at Chosun University. My expertise centers on optimizing wireless network resources and improving efficiency through various reinforcement learning algorithms. Notably, I designed the multi-objective asynchronous advantage single actor-multiple critics (MO-A3Cs) algorithm for transmission power allocation, which jointly enhances network spectral and energy efficiency.

A multi-modal approach is crucial for AI to process sensory inputs such as vision, smell, and texture. Additionally, reinforcement learning is essential for addressing adaptive decision-making and control challenges, emulating human-like thinking. My primary research focus lies in optimizing objective functions and building adaptive decision-making intelligence based on reinforcement learning algorithms. I am also deeply involved in developing sensor-fusion and multimodal AI models that aim to understand contexts in a human-like manner.

As a research assistant, I have developed expertise in using deep reinforcement learning to optimize objectives and solve complex decision-making problems. I have also designed and implemented wireless testbeds, including software-defined radio (SDR)-based communication systems, end-to-end TDD/TDMA setups, MIMO-OFDM systems, and IoT/ICT-based data communication systems. Recently, I led a project applying multimodal AI techniques for object detection, motion estimation, and tracking using fused WiFi signals and camera data. My responsibilities included hardware setup and developing multimodal AI models using the knowledge distillation method.

Lastly, my interests include music, research, and running a YouTube channel where I share the methodologies and results of my research.