I develop data-driven sensing and communication systems that enable intelligent machines to operate in complex physical environments. My research integrates machine learning, signal processing, and communication system modeling to improve how data is acquired, interpreted, and utilized when observations are incomplete or constrained.
My work spans wireless sensing, robotic perception, distributed sensor networks, and next-generation communication systems. I study adaptive sensing and inference methods that allow systems to actively select informative measurements in environments such as wireless communication networks, robotic platforms, and intelligent infrastructure.
With a background in electrical engineering and integrated circuit design, my research bridges algorithms, systems, and hardware implementation. My group develops efficient signal-processing architectures and communication chips in advanced CMOS technologies, supporting applications including IoT sensing networks, optical communication DSP, intelligent connected vehicles, and emerging 6G communication systems. I have also contributed to communication standards and industry collaborations that translate research innovations into deployable technologies.
How did you end up where you are today? (Your research journey)
My research journey began with a strong interest in signal processing and integrated circuit design. During my early work in communication systems, I realized that many challenges were not only about processing data efficiently but also about acquiring the right data from complex environments.
This realization gradually led me to explore the intersection of sensing, communication, and machine learning. Over time, my research expanded from algorithm design to system architectures and hardware implementations, enabling the development of communication and sensing systems that operate efficiently in real-world environments.
Working across academia, industry collaboration, and communication standardization has also shaped my perspective on building technologies that can scale beyond laboratory prototypes.
What is the most significant scientific contribution you would like to make?
One scientific contribution I would like to make is to transform sensing from a passive data collection process into an adaptive and decision-driven process. In many physical systems, uncertainty arises not because data analysis is insufficient, but because measurements themselves are limited.
By integrating data science methods with communication and sensing architectures, I hope to develop systems that can actively determine what information should be measured and how measurements should be performed. This perspective could fundamentally change how intelligent systems interact with complex environments.
What makes you excited about your data science and AI research?
What excites me most about data science and AI is the opportunity to connect physical systems with intelligent decision-making. Many real-world environments—such as wireless networks, robotic systems, and distributed sensing infrastructures—generate complex and incomplete data.
AI provides powerful tools to interpret this information, but its true potential emerges when it is integrated with the design of sensing and communication systems. I find it particularly exciting to study how data-driven methods can guide physical systems to collect better information in the first place.
What are 1-3 interesting facts about yourself?
- My research spans the full stack of intelligent sensing systems, from machine learning algorithms to communication systems and integrated circuit design.
- I enjoy working at the intersection of theory and real-world deployment, including collaborations with industry and contributions to communication standards.
- I am fascinated by how intelligent systems interact with the physical world, and I enjoy building experimental platforms that allow new ideas to be tested outside purely simulated environments.