Researches
On-going Researches
- Neural Network Implementation and its Application
- Algorithm and Technique for Enhancing Networking Performance
- VLSI Testing and Analysis with Machine Learning
During his master course, his researches were focused on digital VLSI Testing. After receiving master degree, he has designed several driver ICs for motor & actuator and LCD backlight systems in Samsung Electro-mechanics.
Due to the increasing complexity in multimedia, mobile, and network computing systems in many-core era, high performance and low cost implementations should be achieved. In addition, there are many algorithmic and optimization problems that are deserved attention. Therefore, during Ph.D. course, his research interests have revolved around high-performance embedded & parallel systems and algorithm & optimizations. For the achievements in the embedded & parallel systems, he has researched several topics about multiprocessor system design, reconfigurable computing, deep packet inspection, and video signal coprocessor. In addition, meta-heuristics and real-time task scheduling approaches have been researched. After receiving Ph.D. degree, he worked in the field of flash memory controller design in Samsung Electronics. Especially, IO design and mixed-signal circuit design/implementation had been researched under his work in Samsung Electronics.
Combined with his knowledge of the mixed and digital hardware implementations, multidisciplinary researches can be performed. Bayesian circuit implementation and its application are the first topic that can use his combined knowledge about the mixed and digital hardware implementation. In addition, he will continue to researches about the pattern matching scheme using many-core system and energy and battery-aware techniques. Moreover, high-performance embedded & parallel systems and algorithm & optimizations are still in his interest.
In his dissertation, the parallel string matching scheme was proposed for reducing hardware cost. Even though the string pattern matching schemes were studied for the many applications in the deep packet inspection, he thinks that the pattern matching scheme for more complex patterns should be adopted using many cores for the success of industrial fields. In order to solve the energy and thermal problem in data center, mobile devices, and electric cars, energy and battery-aware task scheduling could be more focused in near future. In addition, various mixed-signal circuit design&implementations were his research topics, which were well done based on his field experience. Especially, IO circuit design/evaluation can be focused in mixed-signal circuit design. In addition, algorithm and technique for enhancing networking performance was his interest. Nowadays, he is focusing on the neural network implementation and its application.
Previous Researches
- Adaptable High Performance Packet Engine Design
- Bayesian Circuit Implementation and its Application
- Digital/Mixed-Signal Circuit Design/Implementation
- Energy and Battery-Aware Techniques
- High-Performance Embedded & Parallel Systems and Algorithm & Optimizations
- IO Circuit Design/Evaluation