Hyun-Myung Woo

Assistant Professor

Department of Biomedical & Robotics

Incheon National University

Educations

Ph.D. in Electrical & Computer Engineering, Texas A&M University (2022)

MS in Computer Science, Yonsei University (2010)

BA of Engineering, Yonsei University (2008)

Experience

Assistant Professor, Incheon National University Mar. 2023 - present

Research Associate, Brookhaven National Laboratory Sep. 2022 - Feb. 2023

Research Assistant, Texas A&M University Sep. 2017 - Dec. 2017 and Sep. 2019 - Aug 2022

Teaching Assistant, Texas A&M University Sep. 2015 - May 2016 and Sep. 2018 - May 2019

Research Engineer, LG Electronics Sep. 2016 - Mar. 2017

Lecturer, Yonsei University Mar. 2014 - Jun. 2014

Research Engineer, IDIS Jan. 2010 - Apr. 2014

Teaching Assistant, Yonsei University Mar. 2008 - Feb. 2010

Honor

2023 Academic Research Award, Incheon National University Mar. 2024

2023 Fall Excellence in Teaching Award, Incheon National University Mar. 2024

The Grand Prize, IDIS and ETNEWS Science and Technology & IT paper contest Dec. 2009

The Best Paper Award, KIIECT Fall Conference Oct. 2009

Summa Cum Laude, Yonsei University Feb. 2008

An Honor Prize for Academic Excellence, Yonsei University Fall 2005, and Spring 2006 and 2007

Scholarship for Academic Excellence for Academic Excellence, Yonsei University Fall 2005 - 2007

Openings

Our Computational Science Laboratory is currently accepting applications for Ph.D., MS, and Undergraduate research positions. These opportunities involve conducting cutting-edge research in mathematical optimization and machine/deep learning to address complex scientific and engineering challenges in fields such as bioinformatics, computational materials science, and applied mathematics. Interested candidates are encouraged to reach out via the contact page for further information.

Undergraduate Students

Taeyeong Jang

Taeyeong Jang

Undergraduate Intern

Research Interests: Bioinformatics, Machine Learning

Juhyun Yeom

Juhyun Yeom

Undergraduate Intern

Research Interests: WIFI Sensing, Deep Learning

Jiho Han

Jiho Han

Undergraduate Intern

Research Interests: Multi-Modal Learning

Lee Eun Seok

Lee Eun Seok

Undergraduate Intern

Research Interests: WIFI Sensing, Deep Learning

Yoonsang Park

Yoonsang Park

Undergraduate Intern

Research Interests: Image Processing, Deep Learning

Research

1. Scientific Machine Learning (sciML)


Accelerating Objective-Driven Uncertainty Quantification & Optimal Experimental Design

Accelerating Optimal Experimental Design for Robust Synchronization of Uncertain Kuramoto Oscillator Models Using Machine Learning

Addressing the challenges posed by inherent uncertainties in complex dynamical systems, this study leverages machine learning to achieve robust synchronization of Kuramoto oscillators. By systematically exploring design parameters and establishing optimal control strategies, the proposed technique ensures resilient performance even in highly variable conditions. This advancement is instrumental in real-time control and analysis of dynamic systems.

Neural Message Passing for Objective-Based Uncertainty Quantification and Optimal Experimental Design

This work introduces a novel neural message-passing framework that quantifies experimental uncertainty while simultaneously determining the optimal design under resource constraints. By integrating domain-specific objectives into the uncertainty assessment, the methodology enhances experimental efficiency and reliability. The approach offers a versatile framework applicable to a range of scientific inquiries, thus expediting the research cycle.

2. Optimal Decision Making under Uncertainty


High-Throughput Virtual Screening Pipelines

Optimal Decision-Making in High-Throughput Virtual Screening Pipelines

This research develops an innovative decision-making algorithm tailored for large-scale virtual screening processes. By automating data processing and analysis, it significantly reduces both time and cost in selecting optimal experimental candidates. The method holds promise for accelerating breakthroughs in drug discovery, materials science, and other domains that rely on high-throughput evaluations, with ongoing extensions into reinforcement learning for policy optimization.

3. Bioinformatics


Biological Network Analysis and Generation

Comprehensive Updates in Network Synthesis Models to Create an Improved Benchmark for Network Alignment Algorithms

This study presents a state-of-the-art benchmark for network alignment by updating synthesis models with the latest biological data. Through rigorous statistical analysis of protein–protein interaction networks, it quantitatively captures complex structural features. The resulting framework provides a robust foundation for further advancements in network generation and analysis.

Biological Comparative Analysis

MONACO: Accurate Biological Network Alignment through Optimal Neighborhood Matching between Focal Nodes

By introducing an optimal neighborhood matching algorithm, this work significantly refines the alignment of protein–protein interaction (PPI) networks. It adeptly captures subtle interaction patterns, offering deeper insights into functional similarities and disease mechanisms. The method sets a new standard for comparative biological network analysis.

Network-Based RNA Structural Alignment Through Optimal Local Neighborhood Matching

Focusing on the three-dimensional structure of RNA molecules, this study employs a network-based approach to align RNA structures optimally. It quantifies both similarities and variations with high precision, thereby contributing to a better understanding of RNA function and interaction. This technique is poised to become a key tool in structural biology and genomics.

DNA/RNA Sequencing Data Analysis

Our research in DNA/RNA sequencing data analysis involves developing robust computational methods designed to decipher complex genomic information from high-throughput sequencing experiments. By leveraging state-of-the-art algorithms for sequence alignment, variant calling, and differential expression analysis, we are equipped to uncover genetic variations, expression patterns, and regulatory mechanisms underlying a wide range of biological processes and diseases. Integrating statistical models with advanced machine learning techniques, our approach is poised to enhance data accuracy and processing speed, thereby opening avenues for breakthroughs in personalized medicine, epigenomics, and single-cell sequencing technologies

4. Statistical Signal Processing


Wireless Communication Systems

Reduced-Complexity ML Signal Detection for Spatially Multiplexed Signal Transmission over MIMO Systems with Two Transmit Antennas

This research tackles the challenge of signal detection in MIMO systems by applying machine learning to reduce computational complexity. The proposed algorithm enhances detection accuracy and operational speed, thereby significantly improving real-time performance in wireless communications. Its implications extend to next-generation communication networks where rapid and reliable data transmission is paramount.

5. Biomedical Applications


Wireless Medical Devices for Therapeutic and Neuroscience Applications

AI-Enabled High-Throughput Wireless Telemetry for Effective Photodynamic Therapy

By integrating AI with high-speed wireless telemetry, this study revolutionizes photodynamic therapy through real-time monitoring and control. The automated data acquisition and analysis facilitate personalized treatment strategies, enhancing therapeutic outcomes. This non-invasive system is set to transform clinical practice in precision medicine.

Machine Learning Enabled Adaptive Wireless Power Transmission System for Neuroscience Study

Targeting the unique challenges of neuroscience research, this work introduces an adaptive wireless power transmission system powered by machine learning. It dynamically optimizes power delivery to ensure stable data collection in non-invasive experimental setups. This breakthrough supports advanced neurophysiological studies and could redefine experimental paradigms in brain research.

Publications


Journals

[13] Hyun-Myung Woo, Xiaoning Qian, Li Tan, Shantenu Jha, Francis J. Alexander, Edward R. Dougherty, Byung-Jun Yoon, "Optimal Decision Making in High-Throughput Virtual Screening Pipelines," Patterns (2023).

[12] Qihua Chen, Xuejin Chen, Hyun-Myung Woo, and Byung-Jun Yoon, "Neural Message passing for Optimal Experimental Design in Complex Uncertain Systems," Engineering Applications of Artificial Intelligence 123 (2023): 106171.

[11] Hyun-Myung Woo¶, Omar Allam¶, Junhe Chen, Seung Soon Jang, and Byung-Jun Yoon, "Optimal high-throughput virtual screening pipeline for efficient selection of redox-active organic materials," iScience, 105735. (¶: Equally contributed author)

[10] Woo Seok Kim¶, M. Ibrahim Khot¶, Hyun-Myung Woo¶, Sungcheol Hong, Dong-Hyun Baek, Thomas Maisey, Brandon Daniels, Patricia Coletta, Byung-Jun Yoon, David Jayne, and Sung Il Park, "AI-enabled, implantable, multichannel wireless telemetry for photodynamic therapy," Nature Communications, 13, 2178 (2022). https://doi.org/10.1038/s41467-022-29878-1.(¶: Equally contributed author)

[9] Hyun-Myung Woo, Youngjoon Hong, Bongsuk Kwon, and Byung-Jun Yoon, "Accelerating Optimal Experimental Design for Robust Synchronization of Uncertain Kuramoto Oscillator Model Using Machine Learning," IEEE Transactions on Signal Processing, doi: 10.1109/TSP.2021.3130967.

[8] Hyun-Myung Woo and Byung-Jun Yoon, "MONACO: accurate biological network alignment through optimal neighborhood matching between focal nodes," Bioinformatics, btaa962.

[7] Minyu Gu, Daniel Vorobiev, Woo Seok Kim, Hung-Ta Chien, Hyun-Myung Woo, Sung Cheol Hong, and Sung Il Park. "A novel approach using an inductive loading to lower the resonant frequency of a mushroom-shaped high impedance surface," Progress In Electromagnetics Research M 90 (2020): 19-26. doi:10.2528/pierm19110607.

[6] Hyun-Myung Woo¶, Hyundoo Jeong¶, and Byung-Jun Yoon, "NAPAbench 2: A network synthesis algorithm for generating realistic protein-protein interaction (PPI) network families," Journal Article published 27 Jan 2020 in PLOS ONE volume 15 issue 1 on page e0227598. (¶: Equally contributed author)

[5] Hyun-Myung Woo, Jaekwon Kim, Joo-Hyun Yi, and Yong-Soo Cho, "Reduced complexity ML signal detection for spatially multiplexed signal transmission over MIMO systems with two transmit antennas," IEEE Trans. Veh. Tech., vol. 59, no. 2, pp. 1036-1041, February 2010.

[4] Hyun-Myung Woo, Jaekwon Kim, Joo-Hyun Yi, S. Y. Choi, and Yong-Soo Cho, "A Computationally Efficient ML Signal Detection Technique for MIMO Systems with Two Spatial Streams," SK Telecommun. Review Vol. 19-3, pp. 439-454, June 2009.

[3] Hoon Hur, Hyun-Myung Woo, Won-Young Yang, Seungjae Bahng, Youn-Ok Park, and Jaekwon Kim, "A computationally efficient search space for QRM-MLD signal detection," IEICE Trans. Commun. Vol. E92-B, no. 3, pp. 1045-1048, March 2009.

[2] Hoon Hur, Hyun-Myung Woo, S. J. Bahng, Y. O. Park, and Jaekwon Kim, "A Novel Soft Output Generation Method for Spatially Multiplexed MIMO Systems," KICS Journal Vol. 33-4, pp. 394-402, April 2008.

[1] Hoon Hur, Hyun-Myung Woo, W. Y. Yang, S. J. Bahng, Y. O. Park, and Jaekwon Kim, "An Improved Search Space for QRM-MLD Signal Detection," KICS Journal Vol. 33-4, pp. 403-410, April 2008.

Conferences

[9] Woo Seok Kim, Hyun-Myung Woo, M. Ibrahim Khot, Sungcheol Hong, David G. Jayne, Byung-Jun Yoon, and Sung Il Park, "AI-Enabled High-Throughput Wireless Telemetry for Effective Photodynamic Therapy," In 2021 55th Asilomar Conference on Signals, Systems, and Computers, pp. 811-815. IEEE.

[8] Hyun-Myung Woo and Byung-Jun Yoon, "Network-Based RNA Structural Alignment Through Optimal Local Neighborhood Matching," Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, Nov. 1-4, 2020.

[7] Hyun-Myung Woo, Woo Seok Kim, Sungcheol Hong, Vivekanand Jeevakumar, Clay M. Smithhart, Theodore J. Price, Byung-Jun Yoon, and Sung Il Park, "Machine Learning Enabled Adaptive Wireless Power Transmission System for Neuroscience Study," Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, Nov. 1-4, 2020.

[6] Hyun-Myung Woo, Hyundoo Jeong, and Byung-Jun Yoon, "Comprehensive Updates in Network Synthesis Models to Create An Improved Benchmark for Network Alignment Algorithms," Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics - BCB 2018.

[5] Hyun-Myung Woo, and Jaekwon Kim, "Reduced complexity ML signal detection for spatially multiplexed signal transmission over MIMO systems with two transmit antennas," KIIECT Fall Conference, Gumi-si, October 24, 2009.

[4] Hyun-Myung Woo, and Jaekwon Kim, "Reduced complexity ML signal detection for spatially multiplexed signal transmission over MIMO systems with two transmit antennas," KIISE, Gangwon Branch Conference, Wonju-si, June 12, 2009.

[3] Hyun-Myung Woo, Jaekwon Kim, J. H. Yi, and Yong-Soo Cho, "Reduced complexity ML signal detection for spatially multiplexed signal transmission over MIMO systems with two transmit antennas," JCCI, Gwangju, April 15 - 17, 2009.

[2] Hyun-Myung Woo, and Jaekwon Kim, "A Comparative Studies of Channel Shortening Techniques for OFDM System," KIIECT Summer conference, Kwandong Univ., Gangneung-si, June 13 - 14, 2008.

[1] Hoon Hur, Hyun-Myung Woo, W. Y. Yang, S. J. Bahng, Y. O. Park, and Jaekwon Kim, "An Improved Search Space for QRM-MLD Signal Detection," JCCI, Jeju-si, April 23 - 25, 2008.

Current Projects


Reinforcement Learning-based Optimal Decision Making in High-Throughput Virtual Screening (HTVS) Pipelines. The National Research Foundation of Korea (NRF) (2023~2025)

Knowledge Discovery using Machine Learning for the Objective-based Optimal Experimental Design. Incheon National University (2024~2025)

Previous Projects


Accelerating the Objective-based Optimal Experimental Design using Machine Learning. Incheon National University (2023~2024)

talks


[6] "Accelerating Objective-Driven Optimal Experimental Design using Machine Learning," @ Yonsei University Mirae Campus, Oct, 30, 2023.

[5] "Accelerating Objective-Driven Optimal Experimental Design using Machine Learning," @ Sungkyunkwan University, Apr, 24, 2023.

[4] "Optimal Decision Making in High-Throughput Virtual Screening Pipelines," BioSeminar @ Texas A\&M University, Apr, 29, 2022.

[3] "Optimal decision making for accelerating scientific discovery," Computational Science Initiative Seminar @ Brookhaven National Laboratory, Mar, 25, 2022.

[2] "Machine Learning Enabled Adaptive Wireless Power Transmission System for Neuroscience Study," BioSeminar @ Texas A&M University, Oct, 23, 2020.

[1] "Accurate biological network alignment through an iterative optimal mapping between neighborhood sets of focal nodes," BioSeminar @ Texas A&M University, Oct, 4, 2019.

Let's Get In Touch!


Please contact me if you may have any questions! :D