About

Sang Hyuk Son is an Emeritus Professor of Computer Science at the University of Virginia. He is an IEEE Fellow and has served as a Professor of the Computer Science Department at the University of Virginia, as well as a WCU Chair Professor at Sogang University. His educational background includes a B.S. degree in electronics engineering from Seoul National University, an M.S. degree from KAIST, and a Ph.D. in computer science from the University of Maryland, College Park. Prof. Son has held visiting positions at KAIST, City University of Hong Kong, Ecole Centrale de Lille in France, and at Linkoping University and University of Skovde in Sweden. His professional service includes serving as the chair of the IEEE Technical Committee on Real-Time Systems during 2007-2008, and he is an associate editor for the Real-Time Systems Journal and the Journal of Computing Science and Engineering. He has also served on the editorial boards of IEEE Transactions on Computers and IEEE Transactions on Parallel and Distributed Systems, and is a member of the steering committees for RTCSA, Cyber Physical Systems Week, and SEUS. His research interests encompass cyber physical systems, real-time and embedded systems, database and data services, and wireless sensor networks. He has authored or co-authored over 290 papers and edited or authored four books in these areas. His research has been funded by various organizations including the National Science Foundation, DARPA, the Office of Naval Research, the Department of Energy, the National Security Agency, IBM, and the National Research Foundation of Korea.

Research topics

• Computer Science
• Computer network
• Engineering
• Machine Learning
• Distributed computing
• Data science
• Telecommunications
• Business
• World Wide Web
• Operations research

Selected publications

• Time-Aware World Model for Adaptive Prediction and Control

  ArXiv.org · 2025-06-10

  preprintOpen access

  In this work, we introduce the Time-Aware World Model (TAWM), a model-based approach that explicitly incorporates temporal dynamics. By conditioning on the time-step size, Δt, and training over a diverse range of Δt values -- rather than sampling at a fixed time-step -- TAWM learns both high- and low-frequency task dynamics across diverse control problems. Grounded in the information-theoretic insight that the optimal sampling rate depends on a system's underlying dynamics, this time-aware formulation improves both performance and data efficiency. Empirical evaluations show that TAWM consistently outperforms conventional models across varying observation rates in a variety of control tasks, using the same number of training samples and iterations. Our code can be found online at: github.com/anh-nn01/Time-Aware-World-Model.

  PublisherOA PDFDOI

• Semiconductor Memories for Low-Power and Low-Compute Hardware-Oriented Artificial Intelligence System

  2025-07-12

  article

  The development of artificial intelligence (AI) technologies for reasoning based on big data is rapidly advancing day by day. Moving beyond large language models (LLMs), recent technological trends show the emergence of large vision models (LVMs), indicating that the application scope of AI is expanding at an accelerated pace. Currently, most AI services are implemented through software technologies. However, from the perspective of energy saving and environmental pollution, it is a crucial turning point where a shift to hardware-oriented AI technology must take place. Hardware-oriented AI aims to move away from the conventional series high-speed operation, towards low-power computing technologies that maximize computational concurrency. In order to achieve this goal, changes in computing architecture are necessary, with semiconductor memory technology playing a central role. Simultaneously, recent research indicates that high-speed, large-scale computation systems naturally lead to increased system temperatures, which can produce gases harmful to human health. Although these goals differ in terms of the original starting points, all these technological objectives share a common aim of low-power and small-number computing. This paper examines next-generation AI computing technologies based on large-capacity memory technologies, specifically dynamic random-access memory (DRAM) and flash memories built on relatively mature Si fabrication processing suitable for chip production, evaluating pattern recognition accuracies.

  PublisherDOI

• A Multiagent DRL-Based Method for Cooperatively Determining Coordination and Lane Change of Vehicles at Signal-Free Intersections With Free-Direction Lanes

  IEEE Internet of Things Journal · 2025-07-01

  articleSenior author

  Owing to the growing population and rapid urbanization, intersections, where traffic converges from various directions, have become major bottlenecks for road capacity due to frequent congestion. Recent advances in Connected and Autonomous Vehicle (CAV) technology enable signal-free intersections, where CAVs collaborate to cross intersections without collisions. Most existing signal-free intersection control methods focus on accommodating conflicts among vehicles inside the intersection and fixed-direction lanes are commonly adopted. However, the use of fixed-direction lanes is a legacy from conventional signalized intersections, where turning lanes are predetermined and fixed, so as to direct vehicles with different turning intentions to different lanes and avoid collisions. In this paper, we aim to make full utilization of the capacity of signal-free intersections by making use of free-direction lanes, which allow vehicles to make right, straight or left turns from any lane. To this end, we propose a cooperative multi-agent Deep Reinforcement Learning (DRL)-based control method for signal-free intersections with free-direction lanes. Specifically, we first study the problem of cooperatively determining coordination of vehicles inside the intersection and lane changes of vehicles on the incoming arms. Then, a multi-agent DRL-based control method for cooperatively determining coordination and lane-change of vehicles for signal-free intersections with free-direction lanes, named CD-CLC, is proposed for maximizing non-conflicting vehicles crossing the intersection simultaneously while taking vehicle fairness into consideration, to minimize travel delays of vehicles and improve traffic efficiency. Extensive experiments have been conducted to compare CD-CLC with other state-of-the-art methods to demonstrate the effectiveness of the proposed approach.

  PublisherDOI

• A novel 2T0C DRAM architecture using feedback field-effect transistors for reliability improvement

  Current Applied Physics · 2025-08-21 · 1 citations

  article
  PublisherDOI

• Toward Connected, Cooperative and Intelligent IoV

  2024-01-01 · 1 citations

  bookOpen accessSenior author

  This book presents recent advances in Internet of Vehicles in the areas of e.g. V2X communications, optimization technologies, and AI-enabled applications.

  PublisherOA PDFDOI

• Deep Q-Learning-Based Adaptive Multimedia Streaming in Vehicular Edge Intelligence

  2023-12-20

  book-chapterSenior author
  PublisherDOI

• Toward Timely and Reliable DNN Inference in Vehicular Edge Intelligence

  2023-12-20

  book-chapterSenior author
  PublisherDOI

• Cascade Windows-Based Multi-Stream Convolutional Neural Networks Framework for Early Detecting In-Sleep Stroke Using Wristbands

  IEEE Access · 2023-01-01 · 9 citations

  articleOpen accessSenior author

  A stroke, particularly when it occurs during sleep, is likely to have a negative prognosis due to delayed detection. Timely and early detection plays a vital role in ensuring prompt administration of reperfusion therapy and preventing permanent disabilities. To address this, we propose a wearable system comprising two wristbands that monitor asymmetric motion patterns (hemiparesis) during sleep. A novel deep learning framework called Early Detection of In-sleep Stroke (EDIS) serves as the core engine for stroke detection during sleep. The framework employs cascading windows of various sizes for convolutional neural networks (CNNs) to enhance both the detection performance and the detection time. We utilize 1D accelerometer sensor data from both hands to generate 2D matrix images, which serve as input for multiple CNN models. Predictions from these models are combined using blending ensemble learning to make a final decision. Although the EDIS framework requires a larger parameter size and longer inference time due to its network architecture with multiple CNNs, it outperforms five single-CNN models by improving detection performance and reducing detection time. Extensive evaluation results demonstrate that EDIS framework accurately and quickly detects in-sleep stroke within an eligible time (3 hours). We believe that our framework will be a fundamental component of real-time stroke monitoring systems, contributing to a reduction in mortality rates among patients suspected of having a stroke.

  PublisherOA PDFDOI

• Network Coding-Assisted Data Broadcast in Large-Scale Vehicular Networks

  2023-12-20

  book-chapterSenior author
  PublisherDOI

• Fog Computing Empowered Data Dissemination in Heterogeneous Vehicular Networks

  2023-12-20 · 1 citations

  book-chapterSenior author
  PublisherDOI

Recent grants

• A QoS Management Scheme for Real-Time Data Services

  NSF · $180k · 2002–2007

• Collaborative Research: CSR--EHS: QoS-Aware Data Services in Data-Intensive Real-Time Embedded Applications

  NSF · $200k · 2006–2009

Frequent coauthors

• John A. Stankovic

  67 shared

• Victor C. S. Lee

  University of Hong Kong

  48 shared

• Kai Liu

  Chongqing University

  39 shared

• Joseph Kee‐Yin Ng

  Hong Kong Baptist University

  27 shared

• Penglin Dai

  Southwest Jiaotong University

  25 shared

• Taejoon Park

  Ajou University

  23 shared

• Hee Jung Yoon

  22 shared

• Ho-Kyeong Ra

  20 shared

Awards & honors

• Outstanding Contribution Award from ACM/IEEE Cyber Physical…