Hao-Hsuan Chang

Email: haohsuan [at] vt.edu

[Curriculum Vitae] [Google Scholar] [Github] [Linkedin]

I am a Senior Research Engineer in Standard and Mobility Innovation (SMI) Lab at Samsung Research America.
I received the Ph.D. degree in Electrical and Computer Engineering at Virginia Tech, advised by Prof. Lingjia Liu. Before coming to Virginia Tech, I obtained my M.S. degree in Communication Engineering and B.S. degree in Electrical Engineering from National Taiwan University
I am interested in Deep Learning techniques for Wireless Sensing (include WiFi, UWB, and mmWave Radar) applications such as vital sign monitoring and motion detection, and Deep Reinforcement Learning techniques for Wireless Communications (include Dynamic Spectrum Sharing, Load Balancing, and Resource Scheduling).

Research Interests

Deep Learning, Deep Domain Adaptation, Wireless Sensing

Deep Reinforcement Leanring, Dynamic Spectrum Sharing, Mobility Load Balancing, Resource Scheduling

News

[2024/04] One paper, Multi-Person Respiration Rate Estimation with Single Pair of Transmit and Receive Antenna, is accepted to 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[2024/03] One paper, Optimal preprocessing of WiFi CSI for sensing applications, is accepted to IEEE Transactions on Wireless Communications (TWC).
[2023/01] One paper, Federated Multi-Agent Deep Reinforcement Learning (Fed-MADRL) for Dynamic Spectrum Access, is accepted to IEEE Transactions on Wireless Communications (TWC).
[2022/12] One paper, Federated Dynamic Spectrum Access through Multi-Agent Deep Reinforcement Learning, is accepted to 2022 IEEE Global Communications Conference (GLOBECOM).
[2022/11] One paper, MADRL Based Scheduling for 5G and Beyond, is accepted to 2022 IEEE Military Communications Conference (MILCOM).
[2022/08] One paper, Decentralized Deep Reinforcement Learning Meets Mobility Load Balancing, is accepted to IEEE/ACM Transactions on Networking (TON).
[2021/12] One paper, Resource Allocation for D2D Cellular Networks With QoS Constraints: A DC Programming-Based Approach, is accepted to IEEE Access.
[2020/09] Code for Distributive Dynamic Spectrum Access through Deep Reinforcement Learning: A Reservoir Computing Based Approach (In IEEE Internet of Things Journal, 2019) is released.
[2020/09] One paper, Deep Echo State Q-Network (DEQN) and Its Application in Dynamic Spectrum Sharing for 5G and Beyond, is accepted to IEEE Transactions on Neural Networks and Learning Systems (TNNLS).

Publications

Multi-Person Respiration Rate Estimation with Single Pair of Transmit and Receive Antenna
Hao-Hsuan Chang*, Vishnu Ratnam, Hao Chen, Junsu Choi, and Jianzhong Zhang
IEEE International Conference on Acoustics, Speech and Signal Processing, 2024

Optimal preprocessing of WiFi CSI for sensing applications
Vishnu Ratnam, Hao Chen, Hao Hsuan Chang*, Abhishek Sehgal, and Jianzhong Zhang
IEEE Transactions on Wireless Communications, 2024

Federated Multi-Agent Deep Reinforcement Learning (Fed-MADRL) for Dynamic Spectrum Access
Hao-Hsuan Chang*, Yifei Song, Thinh T. Doan, and Lingjia Liu
IEEE Transactions on Wireless Communications, 2023

MADRL Based Scheduling for 5G and Beyond
Hao–Hsuan Chang*, R.B.Sai Sree, Hao Chen, Jianzhong Zhang, and Lingjia Liu
IEEE Military Communications Conference, 2022

Federated Dynamic Spectrum Access through Multi-Agent Deep Reinforcement Learning
Yifei Song, Hao-Hsuan Chang*, Lingjia Liu
IEEE Global Communications Conference, 2022

Decentralized Deep Reinforcement Learning Meets Mobility Load Balancing
Hao-Hsuan Chang*, Hao Chen, Jianzhong Zhang, and Lingjia Liu
IEEE/ACM Transactions on Networking, 2022

Resource Allocation for D2D Cellular Networks With QoS Constraints: A DC Programming- Based Approach
Hao-Hsuan Chang*, Lingjia Liu, Jianan Bai, Alex Pidwerbetsky, Allan Berlinsky, Joe Huang, Jonathan D Ashdown, Kurt Turck, and Yang Yi
IEEE Access, 2021

Deep Echo State Q-Network (DEQN) and Its Application in Dynamic Spectrum Sharing for 5G and Beyond
Hao-Hsuan Chang*, Lingjia Liu, and Yang Yi
IEEE Transactions on Neural Networks and Learning Systems, 2020

Accelerating Model-Free Reinforcement Learning With Imperfect Model Knowledge in Dynamic Spectrum Access
Lianjun Li, Lingjia Liu, Jianan Bai, Hao-Hsuan Chang*, Hao Chen, Jonathan D. Ashdown, Jianzhong Zhang, and Yang Yi
IEEE Internet of Things Journal, 2020

Learning for Detection: MIMO-OFDM Symbol Detection Through Downlink Pilots
Zhou zhou, Lingjia Liu, and Hao-Hsuan Chang*
IEEE Transactions on Wireless Communications, 2020

Deep Residual Learning Meets OFDM Channel Estimation
Lianjun Li, Hao Chen, Hao-Hsuan Chang*, and Lingjia Liu
IEEE Wireless Communications Letters, 2020

Maximizing System Throughput in D2D Networks using Alternative DC Programming
Hao-Hsuan Chang*, Lingjia Liu, Hao Song, Alex Pidwerbetsky, Allan Berlinsky, Jonathan Ashdown, Kurt Turck, and Yang Yi
IEEE Global Communications Conference, 2019

Distributive Dynamic Spectrum Access through Deep Reinforcement Learning: A Reservoir Computing Based Approach
Hao-Hsuan Chang*, Hao Song, Yang Yi, Jianzhong Zhang, Haibo He, and Lingjia Liu
IEEE Internet of Things Journal, 2019
Code

Deep Q-Network Based Power Allocation Meets Reservoir Computing in Distributed Dynamic Spectrum Access Networks
Hao Song, Lingjia Liu, Hao-Hsuan Chang*, Jonathan Ashdown, and Yang Yi
IEEE Conference on Computer Communications Workshops, 2019