Nguyen Hong Phuc

Ha Noi, Vietnam

23phuc.nh@vinuni.edu.vn

+84 326 060 805

I am a dedicated Electrical and Computer Engineering student at VinUniversity, specializing in AI, machine learning, and signal processing. My work bridges theoretical research with practical engineering applications, spanning semantic communication, multi-task learning for aquatic vision, and embedded AI systems.

I am currently a Research Intern at HKU AIoT Lab, The University of Hong Kong (Jul. 2026 – Present), supervised by Prof. Chenshu Wu, working on thermal sensing research. I also work as an Undergraduate Research Assistant at the Intelligence, Computing and Communication Lab (ICCL) at VinUniversity & Trinity College Dublin, under the supervision of Assist. Prof. Nguyen Van Dinh. I am the recipient of a $3,500 Student Research Grant to lead research on smart aquaculture systems.

Research interests:

Wireless communications & signal processing (5G/Open RAN, semantic communication, energy harvesting)
Machine learning & deep learning (multi-task learning, generative models, computer vision)
WiFi sensing (cross-environment human pose estimation, passive localization)
Quantum computing & quantum information
IoT & embedded AI systems (smart aquaculture, edge AI, flight control)

Education:

BSc in Electrical and Computer Engineering, VinUniversity (Oct. 2023 – Present)
GPA: 3.80/4.00 · Rank 1 in ECE Cohort 4 · 100% Talent Scholarship (2023–2027)
Australia-Vietnam Strategic Technologies Scholarship · Best Poster Award OIC 2025
Bac Ninh High School for the Gifted, Physics Major (2020 – 2023)
2nd Prize National Physics Olympiad (2023) · 5th Place Thomas Jefferson Physics Olympiad (2023)

Professional Activities:

Invited Reviewer: IEEE International Conference on Advanced Technologies for Communications (ATC) 2026
Invited Reviewer: IEEE Transactions on Cognitive Communications and Networking

news

Jul 02, 2026	Starting as a Research Intern at HKU AIoT Lab, The University of Hong Kong — selected as 1 of 40 students for a fully funded internship, supervised by Prof. Chenshu Wu.
Jun 01, 2026	Invited as Reviewer for IEEE Transactions on Cognitive Communications and Networking and IEEE ATC 2026.
May 24, 2026	Paper ChronoSC: Task-Oriented Semantic Communication via Temporal-to-Color Encoding accepted at IEEE ICCE 2026!
Mar 01, 2026	Awarded a ,500 Student Research Grant to lead research on smart aquaculture IoT and multimodal AI systems at VinUniversity.
May 31, 2025	Awarded the Australia-Vietnam Strategic Technologies Scholarship!

selected publications

IEEE Commun. Lett.
Energy-Aware Resource Allocation for Energy Harvesting Powered Wireless Sensor Nodes

Minh Ngoc Ngo , Thanh Trung Nguyen , Hong-Phuc Nguyen, and 1 more author

IEEE Communications Letters, Mar 2025

Abs DOI arXiv Bib HTML

Low harvested energy poses a significant challenge to sustaining continuous communication in energy harvesting (EH)-powered wireless sensor networks. In this paper, we introduce a novel energy-aware resource allocation problem aimed at enabling the asynchronous accumulate-then-transmit protocol. We jointly optimize power allocation and time fraction dedicated to EH to maximize average long-term system throughput, accounting for both data and energy queue lengths.
@article{ngo2025energyaware, title = {Energy-Aware Resource Allocation for Energy Harvesting Powered Wireless Sensor Nodes}, author = {Ngo, Minh Ngoc and Nguyen, Thanh Trung and Nguyen, Hong-Phuc and Nguyen, Van-Dinh}, journal = {IEEE Communications Letters}, volume = {29}, number = {3}, pages = {542--546}, year = {2025}, month = mar, doi = {10.1109/LCOMM.2024.3369687}, }
IEEE TCSV
FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition

H.-P. Nguyen , B. H. Ngo, M. P. Tran, and 1 more author

IEEE Transactions on Circuits and Systems for Video Technology, Jul 2026

Major Revision

Abs arXiv Bib HTML Code Website

Fine-grained aquatic species recognition is inherently challenging due to extreme phenotypic similarities among related species and severe class imbalance in real-world distributions. In this paper, we propose FISHER, a gradient-decoupled hierarchical multi-task learning framework coordinating segmentation, morphological trait identification, and fine-grained classification. By decoupling conflicting task gradients and aligning trait prototypes, FISHER achieves state-of-the-art accuracy and significant gains on ultra-rare species.
@article{nguyen2026fisher, title = {FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition}, author = {Nguyen, H.-P. and Ngo, B. H. and Tran, M. P. and Nguyen, Van-Dinh}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, year = {2026}, month = jul, note = {Major Revision}, }