Posts by Collection

publications

A Low-Power, High Reliable Data Collection Scheme for Wireless Sensor Networks

Published in International Conference on Advanced Technologies for Communications (ATC), 2019

Getting data reliably from wireless sensor networks without quickly draining sensor batteries is crucial. We introduce an improved data collection method that uses a standard communication technique (TSCH) but cleverly manages sensors at the network’s edge, achieving near-perfect 99.99% data delivery while using significantly less power than other approaches.

Recommended citation: N. Q. Hieu, T. T. Huong, N. T. Hung, N. Q. Thu, N. H. Thanh, "A Low-Power, High Reliable Data Collection Scheme for Wireless Sensor Networks," International Conference on Advanced Technologies for Communications (ATC), 2019.
Download Paper

When virtual reality meets rate splitting multiple access: A joint communication and computation approach

Published in IEEE Journal on Selected Areas in Communications, 2023

Virtual Reality (VR) streaming demands not only stringent millisecond latency but also sophisticated computation at the transmitter, a requirement that traditional Rate Splitting Multiple Access (RSMA) schemes fail to meet. Our novel framework addresses this by formulating the problem as a joint communication-computation optimization and introducing a Field-of-View (FoV) based multicast clustering approach, which successfully uses deep reinforcement learning to achieve the necessary millisecond-latency requirements significantly faster than baseline schemes.

Recommended citation: N. Q. Hieu, D. N. Nguyen, D. T. Hoang, E. Dutkiewicz, "When Virtual Reality Meets Rate Splitting Multiple Access: A Joint Communication and Computation Approach," IEEE Journal on Selected Areas in Communications, no. 5, vol. 41, 2023.
Download Paper

Reconstructing Human Pose From Inertial Measurements: A Generative Model-Based Compressive Sensing Approach

Published in IEEE Journal on Selected Areas in Communications, 2024

Virtual reality requires precise 3D body tracking, often using just a few body sensors transmitting data wirelessly, which is difficult over networks like 5G. Our research introduces a method that cleverly compresses sensor data to save power during transmission. An AI component then rapidly reconstructs the user’s complete 3D pose from this compressed, potentially noisy data, achieving accurate results significantly faster than older techniques.

Recommended citation: N. Q. Hieu, D. T. Hoang, D. N. Nguyen, M. A. Alsheikh, "Reconstructing human pose from inertial measurements: A generative model-based compressive sensing approach," IEEE Journal on Selected Areas in Communications, no. 10, vol. 42, 2024.
Download Paper

Enhancing Immersion and Presence in the Metaverse With Over-the-Air Brain-Computer Interface

Published in IEEE Transactions on Wireless Communications, 2024

This research explores using brain signals (EEG), sent wirelessly, to understand what users expect in the Metaverse, allowing for personalized experiences and more efficient network use. Our system processes these signals on a nearby server and uses advanced algorithms to learn individual needs—even accounting for wireless noise and differences between users-automatically tailoring the virtual environment for better quality.

Recommended citation: N. Q. Hieu, D. T. Hoang, D. N. Nguyen, V. D. Nguyen, Y. Xiao, and E. Dutkiewicz, "Enhancing Immersion and Presence in the Metaverse With Over-the-Air Brain-Computer Interface," IEEE Transactions on Wireless Communications , no. 12, vol. 23, 2024.
Download Paper

Point Cloud Compression with Bits-back Coding

Published in arXiv preprint, 2024

Storing and sending large 3D point clouds takes significant digital space, demanding efficient compression methods that preserve all details. We introduce a new AI-powered approach that effectively compresses this data while significantly reducing the size of the decompression instructions needed, unlike many other methods. This makes our technique highly practical and allows it to achieve better compression results than standard tools like Google’s Draco.

Recommended citation: N. Q. Hieu, M. Nguyen, D. T. Hoang, D. N. Nguyen, E. Dutkiewicz, "Point Cloud Compression with Bits-back Coding", 2024.
Download Paper

End-to-End Human Pose Reconstruction from Wearable Sensors for 6G Extended Reality Systems

Published in arXiv preprint, 2025

Accurately capturing human 3D movements is essential for future virtual reality and remote collaboration, but wireless signals often introduce errors that reduce accuracy. We developed a new AI-powered method that effectively handles these wireless transmission problems, leading to significantly more accurate reconstruction of 3D human poses compared to traditional approaches.

Recommended citation: N. Q. Hieu, D. T. Hoang, D. N. Nguyen, M. A. Alsheikh, C. C. N. Kuhn, Y. F. Alem, I. Radwan, "End-to-End Human Pose Reconstruction from Wearable Sensors for 6G Extended Reality Systems", 2025.
Download Paper

Advanced Machine Learning for Cyber-Attack Detection in IoT Networks

Published in Elsevier, 2025

Advanced Machine Learning for Cyber-Attack Detection in IoT Networks analyzes diverse machine learning techniques, including supervised, unsupervised, reinforcement, and deep learning, along with their applications in detecting and preventing cyberattacks in future IoT systems.

Recommended citation: D. T. Hoang, N. Q. Hieu, D. N. Nguyen, and E. Hossain, "Advanced Machine Learning for Cyberattack Detection in IoT Networks," Elsevier, 2025.
Download Paper

Hieu Nguyen