Welcome to the Advanced Wireless Systems Group

Welcome to the Advanced Wireless Systems Group. Our group focuses on both experimental and theoretical aspects of research related to wireless communications and network systems.

A main research focus on the group over the past decade or so has been physical-layer network coding (PNC), a wireless- networking concept first put forth by the group in 2006. PNC research in the group will be tapering down. Instead, a focus will be on potential commercial exploitation of PNC.

Going forward, three research focuses of the group will be

  1. AI-driven wireless communications system and wireless networks.

  2. Industrial wireless networks for IIoT communication (particularly specialized clean-slate network designs for the factory setting rather than Wi-Fi or 5G networks for general applications).

  3. Network protocol and network architecture designs for blockchain, with the aim to boost transaction throughput.

(see Research for more details).

Some representative publications by the group in these directions are as follows:

  1. Y. Shao, A. Rezaee, S. C. Liew, V. W. S. Chan, “Significant Sampling for Shortest Path Routing: A Deep Reinforcement Learning Solution,” IEEE Globecom, Dec. 2019.
    A collaboration with MIT researchers to use the AI technique of deep reinforcement learning to solve problems in network routing.

  2. T. Wang, S.C. Liew, S. Zhang, “PubChain: A Decentralized Open-Access Publication Platform with Participants Incentivized by Blockchain Technology,” Sep. 2019. Available https://arxiv.org/abs/1910.00580
    A blockchain framework for an open-access publication platform. Let us know if you want to join our efforts to create an alternative venue for researchers to publish their results.

  3. T. Wang, S.C. Liew, S. Zhang, “When Blockchain Meets AI: Optimal Mining Strategy Achieved by Reinforcement Learning,” under preparation.
    This work asks the following question: “Can AI techniques be used to devise optimal block mining strategy in blockchain?”

  4. Y. Shao, S. C. Liew, T. Wang, “AlphaSeq: Sequence Discovery with Deep Reinforcement Learning”, accepted by IEEE Trans. Neural Networks and Learning Systems, Sep. 2019.
    This work adapts and modifies the AlphaGo algorithm to discover 0-1 sequences for communications and radar applications.

  5. T. Wang, L. Zhang, S. C. Liew, “Deep Learning for Joint MIMO Detection and Channel Decoding,” IEEE PIMRC, Sep. 2019.
    An exploration of a wireless PHY-layer design based on AI techniques.

  6. Y. Yu, T. Wang, S. C. Liew, “Deep-Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks,” IEEE J. on Selected Areas in Commun., vol. 37, no. 6, pp. 1277-1290, DOI: 10.1109/JSAC.2019.2904329, Jun. 2019.
    This work makes use of deep-reinforcement learning techniques to design a MAC protocol that can co-exist harmoniously with other MAC protocols, without inner knowledge on how these other MAC protocols operate.

  7. Y. Yu, S. C. Liew, T. Wang, “Carrier-Sense Multiple Access for Heterogeneous Wireless Networks using Deep Reinforcement Learning,” IEEE WCNC International Workshop on Smart Spectrum, Apr. 2019.
    This work extends the above work by incorporating carrier-sensing capability into the MAC protocol we design.

(see Publications for more details).

News

28. October 2019

Our new website is online!

... see all News