Peng CHENG

alt text 

Senior Lecturer
Graduate Research Coordinator
Department of Computer Science and Information Technology
La Trobe University
Melbourne, Australia
E-mail: p.cheng AT latrobe.edu.au

Offical Website    Google Scholar    Research Gate    LinkedIn

About me

Dr. Peng Cheng is an Australian Research Council Discovery Early Career Research Fellow (ARC DECRA), Senior Lecturer, and PhD advisor in the Department of Computer Science and Information Technology at La Trobe University, VIC, Australia. Cheng is a core member of the Cisco-LTU Research Centre for AI and Internet of Things. Cheng is also an Honorary Senior Lecturer in the School of Electrical and Information Engineering at the University of Sydney, NSW, Australia. Before joining La Trobe University in 2020, Cheng worked as a Postdoctoral Research Scientist at CSIRO from 2014 to 2017 on projects such as Nagara communications and WASP indoor localization. From 2017 to 2020, Cheng was an ARC DECRA Fellow/Lecturer at the University of Sydney. Cheng obtained a PhD in Communication and Information Systems from Shanghai Jiao Tong University, China.

I am seeking self-motivated students interested in pursuing a PhD to join my group. I also welcome applications of Visiting Scholars. Please send me an email with your CV.

Recent News

  • 10/2024 Simulation code packages for recent published papers will be released.

  • 09/2024 One paper accepted in IEEE Transactions on Signal Processing

  • 08/2024 One paper accepted in IEEE Journal on Selected Areas in Communications

  • 06/2024 One paper accepted in IEEE Transactions on Signal Processing

  • 06/2024 Personal website is accessible

Recent Research (Big Picture)

wirelessAI

My current research focuses on AI-driven IoT and its impact on connectivity and intelligence. The above figure highlights a data lifecycle with four main entities: 1) Data generation through monitoring by smart IoT devices, 2) Data transfer via networks like 4G/5G or Wi-Fi to the Internet, 3) Data collection by custodians using cloud services, and 4) Access and analysis of data by consumers for big data mining. The data lifecycles also involve two shortcuts: one from the physical world directly to data receivers (wireless sensing) and another bypassing both generators and receivers to reach custodians. AI functions are typically centralized in clouds or data centers for big data analysis. My research aims to push AI capabilities to the network edge, i.e., bringing computation functions to data, close to data generators and receivers. This includes the following new research directions/areas (to be updated):

Sensing AI

  • WiFi Sensing

    environment
    Fig. 1. Our team developed a novel multi-task contrastive learning framework for accurate concurrent detection of respiration and heart rates using WiFi sensing. In a test scenario, 80% of respiratory rate errors are below 0.26 bpm and 80% of heart rate errors are below 1.21 bpm.
  • Radar Sensing

    radar
    Fig. 2. Our team is developing radar sensing in assisted living.
  • Hyperspectral Imaging

User and Network Device AI

  • On-device AI

  • Edge AI

Access AI

  • AI for Physical (PHY) Layer

  • AI for Media Access Control (MAC) Layer

  • AI for Network Layer

Data-provenance AI

  • AI for Data Compression

  • AI for Data Privacy

  • AI for Data Security

AI-driven IoT enables real-time analytics and decision-making, offering high-performance data computation right on the network edge and benefits multiple sectors such as agriculture and digital health. Please refer to the following papers for the details.

  • D. C. Nguyen, P. Cheng, M. Ding, et al., "Enabling AI in Future Wireless Networks: A Data Life Cycle Perspective," IEEE Communications Surveys & Tutorials, vol. 23, no. 1, pp. 553-595, Firstquarter 2021. [IEEE PDF]

  • P. Cheng, Y. Chen, M. Ding, Z. Chen, S. Liu, and Y. -P. P. Chen, "Deep Reinforcement Learning for Online Resource Allocation in IoT Networks: Technology, Development, and Future Challenges," IEEE Communications Magazine, vol. 61, no. 6, pp. 111-117, June 2023. [IEEE PDF]

  • P. Cheng, Z. Chen, M. Ding, Y. Li, B. Vucetic and, D. Niyato, "Spectrum Intelligent Radio: Technology, Development, and Future Trends," IEEE Communications Magazine, vol. 58, no. 1, pp. 12-18, January 2020. [IEEE PDF]

Previous Research

Compressive Sensing (CS) for Wireless Networks

CS is a powerful signal processing technique that leverages the sparsity of signals to efficiently acquire and reconstruct data. In wireless networks, CS can enhance performance and efficiency in various ways, including reducing the amount of data to be transmitted, improving signal quality, and optimizing resource usage. The following work [Ref 1] introduces a novel channel estimation method for OFDM systems in doubly selective channels using distributed compressive sensing (DCS). It addresses the challenge of inter-carrier interference and high pilot subcarrier needs due to numerous channel coefficients. By employing a basis expansion model and exploiting delay domain sparsity, the method transforms the channel into a two-dimensional model aimed at estimating jointly sparse coefficient vectors. A unique decoupling form based on a new sparse pilot pattern facilitates ICI-free structure and accurate joint vector estimation.

DS channel

[Ref 1] P. Cheng, Z. Chen, Y. Rui, Y. J. Guo, L. Gui, M. Tao, and Q. T. Zhang, "Channel Estimation for OFDM Systems over Doubly Selective Channels: A Distributed Compressive Sensing Based Approach," IEEE Transactions on Communications, vol. 61, no. 10, pp. 4173-4185, October 2013. [IEEE PDF]

Performance Analysis and Optimization for Wireless Networks

Performance analysis and optimization are crucial for the efficient operation of wireless networks. This involves evaluating the performance of the network under various conditions and implementing strategies to enhance its efficiency, reliability, and capacity. The following work presents an analytical study of Vector OFDM (V-OFDM) over multi-path fading channels based on algebraic number theory. The goal is to investigate the diversity gain and coding gain of each vector block (VB) in V-OFDM so as to ultimately reveal its performance limits over fading channels. Interestingly, V-OFDM is closely related to the recent promising Orthogonal Time Frequency Space (OTFS) technique.

VOFDM

[Ref 2] P. Cheng, M. Tao, Y. Xiao and W. Zhang, "V-OFDM: On Performance Limits over Multi-Path Rayleigh Fading Channels," IEEE Transactions on Communications, vol. 59, no. 7, pp. 1878-1892, July 2011. [IEEE PDF]

Publications

Note: * PhD student under my supervision

Full list of publications in Google Scholar

  1. [TSP] G. Wang*, S. Li, P. Cheng, B. Vucetic, and Y. Li, "ToF-based NLoS Indoor Tracking with Adaptive Ranging Error Mitigation," to appear in IEEE Transactions on Signal Processing, 2024.

  2. [TSP] G. Wang*, P. Cheng, Z. Chen, B. Vucetic, and Y. Li, "Green Cell-free Massive MIMO: An Optimization Embedded Deep Reinforcement Learning Approach," IEEE Transactions on Signal Processing, vol. 72, pp. 2751-2766, June 2024. [IEEE PDF]

  3. [TSP] Y. Xu*, P. Cheng, Z. Chen, M. Ding, Y. Li, and B. Vucetic, "Task Offloading for Large-Scale Asynchronous Mobile Edge Computing: An Index Policy Approach," IEEE Transactions on Signal Processing, vol. 69, pp. 401-416, December 2021. [IEEE PDF]

  4. [TSP] Z. Yan*, P. Cheng, Z. Chen, Y. Li, and B. Vucetic, "Gaussian Process Reinforcement Learning for Fast Opportunistic Spectrum Access," IEEE Transactions on Signal Processing, vol. 68, pp. 2613-2628, April 2020. [IEEE PDF]

  5. [TSP] R. Zhang*, P. Cheng, Z. Chen, Y. Li, and B. Vucetic, "A Learning-Based Two-Stage Spectrum Sharing Strategy With Multiple Primary Transmit Power Levels," IEEE Transactions on Signal Processing, vol. 67, no. 18, pp. 4899-4914, August 2019. [IEEE PDF]

  6. [TSP] Y. Xu*, P. Cheng, Z. Chen, Y. Li and B. Vucetic, "Mobile Collaborative Spectrum Sensing for Heterogeneous Networks: A Bayesian Machine Learning Approach," IEEE Transactions on Signal Processing, vol. 66, no. 21, pp. 5634-5647, November 2018. [IEEE PDF]

  7. [TON] Z. Yan*, P. Cheng, Z. Chen, B. Vucetic, and Y. Li, "Two-Dimensional Task Offloading for Mobile Networks: An Imitation Learning Framework," IEEE/ACM Transactions on Networking, vol. 29, no. 6, pp. 2494-2507, December 2021. [IEEE PDF]

  8. [JSAC] Y. Cai*, P. Cheng, Z. Chen, W. Xiang, B. Vucetic, and Y. Li, "Graphic Deep Reinforcement Learning for Dynamic Resource Allocation in Space-Air-Ground Integrated Networks," to appear in IEEE Journal on Selected Areas in Communications, 2024.

  9. [JSAC] Y. Lu*, P. Cheng, Z. Chen, W. H. Mow, Y. Li, and B. Vucetic, "Deep Multi-Task Learning for Cooperative NOMA: System Design and Principles," IEEE Journal on Selected Areas in Communications, vol. 39, no. 1, pp. 61-78, January 2021. [IEEE PDF]

  10. [JSAC] Y. Rui, Q. T. Zhang, L. Deng, P. Cheng, and M. Li, "Mode Selection and Power Optimization for Energy Efficiency in Uplink Virtual MIMO Systems," IEEE Journal on Selected Areas in Communications, vol. 31, no. 5, pp. 926-936, May 2013. [IEEE PDF]

  11. [TMC] G. Wang*, P. Cheng, Z. Chen, B. Vucetic, and Y. Li, "Inverse Reinforcement Learning With Graph Neural Networks for Full-Dimensional Task Offloading in Edge Computing," IEEE Transactions on Mobile Computing, vol. 23, no. 6, pp. 6490-6507, June 2024. [IEEE PDF]

  12. [TMC] Y. Cai*, P. Cheng, Z. Chen, M. Ding, B. Vucetic, and Y. Li, "Deep Reinforcement Learning for Online Resource Allocation in Network Slicing," IEEE Transactions on Mobile Computing, vol. 23, no. 6, pp. 7099-7116, June 2024. [IEEE PDF]

  13. [TMC] S. Liu*, P. Cheng, Z. Chen, W. Xiang, B. Vucetic, and Y. Li, "Contextual User-Centric Task Offloading for Mobile Edge Computing in Ultra-Dense Network," IEEE Transactions on Mobile Computing, vol. 22, no. 9, pp. 5092-5108, September 2023. [IEEE PDF]

  14. [TCOM] R. Zhang*, P. Cheng, Z. Chen, S. Liu, B. Vucetic, and Y. Li, "Calibrated Bandit Learning for Decentralized Task Offloading in Ultra-Dense Networks," IEEE Transactions on Communications, vol. 70, no. 4, pp. 2547-2560, April 2022. [IEEE PDF]

  15. [TCOM] C. Jiang*, Y. Wang, P. Cheng, and W. Xiang, "A Low-Complexity Codebook Optimization Scheme for Sparse Code Multiple Access," IEEE Transactions on Communications, vol. 70, no. 4, pp. 2451-2463, April 2022. [IEEE PDF]

  16. [TCOM] Y. Lu*, P. Cheng, Z. Chen, Y. Li, W. H. Mow, and B. Vucetic, "Deep Autoencoder Learning for Relay-Assisted Cooperative Communication Systems," IEEE Transactions on Communications, vol. 68, no. 9, pp. 5471-5488, September 2020. [IEEE PDF]

  17. [TCOM] P. Cheng, C. Ma, M. Ding, Y. Hu, Y. Li, and B. Vucetic, "Localized Small Cell Caching: A Machine Learning Approach Based on Rating Data," IEEE Transactions on Communications, vol. 67, no. 2, pp. 1663-1676, February 2019. [IEEE PDF]

  18. [TCOM] P. Cheng, Z. Chen, J. A. Zhang, Y. Li, and B. Vucetic, "A Unified Precoding Scheme for Generalized Spatial Modulation," IEEE Transactions on Communications, vol. 66, no. 6, pp. 2502-2514, June 2018. [IEEE PDF]

  19. [TCOM] P. Cheng, Z. Chen, F. de Hoog, and C. K. Sung, "Sparse Blind Carrier-Frequency Offset Estimation for OFDMA Uplink," IEEE Transactions on Communications, vol. 64, no. 12, pp. 5254-5265, December 2016. [IEEE PDF]

  20. [TCOM] P. Cheng, Z. Chen, Y. Rui, Y. J. Guo, L. Gui, M. Tao, and Q. T. Zhang, "Channel Estimation for OFDM Systems over Doubly Selective Channels: A Distributed Compressive Sensing Based Approach," IEEE Transactions on Communications, vol. 61, no. 10, pp. 4173-4185, October 2013. [IEEE PDF]

  21. [TCOM] P. Cheng, M. Tao, Y. Xiao and W. Zhang, "V-OFDM: On Performance Limits over Multi-Path Rayleigh Fading Channels," IEEE Transactions on Communications, vol. 59, no. 7, pp. 1878-1892, July 2011. [IEEE PDF]

  22. [TWC] D. Zhang, A. Li, M. Shirvanimoghaddam, P. Cheng, Y. Li and B. Vucetic, "Codebook-Based Training Beam Sequence Design for Millimeter-Wave Tracking Systems," IEEE Transactions on Wireless Communications, vol. 18, no. 11, pp. 5333-5349, November 2019. [IEEE PDF]

  23. [TGRS] S. Liang, T. Gao, T. Chen and P. Cheng, "A Remote Sensing Image Dehazing Method Based on Heterogeneous Priors," IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-13, March 2024. [IEEE PDF]

Competitive Grants

  • CI, “Low-cost sensing methods and hybrid learning models," Australian Research Council (ARC) Discovery Project, 2022-2024

  • CI, “Wireless cellular connectivity for large scale critical applications," ARC Discovery Project, 2021-2023

  • Sole CI, “Intelligent wireless access for Internet of Things," ARC DECRA Fellowship, 2020-2022

  • Sole CI, “Distributed compressive sensing for a new sensing paradigm," CSIRO TCP Grant, 2014-2017

Research Team

Current PhD students

  • Natasha Elizabeth Francis

  • William Lukito

  • Yijie Gao

  • Jianqiao Zhang

  • Yue Cai

  • Geng Wang

  • Tiantian Zhang

Graduated HDRs

  • Yizhen Xu (PhD)

  • Rui Zhang (PhD)

  • Zun Yan (PhD)

  • Guangchen Wang (PhD)

  • Sige Liu (PhD)

  • Yuxin Lu (PhD)

  • Chunyang Wang (MPhil)

  • Chen Qiu (MPhil)

  • Yilun Wang (MPhil)

Teaching

  • 2021-, Subject Coordinator & Lecturer, CSE5ML Machine Learning, Semesters & Online Terms, La Trobe University

  • 2021-, Subject Coordinator & Lecturer, CSE3CI Computational Intelligence, La Trobe University

  • 2020, Lecturer, CSE4RFS Real-Time and Fault-Tolerant Systems, Semester 2, La Trobe University

  • 2019, Lecturer, ELEC3506 Data Communications and the Internet, Semester 2, School of Electrical and Information Engineering, The University of Sydney

  • 2018, Guest Lecturer, TELE 4652 Mobile and Satellite Communications, Semester 2, The University of New South Wales

  • 2017, Lecturer, ELEC5510 Satellite Communication Systems, Semester 2, School of Electrical and Information Engineering, The University of Sydney