
Dr Mahdi Boloursaz Mashhadi
About
Biography
Dr Mahdi Boloursaz Mashhadi (Member, IEEE) is a Lecturer at the 5G/6G Innovation Centre (5G/6GIC) at the Institute for Communication Systems (ICS), University of Surrey (UoS). Prior to joining ICS, he was a Postdoctoral Research Associate at the Intelligent Systems and Networks (ISN) Research Group, Imperial College London, 2019-2021. He received the B.S. degrees (Hons.) in electrical and industrial engineering and the M.S. and Ph.D. degrees in mobile telecommunications all from the Sharif University of Technology (SUT), Tehran, Iran, in 2011, 2013, and 2018, respectively. He was a visiting Research Associate with the University of Central Florida, Orlando, USA, in 2018, and Queen's University, Ontario, Canada, in 2017. He has more than 40 peer-reviewed publications (see non-exhaustive list below) including high impact IEEE transactions papers, prestigious IEEE conference publications, and granted patents, in the areas of wireless communications, Artificial Intelligence (AI), Machine Learning (ML), and signal processing. He received the Best Paper Award from the IEEE EWDTS 2012 conference, and the Exemplary Reviewer Award from the IEEE TRANSACTIONS ON COMMUNICATIONS in 2021. In December 2020, he won Bronze in the international AI/ML in 5G challenge by the International Telecommunications Union (ITU). He is currently collaborating with the ITU in the international competition on AI/ML in 5G where he is a member of a global panel of judges to evaluate innovative submissions on applications of AI/ML in 5G and beyond wireless networks.
News
ResearchResearch interests
My current research is focused at the intersection of AI and machine learning and wireless communications. I'm interested in the specific role of AI and machine learning in future generation wireless networks and joint design of smart machine learning agents and the underlying wireless network to achieve goal oriented and semantic communications. I’m interested in design of the so called AIOT systems which is when numerous tiny AI agents meet the IOT. I am looking at the interactions between AI and wireless communications which can be either AI for wireless communications or wireless communications for distributed or federated machine learning. I am collaborating with the ITU in the international competition on AI/ML in 5G where I am a member of a global panel of judges to evaluate innovative submissions on applications of AI/ML in 5G and beyond wireless networks. I am also an affiliate member of the Surrey Institute for People-Centred AI. I chaired a special session on "Machine Learning for Communications" at the 55'th Annual Asilomar Conference on Signals, Systems, and Computers in November 2021, and the first 6GIC-CLICK workshop on “WIRELESS AI” in the UK in June 2022.
Research interests
My current research is focused at the intersection of AI and machine learning and wireless communications. I'm interested in the specific role of AI and machine learning in future generation wireless networks and joint design of smart machine learning agents and the underlying wireless network to achieve goal oriented and semantic communications. I’m interested in design of the so called AIOT systems which is when numerous tiny AI agents meet the IOT. I am looking at the interactions between AI and wireless communications which can be either AI for wireless communications or wireless communications for distributed or federated machine learning. I am collaborating with the ITU in the international competition on AI/ML in 5G where I am a member of a global panel of judges to evaluate innovative submissions on applications of AI/ML in 5G and beyond wireless networks. I am also an affiliate member of the Surrey Institute for People-Centred AI. I chaired a special session on "Machine Learning for Communications" at the 55'th Annual Asilomar Conference on Signals, Systems, and Computers in November 2021, and the first 6GIC-CLICK workshop on “WIRELESS AI” in the UK in June 2022.
Supervision
Postgraduate research supervision
Current Students:
-Mahnoosh Mahdavimoghadam (PG/R - Comp Sci & Elec Eng, ICS)
I am recruiting PhD students in Advanced Wireless and Distributed Data Processing to work on cutting-edge distributed learning technologies over 6G. Interested applicants send CV's to: m.boloursazmashhadi@surrey.ac.uk
Publications
With the large number of antennas and subcarriers the overhead due to pilot transmission for channel estimation can be prohibitive in wideband massive multiple-input multiple-output (MIMO) systems. This can degrade the overall spectral efficiency significantly, and as a result, curtail the potential benefits of massive MIMO. In this paper, we propose a neural network (NN)-based joint pilot design and downlink channel estimation scheme for frequency division duplex (FDD) MIMO orthogonal frequency division multiplex (OFDM) systems. The proposed NN architecture uses fully connected layers for frequency-aware pilot design, and outperforms linear minimum mean square error (LMMSE) estimation by exploiting inherent correlations in MIMO channel matrices utilizing convolutional NN layers. Our proposed NN architecture uses a non-local attention module to learn longer range correlations in the channel matrix to further improve the channel estimation performance.We also propose an effective pilot reduction technique by gradually pruning less significant neurons from the dense NN layers during training. This constitutes a novel application of NN pruning to reduce the pilot transmission overhead. Our pruning-based pilot reduction technique reduces the overhead by allocating pilots across subcarriers non-uniformly and exploiting the inter-frequency and inter-antenna correlations in the channel matrix efficiently through convolutional layers and attention module.
Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to achieve spatial diversity and multiplexing gains. In a frequency division duplex (FDD) multiuser massive MIMO network, each user needs to compress and feedback its downlink CSI to the BS. The CSI overhead scales with the number of antennas, users and subcarriers, and becomes a major bottleneck for the overall spectral efficiency. In this paper, we propose a deep learning (DL)-based CSI compression scheme, called DeepCMC , composed of convolutional layers followed by quantization and entropy coding blocks. In comparison with previous DL-based CSI reduction structures, DeepCMC proposes a novel fully-convolutional neural network (NN) architecture, with residual layers at the decoder, and incorporates quantization and entropy coding blocks into its design. DeepCMC is trained to minimize a weighted rate-distortion cost, which enables a trade-off between the CSI quality and its feedback overhead. Simulation results demonstrate that DeepCMC outperforms the state of the art CSI compression schemes in terms of the reconstruction quality of CSI for the same compression rate. We also propose a distributed version of DeepCMC for a multi-user MIMO scenario to encode and reconstruct the CSI from multiple users in a distributed manner. Distributed DeepCMC not only utilizes the inherent CSI structures of a single MIMO user for compression, but also benefits from the correlations among the channel matrices of nearby users to further improve the performance in comparison with DeepCMC. We also propose a reduced-complexity training method for distributed DeepCMC, allowing to scale it to multiple users, and suggest a cluster-based distributed DeepCMC approach for practical implementation.
Efficient millimeter wave (mmWave) beam selection in vehicle-to-infrastructure (V2I) communication is a crucial yet challenging task due to the narrow mmWave beamwidth and high user mobility. To reduce the search overhead of iterative beam discovery procedures, contextual information from light detection and ranging (LIDAR) sensors mounted on vehicles has been leveraged by data-driven methods to produce useful side information. In this paper, we propose a lightweight neural network (NN) architecture along with the corresponding LIDAR preprocessing, which significantly outperforms previous works. Our solution comprises multiple novelties that improve both the convergence speed and the final accuracy of the model. In particular, we define a novel loss function inspired by the knowledge distillation idea, introduce a curriculum training approach exploiting line-of-sight (LOS)/non-line-of-sight (NLOS) information, and we propose a non-local attention module to improve the performance for the more challenging NLOS cases. Simulation results on benchmark datasets show that utilizing solely LIDAR data and the receiver position, our NN-based beam selection scheme can achieve 79.9% throughput of an exhaustive beam sweeping approach without any beam search overhead and 95% by searching among as few as 6 beams. In a typical mmWave V2I scenario, our proposed method considerably reduces the beam search time required to achieve a desired throughput, in comparison with the inverse fingerprinting and hierarchical beam selection schemes.
Additional publications
For a comprehensive list of my publications please refer to my Google Scholar.
[1] M. B. Mashhadi and D. Gündüz, "Pruning the Pilots: Deep Learning-Based Pilot Design and Channel Estimation for MIMO-OFDM Systems," IEEE Transactions on Wireless Communications, vol. 20, no. 10, pp. 6315-6328, Oct. 2021.
[2] M. B. Mashhadi, Q. Yang and D. Gündüz, "Distributed Deep Convolutional Compression for Massive MIMO CSI Feedback," IEEE Transactions on Wireless Communications, vol. 20, no. 4, pp. 2621-2633, April 2021.
[3] M. B. Mashhadi, M. Jankowski, T. -Y. Tung, S. Kobus and D. Gündüz, "Federated mmWave Beam Selection Utilizing LIDAR Data," IEEE Wireless Communications Letters, vol. 10, no. 10, pp. 2269-2273, Oct. 2021.
[4] M. B. Mashhadi, N. Shlezinger, Y. C. Eldar and D. Gündüz, "Fedrec: Federated Learning of Universal Receivers Over Fading Channels," 2021 IEEE Statistical Signal Processing Workshop (SSP), 2021, pp. 576-580.
[5] M. B. Mashhadi, Q. Yang and D. Gündüz, "CNN-Based Analog CSI Feedback in FDD MIMO-OFDM Systems," ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 8579-8583.
[6] Q. Yang, M. B. Mashhadi and D. Gündüz, "Deep Convolutional Compression for Massive MIMO CSI Feedback," 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP), 2019, pp. 1-6.
[7] F. Marvasti and M. B. Mashhadi, “Wideband analog to digital conversion by random or level crossing sampling,” US Patent 9 729 160, Aug. 8, 2017.
[8] A. R. Safavi, A. G. Perotti, B. M. Popovic, M. B. Mashhadi, and D. Gündüz, “Deep extended feedback codes,” ITU Journal on Future and Evolving Technologies (ITU J-FET), vol. 2, no. 6, 2021.