Walid Saad

Check out our recent publication in IEEE Wireless Communications Letters entitled " GumbelRIS: End-to-End CNN-Based 2-Bit Phase Optimization for Large-Scale RIS-Aided MIMO Systems". The work, led by our brilliant PhD researcher Kinza Shafique and with the insightful contribution of Dr. Haitham Saleh, shows that the proposed technique outperforms metaheuristics and learning-based baselines across varying RIS sizes and channel conditions and generalizes well without retraining. https://lnkd.in/dTjrUetd #RIS #MIMO #6G 

91

3 Comments

Our work on understanding the potential of peering among cellular providers will appear in IEEE TCCN. The study sheds light on the viability of settlement-free peering as an alternative roaming agreements among the cellular providers. Our framework suggests that the providers select regions where they will treat each other's customers equal to their subscribed customers -- without charging roaming fees which is the current practice. Anindo Mahmood Shahzeb Mustafa Sayanta Seth, Ph.D Mostafizur Rahman

62

1 Comment

I am pleased to share my newest paper about the pros and cons of drain vs. gate modulation when used on a GaN RF PA. Which one to use has been an ongoing debate for a while, and this work should add some clarity to the problem. Here is the link to the paper, it is in open access: https://lnkd.in/ek6_tcCd Villanova University College of Engineering IEEE Microwave Theory & Technology Society

139

7 Comments

Reconfigurable Intelligent Surfaces (RIS) are rapidly becoming one of the hottest research directions in wireless communications. RIS is envisioned as a key enabler for 6G networks, offering “second-line-of-sight” and many other exciting possibilities for future telecom systems. At KAUST IMPACT Lab, in close collaboration with Ericsson Research (Behrooz Makki), our team (Yiming Yang, Ruiqi Wang, Mohammad Vaseem, PhD Vaseem) has been investing deeply in RIS hardware innovations. Here is a summary of our contributions that tackle the most critical RIS challenges: 🔹 Wideband 1-bit 5G mm-Wave RIS hardware (IEEE TAP, 2024) For the first time, we demonstrated a 1-bit wideband RIS that covers the entire 5G n257 and n258 bands—while maintaining stable phase and magnitude over such wide frequencies. This work became an IEEE Xplore featured article and was the most dowloaded paper in IEEE TAP throughout 2024 (> 20,000 downloads).  https://lnkd.in/eiWNqhuR 🔹 Wideband 2-bit 5G mm-Wave RIS hardware (IEEE TAP, 2025) Our 1-bit RIS suffers from high sidelobes in the near field and quantization lobe in the far field, affecting wireless link quality. To solve this, we designed a 2-bit wideband RIS, which significantly reduces sidelobe levels and improves beam control across the n258 band.  https://lnkd.in/eEG2vkvV 🔹 Fully printed wideband 5G mm-Wave RIS hardware (IEEE TMTT, 2025) RIS at mm-Wave typically relies on expensive semiconductor switches, driving fabrication costs into the thousands of dollars. Leveraging our group’s expertise in printing, we introduced the world’s first fully printed RIS with vanadium dioxide (VO₂) switches directly integrated into the metallic patterns through screen printing. This breakthrough achieves 10–20× cost reduction while still delivering competitive performance at 30 GHz. https://lnkd.in/eiTG_69i More to come on our RIS work soon….

500

13 Comments

I am happy to inform that our work on designing multi-agent reinforcement learning (RL) based deep deterministic policy gradient (DDPG) algorithm for optimizing the IRS phases for multi-cell IRS massive MIMO systems is accepted for publication in IEEE Transactions on Wireless Communications. In this work, each RL agent optimizes the IRS phases of a particular cell while interacting with each other to reduce the inter-cell IRS interference. This work also develops practical low-complexity practically-implementable optimization algorithms for allocating the downlink BS power. This work is done jointly with my PhD Student Sauradeep Dey and M.Tech students Aritra roy Tejesh Kodeboina #RL #AIML #IRS #6G

172

3 Comments

Together with Borbala Hunyadi and Sofia-Eirini Kotti we are excited to present a 9-hour short course titled "Tensor Decompositions for Multilayer Network Analysis" at ICASSP'26 in Barcelona in May 2026. This short course will introduce tensor decompositions as a principled and scalable framework for analyzing temporal and multilayer networks. The course covers fundamental tensor algebra and key decomposition models, including canonical polyadic, multilinear SVD, and block term decompositions, and explains their properties, computation, and practical use. These tools are then connected to network science concepts, with a focus on community detection in multilayer networks. By establishing links between tensor generative models and classical network objectives, the course bridges modern multilinear algebra with network analysis, supported by hands-on applications to brain connectivity and social networks. https://lnkd.in/g3rHZiXT

47

Excited to share two new IEEE Journal of Solid-State Circuits (JSSC) papers from our group, both pushing the boundaries of UWB wireless links for high-channel-count implantable neural interfaces! Over the past two years, we have been exploring how UWB can deliver high-data-rate, low-power, and robust wireless communication through biological tissue, and this effort has now resulted in two JSSC papers, each addressing a key challenge in next-generation neural implants: 1️⃣ A 3-mm² multi-data-rate IR-UWB TX with an on-chip antenna, achieving - Flexible, multi-rate operation: 50 Mb/s to 1.2 Gb/s - Ultra-compact 3-mm² footprint - Dual-modulation: 4-PPM + 2-PSK (high rate), OOK (low rate) - 1.49–7.26 mW power consumption across modes This is the first mm-scale UWB transmitter that combines Gb/s-class data rates, extended communication range, and full multi-rate flexibility, enabling high-density, multi-mode (e.g., closed-loop) neural interfaces. (extended from our ESSERC 2024 work) https://lnkd.in/ezdgjTfT 2️⃣ An IR-UWB TX with co-designed PA & antenna This paper introduces a 49.8-mm² IR-UWB transmitter with a co-designed power amplifier and antenna, achieving a unique combination of high data rate (500 Mb/s), extended transmission range (meter-scale), and miniaturized, mm-scale form factor. (extended from CICC 2024) https://lnkd.in/ean52xqq I am proud of Cong Ding for her outstanding work on these projects, and many thanks to our co-authors Mingxiang Gao and Prof. Anja Skrivervik at EPFL for the collaborative effort. We are also grateful for the support from the SwissChips initiative. #JSSC #BCI #Neurotechnology

515

8 Comments

A new publication on IEEE Transactions on Vehicular Technology (TVT). Title: NOMA Systems over Fluctuating Nakagami-m Fading Channels In this work, we shed light on the efficiency of downlink transmission of NOMA systems over the recently proposed Fluctuating Nakagami-m fading channels whose applications cover vehicle-to-vehicle (V2V) communications, and device-to-device (D2D) communications among others. This work is co-authored by: Basem M. ElHalawany, Professor, SMIEEE (Kuwait College of Science and Technology & Benha University), Mohamed H. Saad (Egyptian Atomic Energy Authority), Mohamed S. Elbakry (@Institute of Aviation Engineering, and Technology (IAET), Egypt) and Osamah Badarneh (German Jordanian University & Princess Sumaya University for Technology) #Publications

66

10 Comments

Our paper, titled "Integrating Optimization Theory with Deep Learning for Wireless Network Design," has been published in early access in IEEE Communications Magazine. This is a joint work with Marco Di Renzo and Aysun G. Önalan. In this article, we introduce an innovative structured and analytical framework for wireless network design that integrates optimization theory with deep learning techniques, addressing the current lack of a theoretical foundation in existing studies. https://lnkd.in/d2RVZAQv Traditional wireless network design relies on optimization algorithms derived from domain-specific mathematical models, which are often inefficient and unsuitable for dynamic, real-time applications due to high complexity. Deep learning has emerged as a promising alternative to overcome complexity and adaptability concerns, but it faces challenges such as accuracy issues, delays, and limited interpretability due to its inherent black-box nature. This article introduces a novel approach that integrates optimization theory with deep learning methodologies to address these issues. The methodology starts by constructing the block diagram of the optimization theory- based solution, identifying key building blocks corresponding to optimality conditions and iterative solutions. Selected building blocks are then replaced with deep neural networks, enhancing the adaptability and interpretability of the system. Extensive simulations show that this hybrid approach not only reduces runtime compared to optimization theory based approaches, but also significantly improves accuracy and convergence rates, outperforming pure deep learning models.

195

5 Comments

Excited to share our latest work, now published in IEEE Communications Letters 🚀 📄 “Spread Spectrum Noise Modulation: Analysis and Detection.” In this letter, we introduce a Spread Spectrum Noise Modulation (SSNM) framework that rethinks how information can be conveyed through noise itself, bridging ideas from noise communication and spread-spectrum systems. 🔍 What’s inside the paper? - A high-data-rate SSNM framework based on a bank of noise generators - Two receiver architectures: - PTPR (Parallel Transmitter–Parallel Receiver) for high performance - PTSR (Parallel Transmitter–Serial Receiver) for reduced complexity - Low-complexity detection rules and closed-form performance analysis - Analytical results for bit error probability, index error, miss-detection, and false alarm - Insights into performance–complexity trade-offs, validated by simulations 💡 The results show that SSNM can achieve strong reliability while preserving the covert, noise-like nature of transmission, making it a promising candidate for low-power, secure, and future wireless systems. 📌 If you’re interested in noise modulation, spread spectrum, non-coherent detection, or next-generation communication paradigms, we’d love for you to check it out: 👉 Read the paper on IEEE Xplore: https://lnkd.in/dBwxpZiA Happy to discuss ideas, extensions, and potential applications. Feel free to reach out!

81

Our new paper was just online in IEEE Transactions Communications with titled "RIS-assisted SATINs with RSMA and DRL: A Trade-off between Spectral, Secrecy, and Energy Efficiency". In this paper, we address the problem of maximising secrecy energy efficiency (SEE) in SATINs, which can accurately describe the effective trade-off between security, spectral efficiency and transmit power. Particularly, we investigate a secure beamforming (BF) scheme in cognitive SATINs that employs rate-splitting multiple access (RSMA) and reconfigurable intelligent surface (RIS) in the presence of multiple eavesdroppers (Eves) in a UAV-aided secondary network (SN). To optimize the SEE for secondary vehicle users while satisfying the constraints of primary users (PUs), we utilize deep reinforcement learning (DRL) to address the coupling between different optimized parameters based on the improved long short-term memory proximal policy optimization (LSTM-PPO) algorithm. The main innovation of this paper is to design a sophisticated reward function, action space, and state space according to each constraint to speed up the convergence. In addition, simulation results show that the proposed DRL-based optimization scheme exhibits significant advantages in terms of SEE compared with benchmark schemes, validating the effectiveness of this work. https://lnkd.in/g3VizaHH

57

12 Comments