Mohammed Zourob

Mohammed Zourob

Auto-generated profile, based on publicly available information

Mohammed Zourob

Wireless Technologies Research and Development Department, CableLabs, Louisville, CO, USA

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 February 2025 in IEEE Wireless Communications Letters
Verified
Journal Article
Closed access
MAMohammed Kamel AbuFoul
Mohammed Kamel AbuFoul
DTDeeb Assad Tubail
Deeb Assad Tubail
MZMohammed Zourob
Mohammed Zourob
SISalama Ikki
Salama Ikki
This study aims to estimate a Block Time-Varying channel by identifying its key parameters using a limited number of pilots occupying a subset of transmitted symbols. The method is evaluated in the context of an Orthogonal Time-Frequency Space (OTFS) system, proposing two estimators for different levels of available information. The first, based on received signals, employs Maximum Likelihood (ML) with a four-dimensional grid search, simplified to two dimensions via a linear model reformulation. The second estimator incorporates prior knowledge of parameter transitions using the Extended Kalman Filter (EKF). Performance is evaluated against theoretical lower bounds.

2 November 2017 in Mobile Networks and Applications
Verified
Journal Article
Closed access
PDF file
MZMohammed Zourob
Mohammed Zourob
Raveendra RaoRaveendra Rao
Raveendra Rao

14 January 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
DTDeeb Assad Tubail
Deeb Assad Tubail
MZMohammed O. M. Zourob
Mohammed O. M. Zourob
SISalama Ikki
Salama Ikki
This work addresses two innovative and challenging aspects in the pursuit of an accurate localization process, which can be achieved through a complex and nonlinear approach such as neural networks (NN). This study specifically focuses on developing a low-complexity localization method using NNs, along with presenting the associated Cramer-Rao Lower Bound (CRB). The research considers real-world scenarios where system performance is corrupted by imperfect synchronization and hardware impairments (HWI), which cause significant accuracy reduction when using traditional estimators. The NN approach offers a promising solution to counteract the effects of HWI and synchronization issues, by using substantial prior information during the training phase. However, incorporating this prior information and dealing with the non-linearity of NNs presents challenges in deriving the CRB of the neural localization process. To overcome these challenges, the research utilizes the f-divergence function and the concept of mutual information to derive the CRB, making it applicable to various HWI, nonlinear activation functions in NNs and statistical models. The study further simplifies the optimization problem traditionally associated with this approach used in calculating the CRB. The simulation results demonstrate that the proposed approach achieves a low-complexity and accurate localization process even in asynchronous and impaired systems. Furthermore, the simulations validate the proposed CRB driving technique and provide the CRB values for various neural localization scenarios.

23 December 2024 in IEEE Open Journal of the Communications Society
Verified
Journal Article
Open access
DTDeeb Assad Tubail
Deeb Assad Tubail
MZMohammed Zourob
Mohammed Zourob
SISalama Ikki
Salama Ikki
This work aims to enhance and generalize the joint position-velocity tracking process in millimeter wave (mmWave) systems that suffer from hardware impairments (HWIs), all while considering computational complexity. Initially, we investigate the performance of two widely used traditional trackers: the extended Kalman filter (EKF) and the unscented Kalman filter (UKF). Through this investigation, we identify the strengths and limitations of these trackers. Besides, we evaluate the gap between traditional tracking performance and the theoretical optimum by deriving the Bayesian Cramér-Rao Bound (BCRB) as a benchmark. Our findings reveal a significant disparity between the performance of traditional trackers and the benchmark, with performance being influenced by noise characteristics, initial conditions, and the accuracy of prior knowledge about the transition model. To address these challenges, we propose a neural network (NN)-based approach to achieve accurate and generalized tracking without relying on prior knowledge of the transition model, initial conditions, or noise characteristics. Specifically, our method trains a NN that performs effectively under any noise conditions, without needing to recognize the transition model or initial state. To manage the computational demands of the training phase, we employ a low-complexity algorithm, the Extreme Learning Machine (ELM), which calculates weights and biases through closed-form solution, avoiding complex optimization processes. Finally, we validate the accuracy and generality of the ELM tracker through computer simulations, testing it under various scenarios, including Gaussian and non-Gaussian HWI distortions, as well as systems with known transition models and those involving uncharacterized inputs.

25 November 2025 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
IMIslam Abu Mahady
Islam Abu Mahady
DTDeeb Assad Tubail
Deeb Assad Tubail
MZMohammed Zourob
Mohammed Zourob
SISalama Ikki
Salama Ikki
This work seeks to uncover the black-box nature of the Neural Networks (NNs) solutions in wireless systems. Specifically, this work examines direction and range estimation in millimetre-wave ($mm$-wave) systems, particularly under real-world conditions influenced by the transceivers' hardware impairments (HWIs). As a case study, we focus on the Extreme Learning Machine (ELM) algorithm, widely used in the literature as a low-complexity and efficient NN-based solution for mitigating HWIs effects. To address the challenges associated with the hidden nature of NNs, the well-known metric, Mean Squared Error (MSE), of the ELM solution is derived and studied analytically. Simulation results validate the accuracy of the derived MSE expression, demonstrating the effectiveness of this approach.

6 March 2025 in IEEE Wireless Communications Letters
Verified
Journal Article
Closed access
IMIslam Abu Mahady
Islam Abu Mahady
DTDeeb Assad Tubail
Deeb Assad Tubail
MZMohammed Zourob
Mohammed Zourob
SISalama Ikki
Salama Ikki
This study improves the interpretability of neural networks (NNs) while designing a low-complexity, yet efficient, joint localization-synchronization method. It focuses on reconfigurable intelligent surface (RIS)-assisted millimeter-wave (mmwave) communication systems. The goal is to achieve jointly accurate localization and synchronization, even under real-world conditions with hardware impairments (HWI). A novel NNs-based method is proposed to counteract HWI with reduced complexity. The mathematical framework for NNs interpretability has been investigated, and a mathematical expression for the mean squared error (MSE) of the solution is analytically derived. Furthermore, the simulation results confirm the reliability of the approach, demonstrating effective performance and validating the accuracy of the MSE derivation across various scenarios.