AAAbdulmuneem Alselwi

Abdulmuneem Alselwi

*This is an algorithmically generated author record based on publicly available information.

Abdulmuneem Alselwi has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Adaptive Radar Control Under Latent-Type Jamming via Game-Informed Reinforcement Learning

    by Abdulmuneem Alselwi, Osamah Khaled, Adnan Umar Khan, Khaled Abdullah, Hussein Abdulhadi, Hasan Abdulhadi

  • Open Access

    Hybrid Game-Theoretic and Reinforcement Learning for Adaptive Radar Jamming Decision-Making

    by Abdulmuneem Alselwi, Hussein Abdulhadi, Abdulrahman Alsalehi, Hasan Abdulhadi, Khaled Abdullah, Osamah Khaled

    This paper presents a novel decision-making framework for adaptive radar jamming, termed Hybrid Game-Theoretic and Reinforcement Learning (GTRL), which fuses game-theoretic (GT) priors with deep reinforcement learning (RL) through a confidence-weighted policy fusion mechanism. While RL-based jammers excel in adapting to dynamic environments, they often lack strategic foresight; conversely, GT methods offer anticipatory advantages but remain rigid in non-stationary scenarios. Hybrid GTRL bridges this gap by incorporating Stackelberg game-based initialization, utility-guided action pruning, and confidence-aware policy fusion that dynamically balances the influence of GT and RL agents. Experimental results demonstrate that Hybrid GTRL consistently outperforms both RL-only and GT-only baselines across key metrics, including average jamming utility, policy volatility, and convergence efficiency. Ablation studies confirm the non-redundancy of each architectural module. Despite moderate computational overhead, the system remains suitable for deployment on edge-grade hardware. Hybrid GTRL represents a promising step toward intelligent, resilient jamming agents capable of operating effectively in adversarial, rapidly evolving electromagnetic environments.


  • Open Access

    CRB-Based Sensing and Robust Beamforming for Secure ISAC in 6G

    by Abdulmuneem Alselwi, Khaled Abdullah, Osamah Khaled, Hussein Abdulhadi

    Integrated sensing and communication (ISAC) is a core enabler for 6G networks, yet ensuring physical layer security (PLS) remains challenging under mobility and imperfect channel knowledge. This paper proposes a unified framework that integrates a CRB-based mobility-aware sensing trigger with robust beamforming via semidefinite programming (SDP). The CRB-velocity policy adaptively invokes sensing based on estimation accuracy and eavesdropper mobility, thereby reducing redundant activations in low-mobility regimes while intensifying sensing when mobility threatens secrecy. Robust beamforming with artificial noise is then employed to guarantee worst-case secrecy under channel state information (CSI) uncertainty. Theoretical analysis establishes a quadratic CRB scaling law for mobility-aware thresholds and proves the rank-one tightness of the robust SDP relaxation. Extensive simulations confirm that the proposed framework reduces sensing overhead by up to 80% relative to fixed and periodic baselines, while maintaining secrecy rates above 2 bps/Hz even under large CSI errors. Tradeoff analysis further shows that the proposed method lies on the Pareto frontier between secrecy and sensing efficiency, and a multiuser extension demonstrates scalability to practical deployments. These results highlight that integrating mobility-aware sensing with robust transmission design provides an effective and practical pathway toward secure ISAC in future 6G networks.

  • Open Access

    Game Informed Reinforcement Learning Framework for Radar-Jammer Strategy Optimization in Cognitive Electronic Warfare

    by Abdulmuneem Alselwi, Osamah Khaled

    This paper presents Game-Informed Reinforcement Learning (GIRL), a framework for optimizing radar behavior in adversarial electromagnetic environments. GIRL integrates a game-theoretic Stackelberg policy prior with online Bayesian belief inference and KL-regularized policy learning, enabling the radar to infer adversarial intent and adapt its control policy dynamically. We model radar-jammer interactions as a partially observable stochastic game and demonstrate that embedding game priors into the learning loop significantly accelerates convergence and improves robustness to type uncertainty and prior mismatch. Extensive simulations under four cognitive electronic warfare scenarios show that GIRL consistently outperforms conventional model-free and belief-only baselines in both performance and generalization. We also provide ablation studies to isolate the contributions of each module and confirm the framework's resilience under adversarial prior distortions. The proposed GIRL framework offers a principled and modular approach to integrating domain knowledge and statistical learning for radar decision-making in complex contested settings.

  • Open Access

    Task-Aware Pilot Design for ISAC Systems via Mutual Information Optimization

    by Abdulmuneem Alselwi, Osamah Khaled, Magdi Dhaiban, Khaled Abdullah, Hussein Abdulhadi

    This paper presents an environment-aware adaptive pilot design framework for integrated sensing and communication (ISAC) systems operating in dynamic wireless environments. Unlike conventional static pilot schemes, our approach leverages real-time updates based on evolving channel and scene statistics to jointly optimize sensing and communication performance. We formulate a scalarized optimization problem that jointly considers the communication and sensing MI, parameterized by a task-priority weight ρ. To solve this problem under orthogonality constraints, we develop a projected gradient descent (PGD) algorithm operating on the Stiefel manifold, enabling the generation of environment-adaptive and task-aware pilot matrices. The proposed approach exhibits superior performance across a wide range of operating conditions. Extensive simulations demonstrate that it achieves lower channel estimation error, improved mutual information trade-offs, and faster convergence compared to fixed or random orthogonal designs. Furthermore, the framework adapts to variations in user load, pilot length, SNR, and clutter power, while maintaining computational efficiency. The PGD method's ability to dynamically balance communication and sensing objectives makes it highly suitable for next-generation ISAC systems requiring flexible and efficient joint functionality.

  • Multi-user transmission for the joint radar communication systems based on amplitude phase shift keying modulation and waveform diversity

    by Abdulmuneem Alselwi, Adnan Umar Khan, Ijaz Mansoor Qureshi, Wasim Khan, Abdul Basit

    In this paper, an efficient dual function radar-communication system is proposed to improve the system's resource utilization. In this work, we considered a scenario where the location of the communication receiver is known prior but the radar target is moving and its location is changing with time. Therefore, we proposed a closed-loop design that allows an adaptive selection of appropriate information embedding strategies during tracking operations. We used two strategies that utilize the amplitudes and/or phases of the transmitted radar waveforms toward the communication direction according to the position of the communication receiver during each scan. Hence, during each radar illumination, the system carries out a target-tracking task and simultaneously maintains the communication symbols transmission toward the intended communication direction. The simulation results verify the effective performance of the proposed approach in terms of target detection and tracking performance and angular bit error rate (BER). Furthermore, the proposed amplitude phase-shift keying signaling strategy can transmit different communication symbols to different users located within the sidelobe region and also provides a significant improvement in data rate transmission and BER performance compared with the existing sidelobe-based communication strategies.


  • Open Access

    Throughput Enhancement for the Joint Radar-Communication Systems Based on Cognitive Closed-Loop Design

    by Abdulmuneem Alselwi, Adnan Umar Khan, Ijaz Mansoor Qureshi, Wasim Khan, Abdul Basit

    The majority of the current dual function radar-communication (DFRC) systems are producing only an angle-dependent transmit beampattern (BP) and imposing a constraint for the communication receiver to be present within the sidelobe (SL) directions to decode the transmitted information. In this paper, an efficient angle-range dependent DFRC system is proposed using frequency diverse array (FDA)-multiple-input multiple-output (MIMO) configuration. We developed a closed-loop design that improves the tracking task of the system and permits a cognitive selection for an optimum signaling strategy towards the intended communication receiver during each scan. We used two information embedding schemes, a proposed amplitude phase shift keying (APSK) and phase-shift keying (PSK), that utilize either the magnitude ratios and/or phase shifts between the radar waveform pairs towards the communication direction. Hence, the communication link is maintained and the system throughput is enhanced. The simulation results verify that the communication performance is enhanced in terms of low symbol error rate (SER), secure information transmission, and increased throughput, while for radar applications the performance is improved in terms of target detection and parameter estimation. It also showed that the proposed symbol mapping APSK scheme provides a high data rate transmission compared to the existing SL-based information embedding schemes while preserving a low bit error rate (BER). Besides, the Cramer-Rao lower bounds (CRLB) for range and angle estimation and the signal-to-interference-noise ratio (SINR) for the proposed DFRC system are analyzed.