Christos Masouros

Zhentian Zhang, Kai-Kit Wong, David Morales-Jimenez et al.

This paper investigates fluid antenna systems (FASs) subject to finite-blocklength (FBL) constraints, motivated by the strict reliability-latency and ultra-massive connectivity requirements of future wireless networks. While FAS performance has been widely studied in the asymptotic regime, its behavior under FBL remains largely unexplored. Our objective is to develop a unified set of analytical tools for evaluating FASs under FBL that remains applicable across different spatial-correlation models. First, to establish accurate benchmarks for non-orthogonal finite-length user signature design, we characterize both the average and the worst-case correlation coefficients via extreme value theory (EVT) and derive closed-form predictions of the achievable correlation levels. Second, taking block error rate (BLER) as the fundamental FBL metric, we study joint detection and decoding in FAS-assisted links and derive a closed-form BLER expression that is universally applicable across channel models. Additionally, we revisit outage probability (OP) in the FBL regime and obtain tractable OP characterizations for both FASs and conventional multiple fixed-position antenna (FPA) systems. In order to reduce the computational burden for multi-fold integrals in correlated fading models, we further propose a Taylor-expansion-assisted mean value theorem for integrals (MVTI), thus enabling efficient performance evaluation with marginal accuracy loss. Numerical results validate the analysis and reveal that even single-antenna FASs can have superior spatial diversity relative to conventional multi-FPA systems. Moreover, under both FBL and interference-limited environments, FASs provide improved energy, spectral, and hardware efficiencies, hence highlighting FAS as a promising enabler for next-generation wireless networks.

Yubo Peng, Luping Xiang, Kun Yang et al.

The transition to 6G calls for tightly integrated sensing and communication to support mission-critical services such as autonomous driving, embodied AI, and high-precision telemedicine. However, most existing ISAC designs rely on a single sensing modality (often RF), which limits environmental understanding and becomes a bottleneck in complex and dynamic scenes. This motivates a shift from single-modal to multimodal ISAC, where heterogeneous sensors (e.g., radar, LiDAR, and cameras) complement each other to improve robustness and semantic awareness. In this article, we first summarize key challenges for multimodal ISAC, including heterogeneous fusion, communication overhead, and scalable system design. We then highlight three enabling technologies: large AI models, semantic communications, and multi-agent systems, and discuss how their combination can enable task-oriented multimodal perception. Building on these insights, we propose a unified cloud-edge-terminal (CET) framework that hierarchically distributes intelligence and supports three adaptive operation modes: global fusion mode (GFM), cooperative relay mode (CRM), and peer interaction mode (PIM). A case study evaluates the framework across three modes, demonstrating that GFM achieves the highest accuracy, PIM minimizes latency, and CRM strikes an optimal balance between performance and efficiency. Finally, we conclude with open research issues and future directions.

Murat Temiz, Yongwei Zhang, Yanwei Fu et al.

This article comprehensively reviews recent developments and research on deep learning-based (DL-based) techniques for integrated sensing and communication (ISAC) systems. ISAC, which combines sensing and communication functionalities, is regarded as a key enabler for 6G and beyond networks, as many emerging applications, such as vehicular networks and industrial robotics, necessitate both sensing and communication capabilities for effective operation. A unified platform that provides both functions can reduce hardware complexity, alleviate frequency spectrum congestion, and improve energy efficiency. However, integrating these functionalities on the same hardware requires highly optimized signal processing and system design, introducing significant computational complexity when relying on conventional iterative or optimization-based techniques. As an alternative to conventional techniques, DL-based techniques offer efficient and near-optimal solutions with reduced computational complexity. Hence, such techniques are well-suited for operating under limited computational resources and low latency requirements in real-time systems. DL-based techniques can swiftly and effectively yield near-optimal solutions for a wide range of sophisticated ISAC-related tasks, including waveform design, channel estimation, sensing signal processing, data demodulation, and interference mitigation. Therefore, motivated by these advantages, recent studies have proposed various DL-based approaches for ISAC system design. After briefly introducing DL architectures and ISAC fundamentals, this survey presents a comprehensive and categorized review of state-of-the-art DL-based techniques for ISAC, highlights their key advantages and major challenges, and outlines potential directions for future research.

Jiawei Huang, Di Zhang, Yuanhao Cui et al.

Wireless sensing has become a fundamental enabler for intelligent environments, supporting applications such as human detection, activity recognition, localization, and vital sign monitoring. Despite rapid advances, existing datasets and pipelines remain fragmented across sensing modalities, hindering fair comparison, transfer, and reproducibility. We propose the Sensing Dataset Protocol (SDP), a protocol-level specification and benchmark framework for large-scale wireless sensing. SDP defines how heterogeneous wireless signals are mapped into a unified perception data-block schema through lightweight synchronization, frequency-time alignment, and resampling, while a Canonical Polyadic-Alternating Least Squares (CP-ALS) pooling stage provides a task-agnostic representation that preserves multipath, spectral, and temporal structures. Built upon this protocol, a unified benchmark is established for detection, recognition, and vital-sign estimation with consistent preprocessing, training, and evaluation. Experiments under the cross-user split demonstrate that SDP significantly reduces variance (approximately 88%) across seeds while maintaining competitive accuracy and latency, confirming its value as a reproducible foundation for multi-modal and multitask sensing research.

Abdullahi Mohammad, Christos Masouros, Yiannis Andreopoulos

This paper introduces a framework for systematic complexity scaling of deep neural network(DNN) based MIMO detectors. The model uses a fraction of the DNN inputs by scaling their values through weights that follow monotonically non-increasing functions. This allows for weight scaling across and within the different DNN layers in order to achieve accuracy-vs.-complexity scalability during inference. In order to further improve the performance of our proposal, we introduce a sparsity-inducing regularization constraint in conjunction with trainable weight-scaling functions. In this way, the network learns to balance detection accuracy versus complexity while also increasing robustness to changes in the activation patterns, leading to further improvement in the detection accuracy and BER performance at the same inference complexity. Numerical results show that our approach is 10-foldand 100-fold less complex than classical approaches based on semi-definite relaxation and ML detection, respectively.

Muhammad R. A. Khandaker, Christos Masouros, Kai-Kit Wong

This paper considers full-duplex (FD) device-to-device (D2D) communications in a downlink MISO cellular system in the presence of multiple eavesdroppers. The D2D pair communicate sharing the same frequency band allocated to the cellular users (CUs). Since the D2D users share the same frequency as the CUs, both the base station (BS) and D2D transmissions interfere each other. In addition, due to limited processing capability, D2D users are susceptible to external attacks. Our aim is to design optimal beamforming and power control mechanism to guarantee secure communication while delivering the required quality-of-service (QoS) for the D2D link. In order to improve security, artificial noise (AN) is transmitted by the BS. We design robust beamforming for secure message as well as the AN in the worst-case sense for minimizing total transmit power with imperfect channel state information (CSI) of all links available at the BS. The problem is strictly non-convex with infinitely many constraints. By discovering the hidden convexity of the problem, we derive a rank-one optimal solution for the power minimization problem.