
Jamming attacks pose a critical threat to wireless networks, particularly in cell-free massive MIMO systems, where distributed access points and user equipment (UE) create complex, time-varying topologies. This paper proposes a novel jamming detection framework leveraging dynamic graphs and graph convolution neural networks (GCN) to address this challenge. By modeling the network as a dynamic graph, we capture evolving communication links and detect jamming attacks as anomalies in the graph evolution. A GCN-Transformers-based model, trained with supervised learning, learns graph embeddings to identify malicious interference. Performance evaluation in simulated scenarios with moving UEs, varying jamming conditions and channel fadings, demonstrates the method’s effectiveness, which is assessed through accuracy and F1 score metrics, achieving promising results for effective jamming detection.
A promising artificial intelligence (AI)-driven cross-layer modulation is proposed to perform the bit-symbol mapping for the multiple-input-multiple-output (MIMO) transmission mode in the next generation wireless communication system. Unlike the prior modulation technologies, multiple influence factors including he constellation mapping, the number of spatial layers, layer mapping and power allocation among spatial layers are simultaneously taken into account in the proposed method pursuing for spectral efficiency maximization via auto-encoder (AE) model. In this paper, a joint optimization subject to influence factors above for the cross-layer modulation is fulfilled based on the AE framework for simplifying the design complexity and achieving a better performance. Simulation results demonstrate that the block error rate (BLER) performance of the proposed cross-layer modulation is beyond the traditional scheme by around 1 dB as a result of the learned bit-symbol mapping for spatial layers.
To enhance target sensing capabilities in low Earth orbit (LEO) satellite communication systems, this paper proposes a LEO satellite-enabled integrated sensing and communication (ISAC) beamforming (LSEIB) algorithm. Specifically, a LEO satellite-enabled bistatic ISAC system is constructed, in which the LEO satellite simultaneously transmits both communication and sensing signals, while the ground gateway receives the echoes to enable cooperative sensing. To balance communication performance and sensing accuracy, the upper bound of the achievable communication rate based on statistical channel state information and the Cramer-Rao bound (CRB) expression for two-dimensional angle-of-arrival estimation are derived. A joint beamforming optimization problem is then formulated with the objective of minimizing the CRB. Subsequently, a semidefinite relaxation method is introduced to transform the original non-convex problem into an equivalent semidefinite program, and a closed-form rank-one solution is constructed to satisfy the rank constraint. Simulation results demonstrate that the proposed LSEIB algorithm exhibits great convergence and optimization performance under various settings, and the proposed bistatic architecture achieves significant improvements in sensing performance compared to the monostatic counterpart.
This paper presents an IoT-enabled digital twin framework designed to enhance real-time monitoring and management of freshwater pollution. The framework integrates distributed IoT sensors to collect high-resolution data on dissolved oxygen (DO), temperature, and pollution dynamics, enabling the timely detection of ecological stressors. A four-layer architecture, comprising device, virtualisation, aggregation, and service layers, facilitates scalable data processing, visualisation, and stakeholder engagement. Key contributions include empirical validation of the IoT-enabled digital twin framework to monitor fresh water pollution, a modular system for anomaly detection and historical trend analysis, and actionable insights derived from spatially distributed edge nodes. The results highlight the inverse correlation between temperature and DO levels, disrupted during storm events by abrupt oxygen crashes (e.g. below 4 mg/l) and the critical role of edge node deployment in the river bed. The digital twin monitoring, recollection, and predictive modules collectively support proactive water quality management, identifying pollution gradients and seasonal patterns. Testing and evaluation on the Derwent river shows the system’s practical efficacy in reducing environmental risks and informing sustainable interventions.
This study presents a bio-hybrid implant comprising a passive microwave resonator and a colony of engineered E. coli that express proteins in response to thermal stimuli. We propose a novel method for wireless control of the genetically modified bacteria using microwave hyperthermia. Synthetic biology has enabled cell-based sensing and actuation; however, the lack of viable wireless communication mechanisms with those cells limits their usage inside the human body. Direct electromagnetic interaction with individual cells would require terahertz and beyond frequencies, which are impractical for in-body use due to high tissue absorption. Instead, we introduce a wireless control strategy based on focused microwave hyperthermia, delivered via an on-body antenna operating between 0.782 GHz and 1.938 GHz. Cellular activation is achieved by localized heating at the implant site, created by the passive resonator. Preliminary results demonstrate that the system can achieve a localized temperature increase of more than 6 degrees C in 5 minutes with 1 W transmit power to activate heat-sensitive genetic circuits, thus establishing a proof-of-concept for wireless thermal control of biological function.