Convolutional Neural Networks (CNNs) achieve remarkable accuracy in vision tasks, yet their computational complexity challenges low-power edge deployment. In this work, we present COMET, a framework of CNN models that employ efficient hardware offset-binary coding (OBC) techniques to enable co-optimization of performance and resource utilization. The approach formulates CNN inference using OBC representations applied separately to inputs (Scheme A) and weights (Scheme B), enabling exploitation of bit-width asymmetry. The shift–accumulate operation is modified by incorporating offset-term with the pre-scaled bias. Leveraging symmetries in Schemes A and B, we introduce four look-up table (LUT) techniques—parallel, shared, split, and hybrid—and evaluate their efficiency. Building on this foundation, we develop a general matrix multiplication core using theim2coltransformation for efficient CNN acceleration. We consider LeNet-5 and All-CNN-C to demonstrate that the OBC-GEMM core efficiently supports modern workloads. Evaluation shows that COMET enables efficient FPGA deployment compared to state-of-the-art designs, with negligible accuracy loss, demonstrating its efficiency and scalability across diverse network architectures.

Resource distribution in radio networks aims at maximizing spectrum utilization while minimizing interference. In this paper, we consider the problem of uniform radio resource distribution on a periodic grid. We formulate the problem as finding the sublattice configuration that maximises the distance between adjacent resources, crucial for reducing interference and improving throughput performance. Leveraging concepts from lattice theory and discrete geometry, we present an enumerative, parallelizable algorithm to explore all possible sublattices and efficiently identify the optimal configurations. Additionally, we investigate the existence and properties of scaled-rotated sublattices, exploring how different lattice geometries impact optimal solutions. Numerical results demonstrate the effectiveness of the proposed algorithm and highlight insights into optimal sublattice design for various lattice structures. Furthermore, the results are applied to the identification of the beam layout in a fixed multibeam geostationary satellite. Numerical results show that the spectral efficiency of the optimised sublattice is higher than all other sublattices. This work thus advances the field of radio resource distribution and offers practical implications for improving satellite network performance.

The computational demands of next-generation (Next-Gen) communication systems pose major challenges for real-time signal processing, particularly in digital predistortion (DPD), which is essential for linearizing power amplifier (PA) nonlinearities. While traditional DPD methods-such as polynomial and Volterra series models-remain prevalent, neural network (NN)-based approaches offer superior modeling accuracy and adaptability. However, their deployment is hindered by high computational complexity, limited scalability, and hardware integration challenges. This review presents a comprehensive analysis of NN-based DPD techniques and hardware acceleration strategies for efficient real-time implementation. We assess the strengths of various NN architectures-deep, convolutional, recurrent, and hybrid-and evaluate their tradeoffs across graphics processing unit (GPU), field-programmable gate arrays (FPGA), and application-specific integrated circuits (ASIC) platforms. We also examine key challenges, including fragmented evaluation standards and limited real-world validation. Finally, we outline future directions emphasizing model-hardware codesign, reconfigurable computing, and on-chip learning to enable scalable, energy-efficient DPD for 5G, 6G, and beyond.

The Consultative Committee for Space Data Systems (CCSDS) File Delivery Protocol (CFDP) enables reliable file transfer across space communication links that experience interruptions and delays, supporting diverse transfer modes with minimal human intervention. This paper presents an open-source Python library implementing CFDP, following guidelines from the CCSDS Blue Book. To date, this library is the only fully functional CFDP implementation in Python and is among the first open-source versions available. Developed in Python 3, with compatibility for MicroPython for low-power applications, the library supports both Class 1 (unreliable) and Class 2 (reliable) file transfers, using Zero Message Queue (ZMQ), CCSDS Space Packet Protocol, and User Datagram Protocol (UDP) for transport and network layers. An extendable virtual file store is included to support various data storage options. Full CCSDS compliance has been validated through cross-testing with the European Space Agency (ESA) CFDP implementation. A graphical user interface (GUI) enhances usability for nontechnical users, supplementing the command-line interface. This open-source CFDP library is ideal for space and terrestrial file transfers and is increasingly valuable for file-based operations in space missions.

This paper presents a millimeter-wave shared-volume dual-aperture antenna array with enhanced spatial coverage efficiency for IoT devices. The antenna unit is implemented with two substrate integrated step horns sharing the volume of a cube. The radiation apertures of the two step horns are perpendicular to each other, namely the horizontal aperture and the vertical aperture, enabling a large spatial coverage with a small size. The working bandwidth of the horizontal aperture is from 22 GHz to 37 GHz, and the working bandwidth of the vertical aperture is from 19 GHz to 30 GHz. A 4-element linear array is proposed using the antenna unit. The horizontal and vertical subarrays obtain an average 11.5 dBi and 10.5 dBi realized gain respectively, with –3 dB scanning angle being up to ±35∘ at 27 GHz. A simulation is conducted by deploying the designed array in a smartphone to demonstrate its performance in practical applications. The spatial coverage efficiency of the proposed antenna array is calculated to quantify its spatial coverage capability. A prototype of the 4-element array is fabricated and a good agreement is achieved between the measurement and the simulation.

This paper presents a novel radio frequency fingerprint (RFF) enhancement strategy by exploiting the physical unclonable function (PUF) to tune the RF hardware impairments in a unique and secure manner, which is exemplified by taking power amplifiers (PAs) in RF chains as an example. This is achieved by intentionally and slightly tuning the PA non-linearity characteristics using the active load-pulling technique. The motivation driving the proposed research is to enlarge the RFF feature differences among wireless devices of same vendor, in order to massively improve their RFF classification accuracy in low to medium signal to noise ratio (SNR) channel conditions. PUF is employed to dynamically tune the PA’s RFF feature which guarantees the security since the PUF response cannot be cloned. Specifically, a ring oscillator (RO)-based PUF is implemented to control the PA non-linearity by selecting unique but random configuration parameters. This approach is proposed to amplify the distinctions across same model PAs, thereby enhancing the RFF classification performance. In the meantime, our innovative strategy of PUF-assisted RFF does not noticeably compromise communication link performance which is experimentally tested. The resulting RFF features can be extracted from the received distorted constellation diagrams with the help of image recognition-based machine learning classification algorithms. Extensive experimental evaluations are carried out using both cable-connected and over-the-air (OTA) measurements. Our proposed approach, when classifying eight PAs from a same vendor, achieves 11% to 24% average classification accuracy improvement by enlarging the RFF feature differences arising from the PA non-linearity.

Backscatter communication is an emerging paradigm for pervasive connectivity of low-power communication devices. Wirelessly powered backscattering wireless sensor networks (WSNs) become particularly important to meet the upcoming era of the Internet of Things (IoT), which requires the massive deployment of self-sustainable and maintenance-free low-cost sensing and communication devices. This article will introduce the state-of-the-art antenna design and radio frequency (RF) system integration for wirelessly powered backscatter communications, covering both the node and the base unit. We capture the latest development in ultralow-power RF front ends and coding schemes for$\mu \text{W}$-level backscatter modulators, as well as the latest progress in wireless power transfer (WPT) and energy harvesting (EH) techniques. Newly emerged rectenna system, waveform design, and channel optimization are reviewed in light of the opportunities for adaptively optimizing the WPT/EH efficiency for low-power signals with varying conditions. In addition, advanced device packaging and integration technologies in, e.g., additively manufactured RF components and modules for microwave and millimeter-wave ubiquitous sensing and backscattering energy-autonomous RF structures are reported. Inkjet printing for the sustainable and ultralow-cost fabrication of flexible RF devices and sensors will be reviewed to provide a prospective insight into the future packaging of backscatter communications from the chip-level design to complete system integration. Finally, this article will also address the challenges in fully wireless powered backscatter radio networks and discuss the future directions of backscatter communication in terms of “Green IoT” and “Low Carbon” smart home, smart city, smart skin, and machine-to-machine (M2M) applications.

In this study, a new hybrid secondary transmitter (ST) mode is proposed for cognitive radio Internet of Things (CR‐IoT) networks with energy harvesting (EH) and ambient backscatter (AmBack) communication capabilities. The authors firstly describe the proposed hybrid mode with wireless‐powered ST. The ST, consisting of EH, Amback, and conventional active transmission modules, adapts itself under different primary user operation states, i.e. active or idle. The overall throughput of the secondary system is formulated and the system settings for achieving optimal performance are derived and validated through numerical simulations.

High-speed train (HST) communications in tunnels have attracted more and more research interests recently, especially within the framework of the fifth generation (5G) wireless networks. In this paper, based on cuboid-shape, three-dimensional (3D) non-stationary wideband geometry-based stochastic models (GBSMs) for HST tunnel scenarios are proposed. By considering the influence of the tunnel walls, a theoretical channel model is first established, which assumes clusters with an infinite number of scatterers randomly distributed on the tunnel walls. The corresponding simulation model is then developed and the method of equal areas is employed to obtain the discrete parameters, such as the azimuth and elevation angles. We derive and investigate the most important channel statistical properties of the proposed 3D GBSMs, including the time-variant autocorrelation function, spatial cross-correlation function, and Doppler power spectrum density. It is indicated that all statistical properties of the simulation model, verified by simulation results, can match very well with those of the theoretical model. Furthermore, a validation is presented by comparing the stationary regions of our proposed tunnel channel model to those of relevant measurement data.

This paper proposes a procedure of predicting channel characteristics based on a well‐known machine learning (ML) algorithm and convolutional neural network (CNN), for three‐dimensional (3D) millimetre wave (mmWave) massive multiple‐input multiple‐output (MIMO) indoor channels. The channel parameters, such as amplitude, delay, azimuth angle of departure (AAoD), elevation angle of departure (EAoD), azimuth angle of arrival (AAoA), and elevation angle of arrival (EAoA), are generated by a ray tracing software. After the data preprocessing, we can obtain the channel statistical characteristics (including expectations and spreads of the above‐mentioned parameters) to train the CNN. The channel statistical characteristics of any subchannels in a specified indoor scenario can be predicted when the location information of the transmitter (Tx) antenna and receiver (Rx) antenna is input into the CNN trained by limited data. The predicted channel statistical characteristics can well fit the real channel statistical characteristics. The probability density functions (PDFs) of error square and root mean square errors (RMSEs) of channel statistical characteristics are also analyzed.