Abstract:Millimeter-wave (mmWave) OFDM radar equipped with rainbow beamforming, enabled by joint phase-time arrays (JPTAs), provides wide-angle coverage and is well-suited for fast real-time target detection and tracking. However, accurate detection of multiple closely spaced targets remains a key challenge for conventional signal processing pipelines, particularly those relying on constant false alarm rate (CFAR) detectors. This paper presents CFARNet, a learning-based processing framework that replaces CFAR with a convolutional neural network (CNN) for peak detection in the angle-Doppler domain. The network predicts target subcarrier indices, which guide angle estimation via a known frequency-angle mapping and enable high-resolution range and velocity estimation using the MUSIC algorithm. Extensive simulations demonstrate that CFARNet significantly outperforms a CFAR+MUSIC baseline, especially under low transmit power and dense multi-target conditions. The proposed method offers superior angular resolution, enhanced robustness in low-SNR scenarios, and improved computational efficiency, highlighting the potential of data-driven approaches for high-resolution mmWave radar sensing.
Abstract:Massive multiple-input multiple-output (MIMO) technology is a key enabler of modern wireless communication systems, which demand accurate downlink channel state information (CSI) for optimal performance. Although deep learning (DL) has shown great potential in improving CSI feedback, most existing approaches fail to exploit the semantic relationship between CSI and other related channel metrics. In this paper, we propose SemCSINet, a semantic-aware Transformer-based framework that incorporates Channel Quality Indicator (CQI) into the CSI feedback process. By embedding CQI information and leveraging a joint coding-modulation (JCM) scheme, SemCSINet enables efficient, digital-friendly CSI feedback under noisy feedback channels. Experimental results on DeepMIMO datasets show that SemCSINet significantly outperforms conventional methods, particularly in scenarios with low signal-to-noise ratio (SNR) and low compression ratios (CRs), highlighting the effectiveness of semantic embedding in enhancing CSI reconstruction accuracy and system robustness.
Abstract:In this paper, we explore the feasibility of using communication signals for extended target (ET) tracking in an integrated sensing and communication (ISAC) system. The ET is characterized by its center range, azimuth, orientation, and contour shape, for which conventional scatterer-based tracking algorithms are hardly feasible due to the limited scatterer resolution in ISAC. To address this challenge, we propose ISACTrackNet, a deep learning-based tracking model that directly estimates ET kinematic and contour parameters from noisy received echoes. The model consists of three modules: Denoising module for clutter and self-interference suppression, Encoder module for instantaneous state estimation, and KalmanNet module for prediction refinement within a constant-velocity state-space model. Simulation results show that ISACTrackNet achieves near-optimal accuracy in position and angle estimation compared to radar-based tracking methods, even under limited measurement resolution and partial occlusions, but orientation and contour shape estimation remains slightly suboptimal. These results clearly demonstrate the feasibility of using communication-only signals for reliable ET tracking.
Abstract:Joint phase-time arrays (JPTA) emerge as a cost-effective and energy-efficient architecture for frequency-dependent beamforming in wideband communications by utilizing both true-time delay units and phase shifters. This paper exploits the potential of JPTA to simultaneously serve multiple users in both near- and far-field regions with a single radio frequency chain. The goal is to jointly optimize JPTA-based beamforming and subband allocation to maximize overall system performance. To this end, we formulate a system utility maximization problem, including sum-rate maximization and proportional fairness as special cases. We develop a 3-step alternating optimization (AO) algorithm and an efficient deep learning (DL) method for this problem. The DL approach includes a 2-layer convolutional neural network, a 3-layer graph attention network (GAT), and a normalization module for resource and beamforming optimization. The GAT efficiently captures the interactions between resource allocation and analog beamformers. Simulation results confirm that JPTA outperforms conventional phased arrays (PA) in enhancing user rate and strikes a good balance between PA and fully-digital approach in energy efficiency. Employing a logarithmic utility function for user rates ensures greater fairness than maximizing sum-rates. Furthermore, the DL network achieves comparable performance to the AO approach, while having orders of magnitude lower computational complexity.
Abstract:Coping with the impact of dynamic channels is a critical issue in joint source-channel coding (JSCC)-based semantic communication systems. In this paper, we propose a lightweight channel-adaptive semantic coding architecture called SNR-EQ-JSCC. It is built upon the generic Transformer model and achieves channel adaptation (CA) by Embedding the signal-to-noise ratio (SNR) into the attention blocks and dynamically adjusting attention scores through channel-adaptive Queries. Meanwhile, penalty terms are introduced in the loss function to stabilize the training process. Considering that instantaneous SNR feedback may be imperfect, we propose an alternative method that uses only the average SNR, which requires no retraining of SNR-EQ-JSCC. Simulation results conducted on image transmission demonstrate that the proposed SNR-EQJSCC outperforms the state-of-the-art SwinJSCC in peak signal-to-noise ratio (PSNR) and perception metrics while only requiring 0.05% of the storage overhead and 6.38% of the computational complexity for CA. Moreover, the channel-adaptive query method demonstrates significant improvements in perception metrics. When instantaneous SNR feedback is imperfect, SNR-EQ-JSCC using only the average SNR still surpasses baseline schemes.
Abstract:Federated semi-supervised learning (FSSL) is primarily challenged by two factors: the scarcity of labeled data across clients and the non-independent and identically distribution (non-IID) nature of data among clients. In this paper, we propose a novel approach, diffusion model-based data synthesis aided FSSL (DDSA-FSSL), which utilizes a diffusion model (DM) to generate synthetic data, bridging the gap between heterogeneous local data distributions and the global data distribution. In DDSA-FSSL, clients address the challenge of the scarcity of labeled data by employing a federated learning-trained classifier to perform pseudo labeling for unlabeled data. The DM is then collaboratively trained using both labeled and precision-optimized pseudo-labeled data, enabling clients to generate synthetic samples for classes that are absent in their labeled datasets. This process allows clients to generate more comprehensive synthetic datasets aligned with the global distribution. Extensive experiments conducted on multiple datasets and varying non-IID distributions demonstrate the effectiveness of DDSA-FSSL, e.g., it improves accuracy from 38.46% to 52.14% on CIFAR-10 datasets with 10% labeled data.
Abstract:This paper studies energy-efficient hybrid beamforming architectures and its algorithm design in millimeter-wave communication systems, aiming to address the challenges faced by existing hybrid beamforming due to low hardware flexibility and high power consumption. To solve the problems of existing hybrid beamforming, a novel energy-efficient hybrid beamforming architecture is proposed, where radio-frequency (RF) switch networks are introduced at the front and rear ends of the phase shifter network, enabling dynamic connections between the RF chains and the phase shifter array as well as the antenna array. The system model of the proposed architecture is established, including digital precoding and analog precoding processes, and the practical hardware limitations such as quantization errors of the digital-to-analog converter (DAC) and phase shifter resolution. In order to maximize the energy efficiency, this paper derives an energy efficiency model including spectral efficiency and system power consumption, and a hybrid precoding algorithm is proposed based on block coordinate descent to iteratively optimize the digital precoding matrix, analog precoding matrix, and DAC resolution. Simulation results under the NYUSIM-generated millimeter-wave channels show that the proposed hybrid beamforming architecture and precoding algorithm have higher energy efficiency than existing representative architectures and precoding algorithms under complete and partial channel state information, while the loss of spectral efficiency compared to fully connected architecture is less than 20%
Abstract:With the increasing demand for seamless connectivity and intelligent communication, the integration of artificial intelligence (AI) and communication for sixth-generation (6G) network is emerging as a revolutionary architecture. This paper presents a comprehensive overview of AI and communication for 6G networks, emphasizing their foundational principles, inherent challenges, and future research opportunities. We commence with a retrospective analysis of AI and the evolution of large-scale AI models, underscoring their pivotal roles in shaping contemporary communication technologies. The discourse then transitions to a detailed exposition of the envisioned integration of AI within 6G networks, delineated across three progressive developmental stages. The initial stage, AI for Network, focuses on employing AI to augment network performance, optimize efficiency, and enhance user service experiences. The subsequent stage, Network for AI, highlights the role of the network in facilitating and buttressing AI operations and presents key enabling technologies, including digital twins for AI and semantic communication. In the final stage, AI as a Service, it is anticipated that future 6G networks will innately provide AI functions as services and support application scenarios like immersive communication and intelligent industrial robots. Specifically, we have defined the quality of AI service, which refers to the measurement framework system of AI services within the network. In addition to these developmental stages, we thoroughly examine the standardization processes pertinent to AI in network contexts, highlighting key milestones and ongoing efforts. Finally, we outline promising future research opportunities that could drive the evolution and refinement of AI and communication for 6G, positioning them as a cornerstone of next-generation communication infrastructure.
Abstract:Large Language Models (LLMs) have achieved significant success in various natural language processing tasks, but the role of wireless networks in supporting LLMs has not been thoroughly explored. In this paper, we propose a wireless distributed Mixture of Experts (WDMoE) architecture to enable collaborative deployment of LLMs across edge servers at the base station (BS) and mobile devices in wireless networks. Specifically, we decompose the MoE layer in LLMs by placing the gating network and the preceding neural network layer at BS, while distributing the expert networks among the devices. This deployment leverages the parallel inference capabilities of expert networks on mobile devices, effectively utilizing the limited computing and caching resources of these devices. Accordingly, we develop a performance metric for WDMoE-based LLMs, which accounts for both model capability and latency. To minimize the latency while maintaining accuracy, we jointly optimize expert selection and bandwidth allocation based on the performance metric. Moreover, we build a hardware testbed using NVIDIA Jetson kits to validate the effectiveness of WDMoE. Both theoretical simulations and practical hardware experiments demonstrate that the proposed method can significantly reduce the latency without compromising LLM performance.
Abstract:In this paper, we propose a novel multi-task, multi-link relay semantic communications (MTML-RSC) scheme that enables the destination node to simultaneously perform image reconstruction and classification with one transmission from the source node. In the MTML-RSC scheme, the source node broadcasts a signal using semantic communications, and the relay node forwards the signal to the destination. We analyze the coupling relationship between the two tasks and the two links (source-to-relay and source-to-destination) and design a semantic-focused forward method for the relay node, where it selectively forwards only the semantics of the relevant class while ignoring others. At the destination, the node combines signals from both the source node and the relay node to perform classification, and then uses the classification result to assist in decoding the signal from the relay node for image reconstructing. Experimental results demonstrate that the proposed MTML-RSC scheme achieves significant performance gains, e.g., $1.73$ dB improvement in peak-signal-to-noise ratio (PSNR) for image reconstruction and increasing the accuracy from $64.89\%$ to $70.31\%$ for classification.