Diagnosing the root causes of Quality of Experience (QoE) degradations in operational mobile networks is challenging due to complex cross-layer interactions among kernel performance indicators (KPIs) and the scarcity of reliable expert annotations. Although rule-based heuristics can generate labels at scale, they are noisy and coarse-grained, limiting the accuracy of purely data-driven approaches. To address this, we propose DK-Root, a joint data-and-knowledge-driven framework that unifies scalable weak supervision with precise expert guidance for root-cause analysis. DK-Root first pretrains an encoder via contrastive representation learning using abundant rule-based labels while mitigating their noise through representation-level learning rather than direct noisy-label classification. To supply task-faithful data augmentation, we introduce a class-conditional diffusion model that generates KPIs sequences designed to preserve root-cause semantics, and by controlling reverse diffusion steps, it produces weak and strong augmentations that improve intra-class compactness and inter-class separability. Finally, the encoder and the lightweight classifier are jointly fine-tuned with scarce expert-verified labels to sharpen decision boundaries. Experiments on a real-world operator-grade dataset show that DK-Root consistently outperforms strong competing methods, delivers more balanced and discriminative class-level predictions for confusable root causes, and approaches comparable root-cause analysis performance with approximately one-third to one-half fewer expert annotations.

This paper investigates a collaborative integrated sensing and communication (ISAC) network enabled by movable antennas (MAs), where the base station (BS) equipped with an MA array performs target sensing using downlink signaling while supporting uplink computation offloading from multiple devices. Using the Cramér-Rao bound (CRB) of target angle estimation as the sensing-performance metric, we characterize its dependence on the BS antenna positions and formulate a joint optimization problem to minimize the CRB by co-designing device transmit powers, BS receive beamforming, and MA positions, subject to maximum transmit-power constraints, computation offloading requirements, constraints on the beamforming vectors, and antenna position constraints. To address the resulting non-convex coupling, we develop an alternating optimization (AO) algorithm that incorporates successive convex approximation (SCA) and semidefinite relaxation (SDR) to obtain a high-quality suboptimal solution. Simulation results show that the proposed joint MA–resource optimization substantially reduces the CRB, meets the computation requirements, and consistently outperforms benchmark schemes.

To support the development of low altitude economy, the air-ground integrated sensing and communication (ISAC) networks need to be constructed to provide reliable and robust communication and sensing services. In this paper, the sensing capabilities in the cooperative air-ground ISAC networks are evaluated in terms of area radar detection coverage probability under a constant false alarm rate, where the distribution of aggregated sensing interferences is analyzed as a key intermediate result. Compared with the analysis based on the strongest interferer approximation, taking the aggregated sensing interference into consideration is better suited for pico-cell scenarios with high base station density. Simulations are conducted to validate the analysis.

Matched-field processing localizes underwater acoustic targets by measuring the degree of correlation between the acoustic field and replica fields. The intrusion of mesoscale eddies can induce sound speed mismatch in the matched-field process. Therefore, it is essential to investigate the impact of mesoscale eddies on matched-field localization errors. In this study, the typical vertical structure of mesoscale eddies in a certain region of the Northwestern Pacific was synthesized using the mesoscale eddy dataset META 2.0 and Argo float data. Furthermore, by employing both an idealized eddy model and composite-analysis structure of eddy, the performance of the localization algorithm was evaluated under the influence of mesoscale eddies with different structures and in different regions. The results show that under specific conditions, the distribution of localization errors exhibits certain patterns, which is beneficial for inverting eddy parameters via matched-field processing. Finally, the mechanism behind the systematic distribution of localization errors is discussed and analyzed. In the simulations, the source frequency was swept from 50 to 75 Hz with a 1 Hz step, and a circular array was employed as the receiving aperture. These findings indicate that, in the absence of small-scale interference and within a certain range of sound speed mismatch, the localization error of underwater acoustic targets increases with the strengthening of mesoscale eddy disturbances.

To support the development of air-ground integrated sensing and communication (ISAC), network-level performance analysis is needed for providing an essential guide on the network design. Following the widely adopted orthogonal frequency-division multiplexing (OFDM) technology in existing wireless systems, a cooperative air-ground wireless network based on OFDM-ISAC is introduced in this paper, where the ISAC-enabled base stations (BSs) following the two-dimensional homogeneous Poisson point process (HPPP) distribution serve the terrestrial communication users while sensing the aerial targets. In particular, cooperative beamforming schemes are designed for mitigating the interference among ISAC BSs. First, we analyze the communication as well as sensing performances in terms of different metrics including area communication coverage probability, area communication spectral efficiency, area radar detection coverage probability, and average Cram & eacute;r-Rao Bound. Simulation results are then presented to validate the theoretical analysis and illustrate the effects of key system parameters on the network performance. It is observed that both the communication and sensing (C&S) performances depend on the BS density and height, while the sensing performance also depends on the height of sensing target together with the numbers of OFDM subcarriers and symbols. Moreover, there exists a tradeoff between the C&S performances with respect to the BS density and height. The results of this paper provide useful guidance to the design and implementation of air-ground wireless network for harnessing the dual benefits of ISAC.

Driven by the prosperous vision of a low-altitude economy (LAE), the low-altitude airspace is expected to be exploited for commercial and social flying activities. The network architectures for supporting LAE are first introduced in this article, including the localized statistical channel modeling and performance analysis based on stochastic geometry. Then, the technological prerequisites for ground-to-air sensing and communication are discussed, including cellular access, spectrum sharing, three-dimensional beamforming, and interference cancellation, as well as cooperative active sensing and non-cooperative passive sensing. The aircraft-assisted sensing and communication functionalities for LAE are further reviewed, including terrestrial and non-terrestrial target sensing, ubiquitous coverage, relaying, and traffic offloading. Finally, several future directions are identified, including aircraft collaboration, energy efficiency, and artificial intelligence-enabled LAE.

The impressive performance of ChatGPT and other foundation-model-based products in human language understanding has prompted both academia and industry to explore how these models can be tailored for specific industries and application scenarios. This process, known as the customization of domain-specific foundation models (FMs), addresses the limitations of general-purpose models, which may not fully capture the unique patterns and requirements of domain-specific data. Despite its importance, there is a notable lack of comprehensive overview papers on building domain-specific FMs, while numerous resources exist for general-purpose models. To bridge this gap, this article provides a timely and thorough overview of the methodology for customizing domain-specific FMs. It introduces basic concepts, outlines the general architecture, and surveys key methods for constructing domain-specific models. Furthermore, the article discusses various domains that can benefit from these specialized models and highlights the challenges ahead. Through this overview, we aim to offer valuable guidance and reference for researchers and practitioners from diverse fields to develop their own customized FMs.

The synergy between Federated Learning (FL) and Foundation Models (FMs) holds great promise in enhancing privacy protection and improving the generalization capabilities of AI systems. However, the high computational and communication overhead of FMs hinders effective deployment in real-world scenarios. Although some pioneering research has proposed using proxy sub-Foundation Models (sub-FMs) to reduce the computational and communication costs when fine-tuning FMs in FL environments, it overlooks the challenges posed by heterogeneous mobile devices with varying computational and communication capabilities, and by dynamic changes in their operational conditions, which cause very long FL training delay. Motivated by these challenges, we propose a novel federated fine-tuning of Foundation Models design via adaptive pruning (FedFTAP). FedFTAP introduces a pruning method specifically designed for FMs, combined with parameter-efficient fine-tuning modules to enhance communication and computational efficiency. FedFTAP further addresses system heterogeneity and system dynamic changes by adaptively tailoring heterogeneous sub-FMs suitable for local training on mobile devices. Moreover, FedFTAP introduces a method for aligning heterogeneous sub-FMs with the global FM. The experimental results show that FedFTAP effectively reduces computational and communication costs in federated fine-tuning scenarios.

The analysis of network performance is an important guide for network deployment and design. In this work, the low-altitude integrated sensing and communication (ISAC) networks performance is studied in terms of communication coverage at the network level, where the ISAC base station (BS) serves the terrestrial communication users (CUs) while sensing the aerial targets. In contrast to previous works, the specific beamforming schemes rather than simple antenna beam gain are considered. As the interferences from other BSs during sensing are non-negligible, the cooperative beamforming design is necessary for effective sensing. Following the common fashion of stochastic geometry, the BSs, CUs and sensing targets are randomly distributed as two-dimensional homogeneous Poisson point processes (HPPP). By comparing HPPP model with the lattice model and actual BS deployment, it can be observed that the presented analysis in HPPP model and ideal lattice model are the lower and upper bounds of the actual deployments, respectively.

The development of integrated sensing and communication (ISAC) brings new challenges to network optimization. This is not only due to the unpredictable relationship between ISAC network performance and network parameters but also the lack of well-suited ISAC channel models for ISAC network optimization. We propose a framework of multi-beam statistical channel modeling aided ISAC signal signal-to-interference-plus-noise ratios (SINR) prediction, utilizing channel angular power spectrum to accurately characterize both echo signal and communication signal-to-interference-plus-noise ratio after antenna parameter adjustment. Utilizing real-world driving test data for multi-path channel estimation, this framework accurately characterizes the stochastic sensing channels and provides effective prediction strategies for antenna parameter adjustments. Simulation results demonstrate that our approach outperforms the conventional method with a single-beam path loss model.

Driven by the rapid development of deep learning approaches, many novel WiFi sensing based applications have emerged, such as human activity recognition, pose estimation and indoor localization. However, due to the limited richness of collected WiFi data, the performance of WiFi sensing based models still lags behind conventional vision based models in terms of recognition accuracy and generalization. To break through the bottleneck of insufficient WiFi data, we propose a diffusion model based data augmentation scheme for human activity recognition task, in which the training dataset is composed of both real data and synthetic data. In particular, to reduce training overheads of the diffusion model, it is trained by taking activity classes as input conditions. Therefore, a single model is able to generate multiple types of WiFi data corresponding to activities, thereby avoiding the need to train separate models for each individual activity. Simulation results show that the generated WiFi data samples are visually indistinguishable from real ones, even when the model is trained on a small-scale dataset. Moreover, it also shows that adding an appropriate amount of synthetic data into training dataset can indeed improve the performance of WiFi sensing in most cases.

Semantic communication (SemCom) offers a promising avenue for enhancing transmission efficiency, especially as traditional bit-level communication approaches its theoretical limits. A key enabling technology in SemCom is deep learning-based joint source and channel coding (DeepJSCC). However, existing DeepJSCC methods lack interpretability because they transmit semantic information implicitly by mapping data to latent features. Additionally, the black-box nature of neural networks makes it challenging to ensure the reliable transmission of critical semantics. To address these challenges, we propose advancing DeepJSCC towards a more "semantic" approach. Specifically, we suggest transmitting interpretable and lightweight semantics as side information alongside JSCC latent features. At the receiver end, we introduce a novel latent diffusion model designed for wireless communication, trained from scratch to integrate seamlessly with DeepJSCC. Using the semantic side information, the receiver employs the proposed semantics-guided latent diffusion for denoising. Furthermore, since accurate channel state information (CSI) is essential in practice, we propose estimating CSI directly from the channel output. The estimated CSI is then used for step matching in the denoising diffusion process, enabling CSI-free transmission. Finally, the denoised feature is fed into the JSCC decoder to reconstruct the image. Numerical results demonstrate that our proposed scheme can achieve comparable performance without accurate CSI. Additionally, guided by semantic information and leveraging the powerful diffusion model, our method surpasses current DeepJSCC schemes, delivering satisfactory reconstruction performance even at SNR = -5dB. This proposed scheme highlights the potential of incorporating diffusion models in future SemCom systems and suggests several promising applications.

The Age of Information (AoI) is viewed as a key performance metric in real-time applications. This letter focuses on the analysis and optimization of AoI in the context of area sensing. First, we develop a model for an omnidirectional sensing system and divide the entire area into multiple sub-areas. Then, the analytical expression of the average AoI for each sub-area is derived by modelling the evolution process of the instantaneous AoI for each sub-area as a Discrete-Time Markov Chain (DTMC). Finally, we formulate two optimization problems, one based on the min-max criterion and the other on the sum-optimal criterion. The former is solved analytically, and the latter is a sum-of-ratios minimization fractional programming (min-FP) problem, which is solved by an alternating iterative algorithm. Simulation results verify the accuracy of our analytical results of the average AoI and demonstrate the effectiveness of our solutions in addressing the two optimization problems.

Integrated sensing and communication (ISAC) is considered as the potential key technology of the future mobile communication systems. The signal design is fundamental for the ISAC system. The reference signals in mobile communication systems have good detection performance, which is worth further research. Existing studies applied the single reference signal to radar sensing. In this paper, a multiple reference signals collaborative sensing scheme is designed. Specifically, we jointly apply channel state information reference signal (CSI-RS), positioning reference signal (PRS) and demodulation reference signal (DMRS) in radar sensing, which improve the performance of radar sensing via obtaining continuous time-frequency resource mapping. Cr\'amer-Rao lower bound (CRLB) of the joint reference signal for distance and velocity estimation is derived. The impacts of carrier frequency and subcarrier spacing on the performance of distance and velocity estimation are revealed. The results of simulation experiments show that compared with the single reference signal sensing scheme, the multiple reference signals collaborative sensing scheme effectively improves the sensing accuracy. Moreover, because of the discontinuous OFDM symbols, the accuracy of velocity estimation could be further improved via compressed sensing (CS). This paper has verified that multiple reference signals, instead of single reference signal, have much more superior performance on radar sensing, which is a practical and efficient approach in designing ISAC signal.

In this paper, a cloud radio access network (Cloud-RAN) based collaborative edge AI inference architecture is proposed. Specifically, geographically distributed devices capture real-time noise-corrupted sensory data samples and extract the noisy local feature vectors, which are then aggregated at each remote radio head (RRH) to suppress sensing noise. To realize efficient uplink feature aggregation, we allow each RRH receives local feature vectors from all devices over the same resource blocks simultaneously by leveraging an over-the-air computation (AirComp) technique. Thereafter, these aggregated feature vectors are quantized and transmitted to a central processor (CP) for further aggregation and downstream inference tasks. Our aim in this work is to maximize the inference accuracy via a surrogate accuracy metric called discriminant gain, which measures the discernibility of different classes in the feature space. The key challenges lie on simultaneously suppressing the coupled sensing noise, AirComp distortion caused by hostile wireless channels, and the quantization error resulting from the limited capacity of fronthaul links. To address these challenges, this work proposes a joint transmit precoding, receive beamforming, and quantization error control scheme to enhance the inference accuracy. Extensive numerical experiments demonstrate the effectiveness and superiority of our proposed optimization algorithm compared to various baselines.

In recent years, significant advancements in deep learning, wireless communication, and sensing have laid the foundation for integrated sensing and learning (ISAL), which involves machines actively and collaboratively collecting data from the environment to facilitate model training at the network edge, specifically for tactile intelligence service provisioning. Despite the progress in deep learning, a it faces a vital issue of overfitting, wherein models excel on training samples but struggle with unseen ones, particularly when resource constraints are in play. To address this issue, we draw inspiration from the classic stochastic gradient Langevin dynamics (SGLD) approach, where a right amount of noise is introduced to gradients to alleviate overfitting and enhance model generalizability. We propose an over-the-air federated stochastic gradient descent (Air-FedSGD) scheme for distributed model training. This scheme inherently introduces the required noisy gradient akin to SGLD, where the noise level is jointly determined by the devices' transmission power and sensing duration. Within this context, we formulate a joint sensing and communication (SC) resource allocation problem with the objective of minimizing the population loss of the learned model. Unlike the commonly used empirical loss, population loss measures model performance not only on the training set but on every set identically independent of the training set, thereby giving us a handle on the generalization ability of a model. The solution to this problem establishes an AI task-oriented joint sensing and communications design framework, which is elaborated considering a specific use case of human motion recognition. Extensive experimental results validate the superiority of the proposed design, affirming its effectiveness in addressing over-fitting challenges and enhancing generalization capabilities.

Addressing the communication and sensing demands of sixth-generation (6G) mobile communication system, integrated sensing and communication (ISAC) has garnered traction in academia and industry. With the sensing limitation of single base station (BS), multi-BS cooperative sensing is regarded as a promising solution. The coexistence and overlapped coverage of macro BS (MBS) and micro BS (MiBS) are common in the development of 6G, making the cooperative sensing between MBS and MiBS feasible. Since MBS and MiBS work in low and high frequency bands, respectively, the challenges of MBS and MiBS cooperative sensing lie in the fusion method of the sensing information in high and low-frequency bands. To this end, this paper introduces a symbol-level fusion method and a grid-based three-dimensional discrete Fourier transform (3D-GDFT) algorithm to achieve precise localization of multiple targets with limited resources. Simulation results demonstrate that the proposed MBS and MiBS cooperative sensing scheme outperforms traditional single BS (MBS/MiBS) sensing scheme, showcasing superior sensing performance

The rapid development of communication systems has aroused the expectation of providing localization and communication services simultaneously. In this letter, a hybrid uplink transmission for joint localization and communication (JLC) networks is studied. First, the closed-form expressions of Crámer–Rao lower bound (CRLB) of the localization estimation error are derived for the first time, providing a metric for evaluating the localization performance. Then, a joint power and subcarrier allocation problem for uplink JLC networks is formulated. An alternative algorithm is proposed to solve the mixed integer nonlinear programming (MINLP) problem based on majorization-minimization (MM) and sequential parametric convex approximation (SPCA) methods. Simulation results are presented to verify the effectiveness of the proposed algorithm.

Prior works on near-field beam training mostly assume dedicated polar-domain codebooks and on-grid range estimation, however, this may incur large training overhead and deteriorated estimation accuracy. In this paper, we propose a new and efficient beam training scheme with off-grid range esti-mation based on conventional discrete Fourier transform (DFT) codebook, which greatly reduces the beam training overhead. In particular, we first analyze the received beam pattern at the user when far-field beamforming vectors are used for beam scanning, and reveal an interesting result that this beam pattern contains useful user angle and range information. Then, an efficient scheme was proposed to jointly estimate the user angle and range using DFT codebook. This scheme estimates the user angle based on a defined angular support and resolves the user range by leveraging an approximated angular support width. Finally, numerical simulations show that our proposed scheme significantly reduces the near-field beam training overhead and improves the range estimation accuracy compared with various benchmark schemes.

As the proliferation of sophisticated task models in 5G-empowered digital twin, it yields significant demands on fast and accurate model training over resource-limited wireless networks. It is vital to investigate how to accelerate the training process based on the salient features of practical systems, including heterogeneous data distributions and system resources both across devices and over time. To study the nontrivial coupling between participating device selection and their appropriate training parameters, we first characterize the dependency of convergence performance bound on system parameters, i.e., statistical structure of local data, mini-batch size, and gradient quantization level. Based on the theoretical analysis, a training efficiency optimization problem is formulated subject to heterogeneous communication and computation capabilities among devices. To realize online control of training parameters, we propose an adaptive batch-size-assisted device scheduling strategy, which prioritizes the selection of devices that offer good data utility and dynamically adjust their mini-batch sizes and gradient quantization levels adapting to network conditions. Simulation results demonstrate that our proposed strategy can effectively speed up the training process as compared with benchmark algorithms.