arXiv subjects

Jiali Nie

Publications and source records attributed to Jiali Nie.

6 recordsLinked to original sources

arXiv2026

Radar-Aided Near-Field Beam Prediction via Beam Map Learning for XL-MIMO V2I Communications

Near-field beam training in extremely large-scale multiple-input multiple-output (XL-MIMO) vehicle-to-infrastructure (V2I) systems incurs high overhead due to large range-angle codebooks and rapid channel variation. This paper proposes a passive radar-aided framework for near-field beam prediction based on radar-to-beam map learning. By exploiting the spatial correlation between radar observations and communication signals, the proposed method maps radar Bartlett spectra to communication beam maps using a lightweight encoder-decoder convolutional neural network. Gaussian soft supervision is further introduced to preserve beam-space continuity. Simulations on a synchronized Sionna ray tracing radar-communication dataset show that the proposed method consistently improves Top-k accuracy, distance-based accuracy, beam loss, and spectral efficiency.

eess.SP↗

arXiv2026

Low-Altitude Wireless Networks: The Next Horizon of Wireless Infrastructure

Low-altitude airspace, roughly defined as the region up to 3000 meters above ground level, is envisioned as a new spatial domain for daily human and machine activities. This article introduces the concept of the Low-Altitude Wireless Network (LAWN), which represents a paradigm shift from the current ground-based communication-only network to a three-dimensional (3D) multifunctional network. We analyze the key driving forces, network architecture, and limiting factors of LAWN, with a particular focus on the tight integration of communication, sensing, and control in highly dynamic airspace environments. By establishing the coupling between airspace capacity and wireless channel capacity, we reveal the intrinsic limits of airspace management and identify the fundamental challenges and opportunities associated with its evolution.

cs.NI↗

arXiv2026

Analytical Framework of Airy Beams in Near-Field XL-MIMO: From Ideal Optics to Wireless Reality

The synthesis of Airy-profiled wavefronts has emerged as a pivotal paradigm for advanced electromagnetic engineering, attributed to their intrinsic non-diffractive propagation, transverse self-acceleration, and structural self-healing properties. While the advent of extremely large-scale multiple-input multiple-output (XL-MIMO) and the elevation in frequency bands for sixth generation wireless systems provide the physical foundation for generating such structured beams, their wireless realization is fundamentally governed by hybrid precoding architectures, finite array apertures, and discrete antenna topologies. These constraints induce significant deviations from ideal optical Airy beam models, necessitating a rigorous re-characterization of Airy beams in practical wireless contexts. Consequently, this paper establishes an analytical theoretical framework to explicitly characterize Airy beam propagation in near-field XL-MIMO and derives the constraints on array aperture and antenna spacing to sustain distortion-free main lobe trajectories. Furthermore, quantitative metrics are developed to rigorously evaluate the performance trade-offs between Airy beams and Gaussian focusing beams, thereby providing systematic guidelines for their deployment in scenario-dependent wireless applications. Numerical results corroborate the proposed analytical theoretical framework of Airy beams in near-field XL-MIMO, and demonstrate the potential to achieve robust communication and spectral efficiency (SE) improvement in certain scenarios.

eess.SP↗

arXiv2025

Integrated Sensing and Communication: Towards Multifunctional Perceptive Network

The capacity-maximization design philosophy has driven the growth of wireless networks for decades. However, with the slowdown in recent data traffic demand, the mobile industry can no longer rely solely on communication services to sustain development. In response, Integrated Sensing and Communications (ISAC) has emerged as a transformative solution, embedding sensing capabilities into communication networks to enable multifunctional wireless systems. This paradigm shift expands the role of networks from sole data transmission to versatile platforms supporting diverse applications. In this review, we provide a bird's-eye view of ISAC for new researchers, highlighting key challenges, opportunities, and application scenarios to guide future exploration in this field.

eess.SP↗

arXiv2024

Edge Perception: Intelligent Wireless Sensing at Network Edge

Future sixth-generation (6G) networks are envisioned to support intelligent applications across various vertical scenarios, which have stringent requirements on high-precision sensing as well as ultra-low-latency data processing and decision making. Towards this end, a new paradigm of edge perception networks emerges, which integrates wireless sensing, communication, computation, and artificial intelligence (AI) capabilities at network edge for intelligent sensing and data processing. This article provides a timely overview on this emerging topic. We commence by discussing wireless edge perception, including physical layer transceiver design, network-wise cooperation, and application-specific data analytics, for which the prospects and challenges are emphasized. Next, we discuss the interplay between edge AI and wireless sensing in edge perception, and present various key techniques for two paradigms, namely edge AI empowered sensing and task-oriented sensing for edge AI, respectively. Finally, we emphasize interesting research directions on edge perception to motivate future works.

cs.IT↗

arXiv2024

Near-field Beam training for Extremely Large-scale MIMO Based on Deep Learning

Extremely Large-scale Array (ELAA) is considered a frontier technology for future communication systems, pivotal in improving wireless systems' rate and spectral efficiency. As ELAA employs a multitude of antennas operating at higher frequencies, users are typically situated in the near-field region where the spherical wavefront propagates. The near-field beam training in ELAA requires both angle and distance information, which inevitably leads to a significant increase in the beam training overhead. To address this problem, we propose a near-field beam training method based on deep learning. We use a convolutional neural network (CNN) to efficiently learn channel characteristics from historical data by strategically selecting padding and kernel sizes. The negative value of the user average achievable rate is utilized as the loss function to optimize the beamformer. This method maximizes multi-user networks' achievable rate without predefined beam codebooks. Upon deployment, the model requires solely the pre-estimated channel state information (CSI) to derive the optimal beamforming vector. The simulation results demonstrate that the proposed scheme achieves a more stable beamforming gain and significantly improves performance compared to the traditional beam training method. Furthermore, owing to the inherent traits of deep learning methodologies, this approach substantially diminishes the near-field beam training overhead.

cs.LG↗