Zhi-Yong Feng

DMSNet: Cross-Band Learning for Multi-Target Sensing in Dual-Band ISAC

Dual-band integrated sensing and communication (ISAC) offers complementary high- and low-frequency echo information for multi-target sensing. However, existing dual-band ISAC sensing methods have a limited ability to exploit deep complementary information across heterogeneous bands and often incur high computational co...

Joint Parametric Sensing and Bilinear Interference Recovery in Low-Altitude ISAC Networks

Networked integrated sensing and communication (ISAC) is a promising paradigm for future wireless systems, especially for low-altitude UAV sensing and tracking. However, its sensing performance can be severely degraded by crosslink interference from neighboring communication base stations, whose power is typically much...

Communication-infrastructure-enabled ISAC for low-altitude sensing

As a core infrastructure of modern information society, cellular networks have long supported terrestrial communications and are now being extended to low-altitude connectivity with the growth of the low-altitude economy. However, the increasing number of aerial vehicles poses new challenges to airspace supervision and...

Dynamic Measurement-Pilot Allocation for Low-Earth-Orbit Satellite Integrated Communication and Navigation

Low Earth Orbit (LEO) satellite systems have potential to support integrated communication and navigation (ICaN) services. However, their rapid orbital motion makes resource allocation more difficult than in terrestrial or quasistatic satellite scenarios. In LEO-ICaN systems, the satelliteground channel quality and pos...

Deep Reinforcement Learning for Joint Communication and Control Design in Wireless Networked Control Systems

This paper investigates a wireless networked control system where a base station (BS) controller coordinates multiple nonlinear dynamic subsystems over wireless fading channels. In the considered setup, sensors first upload state observations to the BS, which then processes the received information to generate control...

Joint Optimization for Federated Learning and Transmission over Unreliable Wireless Networks with Heterogeneous Data

A federated random walk averaging framework is proposed, which is a variant of federated averaging (FedAvg) that mitigates data heterogeneity by updating models along random walk (RW) paths and aggregating them at the server and reduces the problem to a general form agnostic to task type and model architecture.

Direct Satellite-to-Device Communications: From Cooperative Task Offloading to Noncooperative Access Monitoring

A versatile DS2D system that supports cooperative task offloading and non-cooperative access monitoring, and Transformer-based models to enable blind signal detection and automatic modulation classification (AMC) are proposed.

Mixture-of-Experts for Hybrid Channel Prediction