Jun Peng Hu

SparseLGS: Sparse View Language Embedded Gaussian Splatting

Jun Peng Hu, Zhang Chen, Zhong Li, Yi Xu et autres

Recently, several studies have combined Gaussian Splatting to obtain scene representations with language embeddings for open-vocabulary 3D scene understanding. While these methods perform well, they essentially require very dense multi-view inputs, limiting their applicability in real-world scenarios. In this work, we propose …

cn, fi, us (code pays fourni par la source)

Adaptive Dual‐Attention Learning Frame for Bearing Fault Diagnosis

Jun Peng Hu, Ali Nawaz Sanjrani, Ying Zeng, Huanwei Xu

ABSTRACT Real‐time fault diagnosis of high‐speed train bearings is critical for operational safety but remains challenging due to the complex, non‐stationary nature of vibration signals. While Transformer‐based models excel at capturing long‐range dependencies, they often struggle to extract localized fault features and …

cn (code pays fourni par la source)

Distributed Stochastic Optimization for Non-Smooth and Weakly Convex Problems under Heavy-Tailed Noise

Jun Peng Hu, Chao Sun, Bo Chen, Jianzheng Wang et autres

cn (code pays fourni par la source)

An Improved OCDM-FMCW ISAC Waveform With a Cyclically Shifted Dedicated Sensing Subcarrier Index

Zhiyuan Xie, Jun Peng Hu, Wei Chen, Yu Xiao et autres

The integrated orthogonal chirp division multiplexing (OCDM) and frequency-modulated continuous-wave (FMCW) waveform is a promising low-cost solution for integrated sensing and communication (ISAC) in sixth-generation (6G) wireless networks. However, conventional designs with a cyclic prefix (CP) and a fixed dedicated sensing subcarrier …

cn (code pays fourni par la source)

FDA-Based Integrated Sensing and Multi-Mode Communication Waveform Design and Receiver Processing Algorithm

Wei Chen, Jun Peng Hu, Yingmin Li, Yue Zhang et autres

cn (code pays fourni par la source)

A Few-Shot Specific Emitter Identification Method with Modulation-Scheme Decoupling

Dan Jiang, Chenzi Zhang, Lianyi Lu, Jun Peng Hu et autres

cn (code pays fourni par la source)

TAP-SNet: Lightweight Few-Shot Modulation Recognition via Selective Mamba Mechanism

Chenzi Zhang, Dan Jiang, Xueyang Qi, Jun Peng Hu et autres

cn (code pays fourni par la source)

Real-Time Radar Emitter Recognition on RFSoC with Integrated Preprocessing and Lightweight CNN

Shengkai Ruan, Jun Peng Hu, Zengping Chen

Radar emitter recognition (RER) is a critical task in electronic reconnaissance. While deep learning methods have significantly improved recognition accuracy, their high computational demands often hinder deployment on edge platforms. Most existing approaches predominantly rely on one-dimensional signal processing or offline two-dimensional …

cn (code pays fourni par la source)

Adaptive Electromagnetic Working Mode Decision-Making Algorithm for Miniaturized Radar Systems in Complex Electromagnetic Environments: An Improved Soft Actor–Critic Algorithm

Chudi Zhang, Jun Peng Hu, Shiyou Xu

With the advancement of multi-function radar (MFR) technology, miniaturized radar systems (MRSs) inevitably operate in complex electromagnetic environments (CEEs) dominated by MFRs as single-function radars are gradually being replaced by MFRs. MFRs can not only flexibly switch working states and generate diverse …

cn (code pays fourni par la source)

Coarse-to-Fine Spectrum Monitoring: A Joint Signal Detection and Classification via Complex Neural Network

Rundong Jiang, Jun Peng Hu, Dan Jiang, Lei Wang et autres

With the rapid development of Internet of Things (IoT) technologies, efficient spectrum management becomes crucial. Wideband monitoring helps detect abnormal channels, ensuring reliable operation of IoT devices. Software-defined radio (SDR), with its wideband acquisition capability, offers flexibility for spectrum monitoring. We propose …

cn (code pays fourni par la source)

ADSRF: A deep stacked residual framework for spectrum prediction with missing data

Lei Wang, Jun Peng Hu, Dan Jiang, Zengping Chen

cn (code pays fourni par la source)

Joint Loss-Optimized End-to-End Network for Through-Wall Multiperson Pose Estimation With Portable UWB Radar

Guangjia Huang, Jun Peng Hu, Haowen Liu, Junyu Lin

With advancements in through-wall radar (TWR), perceiving the fine-grained human poses obscured behind walls has become possible. Although imaging-based pose estimation methods have been explored, they heavily rely on image quality, which is influenced by sensor aperture. Due to the limited aperture …

cn (code pays fourni par la source)