Zhiguo Zhang

Automated Mid-Surface Mesh Reconstruction for Automotive Plastic Parts Based on Point Cloud Registration

Yan Ma, Hongbin Tang, Zehui Huang, Jianjiao Deng et autres

In automotive Computer-Aided Engineering (CAE), the fidelity of high-quality shell element meshes is fundamentally governed by the accuracy of mid-surface geometry extraction. Conventional manual extraction for complex automotive plastic components is labor-intensive, error-prone, and often compromises mesh quality. To address these issues, …

cn (code pays fourni par la source)

A-SNNMS: An Attentive Shared Neural Normalized Min-Sum Decoder for LDPC Codes

Fengquan Zheng, Liqian Wang, Kunfeng Liu, Zhiguo Zhang

To address the limitations of static message aggregation and training instability in the existing Shared Neural Normalized Min-Sum (SNNMS) algorithm, this paper proposes A-SNNMS, an attentive deep LDPC decoding network with adaptive training. First, an attention mechanism is introduced into the variable …

cn (code pays fourni par la source)

Adaptive Longitudinal–Lateral Coordinated Control of Distributed Drive Vehicles Under Unknown Road Conditions

Jiansen Yang, Zhongliang Han, Zhiguo Zhang, X. Wang et autres

Distributed drive vehicles provide enhanced actuation flexibility, making longitudinal–lateral coordinated stability control essential for improving vehicle handling and safety under complex driving conditions. Nevertheless, the existing coordinated control strategies commonly employ stability reference models with fixed tire–road friction coefficients, which restrict their …

cn, hk (code pays fourni par la source)

DAR-Swin: Dual-Attention Revamped Swin Transformer for Intelligent Vehicle Perception Under NVH Disturbances

Xinglong Zhang, Zhiguo Zhang, Huihui Zuo, Chaotan Xue et autres

In recent years, deep learning-based image classification has made significant progress, especially in safety-critical perception fields such as intelligent vehicles. Factors such as vibrations caused by NVH (noise, vibration, and harshness), sensor noise, and road surface roughness pose challenges to robustness and …

cn, hk (code pays fourni par la source)

Optimizing Multi-DNN Inference on Mobile Devices Through Heterogeneous Processor Co-Execution

Yunquan Gao, Zhiguo Zhang, Praveen Kumar Donta, Chinmaya Kumar Dehury et autres

Deep Neural Networks (DNNs) are increasingly adopted across various industries, driving the demand for deploying their capabilities on mobile devices. However, current mobile inference frameworks often rely on a single processor to execute each model inference, limiting hardware utilization and leading to …

cn, se, ee, sg (code pays fourni par la source)

Inferring ancient from modern: a deep learning approach for species identification of archaeological wood

Jiajun Wang, Aikun Lin, Ling Fang, Yang Lu et autres

Identification of archaeological wood species is critical for decoding the biogeographical, historical, and cultural narratives of artifacts, but remains a challenge in practice. To address this challenge, we developed a deep learning framework integrating computer vision and archaeological wood species analysis. Images …

cn (code pays fourni par la source)

High-power small-core-diameter semiconductor laser at 1550 nm: A novel solution for low-loss long-distance energy transmission

Zhongwei Cao, Haojie Zhang, Zhen Ma, Haibin Wu et autres

cn (code pays fourni par la source)

HUANNet: A High-Resolution Unified Attention Network for Accurate Counting

Haixia Wang, Huan Zhang, Xiuling Wang, Zhiguo Zhang

Accurately counting dense objects in complex and diverse backgrounds is a significant challenge in computer vision, with applications ranging from crowd counting to various other object counting tasks. To address this, we pro... | Find, read and cite all the research you …

cn (code pays fourni par la source)

Passive-active hybrid FBG-power-over-fiber system for integrated sensing, power delivery, and communication

Xueliang Gu, Zhiguo Zhang, Xin Peng, Tong Zhai et autres

Despite advancements in optical fiber sensing and power transmission technologies, existing systems face challenges of redundant multi-device deployment and incoordination between power supply and communication under complex working conditions such as strong electromagnetic interference, hazardous areas, or long-distance monitoring. This paper proposes …

cn, us (code pays fourni par la source)

Efficient parallel relaying FSO communications using rateless codes in horizontal terrestrial and satellite-to-ground scenarios

Beibei Cui, Shanyong Cai, Liqian Wang, Zhiguo Zhang

The reliability of FSO communications is severely limited by atmospheric conditions. Adding redundant communication channels, like parallel relaying, is a solution to achieve high reliability. Parallel relaying can achieve non-linear propagation and compensate for signal degradation by reducing the length of single …

Design and Simulation of a Single-Layer Circularly Polarized Antenna Based on Metasurface

Shuo Chen, Wei Zhang, Zhiguo Zhang, Haojie Zhang

This paper presents the design of a single-layer wideband circularly polarized antenna operating at 2.1 GHz. The antenna integrates metasurface technology and achieves wideband and high-gain performance through optimized structural parameters. A corner-truncated patch is employed as the radiating element, surrounded by …

cn (code pays fourni par la source)

Advanced Multiphysics Fast Design of Electromagnetic Components for Wireless Sensing in Constrained Spaces

Yuyang Jiao, Wenting Wang, Yang Tian, Mingliang Liu et autres

Wireless communication and sensing in underground and electromagnetically constrained spaces present significant challenges due to limited signal propagation, interference, and environmental complexities. High performance wireless components and systems need to be design carefully to satisfy in such real-world multiphysics environments. This paper …

cn (code pays fourni par la source)