检索结果-内蒙古大学图书馆

Delay-Beat Differential Phase Demodulation for Laser Phase Noise Immunity in Phase-Sensitive OTDR

Delay-Beat Differential Phase Demodulation for Laser Phase N...

2023 Asia Communications and Photonics Conference/2023 International Photonics and Optoelectronics Meetings, ACP/POEM 2023

作者： Qian, Heng Li, Chuan Li, Chengli Kunming University of Science and Technology Yunnan Key Laboratory of Computer Technologies Application Faculty of Information Engineering and Automation Kunming China School of Physics and Electronic Information Yunnan Normal University Yunnan Key Laboratory of Opo-electronic Information Technology Kunming China

ISBN: (纸本)9798350312614

A phase demodulation method immune to laser phase noise based on time-delay beat-frequency coherent Φ-OTDR is proposed. In this method, the two Rayleigh backscattered light beams with time delay are beat with local light beams respectively, and the phase difference of the two beat signals is used instead of the traditional distance-difference phase to obtain the local disturbance information. In this way, the impact of laser phase noise introduce by the distance-difference phase is avoid, and the constraint of laser linewidth on phase demodulation performance is weakened. In the experiment, a demodulation accuracy of -63.5dB rad2/Hz is achieved under the condition of a laser with a linewidth of 100kHz, which is improve by 11dB compared to traditional phase demodulation method. © 2023 IEEE.

关键词： distributed optical fiber sensing laser phase noise phase demodulation phase-sensitive optical time-domain reflectometry

来源：评论

学校读者我要写书评

暂无评论

Adaptive Feature Exchange Network with Complementary Advantages for Cooperative Classification of Hyperspectral and Multispectral Imagery

Adaptive Feature Exchange Network with Complementary Advanta...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Qingwang Wang Xingxing Fan Jiangbo Huang Yuanqin Meng Chengbiao Fu Tao Shen Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

With the development of remote sensing technology for earth observation, the collaborative utilization of Hyperspectral images (HSI) and multispectral images (MSI) has received increasing attention in terrestrial observation. HSI and MSI represent two typical types of optical remote sensing data and can provide rich complementary information. However, the paradoxical problem of high spatial resolution and high spectral resolution leads to difficulties in extracting complementary information. In this paper, we propose an Adaptive Feature Exchange network with Complementary Advantages (AFECAnet). Specifically, we enhance the discriminative feature extraction of HSI-MSI by introducing a spectral-spatial feature enhancement module based on a dual attention mechanism. Subsequently, in order to reduce redundant information, we design an adaptive feature interaction strategy based on batch normalization privatization factors. This strategy helps to accurately replace redundant information and reduces the computational burden on the network. Experimental results demonstrate that the proposed AFECAnet has a significant improvement in HSI-MSI collaborative classification.

关键词： Earth Adaptive systems Privatization Redundancy Collaboration Feature extraction Optical imaging

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Enhancement Module for RGB-T Semantic Segmentation in Remote Sensing

Knowledge-Enhancement Module for RGB-T Semantic Segmentation...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Qingwang Wang Haochen Song Junlin Ouyang Yebo Gu Jian Song Tao Shen Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

In accomplishing the task of semantic segmentation of RGB-T remote sensing images, there is a great challenge due to severe occlusion, long-tailed data distribution, and insufficient pixel representation of certain objects. The effective use of high-level semantic contexts among various ground object categories is crucial, yet presents considerable diffi-culties. Traditional RGB-T remote sensing image semantic segmentation methods often fail to capture and utilize complex relationships and interdependencies among these categories, leading to reduced semantic segmentation accuracy. This paper proposes a novel, knowledge-enhancement module, empowering the model to utilize human-like commonsense knowledge. Specifically, we firstly employ the self-attention and cross-attention mechanisms to fuse RGB and Thermal features. Subsequently, we collect the weights of the classification layer to get a high-level semantic pool based on all the categories. Alongside this, a prior knowledge graph is developed to enable information propagation among all categories. We applied this knowledge-enhancement module to enhance the Mask R-CNN, named KEMask R-CNN. Experiments results on the RS RGB-T dataset demonstrate the progressiveness of the proposed method.

关键词： Measurement Knowledge engineering Deep learning Accuracy Fuses Semantic segmentation Semantics

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Network with Local Topology and Spectral Feature Representation for Multispectral Point Cloud Classification

Graph Convolutional Network with Local Topology and Spectral...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Qingwang Wang Xueqian Chen Mingye Wang Chengbiao Fu Tao Shen Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Multispectral LiDAR contributes to the rapid acquisition of 3D spatial and spectral information of land covers, providing more comprehensive features for classification. Despite the impressive performance of existing Graph Neural Networks (GNNs) in point cloud classification, extracting local features with discriminative ability remains challenging in multispectral LiDAR scenes due to the uneven distribution of geometric and spectral information. To enhance the local representation of spectral features, we propose a novel Graph Convolutional Network with Local Topology and Spectral Feature Representation (GCN-LTSFR). The network constructs optimal local topological graphs of corresponding scales based on the feature distribution density of the point cloud to enhance local spectral features. Experimental results demonstrate that the proposed GCN-LTSFR outperforms several state-of-the-art methods on a real multispectral point cloud.

关键词： Point cloud compression Laser radar Three-dimensional displays Network topology Graph convolutional networks Land surface Geoscience and remote sensing

来源：评论

学校读者我要写书评

暂无评论

Differential Feature-Enhanced Fusion Network for Hyperspectral Image Classification

Differential Feature-Enhanced Fusion Network for Hyperspectr...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Qingwang Wang Jiangbo Huang Pengcheng Jin Yebo Gu Tao Shen Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Recently, some hybrid networks, combining graph convolutional network (GCN) and convolutional neural network (CNN) into a unified framework, have drawn increasing attention in hyperspectral image (HSI) classification. Compared with the single CNN or GCN architecture, hybrid networks can simultaneously perform feature learning on pixel-level and superpixel-level regions and generate complementary spectral-spatial features. However, existing methods primarily employ simple fusion strategies such as linear combination or concatenation, resulting in the extracted complementary features not being fully exploited and utilized. In this work, we propose a differential feature-enhanced fusion network (DFEFN) for HSI classification. Specifically, DFEFN consists of two different convolutional network architectures, (i.e. GCN and CNN), and a differential feature enhancement fusion (DFEF) module. The features extracted by CNN and GCN can be enhanced and fused through the DFEF module. Experiments results on two benchmark HSI datasets demonstrate that DFEFN achieves better classification performance compared with state-of-the-art methods.

关键词： Representation learning Graph convolutional networks Neural networks Geoscience and remote sensing Benchmark testing Feature extraction Hybrid power systems

来源：评论

学校读者我要写书评

暂无评论

Design of P Band Filter Antenna with High Out-of-Band Suppression

Design of P Band Filter Antenna with High Out-of-Band Suppre...

引用

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Dou, Jiangling Yuan, Yinsu Song, Jian Wang, Qingwang Shen, Tao Kunming University of Science and Technology School of Information Engineering and Automation Kunming650500 China Kunming University of Science and Technology Yunnan Key Laboratory of Computer Technologies Application Kunming650500 China Kunming University of Science and Technology Graduate School Kunming650500 China

ISBN: (纸本)9798350375909

P-band antennas offer tremendous potential in various fields, including remote sensing, communication, and radar applications. However, It is crucial to enhance their effectiveness in these domains that the current challenges in the P-band, particularly wide bandwidth and exceptional out-of-band suppression be achieved. This paper aims to introduce an efficient design scheme for a high-efficiency, high out-of-band suppression P-band filter antenna. The antenna structure comprises a Y-shaped feeding network, upper and lower parallel dielectric plates, a vertical dielectric plate, a central metal plate, and a pair of microstrip patches. The bottom feeding network employs a Y-shaped feeding network. The coupling of the antenna was effectively controlled and the good bandwidth and impedance matching have been achieved. In order to achieve a wider bandwidth and lower return loss for the antenna, slotting technology was employed on the semi-circular radiation patch. The introduction of a vertical metal plate enhances filtering performance of antenna. Additionally, there are radiation zeros at 0.68 GHz and 1.43 GHz, high-frequency selectivity is imparted and signal reflection losses are effectively reduced. key performance indicators include a filter antenna center frequency of 0.75 GHz, a -10 dB impedance bandwidth of 32.9% (0.89 GHz-1.24 GHz). In the upper stopband (0.5 GHz-0.8 GHz), the suppression level exceeds 20 dB, while in the lower stopband (1.1 GHz-1.8 GHz), suppression level exceeds 15 dB. Significant suppression characteristics are observed in the 0.5 GHz-0.8 GHz and 1.1 GHz-1.8 GHz frequency ranges. Design elements such as the semi-circular radiating patch, slotting technology, and rectangular slots on the substrate have been employed in the antenna. The suppression level, frequency selectivity had been enhance of antenna. Simulation results indicate a gain of 7.06 dB, overall efficiency beyond 95%, co-pol superior to cross-pol by more than 35 dB, and antenna

关键词： Slotting

来源：评论

学校读者我要写书评

暂无评论

An Efficient Antenna Optimization Method Based on a Parameter Dimensionality Reduction Approach

An Efficient Antenna Optimization Method Based on a Paramete...

引用

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Dou, Jiangling Zhao, Chenyang Song, Jian Wang, Qingwang Shen, Tao Kunming University of Science and Technology School of Information Engineering and Automation Kunming650500 China Kunming University of Science and Technology Yunnan Key Laboratory of Computer Technologies Application Kunming650500 China Kunming University of Science and Technology Graduate School Kunming650500 China

ISBN: (纸本)9798350375909

As antenna structure grow in complexity, the problem of time-consuming in electromagnetic (EM) simulation have become more common. This problem undoubtedly brings a series of the challenges in raising the effectiveness of antenna optimization. In order to overcome the existing difficulties, an antenna optimization method based on RF-GWO method is proposed. This approach consists of three major components. Firstly, an artificial neural network (ANN) is used to build the dataset. Compared with the traditional sampling method, the data filtered by the artificial neural network (ANN) are closer to the optimization objective. Consequently, it can better responsive to the relationship between the antenna parameters and the optimization objective. Then, the Random Forest method (RF) is utilized to analyze the impact of the ten selected parameters based on the electromagnetic (EM) simulation results on the antenna performance. Random Forest Algorithm (RF) has strong interpretability, allowing for the assessment of the contribution of different parameters to the optimization objective, which can effectively reduce the number of design variables. Finally, the antenna optimization is performed utilizing the Grey Wolf Optimization (GWO) algorithm. Combined with the sensitivity analysis results, the Gray Wolf Algorithm (GWO) can effectively search for improved results in a faster manner. In order to evaluate the algorithm's performance, the proposed method is employed to optimize a multiband miniaturized microstrip antenna. The result demonstrates that substantial improvement in impedance bandwidth is achieved by the proposed method, with an approximate 29% increase compared to conventional manual optimization methods. This outcome has proved potential and effectiveness of the proposed method in practical implications of antenna optimization. © 2024 IEEE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

A Multi-objective Antenna Optimization Method Based on Preferred Parameter Spaces

A Multi-objective Antenna Optimization Method Based on Prefe...

引用

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Dou, Jiangling Lin, Siyu Song, Jian Wang, Qingwang Shen, Tao Kunming University of Science and Technology School of Information Engineering and Automation Kunming650500 China Kunming University of Science and Technology Yunnan Key Laboratory of Computer Technologies Application Kunming650500 China Kunming University of Science and Technology Graduate School Kunming650500 China

ISBN: (纸本)9798350375909

Machine learning has been successfully used in the field of multi-objective antenna design, enabling the enhancement of antenna performance and optimizing efficiency. However, the prediction within an exceptionally vast parameter space imposes significant demands on machine learning algorithms. Moreover, minor adjustments in dimensions can bring about significant alterations in antenna performance, which renders simultaneous optimization for all objectives exceedingly challenging. To solve the multi-objective antenna optimization problem, a multi-objective antenna optimization method based on a preferred parameter space is proposed. Specifically, this method utilizes the KNN algorithm to preliminarily optimize the antenna and acquire a high-quality dataset. Subsequently, the sensitivity of ten selected parameters based on the electromagnetic (EM) simulation results is calculated by the XGBoost algorithm. The value of the parameter sensitivity is acquired by averaging ten calculations. The top four ranked parameters are designated as variables while the rest are fixed as constants. This approach reduces the number of parameters for subsequent optimization, thus greatly improving the subsequent prediction accuracy while ensuring the antenna performance. Finally, the variables derived from XGBoost are input into the fruit-fly optimization algorithm (FOA) to find the near-optimal solution. Hence, the task of parameter optimization under the multi-objectives of the impedance bandwidth and circular polarization characteristics can be effectively accomplished. To further validate its performance, the proposed algorithm is applied to optimize the S-band miniaturized broadband circularly polarized antenna. Compared to the results obtained by electromagnetic simulation only, the optimized results exhibit a 17.95% improvement of impedance bandwidth and a 42.86% enhancement of axial ratio bandwidth. Numerical outcomes validate that the proposed method achieves multi-objective o

关键词： Circular polarization

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Large-Scale AI Models for Intelligent Railway Transportation Systems:Hierarchical Poisoning Attacks and Defenses in Federated Learning

引用

computer Modeling in Engineering & Sciences 2024年第11期141卷 1305-1325页

作者： Yongsheng Zhu Chong Liu Chunlei Chen Xiaoting Lyu Zheng Chen Bin Wang Fuqiang Hu Hanxi Li Jiao Dai Baigen Cai Wei Wang School of Automation and Intelligence Beijing Jiaotong UniversityBeijing100044China Institute of Computing Technologies China Academy of Railway Sciences Corporation LimitedBeijing100081China School of Computer Science and Technology Beijing Jiaotong UniversityBeijing100044China Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing Jiaotong UniversityBeijing100044China Institute of Infrastructure Inspection China Academy of Railway Sciences Corporation LimitedBeijing100081China Zhejiang Key Laboratory of Multi-Dimensional Perception Technology Application and CybersecurityHangzhou310053China

The development of Intelligent Railway Transportation Systems necessitates incorporating privacy-preserving mechanisms into AI models to protect sensitive information and enhance system *** learning offers a promising solution by allowing multiple clients to train models collaboratively without sharing private ***,despite its privacy benefits,federated learning systems are vulnerable to poisoning attacks,where adversaries alter local model parameters on compromised clients and send malicious updates to the server,potentially compromising the global model’s *** this study,we introduce PMM(Perturbation coefficient Multiplied by Maximum value),a new poisoning attack method that perturbs model updates layer by layer,demonstrating the threat of poisoning attacks faced by federated *** experiments across three distinct datasets have demonstrated PMM’s ability to significantly reduce the global model’s ***,we propose an effective defense method,namely CLBL(Cluster Layer By Layer).Experiment results on three datasets have confirmed CLBL’s effectiveness.

关键词： Privacy-preserving intelligent railway transportation system federated learning poisoning attacks defenses

来源：评论

学校读者我要写书评

暂无评论

Coupled Graph Convolution Network for Cross-Scene Multispectral Point Cloud Classification

Coupled Graph Convolution Network for Cross-Scene Multispect...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Mingye Wang Qingwang Wang Tao Shen Jian Song Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming China

Cross-scene multispectral point cloud classification aims to transfer knowledge of labeled source scenes to improve the discriminability of the model on the unlabeled target scenes. From a novel perspective, we argue that the information transfer between the source and target scenes can be used to solve cross-scene multispectral point cloud classification task. Specifically, we propose a Coupled Graph Convolutional Network (Coupled-GCN) to achieve joint alignment of node- and class-level structures within scenes by passing information between different scenes. To reduce the effect of spectral shift between the source and target scenes and seek scene-invariant intrinsic features, we propose a scene adaptive learning module by optimizing three different loss functions, namely, source classifier loss, domain classifier loss, and target classifier loss as a whole. In the cross-scene multispectral point cloud classification task, the proposed Coupled-GCN can alleviate the spectral shift problem compared to the traditional GCN and achieves an overall F_score of 65.04%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：