检索结果-内蒙古大学图书馆

2021 CIE International Conference on radar, radar 2021

作者： Zhixin, Wu Mengdao, Xing Yuexin, Gao Xidian University National Laboratory of Radar Signal Processing Xi'an China School of Aerospace Science and Technology Xidian University Xi'an China

ISBN: (纸本)9781665498142

Microwave photonics radar generates signals with large bandwidth and cross-spectrum. It has the capability of ultra-high resolution of Inverse Synthetic Aperture radar(ISAR) image and more electromagnetic information. The large-bandwidth signal simulated by the scattering point model cannot accurately characterize the electromagnetic scattering of a target, and the imaging results are not realistic enough according to the acquired images. This paper proposes a method for electromagnetic scattering calculation based on the Local Coordinate Improved Moller (LCIM) algorithm to solve this problem. Our algorithm adaptively processes the facets in the local coordinate, which makes the redundant tube eliminated. And the LCIM algorithm simplifies the solution formula so that the intersection can be calculated in parallel through the matrix. Because of the difference between the acquired images and the simulation results of the simplified model, the normal vector adjustment factor (NVAF) is introduced to make the imaging results of the fully polarized backscatter more realistic. The results of the satellite model with the condition of the large band and wide-angle demonstrate the feasibility of our method. © 2021 IEEE.

关键词： electromagnetic scat tering calculation Microwave photonics radar Normal vector adjustment factor (NVAF) Shooting and bouncing rays (SBR) technique

来源：评论

学校读者我要写书评

暂无评论

Deep Graph Learning on Bipartite Observed Networks 2

Deep Graph Learning on Bipartite Observed Networks

引用

2nd Asia-Pacific Conference on Communications technology and Computer science, ACCTCS 2022

作者： Wei, Qiang School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (纸本)9781665400343

In real-world settings, network structure observations are often incomplete due to the difficulties of data collection. However, most existing network analysis methods assume that the whole underlying structure is observed. In this paper, we focus on a common but overlooked network observation, named bipartite observation. We systematically study the influence of bipartite observations, and give an analytical representation using the stochastic block model. Moreover, we propose a new framework LP-GNN, which combines link prediction, sparsification, and graph neural networks for node classification tasks in bipartite observations. The effectiveness of LP-GNN is illustrated by experimental results on real datasets. © 2022 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Feature-fusion-based Detection of Sea-surface Small Targets in Logarithmic Domain 10

Feature-fusion-based Detection of Sea-surface Small Targets ...

引用

10th International Conference on Information Systems and Computing technology, ISCTech 2022

作者： Guo, Zixun Bai, Xiaohui Shui, Penglang Wang, Ling Su, Jia Shi, Sainan School of Electronics and Information Northwestern Polytechnical University Xi'an China Xidian University National Laboratory of Radar Signal Processing Xi'an China School of Electronic and Information Engineering Nanjing University of Information Science & Technology Nanjing China

ISBN: (纸本)9798350332933

Sea-surface and low altitude small target detection in complicated sea clutter background is still a challenging but important work, owing to weak returns of targets, diversity of small targets, and complicated interactions between targets and sea waves. Existing feature-based detectors using more than three features has high computation cost, however using more features can increase the detection ability indeed. In this paper, through a proposed feature fusion method, seven known features are fused to a novel test statistic to design an easy but significant feature-fusion-based detector (FFD). The proposed FFD is to learn a set of fused weights to maximize the between-class distance of sea clutter and target returns in the seven dimensional space built by features. Through the experimental results on the two measured and known radar databases, the proposed detector gets comparable performance and lower computation cost, comparing with other feature-based detectors in three dimensional space built by features. © 2022 IEEE.

关键词： Clutter (information theory)

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous-attributes enhancement deep framework for network embedding

引用

Frontiers of Computer science 2021年第6期15卷 121-131页

作者： Lisheng QIAO Fan ZHANG Xiaohui HUANG Kai LI Enhong CHEN Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of ChinaHefei 230022China National Key Laboratory of Blind Signal Processing Chengdu 610041China School of Computer Science and Technology University of Science and Technology of ChinaHefei 230022China

Network embedding,which targets at learning the vector representation of vertices,has become a crucial issue in network ***,considering the complex structures and heterogeneous attributes in real-world networks,existing methods may fail to handle the inconsistencies between the structure topology and attribute ***,more comprehensive techniques are urgently required to capture the highly non-linear network structure and solve the existing inconsistencies with retaining more *** that end,in this paper,we propose a heterogeneous-attributes enhancement deep framework(HEDF),which could better capture the non-linear structure and associated information in a deep learningway,and effectively combine the structure information of multi-views by the combining *** this line,the inconsistencies will be handled to some extent and more structure information will be preserved through a semi-supervised *** extensive validations on several real-world datasets show that our model could outperform the baselines,especially for the sparse and inconsistent situation with less training data.

关键词： network embedding heterogeneous-attributes deep framework inconsistent

来源：评论

学校读者我要写书评

暂无评论

Unified Localization Method Without Prior Range Information of Moving Target

Unified Localization Method Without Prior Range Information ...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Weishuang Gong Qi Wang Yachao Li Xidian University Hangzhou Institute of Technology Xidian University Hangzhou China National Key Laboratory of Radar Signal Processing Xidian University Xi’an China

ISBN: (数字)9798350355581

ISBN: (纸本)9798350355598

This paper proposes a unified localization method based on the time difference of arrival (TDOA) and the frequency difference of arrival (FDOA), which can estimate the position and velocity of the target when it is in the near-field, or the direction of the target when it is in the far-field. We use the modified polar representation (MPR) to unify the far-field and near-field models to construct an optimal localization problem with two constraints and propose an algebraic solution. The method first uses the least squares method to find the initial value without considering the constraints. Then the constraints are used to build an optimization equation to reduce the error of the initial value and obtain the precise value. Simulation results show that the proposed algorithm is close to the Cramer-Rao lower bound (CRLB), verifying the performance.

关键词： Location awareness Time-frequency analysis Time difference of arrival Simulation Computational electromagnetics Mathematical models Frequency estimation Optimization Least mean squares methods

来源：评论

学校读者我要写书评

暂无评论

Registration Error-resistant Track-to-track Association for Multiple Sensors

Registration Error-resistant Track-to-track Association for ...

引用

signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Shuyang Zhang Chang Gao Qingfu Zhang Junkun Yan Tianyi Jia Rongrong Wang Hongwei Liu National Key Laboratory of Radar Signal Processing Xidian University Xi’an China Department of Computer Science City University of Hong Kong Hong Kong

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

The process of Multi-sensor Track-to-Track Association (MTTA) involves the association of tracks observed by multiple sensors, which are of the same target. This process serves as a foundation for enhancing track continuity and refining state estimation via the fusion of multi-sensor information. Predominantly, the existing methods employ statistical modeling of target motion to devise association gates between tracks. However, these methods encounter a decrease in association accuracy when faced with unknown registration errors. To address this challenge, a data-driven approach is proposed, which reconfigures track association into a classification problem. This approach harnesses target kinematic characteristics and track trajectory features extracted at the track level. Subsequently, these features are employed in constructing a track association algorithm based on decision trees. Experiments are conducted on a publicly available dataset, Multi-source Track Association Dataset (MTAD) derived from real data. The results have demonstrated superior association performance, particularly under conditions of inadequate system registration.

关键词： Target tracking Refining Kinematics Sensor phenomena and characterization Logic gates Feature extraction Classification algorithms Trajectory Decision trees State estimation

来源：评论

学校读者我要写书评

暂无评论

MSCA-UNet: Multi-Scale Channel Adaptive Sensing Module for Medical Image Segmentation

MSCA-UNet: Multi-Scale Channel Adaptive Sensing Module for M...

引用

2024 International Conference on New Trends in Computational Intelligence, NTCI 2024

作者： Diao, Liangjin Shen, Longfeng Chen, Jiacong Ge, Fangzhen Li, Mengwen College of Computer Science and Technology Huaibei Normal University Anhui Huaibei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Anhui University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui Hefei China

ISBN: (纸本)9798331517021

Recent advancements in CNNs for medical image segmentation have focused on the combination of CNN and Transformer architectures to capture both local and global features. However, challenges remain, such as effectively utilizing fused features at the encoder-decoder bottleneck and addressing blurred object edges in datasets. To tackle these issues, we introduce a multi-scale channel adaptive sensing module, enhancing the model's representational and perceptual capabilities by integrating multi-scale and channel-specific information. Additionally, we propose a cross-perception module and multi-scale segmentation head to improve global coordination and multi-scale information gathering. Experiments on the ACDC and Synapse datasets demonstrate our model's superiority. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Robust Equalizer for Joint Extended Preprocessing in Impulsive Noise

Robust Equalizer for Joint Extended Preprocessing in Impulsi...

引用

2024 OES China Ocean Acoustics, COA 2024

作者： Tian, Yanan Han, Xiao Yin, Jingwei Zhang, Yangfan Pu, Zhanqing Huang, Haining Institute of Acoustics Chinese Academy of Science Kay Laboratory of Science and Technology on Advanced Underwater Acoustic Signal Processing Beijing100190 China College of Underwater Acoustic Engineering Harbin Engineering University National Key Laboratory of Underwater Acoustic Technology Harbin150001 China Harbin Engineering University Key Laboratory for Polar Acoustics and Application of Ministry of Education Harbin150001 China

ISBN: (纸本)9798350340297

An important strategy for signal processing in impulsive noise environment is to first suppress the high amplitude mutations by a preprocessor and then use the signal processing method under Gaussian noise. This paper proposes an equalizer for joint impulsive noise extended preprocessing, which performs a nonlinear transform of received signals disturbed by impulsive noise, retaining more useful information while remaining robust. Combined with the sparse characteristics of the equalizer, the improved proportional stable fast transversal filter is then exploited to improve the convergence speed and reduce the equalization error. The results of underwater acoustic communication test in the Yellow Sea verify the superiority of the proposed method. © 2024 IEEE.

关键词： Transversal filters

来源：评论

学校读者我要写书评

暂无评论

SAR Target Recognition Using Simulated Data by an Ensemble Multi-scale Deep Domain Adaptation Recognition Framework

SAR Target Recognition Using Simulated Data by an Ensemble M...

引用

2021 CIE International Conference on radar, radar 2021

作者： Sun, Yuanshuang Wang, Yinghua Hu, Liping Liu, Hongwei Xidian University National Laboratory of Radar Signal Processing Xi'an China Beijing Institute of Environmental Features Science and Technology on Electromagnetic Scattering Laboratory Beijing China

ISBN: (纸本)9781665498142

Obtaining lots of synthetic aperture radar (SAR) data for automatic target recognition (ATR) can be unrealistic in many situations. Relatively speaking, electromagnetic simulated SAR data is easier to acquire. However, there is an apparent distribution gap between the electromagnetic simulated data and the real data. It is not suitable to use the simulated data for recognition directly, and thus the way to apply the simulated SAR data for recognition is worth considering. In this paper, we focus on a challenging recognition problem of training solely on simulated data and testing on real data. Firstly, a multi-scale feature extraction module is used for robust feature extraction, which aims to make the extracted feature more generalized for both simulated data and real data. Secondly, the idea of domain adaptation is considered to learn a representation trained to jointly optimize for classification and domain invariance. Thirdly, an ensembling technique is applied, and an ensemble multi-scale deep domain adaptation recognition framework is proposed. The Moving and Stationary Target Acquisition and Recognition (MSTAR) benchmark data set and an electromagnetic simulated SAR data set are used for verification, and experimental results illustrate the effectiveness of our methods. © 2021 IEEE.

关键词： deep learning domain adaptation SAR target recognition simulated data Synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Fast Sampling Based on Policy Gradient for Diffusion-Based Speech Enhancement

Fast Sampling Based on Policy Gradient for Diffusion-Based S...

引用

International Symposium on Chinese Spoken Language processing

作者： Yubo Jiang Zhihua Huang School of Computer Science and Technology Xinjiang University Xinjiang Key Laboratory of Signal Detection and Processing Urumqi

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

The effectiveness of diffusion-based generative models in speech enhancement tasks has been reported. These generative methods can produce high-quality audio with less distortions and outperform their discriminative counterparts, especially in mismatched conditions. However, due to the multi-step denoising property, these models usually have slower audio generation speed and a tendency to accumulate errors in the enhancement process. To address these issues, we propose a novel approach that considers the reverse process as a sequential decision-making task and constructs the distribution similarity metric into the training objective. In this way, the generator can learn data distributions well and explore more efficient sampling trajectories. The results of our experiments indicate that our proposed method not only reduces the number of steps required for audio generation, but it also produces even higher quality samples and preserves the generalizability to unknown noise.

关键词： Training Measurement Noise reduction Noise Reinforcement learning Speech enhancement Probabilistic logic Distortion Generators Trajectory

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：