检索结果-内蒙古大学图书馆

International Conference on Computing, Networking and Communications (ICNC)

作者： Xiaowei Nie Demin Wang Yuqing Zhang Xiaoduo Pan Zhibin Zuo National Tibetan Plateau Data Center (TPDC) State Key Laboratory of Tibetan Plateau Earth System Environment and Resources (TPESER) Institute of Tibetan Plateau Research Chinese Academy of Sciences Beijing China Science Center of Lingshan Forum of Guangdong Province Guangzhou China School of Ecology and Environment Tibet University Lhasa China College of Information Science and Engineering Henan University of Technology Zhengzhou China Henan International Joint Laboratory of Grain Information Processing Zhengzhou China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350370997

ISBN: (纸本)9798350371000

This study introduces a Deep Reinforcement Learning-based Contention Window Avoidance Scheme aimed at improving service priority differentiation and network throughput under high load conditions within wireless networks that utilize the Network Distributed Coordination Function (DCF) mechanism. This novel approach involves two key strategies: firstly, it enables the differentiation of service priorities within DCF-based channel access by categorizing them in accordance with the varying data types and streams transmitted by different stations; secondly, it leverages Deep Reinforcement Learning to dynamically evaluate the network state through analysis of collision probabilities derived from channel observations. By doing so, the scheme dynamically modulates the ranges of contention windows in alignment with the service priorities, responding to the immediate network circumstances. Empirical evidence indicates that the proposed scheme substantially mitigates collision frequencies and augments data transmission throughput, thus significantly advancing the overall performance of networks that require service priority differentiation.

关键词： Frequency modulation Wireless networks Throughput Deep reinforcement learning data communication Streams Optimization

来源：评论

学校读者我要写书评

暂无评论

Quantized Tensor Neural Network

引用

ACM/IMS Transactions on data Science 2021年第4期2卷 1–18页

作者： Gao, Yuan Yang, Laurence T. Zheng, Dehua Yang, Jing Zhao, Yaliang School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Technology Huazhong University of Science and Technology and Department of Computer Science St. Francis Xavier University AntigonishNSB2G2W5 Canada Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Henan University and with Department of Computer Science St. Francis Xavier University Antigonish Canada

Tensor network as an effective computing framework for efficient processing and analysis of high-dimensional data has been successfully applied in many fields. However, the performance of traditional tensor networks still cannot match the strong fitting ability of neural networks, so some data processing algorithms based on tensor networks cannot achieve the same excellent performance as deep learning models. To further improve the learning ability of tensor network, we propose a quantized tensor neural network in this article (QTNN), which integrates the advantages of neural networks and tensor networks, namely, the powerful learning ability of neural networks and the simplicity of tensor networks. The QTNN model can be further regarded as a generalized multilayer nonlinear tensor network, which can efficiently extract low-dimensional features of the data while maintaining the original structure information. In addition, to more effectively represent the local information of data, we introduce multiple convolution layers in QTNN to extract the local features. We also develop a high-order back-propagation algorithm for training the parameters of QTNN. We conducted classification experiments on multiple representative datasets to further evaluate the performance of proposed models, and the experimental results show that QTNN is simpler and more efficient while compared to the classic deep learning models. © 2022 Association for Computing Machinery.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

HMFT: Hyperspectral and Multispectral Image Fusion Super-Resolution Method Based on Efficient Transformer and Spatial-Spectral Attention Mechanism

引用

Computational intelligence and neuroscience 2023年第1期2023卷 4725986页

作者： Baojun Qiao Binghui Xu Yi Xie Yinghao Lin Yang Liu Xianyu Zuo Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Henan University Kaifeng 475000 China. Henan Engineering Laboratory of Spatial Information Processing Henan University Kaifeng 475000 China.

Due to the imaging mechanism of hyperspectral images, the spatial resolution of the resulting images is low. An effective method to solve this problem is to fuse the low-resolution hyperspectral image (LR-HSI) with the high-resolution multispectral image (HR-MSI) to generate the high-resolution hyperspectral image (HR-HSI). Currently, the state-of-the-art fusion approach is based on convolutional neural networks (CNN), and few have attempted to use Transformer, which shows impressive performance on advanced vision tasks. In this paper, a simple and efficient hybrid architecture network based on Transformer is proposed to solve the hyperspectral image fusion super-resolution problem. We use the clever combination of convolution and Transformer as the backbone network to fully extract spatial-spectral information by taking advantage of the local and global concerns of both. In order to pay more attention to the information features such as high-frequency information conducive to HR-HSI reconstruction and explore the correlation between spectra, the convolutional attention mechanism is used to further refine the extracted features in spatial and spectral dimensions, respectively. In addition, considering that the resolution of HSI is usually large, we use the feature split module (FSM) to replace the self-attention computation method of the native Transformer to reduce the computational complexity and storage scale of the model and greatly improve the efficiency of model training. Many experiments show that the proposed network architecture achieves the best qualitative and quantitative performance compared with the latest HSI super-resolution methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Weather radar echo prediction method based on recurrent convolutional neural network

Weather radar echo prediction method based on recurrent conv...

引用

IEEE International Conference on Big data

作者： Xiajiong Shen Kunying Meng Daojun Han Kai Zhai Lei Zhang Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China Henan Air Traffic Management Branch Civil Aviation of China Zhengzhou China

ISBN: (纸本)9781665445993

The emergence of strong convective weather has caused serious threats to people’s lives and production activities, and also caused serious damage to the ecological environment. Because this kind of weather has a short duration and a small impact area, it is difficult to be accurate predicted. Doppler weather radar is one of the devices that can sample strong convective weather continuously for a long time, and plays an extremely important role in the detection and prediction of severe weather. The prediction of radar echo intensity by using deep learning methods has largely improved the prediction accuracy of strong convective weather, but the prediction of radar echo shape change is not yet ideal, so the trend of strong convective weather cannot be accurately judged. This paper proposes a weather radar echo prediction method based on cyclic convolutional neural network, which is called the EDD model, its design was inspired by the RU_Net families of deep learning models. The feature fusion layer was added to the neural network, thus ensuring that the feature matrix contains more feature parameters and improving the problem of inaccurate prediction of radar echo shape change due to insufficient information during upsampling. The EDD model is trained using Doppler weather radar echo maps, and the experimental results show that the EDD model used in this paper can improve the prediction accuracy of radar echo intensity and make good predictions of radar echo shape changes, thus helping meteorologists to make more accurate judgments on the occurrence, development and change trends of strong convective weather.

关键词： Deep learning Meteorological radar Shape Biological system modeling Neural networks Predictive models Radar imaging

来源：评论

学校读者我要写书评

暂无评论

Influence of Elevation and Orbit Interpolation on the Accuracy of R-D Location Model 6

Influence of Elevation and Orbit Interpolation on the Accura...

引用

6th Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2019

作者： Fan, Minghu Zuo, Xianyu Tian, Junfeng Key Laboratory of Big Data Analysis and Processing of Henan Province College of Computer Science and Information Engineering Henan University Kaifeng China

ISBN: (纸本)9781728129129

R-D model is the most commonly location model in geometric processing of SAR images. How to improve its location accuracy has been one of the focuses in application. Based on the in-depth analysis of the solving process of R-D equation, two kinds of influencing factors are selected to study. They are elevation and satellite orbit interpolation method. Then, aiming at the pixel location of high-resolution spaceborne SAR images, three kinds of DEM and two orbit interpolation algorithms were studied. The experimental results show that these two kinds of factors mainly affect the location accuracy of range direction, both the horizontal and vertical resolution of elevation have great influence on location accuracy, the quartic polynomial orbit interpolation can meet requirements of high accuracy location, and further improvement of the location accuracy need other auxiliary means. © 2019 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Parallel Geometric Correction for Single Spaceborne SAR Image 6

Parallel Geometric Correction for Single Spaceborne SAR Imag...

引用

6th Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2019

ISBN: (纸本)9781728129129

The fast processing of SAR images is of great significance for SAR applications, and parallel computing is the most common solution. The paper studied the parallel computing algorithm for the geometric correction of single spaceborne SAR image, which is based on a classical serial geometric correction algorithm. After fully analyzing the parallel features of the algorithm, a CPU-oriented and a GPU-oriented global parallel correction algorithm were designed. Then, two spaceborne SAR images were used to test the speedup performance of the two algorithms. The experimental results show that the two parallel algorithms can greatly improve the speed of the geometric correction of spaceborne SAR image, and the performance of CPU-oriented parallel algorithm is mainly related to the number of CPU/cores, while the performance of GPU-oriented parallel algorithm is mainly related to the data granularity, and the latter has very high speedup ratio and is an efficient method for geometric correction of spaceborne SAR image. © 2019 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Irregular Convolution U-Net for Reconstructing Ancient Channel of the Yellow River

An Adaptive Irregular Convolution U-Net for Reconstructing A...

引用

IEEE SENSORS

作者： Zhishun Guo Jianhui Zhao Ning Li Lin Wu College of Computer and Information Engineering Henan University Kaifeng China Henan. Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng China

The lower reaches of the ancient Yellow River (AYR) migrated very frequently, like a loong swinging its tail on the land of China. This paper, based on Gaofen-3 full-polarization synthetic aperture radar (SAR) data, analyzed scattering characteristics of archaeolandscapes, which provided reliable evidences for the existence of AYR between Lankao and Sui County. Then, an adaptive irregular convolution kernel U-Net (AICK-U-Net) was proposed to reconstruct the part of channel of AYR, based on the image obtained by polarization decomposition, and the precision reached 96.21%. In summary, polarization decomposition and neural network in spaceborne SAR field, provided new insights for detecting and reconstructing archaeolandscapes.

关键词： Convolution Spaceborne radar Neural networks Scattering Sensors Rivers Reliability

来源：评论

学校读者我要写书评

暂无评论

A new classification method of SAR image based on OGMRF-RC model 5

A new classification method of SAR image based on OGMRF-RC m...

引用

IET International Radar Conference 2020, IET IRC 2020

作者： Li, Yuan Guo, Zhishun Wu, Lin Guo, Zhengwei College of Computer and Information Engineering Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng475000 China College of Environment and Planning Henan University Kaifeng475004 China

ISBN: (纸本)9781839535635

Synthetic Aperture Radar (SAR) image classification is a key technique and research focus in the application of remote sensing. This paper proposes a new classification method of SAR image based on Object-based Gaussian-Markov Random Field model with Region Coefficients (OGMRF-RC), the new method use Fuzzy Probability (FP) represents the region's category probability, FP is obtained by regional posterior probability and edge information of neighborhood. Use FP to replace the unique class label of the region, which avoids the parameters estimation inaccurate of the feature field caused by the unique initial class label. And the parameter calculation method of feature field takes into account the feature information of all regions in the image. In this paper, we take the area around Baliwan in Kaifeng as study area, Sentinel-1 is used as the remote sensing data sources. FCM, K-means, classic MRF and OGMRF-RC are used as contrast methods, the experimental result demonstrates the accuracy of our method is better than these methods. © 2020 Institution of Engineering and Technology. All rights reserved.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Surface soil moisture inversion based on DEFS-GA-BP model using Sentinel-1/2 remote sensing data 5

Surface soil moisture inversion based on DEFS-GA-BP model us...

引用

IET International Radar Conference 2020, IET IRC 2020

作者： Zhang, Chenyang Min, Lin Zhao, Jianhui College of Computer and Information Engineering Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng475004 China Network Information Center Office Henan University Kaifeng475004 China

ISBN: (纸本)9781839535635

The major work is to retrieve the surface soil moisture under crop cover in this paper. This paper proposes an improved GA-BP model called as DEFS-GA-BP model. This model is proposed to retrieve the surface soil moisture distribution using Sentinel-1 and Sentinel-2 remote sensing data. After extracting nine polarization features and one roughness parameter from Sentinel-1 data, five vegetation indexes from Sentinel-2 data. The differential evolution feature selection (DEFS) algorithm is applied to select the optimal feature subset. By using the genetic algorithm (GA) to optimize the node weights, the back propagation (BP) neural network is trained using the optimal feature subset and then used to generate the surface soil moisture distribution. The results of inversion algorithm indicate that the proposed DEFS-GA-BP model has a better inversion precision than GA-BP model, and demonstrates its application potential in surface soil moisture inversion. © 2020 Institution of Engineering and Technology. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Evolution analysis of NO 2 Column Density before and after COVID-19 Pandemic in henan province Based on SI-APSTE Model

Research Square

引用

Research Square 2021年

作者： Liu, Yang Zhao, Jinhuan Song, Kunlin Cheng, Cheng Li, Shenshen Cai, Kun Henan Engineering Laboratory of Spatial Information Processing Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Henan University Kaifeng475004 China State Key Laboratory of Remote Sensing Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100101 China School of Information and Electronics Beijing Institute of Technology Beijing100081 China

Air pollution is the result of comprehensive evolution of a dynamic and complex system composed of emission sources, topography, meteorology and other environmental factors. The establishment of spatiotemporal evolution model is of great significance for the study of air pollution mechanism, trend prediction, identification of pollution sources and pollution control. In this paper, the air pollution system is described based on cellular automata and restricted agents, and a Swarm Intelligence based Air Pollution SpatioTemporal Evolution (SI-APSTE) model is constructed. Then the spatiotemporal evolution analysis method of air pollution is studied. Taking henan province before and after COVID-19 pandemic as an example, the NO2 products of TROPOMI and OMI were analysed based on SI-APSTE model. The tropospheric NO2 Vertical Column Densities (VCDs) distribution characteristics of spatiotemporal variation of henan province before COVID-19 pandemic were studied. Then the tropospheric NO2 VCDs of TROPOMI was used to study the pandemic period, month-on-month and year-on-year in 18 urban areas of henan province. The results show that SI-APSTE model can effectively analyse the spatiotemporal evolution of air pollution by using environmental big data and swarm intelligence, and also can establish a theoretical basis for pollution source identification and trend prediction. © 2021, CC BY.

关键词： Air pollution

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：