检索结果-内蒙古大学图书馆

Depth Guided Cross-modal Residual Adaptive Network for RGB-D Salient Object Detection

Journal of Physics: Conference Series 2021年第1期1873卷

作者： Zhengyun Zhao Qingpeng Yang Shangqin Yang Jun Wang School of Artificial Intelligence Henan University Kaifeng Henan 475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng Henan 475004 China

Depth modal features can provide complementary information for salient object detection (SOD). Most of the existing RGB-D SOD methods focus on fully combining RGB and Depth modal features without distinguishing them. In this paper, we propose a new depth guided cross-modal residual adaptive network for RGB-D SOD. We use two independent resnet-50 to extract the features of the two modes respectively. Then the cross-modal channel-wise refinement module is designed to obtain complementary modal information. We design a crossmodal guided module to make complementary modal information guide RGB image feature extraction. Finally, the residual adaptive selection module is used to enhance the spatial mutual concerns between the two modal features to achieve multimodal information fusion. Experimental results show that our method can achieve a more reasonable fusion state of RGB and Depth, and verify the effectiveness of our final saliency model.

关键词：

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

Comparison of Satellite-retrieved NO2 Vertical Column Density with Ground-level NO2 concentration in a provincial scale region

引用

IOP Conference Series: Earth and Environmental Science 2020年第1期615卷

作者： Fengbin Zheng Yu Xia Qiang Ge Kun Cai Henan Engineering Laboratory of Spatial Information Processing Henan University Henan 475004 PR China Henan Key Laboratory of Big Data Analysis and Processing Henan University Henan 475004 PR China School of Computer and Information Engineering Henan University Henan 475004 PR China

Satellite remote sensing will have certain errors in data retrieval accuracy, which requires further ground observation verification. This paper examines and verifies 2019 Jiangsu provincial Ground-level monitoring data and TROPOMI data to evaluate the applicability of TROPOMI tropospheric NO2 Vertical Column Density (VCD) data and compares the results to OMI data analysis verification results. The results show that the correlation coefficient r between the TROPOMI NO2 data and Ground-level monitoring data at the monthly mean scale is as high as 0.9, and consistent seasonal cyclic changes are observed. The correlation between Ground-level monitoring data and OMI NO2 data is lower than TROPOMI (r=0.78 < 0.9). Compared to OMI satellites, the TROPOMI attains a smaller deviation in tropospheric NO2 monitoring. Jiangsu Province had the highest monthly average concentration in January, which were 38.67 ug/m3 (Ground-level), 17.35 × 1015 molec/cm2 (TROPOMI) and 20.04 × 1015 molec/cm2 (OMI). The lowest concentration in August was 13.39 ug/m3 (Ground-level), 5.2 × 1015 molec/cm2 (TROPOMI) and 7.03 × 1015 molec/cm2 (OMI).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-UAVs cooperative task assignment and path planning scheme

引用

Journal of Physics: Conference Series 2021年第1期1856卷

作者： Xiaoyu Du Qicheng Guo Hui Li Yanyu Zhang International Joint Research Laboratory for Cooperative Vehicular Networks of Henan Henan University Kaifeng Henan 475000 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng Henan 475000 China Henan University Minsheng College Kaifeng Henan 475000 China

The task assignment and path planning problems of multiple unmanned aerial vehicles (multi-UAVs) cooperative assistance roadside units (RSUs) for data collection are optimization problems with the goal of minimizing time and energy consumption. This paper proposes a hierarchical optimization scheme for multi-UAVs collaborative assistance RSUs data collection. This solution solves the problems that the number of UAVs needs to be set in advance, the convergence speed is slow when the number of tasks increases, and it is easy to fall into a local optimal solution, and the convergence accuracy is poor. First, the solution uses the K-means algorithm to allocate tasks and group RSUs to find the right number of UAVs to perform the task. Then, this paper proposes a hybrid optimization algorithm based on bionic learning for path planning. Finally, we set up a reasonable evaluation mechanism and conducted simulation experiments. The algorithm in this paper is compared with genetic algorithm, gray wolf algorithm and whale algorithm, the results show that the total cost of the task obtained by the proposed algorithm is the lowest, the algorithm stability is better, and the convergence accuracy is the highest.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning robust and discriminative low-rank representations for face recognition with occlusion

引用

Pattern Recognition 2017年 66卷 129-143页

作者： Guangwei Gao Jian Yang Xiao-Yuan Jing Fumin Shen Wankou Yang Dong Yue Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China Jiangsu Engineering Laboratory of Big Data Analysis and Control for active distribution network Nanjing University of Posts and Telecommunications Nanjing China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University) Fuzhou China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Automation Nanjing University of Posts and Telecommunications Nanjing China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Automation Southeast University Nanjing China

For robust face recognition tasks, we particularly focus on the ubiquitous scenarios where both training and testing images are corrupted due to occlusions. Previous low-rank based methods stacked each error image into a vector and then used L 1 or L 2 norm to measure the error matrix. However, in the stacking step, the structure information of the error image can be lost. Depart from the previous methods, in this paper, we propose a novel method by exploiting the low-rankness of both the data representation and each occlusion-induced error image simultaneously, by which the global structure of data together with the error images can be well captured. In order to learn more discriminative low-rank representations, we formulate our objective such that the learned representations are optimal for classification with the available supervised information and close to an ideal-code regularization term. With strong structure information preserving and discrimination capabilities, the learned robust and discriminative low-rank representation (RDLRR) works very well on face recognition problems, especially with face images corrupted by continuous occlusions. Together with a simple linear classifier, the proposed approach is shown to outperform several other state-of-the-art face recognition methods on databases with a variety of face variations.

关键词： Face recognition Low-rank matrix recovery Nuclear norm

来源：评论

学校读者我要写书评

暂无评论

GrabDAE: An Innovative Framework for Unsupervised Domain Adaptation Utilizing Grab-Mask and Denoise Auto-Encoder

arXiv

引用

arXiv 2024年

作者： Chen, Junzhou Wen, Xuan Zhang, Ronghui Ren, Bingtao Wu, Di Xu, Zhigang Wang, Danwei The Guangdong Provincial Key Laboratory of Intelligent Transport System School of Intelligent Systems Engineering Sun Yat-sen University Guangzhou510275 China The School of Transportation Science and Engineering Beihang University State Key Lab of Intelligent Transportation System Beijing100191 China The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China The Guangdong Key Laboratory of Big Data Analysis and Processing Guangdong510006 China The School of Information Engineering Chang’an University Shaanxi Xi’an710064 China The School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore

Unsupervised Domain Adaptation (UDA) aims to adapt a model trained on a labeled source domain to an unlabeled target domain by addressing the domain shift. Existing Unsupervised Domain Adaptation (UDA) methods often fall short in fully leveraging contextual information from the target domain, leading to suboptimal decision boundary separation during source and target domain alignment. To address this, we introduce GrabDAE, an innovative UDA framework designed to tackle domain shift in visual classification tasks. GrabDAE incorporates two key innovations: the Grab-Mask module, which blurs background information in target domain images, enabling the model to focus on essential, domain-relevant features through contrastive learning;and the Denoising Auto-Encoder (DAE), which enhances feature alignment by reconstructing features and filtering noise, ensuring a more robust adaptation to the target domain. These components empower GrabDAE to effectively handle unlabeled target domain data, significantly improving both classification accuracy and robustness. Extensive experiments on benchmark datasets, including VisDA-2017, OfficeHome, and Office31, demonstrate that GrabDAE consistently surpasses state-of-the-art UDA methods, setting new performance benchmarks. By tackling UDA’s critical challenges with its novel feature masking and denoising approach, GrabDAE offers both significant theoretical and practical advancements in domain adaptation. © 2024, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel cloud game framework in dual Gigabit Network

引用

Journal of Physics: Conference Series 2020年第1期1684卷

作者： Kai Sun Tao Xu Shanghai Urban Construction Vocational College Shanghai 201415 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng 475004 China. School of Computer and Information Engineering Henan University Kaifeng 475004 China.

With the development of 5G, cloud computing, and artificial intelligence (AI) technology, cloud game has become a hotspot about application and innovation of Gigabit bandwidth. This paper, firstly, analyses the present situation and development of cloud game to clarify the key business and key technology of cloud game, then, proposes an operational framework of cloud game, finally, the feasibility of the proposed framework is discussed and several suggestions about the operation of cloud game are given.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Convolutional Neural Networks Architecture Using a Modified Particle Swarm Optimization for Image Classification

SSRN

引用

SSRN 2022年

作者： Elhani, Djenaihi Megherbi, Ahmed Chaouki Zitouni, Athmane Dornaika, Fadi Sbaa, Salim Taleb-Ahmed, Abdelmalik Laboratory of LESIA University of Biskra Algeria Department of Electrical Engineering University of Biskra BP 145 RP Biskra07000 Algeria Laboratory of LI3C University of Biskra Algeria Department of Electrical Engineering University of Biskra BP 145 RP Biskra07000 Algeria Henan University Henan Key Laboratory of Big Data Analysis and Processing Kaifeng China University of the Basque Country UPV/EHU Manuel Lardizabal 1 San Sebastian20018 Spain IKERBASQUE Basque Foundation for Science Bilboa Spain Univ. Polytechnique Hauts-de-France Univ. Lille CNRS Centrale Lille UMR CNRS 8520 ValenciennesF-59313 France

Although the Convolutional Neural Network (CNN) has been shown to be effective in solving image classification tasks, its architecture is often difficult to design (i.e., much tuning is required for optimization) due to the large number of hyperparameters that require careful human intervention to determine their optimal values. In this paper, we propose an approach to create the best CNN design and reduce human intervention during this process. The approach uses an optimization algorithm derived from the particle swarm without velocity (PSWV) equation to significantly reduce the number of iterations to determine the optimal CNN hyperparameters and architecture for a given dataset. A novel strategy for updating a particle swarm without velocity using particle swarm optimization (PSO) with CNNs was developed. In this approach, we adopted the variable-length coding strategy to represent the particles in the population. We proposed an algorithm for a suitable process that allows fast convergence to the best architecture. The proposed algorithm was studied and compared with several recent algorithms in the literature. Experiments on eight benchmark datasets for classification tasks have demonstrated the efficiency and practicality of our approach in finding the best CNN architecture with less human intervention. © 2022, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Prediction model of physical activity level and hypertension based on artificial neural network

引用

Journal of Physics: Conference Series 2021年第1期1848卷

作者： Liang Hua Wang Yu Li Jinying Zhang Wanjun Wang Yiting school of Physical Education Henan University Kaifeng Henan 475001 China Department of Health Management People's Hospital of Henan Province People's Hospital of Henan University People's Hospital of Zhengzhou University Zhengzhou 450003 China Key Laboratory of Big Data Analysis and Processing of Henan province Henan University Kaifeng 475004 PR China school of Foreign Language Henan University Kaifeng Henan 475001 China

Purpose: Taking the population of henan provincial People's Hospital Chronic Disease Control Center from July 1, 2020 to December 31, 2020 who came to the hospital for physical examination as the research object, analyze and explore the role and contribution of physical activity level in the prediction of hypertension by using the LSTM network model, which can provide references for the clinical diagnosis of hypertension. Methods: Randomly select 2000 physical examination data, remove missing and invalid data, and preprocess them. Finally, select factors such as gender, age, body mass index, weight grade, waist-to-hip ratio, physical activity level, body fat percentage and other factors to establish a neural network prediction model. Then test and study the model, focusing on exploring the contribution of physical activity level to prediction. Result: The level of physical activity has certain advantages in predicting the prevalence of hypertension, but the predictive ability in the later stage is insufficient

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiple residual dense networks for reconfigurable intelligent surfaces cascaded channel estimation

arXiv

引用

arXiv 2021年

作者： Jin, Yu Zhang, Jiayi Huang, Chongwen Yang, Liang Xiao, Huahua Ai, Bo Wang, Zhiqin The School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China The Frontiers Science Center for Smart High-speed Railway System Beijing Jiaotong University Beijing100044 China Zhejiang Provincial Key Lab of Information Processing Communication and Networking Zhejiang University Hangzhou310007 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China ZTE Corporation State Key Laboratory of Mobile Network Mobile Multimedia Technology Shenzhen518057 China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China Henan Joint International Research Laboratory of Intelligent Networking and Data Analysis Zhengzhou University Zhengzhou450001 China Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen518055 China China Academy of Information and Communications Technology Beijing100191 China

Reconfigurable intelligent surface (RIS) constitutes an essential and promising paradigm that relies programmable wireless environment and provides capability for space-intensive communications, due to the use of low-cost massive reflecting elements over the entire surfaces of man-made structures. However, accurate channel estimation is a fundamental technical prerequisite to achieve the huge performance gains from RIS. By leveraging the low rank structure of RIS channels, three practical residual neural networks, named convolutional blind denoising network, convolutional denoising generative adversarial networks and multiple residual dense network, are proposed to obtain accurate channel state information, which can reflect the impact of different methods on the estimation performance. Simulation results reveal the evolution direction of these three methods and reveal their superior performance compared with existing benchmark schemes. Copyright © 2021, The Authors. All rights reserved.

关键词： Channel estimation

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：