检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Li, Huanhuan Luo, Haifeng Huang, Tianqiang Ding, Xuemei Huang, Liqing College of Computer and Cyber Security Fujian Normal University China Digital Fujian Big Data Security Technology Institute China Fujian Provincial Engineering Research Center for Public Service Big Data Mining and Application China

Graph representation learning(GRL) aims to extract valid graph information to generate informative representations for handling various tasks on graphs. Supervised graph representation learning (SGRL) has achieved remarkable success recently. However, when labels are missing, or task-free representations are expected, self-supervised graph representation learning (SSGRL) is a promising paradigm. Graph auto-encoders (GAEs) are one of the prevalent frameworks in SSGRL. There are two issues that hinder the effectiveness of existing GAEs: a) There is no appropriate strategy to fuse attributive and structural information in the reconstruction target;b) The decoder cannot fully retain valid information for classification tasks. In this work, we propose a self-supervised graph auto-encoders via proximity matrix reconstruction (PMGAE) to address the above issues. For the proper information fusion, a proximity matrix is designed as the reconstruction target. Then, we design a cosine decoder to enhance the decoder's ability to retain information. Moreover, to adapt PMGAE to the large-scale graph, a random sub-matrix reconstruction mechanism is introduced to reduce memory consumption and running time in the decoding stage. In the experiment, we used seven benchmarks to verify the effectiveness of PMGAE. The results show that the proposed PMGAE is significantly improved compared to the state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A U-Shaped Multi-Scale Network for Defocus Blur Detection

A U-Shaped Multi-Scale Network for Defocus Blur Detection

引用

International Congress on Image and Signal Processing, BioMedical engineering and Informatics (CISP-BMEI)

作者： Longrui Li Liqing Huang College of Computer and Cyber Security Fujian Normal University Fuzhou Digital Fujian Institute of Big Data Security Technology Fuzhou Fujian Provincial Engineering Research Center of Big Data Analysis and Application Fuzhou China

ISBN: (数字)9798331507398

ISBN: (纸本)9798331507404

Defocus blur detection (DBD) aims at accurately extract the in-focus sharp regions in natural images. Despite significant progress, the presence of uniform regions and gradient boundaries remain two of the most challenging problems. In this paper, we use a U-shaped multi-scale image input network for image DBD. The model is a U-shaped encoder-decoder structured network that incorporates inputs from multi-scale images to simultaneously extract features from images of different scales, and a feature fusion module (FFM) of the corresponding scales in the encoder part in order to better learn the features of these different scales. Experiments on two public datasets demonstrate the superior performance of the method in this paper in dealing with defocus blur detection.

关键词： Measurement Visualization Convolution Fuses Computational modeling Feature extraction Robustness Encoding Decoding Informatics

来源：评论

学校读者我要写书评

暂无评论

Differential Privacy Information Publishing Algorithm based on Cluster Anonymity

Differential Privacy Information Publishing Algorithm based ...

引用

2020 International Conference on Big data, Artificial Intelligence and Internet of Things engineering, ICBAIE 2020

作者： Lin, Guobin Zhao, Huijun Zhao, Leyang Gan, Xinli Yao, Zhiqiang Spatial Data Mining and Application Fujian University Engineering Research Center Yango University Fu Zhou350015 China Fujian Engineering Research Center of Public Service Big Data Mining and Application Fuzhou350108 China

ISBN: (纸本)9781728164991

With the development of Internet technology, the attacker gets more and more complex background knowledge, which makes the anonymous model susceptible to background attack. Although the differential privacy model can resist the background attack, it reduces the versatility of the data. In this paper, this paper proposes a differential privacy information publishing algorithm based on clustering anonymity. The algorithm uses the cluster anonymous algorithm based on KD tree to cluster the original data sets and gets anonymous tables by anonymous operation. Finally, the algorithm adds noise to the anonymous table to satisfy the definition of differential privacy. The algorithm is compared with the DCMDP (Density-Based Clustering Mechanism with Differential Privacy, DCMDP) algorithm under different privacy budgets. The experiments show that as the privacy budget increases, the algorithm reduces the information loss by about 80% of the published data. © 2020 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Coordinate Attention Based 3D-CNN Using Ghost Multi-Scale for Diagnosing Alzheimer’s Disease

Coordinate Attention Based 3D-CNN Using Ghost Multi-Scale fo...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiaolu Lin Pinya Lu Jie Pan Hongqin Yang Xuemei Ding Fujian Provincial Engineering Research Center for Public Service Big Data Mining and Application Fujian Provincial University Engineering Research Center for Big Data Analysis and Application Fujian Normal University Fuzhou China Xiamen Jingyi Zhikang Technology Co. Ltd Xiamen China Fujian Provincial Key Laboratory for Photonics Technology Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education Fujian Normal University Fuzhou China School of Computing Engineering and Intelligent Systems Ulster University Derry-Londonderry NI UK

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Alzheimer's disease (AD) is a neurodegenerative disease and mild cognitive impairment (MCI) is the early stage of AD. Previous studies have predominantly focused on binary classification using 3 dimensional - convolutional neural network (3D-CNN) for AD diagnosis, with limited progress in multi-classification. Moreover, the current 3D-CNNs often adopt a single-scale architecture with massive parameters growth. Additionally, obtaining precise location information of brain imaging data is crucial for improving the classification accuracy with 3D-CNN. Hence, we propose a multi-scale 3D-CNN based on coordinate attention mechanism to marvelously capture and integrate 3D features with fewer parameters, improving the accuracy of AD diagnosis. A total of 447 cognitively normal (CN), 512 MCI, and 358 AD sMRI images from the Alzheimer's Disease Neuroimaging Initiative datasets are used for multi-class classification task, yielding a classification accuracy of 92.8%. The model merely involves 2.41 M parameters and achieves the best classification results with the least number of parameters when compared to other representative CNN architectures including ResNet 18, ResNet 34, ConvNeXt tiny, and VGG 11. Through the ablation experiment, the addition of attention mechanism and the multi-scale classification enhances the classification performance by 4.5% and 1.5%, respectively. Furthermore, our model outperforms the other six existing studies in terms of accuracy for classifying AD vs. MCI vs. CN. Overall, this study underscores the efficacy of our approach for AD diagnosis, showcasing its utility in diagnosing AD patients and providing novel insights for diagnosing other neurological disorder diseases.

关键词： Neuroimaging Accuracy Attention mechanisms Three-dimensional displays Resonance Convolutional neural networks Alzheimer's disease

来源：评论

学校读者我要写书评

暂无评论

Icon-to-Icon Translation using Pixel-Level Weight Adversarial Networks

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第1期7卷 147-160页

作者： Pan, Yao-Ming Lin, Kai-Biao Chen, Chin-Ling School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Engineering Research Center of Big Data Application in Private Health Medicine Fujian Provincial University Putian351100 China School of Information Engineering Changchun Sci-Tech University Changchun130600 China Department of Computer Science and Information Engineering Chaoyang University of Technology Taichung41349 Taiwan

We investigate image-to-image translation as a solution to icon-to-icon translation problems. Icon-to-icon translation aims to translate the input icon to appear like the target domain’s icons and simultaneously preserve the original icon’s information (e.g., application logo, text and background color). We present a novel approach to trans-lating icons to the version with the target style intelligently. By observing many icons with various styles, we propose a pixel-level weight matrix to calculating the weighted losses. These losses guide the generator to focus on the critical regions of the icon. People can clearly get the original icon’s information from the proposed method’s results, while the existing state-of-the-art image-to-image translation methods may fail to do this. © 2022, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Clustering Network Based on Pre-Clustering center Codebook

Clustering Network Based on Pre-Clustering Center Codebook

引用

International Conference on Intelligent System and Knowledge engineering, ISKE

作者： Qiulong An Jianning Wu Tianqiang Huang Liqing Huang Haifeng Luo Feng Ye Fujian Provincial Engineering Research Center of Big Data Analysis and Application College of Computer and Cyber Security Fujian Normal University Digital Fujian Institute of Big Data Security Technology Fuzhou China

Most existing deep clustering models attempt to group similar datas by using autoencoders to simultaneously minimize the clustering loss and reconstruction losses. However, these methods do not impose any constraints on the latent space, resulting in intermediate features that are not suitable for clustering. Moreover, they suffer from poor clustering performance when the number of clusters is large. To address this problem, this paper proposes an autoencoder network with preclustered center codebooks for clustering, two codebooks to represent the cluster centers and center offsets, respectively, making the network features more compatible with the clustering task. Finally, We conducted experiments on CIFAR-10 and STL-10 datasets, the results indicate the effectiveness and superiority of the proposed network model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Optimization Approach Based on Heuristic Information with Pseudo-Utility for the Quadratic Assignment Problem

SSRN

引用

SSRN 2023年

作者： Du, Xin Liu, Wentao Ni, Youcong Xiao, Ruliang Chen, Gaolin Wu, Yong College of Computer and Security Fujian Normal University Fujian Fuzhou350117 China Fujian Provincial Engineering Research Center for Public Service Big Data Mining and Application Fujian Normal University Fujian Fuzhou350117 China School of Geographical Sciences Fujian Normal University Fujian Fuzhou350117 China

Existing data mining-based meta-heuristic approaches have attempted to efficiently solve the Quadratic Assignment Problem (QAP), but their heuristic information is limited to frequent itemsets with adjacent locations or maximum length, while ignoring the objective information. This makes it challenging to generate new solutions that balance global and local search. To alleviate these issues, we propose an approach called EOHIPU. EOHIPU efficiently mines and represents more itemsets composed of frequent items, and simultaneously introduces pseudo-utility to quantitatively characterize the contribution of each item to the objective, thereby capturing more comprehensive and useful heuristic information. Based on the heuristic information with pseudo-utility, a mechanism for new solution generation is designed by considering both global and local searches. We conduct experiments on 21 hard benchmark instances from QAPLIB and compare EOHIPU with five state-of-the-art approaches. Our experimental results show that EOHIPU achieves better solution quality and faster convergence rate. Moreover, the captured heuristic information and mechanism for new solution generation have also been validated to be effective. © 2023, The Authors. All rights reserved.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Long-term(2013-2022)mapping of winter wheat in the North China Plain using Landsat data:classification with optimal zoning strategy

引用

Big Earth data 2024年第3期8卷 494-521页

作者： Yifei Liu Xuehong Chen Jin Chen Yunze Zang Jingyi Wang Miao Lu Liang Sun Qi Dong Bingwen Qiu Xiufang Zhu State Key Laboratory of Remote Sensing Science Institute of Remote Sensing Science and EngineeringFaculty of Geographical ScienceBeijing Normal UniversityBeijingChina Beijing Engineering Research Center for Global Land Remote Sensing Products Institute of Remote Sensing Science and EngineeringFaculty of Geographical ScienceBeijing Normal UniversityBeijingChina State Key Laboratory of Crop Gene Resources and Breeding Institute of Crop SciencesChinese Academy of Agricultural Sciences(CAAS)BeijingChina State Key Laboratory of Efficient Utilization of Arid and Semi-arid Arable Land in Northern China Institute of Agricultural Resources and Regional PlanningChinese Academy of Agricultural SciencesBeijingChina Key Laboratory of Spatial Data Mining&Information Sharing of Ministry of Education Academy of Digital China(Fujian)Fuzhou UniversityFuzhouChina

Long-term mapping of winter wheat is vital for assessing food security and formulating agricultural *** data are the only available source for long-term winter wheat mapping in the North China Plain due to the fragmented landscape in this *** various methods,such as index-based methods,curve similarity-based methods and machine learning-based methods,have been developed for winter wheat mapping based on remote sensing,the former two often require satellite data with high temporal resolution,which are unsuitable for Landsat data with sparse *** learning is an effective method for crop classification using Landsat ***,applying machine learn-ing for winter wheat mapping in the North China Plain encounters two main issues:1)the lack of adequate and accurate samples for classifier training;and 2)the difficulty of training a single classifier to accomplish the large-scale crop mapping due to the high spatial heterogeneity in this *** address these two issues,we first designed a sample selection rule to build a large sample set based on several existing crop maps derived from recent Sentinel data,with specific consideration of the confusion error between winter wheat and winter rapeseed in the available crop ***,we developed an optimal zoning method based on the quadtree region splitting algorithm with classification feature consistency criterion,which divided the study area into six subzones with uni-form classification *** each subzone,a specific random forest classifier was trained and used to generate annual winter wheat maps from 2013 to 2022 using Landsat 8 OLI *** sample validation confirmed the high accuracy of the produced maps,with an average overall accuracy of 91.1%and an average kappa coefficient of 0.810 across different *** derived winter wheat area also has a good correlation(R2=0.949)with census area at the provincial *** results underscore the reliability of the produced ann

关键词： Winter wheat mapping Landsat machine learning North China Plain optimal zoning

来源：评论

学校读者我要写书评

暂无评论

BioAR: Bio-Laboratory Automation Meets Augmented Reality 14th

BioAR: Bio-Laboratory Automation Meets Augmented Reality

引用

14th International Conference on Genetic and Evolutionary Computing, ICGEC 2021

作者： Zou, Zheng Liu, Shi-Jian College of Computer and Cyber Security Fujian Normal University No. 8 Xuefu South Road Fujian Shangjie Minhou Fuzhou China Fujian Provincial Engineering Technology Research Center for Public Service Big Data Mining and Application Fujian Normal University No. 8 Xuefu South Road Fujian Shangjie Minhou Fuzhou China Digital Fujian Institute of Big Data Security Technology Fujian Normal University No. 8 Xuefu South Road Fujian Shangjie Minhou Fuzhou China College of Computer Science and Mathematics Fujian University of Technology No. 3 Xueyuan Road University Town Fujian Minhou Fuzhou China

ISBN: (纸本)9789811684296

Modern laboratory is benefiting from science and engineering by adopting automated systems into labor-intensive lab routines. In this paper, a computer-aided system that involves augmented reality (AR) to promote the automatic levels of the bio-laboratory is introduced. The motivation of this work lies in the idea of offering visual guidance for users to pick a tube manually from the rack after the retrieval. Because it is difficult for people to tell the target tube from the others since they look almost the same. Design issues and implementation details are given after a careful analysis of the system requirements. The BioAR system is tested out and successfully applied to a bio-laboratory with tube related operations, whose performance is approved by the technicians. A video demo of the proposed system can be found at https://***/video/BV1FX4y157WB/. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Option Sequence Optimization Method for Energy Consumption Minimization

SSRN

引用

SSRN 2023年

作者： Ni, Youcong Du, Xin Ye, Peng Xiao, Ruliang Wang, Jianwen College of Computer and Security Fujian Normal University Fujian Fuzhou350117 China Fujian Provincial Engineering Research Center for Public Service Big Data Mining and Application Fujian Normal University Fujian Fuzhou350117 China College of Mathematics and Computer Wuhan Textile University Wuhan430200 China

To efficiently tackle the challenges of optimizing LLVM compilers, including the vast search space, intricate option interactions and time-consuming energy consumption evaluations, we present TSOMFEC, a Two-Stage option sequence Optimization Method For Energy Consumption minimization. In the first stage, OSPM, our option selection algorithm, leverages pattern mining to extract frequent options from diverse samples. These options are further refined through code-based preselection, effectively reducing the optimization space. Moving to the second stage, OSOA, our option sequence evolutionary algorithm, encodes option positions as individual items and captures their interactions through an item interaction graph model. This method streamlines option sequence optimization, minimizing the need for time-consuming energy consumption evaluations, resulting in faster and higher-quality sequences. We rigorously evaluate TSOMFEC against three leading methods using eight embedded software applications, affirming its superior performance. OSPM demonstrates exceptional option preselection capabilities, while OSOA enhances both solution quality and optimization time. © 2023, The Authors. All rights reserved.

关键词： Energy utilization

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：