检索结果-南通市图书馆

Relational graph location network for multi-view image localization

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2023年第2期34卷 460-468页

作者： YANG Yukun LIU Xiangdong School of Automation Beijing Institute of TechnologyBeijing 100081China

In multi-view image localization task,the features of the images captured from different views should be fused *** paper considers the classification-based image localization *** propose the relational graph location network(RGLN)to perform this *** this network,we propose a heterogeneous graph construction approach for graph classification tasks,which aims to describe the location in a more appropriate way,thereby improving the expression ability of the location representation *** show that the expression ability of the proposed graph construction approach outperforms the compared methods by a large *** addition,the proposed localization method outperforms the compared localization methods by around 1.7%in terms of meter-level accuracy.

关键词： multi-view image localization graph construction heterogeneous graph graph neural network

Nearest-neighbor classifier motivated marginal discriminant projections for face recognition

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2011年第4期5卷 419-428页

作者： Pu HUANG Zhenmin TANG Caikou CHEN Xintian CHENG School of Computer Science and Technology Nanjing University of Science and Technology Nanjing 210094 China College of Information Engineering Yangzhou University Yangzhou 225009 China

Marginal Fisher analysis （MFA） is a repre- sentative margin-based learning algorithm for face recognition. A major problem in MFA is how to select appropriate parameters, k1 and k2, to construct the respective intrinsic and penalty graphs. In this paper, we propose a novel method called nearest-neighbor （NN） classifier motivated marginal discriminant projections （NN-MDP）. Motivated by the NN classifier, NN-MDP seeks a few projection vectors to prevent data samples from being wrongly categorized. Like MFA, NN-MDP can characterize the compactness and separability of samples simultaneously. Moreover, in contrast to MFA, NN-MDP can actively construct the intrinsic graph and penalty graph without unknown parameters. Experimental results on the 0RL, Yale, and FERET face databases show that NN-MDP not only avoids the intractability, and high expense of neighborhood parameter selection, but is also more applicable to face recognition with NN classifier than other methods.

关键词： dimensionality reduction (DR) face recogni-tion marginal Fisher analysis (MFA) locality preservingprojections (LPP) graph construction margin-based,nearest-neighbor (NN) classifier

Local Preserving graphs Using Intra-Class Competitive Representation for Dimensionality Reduction of Hyperspectral Image

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Beijing Institute of Technology 2021年第2期30卷 139-158页

作者： Zhen Ye Shihao Shi Tao Sun Lin Bai School of Electronics and Control Engineering Chang’an UniversityXi’an 710064China

As a key technique in hyperspectral image pre-processing,dimensionality reduction has received a lot of ***,most of the graph-based dimensionality reduction methods only consider a single structure in the data and ignore the interfusion of multiple *** this paper,we propose two methods for combining intra-class competition for locally preserved graphs by constructing a new dictionary containing neighbourhood *** two methods explore local information into the collaborative graph through competing constraints,thus effectively improving the overcrowded distribution of intra-class coefficients in the collaborative graph and enhancing the discriminative power of the *** classifying four benchmark hyperspectral data,the proposed methods are proved to be superior to several advanced algorithms,even under small-sample-size conditions.

关键词： intra-class competition graph construction hyperspectral image dimensionality reduction

Insider threat detection approach for tobacco industry based on heterogeneous graph embedding

在线全文

学校读者我要写书评

暂无评论

High Technology Letters 2024年第2期30卷 199-210页

作者：季琦 LI Wei PAN Bailin XUE Hongkai QIU Xiang Hangzhou Cigarette Factory China Tobacco Zhejiang Industrial Co.Ltd.Hangzhou 310024P.R.China Information Center China Tobacco Zhejiang Industrial Co.Ltd.Hangzhou 310024P.R.China College of Information Engineering Zhejiang University of TechnologyHangzhou 310014P.R.China

In the tobacco industry,insider employee attack is a thorny problem that is difficult to *** solve this issue,this paper proposes an insider threat detection method based on heterogeneous graph ***,the interrelationships between logs are fully considered,and log entries are converted into heterogeneous graphs based on these ***,the heterogeneous graph embedding is adopted and each log entry is represented as a low-dimensional feature ***,normal logs and malicious logs are classified into different clusters by clustering algorithm to identify malicious ***,the effectiveness and superiority of the method is verified through experiments on the CERT *** experimental results show that this method has better performance compared to some baseline methods.

关键词： insider threat detection advanced persistent threats graph construction heterogeneous graph embedding

Constructing Non-binary Asymmetric Quantum Codes via graphs

在线全文

学校读者我要写书评

暂无评论

China Communications 2013年第2期10卷 33-41页

作者：马智冷日光魏正超钟淑琴 State key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou Information Science and Technology Institute

The theory of quantum error correcting codes is a primary tool for fighting decoherence and other quantum noise in quantum communication and quantum computation. Recently, the theory of quantum error correcting codes has developed rapidly and been extended to protect quantum information over asymmetric quantum channels, in which phase-shift and qubit-flip errors occur with different probabilities. In this paper, we generalize the construction of symmetric quantum codes via graphs (or matrices) to the asymmetric case, converting the construction of asymmetric quantum codes to finding matrices with some special properties. We also propose some asymmetric quantum Maximal Distance Separable (MDS) codes as examples constructed in this way.

关键词： asymmetric quantum codes quantum MDS codes graph construction