检索结果-内蒙古大学图书馆

An Ensemble Detection Method for Shilling Attacks Based on Features of Automatic Extraction

China Communications 2019年第8期16卷 130-146页

作者： Yaojun Hao Fuzhi Zhang Jinbo Chao School of Information Science and Engineering Yanshan UniversityQinhuangdao 066004China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao 066004China Department of Computer Science and Technology Xinzhou Teachers UniversityXinzhou 034000China

Faced with the evolving attacks in recommender systems, many detection features have been proposed by human engineering and used in supervised or unsupervised detection methods. However, the detection features extracted by human engineering are usually aimed at some specific types of attacks. To further detect other new types of attacks, the traditional methods have to re-extract detection features with high knowledge cost. To address these limitations, the method for automatic extraction of robust features is proposed and then an Adaboost-based detection method is presented. Firstly, to obtain robust representation with prior knowledge, unlike uniform corruption rate in traditional mLDA(marginalized Linear Denoising Autoencoder), different corruption rates for items are calculated according to the ratings’ distribution. Secondly, the ratings sparsity is used to weight the mapping matrix to extract low-dimensional representation. Moreover, the uniform corruption rate is also set to the next layer in mSLDA(marginalized Stacked Linear Denoising Autoencoder) to extract the stable and robust user features. Finally, under the robust feature space, an Adaboost-based detection method is proposed to alleviate the imbalanced classification problem. Experimental results on the Netflix and Amazon review datasets indicate that the proposed method can effectively detect various attacks.

关键词： shilling attack ensemble detection features of automatic extraction marginalized linear denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Angle historgam model of directional relationship in 3D based on Double-projection and Rounded-subdivision

引用

Journal of Information and Computational Science 2014年第18期11卷 6471-6478页

作者： Kong, Dehan Liu, Yongshan Ma, Junlei Department of Information Science and Engineering Yanshan University Qinhuangdao China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao China Data Industry Research Lab Qinhuangdao China

The formal model of spatial directional relations is one of the most important parts in spatial relation research. The most of models are based on Minimum Bounding Rectangle (MBR), and they are not compliant with the regular pattern of human cognition. In order to get a closer conclusion to human cognition on directional relationship, Angle Histogram model based on Double-projection and Rounded-subdivision (AHDPRS) is proposed in this paper. The model uses the maximum inscribed circles to find out the maximum parts of the object, and calculates the directional relationship between the centers of the circles. This model ignores the inessential details to ensure the result which will be closer to human cognition. The experiments show that this model is feasible.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Point cloud coarse registration based on 3DSIFT keypoint detection

引用

Journal of Computational Information systems 2014年第23期10卷 10121-10128页

作者： Gu, Xiaoying Liu, Yongshan Department of Information Science and Engineering Yanshan University Qinhuangdao China The Key Laboratory for Computer Virtual Technology and System Integration of HeBei Province Yanshan University Qinhuangdao China Data Industry Research Lab Qinhuangdao China

Since the SIFT feature point extraction algorithm with scale changes, rotation transformation invariance, is widely used in image registration. In this paper, the SIFT algorithm is applied to three-dimensional point cloud coarse registration, the proposed 3DSIFT extraction algorithm is suitable for three-dimensional point cloud data, then point coordinates, curvature, the nearest neighbor distance mean and other information compose fourteen-dimensional vector to conduct correspondence match, use the interior point rate of Ransac to obtain optimal transformation, and finally transform the coordinates for source point clouds using the optimal transform, complete the point cloud data coarse registration. Experimental results show that our coarse registration algorithm can effectively extract feature points, and it is robust for the point cloud with noisy point, it can provide accurate and effective initial value for the precise registration such as ICP.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

A RIHS-tree-based algorithm of mining frequent closed itemsets in high dimensional datasets

引用

Journal of Convergence Information technology 2012年第21期7卷 467-476页

作者： Huang, Guoyan Chen, Shuai Ren, Shenyuan Dong, Jun College of Information Science and Engineering Yanshan University Qinhuangdao Hebei 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao City 066004 China College of Computer Science Sichuan University Chengdu Sichuan 610000 China

In order to fully utilize the minimum support threshold to prune the rowset search space and avoid scanning the whole dataset in close-checking, we proposed two new data structure, Rowset-Itemset-Hybrid-Search-Tree (RIHS-Tree) and Frequent-Closed-Itemset-Rowset-Tree (FCIR-Tree). The former stores the rowsets which share common rowid prefixes, according to some predefined order of rowids. Each path from the root node to the leaf node represents a rowset in which the rowids increase. The later also stores the large rowsets which also share common rowid prefixes. The corresponding closed itemsets are stored in the nodes carrying the last rowids in rowsets. Moreover, a new algorithm, RIHS-Tree-based algorithm for mining frequent closed patterns (FCIM-RIHS), is proposed. We translate the whole dataset into a transposed table, construct RIHS-Tree according to the rowsets in the transposed table and use a bottom-up search strategy to traverse RIHS-Tree. In the process of mining, we use the rowsets-inclusion strategy to implement pattern growth and then obtain large rowsets with their corresponding frequent closed itemsets. In FCIR-Tree, if the nodes in the subtree rooted by the nodes carrying the last rowid in the rowsets do not contain the found itemsets, the found itemsets are frequent closed itemsets. The experiment results with dataset demonstrate that FCIM-RIHS has highly efficiency.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Local outlier detection algorithm based on gaussian kernel density function 10th

Local outlier detection algorithm based on gaussian kernel d...

引用

10th International Symposium on Intelligence Computation and Applications, ISICA 2018

作者： Zhang, Zhongping Liu, Jiaojiao Miao, Chuangye School of Information Science and Engineering Yanshan University QinhuangdaoHebei066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province QinhuangdaoHebei066004 China

ISBN: (纸本)9789811364723

With the rapid development of information technology, the structure of data resources is becoming more and more complex, and outlier mining is attracting more and more attention. Based on Gaussian kernel function, this paper considers three neighbors: k nearest neighbors, reverse k neighbors and shared nearest neighbors. A local outlier detection algorithm based on Gaussian kernel function is proposed. Firstly, the algorithm stores the nearest neighbors of each data object through kNN maps, including k-nearest neighbors, reverse k-nearest neighbors, and shared nearest neighbors, forming a kernel neighbor set S. Secondly, Estimating density of data objects through kernel density estimation KDE method. Finally, the relative density outlier factor RDOF is used to estimate the degree of data objects deviating from the neighborhood, and then determines whether the data objects are outliers, and the validity of the algorithm is proved on the real and synthetic data sets. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Real-time simulation of foam and sprays based on the Weber number

引用

Journal of Computational Information systems 2014年第7期10卷 2829-2836页

作者： Zhang, Lihui Zhang, Chao Li, Ying Lv, Mengya Tang, Yong The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province The College of Information Science and Engineering Yanshan University Qinhuangdao 066004 China Department of Information Engineering Environmental Management College of China Qinhuangdao 066004 China

In this paper, we propose a method based on the Weber number to uniformly model and simulate the foam and sprays generated by the fluid motion. We use the SPH to construct the fluid and calculate the Weber number of each particle. The fluid particles are divided into foam particles, transition particles and water particles by comparing their Weber number with a given critical value. These particles are rendered independently. For the solid-liquid interaction in fluid, we use SPH particles to mark the solid shape, and correct the changed solid particle position using a rotating equation. Finally, a more precise fluid surface illumination model is proposed, and the Fresnel reflection coefficient of this model can be gotten by the Snell law. Experiment results show that our method achieve real-time performance and the visual effect is desirable. © 2014 Binary Information Press.

关键词： Hydrodynamics

来源：评论

学校读者我要写书评

暂无评论

A homogenization method for nonlinear inhomogeneous elastic materials

引用

virtual Reality & Intelligent Hardware 2021年第2期3卷 156-170页

作者： Jing ZHAO Fei ZHU Liyou XU Yong TANG Sheng LI College of Information Science and Engineering Yanshan UniversityQinhuangdaoHebei 066004China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province QinhuangdaoHebei 066004China School of Electronics Engineering and Computer Science Peking UniversityBeijing 100871China Beijing Engineering Research Center for Virtual Simulation and Visualization Beijing 100871China

Background Fast simulation techniques are strongly favored in computer graphics,especially for the nonlinear inhomogeneous elastic *** homogenization theory is a perfect match to simulate inhomogeneous deformable objects with its coarse discretization,as it reveals how to extract information at a fine scale and to perform efficient computation with much less *** existing homogenization method is not applicable for ubiquitous nonlinear materials with the limited input deformation *** In this paper,we have proposed a homogenization method for the efficient simulation of nonlinear inhomogeneous elastic *** approach allows for a faithful approximation of fine,heterogeneous nonlinear materials with very coarse *** analysis provides the basis of a linear deformation space and modal derivatives extend the space to a nonlinear regime;based on this,we exploited modal derivatives as the input characteristic deformations for *** also present a simple elastic material model that is nonlinear and anisotropic to represent the homogenized *** nonlinearity of material deformations can be represented properly with this *** material properties for the coarsened model were solved via a constrained optimization that minimizes the weighted sum of the strain energy deviations for all input deformation *** arbitrary number of bases can be used as inputs for homogenization,and greater weights are placed on the more important low-frequency *** Based on the experimental results,this study illustrates that the homogenized material properties obtained from our method approximate the original nonlinear material behavior much better than the existing homogenization method with linear displacements,and saves orders of magnitude of computational *** The proposed homogenization method for nonlinear inhomogeneous elastic materials is capable of capturing the nonlinear dynamics of the

关键词： Physical-based simulation Homogenization theory Heterogeneous material Modal basis

来源：评论

学校读者我要写书评

暂无评论

A new estimator analysis method to synchronization among multivariate neural series of mild cognitive impairment

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content technology and its Applications 2012年第23期6卷 868-874页

作者： Wen, Dong Guan, Xinyong Chen, Ruihong The Key Laboratory for Computer Virtual Technology System Integration of HeBei Province Yanshan University Qinhuangdao Hebei 066004 China Liren College Yanshan University Qinhuangdao Hebei 066004 China Division of General Internal Medicine Xiantao First People's Hospital Xiantao Hubei 433000 China

Synchronization decay of resting state EEG has shown that cognitive dysfunction in mild cognitive impairment (MCI) was relevant to a loss of functional connectivity in intermediate frequency bands. A new estimator analysis method called new S estimator (NSE) proposed recently by us quantifies synchronization between neuronal signals at multiple *** paper meant to explore the behavior of synchronization of multichannel EEG in MCI and healthy normal controls at rest, and preliminarily make clear the clinical significance of the NSE in MCI *** (EEG) were recorded from 10 MCI patients and 12 age-matched healthy normal controls (NC). NSE values were computed both across the all frequency band and separately in the delta, theta, alpha, beta (including beta1, beta2 and beta3), and gamma bands. The Montreal Cognitive Assessment (MoCA) was used to assess the symptom severity of MCI patients and *** values in the alpha and beta1 bands were significantly lower in MCI patients than in NC. NSE values in the alpha and beta1 bands were positively correlated with the MoCA scores in all participants (MCI and NC). In MCI patients, NSE values in the alpha and beta1 bands were also positively correlated with MoCA *** results suggest that NSE values are a useful correlate of EEG synchronization in MCI patients.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

An algorithm based on bit vector decomposition and hash linklist for mining frequent patterns in data streams

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content technology and its Applications 2012年第22期6卷 570-579页

作者： Ren, Jiadong Zhang, Yuanyuan Yu, Shiying College of Information Science and Engineering Yanshan University Qinhuangdao Hebei 066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao City 066004 China Hebei Provincial S and T Management Information Center 159 Dongfeng Road Shijiazhuang 050021 China

Most of algorithms based on bit vector for mining frequent pattern always produce candidate itemsets and scan the same data repeatedly;this increases the running time and the space consumption. In this paper, an algorithm BVDAHL based on bit vector decomposition and hash linklist for mining frequent patterns on data streams which solves the above issues, is proposed. The itemsets (transactions) whose corresponding number of 1 is k, denoted as k-one itemsets (k-one transactions). The arrival transactions are converted into bit vectors, and permutations and combinations are used to decompose converted results, then the decomposed itemsets are stored in the hash linklist. In hash function, according to the position of 1 of bit vector to compute the address, if the transaction has same address and same content that already exists in data domain, then the value adds one in count domain, otherwise the pointer in pointer domain points to the next node directly, it is no need to deal with conflict. Afterwards the property of anti-monotonic will be used to prune the k+1-one transactions in bit vector table if there exists infrequent k-one itemsets that decomposed by such k+1-one transactions. Then the algorithm repeats the above processes until the transaction in bit vector table can not be decomposed. Finally we will receive the frequent itemsets by comparing the obtained value of count domain in hash linklist with minSup. Experiment results show that BVDAHL is very efficiency and scalable.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Capacity planning of the registration server in cloud storage

引用

International Journal of High Performance systems Architecture 2017年第2期7卷 105-112页

作者： Gu, Rui Jin, Shunfu Wu, Haixing School of Information Science and Engineering Yanshan University No. 438 Hebei Avenue Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province No. 438 Hebei Avenue Qinhuangdao066004 China Science and Technology on Communication Networks Laboratory No. 589 West Zhongshan Road Shijiazhuang050081 China

Cloud storage is one of the key services in cloud computing. In order to appeal more users to the cloud storage, free cloud experience is provided to potential users. A registration server is set specially for intentional users who are satisfied with the free experience and want to register as very important persons (VIPs). In order to mathematically evaluate the system performance and optimally plan the registration server, we establish a queueing network-based system model. We analyse the steady-state distribution of the system model and derive the performance measures of the system in terms of the average response time of potential users and the utilisation of registration server. For balancing different performance measures, we establish a cost function and develop an optimisation algorithm to plan the capacity of the registration server with a reasonable service rate. © Copyright 2017 Inderscience Enterprises Ltd.

关键词： Queueing networks

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：