检索结果-内蒙古大学图书馆

Robust recommendation algorithm based on user rating matrix block and modified LTS-estimator

Journal of Information and Computational Science 2014年第6期11卷 1889-1898页

作者： Xu, Yuchen Liu, Zhen Zhang, Fuzhi School of Information Science and Engineering Yanshan University Qinhuangdao 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao 066004 China

The most widely-used collaborative recommendation algorithms are vulnerable to shilling attacks. To this end, in this paper we propose a robust recommendation algorithm based on user rating matrix block and modified LTS-estimator. Firstly, we construct user rating matrix blocks using user rating matrix block algorithm based on k-median clustering. Secondly, we apply the modified LTS-estimator to matrix factorization model in order to produce user feature matrix and item feature matrix. Finally, we devise a robust recommendation algorithm to generate recommendations for the target users. Experimental results on the MovieLens dataset show that the proposed algorithm outperforms the existing methods in terms of both the prediction accuracy and robustness. © 2014 Binary Information Press.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

A high dimensional data clustering algorithm based on hypergraph

引用

Journal of Computational Information systems 2012年第23期8卷 9839-9846页

作者： Liu, Yongshan Chen, Wei Shang, Xuehui Lv, Yongteng Han, Yuanyuan Liu, Chang College of Information Science and Engineering Yanshan University Qinhuangdao 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao 066004 China

High dimensional data clustering is an important issue for data mining. Firstly, the records in the dataset are mapped to the vertices of hypergraph, the hyperedges of hypergraph are composed of the vertices which have the same value on one certain attributes. Then a multilevel hypergraph partitioning algorithm is used to find k parts of the hypergraph. Finally, the clusters with good quality are choosed out by computing the value of clusters validity. The experimental results show that the new algorithm can efficiently construct high quality clusters. ©2012 by Binary Information Press.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Sequential pattern mining with gap constraints for discovery of the software bug features

引用

Journal of Computational Information systems 2014年第2期10卷 673-680页

作者： Zeng, Qiang Chen, Yuping Han, Gaowei Ren, Jiadong College of Information Science and Engineering Yanshan University Qinhuangdao 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao 066004 China

In order to process the software bug feature sequences, this paper presents a gap-constrained sequential pattern mining algorithm, MEMIGCSP algorithm. The length of the interval between items is limited in the original sequences so as to find interested sequences. The gap constrained prefix index set (P-Gidx) based on memory indexing provides the position information of the bug sequence patterns. Strategy of divide-and-conquer is used to deal with the sequences which are in the P-Gidx and others respectively. What's more, pattern growth is advanced to extend the prefix pattern after the local extension items are searched from the forward and backward space, thus the complete set of sequential patterns can be found. The performance evaluation demonstrates the scalability of MEMIGCSP and shows the efficiency and accuracy for mining sequential pattern with gap constraints. Copyright © 2014 Binary Information Press.

关键词： Indexing (of information)

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Subspace clustering over high-dimensional data stream based on grid density and attribute relativity

引用

Advances in Information Sciences and Service Sciences 2012年第17期4卷 91-99页

作者： Huang, Guoyan Miao, Liyun Ren, Jiadong College of Information Science and Engineering Yanshan University Qinhuangdao City 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao City 066004 China

The traditional clustering algorithms often fail to detect meaningful clusters in high-dimensional data space. To improve the above shortcoming, we propose GDRH-Stream, a clustering method based on the attribute relativity and grid density for high-dimensional data stream, which consists of an online component and an offline component. First, the algorithm filters out redundant attributes by computing the relative entropy. Then we define a weighted attribute relativity measure and estimate the relativity of the non-redundant attributes, and form the attribute triple. At last, the best interesting subspaces are searched by the attribute triple. On the online component, GDRH-Stream maps each data object into a grid and updates the characteristic vector of the grid. On the offline component, when a clustering request arrives, the best interesting subspaces will be generated by attribute relativity. Then the original grid structure is projected to the subspace and a new grid structure is formed. The clustering will be performed on the new grid structure by adopting an approach based on the density grid. Experimental results show that GDRH-Stream algorithm has better quality and scalability.

关键词： Relativity

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

A clustering algorithm for heterogeneous objects based on information dissimilarity

引用

Journal of Convergence Information technology 2012年第22期7卷 93-100页

作者： Chen, Ziyang Wang, Xuefeng Ren, Jiadong College of Information Science and Engineering Yanshan University Qinhuangdao City 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao City 066004 China

Due to the introduction of weight of attributes, most of existing dissimilarity measures can not accurately reflect the difference between two heterogeneous objects, and then clustering quality was decreased. In this paper, we present HIDK-means, an approach for clustering heterogeneous data based on information dissimilarity. At first, the algorithm defines heterogeneous information dissimilarity between two heterogeneous objects based on Kolmogorov information theory, and calculates approximately heterogeneous information dissimilarity by a universal probability of an object. Then, in the clustering process, the algorithm selects the initial cluster centers by maximum sum of dissimilarity. After that, each remaining object is assigned to a cluster center which has the smallest dissimilarity with it and the criterion function is calculated. Iteratively, cluster centers are updated and the process is ceased until the criterion function converges or the iteration number reaches the pre-set threshold. The experimental results show that the proposed algorithm HIDK-means is effective in clustering heterogeneous objects and also scalable to large datasets.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

An algorithm based on temporary table for mining top-k closed 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20期6卷 582-589页

作者： Wang, Peilong Yang, Xuan Zhang, Yuanyuan Ren, Jiadong College of Information Science and Engineering Yanshan University Qinhuangdao City 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao City 066004 China

In this paper, we present an algorithm TKBT(top-k closed frequent mining based on TKTT) to mine top-k closed frequent itemsets in data streams efficiently. First according to the consecutive and changeable characteristics of the data from data streams in sliding window, a novel structure, BWT(bit-vector window table) is defined. In BWT horizontal direction we use bit vectors to express the transactions, record the count of items in the oldest, the newest window and all the windows a t current time, which decreases the calculating time of the items count when a new window slides in. In BWT vertical direction we set window partition, which makes us just need replace the oldest window information with the corresponding newest window when a new window comes. The construction of TKTT (top-k temporary table) is based on BWT. The itemsets in TKTT are ranked in a descending count order. TKBT can get top-k closed frequent itemsets by connecting the candidates in TKTT using top-down strategy. The candidate number is reduced by using closed itemset displace its subset and less connection times are contributed to the less runtime. Experiment results show that TKBT is very effective and scalable.

关键词： Data Streams Sliding Window Top-K Closed Frequent Itemsets

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

Mining weighted closed sequential patterns by memory indexing

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content technology and its Applications 2012年第19期6卷 432-440页

作者： Ren, Jiadong Li, Shuo 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

There exist two major problems in weighted closed sequential patterns mining. The first is that only the weights of items are considered and they ignore the time-interval information of data elements during the mining process;the second is that the existing weighted closed sequential pattern mining algorithms need to scan the sequence database many times or to construct numerous intermediate databases. To address these problems, we propose a memory-based algorithm, MIWCSpan (Memory Indexing for Weighted Closed Sequential pattern mining), for weighted closed sequential pattern mining. In the algorithm, we define a novel sequence weighting approach to find more interesting sequential patterns. Both the weight of sequence items and the time-interval of the data elements are considered in this approach. Moreover, an improved index set based on time-interval, p-iidx, is defined. The structure is a set of triples which store the pointer pointing to the sequence containing p, the time-interval of p in the sequence and the position where p occurs. In the mining process, MIWCSpan first scans the sequence database to read the database into memory. Then it adopts the find-then-index technique recursively to find the items which can constitute a weighted closed sequential pattern and construct p-iidx for the possible weighted closed sequential pattern. At last, the algorithm uses the close-detecting to mine the weighted closed sequential patterns efficiently. The experimental results show that MIWCSpan is better on running time, and it has good scalability.

关键词： Database systems

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：