检索结果-内蒙古大学图书馆

Multi-objective frequent termset clustering

KNOWLEDGE AND INFORMATION SYSTEMS 2012年第3期30卷 715-738页

作者： Morik, Katharina Kaspari, Andreas Wurst, Michael Skirzynski, Marcin Tech Univ Dortmund Dortmund Germany IBM Dublin Smarter Cities Technol Ctr Dublin Ireland Dortmund Intelligence Project GmbH Duisburg Germany

Large media collections rapidly evolve in the World Wide Web. In addition to the targeted retrieval as is performed by search engines, browsing and explorative navigation is an important issue. Since the collections grow fast and authors most often do not annotate their web pages according to a given ontology, automatic structuring is in demand as a prerequisite for any pleasant human-computer interface. In this paper, we investigate the problem of finding alternative high-quality structures for navigation in a large collection of high-dimensional data. We express desired properties of frequent termset clustering (FTS) in terms of objective functions. In general, these functions are conflicting. This leads to the formulation of FTS clustering as a multi-objective optimization problem. The optimization is solved by a genetic algorithm. The result is a set of Pareto-optimal solutions. Users may choose their favorite type of a structure for their navigation through a collection or explore the different views given by the different optimal solutions. We explore the capability of the new approach to produce structures that are well suited for browsing on a social bookmarking data set.

关键词： Collaborative clustering distributed data mining Ensemble clustering Multi-media collections

来源：评论

学校读者我要写书评

暂无评论

A Practical Differentially Private Random Decision Tree Classifier

引用

TRANSACTIONS ON data PRIVACY 2012年第1期5卷 273-295页

作者： Jagannathan, Geetha Pillaipakkamnatt, Krishnan Wright, Rebecca N. Columbia Univ Dept Comp Sci New York NY 10027 USA Hofstra Univ Dept Comp Sci Hempstead NY 11550 USA Rutgers State Univ Dept Comp Sci New Brunswick NJ USA

In this paper, we study the problem of constructing private classifiers using decision trees, within the framework of differential privacy. We first present experimental evidence that creating a differentially private ID3 tree using differentially private low-level queries does not simultaneously provide good privacy and good accuracy, particularly for small datasets. In search of better privacy and accuracy, we then present a differentially private decision tree ensemble algorithm based on random decision trees. We demonstrate experimentally that this approach yields good prediction while maintaining good privacy, even for small datasets. We also present differentially private extensions of our algorithm to two settings: (1) new data is periodically appended to an existing database and (2) the database is horizontally or vertically partitioned between multiple users.

关键词： Differential privacy Classifiers Ensembles distributed data mining

来源：评论

学校读者我要写书评

暂无评论

distributed multi-class rule based classification using RIPPER 16

Distributed multi-class rule based classification using RIPP...

引用

IEEE International Conference on Computer and Information Technology (CIT)

作者： Govada, Aruna Thomas, Varsha S. Samal, Ipsita Sahay, Sanjay K. BITS Pilani Dept Comp Sci & Informat Syst KK Birla Goa Campus Sancoale Goa India

ISBN: (纸本)9781509043149

Traditional data mining (DM) has certain challenges viz. scalability, high dimensionality, distributed data and often it also requires huge amount of computational resources in terms of space and time to extract the hidden patterns in the data. In addition, the data has to be available at one location. But in today's era the data are often inherently distributed in several databases. Hence, due to the limited bandwidth, centralized processing of the data is highly inefficient. Therefore, distributed computing becomes very important for efficient DM, both in terms of space and time. This can be done by developing a mechanism to mine the massive data by applying DM in a non-centralized way that distributes the work load seamlessly among the available sites. Therefore, in this paper, we propose an algorithm distributed multi-class rule based classification (DiRUC) which implements repeated incremental pruning to produce error reduction (RIPPER) at local level and then merges into a global level in a distributed manner. The algorithm first constructs the local rule sets for the distributed data and then at each iteration the local models are sent from one location to other. Finally, the global model is constructed by efficiently merging these local models and is made available at each site for further prediction of the class labels. The performance (accuracy and efficiency) analysis of the algorithm is done for the five data sets with different parameters and the result shows that the proposed approach DiRUC outperforms the normal RIPPER and Ischibuchi et al. island model.

关键词： distributed data mining RIPPER HADOOP

来源：评论

学校读者我要写书评

暂无评论

Experimental studies using photonic data services at IGrid 2002

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2003年第6期19卷 945-955页

作者： Grossman, RL Gu, YH Hamelburg, D Hanley, D Hong, XW Levera, J Lillethun, D Mazzucco, M Mambretti, J Weinberger, J Univ Illinois Chicago IL 60612 USA Northwestern Univ Evanston IL USA

We describe an architecture for remote and distributed data intensive applications that integrates optical path services, network protocol services for high performance data transport, and data services for remote data analysis and distributed data mining. We also present experimental evidence using geoscience data that this architecture scales to long haul, high performance networks. (C) 2003 Elsevier Science B.V All rights reserved.

关键词： high performance networks distributed data mining data webs TCP UDP

来源：评论

学校读者我要写书评

暂无评论

distributed Clustering Using distributed Mixture of Probabilistic PCA 11

Distributed Clustering Using Distributed Mixture of Probabil...

引用

11th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Yin, Hang Zhang, Chunhong Ji, Yang Beijing Univ Posts & Telecommun Sch Informat & Commun Engn Beijing 100088 Peoples R China

ISBN: (纸本)9781479951482

This paper considers the clustering algorithm based on mixture of probabilistic principle component analyzers in distributed environments. The EM procedure of it is first transformed to a summing variant. Following the classic distributed EM framework for mixture of exponential family distributions and utilizing the summing variant, we propose the distributed EM for mixture of probabilistic principle component analyzers. The proposed algorithm avoids transferring all data from distributed nodes to a central node. Experiment verifies the validity and feasibility of the proposed method. For some datasets, the proposed method can even enhance the log-likelihood as well as the clustering performance.

关键词： Mixture of Probabilistic PCA distributed Clustering distributed EM distributed data mining

来源：评论

学校读者我要写书评

暂无评论

CONQUEST:: A distributed tool for constructing summaries of high-dimensional discrete attributed datasets

CONQUEST:: A distributed tool for constructing summaries of ...

引用

4th SIAM International Conference on data mining

作者： Chi, J Koyutürk, M Grama, A Purdue Univ Dept Comp Sci W Lafayette IN 47907 USA

ISBN: (纸本)0898715687

The problem of constructing bounded-error summaries of binary attributed data of very high dimensions is an important and difficult one. These summaries enable more expensive analysis techniques to be applied efficiently with little loss in accuracy. Recent work in this area has resulted in the use of discrete linear algebraic transforms to construct such summaries efficiently. This paper addresses the problem of constructing summaries of distributed datasets. Specifically, the problem can be stated as follows: given a set of n discrete attributed vectors distributed across p sites, construct a summary of k << n vectors such that each of the input vectors is within given bounded distance from some output vector. In addition to being algorithmically efficient (i.e., must do no more work than corresponding serial algorithm), the distributed formulation must have low parallelization overheads. We present here, CONQUEST, a tool that achieves excellent performance and scalability for summarizing distributed datasets. In contrast to traditional parallel techniques that distribute the kernel operations, CONQUEST uses a less aggressive parallel formulation that relies on the principle of sampling to reduce communication overhead while maintaining high accuracy. Specifically, each individual site computes its local patterns independently. Various sites cooperate within dynamically orchestrated workgroups to construct consensus patters from these local patterns. Individual sites then decide to participate in the consensus or leave the group. Experimental results on a set of Intel Xeon servers demonstrate that this strategy is capable of excellent performance in terms of compression time, ratio, and accuracy with respect to postprocessing tasks. The communication overhead associated with CONQUEST is also shown to be minimal, making it ideally suited to wide-area deployment.

关键词： distributed data mining compressing binary attributed vectors non-orthogonal matrix decompositions correlations in high dimensions

来源：评论

学校读者我要写书评

暂无评论

Outlier Preprocessing in Wireless Sensor Networks: A Two-layered Ellipse Approach 6

Outlier Preprocessing in Wireless Sensor Networks: A Two-lay...

引用

Sixth International Conference on Developments in eSystems Engineering (DeSE)

作者： Khamis, Ibrahim Aung, Zeyar Masdar Inst Sci & Technol Dept Comp Sci & Elect Engn Inst Ctr Smart & Sustainable Syst iSmart POB 54224 Abu Dhabi U Arab Emirates

ISBN: (纸本)9781479952649

Sensor nodes in wireless sensor networks have limited energy resources and this hinders the dissemination of the gathered data to a central location. This stimulated our research to make use of the limited computational capabilities of these sensor nodes to build a normal model of the data gathered. Hence by having the normal model, anomalies can then be detected and forwarded to a central location. This process is done locally in the sensor nodes and hence reduces the power consumption used in transmitting all the data. Our algorithm is an enhanced version of the data Capture Anomalies Detection Algorithm;which is used to compute a local model of the normal data in wireless sensor networks. In this paper the data Capture Anomalies Detection is used to partition the data and then send all the data to a central server for data classification, building on the data Capture Anomalies Detection method and in order to classify the partitioned data;our algorithm Two-Layered data Capture Anomalies Detection sends anomalies (2%) as well as roughly (2% or 4%) of normal data for further data processing and classification purposes. Experimental results on synthetic data show that Two-Layered data Capture Anomalies Detection is able to provide promising results.

关键词： wireless sensor network anomaly detection elliptical boundary estimation two-layered ellipse approach distributed data mining

来源：评论

学校读者我要写书评

暂无评论

Grid-based Platform for mining Association Rules

Grid-based Platform for Mining Association Rules

引用

International Conference on Mechanical Engineering and Green Manufacturing (MEGM) 2010

作者： Chang, Youqu Deng, Huaiyong Hou, Guoping Chongqing Elect Power Coll Chongqing 400053 Peoples R China Chongqing Water Resources & Elect Engn Chongqing 402160 Peoples R China

ISBN: (纸本)9780878492329

distributed data mining is widely used in industrial and commercial applications to analyze large datasets maintained over geographically distributed sites. This paper discusses the disadvantages of existing distributed data mining systems, and puts forward a distributed data mining platform based grid computing. The experiments done on a data set showed that the proposed approach produces meaningful results and has reasonable efficiency and effectiveness providing a trade-off between runtime and rule interestingness.

关键词： distributed data mining grid computing Globus Toolkit

来源：评论

学校读者我要写书评

暂无评论

Hp-Apriori:Horizontal Parallel-Apriori Algorithm For Frequent Itemset mining from Big data 2

Hp-Apriori:Horizontal Parallel-Apriori Algorithm For Frequen...

引用

2017 IEEE 2nd International Conference on Big data Analysis（ICBDA 2017）

作者： Mohammad-Hossein Nadimi-Shahraki Mehdi Mansouri Faculty of Computer Engineering Najafabad branchIslamic Azad University Big Data Research Center Najafabad branchIslamic Azad University

ISBN: (纸本)9781509036202

Due to large scale and complexity of big data,mining the big data using a single personal computer is a difficult *** increasing in the size of databases,parallel computing systems can cause considerable advantages in the data mining applications by means of the exploitation of data mining *** of association rule mining algorithms is an important task in data mining to mine frequent patterns from transaction *** algorithms either distribute database horizontally or increase number of CPU to reduce execution time of frequent pattern *** this paper,a novel frequent itemset mining algorithm,namely Horizontal parallel-Apriori(HP-Apriori),is proposed that divides database both horizontally and vertically with partitioning mining process into four sub-processes so that all four tasks are performed in parallel *** the HPApriori tries to speed up the mining process by an index file that is generated in the first step of *** proposed algorithm has been compared with Count Distribution(CD) in terms of execution time and speedup criteria on the four real *** results demonstrated that the HPApriori outperforms over CD in terms of minimizing execution time and maximizing speedup in high scalability.

关键词： big data frequent itemsets distributed data mining parallel data mining transaction data

来源：评论

学校读者我要写书评

暂无评论

distributed Knowledge Discovery with Non Linear Dimensionality Reduction

Distributed Knowledge Discovery with Non Linear Dimensionali...

引用

14th Pacific-Asia Conference on Knowledge Discovery and data mining

作者： Magdalinos, Panagis Vazirgiannis, Michalis Valsamou, Dialecti Athens Univ Econ & Business Athens Athens Greece

ISBN: (纸本)9783642136719

data mining tasks results are usually improved by reducing the dimensionality of data. This improvement however is achieved harder in the case that data lay on a non linear manifold and are distributed across network nodes. Although numerous algorithms for distributed dimensionality reduction have been proposed, all assume that data reside in a linear space. In order to address the non-linear case, we introduce D-Isomap, a novel distributed non linear dimensionality reduction algorithm, particularly applicable in large scale, structured peer-to-peer networks. Apart from unfolding a non linear manifold, our algorithm is capable of approximate reconstruction of the global dataset at peer level a very attractive feature for distributed data mining problems. We extensively evaluate its performance through experiments on both artificial and real world datasets. The obtained results show the suitability and viability of our approach for knowledge discovery in distributed environments.

关键词： distributed non linear dimensionality reduction distributed data mining

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：