检索结果-内蒙古大学图书馆

Application of an improved clustering algorithm in customer risk preference recognition model

ICIC Express Letters, Part B: Applications 2016年第5期7卷 1077-1082页

作者： Xiao, Lin Xu, Shenghua Pan, Jeng-Shyang Yang, Tonghua College of Information Management Jiangxi University of Finance and Economics No. 665 West Yuping Road Nanchang330013 China College of Information Science and Engineering Fujian University of Technology No. 3 Xueyuan Road University Town Minhou Fuzhou350108 China Key Laboratory of Big Data Mining and Applications of Fujian Province Fuzhou350108 China

The main problem of this paper is to establish a recognition model for the risk preference of brokerage individual customer. It is based on transaction data. Its core algorithm is the use of improved K-means algorithm. Its process includes the principal component analysis and clustering operation of the data. In this paper, we improve the design of automatic merging approximation class in clustering algorithm. The main basis of customer risk is the investment subject of the customer. The contribution of this research is to promote the accuracy and success rate of marketing and provide a good support for the company to make reasonable marketing decision. © 2016, ICIC International. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Ramp Loss Linear Programming Nonparallel Support Vector Machine

引用

Procedia Computer Science 2016年 80卷 1745-1754页

作者： Dalian Liu Dandan Chen Yong Shi Yingjie Tian School of Computer and Information Technology Beijing Jiaotong University Beijing 100044 China Department of Basic Course Teaching Beijing Union University Beijing 100101 China College of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100049 China Research Center on Fictitious Economy and Data Science University of Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing 100190 China College of Information Science and Technology University of Nebraska at Omaha Omaha NE 68182 USA

Motivated by the fact that the l 1 -penalty is piecewise linear, we proposed a ramp loss linear programming nonparallel support vector machine (ramp-LPNPSVM), in which the l 1 -penalty is applied for the RNPSVM, for binary classification. Since the ramp loss has the piecewise linearity as well, ramp- LPNPSVM is a piecewise linear minimization problem and a local minimum can be effectively found by the Concave Convex Procedure and experimental results on benchmark datasets confirm the effectiveness of the proposed algorithm. Moreover, the l 1 -penalty can enhance the sparsity.

关键词： support vector machine nonparallel CCCP linear programming ramp loss

来源：评论

学校读者我要写书评

暂无评论

A Multi-replica Associated Deleting Scheme in Cloud

A Multi-replica Associated Deleting Scheme in Cloud

引用

International Conference on Complex, Intelligent and Software Intensive Systems, CISIS

作者： Yuanyuan Zhang Jinbo Xiong Xuan Li Biao Jin Suping Li Xu An Wang Fujian Provincial Key Laboratory of Network Security and Cryptology Fujian Normal University Fuzhou China Fujian Engineering Research Center of Public Service Big Data Mining and Application Fuzhou China Faculty of Software Fujian Normal University Fuzhou China Fujian Eng. Res. Center of Public Service Big Data Min. & Applic. Fuzhou China Engineering University of CAPF Xi'an China

ISBN: (纸本)9781509009886

Rapid development of cloud storage services produces a tremendous amount of user data outsourcing to cloud servers. Therefore, it is easy to generate data multi-replica, which is able to improve data availability and users' experience. However, when the management of data is poor, the sensitive information will be disclosed more easily. This may bring serious security and privacy challenges for both user's data and its multi-replica in cloud environment. In order to tackle the above issues, in this paper, we propose a multi-replica associated deleting scheme (MADS) in cloud environment. We first introduce a replica associated model to organize all of data replicas among different cloud servers. Furthermore, we propose the MADS scheme which is consists of data storage algorithm, replica generation algorithm, replica deletion and feedback algorithm. Finally, we employ Amazon S3 to implement MADS and the results indicate that the proposed scheme is available and effective.

关键词： Servers Cloud computing Memory Security data privacy Metadata

来源：评论

学校读者我要写书评

暂无评论

China's New Third Board Market: Opportunities and Challenges

引用

Procedia Computer Science 2015年 55卷 1050-1059页

作者： Yumeng Li Xiangying Meng Xianhua Wei School of Management University of Chinese Academy Sciences Beijing 100010 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences

The New Third Board Market is China's OTC market, established in 2006. Compared to China's Main Board Market and the Second Board Market, it attracts a lot of start-up companies needing financing with lower listing requirements. Meanwhile, it is full of opportunities and challenges that appeal to numerous securities traders and investors with the rapid development momentum. This paper is intended to build a comprehensive and systematic knowledge framework of China's New Third Board Market for those enterprises and individuals interested in it, and to provide a research base for future researchers.

关键词： China's New Third Board Market SME financing market makers opportunities challanges

来源：评论

学校读者我要写书评

暂无评论

Exploring the heterogeneity of social media: dataset and a pilot study 15

Exploring the heterogeneity of social media: Dataset and a p...

引用

7th International Conference on Internet Multimedia Computing and Service, ICIMCS 2015

作者： Lu, Dongyuan Zheng, Nan School of Information Technology and Management University of International Business and Economics Beijing100029 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781450335287

Social media has exploded beyond anyone's wildest imagination, and User Generated Content (UGC) is propagated online at an unparalleled level. Organizing and associating the heterogeneous UGC data in different social media networks is playing a more and more important role in comprehensive user modeling and social media applications. Since social media data are essentially user-centric, which are generated from user and customized for user, we introduce a user-centric dataset to analyze and exploit the social media heterogeneity, which involves with six popular social media networks and 180, 000 overlapped users. A pilot study on the collected dataset is conducted to demonstrate the limitations of traditional content-centric metrics in analyzing the cross-OSN data. Finally, we conclude this work with discussions on the potentials of usercentric framework for cross-OSN organization and association. © 2015 ACM.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Neighborhood collaborative classifiers

Neighborhood collaborative classifiers

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Suping Xu Xibei Yang Eric C. C. Tsang Eric A. Mantey Intelligent Information Processing Key Laboratory of Shanxi Province Shanxi University Taiyuan China School of Computer Science and Engineering Jiangsu University of Science and Technology Zhenjiang China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University Zhoushan China School of Economics and Management Nanjing University of Science and Technology Nanjing China Faculty of Information Technology Macau University of Science and Technology Macau China

ISBN: (纸本)9781509003914

In neighborhood rough set model, the majority rule based neighborhood classifier (NC) is easy to be misjudged with the increasing of the size of information granules. To remedy this deficiency, we propose a neighborhood collaborative classifier (NCC) based on the idea of collaborative representation based classification (CRC). NCC first performs feature selection with neighborhood rough set, and then instead of solving the classification problem by the majority rule, NCC solves a similar problem with collaborative representation among the neighbors of each unseen sample. Experiments on UCI data sets demonstrate that: 1) Our NCC achieves satisfactory performance in larger neighborhood information granules when compared with NC; 2) NCC reduces the size of dictionary when compared with CRC.

关键词： Collaboration Rough sets Training Cybernetics Numerical models Error analysis Measurement

来源：评论

学校读者我要写书评

暂无评论

Time-Series Analysis on the Impact Level upon Taiwan Stock Market with Events of Signing International Agreements

Time-Series Analysis on the Impact Level upon Taiwan Stock M...

引用

International Conference on Computing, Measurement, Control and Sensor Network (CMCSN)

作者： Pei-Wei Tsai You-Xin Lin Jing Zhang Jui-Fang Chang Jhih-Sheng Chen Jilin Zhang College of Information Science and Engineering Fujian University of Technology Fuzhou China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China Department of International Business National Kaohsiung University of Applied Sciences Kaohsiung Taiwan Department of Mathematics and Physics Fujian University of Technology Fuzhou China

ISBN: (纸本)9781509010943

Stock investment is one of the available conventional financial commodities in the investment market. The individual price of stocks including stocks in the field of industrial, medical, financial, overall, etc. Is subject to many different aspects. The relationship between aspects, the international economy, and the stock price is complex and is not easy to be categorized. Moreover, the trend of the world increases the cooperation and links between countries and different nations. Many agreements in tourism, trade, etc. Are signed between countries. In this paper, we focus on the effect on the stock prices caused by the agreements signed between Taiwan and other countries. The time series method is utilized to analyze the effect on the stock price forecasting caused by 5 of the incidents including WTO, Taiwan-Nicaragua FTA, Taiwan-Honduras FTA, and Taiwan-Japan BIA. Both the pre-event and the post-event periods are included for observing the fluctuation behavior of the stock market price. The MAPE value is used as the criterion to verify the correctness of the forecasting result. The MAPE values obtained in all experiments are all less than 10%. It implies that the time series method presents good forecasting ability in the analyzed cases.

关键词： Stock markets Forecasting Time series analysis Companies Industries Predictive models

来源：评论

学校读者我要写书评

暂无评论

Enable Privacy Preservation and Result Verification for Top-k Query in Two-Tiered Sensor Networks

Enable Privacy Preservation and Result Verification for Top-...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Hui Peng Xiaoying Zhang Hong Chen Yuncheng Wu Yao Wu Juru Zeng Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education Renmin University of China Beijing China

ISBN: (纸本)9781467379533

Wireless sensor network is an important part of the Internet of Things. Preservation of privacy and integrity in wireless sensor networks is extremely urgent and challenging. This paper proposes an efficient mechanism, called PTK, for define and solve the practical and challenging problem of privacy-preserving and verifiable Top-k query processing in two-tier sensor network. PTK prevents adversaries from gaining sensitive information of both queries issued by users and data collected by sensor nodes while allows the ink to verify whether the results are valid. It offers confidentiality of queries and data by constructing a special code, and also achieves high defense capability against the background analysis attack through the implementation of obfuscation coding mechanism. Moreover, PTK provides integrity verification by the correlation among data. Finally, the experimental results show the high performance of proposed schemes in terms of privacy preservation and query efficiency.

关键词： data privacy Privacy Wireless sensor networks Protocols Query processing Cryptography data models

来源：评论

学校读者我要写书评

暂无评论

Enable Privacy Preservation for k-NN Query in Two-tiered Wireless Sensor Networks

Enable Privacy Preservation for k-NN Query in Two-tiered Wir...

引用

IEEE International Conference on Communications

作者： Hui Peng Xiaoying Zhang Hong Chen Yao Wu Juru Zeng Deying Li Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education School of Information Renmin University of China

ISBN: (纸本)9781467364300

Wireless sensor network is an important part of the Internet of Things. Preservation of privacy and integrity in wireless sensor networks is extremely urgent and challenging. To address this problem, we propose PPKN, an efficient and privacy-preserving k-NN query protocol in two-tiered wireless sensor networks. Our proposal prevents adversaries from gaining sensitive information of both queries issued by users and data collected by sensor nodes while allows the sink to verify whether results are valid. It offers confidentiality of queries and data by constructing a special code, provides integrity verification by the correlation among data. Moreover, by the implementation of KNQ query framework, PPKN also achieves high efficient in query response and energy consumption. Finally, the theoretical analysis and experiment results show the high performance of PPKN in terms of privacy preservation and query efficiency.

关键词： Wireless sensor networks Energy consumption data privacy Privacy Protocols Cryptography Storage management

来源：评论

学校读者我要写书评

暂无评论

A hierarchical and dynamic large-scale railway-track modeling solution for high-speed train real-time visual simulation

引用

ICIC Express Letters, Part B: Applications 2016年第12期7卷 2705-2711页

作者： Liu, Shijian Pan, Jeng-Shyang Zou, Zheng Zou, Beiji Liao, Shenghui Shcool of Information Science and Engineering Fujian University of Technology No. 3 Xueyuan Road University Town Minhou Fuzhou350118 China Key Laboratory of Big Data Mining and Applications of Fujian Province Fujian University of Technology No. 3 Xueyuan Road University Town Minhou Fuzhou350118 China The Key Laboratory for Automotive Electronics and Electric Drive of Fujian Province Fujian University of Technology No. 3 Xueyuan Road University Town Minhou Fuzhou350118 China Shcool of Information Science and Engineering Central South University No. 932 South Lushan Road Changsha410083 China

Large-scale railway-track modeling is a key and challenging problem for real- time visual simulation of the high-speed train. The railway-track can generally be described by its central line, whose length and shape vary dramatically between different ones. Therefore, modeling of a large-scale specified railway-track is not a trivial work. A new hierarchical and dynamic modeling framework is proposed to deal with the challenges. Unlike existing top-down approach, this bottom-up solution treats the entire railway-track as the combination of multiple repetitive regularity patterns, namely the elements referred by us. It is an optimized strategy for large model decomposition and is superior in modeling local details. Experiments, including the usage of the proposed method for track assembling and its applications to high-speed train real-time visual simulation, demonstrate the effect and efficiency of our work. Though designed for railway-track modeling, this method can be easily extended to other transportation applications as well. © 2016 ISSN 2185-2766.

关键词： Railroads

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：