检索结果-内蒙古大学图书馆

Exploring big data Analysis: Fundamental Scientific Problems

Annals of data Science 2015年第4期2卷 363-372页

作者： Xu, Zongben Shi, Yong Department of Mathematics Xi’an Jiaotong University Xi’an China The Key Research Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

Although big data has been one of most popular topics since last several years, how to effectively conduct big data analysis is a big challenge for every field. This paper tries to address some fundamental scientific problems in big data analysis, such as opportunities, challenges, and difficulties encountered in the analysis. The challenges rise from multiple domains that include how management Science influences data acquisition and data management, Information Science for data access and processing, Mathematics and Statistics for data understanding and Engineering for data applications. The paper outlines six open research problems on big data. It also reports some advances on current big data research, particularly in high-dimensional data and non-structured data processing. Finally, remarks on how to develop a big data algorithm are provided. © 2016, Springer-Verlag Berlin Heidelberg.

关键词： big data

来源：评论

学校读者我要写书评

暂无评论

ROBUST LATENT POISSON DECONVOLUTION FROM MULTIPLE IMPERFECT FEATURES FOR WEB TOPIC DETECTION

ROBUST LATENT POISSON DECONVOLUTION FROM MULTIPLE IMPERFECT ...

引用

IEEE International Conference on Multimedia & Expo (ICME)

作者： Tao, Fei Pang, Junbiao Zhang, Chunjie Li, Liang Su, Li Zhang, Weigang Huang, Qingming Su, Guiping Univ Chinese Acad Sci Sch Comp & Control Engn Beijing Peoples R China Beijing Univ Technol Coll Metropolitan Transportat Beijing Key Lab Multimedia & Intelligent Software Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin Peoples R China

ISBN: (纸本)9781467372589

In web topic detection, detecting "hot" topics from enormous User- Generated Content (UGC) on web data poses two main difficulties that conventional approaches can barely handle: 1) poor feature representations from noisy images and short texts;and 2) uncertain roles of modalities where visual content is either highly or weakly relevant to textual cues due to less-constrained data. In this paper, following the detection by ranking approach, we address the problem by learning a robust shared representation from multiple, noisy and complementary features, and integrating both textual and visual graphs into a k-NearestNeighbor Similarity Graph (k-N(2)SG). Then Non-negative Matrix Factorization using Random walk (NMFR) is introduced to generate topic candidates. An efficient fusion of multiple graphs is then done by a Latent Poisson Deconvolution (LPD) which consists of a poisson deconvolution with sparse basis similarities for each edge. Experiments show significantly improved accuracy of the proposed approach in comparison with the state-of-the-art methods on two public data sets.

关键词： Similarity Cascade Latent Poisson Deconvolution Multi-view Learning Topic Detection Cross Media

来源：评论

学校读者我要写书评

暂无评论

A Survey on Feature Selection

引用

Procedia Computer Science 2016年 91卷 919-926页

作者： Jianyu Miao Lingfeng Niu School of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100019 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China

Feature selection, as a dimensionality reduction technique, aims to choosing a small subset of the relevant features from the original features by removing irrelevant, redundant or noisy features. Feature selection usually can lead to better learning performance, i.e., higher learning accuracy, lower computational cost, and better model interpretability. Recently, researchers from computer vision, text mining and so on have proposed a variety of feature selection algorithms and in terms of theory and experiment, show the effectiveness of their works. This paper is aimed at reviewing the state of the art on these techniques. Furthermore, a thorough experiment is conducted to check if the use of feature selection can improve the performance of learning, considering some of the approaches mentioned in the literature. The experimental results show that unsupervised feature selection algorithms benefits machine learning tasks improving the performance of clustering.

关键词： feature selection machine learning unsupervised clustering

来源：评论

学校读者我要写书评

暂无评论

Regional Science and Technology Resource Allocation Optimization Based on Improved Genetic Algorithm

引用

KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS 2017年第4期11卷 1972-1986页

作者： Xu, Hao Xing, Lining Huang, Lan Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China Jilin Univ Zhuhai Coll Dept Comp Sci & TechnolMinist Educ Zhuhai Lab Key Lab Symbol Computat & Knowledge En Zhuhai 519041 Peoples R China Foshan Univ Sch Math & Big Data Foshan 528000 Peoples R China Shanghai Polytechn Univ Coll Engn Shanghai 201209 Peoples R China Natl Univ Def Technol Coll Informat Syst & Management Changsha 410073 Hunan Peoples R China Jilin Univ Minist Educ Changchun 130012 Peoples R China

With the advent of the knowledge economy, science and technology resources have played an important role in economic competition, and their optimal allocation has been regarded as very important across the world. Thus, allocation optimization research for regional science and technology resources is significant for accelerating the reform of regional science and technology systems. Regional science and technology resource allocation optimization is modeled as a double-layer optimization model: the entire system is characterized by top-layer optimization, whereas the subsystems are characterized by bottom-layer optimization. To efficaciously solve this optimization problem, we propose a mixed search method based on the orthogonal genetic algorithm and sensitivity analysis. This novel method adopts the integrated modeling concept with a combination of the knowledge model and heuristic search model, on the basis of the heuristic search model, and simultaneously highlights the effect of the knowledge model. To compare the performance of different methods, five methods and two channels were used to address an application example. Both the optimized results and simulation time of the proposed method outperformed those of the other methods. The application of the proposed method to solve the problem of entire system optimization is feasible, correct, and effective.

关键词： Regional science and technology resource allocation optimization genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on the Classification of Commercial Banks’ Fund Clients Based on Learning with label Proportions

引用

Procedia Computer Science 2016年 91卷 988-994页

作者： Fuhai Ma Yong Shi Bo Wang Zhensong Chen Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China School of Management Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of SciencesBeijing100190 China University of Nebraska Omaha Omaha NE 68106 USA

Due to the problem of privacy protection and other issues in reality, we cannot get the specific label of commercial banks’ fund client, which indicates whether each individual is an important client or not, but merely knows the proportion of certain type of clients. In this paper, a novel method, called learning with label proportions (LLP), is applied, by using Inverse Calibration algorithm to identify important commercial banks’ fund clients. The model shows promising results with high accuracy and good stability. The research is practical in solving privacy-preserving data analysis problems that cannot be processed with traditional method.

关键词： Learning with label proportions Inverse Calibration Important client identification

来源：评论

学校读者我要写书评

暂无评论

Genre-based Link Prediction in Bipartite Graph for Music Recommendation

引用

Procedia Computer Science 2016年 91卷 959-965页

作者： Daozhen Zhao Lingling Zhang Weiqi Zhao School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences BeiJing 100190 China

The bipartite graph method of link prediction can apply in many fields of recommendations, with the nodes (users and items) and links (interactions between users and items). However, that links cannot represent the users’ dual preferences (like and dislike). Some researchers improved that limits by complex number representations, but still not consider the influence of users’ similarity recommendation performance. Here, we proposed an improved method to cope with this deficiency, build the relational dualities by complex number representations and computing the users’ similarity by genres weight relations. In experiments with the *** music dataset, the proposed music genre weight-based music recommendation model (MGW) performances better than the CORLP method.

关键词： Music recommendation Link prediction Music genres

来源：评论

学校读者我要写书评

暂无评论

Ramp loss least squares support vector machine

引用

JOURNAL OF COMPUTATIONAL SCIENCE 2016年 14卷 61-68页

作者： Liu, Dalian Shi, Yong Tian, Yingjie Huang, Xiankai Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100044 Peoples R China Beijing Union Univ Dept Basic Course Teaching Beijing 100101 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Univ Nebraska Coll Informat Sci & Technol Omaha NE 68182 USA Beijing Union Univ Tourism Inst Beijing 100101 Peoples R China

In this paper, we propose a novel sparse least squares support vector machine, named ramp loss least squares support vector machine (RLSSVM), for binary classification. By introducing a non-convex and non-differentiable loss function based on the 8-insensitive loss function, RLSSVM has several improved advantages compared with the plain LSSVM: firstly, it has the sparseness which is controlled by the ramp loss, leading to its better scaling properties;secondly, it can explicitly incorporate noise and outlier suppression in the training process, and thirdly, the non-convexity of RLSSVM can be efficiently solved by the Concave-Convex Procedure (CCCP). Experimental results on several benchmark datasets show the effectiveness of our method. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Least squares support vector machine Sparse Ramp loss CCCP Classification

来源：评论

学校读者我要写书评

暂无评论

Video saliency prediction with optimized optical flow and gravity center bias

Video saliency prediction with optimized optical flow and gr...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zhe Wu Li Su Qingming Huang Bo Wu Jian Li Guorong Li Key Lab on Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology Beijing China Capital Medical University Beijing China Beijing University of Posts and Telecommunications China Beijing

ISBN: (纸本)9781467372596

Dynamic videos are viewed fundamentally different from static images. Besides spatial features, motion feature also plays an important role as a temporal factor. Most existing video saliency models usually employ optical flow to represent the motion feature. However, optical flow often suffers from the discontinuity problem. And we also notice that human fixations in one single video frame are much sparser than that in an identical still picture. However, many spatial saliency models take each video frame as static image independently. In this paper, we predict the dynamic visual saliency by fusing spatial and temporal features. In order to construct the temporal relationships among a set of successive frames, we introduce a smoothness operator in optical flow field to obtain more accurate motion feature. Then, considering the sparse property of video saliency, we adapt the weights of the regions surrounding to the saliency gravity center in the final maps. The experiments show that our model is more consistent with humans eye-tracking benchmarks than the state-of-the-art models.

关键词： Optical imaging Gravity Computational modeling Visualization Biomedical optical imaging Adaptation models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Parameters Optimization for Nonparallel Support Vector Machine by Particle Swarm Optimization

引用

Procedia Computer Science 2016年 91卷 482-491页

作者： Seyed Mojtaba Hosseini Bamakan Huadong Wang Ahad Zare Ravasan Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing 100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Research center on fictitious economy and data science Chinese Academy of Sciences Beijing 100190 China Department of Industrial Management Allameh Tabataba’i University Tehran Iran

Support vector machine is a well-known and computationally powerful machine learning technique for pattern classification and regression problems, which has been successfully applied to solve many practical problems in a wide variety of fields. Nonparallel Support Vector Machine (NPSVM) which is an extension of Twin-SVMs, is proved to be theoretically and practically more flexible and superior than TWSVMs and also it overcomes several drawbacks of the existing typical SVMs in order to be applicable in large-scale data sets. However, one of the difficulties in successful implementation of NPSVM is its different parameters, which should be well adjusted during the training process. In fact, the generalization power, robustness and sparsity of NPSVM are extremely depended on well setting of its parameters. In this paper, we propose a hybrid approach for parameter determination of the NPSVM by Particle Swarm Optimization techniques. Furthermore, in order to increase the sparsity of NPSVM and to reduce the training time, we take into account the number of support vectors (SVs) along with classification accuracy as a weighted objective function. Our experiments on several public datasets show that the proposed method can achieve better classification accuracy compare to that of TWSVM and NPSVM with less computational time.

关键词： Nonparallel Support Vector Machine Particle Swarm Optimization Twin SVM Parameter setting

来源：评论

学校读者我要写书评

暂无评论

The Performance Analysis of Real Estate Listed Firms Based on the Sliding Time Window

引用

Procedia Computer Science 2016年 91卷 1038-1043页

作者： Cheng Qing Liu Xinyuan Sun Yi Guo Kun China University of Political Science and Law Beijing 102249 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China

Capital structure and operating capacity exert significant influence on firm's performance. According to the literature, the influence diverges from different business cycle. Based on a sample of real estate listed companies form 2004-2014, this paper dynamically investigates the different influence of capital structure and operating capacity on firm performance in a 3-year sling time window. The study found that there exists the Scale Economies Effect. After the economic crisis, the inventory turnover in days, representing the operation capacity, influence the performance greatly. While the capital structure influences the performance negatively though out the whole time period and the financing structure consistent with The Pecking Order Theory. This conclusion shows that the real estate listed firms are gradually returning to a more rational way.

关键词： real estate firm performance capital structure operation capacity sliding time window

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：