检索结果-内蒙古大学图书馆

Group-combined P-values with applications to genetic association studies

BIOINFORMATICS 2016年第18期32卷 2737-2743页

作者： Hu, Xiaonan Zhang, Wei Zhang, Sanguo Ma, Shuangge Li, Qizhai Univ Chinese Acad Sci Sch Math Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Chinese Acad Sci Acad Math & Syst Sci Key Lab Syst & Control Beijing 100190 Peoples R China Yale Univ Dept Biostat New Haven CT USA

Motivation: In large-scale genetic association studies with tens of hundreds of single nucleotide polymorphisms (SNPs) genotyped, the traditional statistical framework of logistic regression using maximumlikelihood estimator (MLE) to infer the odds ratios of SNPsmay notwork appropriately. This is because a large number of odds ratios need to be estimated, and theMLEsmay be not stable when some of the SNPs are in high linkage disequilibrium. Under this situation, the P-value combination procedures seemto provide good alternatives as they are constructed on the basis of single-marker analysis. Results: The commonly used P-value combination methods (such as the Fisher's combined test, the truncated product method, the truncated tail strength and the adaptive rank truncated product) may lose power when the significance level varies across SNPs. To tackle this problem, a group combined P-value method (GCP) is proposed, where the P-values are divided into multiple groups and then are combined at the group level. With this strategy, the significance values are integrated at different levels, and the power is improved. Simulation shows that the GCP can effectively control the type I error rates and have additional power over the existing methods-the power increase can be as high as over 50% under some situations. The proposed GCP method is applied to data from the Genetic Analysis Workshop 16. Among all the methods, only the GCP and ARTP can give the significance to identify a genomic region covering gene DSC3 being associated with rheumatoid arthritis, but the GCP provides smaller P-value.

关键词： SINGLE nucleotide polymorphisms LOGISTIC regression analysis MAXIMUM likelihood statistics ODDS ratio P-value (Statistics) GENETIC markers

来源：评论

学校读者我要写书评

暂无评论

Cross-modal Retrieval by Real label Partial Least Squares 16

Cross-modal Retrieval by Real Label Partial Least Squares

引用

24th ACM Multimedia Conference (MM)

作者： He, Jianfeng Ma, Bingpeng Wang, Shuhui Liu, Yugui Huang, Qingming Univ Chinese Acad Sci Sch Comp & Control Engn Beijing Peoples R China Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China

ISBN: (纸本)9781450336031

This paper proposes a novel method named Real label Partial Least Squares (RL-PLS) for the task of cross -modal retrieval. Pervious works just take the texts and images as two modalities in PLS. But in RL-PLS, considering that the class label is more related to the semantics directly, we take the class label as the assistant modality. Specially, we build two KPLS models and project both images and texts into the label space. Then, the similarity of images and texts can be measured more accurately in the label space. Furthermore, we do not restrict the label indicator values as the binary values as the traditional methods. By contraries, in RL-PLS, the label indicator values are set to the real values. Specially, the label indicator values are comprised by two parts: positive or negative represents the sample class while the absolute value represents the local structure in the class. By this way, the discriminate ability of RL-PLS is improved greatly. To show the effectiveness of RL-PLS, the experiments are conducted on two cross -modal retrieval tasks (Wiki and Pascal Voc2007), on which the competitive results are obtained.

关键词： Cross-modal retrieval multimedia partial least squares images and documents

来源：评论

学校读者我要写书评

暂无评论

Market Value of Innovation: An Empirical Analysis on China's Stock Market

Market Value of Innovation: An Empirical Analysis on China's...

引用

Portland International Conference on management of Engineering and Technology (PICMET)

作者： Zhang Yueyan Li Xianjun Wei Xianhua Meng Xiangying Meng Donghui Tsinghua Univ Dept Automot Engn Beijing Peoples R China Tsinghua Univ State Key Lab Automot Safety & Energy Beijing Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China

ISBN: (纸本)9781509035953

In China, there is growing attention about innovation from both government and industry level, and the authorities also commit and emphasize the support of capital markets to industrial innovation. However, it's not clear whether China's capital markets have positive responses to enterprises innovation input. Such issues have been studied a lot based on US and European database;nevertheless, few researchers investigate the market value of Chinese firms' R&D. In this paper, we use constructed panel dataset from three representative stock markets in China and then use intangible assets increment as innovation input indicator to examine the innovation performance in both manufacturing and service industries. By comparing the results of different stock markets, we find out the effect of R&D investment and increasing R&D input to market value is insignificant in all three markets, which may result from the weak protection for minority investors and loose regulation of information disclosure. Different constructions of intangible assets of listed firms on Main Board Market and Growth Enterprise Market account for market's relatively low efficiency to reflect real value of R&D investment. On industry-level, we conclude that R&D investment in both service and manufacturing sector contributes positively to market performance, and R&D investment in service industry shows stronger and more significant linkage to market value than manufacturing industry.

关键词： Market Value Innovation China''s Stock Market Legal Services Public disclosure of information intangible asset Investments Stock exchanges Technological Innovations REMEDIAL DESIGN Markets Manufacturing industry

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

The Performance Analysis of Real Estate Listed Firms Based o...

引用

4th International Conference on Information Technology and Quantitative management (ITQM) - Promoting Business Analytics and Quantitative management of Technology

作者： Cheng Qing Liu Xinyuan Sun Yi Guo Kun China Univ Polit Sci & Law Beijing 102249 Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 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

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. (C) 2016 Published by Elsevier B.V.

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

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 & Expo (ICME)

作者： Wu, Zhe Su, Li Huang, Qingming Wu, Bo Li, Jian Li, Guorong Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China Inst Comp Technol Key Lab Intelligent Informat Proc Beijing Peoples R China Capital Med Univ Beijing Peoples R China Beijing Univ Posts & Telecommun Beijing Peoples R China

ISBN: (纸本)9781467372589

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： video saliency optical flow temporal superpixel gravity center

来源：评论

学校读者我要写书评

暂无评论

Structural nonparallel support vector machine for pattern recognition

引用

PATTERN RECOGNITION 2016年 60卷 296-305页

作者： Chen, Dandan Tian, Yingjie Liu, Xiaohui Univ Chinese Acad Sci Coll Math Sci Beijing 100049 Peoples R China Chinese Acad Sci Res Ctr Fictit Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Brunel Univ London Dept Comp Sci Uxbridge UB8 3PH Middx England

It has been widely accepted that the underlying structural information in the training data within classes is significant for a good classifier in real-world problems. However, existing structural classifiers do not balance structural information's relationships both intra-class and inter-class. Combining the structural information with nonparallel support vector machine (NPSVM), we design a new structural nonparallel support vector machine (called SNPSVM). Each model of SNPSVM considers not only the compactness in both classes by the structural information but also the separability between classes, thus it can fully exploit prior knowledge to directly improve the algorithm's generalization capacity. Furthermore, we apply the improved alternating direction method of multipliers (ADMM) to SNPSVM. Both our model itself and the solving algorithm can guarantee that it can deal with large-scale classification problems with a huge number of instances as well as features. Experimental results show that SNPSVM is superior to the other current algorithms based on structural information of data in both computation time and classification accuracy. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Structural information Nonparallel support vector machine Alternating direction method of multipliers Pattern recognition

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

Research on the Classification of Commercial Banks' Fund Cli...

引用

4th International Conference on Information Technology and Quantitative management (ITQM) - Promoting Business Analytics and Quantitative management of Technology

作者： Ma, Fuhai Shi, Yong Wang, Bo Chen, Zhensong Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Sch Management Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big DataMin & Knowledge Management Beijing 100190 Peoples R China Univ Nebraska Omaha NE 68106 USA

Due tothe problem of privacy protection and other issues in reality, we cannot get the specific label of commercial banks' fund client, which indicates whether each individualis an important clientor 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, byusing Inverse Calibration algorithm to identify important commercial banks' fund clients. The model shows promising results withhigh accuracy and goodstability. The research is practical in solving privacy-preservingdata analysis problems that cannot be processedwith traditional method. (C) 2016 Published by Elsevier B.V.

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

The Regime Characteristics of Chinese Stock Market Industry Sectors

引用

Procedia Computer Science 2016年 91卷 512-518页

作者： Jiangjian Shen Wen Long CAS Research Center On Ficititious Economy & Data Science BeiJing 100190 Chian School of Economics and Management UCAS BeiJing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences BeiJing 100190 China

This article uses Markov regime Switching ARCH (SWARCH) model to research the volatility of Chinese stock market industry sectors, finding that all industry sectors were able to be significantly divided into two regimes, the high volatility regime and the low volatility regime. For different regime transfer, we can classify all sectors into three categories. Further the article analyzes the regime characteristics of industry sectors. The results show that the correlation coefficient in high volatility regime is higher than that in low volatility regime.

关键词： Industry sectors High volatility regime Low volatility regime Correlation

来源：评论

学校读者我要写书评

暂无评论

On linear conic relaxation of discrete quadratic programs

引用

OPTIMIZATION METHODS & SOFTWARE 2016年第4期31卷 737-754页

作者： Nie, Tiantian Fang, Shu-Cherng Deng, Zhibin Lavery, John E. N Carolina State Univ Edward P Fitts Dept Ind & Syst Engn Raleigh NC 27695 USA Univ Chinese Acad Sci Sch Management Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Army Res Lab Div Mat Sci Army Res Off Durham NC 27709 USA Army Res Lab Div Comp Sci Army Res Off Durham NC 27709 USA

A special reformulation-linearization technique based linear conic relaxation is proposed for discrete quadratic programming (DQP). We show that the proposed relaxation is tighter than the traditional positive semidefinite programming relaxation. More importantly, when the proposed relaxation problem has an optimal solution with rank one or two, optimal solutions to the original DQP problem can be explicitly generated. This rank-two property is further extended to binary quadratic optimization problems and linearly constrained DQP problems. Numerical results indicate that the proposed relaxation is capable of providing high quality and robust lower bounds for DQP.

关键词： discrete quadratic program linear conic relaxation RLT method

来源：评论

学校读者我要写书评

暂无评论

The Econometric Study on Effects of Chinese Economic Growth of Human Capital

The Econometric Study on Effects of Chinese Economic Growth ...

引用

4th International Conference on Information Technology and Quantitative management (ITQM) - Promoting Business Analytics and Quantitative management of Technology

作者： Chang, Xianyu Shi, Yong Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big DataMining & Knowledge Management Beijing 100190 Peoples R China Univ Nebraska Omaha Omaha NE 68182 USA China Huarong Asset Management CO LTD Beijing 100033 Peoples R China

In the case of population dividend which tends to disappear, to choose a new driving force of economic growth has become essential. In this "new normal" economy, in essence, the supply-side reform is to optimize the allocative capital, labor and land. Raising human capital may be the source of economic growth in the new situation. In academia today, there is consensus that human capital is an important driver of economic growth, but how human capital promotes economic growth mechanism remains controversial. This paper discusses mechanism and classification of heterogeneous effects of human capital on economic growth, on which hypothesis is based. It uses demographic data from the country's 30 provinces and autonomous regions to analyze and verify this. The last comprehensive actual situation in China is concluded. (C) 2016 Published by Elsevier B.V.

关键词： human capital heterogeneity spillover effects panel data spatial econometric model

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：