检索结果-内蒙古大学图书馆

2015 International Conference on Software, Multimedia and Communication Engineering(SMCE 2015)

作者： Yun GE Yan-feng SUN Xing-lin PIAO Bao-cai YIN Beijing Key Laboratory of Multimedia and Intelligent Software Technology College of Metropolitan Transportation Beijing University of Technology Computer Science and Application Center China Youth University for Political Science

Disturbed by the external environment, the depth map obtained by consumer RGB-D equipment usually has the problem of low-resolution, noisy and miss values as some pixels. In order to enhance the quality of depth map, we proposed an efficient method to enhance the quality based on total variation model. To achieve high quality image enhancement, we infliction the color information derived from color image and smoothness constrain to guide the enhance work. The experiment results show that the proposed method can get high quality enhance result.

关键词： Total variation Depth map Depth enhancement

来源：评论

学校读者我要写书评

暂无评论

An improved method for exon array data analysis

引用

Chemical Engineering Transactions 2015年 46卷 379-384页

作者： Jin, Shenghua School of Computer Engineering Huaiyin Institute of Technology Huaian Jiangsu China Huaian Key Laboratory of the Study and Application of Internet of Things Huaian Jiangsu China Jiangsu Internet of Things Mobile Internet Technology Engineering Laboratory Huaian Jiangsu223003 China

ISBN: (纸本)9788895608372

Alternative splicing of genes is usually induced by some severe diseases. Exon array manufactured by Affymetrix Company has been widely used to detect alternative splicing. Utilizing the mapping between the gray values of splice isoforms and the array probes, we proposed the calculation of gene expression level based on Kseq model. Aiming at the massive amount of array data, an algorithm for parallel computation using multi-core processor was presented. The algorithm was verified through experiments using real datasets and compared with the commonly used algorithm. It was found that parallel computation improved the computation efficiency of the model and the new model enhanced the computation accuracy in subsequent bioanalysis. Copyright © 2015, AIDIC Servizi S.r.l.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Context-aware computing for smart home environment

引用

Journal of Computational Information Systems 2015年第15期11卷 5453-5460页

作者： Liu, Li Fu, Xiaodong Liu, Lijun Huang, Qingsong Yunnan Provincial Key Laboratory of Computer Technology Application Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China State-Province Joint Laboratory of Digital Home Interactive Applications School of Information Science & Technology Sun Yat-sen University Guangzhou China

Context-aware computing has proven to be successful in collecting and understanding various sensor data. However, providing an intelligent service by exploiting the collected context data from heterogeneous sensors is difficult on smart home because it is a complex environment with various devices and appliances. In this paper, we propose a context-aware computing approach for heterogeneous smart home environments. The key idea in this work is to integrate large-scale home context information from multiple heterogeneous sensors. We first define a semantic decision by context-aware inference including rule, inference and pattern driven. Then, a designed architecture that manages home environment is developed between large numbers of heterogeneous information entities and enhances intelligence abilities. Using the established rules and inferences, the proposed method is applicable for intelligent home to further discover more useful representative activities and personalized services with inhabitant needs. Experimental results show the effectiveness of our proposed method. Copyright © 2015 Binary Information Press.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Evolution of isolated G-band bright points: size, intensity and velocity

引用

Research in Astronomy and Astrophysics 2014年第6期14卷 741-752页

作者： Yun-Fei Yang Jia-Ben Lin Song Feng Kai-Fan Ji Hui Deng Feng Wang Faculty of Information Engineering and Automation/Yunnan Key Laboratory of Computer Technology Application Kunming University of Science and Technology Key Laboratory of Solar Activity National Astronomical Observatories Chinese Academy of Sciences Key Laboratory of Modern Astronomy and Astrophysics Nanjing University Ministry of Education

We study the evolution pattern of isolated G-band bright points （GBPs） in terms of their size, intensity and velocity. Using a high resolution image sequence taken with the Hinode/Solar Optical Telescope （SOT）, we detect GBPs in each image by the Laplacian and Morphological Dilation algorithm, and track their evolutions by a 26-adjacent method in a three-dimensional space-time cube. For quantifying the evolution, we propose a quantification method based on lifetime normalization which aligns the different lifetimes to common stages. The quantification results show that, on average, the diameter of isolated GBPs changes from 166 to 173 km, then down to 165 km; the maximum intensity contrast changes from 1.012 to 1.027, then down to 1.011; however, the velocity changes from 1.709 to 1.593 km s-1, then up to 1.703 km s-i. The results indicate that the evolution follows a pattern such that the GBP is small, faint and fast-moving at the birth stage, becomes big, bright and slow-moving at the middle stage, then gets small, faint and fast-moving at the decay stage until disappearance. Although the differences are very small, a two-sample t-test is used to demonstrate there are significant differences in means between the distri- butions of the different stages. Furthermore, we quantify the relationship between the lifetimes of GBPs and their properties. It is found that there are positive correlations between the lifetimes and their sizes and intensities with correlation coefficients of 0.83 and 0.65, respectively; however, there is a negative correlation between the life- times and velocities with a correlation coefficient of-0.49. In summary, the longer the GBP persists, the bigger, brighter and slower it will be.

关键词： techniques： image processing -- Sun： photosphere -- methods： dataanalysis -- methods： statistical

来源：评论

学校读者我要写书评

暂无评论

Axiom vis: An axiom-oriented ontology visualization tool

Communications in Computer and Information Science

引用

Communications in computer and Information Science 2014年 480卷 156-166页

作者： Zhou, Jian Wang, Xin Feng, Zhiyong School of Computer Science and Technology Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China

With the continuous growth of ontologies in size, the amount of ontology axioms is steadily increasing. To help users understand ontologies with a large number of axioms, we devise a novel ontology visualization tool, called AxiomVis, which defines a mapping from DL axioms to the directed acyclic graph (DAG). We give a recursive procedure to generate the target DAG and then propose a new axiom-aware layout algorithm to display the DAG elements using the characteristics of the expression tree. The distinguishing feature of our tool is that it visualizes ontologies from the axiom viewpoint. This paper demonstrates comparison of different layouts, which exhibits the advantages of our layout on ontology visualization. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Recommendation of programming problems in online judge platform: an experimental research

引用

Journal of Computational Information Systems 2015年第20期11卷 7263-7270页

作者： Yu, Ruiguo Li, Yongxing Cai, Zhiyong Dong, Xuyuan He, Muwen Chang, Peng Wang, Zan School of Computer Science and Technology Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Information and Network Center Tianjin University Tianjin China School of Computer and Software Tianjin University Tianjin China

The explosive growth of the internet and the emergence of e-commerce have given rise to the fast development of recommendation algorithms-a kind of personalized information collection technology used to gather a set of items that meet the interest of a certain amount of persons. Recommendation systems based on collaborative filtering algorithms are one of the most widely adopted and successful online recommendation services. However, the successful operation of every online recommendation service in a particular application field requires careful experimental research and parameterization before their actual running. Our work in this paper is an experimental research of programming problems recommendation in online judge platform for further establishment of a programming problems recommendation system. In this study, we analyze the performance of collaborative filtering recommendation algorithms on data set of online judge platform. Moreover, different similarity calculation methods and cluster-based data smoothing technique are also evaluated in our research to determine whether they are suitable for programming problems recommendation. Copyright © 2015 Binary Information Press.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Lable-based hybrid recommendation algorithm: Implementation and analysis

引用

Journal of Information and Computational Science 2015年第6期12卷 2221-2228页

作者： Yu, Ruiguo Mao, Hongyue Wang, Zan Zhang, Minjie Yuan, Zhenxia He, Muwen Chang, Peng School of Computer Science and Technology Tianjin University Tianjin China School of Computer and Software Tianjin University Tianjin China Information and Network Center Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China

Recommendation system, as an information filtering method, has been widely applied and the hybrid recommendation algorithm is by far the most commonly used technique. But in the field of online learning system, recommendation system is not mature enough. In this paper, we analyzed the Tianjin University Online Judge, established a model to apply the recommendation algorithm to it, and then proposed a label-based hybrid recommendation algorithm which is applicable to the system. Also, by conducting experiments on real users' data of Tianjin University Online Judge System, we evaluated our algorithm and obtained good results. Copyright © 2015 Binary Information Press.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Research on personalized recommendation algorithm based on user’s attention behavior

引用

ICIC Express Letters 2016年第11期10卷 2615-2622页

作者： Yu, Mei Di, Haibo Hou, Dejun Ma, Huijuan Pei, Yingjie Li, Zengjie Tianjin Key Laboratory of Cognitive Computing and Application No. 92 Weijin Road Nankai Dist Tianjin300072 China School of Computer Science and Technology Management Tianjin University No. 92 Weijin Road Nankai Dist Tianjin300072 China School of Computer Software Management Tianjin University No. 92 Weijin Road Nankai Dist Tianjin300072 China Office of State-Owned Assets and Equipment Management Tianjin University No. 92 Weijin Road Nankai Dist Tianjin300072 China Karamay Power Supply Company Xinjiang Oilfield Company Petro China Karamay834000 China The Thermal Power Plant of Dushanzi Petrochemical Company Karamay833699 China

Nowadays, how to deal with mass data and to perform personalized recommendation for users has become a research hotspot. Collaborative filtering recommendation algorithm has been widely used since it was proposed. However, there is still more room for improvement in the computation of similarity. This paper introduces user’s attention behavior on the basis of the traditional homogeneity measure, and puts forward a personalized recommendation algorithm based on user’s attention behavior which combines with the low rank matrix factorization technique to improve the accuracy of the predictions. We named the algorithm pTrust. Through contrast experiments on a public dataset, the pTrust algorithm shows better effectiveness both on accuracy and time complexity in the trust network. © 2016 ICIC International.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

3D garment segmentation based on semi-supervised learning method

引用

Journal of Fiber Bioengineering and Informatics 2015年第4期8卷 657-665页

作者： Huang, Mian Liu, Li Liu, Ruomei Fu, Xiaodong Liu, Lijun Yunnan Provincial Key Laboratory of Computer Technology Application Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China National Engineering Research Center of Digital Life State-Province Joint Laboratory of Digital Home Interactive Applications School of Data and Computer Science Sun Yat-sen University Guangzhou China

In this paper, we propose a semi-supervised learning method to simultaneous segmentation and labeling of parts in 3D garments. The key idea in this work is to analyze 3D garments using semi-supervised learning method which can label parts in various 3D garments. We first develop an objective function based on Conditional Random Field (CRF) model to learn the prior knowledge of garment components from a set of training examples. Then, we exploit an effective training method that utilizes JointBoost classifiers based on the co-analysis for garments. And we modify the JointBoost to automatically cluster the segmented components without requiring manual parameter tuning. The purpose of our method is to relieve the manual segmentation and labeling of components in 3D garment collections. Finally, the experimental results show the performance of our proposed method is effective. © 2015 Binary Information Press & Textile Bioengineering and Informatics Society December 2015.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

A survey of major techniques of clothing in vision

引用

Journal of Fiber Bioengineering and Informatics 2015年第4期8卷 725-732页

作者： Huang, Dongyan Liu, Li Fu, Xiaodong Liu, Lijun Huang, Qingsong Yunnan Provincial Key Laboratory of Computer Technology Application Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China National Engineering Research Center of Digital Life State-Province Joint Laboratory of Digital Home Interactive Applications School of Data and Computer Science Sun Yat-sen University Guangzhou China

Clothing in vision plays an important role in many applications of digital clothing, virtual fitting, fashion design and manufacturing. The research of clothing in vision is full of technical challenges, such as background detection and features extraction. In this paper, we introduce the latest remarkable works of clothing in vision area, including clothing segmentation, clothing recognition and clothing retrieval. There are many remarkable advances on the basis of the predecessors' achievements in the three fields. Firstly, we provide an overview of the techniques for clothing segmentation and clothing recognition. Then, we introduce and analyze the representative works on clothing retrieval. Finally, we forecast broader application prospect and future research work of clothing in vision. © 2015 Binary Information Press & Textile Bioengineering and Informatics Society December 2015.

关键词： Textiles

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：