检索结果-内蒙古大学图书馆

9th International Conference on Information, Communications and Signal Processing, ICICS 2013

作者： Ge, Yongxin Bu, Wenbin Yang, Dan Feng, Xin Zhang, Xiaohong Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education Chongqing 400044 China School of Software Engineering Chongqing University Chongqing 400044 China College of Mathematics and Statistics Chongqing University Chongqing 400044 China College of Computer Science and Technology Chongqing University of Technology Chongqing 400044 China

ISBN: (纸本)9781479904341

For benefiting from incorporating the class information, partial least squares (PLS) and its two dimension version (2DPLS) have been widely employed in face recognition when extracting principal components. However, currently popular statistic methods, such as principal component analysis (PCA) and linear discriminant analysis (LDA), only learn holistic, not parts-based, representations which ignore available local features for face recognition. In this paper, we propose a novel approach to extract the facial features called two dimension nonnegative partial least squares (2DNPLS).Our approach can grab the local features via adding non-negativity constraint to the 2DPLS, and can also reserve the advantages of 2DPLS, which are both inherent structure and class information of images. For evaluating our approach's performance, a series of experiments were conducted on two famous face image databases include ORL and Yale face databases, which demonstrate that our proposed approach outperforms the compared state-of-art algorithms. © 2013 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Goal-based Framework for cold-start problem using multi-user personalized similarities in e-Learning scenarios

Goal-based Framework for cold-start problem using multi-user...

引用

International Conference on e-Learning and e-Technologies in Education (ICEEE)

作者： M. Waseem Chughtai Imran Ghani Ali Semalat Seung Ryul Jeong Software Engineering Department Faulty of Computing Universiti Teknologi Malaysia Skudai Johor Malaysia School of Business IT Seongbuk Gu Kookmin Univerity Seoul South Korea

This article presents the Goal-based Framework for providing personalized similarities between multi users profile preferences in formal e-Learning scenarios. It consists of two main approaches: content-based filtering and collaborative filtering because only traditional content-based filtering is not sufficient to generate the recommendations for new-users / learners. Therefore, the proposed work hybridized multi users collaborative filtering functionalities with personalized content-based profile preferences filtering. The main purpose of this proposed work is to (a) overcome the user-based cold-start profile recommendations and (b) improve the recommendations accuracy for new-users in formal e-learning recommendation systems. The experimental results of proposed Goal-based framework are tackled by using famous `MovieLens' dataset while the evaluation of experimental results have been performed with precision mean and recall mean to test the effectiveness of goal-based recommendation framework. Experimental results (precision mean: 76.284% and recall mean: 82.413%) show that the proposed framework goals performed well for the improvement of user-based cold-start issue as well as for content-based profile recommendations, using multi users personalized collaborative similarities, in formal e-Learning scenarios effectively.

关键词： Recommender systems Collaboration Electronic learning Accuracy Training

来源：评论

学校读者我要写书评

暂无评论

Optimization for reliable erasure-coded storage allocation under multiple constraints

Optimization for reliable erasure-coded storage allocation u...

引用

IEEE International Conference on Performance, computing and Communications (IPCCC)

作者： Guangping Xu Xing Guo Hua Zhang Sheng Lin Chunxia Yang Computer and Communication Engineering School Tianjin University of Technology Tianjin China Tianjin Key Lab. of Intelligence Computing and New Software Technology Tianjin China

ISBN: (纸本)9781479932153

To maximize the reliability of erasure coded objects in cloud storage, the optimal allocation is a challenging problem constrained with the node heterogeneities and erasure coding budgets. We model the optimal problem from a combinatorial view under multiple constraints and propose an efficient search algorithm to find the most reliable allocation. The experiments are evaluated and analyzed including the optimal reliability, redundancy reduction and allocation pattern.

关键词： Peer-to-peer computing Resource management Encoding Redundancy Availability Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Detecting Flu Transmission by Social Sensor in China

Detecting Flu Transmission by Social Sensor in China

引用

IEEE/ACM Int'l Conference on & Int'l Conference on Cyber, Physical and Social computing (CPSCom) Green computing and Communications (GreenCom)

作者： Jiangmiao Huang Hui Zhao Jie Zhang Software Engineering Institute East China Normal University Shanghai China Key Laboratory of Trustworthy Computing of Shanghai East China Normal University Shanghai China

ISBN: (纸本)9781479906314

The control and prevention of transmissible diseases is an important public health concern. This paper gives a strategy to detect the transmission of contagion based on social network. With the popularity of the Weibo, a hybrid of Twitter and Facebook in China, people often posts his/her feelings when he/she or his/her friend suffers from disease. Thus, Weibo plays a social sensor role to surveill people's health status. By exploring more than 35.3 million tweets from Sina Weibo, we first filter the data according to the ILI (Influenza like Illness ) definition and compare the online social network data with the statistics summery of China CDC (Center of Disease Control and Prevention) using cosine similarity and the standard deviation metrics. Dynamic Bayesian Network is applied to detect the outbreak and transmission of influenza in a certain city considering the co-location and the social ties. The experiment results show our methods can give effective suggestions to control and prevent the influenza epidemic in China.

关键词： Cities and towns Social network services Diseases Standards Bayes methods Hidden Markov models Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Presentation design of e-assessments for blind users using touch screen devices

Presentation design of e-assessments for blind users using t...

引用

International Conference on Electronics, Computers and Artificial Intelligence (ECAI)

作者： Mohammed Fakrudeen Sufian Yousef Abdelrahman H. Hussein Maaruf Ali Department of Computing and Technology Anglia Ruskin University Chelmsford UK College of Computer Sciences & Software Engineering University of Ha'il Ha'il Saudi Arabia

The Web Content Accessibility Guidelines (WCAG) have been used by web developers to develop accessible web pages. However, touch screen accessibility varies with web site accessibility. This research is dedicated to the improvement of accessibility of e-assessment in mobile touch screen for blind users. We chose IMS' Question and Test Interoperability specification (QTI) as a basis to generate the components of the e-assessment. We then extended the components to derive the Accessibility and Usability features Guidelines (AUG) using the WCAG. Specifically, we designed a prototype according to the derived AUG to check the accessibility for blind users. We analysed the results and found that the performance of the prototype is promising.

关键词： Usability Presses Prototypes Smart phones Guidelines Thumb Materials

来源：评论

学校读者我要写书评

暂无评论

Continuous ranking on uncertain streams

引用

Frontiers of Computer Science 2012年第6期6卷 686-699页

作者： Cheqing JIN Jingwei ZHANG Aoying ZHOU Shanghai Key Laboratory of Trustworthy Computing Software Engineering InstituteEast China Normal UniversityShanghai 200062China

Data uncertainty widely exists in many web applications, financial applications and sensor networks. Ranking queries that return a number of tuples with maximal ranking scores are important in the field of database management. Most existing work focuses on proposing static solutions for various ranking semantics over uncertain data. Our focus is to handle continuous ranking queries on uncertain data streams： testing each new tuple to output highly-ranked tuples. The main challenge comes from not only the fact that the possible world space will grow exponentially when new tuples arrive, but also the requirement for low space- and time- complexity to adapt to the streaming environments. This paper aims at handling continuous ranking queries on uncertain data streams. We first study how to handle this issue exactly, then we propose a novel method （exponential sampling） to estimate the expected rank of a tuple with high quality. Analysis in theory and detailed experimental reports evaluate the proposed methods.

关键词： possible world semantics uncertain data stream continuous ranking query sampling

来源：评论

学校读者我要写书评

暂无评论

eXRUP: A Hybrid software Development Model for Small to Medium Scale Projects

引用

Journal of software engineering and Applications 2013年第9期6卷 446-457页

作者： Ghulam Rasool Shabib Aftab Shafiq Hussain Detlef Streitferdt Department of Computer Science COMSATS Institute of Information Technology Lahore Pakistan Department of Engineering Computing and Technology University of Sunderland Sunderland UK Software Architectures and Product Lines Group The Ilmenau University of Technology Ilmenau Germany

The conventional and agile software development process models are proposed and used nowadays in software industry to meet emergent requirements of the customers. Conventional software development models such as Waterfall, V model and RUP have been predominant in industry until mid 1990s, but these models are mainly focused on extensive planning, heavy documentation and team expertise which suit only to medium and large scale projects. The Rational Unified Process is one of the widely used conventional models. Agile process models got attention of the software industry in last decade due to limitations of conventional models such as slow adaptation to rapidly changing business requirements and they overcome problems of schedule and cost. Extreme Programming is one of the most useful agile methods that provide best engineering practices for a good quality product at small scale. XP follows the iterative and incremental approach, but its key focus is on programming, and reusability becomes arduous. In this paper, we present characteristics, strengths, and weaknesses of RUP and XP process models, and propose a new hybrid software development model eXRUP (eXtreme Programming and Rational Unified Process), which integrates the strengths of RUP and XP while suppressing their weaknesses. The proposed process model is validated through a controlled case study.

关键词： Process Models Agile Modeling eXtreme Programming Rational Unified Process Process Evaluation

来源：评论

学校读者我要写书评

暂无评论

Spelling out opinions: Difficult cases of sentiment analysis

Spelling out opinions: Difficult cases of sentiment analysis

引用

IEEE International Conference on Ubi-Media computing

作者： Ivan Khozyainov Evgeny Pyshkin Vitaly Klyuev Institute of Computing and Control St. Petersburg State Polytechnical University St. Petersburg Russia Software Engineering Lab. University of Aizu Fukushima Japan

In recent years there is growing interest to the opinion mining applications in numerous areas of information and social science. In this paper we investigate main problems in opinion mining and sentiment analysis systems development. We review examples of difficulties in process of opinion extraction and introduce essential multidimensionality of opinion mining. We carried out a series of experiments with different sentiment analyzers and classified main reasons of incorrect sentiment recognition.

关键词： Data mining Context Motion pictures Monitoring Media Grammar Text recognition

来源：评论

学校读者我要写书评

暂无评论

Schedulability Analysis with CCSL Specifications

Schedulability Analysis with CCSL Specifications

引用

Asia-Pacific Conference on software engineering

作者： Ling Yin Jing Liu Zuohua Ding Frédéric Mallet Robert de Simone Shanghai Key lab of Trustworthy Computing East China Normal University Shanghai China Center of Math Computing and Software Engineering Zhejiang Sci-Tech University Hangzhou Zhejiang China INRIA Sophia Antipolis Méditerranée France

ISBN: (纸本)9781479921454

The Clock Constraint Specification Language (CCSL) is a formal polychronous language based on the notion of logical clock. It defines a set of kernel constraints that can represent both asynchronous and synchronous relations. It was originally developed as part of the UML Profile for MARTE to express causal and temporal constraints of Real-time and Embedded Systems. In this paper, we explore the use of CCSL for modeling scheduling requirements and to conduct schedulability analysis. For this purpose, a dedicated scheduling library of CCSL has been built. This library is endowed with a state-based operational semantics, and is applied to solve issues related to schedulability analysis and latency-insensitive design. We establish schedulability categories and latency-insensitiveness property in the context of the semantics, and solve those issues by using model checking techniques.

关键词： software engineering

来源：评论

学校读者我要写书评

暂无评论

Image registration using consistent robust point matching

Image registration using consistent robust point matching

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xuan Yang Jihong Pei Jingli Shi College of Computer Science and Software Engineering Shenzhen University Shenzhen China College of Information Engineering Shenzhen University Shenzhen China National High Performance Computing Center at Shenzhen Shenzhen University Shenzhen China

ISBN: (纸本)9781479913114

The robust point matching (RPM) has been applied in image registration. Although the RPM has been extensively used in non-rigid registration of images, it does not solve a consistent correspondence between the two images except at the estimated corresponding points. In this paper, we propose an image registration method based on the consistent robust point matching to solve the forward and reverse transformations between two images. It defines a novel cost function for RPM by introducing the inverse consistency constraint. The fuzzy corresponding relationship between points is estimated based on both the forward and reverse transformations simultaneously. The proposed method also introduces similarity of image content in the procedure of points matching. The performance of our method is demonstrated and validated in synthetic experiments. Moreover, we apply the method to the problem of non-rigid registration of real images and brain images. The results indicate the improvement of the proposed method in the aspect of bi-directional image registration and the decrease of the inverse consistency errors of the forward and the reverse transformations between two images.

关键词： Image registration Cost function Accuracy Robustness Brain Educational institutions Splines (mathematics)

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：