检索结果-内蒙古大学图书馆

37th ASEE/IEEE Frontiers in Education Conference, FIE

作者： Van Thanh, Le Haddawy, Peter Asian Institute of Technology Computer Science and Information Management Program

ISBN: (纸本)1424410843

This paper presents a novel approach to deriving probabilistic models that predict enrollment given applicant background and the amount of financial aid offered. Our Bayesian network models can be used to optimize various enrollment objectives. We present a novel efficient optimization algorithm that uses the models to maximize expected tuition revenue under capacity constraints including student-faculty ratio and accommodation. We demonstrate and evaluate our approach using four years of graduate admissions data from the Asian Institute of Technology, consisting of 7,788 applicants from 84 different countries. This data set is particularly challenging since reliable family income data is not available for students from most of these countries. Evaluating the Bayesian network model with 10-fold cross validation yields an ROC Az value of 0.8451, with a predictive accuracy of 82.70% at a threshold of 0.5. Comparing the results of the tuition revenue optimization model to the institute's current financial aid allocation practice shows that if single-term tuition revenue is the sole optimization criterion, the institute can achieve its current enrollment numbers while realizing significant savings in its financial aid budget. The prediction and optimization software is currently being incorporated into the institute's online admissions processing system. ©2007 IEEE.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

A comparative analysis of techniques for predicting academic performance

A comparative analysis of techniques for predicting academic...

引用

37th Annual Frontiers in EducationConference

作者： Nghe, Nguyen Thai Janecek, Paul Haddawy, Peter Computer Science and Information Management Program Asian Institute of Technology (AIT) 12120 Thailand AIT Thailand Can Tho University Viet Nam

ISBN: (纸本)9781424410835

This paper compares the accuracy of Decision Tree and Bayesian Network algorithms for predicting the academic performance of undergraduate and postgraduate students at two very different academic institutes: Can Tho University (CTU), a large national university in Viet Nam;and the Asian Institute of Technology (AIT), a small international postgraduate institute in Thailand that draws students from 86 different countries. Although the diversity of these two student populations is very different, the data-mining tools were able to achieve similar levels of accuracy for predicting student performance: 73/71% for {fail, fair, good, very good} and 94/93% for {fail, pass} at the CTU/AIT respectively. These predictions are most useful for identifying and assisting failing students at CTU (64% accurate), and for selecting Very Good students for scholarships at the AIT (82% accurate). In this analysis, the Decision Tree was consistently 3-12% more accurate than the Bayesian Network. The results of these case studies give insight into techniques for accurately predicting student performance, compare the accuracy of data mining algorithms, and demonstrate the maturity of open source tools.

关键词： Bayesian Networks data mining Decision Trees prediction

来源：评论

学校读者我要写书评

暂无评论

Perceptual-based region extraction from hand drawn sketches

Perceptual-based region extraction from hand drawn sketches

引用

3rd IASTED International Conference on Advances in computer science and Technology, ACST 2007

作者： Waranusast, Rattapoom Computer Science and Information Management Program Asian Institute of Technology P.O. Box 4 Khlong Luang Pathumthani 12120 Thailand

ISBN: (纸本)9780889866560

Pen-based computing devices have become more popular and more important, because it facilitates a natural way of input to users. To develop pen-based systems, automatic interpretation of sketches is crucial. However, this task is sensitive to drawing styles. This paper proposes a stroke grouping method based on Gestalt theory. The proposed algorithm group strokes into regions, each stroke is split into smaller stroke segments according to its corners and junctions. Then, for every stroke segments that can form closed loops, all possible regions are searched. Applying the notion of law of continuity in Gestalt theory to a set of all possible regions, scores of good continuity and convexity of all regions can be computed. The region with the best score is stored and extracted from the sketch. This iterative process is repeated until no stroke segments are left in the set of closed-loop segments. The algorithm implemented and tested on a tablet PC showed good results.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Deriving financial aid optimization models from admissions data

Deriving financial aid optimization models from admissions d...

引用

Frontiers in Education (FIE) Conference

作者： Le Van Thanh Peter Haddawy Computer Science and Information Management Program Asian Institute of Technology Thailand

关键词： Predictive models Bayesian methods Logistics Accuracy Resource management Probability Error analysis Neural networks Regression tree analysis computer science

来源：评论

学校读者我要写书评

暂无评论

A Decision Support System for Evaluating International Student Applications

A Decision Support System for Evaluating International Stude...

引用

37th Annual Frontiers in Education Conference (FIE 2007), vol.2

作者： Nguyen Thi Ngoc Hien Peter Haddawy Computer Science and Information Management Program Asian Institute of Technology Thailand

In today's transnational admission environment, evaluating applicant qualifications is becoming increasingly challenging. While standardized tests can be helpful, studies have shown that they are rather noisy predictors of performance. Predicting educational outcome is a viable alternative in such heterogeneous environments. Performance prediction models can be built by applying data mining techniques to enrollment data. In this paper we present an approach to using Bayesian networks to predict graduating cumulative Grade Point Average based on applicant background at the time of admission. While such prediction models can be helpful, their recommendations may not be followed by departmental faculty members making admission decisions if they are presented as black boxes. We thus present a novel approach to deriving a case-based retrieval mechanism from the Bayesian network prediction model in such a way that the similarity measure used by the case-based system is consistent with the predictive model. The case-based component retrieves the past student most similar to the applicant being evaluated. The Bayesian network model is evaluated using stratified ten-fold cross validation.

关键词： Bayesian networks Case-based retrieval Student evaluation

来源：评论

学校读者我要写书评

暂无评论

A comparative analysis of techniques for predicting academic performance

A comparative analysis of techniques for predicting academic...

引用

Frontiers in Education (FIE) Conference

作者： Nguyen Thai Nghe Paul Janecek Peter Haddawy Computer Science and Information Management Program Asian Institute of Technology Thailand Cantho University Vietnam

This paper compares the accuracy of decision tree and Bayesian network algorithms for predicting the academic performance of undergraduate and postgraduate students at two very different academic institutes: Can Tho University (CTU), a large national university in Viet Nam; and the Asian Institute of Technology (AIT), a small international postgraduate institute in Thailand that draws students from 86 different countries. Although the diversity of these two student populations is very different, the data-mining tools were able to achieve similar levels of accuracy for predicting student performance: 73/71% for {fail, fair, good, very good} and 94/93% for {fail, pass} at the CTU/AIT respectively. These predictions are most useful for identifying and assisting failing students at CTU (64% accurate), and for selecting very good students for scholarships at the AIT (82% accurate). In this analysis, the decision tree was consistently 3-12% more accurate than the Bayesian network. The results of these case studies give insight into techniques for accurately predicting student performance, compare the accuracy of data mining algorithms, and demonstrate the maturity of open source tools.

关键词： Performance analysis Data mining Decision trees Bayesian methods Prediction algorithms Accuracy Scholarships Predictive models information analysis Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

The constraints of the valuation distribution for solving a class of games by using a best response algorithm

引用

International Journal of Manufacturing Technology and management 2007年第4期12卷 327-341页

作者： Gangshu, Cai Jie, Zhong Wurman, Peter R. Management Information Systems and Decision Sciences Texas A and M International University Laredo TX 78041 United States Management Information Systems and Decision Sciences Department Texas A and M International University United States Operations Research and Computer Science North Carolina State University Raleigh NC 27695-7535 United States SAS Institute Cary United States Operations Research and Computer Science Graduate Program North Carolina State University United States Computer Science Department North Carolina State University United States

Infinite games with incomplete information are common in practice. First-price, sealed-bid auctions are a prototypical example. To solve this kind of infinite game, a heuristic approach is to discretise the strategy spaces and enumerate to approximate the equilibrium strategies. However, an approximate algorithm might not be guaranteed to converge. This paper discusses the utilisation of a best response algorithm in solving infinite games with incomplete information. We show the constraints of the valuation distributions define the necessary conditions of the convergence of the best response algorithm for several classes of infinite games, including auctions. A salient feature of the necessary convergence conditions lies in that they can be employed to compute the exact Nash equilibria without discretising the strategy space if the best response algorithm converges. Copyright © 2007 Inderscience Enterprises Ltd.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Challenges associated with privacy in health care industry: Implementation of HIPAA and the security rules

引用

Journal of Medical Systems 2006年第1期30卷 57-64页

作者： Choi, Young B. Capitan, Kathleen E. Krause, Joshua S. Streeper, Meredith M. Department of Computer Information Systems and Management Science James Madison University Harrisonburg VA 22807-0001 United States Communication Sciences and Disorders Program James Madison University Harrisonburg VA 22807-0001 United States Department of Integrated Science and Technology James Madison University Harrisonburg VA 22807-0001 United States

This paper discusses the challenges associated with privacy in health care in the electronic information age based on the Health Insurance Portability and Accountability Act (HIPAA) and the Security Rules. We examine the storing and transmission of sensitive patient data in the modern health care system and discuss current security practices that health care providers institute to comply with HIPAA Security Rule regulations. Based on our research results, we address current outstanding issues that act as impediments to the successful implementation of security measures and conclude the discussion and offer possible avenues of future research. © Springer science+Business Media, Inc. 2006.

关键词： Electronic data interchange (EDI) Health Insurance Portability and Accountability Act (HIPAA) Protected health information (PHI) Security rule

来源：评论

学校读者我要写书评

暂无评论

Remote internetworking laboratory

Remote internetworking laboratory

引用

113th Annual ASEE Conference and Exposition, 2006

作者： Jabbour, Imad Haydamous, Linda Kazan, Wissam Hayek, Amine Massachusetts Institute of Technology United States Information Technology Program MIT United States MIT's Center for Educational Computing Initiatives IEEE New Jersey Institute of Technology United States Engineering Management Program New Jersey Institute of Technology United States Operations Research Stanford University United States Computer Science Program Stanford University United States

Remote experimentation is the process of conducting real lab experiments without being physically in contact with lab devices. Recently, the development of Internet technologies fostered the spread of online laboratories, and significant benefits helped establish remote experimentation as a potential substitute to real experimentation. Internetworking lab experiments usually involve very expensive hardware;and providing remote access to this type of laboratories is highly desired, especially when a large number of students must share a limited set of devices. Very few remote internetworking laboratories have previously been implemented, and they had several drawbacks. In this paper, we discuss our design of a Remote Internetworking Laboratory which provided access to the internetworking lab at the American University of Beirut (AUB). The uniqueness of our approach is that it uses VLANs (Virtual LANs) to build network topologies, a technique that separates network subnets into different broadcast domains before allowing users to configure each lab device. The proposed scheme overcomes the limitations of other designs, and allows users to build any desired network topology and configure the lab devices in real-time. Many technical and educational features were integrated into the system, and possible enhancements were suggested based on several evaluation criteria. © American Society for Engineering Education, 2006.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

A connection-oriented telecommunications disaster management model using mobile GIS

引用

International Journal of Mobile Communications 2006年第1期4卷 63-81页

作者： Choi, Young B. Blackburn, Jonathan M. Seo, Hyewon Information Technology and Management Science Program College of Business James Madison University 800 South Main Street Harrisonburg VA 22807-0001 United States Computer Science Program James Madison University 800 South Main Street Harrisonburg VA 22807-0001 United States Accounting and Information Technology James Madison University 800 South Main Street Harrisonburg VA 22807-0001 United States Information Technology and Management Science Program James Madison University Harrisonburg VA United States James Madison University United States

Mobile Geographic information Systems are a versatile extension of traditional GIS and can provide GIS data between the field and the office. This paper addresses the challenges imposed on telecommunications infrastructure management by disaster events. MGIS are presented as tools that provide meaningful real-time communication between field workers and management. Copyright © 2006 Inderscience Enterprises Ltd.

关键词： Geographic information systems

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：