检索结果-内蒙古大学图书馆

2013 International Conference for Smart Health, ICSH 2013

作者： Liang, Yunji Zheng, Xiaolong Zeng, Daniel Dajun Zhou, Xingshe Leischow, Scott School of Computer Science Northwestern Polytechnical University Xi'an China Department of Management Information System University of Arizona Tucson AZ United States State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Dongguan Research Institute of CASIA Cloud Computing Center Chinese Academy of Sciences Songshan Lake Dongguan China Mayo Clinic in Arizona Phoenix AZ United States

ISBN: (纸本)9783642398438

Social media is widely utilized in the tobacco control campaigns. It is a great challenge to evaluate the efficiency of tobacco control policies on social network sites and find gaps among tobacco-oriented social networks. In this paper, we construct three tobacco-oriented social networks according to user interaction on Facebook tobacco-related fan pages. We further investigate the interaction patterns including temporal distribution and interaction patterns to reveal the differences of tobacco-oriented social networks. Our empirical analysis demonstrates that: 1) the user interaction on the pro-tobacco fan pages is more active. Fan pages for tobacco promotion are more successful in obtaining more user attention. 2) The gap between tobacco promotion and tobacco control is widening. These empirical results can provide us significant insights into understanding the evolutionary patterns of social interaction in tobacco-oriented social networks and further help the government departments of tobacco control to make reasonable decisions. © 2013 Springer-Verlag.

关键词： Tobacco

来源：评论

学校读者我要写书评

暂无评论

Adaptive nonlinear auto-associative modeling through manifold learning

引用

9th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, PAKDD 2005

作者： Zhang, Junping Li, Stan Z. Intelligent Information Processing Laboratory Department of Computer Science and Engineering Fudan University Shanghai 200433 China Key Laboratory of Complex Systems and Intelligence Science Chinese Academy of Sciences China National Laboratory of Pattern Recognition Center for Biometrics and Security Research Institute of Automation Beijing 100080 China

ISBN: (纸本)3540260765

We propose adaptive nonlinear auto-associative modeling (ANAM) based on Locally Linear Embedding algorithm (LLE) for learning intrinsic principal features of each concept separately and recognition thereby. Unlike traditional supervised manifold learning algorithm, the proposed ANAM algorithm has several advantages: 1) it implicitly embodies discriminant information because the suboptimal parameters of ANAM are determined based on error rate of the validation set. 2) it avoids the curse of dimensionality without loss accuracy because recognition is completed in the original space. Experiments on character and digit databases show that the advantages of the proposed ANAM algorithm. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Developing a prototype concurrent design tool for composite topside structures

引用

NAVAL ENGINEERS JOURNAL 1997年第3期109卷 279-290页

作者： Dirlik, S Hambric, S Azarm, S Marquardt, M Hellman, A Bartlett, S Castelli, V Steve Dirlik:began his career at the Naval Surface Warfare Center Carderock Division in 1981 as an aerospace engineer co-op student. He completed his bachelor of science degree in aeropace and ocean engineering from Virginia Polytechnic Institute and State University in 1985 and his master of science degree in aerospace engineering from the University of Maryland in 1990. Mr. Dirlik recently completed a master of science program in applied physics at The Johns Hopins University and currently works in the Radar Cross Section and Target Physics Branch of the Signatures Directorate at the Naval Surface Warfare Center Corderoke Division. He has worked on Navy low observable programs since 1990. Stephen Hambric:is a research associate at the Applied Research Laboratory at The Pennsylvania State University. He received his B. S. and M.S. degree in mechanical engineering from Virginia Polytechnic Institute and State University and his D. Sc. in mechnical engineering from the George Washington University. He has worked on several computer aided multidiscikplinary design and optimization projects over the years including an automated propeller design system and a structural acoustic optimization capability. Dr. Shpour Azarm:is currently working as an associate professor with the Design and Manufacturing Group of the Department of Mechanical Engineering at the University of maryland at College Park. Dr Azarm's expertise is in the areas of optimization-based designed and concurrent design and optimization of multidisciplinary systems. He was a consultant at Black & Decker Corporation (summer 1996) and worked as a Navy senior summer faculty fellow (summer 1995) and a NASA summer faculty fellow (summer 1994). He was a visiting scientist at NASA Langley Research Center for Multidisciplinary Analysis and Applied Structural Optimzatiom at the University of Siegen in Germany (spring 1992) and the Design Institute of the Technical University of Denmark (summer 1990). Dr Azarm was an associate technical editor of the ASME Jour

A prototype concurrent engineering tool has been developed for the preliminary design of composite topside structures for modern navy warships. This tool, named GELS for the Concurrent Engineering of Layered Structures, provides designers with an immediate assessment of the impacts of their decisions on several disciplines which are important to the performance of a modern naval topside structure, including electromagnetic interference effects (EMI), radar cross section (RCS), structural integrity, cost, and weight. Preliminary analysis modules in each of these disciplines are integrated to operate from a common set of design variables and a common materials database. Performance in each discipline and an overall fitness function for the concept are then evaluated. A graphical user interface (GUI) is used to define requirements and to display the results from the technical analysis modules. Optimization techniques, including feasible sequential quadratic programming (FSQP) and exhaustive search are used to modify the design variables to satisfy all requirements simultaneously. The development of this tool, the technical modules, and their integration are discussed noting the decisions and compromises required to develop and integrate the modules into a prototype conceptual design tool.

关键词： Warships

来源：评论

学校读者我要写书评

暂无评论

Experiments with various neural architectures for handwritten character recognition

Experiments with various neural architectures for handwritte...

引用

Midwest Symposium on Circuits and systems (MWSCAS)

作者： C. Koutsougeras A. Jameel Center for Automation Autonomous and Complex Systems Computer Science Department Tulane University New Orleans LA USA Computer Science Department Xavier University New Orleans LA USA

In this research we address the problem of recognition of isolated handwritten characters. Handwritten character recognition has been a topic of research for a long period of time. It has been argued that this problem is difficult to model using classical modeling techniques, and that neural networks offer a new perspective to approaching this problem. This paper outlines the experimental evidence we have compiled while investigating possible approaches to handwritten character recognition. It is the hypothesis of our approach that handwritten character recognition is a pattern recognition problem and that there exists a set of unique features in the data which can be used for classification.

关键词： Character recognition Neural networks Handwriting recognition Feedforward neural networks Testing Feedforward systems computer architecture automation computer science Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Experiments with various recurrent neural network architectures for handwritten character recognition

Experiments with various recurrent neural network architectu...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： A. Jameel Computer Science Department Xavier University New Orleans LA USA Center for Automation Autonomous and Complex Systems Computer Science Department Tulane University New Orleans LA USA

This paper reports evaluations of several neural architectures when the handwritten character recognition is approached as a problem of spectro-temporal pattern recognition. In general, neural networks specialize in learning either the spectral or temporal characteristics of patterns. However, choice of appropriate features and architectures could lead to obtaining both spectral and temporal characteristics from the handwritten character patterns. One such feature and three appropriate architectures are the focus of this paper. The results obtained during a limited set of experiments indicate a great potential for the spectro-temporal approach to be a useful contender for being a part of schemes of handwritten character recognition systems. In addition, a simple voting method is presented for collaborative character recognition using three different recognition criteria.< >

关键词： Recurrent neural networks Character recognition Handwriting recognition Neural networks computer architecture Pattern recognition computer science automation Collaborative work Feedforward systems

来源：评论

学校读者我要写书评

暂无评论

Experiments with Kohonen's learning vector quantization in handwritten character recognition systems

Experiments with Kohonen's learning vector quantization in h...

引用

Midwest Symposium on Circuits and systems (MWSCAS)

作者： A. Jameel C. Koutsougeras Computer Science Deparmnent Xavier University New Orleans LA USA Center for Automation Autonomous and Complex Systems Computer Science Department Tulane University New Orleans LA USA

In this paper we present the results of classification of handwritten characters on a Kohonen neural network. Three types of features, Fourier transform, geometric moments and shadow feature extracted from handwritten character data were used for classification. Classification accuracy is found to be much higher with the shadow feature in comparison to the more traditional Fourier transform and geometric moments. We have also explored the relation between Kohonen's learning of orientation based correlations and the learning rule of a minimum distance approach, used in a feedforward Athena neural network.

关键词： Vector quantization Character recognition Neural networks Fourier transforms Testing computer science Feedforward neural networks automation Feature extraction Data mining

来源：评论

学校读者我要写书评

暂无评论

Data transformation for learning in feedforward neural nets

Data transformation for learning in feedforward neural nets

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： C. Koutsougeras R. Srikanth Center for Automation Autonomous and Complex Systems Computer Science Department Tulane University New Orleans LA USA

The authors target the problem of curve fitting on data samples for the purpose of subsequent interpolation. This is what backpropagation was developed for but its dependency on initial conditions and net topology affects its robustness. Here the authors present a different method which is based on an analysis of possible properties of the internal representations developed as a result of learning. Thus they introduce some additional constraints concerning direct control on internal representations. This method incorporates properties of supervised as well as unsupervised learning in the fitting problem.

关键词： Neural networks Feedforward neural networks Learning systems Curve fitting Interpolation Robustness automation computer science Backpropagation Topology

来源：评论

学校读者我要写书评

暂无评论

Embedding discriminant directions in backpropagation

Embedding discriminant directions in backpropagation

引用

IEEE Southeastcon

作者： G.M. Georgiou C. Koutsougeras Center of Automation and Autonomous Complex Systems Computer Science Department Tulane University New Orleans LA USA

A two-phase backpropagation algorithm is presented. In the first phase the directions of the weight vectors of the first hidden layer are constrained to remain in directions suitably chosen by pattern recognition, data compression, or speech and image processing techniques. Then, the constraints are removed and the standard backpropagation algorithm takes over to further minimize the error function. The first phase swiftly situates the weight vectors in a good position which can serve as the initialization of the standard backpropagation algorithm. The generality of its application, its simplicity, and the shorter training time it requires, makes this approach attractive.< >

关键词： Backpropagation algorithms Vectors Data compression Speech processing Speech analysis automation computer science Pattern recognition Feedforward systems Neural networks

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：