检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： N.M. Wanas M.R. El-Sakka M.S. Kamel Pattern Analysis and Machine Intelligence Laboratory Department of Systems Design Engineering University of Waterloo Waterloo ONT Canada

Combining decisions from several classifiers can be used to improve on the results of handwritten characters recognition. There are different methods to combine these decisions, most of which are static. We present an architecture that integrates learning into the voting scheme used to aggregate individual decisions. The focus of the work is to make the decision fusion a more adaptive process. This approach makes use of feature detectors responsible for gathering information about the input to perform adaptive decision aggregation. The approach is tested on handwritten Arabic character recognition. The results showed an improvement over any individual classifier, as well as different static classifier combining schemes.

关键词： Character recognition Voting Handwriting recognition Neural networks Bayesian methods Pattern recognition Aggregates Optical character recognition software Decision making Multi-layer neural network

来源：评论

学校读者我要写书评

暂无评论

Neural networks: the state of the art

Neural networks: the state of the art

引用

International Conference on Microelectronics, ICM

作者： M.S. Kamel Pattern Analysis and Machine Intelligence Laboratory Department of Systems Design Engineering University of Waterloo Waterloo ONT Canada

Artificial neural networks (ANNs) have demonstrated their success in many applications due to their ability to solve some problems with relative ease of use and the model-free property they enjoy. ANNs can solve problems without the need to understand or learn the analytical and statistical properties of the problem nor the solution steps. Research in ANNs has resulted in a variety of models and learning algorithms. In this paper, a brief review of recent advances in the field is presented. The paper then focuses on the recent work conducted by the author's group on modular neural networks. In particular, the paper discusses the different modular structures, modes of interactions, capabilities, co-operation among modules and fusion of their decisions. Performance of these models has proven to be superior to nonmodular neural networks.

关键词： Neural networks Artificial neural networks Computer errors Multilayer perceptrons Supervised learning Feedback Pattern analysis Machine intelligence System analysis and design design engineering

来源：评论

学校读者我要写书评

暂无评论

Recursive multiscale estimation of space-time random fields

Recursive multiscale estimation of space-time random fields

引用

IEEE International Conference on Image Processing

作者： T.T. Ho P.W. Fieguth A.S. Willski Laboratory for Information and Decision Systems Massachusetts Institute of Technology USA Department of Systems Design Engineering University of Waterloo Canada

We recently developed a multiscale recursive estimation procedure for the estimation of large-scale dynamic systems. The procedure propagates multiscale models for the estimation errors more efficiently than the Kalman filter's propagation of the error covariances, with a resulting computational complexity of 𝒪(N) and 𝒪(N 3/2 ), where N is the number of variables estimated, for 1-D and 2-D dynamic systems, respectively. To further reduce the computational cost, we introduce in this paper a new class of reduced-order spatially-interpolated multiscale models, and demonstrate their use in remote.

关键词： Recursive estimation Estimation error Computational efficiency Decorrelation Laboratories design engineering systems engineering and theory Space technology Large-scale systems Kalman filters

来源：评论

学校读者我要写书评

暂无评论

An information theoretic image-quality measure

An information theoretic image-quality measure

引用

Canadian Conference on Electrical and Computer engineering (CCECE)

作者： O. Elbadawy M.R. El-Sakka M.S. Kamel Pattern Analysis and Machine Intelligence Laboratory Department of Systems Design Engineering University of Waterloo Waterloo ONT Canada

Lossy image compression techniques aim at encoding images with a minimal representation. During this process, some visually useful information may be lost. Assessing the information loss in decompressed images is not an easy task. In this paper, a new quantitative image-quality measure is introduced. This new measure incorporates information theory into the most commonly used objective criterion (the mean square error). The new measure has been tested by experiments performed on a wide variety of images. The results show an increase in the correlation between subjective rating by human observers and the normalized mean square error after applying the new measure.

关键词： Image coding Testing Mean square error methods Humans Image quality Information theory Layout Pattern analysis Machine intelligence Laboratories

来源：评论

学校读者我要写书评

暂无评论

Hierarchical methods for global-scale estimation problems

Hierarchical methods for global-scale estimation problems

引用

Canadian Conference on Electrical and Computer engineering (CCECE)

作者： P.W. Fieguth M.R. Allen M.J. Murray Department of Systems Design Engineering University of Waterloo Waterloo ONT Canada Department of Physics University of Oxford UK Rutherford and Appleton Laboratory Didcot UK

There is a substantial signal-processing challenge associated with large-scale (especially global-scale) remote-sensing problems: solving the statistical inverse problem (i.e. deducing the properties of the sensed field from measurements) by brute force, that is by covariance matrix inversion, is completely impractical for fields involving millions of pixels. This paper reports on the ongoing development of an alternative technique, in which the statistical problem is modeled on a multiscale tree, applied to estimating sea-surface temperature (SST) based on infrared radiance observations from the along-track scanning radiometers (ATSRs).

关键词： Ocean temperature Signal resolution Remote sensing Sea measurements Force measurement Atmospheric modeling Sea surface Statistics Decorrelation Satellites

来源：评论

学校读者我要写书评

暂无评论

Recapitalizing the Navy through optimized manning and improved reliability

引用

NAVAL ENGINEERS JOURNAL 1998年第6期110卷 61-72页

作者： Anderson, DE Malone, TB Baker, CC Mr. David E. Anderson:is a Navel Engineer with the Naval Sea Systems Command where he is currently assigmd to the HumanSystems Integration branch. Mr Anderson has a Bachelor of Science degree an Environmental Engineering from Flurida Technological University and a Master's in Environmental Engiwering from the University of Central Flurida. He currentEy is an HSI manager for a number oflvay R&D and skig acquisition efforts. Dr. Thomas B. Malone:received a Ph.D. in Experimental Psychology from Fordham University in 1964. He is President of Carlow International Incorporated an organization dedicated to human factors research and development with emphasis an mantime systems. He has directed over 350 programs and projects in his 33 year career and is responsible for overall management of all contract programs within the Corporation. He is a Past President of the Human Factors and E r g m i c s Society (HFES) of which he is a Fellow. He is also a Fellow of the Washington Academy of Sciences He was selected as a member of the N A S Space Sciences Technical Advisuiy Committee on Technoloo Requirements for Human Performance on Long Duration Space Missions in 2989 and 90. He was elected as the First Chair of the Systems Development Technical Group of the HFES. Dr Malone is currently managing eflorts to devehp and auto- mate standardized processes for canducting human systems integration (HSI) in the military weapon systems acquisition process and fov developing automated tools to facilitate fledormance of specific steps in the HSI process. Dr Malone also is currently occupied in applying human engineering to the DD 21 and is serving as the Chair ofthe System ManninglHuman Perfomzance Working IPT under the DD 21 ManninglHSI IPT chaired ty PMS 500M. Mr. Clifford Baker:has over 20 years experience in developing and applying human factors technology to complex systems. He holds a masters degree in psychology with a specialization in human factors engineering and he is a Board Certified Human Factors Engineering Profesional

Reduced manning is the process (and the result) of removing human functions from a system while retaining or improving system operability and effectiveness. Reliability and maintainability characterize a system's operability and effectiveness. Reduced manning impacts system reliability by changing the characteristics of (1) human error associated with system operation and maintenance, (2) time to repair failed components, and (3) mean-time-between-failures (MBTF) in a reduced manning environment. Simply reducing manning without compensating for system dependence on human involvement generally has a negative impact on system maintainability. Methods to address this include (1) human-system integration design of maintenance interfaces and (2) design of operations activities that are closely related to device failures. After demonstrating reliable performance through testing and operation, ship commanders can be assured that fewer people can effectively operate and maintain Navy ships and systems.

关键词： Naval vessels

来源：评论

学校读者我要写书评

暂无评论

Parallel processor system specific for Monte Carlo analysis based on ring bus architecture

Parallel processor system specific for Monte Carlo analysis ...

引用

International Workshop on Computational Electronics

作者： H. Kurino T. Ono N. Kuroishi T. Kawata N. Miyakawa M. Fukase R. Aibara M. Koyanagi Intelligent System Design Laboratory Department of Machine Intelligent and Systems Engineering Graduate School of Engineering University of Tohoku Sendai Japan Advanced Technology & Engineering Center Fuji Xerox Company Limited Faculty of Science and Technology Hirosaki University Information Processing Center Hiroshima Institute of Technology

We have developed a new parallel processor system specific for the MC analysis, to dramatically reduce the calculation time. Our parallel processor system is based on ring bus architecture. The RISC micro processor chip, which contains a ring bus interface unit (RBIU), a floating point arithmetic unit (FAU) and so on, was also developed for our system. Speed up ratio compared with a single processor reached to 13.5 at 23 PEs.

关键词： Monte Carlo methods design engineering Analytical models Computational modeling Master-slave Intelligent systems Machine intelligence Poisson equations System analysis and design systems engineering and theory

来源：评论

学校读者我要写书评

暂无评论

Local misorientation change along grain boundary in coarse-grained YBa2Cu3O7-X prepared by melt-texturing process

引用

SCRIPTA MATERIALIA 1997年第2期37卷 141-145页

作者： Yamaura, S Nakashio, K Igarashi, Y Watanabe, T Laboratory of Materials Design and Interface Engineering Department of Machine Intelligence and Systems Engineering Faculty of Engineering Tohoku University Sendai Japan

The present investigation has revealed that the misorientation angle can change locally and systematically along a grain boundary due to the interaction with sub-boundaries in coarse-grained YBCO grown by the MPMG process. More detailed analysis of grain boundary character is required for engineering grain boundaries in superconducting polycrystalline YBCO. References 1. D. Dimos, P. Chaudhari and J. Mannhart. Phys. Rev. B 41 (1990), p. 4038. Full Text via CrossRef | View Record in Scopus | Cited By in Scopus (537) 2. S.E. Babcock, X.Y. Cai, D.L. Kaiser and D.C. Larbalestier. Nature 347 (1990), p. 167. Full Text via CrossRef | View Record in Scopus | Cited By in Scopus (71) 3. C.B. Eom, A.F. Marshall, Y. Suzuki, B. Boyer, R.F. Pease and T.H. Geballe. Nature 353 (1991), p. 544. Full Text via CrossRef | View Record in Scopus | Cited By in Scopus (2) 4. Yimei Zhu. Phil. Mag. A 69 (1994), p. 717. Full Text via CrossRef 5. A.H. King and Y. Zhu. Phil. Mag. A 67 (1993), p. 1037. Full Text via CrossRef 6. S. Jin, T.H. Tiefel, R.C. Sherwood, M.E. Davis, R.B. Van Dover, G.W. Kammlott, R.A. Fastnacht and H.D. Keith. Appl. Phys. Lett. 52 (1988), p. 2074. Full Text via CrossRef | View Record in Scopus | Cited By in Scopus (180) 7. S.I. Yoo, N. Sakai, H. Takaichi, T. Higuchi and M. Murakami. Appl. Phys. Lett. 65 (1994), p. 633. Full Text via CrossRef | View Record in Scopus | Cited By in Scopus (437) 8. M. Nilsson-Mellbin, A. Parikh and K. Salama. Physica C 223 (1994), p. 19. Abstract | PDF (710 K) | View Record in Scopus | Cited By in Scopus (11) 9. T. Watanabe. Phil. Mag. A 47 (1983), p. 141. Full Text via CrossRef | View Record in Scopus | Cited By in Scopus (10) 10. W.J. Kang, K. Yoshimi, S. Hanada, S. Saito, Y. Murayama, S. Hayashi and A. Nagata. J. Appl. Phys. 68 (1990), p. 6341. Full Text via CrossRef | View Record in Scopus | Cited By in Scopus (2) 11. D.M. Kroeger and A. Goyal. J. Metals 5 (1988), p. 14. 12. C.S. Nichols and D.R. Clarke. Acta Metall. Mate

关键词： Boundary superconducting materials grain melt texturing Critical current density polycrystalline materials Misalignment granulation thin films Grain boundaries

来源：评论

学校读者我要写书评

暂无评论

An optimized two-step camera calibration method

An optimized two-step camera calibration method

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： H. Bacakoglu M. Kamel Pattern Analysis and Machine Intelligence Laboratory Department of Systems Design Engineering University of Waterloo Waterloo ONT Canada

An optimized two-step camera calibration algorithm is developed. The proposed method starts with the well known linear calibration which approximates the transformation as a 3/spl times/4 matrix. Based on the results of the linear calibration and the camera model we construct the 4/spl times/4 homogeneous transformation matrix. Quaternion algebra is used to extract the optimum rotation matrix and this optimization is later extended to the other calibration parameters. Our calibration method includes nonlinear optimization which takes into consideration lens distortions. The convergence rate of the nonlinear optimization is accelerated by three more objective functions we introduced. To assess the accuracy of our proposed quaternion method, Euclidean norm of the error matrix between the original and computed homogeneous transformation matrices is calculated and compared to those of the existing methods. Simulations show that the quaternion method yields more accurate results both before and after the nonlinear optimization.

关键词： Optimization methods Cameras Calibration Quaternions Linear approximation Algebra Lenses Nonlinear distortion Convergence Acceleration

来源：评论

学校读者我要写书评

暂无评论

A rough set approach for planner evaluation

A rough set approach for planner evaluation

引用

IEEE International Conference on systems, Man and Cybernetics

作者： B.K. Sy Wang Jiaxin Pattern Analysis and Machine Intelligence Group System Design Engineering Department University of Waterloo Waterloo ONT Canada Department of Computer Science CUNY Flushing NY USA The State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China

This paper discusses a rough set approach for evaluating solutions of scheduling problems. Algorithms for solving scheduling problems are planners and the scheduling problems are modelled as constraint satisfaction problems. Conventional approach for the analysis of algorithms often focuses on the time and representational complexities, and assumes an identical cost on all operations. The proposed rough set approach augments conventional approaches for the analysis of algorithms in two ways: 1) it permits the consideration of different costs arising from different operations; and 2) it allows one to define a new utility for a complexity analysis.

关键词： Algorithm design and analysis Processor scheduling Set theory Machine intelligence Computer science Costs Search problems Educational institutions Pattern analysis System analysis and design

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：