检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing

作者： Li Xingyuan Oh Weon-Geun Hong Jiarong Department of Computer Science and Engineering Harbin Institute of Technology Harbin China AI Division Systems Engineering Research Institute Daejeon South Korea

ISBN: (纸本)0780332598

Now all the block based skeletonizing algorithms only use the compressed line adjacency graph scanned in one direction. For lines approximately parallel to the scan direction, there is difficulty extracting the skeleton because such a line may be separated into several graph nodes or mixed with some pixels of other lines in the intersection point. In this paper, we propose a new skeletonizing method by combining c-LAG of horizontal and vertical direction. The main idea of the method is a rule for the skeletons in horizontal and vertical direction c-LAG and knowledge based node validation. The validation makes full use of global information in the image. It has been tested on a large amount of characters and high quality achieved.

关键词： Skeleton Pixel Artificial intelligence Systems engineering and theory computer science Testing Image segmentation Topology Partitioning algorithms Image coding

来源：评论

学校读者我要写书评

暂无评论

OPTICAL TUNING BEHAVIOR OF AL0.25GA0.75AS/GAAS HBT OSCILLATORS WITH TRANSPARENT ITO EMITTER CONTACTS

引用

MICROWAVE AND OPTICAL TECHNOLOGY LETTERS 1995年第4期9卷 173-175页

作者： FREEMAN, PN KARAKUCUK, M BHATTACHARYA, PK Solid State Electronics Laboratory Department of Electrical Engineering and Computer Science The University of Michigan Ann Arbor Ml 48109

Optical tuning experiments were performed on an Al0.25Ga0.75As / GaAs HBT oscillator operating at 6 GHz. The HBT was fabricated with a transparent emitter ohmic contact made of indium-tin-oxide (ITO) to allow light input through the top of the device. Under direct illumination of the base and base-collector depletion regions, optical tuning was observed with an increase in oscillation frequency of rip to 25 MHz. The observed increase in frequency is attributed to a shift in resonance due to a decrease in the base-emitter-junction capacitance of the HBT under optical illumination. This effect is verified using detailed device and circuit modeling techniques. (C) 1995 John Wiley & Sons, Inc.

关键词： HBT OSCILLATOR MICROWAVE OPTICAL INTERACTIONS OPTICAL TUNING

来源：评论

学校读者我要写书评

暂无评论

Resource Requirements for Field Programmable Interconnection Chips

Resource Requirements for Field Programmable Interconnection...

引用

Proceedings of the 8th International Conference on VLSI Design

作者： Bhatia, Dinesh Hardambidest, James Design Automation Laboratory Department of Electrical and Computer Engineering University of Cincinnati ML - 0030 CincinnatiOH45221-0030 United States Department of Mathematics and Computer Science Barry University 11300 NE 2nd Avenue Miami ShoresFL33161-6695 United States

In this paper we prove an fl(n1og n) lower bound on the number of edges of an n-permutation gmph G = (V,E). The lower bound is applicable to and characterizes permutations for Field Progmmmable Interconnection Chips and, more importantly, permutation networks in geneml. We also propose a family of permutation networks as a variation of the known Bened network with a wide mnge of diameters, a network property directly related to routing delays. Finally, the relation between the total number of progmmmable switches and the routing delay (mazimum length of routing paths for specific 1/0 permutations) is explored. © 1995 IEEE computer Society. All rights reserved.

关键词： Integrated circuit interconnects

来源：评论

学校读者我要写书评

暂无评论

Endomorphic modeling of intelligent system: intelligent card game player

Endomorphic modeling of intelligent system: intelligent card...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Sung-Do Chi Young-Kwang Kim Ja-Ok Lee Tae-Ho Cho AI-Simulation Research Laboratory Department of Computer Engineering Korea Hang kong University Seoul South Korea Department of Computer Science Kyungnam University Masan South Korea

ISBN: (纸本)0780325591

This paper presents an endomorphic modeling methodology for designing intelligent systems. An intelligent system can determine by itself using its knowledge of the world and adapt itself to continuously changing circumstances. We have developed an intelligent endomorphic system by integrating the decision making component and knowledge based internal model with the internal model construction model. Learning capabilities are established using the inductive reasoning and adaptive expert system techniques. The proposed methodology has been successfully applied to the design of an intelligent card game player capable of supporting the intelligent learning and decision making.

关键词： Intelligent systems Game theory Decision making Intelligent structures Adaptive systems Expert systems Artificial intelligence Design engineering computer science Design methodology

来源：评论

学校读者我要写书评

暂无评论

Laboratory investigation: Automatic identification of gray matter structures from MRI to improve the segmentation of white matter lesions

引用

computer aided Surgery 1995年第6期1.0卷 326-338页

作者： Warfield, Simon Dengler, Joachim Zaers, Joachim Guttmann, Charles R.G. Wells, William M. Ettinger, Gil J. Hiller, John Kikinis, Ron School of Computer Science and Engineering University of New South Wales Sydney Australia Vision Systems Neckargemuend Germany German Cancer Research Center Heidelberg Germany Department of Radiology Harvard Medical School and Brigham and Women's Hospital Boston MA United States AI Lab NE43-771 Massachusetts Institute of Technology Cambridge MA United States Department of Radiological Sciences UCLA School of Medicine Los Angeles CA United States

The segmentation of MRI scans of patients with white matter lesions (Wml) is difficult because the MRI characteristics of Wml are similar to those of gray matter. Intensity-based statistical classification techniques misclassify some Wml as gray matter and some gray matter as Wml. We developed a fast elastic matching algorithm that warps a reference data set containing information about the location of the gray matter into the approximate shape of the patient's brain. The region of white matter was segmented after segmenting the cortex and deep gray matter structures. The cortex was identified by using a three-dimensional, region-growing algorithm that was constrained by anatomical, intensity gradient, and tissue class parameters. White matter and Wml were then segmented without interference from gray matter by using a two-class minimum-distance classifier. Analysis of double-echo spin-echo MRI scans of 16 patients with clinically determined multiple sclerosis (MS) was carried out. The segmentation of the cortex and deep gray matter structures provided anatomical context. This was found to improve the segmentation of MS lesions by allowing correct classification of the white matter region despite the overlapping tissue class distributions of gray matter and MS lesion. © 1995 Informa UK Ltd All rights reserved: reproduction in whole or part not permitted.

关键词： Gray matter MRI MS lesion Segmentation

来源：评论

学校读者我要写书评

暂无评论

Automatic identification of gray matter structures from MRI to improve the segmentation of white matter lesions

引用

Journal of Image Guided Surgery 1995年第6期1卷 326-338页

作者： Warfield, Simon Dengler, Joachim Zaers, Joachim Guttmann, Charles R.G. Wells, William M. Ettinger, Gil J. Hiller, John Kikinis, Ron School of Computer Science and Engineering University of New South Wales Sydney Australia Neckargemuend Germany German Cancer Research Center (DKFZ) Heidelberg Germany Department of Radiology Harvard Medical School and Brigham and Women's Hospital Boston Massachusetts United States Massachusetts Institute of Technology AI Lab NE43-771 Cambridge Massachusetts NE43-771 United States Department of Radiological Sciences UCLA School of Medicine Los Angeles California United States

The segmentation of MRI scans of patients with white matter lesions (Wml) is difficult because the MRI characteristics of Wml are similar to those of gray matter. Intensity‐based statistical classification techniques misclassify some Wml as gray matter and some gray matter as Wml. We developed a fast elastic matching algorithm that warps a reference data set containing information about the location of the gray matter into the approximate shape of the patient's brain. The region of white matter was segmented after segmenting the cortex and deep gray matter structures. The cortex was identified by using a three‐dimensional, region‐growing algorithm that was constrained by anatomical, intensity gradient, and tissue class parameters. White matter and Wml were then segmented without interference from gray matter by using a two‐class minimum‐distance classifier. Analysis of double‐echo spin‐echo MRI scans of 16 patients with clinically determined multiple sclerosis (MS) was carried out. The segmentation of the cortex and deep gray matter structures provided anatomical context. This was found to improve the segmentation of MS lesions by allowing correct classification of the white matter region despite the overlapping tissue class distributions of gray matter and MS lesion. J Image Guid Surg 1:326–338 (1995). © 1996 Wiley‐Liss, Inc. Copyright © 1996 Wiley‐Liss, Inc.

关键词： gray matter MRI MS lesion segmentation

来源：评论

学校读者我要写书评

暂无评论

Hough transform for vehicle identification

Hough transform for vehicle identification

引用

1993 Intelligent Vehicles Symposium, IV 1993

作者： Kamat, V. Altan, O. Ganesan, S. Department of Computer Science and Engineering Oakland University RochesterML48309-4401 United States

This paper describes a vision based vehicle identification algorithm. This algorithm has been developed using image processing and pattern recognition techniques. This paper describes the role of the image processing ... 详细信息

ISBN: (纸本)0780313704

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

Rule based design of a multilayer perceptron

Rule based design of a multilayer perceptron

引用

International Joint Conference on Neural Networks (IJCNN)

作者： P.K. Chande M. Shrivastava Center for AI and Robotics Department of Computer Engineering Shri G.S. Institute of Technology and Science Indore Madhya Pradesh India

Multilayer perceptrons (mlP) trained with backpropagation algorithm are popular because they offer certain desirable features. However, the training is time consuming which further limits its use in changing environment. We propose a methodology to partially designs mlP network using formal knowledge-rules and augmenting it with another neural network trained using labeled examples. The approach has the potential of reducing the training time and enables online changes in the user environment. The software developed is being used in a process control system.

关键词： Multilayer perceptrons Neural networks Backpropagation algorithms Diagnostic expert systems Expert systems Artificial intelligence Robots Design methodology Process control Automatic control

来源：评论

学校读者我要写书评

暂无评论

AUTONOMOUS ADAPTIVE SYNCHRONOUS MACHINE CONTROL

引用

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 1992年第2-3期14卷 166-174页

作者： SOBAJIC, DJ PAO, YH LEE, DT Department of Electrical Engineering and Computer Science Case Western Reserve University and AI WARE Inc. Cleveland OH 44106 USA

In this paper, we present a design of a new adaptive control system and demonstrate its performance in a computer simulation of nonlinear synchronous machine control. The new design utilizes self-organization and the predictive estimation capabilities of neural-net computing. Real-time adaptation is facilitated by the error-based on-line learning scheme implemented on a cluster-wise segmented associative memory system. It is demonstrated that the neural network system is capable of modelling highly nonlinear systems, detecting changes in the dynamic process conditions and stabilizing the system.

关键词： NONLINEAR TIME-VARYING MULTIVARIABLE ADAPTIVE CONTROL ASSOCIATIVE MEMORIES SPEED AND VOLTAGE REGULATION

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE POWER SYSTEM CONTROL WITH NEURAL NETWORKS

ADAPTIVE POWER SYSTEM CONTROL WITH NEURAL NETWORKS

引用

1992 International Joint Conference on Neural Networks, IJCNN 1992

作者： Lee, Dennis T. Sobajic, Dejan J. Pao, Yoh-Han Department of Electrical Engineering and Computer Science Case Western Reserve University AI WARE Inc. ClevelandOH44106 United States

ISBN: (纸本)0780305590

In this paper, we present a design of a new adaptive control system and demonstrate its performance in a computer simulation of a synchronous machine control task. The new design utilizes self-organization and predictive estimation capabilities of neural-net computing. The task of real-time adaptation is carried out using an error-based on-line learning scheme which is implemented on a cluster-wise segmented associative memory system. We demonstrate the performance self-improving capability of the new control system and also present the possibility of using the existing control device in a supporting mode during a preliminary phase of the controller design. © 1992 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Adaptive control 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：