检索结果-内蒙古大学图书馆

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： L. Chen K.P. Chan T.Q. Nguyen Y. Zheng Department of Computer Science University of Hong Kong Hong Kong China Department of Electrical Computer Engineering University of Wisconsin Madison USA Institute of AI & PR University of Shantou China

In this paper, a new design algorithm is presented for a family of linear phase paraunitary filter banks with generalized filter length and symmetric polarity. A number of new constraints on the distributions of filter length and symmetry polarity among the channels are derived. In the algorithm, the lengths of the filters are gradually reduced through a cascade of lattice structures. The derivations for filter banks with even and odd number of channels are formulated in a unified form.

关键词： Digital filters Filter bank Finite impulse response filter Channel bank filters Lattices computer science Design engineering Artificial intelligence Strontium Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Automatic feature extraction of facial organs and contour

Automatic feature extraction of facial organs and contour

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： F. Hara K. Tanaka H. Kobayashi A. Tange Department of Mechanical Engineering Science University of Tokyo Shinju Tokyo Japan AI Laboratory Department of Computer Science University of Zurich Zurich Switzerland Sony Company Limited Tokyo Japan

This paper deals with algorithms for extracting contour lines of eyebrow, eye, nose, mouth, and face contour. First we extract the position of both irises using a correlation technique. Then for the eyebrow, edge-image data are used for determining the position of the eyebrow and the contour of the eyebrow is obtained from binary image data around the eye area. For eyes, the edge between the eyeball and skin is determined easily since the edge is clearly differentiated in the brightness distribution of the image data. For the nose, the edge clearly appears in the image data and then the correlation can determine the nose contour. For the mouth, the position of mouth is determined from image-edge information and brightness distribution and then the correlation can determine the most outer corner points of the mouth. We employ an image energy function to be minimized for obtaining the face contour and a dynamic programming like algorithm is used to obtain the minimum. An average human face contour used as a template can give a good extraction of the face contour.

关键词： Feature extraction Eyebrows Mouth Nose Data mining Brightness Face Waveguide discontinuities Eyes Skin

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a WWW-based database system to support software development of computer-generated forces for US Army simulation training

Design and implementation of a WWW-based database system to ...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： R.G. Phelan M.D. McNett M.L. McGinnis Intelligence Center ODISC4 ATTN: SAIS AI U.S. Army Artificial Washington D.C. DC USA Department of Electrical Engineering and Computer Science United States Military Academy West Point NY USA Center Monterey ATTN: ATRC RDM U.S. Army TRADOC Analysis Center Monterrey CA USA

The World Wide Web (WWW) has opened new frontiers for presenting and collecting information from sources around the world. Web browsers provide Internet users with access to information vast amounts of information. This paper addresses the design, development and implementation of a multi-user database system for the World Wide Web to query subject matter experts during development of mission training plans for the Army's new Warfighter's Simulation (WARSIM) 2000. Currently, 262 Army mission training plans for Army units from platoon to corps have been input into in a database repository by subject matter experts using the Internet-based system. The paper discusses how the system converts data from the database to hypertext markup language through the use of the common gateway interface. The system also stores and links individual user input by MTP task through each step of the elicitation process so that previously entered input is available each time a user logs on to the system.

关键词： Database systems Programming Military computing Computational modeling Web sites computer simulation Internet Analytical models Artificial intelligence World Wide Web

来源：评论

学校读者我要写书评

暂无评论

Alarms: An implementation of motivated agency 2nd

Alarms: An implementation of motivated agency

引用

International Joint Conference on Artificial Intelligence, IJCai 1995 held with the 2nd Workshop on Agent Theories, Architectures, and Languages, ATAL 1995

作者： Norman, Timothy J. Long, Derek Distributed AI Unit Department of Electronic Engineering Queen Mary and Westfield College University of London LondonE1 4NS United Kingdom Department of Computer Science University of Durham DurhamDH1 3HP United Kingdom

ISBN: (纸本)3540608052

Autonomous agents in the real world must be capable of asynchronous goal generation. However, one consequence of this ability is that the agent may generate a substantial number of goals, but only a small number of these will be relevant at any one time. Therefore, there is a need for tractable mechanisms to manage a changing and potentially large number of goals. This paper presents both a framework for the design of agents that have the capability to generate and manage their own top level goals, "motivated agency", and an implementation of part of this agent architecture, "alarms". The alarm-processing machinery serves to focus the attention of an agent on a limited number of the most salient goals regardless of the number of possible goals that the agent can pursue or their distribution in time. In this way, a resource-bounded autonomous agent can employ modern planning methods to greater effect. © Springer-Verlag Berlin Heidelberg 1996.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

Skeletonizing by compressed line adjacency graph in two directions

Skeletonizing by compressed line adjacency graph in two dire...

引用

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

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：