检索结果-内蒙古大学图书馆

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Z. Ameur A. Adane S. Ameur Faculty of Electrical Engineering and Computer Science Department of Electronics Laboratory of Random Phenomena Analysis and Modeling LAMPA Mouloud Mammeri University Tizi Ouzou Algeria Faculty of Electronics and Computer Science Department of Telecommunications Laboratory of Image Processing and Radiation University of Sciences and Technology of Algiers U. S. T. H. B. Bab-Ezzouar Algeria

In many cases, an image is made of various types of texture. Such diversity can be usefully exploited to get a suitable decomposition of the image into typical classes and then, identify its constitutive elements. Among the approaches used to segment textured images, those based on the statistical analysis of the neighborhood of each pixel seem to be most efficient. In this paper, this kind of method is implemented, which consists in coding the pixels surrounding each point of the image by taking into account the path traveling through them and their grey levels. The rank vectors namely the codes obtained for all the possible paths, are then classified using the K-means algorithm. Considering the 24- rank vectors, this method is tested on different images of the Brodatz album and compared with Laws filters and GLCM. It yields a satisfactory reproduction of the image contours and a classification ratio exceeding 98 %. The 24 rank based-method is also applied to meteorological images collected by Meteosat over Europe and North Africa during December 1994. It is found that these images can be segmented into eight typical classes assignable to the soils, the seas and the clouds observed in the regions under study.

关键词： Image segmentation Pixel Statistical analysis Image coding Testing Filters Meteorology Europe Africa Soil

来源：评论

学校读者我要写书评

暂无评论

Medical Data Mining using Particle Swarm Optimization for Temporal Lobe Epilepsy

Medical Data Mining using Particle Swarm Optimization for Te...

引用

Congress on Evolutionary Computation

作者： M. Ghannad-Rezaie H. Soltanain-Zadeh M.-R. Siadat K.V. Elisevich Henry Ford Health System and Wayne State University Detroit MI USA Radiology Image Analysis Laboratory Henry Ford Health System Detroit MI USA Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran Neurosurgery Department Henry Ford Health System Detroit MI USA

In clinical problems, numerous factors are usually involved in a medical syndrome. New advances in medicine provide a broad range of diagnosis methods to cover all aspects of a disease. However, huge amounts of raw information may confuse clinicians and decrease decision accuracy. computerized knowledge extraction is an active area of research in medical informatics. This paper suggests a new medical data mining approach using an advanced swarm intelligence data mining algorithm. Considering medical knowledge discovery difficulties, this approach addresses common issues such as missing value management and interactive rule extraction. Here, surgery candidate selection in temporal lobe epilepsy is the main target application. However, the general idea can be applied to other medical knowledge discovery problems. Experimental results show noticeable performance improvement in the final rule-set quality while the method is flexible and fast.

关键词： Data mining Particle swarm optimization Temporal lobe Epilepsy Medical diagnostic imaging Biomedical imaging Coronary arteriosclerosis Diseases Surgery Medical services

来源：评论

学校读者我要写书评

暂无评论

Simulation of infrared bandpass filter using three-dimensional FDTD method

引用

Wuhan Ligong Daxue Xuebao/Journal of Wuhan University of Technology 2006年第1期28卷 102-104页

作者： Wang, Lin Zhang, Lin Zhou, Jian Qiang, Rui Chen, Ji School of Information Engineering Wuhan University of Technology Wuhan 430070 China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Wuhan University of Technology Wuhan 430070 China Department of Electrical and Computer Engineering University of Houston Housten United States

In this research, we developed a three-dimensional finite-difference-time-domain algorithm that incorporated the Lorentz-Drude model through the use of Z-transform technique. This algorithm was used to compute the spectral response of infrared bandpass filters which consisted of the openings of cross-shaped structures in a thin gold film. In creating structures, a graphical user interface was built using Matlab development environment. The created structures were then simulated by running the simulation code written in Fortran. It was observed that cross-shaped structures with large center-broadening effect yielded the highest transmission intensity among the structures that were simulated with a transmittance of approximately 80% at the wavelength of 1.2 μm.

关键词： FDTD Infrared bandpass filter Three-dimensional simulation

来源：评论

学校读者我要写书评

暂无评论

Sustained petaflop and beyond: Can parallel computing systems meet the challenges?

Sustained petaflop and beyond: Can parallel computing system...

引用

19th IEEE International parallel and Distributed processing Symposium, IPDPS 2005

作者： Gao, Guang R. Computer Architecture and Parallel System Laboratory Dept. of Electrical and Computer Engineering University of Delaware Department of Electrical and Computer Engineering University of Delaware

ISBN: (纸本)0769523129

Breakthrough-quality scientific discoveries in the new millennium (such as those expected in computation biology and others), along with optimal engineering designs, have created a demand for High-End Computing (HEC) systems with sustained performance requirements at a petaflop scale and beyond. Despite the very pessimistic (if not negative) views on parallel computing systems that have prevailed in 1990s, there seems to be no other viable alternatives for such HEC systems. In this talk, we present a fresh look at the problems facing the design of petascale parallel computing systems. We review several fundamental issues that such HEC parallel computing systems must resolve. These issues include: execution models that support dynamic and adaptive multithreading, fine-grain synchronization, and global name-space and memory consistency. Related issues in parallel programming, dynamic compilation models, and system software design will also be discussed. Present solutions and future direction will be discussed based on (1) application demand (e.g. computation biology and others), (2) the recent trend as demonstrated by the HTMT, HPCS, and the Blue-Gene Cyclops (e.g. Cyclops-64) architectures, and (3) a historical perspective on influential models such as dataflow, along with concepts learned from these models.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

A critique of java for concurrent programming

引用

IEEE Distributed Systems Online 2005年第9期6卷

作者： Garg, Vijay K. Mittal, Neeraj University of Texas Austin University of Texas Dallas Electrical and Computer Engineering Department University of Texas Austin University's Parallel Distributed Systems Laboratory Department of Computer Science University of Texas Dallas

A comparative study between Java and Avaj, a concurrent programming language, is presented. java uses wait (), notify (), and notifyAll () construct to support monitors, while Avaj simply supports the construct await (B), where B is any Boolean expression. The syntax for the Avaj abort () construct is simple and allows programmer to call abort () inside any method. Avaj also incorporates the selective communication construct in the language. The invariant (B) construct in Avaj allows a Boolean expression to be invariant in a program.

关键词： Java programming language

来源：评论

学校读者我要写书评

暂无评论

Knowledge based unification of medical archives

Knowledge based unification of medical archives

引用

5th International Network Conference, INC 2005

作者： Diou, C. Falelakis, M. Delopoulos, A. Electrical and Computer Engineering Department Information Processing Laboratory Aristotle University of Thessaloniki Greece

ISBN: (纸本)9781841022727

In this paper, the structure of a system is proposed that aims at providing clinicians with easy-to-use, well structured and accurate medical information for support of diagnosis, treatment, medical research and education that will be automatically concentrated from multiple sources. The collection and processing of such information (even in its digital form) is not a straightforward task because of three main constraints: Disparity, dispersion and voluminosity. The proposed model attempts to overcome the aforementioned obstacles by exploiting emerging multimedia database technologies. The most important aspect of the proposed system is its capability to handle user's queries at a semantic level by referring to respective medical knowledge bases that encapsulate relevant medical expertise. Core components of the system are tools that help clinicians or researchers to perform effective content-based search and retrieval of medical information that matches their interests. © 2005 University of the Aegean and University of Plymouth.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

An efficient distributed algorithm for constructing delay- and degree-bounded application-level multicast tree

An efficient distributed algorithm for constructing delay- a...

引用

8th International Symposium on parallel Architectures, Algorithms and Networks, I-SPAN 2005

作者： Feng, Liu Jingshu, Huang Xicheng, Lu Yuxing, Peng National Laboratory for Parallel and Distributed Processing Changsha 410073 China School of Electrical and Computer Engineering Purdue University West Lafayette IN 47907-2035 United States

ISBN: (纸本)0769525091

In this paper we investigate the problem of finding a delay- and degree-bounded maximum sum of nodes application level multicast tree. We then proved the problem is NP-hard, and its relationship with the well-studied degree-bounded minimum maximum-delay multicast tree problem. We propose a distributed algorithm - OverStream, which adopts PPAF heuristic for father node to choose optimal child nodes based on multiple network parameters. Simulation results show that our algorithm is better than OMNI, SpreadIt, HMTP, and Zigzag in general. © 2005 IEEE.

关键词： Algorithms

来源：评论

学校读者我要写书评

暂无评论

Color reduction by using a new self-growing and self-organized neural network

Color reduction by using a new self-growing and self-organiz...

引用

2nd International Conference on Video, Vision and Graphics, VVG 2005

作者： Atsalakis, A. Papamarkos, N. Image Processing and Multimedia Laboratory Department of Electrical and Computer Engineering Democritus University of Thrace 67100 Xanthi Greece

ISBN: (纸本)9783905673579

A new method for the reduction of the number of colors in a digital image is proposed. The new method is based on the developed of a new neural network classifier that combines the advantages of the Growing Neural Gas (GNG) and the Kohonen Self-Organized Feature Map (SOFM) neural networks. We call the new neural network: Self-Growing and Self-Organized Neural Gas (SGONG). Its main advantage is that it defines the number of the created neurons and their topology in an automatic way. As a consecutive, isolated color classes, which may correspond to significant image details, can be obtained. The SGONG is fed by the color components and additional spatial features. To speed up the entire algorithm and to reduce memory requirements, a fractal scanning sub-sampling technique is used. The method is applicable to any type of color images and it can accommodate any type of color space. © The Eurographics Association 2005.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

A time-frequency signal analysis system for power quality assessment

A time-frequency signal analysis system for power quality as...

引用

2005 IEEE International 48th Midwest Symposium on Circuits and Systems, MWSCAS 2005

作者： Rivera, Ivan J. Ramirez, Ana B. Rodriguez, Domingo Automated Information Processing Laboratory Electrical and Computer Engineering Department University of Puerto Rico Mayaguez PR 00681-4092

ISBN: (纸本)0780391977

The purpose of this work is to develop a time-frequency signal analysis system to detect and recognize different kinds of power quality events or disturbances. To achieve our goal, design of computational signal processing methods is being addressed developing time-frequency tools based on signal algebra operators. The use of signal algebra operators permits the formulation of time-frequency algorithms in a computational framework setting, allowing the search for efficient hardware implementations. Time-frequency formulations are being implemented for embedded system applications using Digital Signal processing (DSP) and field programmable gate array (FPGA) units. Voltage disturbances are responsible for many disruptions in industrial, commercial and residential power supply systems, causing time and monetary losses. It is necessary to identify fast methods of determining when these disturbances are occurring in order to make correct power quality decisions. Automated information processing systems are needed to assess existing problems. Although a lot of work has been done on power line disturbance assessment, new techniques are desired to address new challenging power quality issues, specially in the area of physical security. Time-frequency signal analysis is a well known tool used in fields such as speech, sonar, and radar processing and is now finding its being in power quality assessment. A time-frequency representation is a two-dimensional representation that shows how the spectral content of a given signal changes with time. There is a genuine interest in this kind of representations for the field of power quality signal analysis systems since they provide more information than the typical one dimensional analysis. To achieve the goals of this work an environment is being created using MATLAB to simulate power line signal disturbances such as swells, sags, harmonic distortions, and outages. This environment computes desired time-frequency representations of

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

Brain MR image segmentation using tabu search and hidden markov random field model

Brain MR image segmentation using tabu search and hidden mar...

引用

2nd Indian International Conference on Artificial Intelligence, IICAI 2005

作者： Nanda, P.K. Patra, D. Pradhan, A. Department of Electrical Engineering Image Processing and Computer Vision Laboratory National Institute of Technology Rourkela Orissa 769008 India

ISBN: (纸本)0972741216

In this paper, we propose a hybrid Tabu Expectation Maximization (TEM) Algorithm for segmentation of Brain Magnetic Resonance (MR) images in both supervised and unsupervised framewrok. Gaussian Hidden Markov Random Field (GHMRF) is used to model the available degraded image. In supervised framework, the apriori image MRF model parameters as well as the GHMRF model parameters are assumed to be known. The class labels are estimated using the Maximum a Posteriori (MAP) estimation criterion. In unsupervised framework, the problem of model parameter estimation and label estimation is formulated in Expectation Maximization (EM) framework. The labels are estimated using the proposed Tabu Search algorithm while the model parameters are the maximum likelihood estimates. Our proposed algorithm yields results with arbitrary initial paramater set and thus overcomes the problem of proper choice of initial parameters. The results obtained are comparable with the results obtained by using the algorithm proposed by Zhang ***. [15] , where the Iterated Conditional Mode (ICJM) algorithm is used for computing the MAP estimates. Copyright © IICAI 2005.

关键词： Tabu search

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：