检索结果-内蒙古大学图书馆

Speckle Suppression with Edges Preservation for Ultrasound Images

AIP Conference Proceedings 2011年第1期1371卷 44-54页

作者： Mong‐Shu Lee Cho‐Li Yen Shyh‐Kuang Ueng aDepartment of Computer Science and Engineering National Taiwan Ocean University Taiwan bDepartment of Internal Medicine Keelung Chang Gung Memorial Hospital Taiwan

In this paper, a novel speckle reduction method is proposed for ultrasound images. This denoising method is designed to preserve both the edges and structural details of the image. Speckle noise is suppressed, without smearing the edges, by extending the smoothness of the image in the wavelet‐based Hölder spaces. A comparison of smoothing speckles with the other well known methods is provided via the size of Besov norm. We validate the proposed method using synthetic data and simulated ultrasound images. Experiments demonstrate the performance improvement of the proposed method over other state‐of‐the‐art methods in terms of image quality and edge preservation indices.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Ad Hoc Routing Protocols in City Scenario for VANET

引用

AIP Conference Proceedings 2011年第1期1414卷 257-261页

作者： Sanjoy Das Ram Shringar Raw Indrani Das aSchool of Computer & Systems Sciences Jawaharlal Nehru University New Delhi India bDepartment of Computer Science and Engineering Ambedkar Institute of Technology Delhi India cDepartment of Computer Science Assam University Assam India

In this paper, performance analysis of Location Aided Routing (LAR), AODV and DSR protocol in city scenarios has been done. The mobility model considered is Manhattan model. This mobility model used to emulate the movement pattern of nodes i.e., vehicles on streets defined by maps. Our objective is to provide a comparative analysis among LAR, AODV and DSR protocol in city scenarios in Vehicular Ad hoc Networks. The simulation work has been conducted using the Glomosim 2.03 simulator. The results show that LAR1 protocol achieves maximum packet delivery ratio is 100% in the sparsely populated network. The delay is maximum in AODV 121.88 ms when the number of node is 10 in the network. The results show that LAR1 outperform DSR and AODV in term of packet delivery ratio and end to end delay.

关键词：

来源：评论

学校读者我要写书评

暂无评论

computer Simulation of Point Defects in CoO and NiO

引用

AIP Conference Proceedings 2011年第1期1349卷 873-874页

作者： S. D. V. Prasad B. Srinivasa Rao S. Jagadeesh Babu N. Radhika S. P. Sanyal aDepartment of Computer Science & Engineering Malla Reddy Engineering College Maisammaguda Hakimpet Medchal Hyderabad India‐500014 bDepartment of Physics Barkatullah University Bhopal‐ 462026 (India)

We present a computer simulation study of effects of three‐body interactions (TBI) on Schottky defect properties of some transition metal oxides (TMO). The calculations have been done in the framework of polarizable point ion (PPI) model and using the three‐body interaction potential (TBP). The computed cohesive and schottky formation energy are in good agreement with the experimental data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Classification From Histological Images with Multiple Features and Random Subspace Classifier Ensemble

引用

AIP Conference Proceedings 2011年第1期1371卷 19-28页

作者： Yungang Zhang Bailing Zhang Wenjin Lu aDepartment of Computer Science & Software Engineering Xi’an JiaoTong‐Liverpool University Suzhou 215123 P. R. China bDepartment of Computer Science University of Liverpool L69 3BX United Kingdom

Histological image is important for diagnosis of breast cancer. In this paper, we present a novel automatic breaset cancer classification scheme based on histological images. The image features are extracted using the Curvelet Transform, statistics of Gray Level Co‐occurence Matrix (GLCM) and Completed Local Binary Patterns (CLBP), respectively. The three different features are combined together and used for classification. A classifier ensemble approach, called Random Subspace Ensemble (RSE), are used to select and aggregate a set of base neural network classifiers for classification. The proposed multiple features and random subspace ensemble offer the classification rate 95.22% on a publically available breast cancer image dataset, which compares favorably with the previously published result 93.4%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Geometry of Pre‐contrast Functions and Non‐conservative Estimating Functions

引用

AIP Conference Proceedings 2011年第1期1340卷 32-41页

作者： Masayuki Henmi Hiroshi Matsuzoe aThe Institute of Statistical Mathematics 10‐3 Midori‐cho Tachikawa Tokyo 190‐8562 Japan bDepartment of Computer Science and Engineering Graduate School of Engineering Nagoya Institute of Technology Nagoya 466‐8555 Japan

This paper introduces the notion of pre‐contrast functions and studies their geometric properties. A contrast function is an asymmetric squared distance like function. A pre‐contrast function corresponds to the differential of a contrast function, however, it is not integrable in general. While a contrast function induces a statistical manifold, a pre‐contrast function induces a statistical manifold admitting torsion. As an application of pre‐contrast functions, geometry of non‐conservative estimating functions in statistics is also studied.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SYNTHESIS OF FEEDBACK CONTROLLER FOR CHAOTIC SYSTEMS BY MEANS OF EVOLUTIONARY TECHNIQUES

引用

AIP Conference Proceedings 2011年第1期1337卷 273-279页

作者： Roman Senkerik Zuzana Oplatkova Ivan Zelinka Donald Davendra Roman Jasek aTomas Bata University in Zlin Faculty of Applied Informatics Nad Stranemi 4511 762 72 Zlin Czech Republic bDepartment of Computer Science Faculty of Electrical Engineering and Computer Science VB‐TUO 17. listopadu 15 708 33 Ostrava‐Poruba Czech Republic

This research deals with a synthesis of control law for three selected discrete chaotic systems by means of analytic programming. The novality of the approach is that a tool for symbolic regression—analytic programming—is used for such kind of difficult problem. The paper consists of the descriptions of analytic programming as well as chaotic systems and used cost function. For experimentation, Self‐Organizing Migrating Algorithm (SOMA) with analytic programming was used.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS OF A CONCENTRIC COPLANAR CAPACITIVE SENSOR USING A SPECTRAL DOMAIN APPROACH

引用

AIP Conference Proceedings 2011年第1期1335卷 1647-1654页

作者： Tianming Chen Jiming Song John R. Bowler Nicola Bowler aCenter for Nondestructive Evaluation Iowa State University Ames IA 50011 bDepartment of Electrical and Computer Engineering Iowa State University Ames IA 50011 cDepartment of Materials Science and Engineering Iowa State University Ames IA 50011

Previously, concentric coplanar capacitive sensors have been developed to quantitatively characterize the permittivity or thickness of one layer in multi‐layered dielectrics. Electrostatic Green’s functions due to a point source at the surface of one‐ to three‐layered test‐pieces were first derived in the spectral domain, under the Hankel transform. Green’s functions in the spatial domain were then obtained by using the appropriate inverse transform. Utilizing the spatial domain Green’s functions, the sensor surface charge density was calculated using the method of moments and the sensor capacitance was calculated from its surface charge. In the current work, the spectral domain Green’s functions are used to derive directly the integral equation for the sensor surface charge density in the spectral domain, using Parseval’s theorem. Then the integral equation is discretized to form matrix equations using the method of moments. It is shown that the spatial domain approach is more computationally efficient, whereas the Green’s function derivation and numerical implementation are easier for the spectral domain approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Electroluminescence from the fluorine‐plasma treated Ni/Au‐AlGaN/GaN Schottky diode

引用

AIP Conference Proceedings 2011年第1期1399卷 113-114页

作者： B. K. Li M. J. Wang K. J. Chen J. N. Wang aDepartment of Physics Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong China bDepartment of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong China

The effect of fluorine‐plasma (F‐plasma) treatment on current‐voltage and electroluminescence (EL) characteristics of Ni/Au‐AlGaN/GaN Schottky diode were investigated. It was found that the EL spectrum was dominated by the GaN near bandedge emissions with a rather small turn on current for EL emission. We propose that the F‐related deep centers induced by the F‐plasma treatment assist the hole injection processes through hopping conduction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AN INVESTIGATION ON EVOLUTIONARY IDENTIFICATION OF CONTINUOUS CHAOTIC SYSTEMS

引用

AIP Conference Proceedings 2011年第1期1337卷 280-284页

作者： Ivan Zelinka Donald Davendra Roman Senkerik Roman Jasek aDepartment of Informatics and Artificial Intelligence Tomas Bata University in Zlin Nad Stráněmi 4511 Zlin 76001 Czech Republic bDepartment of Computer Science Faculty of Electrical Engineering and Computer Science VSB‐TUO 17. listopadu 15 708 33 Ostrava‐Poruba Czech Republic

This paper discusses the possibility of using evolutionary algorithms for the reconstruction of chaotic systems. The main aim of this work is to show that evolutionary algorithms are capable of the reconstruction of chaotic systems without any partial knowledge of internal structure, i.e. based only on measured data. Algorithm SOMA was used in reported experiments here. Systems selected for numerical experiments here is the well‐known Lorenz system. For each algorithm and its version, repeated simulations were done, totaling 20 simulations. According to obtained results it can be stated that evolutionary reconstruction is an alternative and promising way as to how to identify chaotic systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Portable Electronic Nose System for Identification of Synthesized Gasoline Using Metal Oxide Gas Sensor and Pattern Recognition

引用

AIP Conference Proceedings 2011年第1期1362卷 113-114页

作者： Young Wung Kim Hong Bae Park In Soo Lee Jung Hwan Cho cSchool of Electrical Engineering and Computer Science Kyungpook National University Daegu 702‐701 South Korea aSchool of Electronic & Electrical Engineering Kyungpook National University Sangju Kyungpook 742‐711 South Korea bDepartment of Civil and Environmental Engineering University of Massachusetts Lowell Lowell MA 01854 USA

This paper describes a portable electronic nose (e‐nose) system for use in the identification of synthesized gasoline, comprised of a single semiconductor type of gas sensor and pattern recognition neural networks. The designed e‐nose system consists of a one‐chip microcontroller, a pre‐concentrator, and a gas sensor. Two different neural networks, a multilayer perceptron (MLP) neural network and a fuzzy ARTMAP neural network were applied to discriminate synthesized gasoline from normal gasoline. The results of the classification showed 100% and 85% recognition rates for the training data set and testing data set, respectively.

关键词：

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：