检索结果-内蒙古大学图书馆

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： Hyun-il Kwon Jaehong Park Wonsang Hwang Jong-hyeon Kim Chang-hun Lee M. Latif Anjum Kwang-soo Kim Dong-il Cho Automation and Systems Research Institute and School of Electrical Engineering and Computer Science Inter-University Semiconductor Research Center Seoul South Korea Department of Control and Instrumentation Engineering Hanbat National University Daejeon South Korea

This paper presents a vision tracking system to achieve high recognition performance under dynamic circumstances, using a fuzzy logic controller. The main concept of the proposed system is based on the vestibulo-ocular reflex (VOR) and the opto-kinetic reflex (OKR) of the human eye. To realize the VOR concept, MEMS inertial sensors and encoders are used for robot motion detection. This concept turns the camera towards a selected target, counteracting the robot motion. Based on the OKR concept, the targeting errors are periodically compensated, using vision information. The fuzzy logic controller uses sensor data fusion to detect slip or collision occurrences. To calculate a heading angle of the camera accurately, the output of the fuzzy logic controller and the vision information from the camera are combined, using an extended Kalman filter. The proposed vision tracking system is implemented in a mobile robot and evaluated experimentally. The experimental results are obtained as the tracking and the recognition success rate using a mobile robot. The developed system achieved the excellent tracking and recognition performance during slip or collision occurrences under dynamic circumstances.

关键词： Cameras Mobile robots Robot vision systems Machine vision Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Modeling nonlinear medical ultrasound via a linearized contrast source method

Modeling nonlinear medical ultrasound via a linearized contr...

引用

作者： Demi, L. Verweij, M.D. De Jong, N. Van Dongen, K.W.A. Laboratory of Acoustical Imaging and Sound Control Faculty of Applied Sciences Delft University of Technology Netherlands Laboratory of Electromagnetic Research Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Netherlands Laboratory of Experimental Echocardiography Erasmus Medical Center Rotterdam Netherlands

ISBN: (纸本)9781457703829

research on nonlinear medical ultrasound has been increased over the last decade and has resulted in a wide range of numerical methods for the modeling of the nonlinear distortion of a propagating pressure wave. However, when applied to realistic configurations, the majority of these methods are either computationally expensive or limited by the applied approximations. The Iterative Nonlinear Contrast Source (INCS) method is able to accurately compute the pulsed nonlinear pressure wave field that is generated in a large three-dimensional domain by an arbitrary transducer transmitting under a large steering angle. The method is based on the Neumann iterative solution of a nonlinear integral equation that is equivalent to the Westervelt equation. To improve the performance of the method, it would be beneficial to employ iterative schemes (e.g. Conjugate Gradient based schemes) that are efficient for solving linear integral equations. This motivates the development of a linearized version of the INCS method, as presented in this paper. To test the presented approach, a Bi-CGSTAB scheme is used to solve the linearized Westervelt equation. For the one-dimensional case, results are obtained and compared with the solution obtained with the original INCS method, and the Fubini solution. All the results have been obtained up to the third harmonic component and are in agreement with each other. © 2010 IEEE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Modeling nonlinear acoustic wave fields in media with inhomogeneity in the attenuation and in the nonlinearity

Modeling nonlinear acoustic wave fields in media with inhomo...

引用

ISBN: (纸本)9781457703829

Biomedical tissues usually show inhomogeneity in their acoustic medium parameters. These inhomogeneities cause refraction and scattering of diagnostic and therapeutic ultrasound waves. A method that is able to model the effects of inhomogeneity in the attenuation and in the nonlinearity is essential for the design of transducers for new ultrasound modalities and the development of novel ultrasound applications. The Iterative Nonlinear Contrast Source (INCS) method has originally been designed for the accurate modeling of nonlinear acoustic wave fields in homogeneous media. It considers the nonlinear term from the Westervelt equation as a distributed contrast source, and the corresponding integral equation is solved using an iterative Neumann scheme. This paper presents an extension of the INCS method that can handle inhomogeneity in the attenuation and in the coefficient of nonlinearity. Results are presented for the one-dimensional case. These show that in this case the presented method correctly predicts the effects related to nonlinear propagation and scattering by inhomogeneities in the attenuation and the coefficient of non-linearity. © 2010 IEEE.

关键词： Integral equations

来源：评论

学校读者我要写书评

暂无评论

Prediction of financial time series with recurrent LoLiMot (locally linear model tree)

Prediction of financial time series with recurrent LoLiMot (...

引用

International Conference on computer and Automation engineering, ICCAE

作者： Hossein Chegini Caro Lucas Science and research Branch/Computer Science Islamic Azad university of Tehran Tehran Iran Electrical and Computer Engineering Department Control and Intelligent Processing Center of Excellence University of Tehran Tehran Iran

ISBN: (纸本)9781424455690

The tolerance and non-stability in financial indexes make changes to other sub-systems like human resources, economics, factory productions and etc. Having underling knowledge and a model to simulate such systems obtains a fine vision to estimate further and calculate hard-decision making tasks before execution like: dept from banks, cash injecting and insurance services. Using Neuro-fuzzy networks are one of the most powerful tools for this estimation. The particular locally linear model type of these networks called LoLiMot are in interest because of their linear training and construction optimization. These network can be much efficient when be a recurrent network why can better capture the dynamism's order of dynamic processes. The Locally linear Neuro-Fuzzy model (LoLiMot) here is as basis for making recurrent. In this paper this network with a global state feedback is implemented and the accuracy and the results of this recurrent network on Dow Jones index as a financial time series are compared with the static LoLiMot. The obtained results were better.

关键词： Predictive models State feedback Neurons Output feedback Power system modeling Gaussian processes control engineering computing Process control Intelligent control computer science

来源：评论

学校读者我要写书评

暂无评论

An Effective Feature Extraction Method for Facial Expression Recognition using Adaptive Gabor Wavelet

An Effective Feature Extraction Method for Facial Expression...

引用

The 2010 IEEE International Conference on Progress in Informatics and Computing

作者： Behzad Oshidari Babak N.Araabi Faculty of Engineering Islamic Azad UniversityScience and Research BranchTehranIran Control and Intelligent Processing Center of Excellence School of Electrical and Computer Eng.University of TehranTehranIran

Feature extraction is an important and challenging phase of facial expression recognition *** this paper,an effective feature extraction method is *** facial feature representation method is based on an adaptive Gabor wavelet *** this method,we used a fuzzy controller for tuning the orientation parameter of *** filter can detect the most significant edges of facial ***,the proposed adaptive filter improves the drawbacks of conventional Gabor *** neighbor and multi-class Support Vector Machine(SVM) classifiers are applied for classification task. Experimental results on Japanese Female Facial Expression (JAFFE) database show that the proposed method can provide high recognition *** main advantage of proposed method over other methods is its flexibility.

关键词： adaptive Gabor wavelet transform facial expression recognition fuzzy controller multi-class support vector machine classifier nearest neighbor classifier

来源：评论

学校读者我要写书评

暂无评论

High performance vision tracking system for mobile robot using sensor data fusion with Kalman filter

High performance vision tracking system for mobile robot usi...

引用

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： Jaehong Park Wonsang Hwang Hyun-il Kwon Jong-hyeon Kim Chang-hun Lee M. Latif Anjum Kwang-soo Kim Dong-il Cho Automation and Systems Research Institute (ASRI) and School of Electrical Engineering and Computer Science Inter-University Semiconductor Research Center Seoul South Korea South Korea Department of Control and Instrumentation Engineering Hanbat National University Daejeon South Korea

This paper introduces a high performance vision tracking system for mobile robot using sensor data fusion. For mobile robots, it is difficult to collect continuous vision information due to robot's motion. To solve this problem, the proposed vision tracking system estimates the robot's position relative to a target and rotates the camera towards the target. This concept is derived from the human eye reflex mechanism, known as the Vestibulo-Ocular Reflex (VOR), for compensating the head motion. This concept for tracking the target results in much higher performance levels, when compared with the conventional method that rotates the camera using only vision information. The proposed system do not require heavy computing loads to process image data and can track the target continuously even during vision occlusion. The robot motion information is estimated using data from accelerometer, gyroscope, and encoders. This multi-sensor data fusion is achieved using Kalman filter. The proposed vision tracking system is implemented on a two-wheeled robot. The experimental results show that the proposed system achieves excellent tracking and recognition performance in various motion scenarios, including scenarios where camera is temporarily blocked from the target.

关键词： Robot sensing systems Target tracking Machine vision Kalman filters Cameras

来源：评论

学校读者我要写书评

暂无评论

Solution-Processed Oxide Thin-Film Transistor with Spin-Coated Zinc Tin Oxide Active Layer and Indium Zinc Oxide Source/Drain Electrodes

引用

ECS Transactions 2011年第5期33卷

作者： Yong-Jin Kim Jeong-Soo Lee Yong-Uk Lee Seung-Hwan Cho Yong-Hoon Kim Min-Koo Han Seoul National University gwanak-gu Seoul 151-742 Republic of Korea School of Electrical Engineering and Computer Science Seoul National University Gwanak-ro 599 Gwanak-gu Seoul Seoul 151-742 Republic of Korea Seoul National University Flexible Display Research Center Korea Electronics Technology Institute #68 Yatap-dong Bundang-gu Seongnam 463-816 Republic of Korea School of Electrical Engineering and Computer Sciences Seoul National University 599 Gwanak-ro Gwanak-gu Seoul 151-742 Republic of Korea

We have fabricated oxide-based thin film transistors (TFTs) by employing a solution-based technology and investigated electric characteristics. We have deposited oxide TFTs not only the active layer but also source/drain electrodes by employing spin-coating process using solution with chloride-, acetate- and nitrate- based precursors. Zinc tin oxide (ZTO) film as an active layer and indium zinc oxide (IZO) film as source/drain electrodes have been used. After spin-coating, ZTO active layer and IZO source/drain electrodes were annealed for 10 minutes at 500{degree sign}C in RTA sequentially. The thickness of ZTO active layer is about 450Aå and IZO S/D electrodes is about 700Aå. The fabricated oxide TFTs (W/L=100/20 µm) exhibits a saturation mobility exceeding 0.07cm2/Vs, an on/off current ratio more than 106, and a subthreshold slope less than 0.2V/decade.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tecno-Streams approach for content-based image retrieval

Tecno-Streams approach for content-based image retrieval

引用

World Congress on Nature & Biologically Inspired Computing (NaBIC)

作者： Morteza Analoui Maedeh Beheshti Maryam Tayefeh Mahmoudi Zahra Jadidi School of Computer Engineering Iran University of Science and Technology Tehran Iran Knowledge En. & Intelligent Systems Group IT Research Faculty Education & Research Institute for ICT Iran Telecom Research Center Iran School of Electrical & Computer Engineering University of Tehran Tehran Iran School of Electrical Engineering Islamic Azad University Iran

Content-based image retrieval (CBIR) is based on a collective method of various techniques for retrieving images through the appropriate features, such as color, texture and shape. Despite of selecting an effective collection of features for each image, it is significant to use appropriate and relevant criterion to measure the similarity between a query image and all the available images in the dataset. In this paper we are introducing a new and effective similarity measurement criterion. In other words, in order to retrieve the images in an impressive way, an artificial immune system (AIS) clustering algorithm, called Tecno_Streams, is proposed for content-based image retrieval. According to experimental results the proposed image retrieval immune-based system is more applicable and effective than the other methods such as histogram based criterion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A chaotic model for generating heart rate variability signal using integral pulse frequency modulation

A chaotic model for generating heart rate variability signal...

引用

computers in Cardiology (CinC)

作者： Mahdi Lak Nader Jafarnia Dabanloo S Kamaledin Setarehdan Biomedical Engineering Faculty Science and Research Islamic Azad University Tehran Iran Control and Intelligent Processing Center of Excellence Faculty of Electrical & Computer Engineering University of Tehran Tehran Iran

Heart rate variability (HRV) is a very useful signal to investigate the activity of the autonomic nervous system (ANS), which affects and the heart function. Constructing a mathematical model for producing artificial HRV signal is needed to get a conceptual understanding of how ANS controls the heart rate (HR). The integral pulse frequency modulation (IPFM) structure is employed in this paper to model the sino-atrial node (SAN). Considering the complexity and nonlinear dynamics in the real HRV signal, a chaotic input is used in the proposed model. Instead of using a fixed threshold in IPFM model as in most previous works, we applied an appropriate variable signal, which has nonlinear chaotic dynamics. After running the model, the power spectrum of the output signal is extracted, which was then followed by calculating the nonlinear characteristics. The results were closely correlated with the real data, which confirm the effectiveness of the proposed model.

关键词： Heart rate variability Mathematical model Computational modeling Pacemakers Biological system modeling

来源：评论

学校读者我要写书评

暂无评论

Domain switching in nanometer scale in Bismuth-based relaxor solid solution

引用

Journal of Physics: Conference Series 2011年第1期320卷

作者： Naohiko Yasuda Natsumi Takahashi Nur Hidayah Hidehiro Ohwa Osamu Sakurada Yoshihito Tachi Kazuhiko Fujita Yohachi Yamashita Makoto Iwata Hikaru Terauchi Yoshihiro Ishibashi Electrical and Electronic Engineering Department Gifu University Gifu 501-1193 Japan Material Science and Technology Department Gifu University Gifu 501-1193 Japan Research Laboratories JFE MINERAL Company LTD. Chiba 260-0826 Japan Electronic and Control Engineering Department Gifu National College of Technology Gifu 501-0495 Japan Corporate R & D Center Toshiba Corporation Saiwai-ku Kawasaki 212-8582 Japan Department of Engineering Physics Electronics and Mechanics Graduate School of EngineeringNagoya Institute of Technology Nagoya 466-8555 Japan Advanced Research Center of Science School of Science Kwansei-Gakuin University Sanda 669-1337 Japan Department of Physics Kyushu University Hakozaki Higashi-ku Fukuoka 812-8581 Japan

Microscopic piezoresponse force microscopy observation in 0.9967(Na1/2Bi1/2)TiO3(NBT)-0.0033BaTiO3(BT) rhombohedral (001) plate reveals two kinds of piezoresponse images, one with domain switching characterized with superior piezoresponsibility and the other without one, whereas macroscopic observation reveals non-switching of domain. Such microscopic remarkable difference of domain switching depends on coercive field caused by localized nucleation of domains with reversed polarization. Such coercive fields depend on relaxor states induced by random fields due to built-in charge disorder resulting from lattice defects at A-site and oxygen vacancies in ABO3 perovskite. The random fields based on lattice defects on {110} plane lower activation barrier for domain switching, leading to nucleation and growth of domains, while for non-switching of domains, oxygen vacancies on {110} and/or {001} plane play a role as clamping center for restriction of domain switching.

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：