检索结果-内蒙古大学图书馆

Iranian Machine Vision and Image Processing (MVIP)

作者： Mohamad Hoseyn Sigari Samaneh Abbasi Sureshjani Hamid Soltanian-Zadeh Control & Intelligent Processing Center of Excellence (CIPCE) School of Electrical & Computer Engineering College of Engineering University of Tehran Tehran Iran Image Analysis Laboratory Department of Radiology Henry Ford Health System Detroit MI USA

Sport video classification is an application of video analysis which can be useful in video indexing and retrieval. In this article, a new method for sport video classification using ensemble classifier is proposed. The proposed method uses 6 features: 3 dominant colors, dominant gray level, cut rate and motion rate. These features are classified by 4 simple classifiers in an ensemble classifier: Nearest Neighbor (NN), Linear Discriminant Analysis (LDA), Decision Tree (DT) and Probabilistic Neural Network (PNN). To combine the output of simple classifiers and make final decision, weighted majority vote is used while the weight of each simple classifier is equal to corresponding correct classification rate (CCR). Experimental result shows that the CCR of proposed system is 78.8%. In this experiment, 104 clips in 7 different sport classes are used: football, basketball, tennis, swimming, futsal, ski and box.

关键词： Feature extraction Color Image color analysis Classification algorithms Accuracy Artificial neural networks Histograms

来源：评论

学校读者我要写书评

暂无评论

Gearbox Ripple Rejection of Robots Using Observer and Adaptive control Theory

引用

IFAC Proceedings Volumes 2011年第1期44卷 893-898页

作者： Sebastian Maier Johann Bals Marc Bodson Department of System Dynamics and Control Institute of Robotics and Mechatronics German Aerospace Center (DLR) 82234 Wessling Germany Muenchner Str. 20 Department of Electrical and Computer Engineering University of Utah 50 S Central Campus Dr. Salt Lake City UT 84112 USA

Abstract Robots are often run with permanent magnet synchronous motors (PMSM) with a high ratio gearbox. Both parts can produce parasitic oscillations (ripples), which let the robot shake at tool center point. The gearbox ripple problem is more complicated to be solved with control theory because only motor side sensors should be used. Due to the internal model principle gearbox side information is necessary to solve the problem. The first algorithm uses an observer to get gearbox side information where the second algorithm uses a gearbox side rate sensor. The algorithms are tested with a nonlinear SISO problem and with a nonlinear MIMO system. In both cases the ripples are canceled with an adaptive controller which estimates the phase and magnitude of the ripple. This adaptive controller is designed separately and is added to the existing basis controller. The algorithms are tested in simulation and on a testbed, which is an industrial application.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Training ANFIS system with DE algorithm

Training ANFIS system with DE algorithm

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Allahyar Z. Zangeneh Mohammad Mansouri Mohammad Teshnehlab Ali K. Sedigh Computer Engineering Department Science and Research Branch Islamic Azad university of Tehran Iran Intelligent System laboratory (ISLAB) Control Department K. N. Toosi University of Technology Tehran Iran Advanced Process Automation & Control laboratory (APAC) Control Department K. N. Toosi University of Technology Tehran Iran

In this study, a new type of training the adaptive network-based fuzzy inference system (ANFIS) is presented by applying different types of the Differential Evolution branches. The TSK-type consequent part is a linear model of exogenous inputs. The consequent part parameters are learned by a gradient descent algorithm. The antecedent fuzzy sets are learned by basic differential evolution (DE/rand/1/bin) and then with some modifications in it. This method is applied to identification of the nonlinear dynamic system, prediction of the chaotic signal under both noise-free and noisy conditions and simulation of the two-dimensional function. Instead of DE/rand/1/bin, this paper suggests the complex type (DE/current-to-best/1+1/bin & DE/rand/1/bin) on predicting of Mackey-glass time series and identification of a nonlinear dynamic system revealing the efficiency of proposed structure. Finally, the method is compared with pure ANFIS to show the efficiency of this method.

关键词： Vectors Adaptive systems Input variables Training Mathematical model Equations Firing

来源：评论

学校读者我要写书评

暂无评论

Assimilation of Wireless Sensor Networks and remote microcomputer laboratories

Assimilation of Wireless Sensor Networks and remote microcom...

引用

Proceedings of the International Convention MIPRO

作者： Darko Fudurić Drago Cmuk Petar Knežević Saša Mrvoš Department of Control and Computer Engineering Faculty of Engineering and Computing University of Zagreb Zagreb Croatia Končar-Electronics and Informatics Inc. Zagreb Croatia Department of Fundamentals of Electrical Engineering and Measurements Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Department of Electronic System and Information Processing Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia

Emergence of Web 2.0 technologies became a trigger for a revolution that goes far beyond the Web. For an average student Web was transformed from a steady, accessible source of information into a place of action and viable exchange of knowledge - a kind of a virtual classroom. Students started to look for experience and a touch to reality online, and this is where remote laboratories come in place. Such laboratories became an inevitable need in electrical and computer engineering courses dealing with microcomputers. This paper presents an overview of available architectures of microcomputer laboratories used today and addresses their most important limitations. Moreover, an important extension of such architecture is proposed allowing support for remote Wireless Sensor Network (WSN) laboratory. Different aspects of compatibility between microcomputer laboratories and WSNs have been examined to allow creation of an general extension model. With additional effort and adaptation, WSN nodes may serve remote clients as an economic and accessible microcomputer laboratory providing invaluable hands-on experience and a motivation for a course using it.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Universal Steganalysis Based on Local Prediction Error in Wavelet Domain

Universal Steganalysis Based on Local Prediction Error in Wa...

引用

International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIHMSP)

作者： Anahita Shojaei-Hashemi Mostafa Mehdipour-Ghazi Shahrokh Ghaemmaghami Hamid Soltanian-Zadeh School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Electronics Research Institute Sharif University of Technology Tehran Iran Image Analysis Laboratory Department of Radiology Henry Ford Health System Detroit MI USA Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran

A passive universal image steganalysis method is proposed that is shown to be of higher detection accuracy than existing truly blind steganalysis methods including Farid's and the WAM. This is achieved by improving some weaknesses of Farid's steganalysis scheme in feature extraction, that is, instead of deriving an over-determined equation system for each sub band of the wavelet decomposition, the sub bands are divided into overlapping blocks and an over-determined equation system is constructed for each block. To guarantee the existence of finite answers, the over-determined equation systems are solved in a way different from Farid's by using Moore-Penrose pseudo-inverse concept. Further improvement to the performance is achieved by adding diagonal directions and increasing the number of moments. The comparative evaluations confirm the superiority of the proposed method over prevalent blind steganalysis schemes.

关键词： Equations Mathematical model Payloads Transform coding Correlation Educational institutions Reliability

来源：评论

学校读者我要写书评

暂无评论

Optimal approximation of linear systems using Taguchi-sliding-based differential evolution algorithm

Optimal approximation of linear systems using Taguchi-slidin...

引用

作者： Tsai, Jinn-Tsong Ho, Wen-Hsien Chou, Jyh-Horng Guo, Ching-Yi Department of Computer Science National Pingtung University of Education 4-18 Ming Shen Road Pingtung 900 Taiwan Department of Medical Information Management Kaohsiung Medical University 100 Shi-Chuan 1st Road Kaohsiung 807 Taiwan Institute of System Information and Control National Kaohsiung First University of Science and Technology 1 University Road Yenchao Kaohsiung 824 Taiwan Department of Electrical Engineering National Kaohsiung University of Applied Sciences 415 Chien-Kung Road Kaohsiung 807 Taiwan

A Taguchi-sliding-based differential evolution algorithm (TSBDEA) is proposed in this study to solve the problem of optimally approximating linear systems. The TSBDEA is an approach of combining the differential evolution algorithm (DEA) with the Taguchi-sliding-level-method (TSLM). In the TSBDEA, the TSLM is to provide a new systematic crossover operation for breeding better offspring, and consequently enhances the DEA. By using the proposed TSBDEA, the optimal approximate rational model with/without a time delay for a system described by its rational or irrational transfer function is sought such that an error criterion is minimized. Numerical examples show that the presented TSBDEA gives an effective and robust way for obtaining optimal reduced-order models for stable/unstable and/or nonminimum-phase complex systems, and can get better results than the existing DEA-based method reported in the literature. © 2010 Elsevier B.V. All rights reserved.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Containment control of networked Lagrange systems with group dispersion and cohesion behaviors

Containment control of networked Lagrange systems with group...

引用

Chinese control Conference (CCC)

作者： Ziyang Meng Zongli Lin Wei Ren Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China 200240 China Charles L. Brown Department of Electrical and Computer Engineering University of Virginia P.O. Box 400743 Charlottesville 22904-4743 U.S.A. Department of Electrical and Computer Engineering Utah State University Logan 84322 U.S.A.

In this paper, distributed containment control with group dispersion and cohesion behaviors are discussed for a group of Lagrange systems. Both the cases of constant leaders' generalized coordinate derivatives and time-varying leaders' generalized coordinate derivatives are considered. The proposed control algorithms are shown to obtain velocity matching, connectivity maintenance and collision avoidance. In addition, the sum of the steady-state distances between followers and the convex hull formed by the leaders is shown to be bounded and this bound is explicitly given.

关键词： Lead Dispersion Topology Sensors Laplace equations Maintenance engineering Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Effect of Different Diffusion Maps on Registration Results

Effect of Different Diffusion Maps on Registration Results

引用

Iranian Machine Vision and Image Processing (MVIP)

作者： Maryam Afzali Emad Fatemizadeh Hamid Soltanian-Zadeh Department of Electrical Engineering Biomedical Signal and Image Processing Laboratory (BiSIPL) Sharif University of Technology Tehran Iran Image Analysis Laboratory Radiology Department Henry Ford Health System Detroit MI USA Control and Intelligent Processing Center of Excellence (CIPCE) School of Electrical and Computer Engineering University of Tehran Tehran Iran

In this paper, we compare registration results obtained using different diffusion maps extracted from diffusion tensor imaging (DTI). Fractional Anisotropy (FA) and Ellipsoidal Area Ratio (EAR) are two diffusion maps (indices) that may be used for image registration. First, we use FA maps to find deformation matrix and register diffusion weighted images. Then, we use EAR maps and finally we use both of FA and EAR maps to register diffusion weighted images. The difference between FA values before deformation and after registration using the FA alone or EAR alone has a median of 0.57 and using both of them has a median of 0.29. Therefore, the results of registration using both of the FA and EAR indices are superior to those obtained using only one of them alone.

关键词： Ear Diffusion tensor imaging Tensile stress Registers Eigenvalues and eigenfunctions Anisotropic magnetoresistance Image registration

来源：评论

学校读者我要写书评

暂无评论

A novel method for identification of COPD in inspiratory and expiratory states of CT images

A novel method for identification of COPD in inspiratory and...

引用

Middle East Conference on Biomedical engineering (MECBME)

作者： M. Parsa Hosseini Hamid Soltanian-Zadeh Shahram Akhlaghpoor Department of Electrical Engineering Islamic Azad University Tehran Iran Department of Radiology Henry Ford Health System Image Analysis and Communications Laboratory Detroit MI USA Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran Department of Radiology Tehran University of Medical Sciences Sina Hospital Tehran Iran

Chronic obstructive pulmonary disease (COPD) refers to a group of lung diseases that block airflow and cause a huge degree of human suffering. While there is no cure for COPD and the lung damage that results in this disease cannot be reversed, it is very important to diagnose it as early as possible. Additional to diagnosis, using a mathematical model to estimate severity of disease would be helpful for evaluation of treatment effects. This paper presents a new method for identifying COPD from three-dimensional (3-D) pulmonary X-ray CT images. The method has five main steps. First, corresponding positions of lungs in inspiration and expiration are found based on anatomical structures. Then, lung regions are segmented from the CT images by active contours. Next, the left and right lungs are separated using a sequence of morphological operations. Then, parenchyma variations in each lung are found as a relationship between inspiratory and expiratory states. Finally, a classifier is used to decide about the disease and its severity. A t-test is done to evaluate the results. Twelve patients with variable severity of COPD and twelve normal adults were included in this study. The proposed method may assist radiologists in the detection of COPD as a computer aided diagnosis (CAD) system.

关键词： Lungs Computed tomography Diseases Image segmentation Biomedical imaging Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Assessing lung volumetric variation to detect and stage COPD

Assessing lung volumetric variation to detect and stage COPD

引用

Middle East Conference on Biomedical engineering (MECBME)

Chronic obstructive pulmonary disease (COPD) is a devastating disease. In this paper, we propose a novel method for scoring of air trapping in the lungs for detection and evaluation of COPD. The proposed method finds volumetric changes of the lungs from inspiration to expiration. To this end, trachea CT images at full inspiration and expiration are compared. For this comparison, the lungs parenchyma in the inspiration and expiration images are found and changes in the surface and volume of the lungs between inspiration and expiration are used to define quantitative measures (features). Using these features, the subjects are classified into two groups of normal class and COPD patients using a Bayesian classifier. In addition, t-tests are applied to evaluate discrimination powers of the features for this classification. The main advantage of the proposed method is its ability to estimate air trapping in the lungs from CT images without human intervention. The proposed method may assists radiologists in the detection of COPD as a computer aided diagnosis (CAD) system. It may also assist them with the scoring of the disease (severity of air trapping in the lungs).

关键词： Lungs Computed tomography Diseases Active contours Image segmentation Charge carrier processes

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：