检索结果-内蒙古大学图书馆

GLPCA: dimensionality reduction for image retrieval

Journal of Computational Information Systems 2015年第6期11卷 2269-2277页

作者： Feng, Lin Hao, Xiuqi Wang, Huibing School of Computer Science and Technology Faculty of Electronic Information and Electrical Engineering Dalian University of Technology Dalian China School of Innovation Experiment Dalian University of Technology Dalian China

With the development of information age, image information has been widely applied in various fields, and content-based image retrieval (CBIR) has become a hot topic to research. However, after extracting the underlying visual image feature, the dimensions of the image feature will be high, which will lead to a higher computation complexity and space complexity in the process of image retrieval. In order to solve this problem, a novel manifold learning algorithm, named globally and locally consistent principal component analysis (GLPCA) algorithm, is proposed. Compared with the traditional dimensionality reduction algorithms such as principal component analysis (PCA) and linear discriminant analysis (LDA), GLPCA considers the global and local characteristics of the data structure comprehensively, and it has better performance on both linear and nonlinear data. The experiment results on Corel image data set show the excellent performance of GLPCA algorithm in image retrieval. Copyright © 2015 Binary Information Press.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

A robust clustering algorithm based on extreme learning machine

引用

Journal of Information and Computational Science 2015年第13期12卷 4951-4958页

作者： Du, Meng Zhang, Jing Wu, Bin Feng, Lin School of Computer Science and Technology Faculty of Electronic Information and Electrical Engineering Dalian University of Technology Dalian China School of Innovation Experiment Dalian University of Technology Dalian China

Original ELM-AE algorithm combines Extreme Learning Machine (ELM) with Auto Encoder (AE) to map data to a nonlinear high-dimensional space. This procedure can extract better sample characteristics when solving unsupervised clustering problems. ELM-AE adopts a solution procedure which is similar to ELM to improve the solution speed. However, ELM-AE has some problems. The solution of the system is not stable because of the random input-layer weights. Meanwhile, if the number of hidden layers is small, model fitting effect will be significantly reduced. To solve the above problems, we propose a Robust ELM-AE (RELM-AE) clustering algorithm. This method trains Restricted Boltzmann Machine (RBM) to get stable input-layer weights, and then minimizes the output error to obtain the output-layer weights. Compared with the original model of ELM-AE, this method achieves more stable and accurate results, which makes it more suitable for solving unsupervised clustering problems. ©, 2015, Journal of Information and Computational Science. All right reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-label dimensionality reduction and classification with extreme learning machines

引用

Journal of Systems engineering and electronics 2014年第3期25卷 502-513页

作者： Lin Feng Jing Wang Shenglan Liu Yao Xiao Faculty of Electronic Information and Electrical Engineering School of Computer Science and TechnologyDalian University of Technology School of Innovation Experiment Dalian University of Technology

In the need of some real applications, such as text categorization and image classification, the multi-label learning gradually becomes a hot research point in recent years. Much attention has been paid to the research of multi-label classification algorithms. Considering the fact that the high dimensionality of the multi-label datasets may cause the curse of dimensionality and wil hamper the classification process, a dimensionality reduction algorithm, named multi-label kernel discriminant analysis （MLKDA）, is proposed to reduce the dimensionality of multi-label datasets. MLKDA, with the kernel trick, processes the multi-label integrally and realizes the nonlinear dimensionality reduction with the idea similar with linear discriminant analysis （LDA）. In the classification process of multi-label data, the extreme learning machine （ELM） is an efficient algorithm in the premise of good accuracy. MLKDA, combined with ELM, shows a good performance in multi-label learning experiments with several datasets. The experiments on both static data and data stream show that MLKDA outperforms multi-label dimensionality reduction via dependence maximization （MDDM） and multi-label linear discriminant analysis （MLDA） in cases of balanced datasets and stronger correlation between tags, and ELM is also a good choice for multi-label classification.

关键词： multi-label dimensionality reduction kernel trick classification.

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: Potential of support vector regression for solar radiation prediction in Nigeria

引用

Natural Hazards 2015年第2期77卷 1055-1068页

作者： Olatomiwa, Lanre Mekhilef, Saad Shamshirband, Shahaboddin Petkovic, Dalibor Power Electronics and Renewable Energy Research Laboratory (PEARL) Department of Electrical Engineering Faculty of Engineering University of Malaya Kuala Lumpur Malaysia Department of Electrical and Electronic Engineering Federal University of Technology Minna Nigeria Department of Computer System and Technology Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia Department for Mechatronics and Control Faculty of Mechanical Engineering University of Niš Nis Serbia

In this paper, the accuracy of soft computing technique in solar radiation prediction based on series of measured meteorological data (monthly mean sunshine duration, monthly mean maximum and minimum temperature) taking from Iseyin meteorological station in Nigeria was examined. The process, which simulates the solar radiation with support vector regression (SVR), was constructed. The inputs were monthly mean maximum temperature (Tmax), monthly mean minimum temperature (Tmin) and monthly mean sunshine duration ( $$ \bar{n} $$ ). Polynomial and radial basis functions (RBF) are applied as the SVR kernel function to estimate solar radiation. According to the results, a greater improvement in estimation accuracy can be achieved through the SVR with polynomial basis function compared to RBF. The SVR coefficient of determination R 2 with the polynomial function was 0.7395 and with the radial basis function, the R 2 was 0.5877.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A new disocclusion filling approach in depth image based rendering for stereoscopic imaging

A new disocclusion filling approach in depth image based ren...

引用

International Conference on Control, Automation and Information Sciences (ICCAIS)

作者： Hanxiong Yin Liming Zhang Guibo Luo Yuesheng Zhu Faculty of Science and Technology University of Macau Macao China School of Electronic and Computer Engineering Peking University Shenzhen China

ISBN: (纸本)9781479998937

Depth image based rendering (DIBR) is one of the key techniques in converting the 2D videos into the stereoscopic 3D ones. Warping process is the major step in DIBR, which generates the virtual left and right views with a number of black disocclusion areas. The disocclusion filling process is the main task in DIBR. In this paper, an improved disocclusion filling approach is proposed, which is based on the texture and gradient analysis. Inpainting algorithm is applied first based on the background texture and depth information to repair the disocclusion areas, which can be effectively reduce the large sizes of the disocclusion areas. Then a new gradient direction template is proposed and applied to fill the left disocclusion areas. Experiments are conducted to compare with other disocclusion filling approaches. Our results are promising.

关键词： Filling Maintenance engineering Videos Extrapolation Image color analysis Stereo image processing Three-dimensional displays

来源：评论

学校读者我要写书评

暂无评论

An improved depth map estimation method based on motion detection

An improved depth map estimation method based on motion dete...

引用

IEEE Region 10 International Conference TENCON

作者： Boyu Pan Liming Zhang Yuesheng Zhu Guibo Luo Faculty of Science and Technology University of Macau Macao China School of Electronic and Computer Engineering Peking University Shenzhen China

ISBN: (纸本)9781479986422

Depth map estimation is one of the important research areas in image processing. This paper proposes an improved depth map estimation approach from a video stream of cartoon. It is based on the motion detection. Most depth map estimation approaches based on motion detection usually have two disadvantages. One is that the depth values of the same object have big differences. The other is time-consuming. To solve those problems, we propose an improved approach that includes three steps. First, a revised search strategy is designed in block matching based motion estimation. It helps to reduce the computation time. Then a revised depth consistency approach is used to reduce the large depth value differences in the same object. Finally, mean shift approach is used to segment the original color image and project the depth map onto the color segmentation. It further helps to reduce the depth value differences in the same object. Experiment results are promising.

关键词： Image segmentation Search problems Image color analysis Three-dimensional displays Streaming media Motion estimation Estimation

来源：评论

学校读者我要写书评

暂无评论

Small signal analysis of dual inductor current-fed bidirectional converter for fuel cell vehicle

Small signal analysis of dual inductor current-fed bidirecti...

引用

IEEE International Transportation Electrification Conference (ITEC)

作者： Sudha Bansal Lalit Mohan Saini School of Electrical Engineering Shenyang University of Technology Shenyang China Faculty of Electronic & Computer Engineering University Teknikal Malaysia Melaka Melaka Malaysia

This paper presents the small signal analysis and controller design of Dual Inductor Current-Fed Bidirectional Converter For Fuel Cell Vehicle. The converter achieves zero-current switching (ZCS) of the primary-side switches and zero-voltage switching (ZVS) of the secondary-side switches. A proposed secondary-modulation clamps the voltage across the primary-side devices naturally and eliminates switch turn-off voltage spike concern with ZCS without any additional circuit. State space averaging technique is used to derive the small signal model. The controller is designed using two loop average current control. Frequency response curves using MATLAB and simulation results using PSIM 9.0 are presented to verify to verify the controller design and converter's transient performance.

关键词： Signal analysis Zero current switching Zero voltage switching Fuel cells DC-DC power converters Inductance Inductors

来源：评论

学校读者我要写书评

暂无评论

Simultaneous multi-frequency TE/TM polarization inversion based on FDFD for ground penetrating radar

Simultaneous multi-frequency TE/TM polarization inversion ba...

引用

International Workshop on Advanced Ground Penetrating Radar (IWAGPR)

作者： Shilong Sun Bert Jan Kooij Tian Jin Alexander Yarovoy Faculty Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft The Netherlands College of Electronic Science and Engineering National University of Defense Technology Changsha China

In Ground Penetrating Radar (GPR), inversion techniques like Contrast Source Inversion (CSI) have been applied extensively. In this paper, CSI is applied to handle 2D TE/TM-polarized excitations, in which the form for the TE-polarized Maxwell operator is equivalent to the 3D Maxwell operator. Furthermore, a simultaneous TE/TM polarization CSI method based on Finite Difference Frequency Domain (FDFD) together with a frequency hopping scheme is proposed, in which FDFD is able to handle heterogeneous background media. 2D simulation results verify the advantage of the proposed inversion scheme. Since the proposed method is based on a 2D Maxwell operator which has a similar form as the 3D Maxell operator, it can be extended to a 3D CSI-scheme straightforwardly.

关键词： Ground penetrating radar Conductivity Permittivity Mathematical model Three-dimensional displays Frequency-domain analysis Simulation

来源：评论

学校读者我要写书评

暂无评论

Activity recognition based on accelerometer sensor using combinational classifiers

Activity recognition based on accelerometer sensor using com...

引用

IEEE Conference on Open Systems (ICOS)

作者： M.N.Shah Zainudin Md Nasir Sulaiman Norwati Mustapha Thinagaran Perumal Faculty of Electronic and Computer Engineering Universiti Teknikal Malaysia Melaka Durian Tunggal Melaka Malaysia Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang Selangor Malaysia

In recent years, people nowadays easily to contact each other by using smartphone. Most of the smartphone now embedded with inertial sensors such accelerometer, gyroscope, magnetic sensors, GPS and vision sensors. Furthermore, various researchers now dealing with this kind of sensors to recognize human activities incorporate with machine learning algorithm not only in the field of medical diagnosis, forecasting, security and for better live being as well. Activity recognition using various smartphone sensors can be considered as a one of the crucial tasks that needs to be studied. In this paper, we proposed various combination classifiers models consists of J48, Multi-layer Perceptron and Logistic Regression to capture the smoothest activity with higher frequency of the result using vote algorithmn. The aim of this study is to evaluate the performance of recognition the six activities using ensemble approach. Publicly accelerometer dataset obtained from Wireless Sensor Data Mining (WISDM) lab has been used in this study. The result of classification was validated using 10-fold cross validation algorithm in order to make sure all the experiments perform well.

关键词： Accelerometers Feature extraction Robot sensing systems Support vector machines Classification algorithms Gyroscopes Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Model based control of permanent magnet AC servo motor drives

Model based control of permanent magnet AC servo motor drive...

引用

International Conference on Electrical Machines and Systems (ICEMS)

作者： P. Thounthong S. Sikkabut P. Mungporn B. Yodwong P. Kumam N. Bizon P. Tricoli B. Nahid-Mobarakeh S. Pierfederici Department of Teacher Training in Electrical Engineering KMUTNB Bangkok Thailand Thai-French Innovation Institute King Mongkut's University of Technology North Bangkok Bangkok Thailand Department of Mathematics King Mongkut's University of Technology Thonburi Bangkok Thailand Faculty of Electronics Communications and Computers Science University of Pitesti Pitesti Romania School of Electronic Electrical and Computer Engineering University of Birmingham Birmingham United Kingdom Universite de Lorraine Nancy Lorraine FR Groupe de Recherche en Electrotechnique et Electronique de Nancy Université de Lorraine Lorraine France

ISBN: (纸本)9781467388634

This paper presents an innovative control law for permanent magnet synchronous motor (PMSM) drive for high dynamics applications. This kind of system (three-phase inverter connected with a PMSM) exhibits nonlinear behavior. Classically, to control the speed and the current (torque), a linearized technique is often used to study the stability and to select the controller parameters at specific operating point. In this paper, a model based control based on the flatness property of the drive system is proposed. Flatness provides a convenient framework for meeting a number of performance specifications on the PMSM drive. To validate the proposed method, a prototype PMSM drive (1 kW, 3000 rpm) is realized in the laboratory. The proposed control law is implemented by digital estimation in a dSPACE 1104 controller card. Experimental results demonstrate that the nonlinear differential flatness-based control provides improved speed/current regulation relative to a classical linear PI vector control method.

关键词： Inverters Velocity control Trajectory Permanent magnet motors Torque Stability analysis Planning

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：