检索结果-内蒙古大学图书馆

8th International Conference on Image and Graphics, ICIG 2015

作者： Liu, Junquan Da, Feipeng Deng, Xing Yu, Yi Zhang, Pu School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9783319219776

We propose an automatically and accurately facial landmark localization algorithm based on Active Shape Model (ASM) and Gabor Wavelets Transformation (GWT), which can be applied to both 2D and 3D facial data. First, ASM is implemented to acquire landmarks’ coarse areas. Then similarity maps are obtained by calculating the similarity between sets of Gabor jets at initial coarse positions and sets of Gabor bunches modeled by its corresponding manually marked landmarks in the training set. The point with the maximum value in each similarity map is extracted as its final facial landmark location. It is showed in our laboratory databases and FRGC v2.0 that the algorithm could achieve accurate localization of facial landmarks with state-of-the-art accuracy and robustness. © Springer International Publishing Switzerland 2015.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

PID parameters optimization research for hydro turbine governor by an improved fuzzy particle swarm optimization algorithm

引用

Open Electrical and Electronic engineering Journal 2016年 10卷 101-117页

作者： Chen, Gonggui Yangwei, Du Yanyan, Guo Shanwai, Huang Lilan, Liu Key Laboratory of Industrial Wireless Network and Networked Control of Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China Research Center on Complex Power System Analysis and Control Chongqing University of Posts and Telecommunications Chongqing400065 China The Department of Locomotive and Vehicle Engineering Wuhan Railway Vocational College of Technology Wuhan430205 China

Parameter optimization of water turbine regulating system (WTRS) is decisive in providing support for the power quality and stability analysis of power system. In this paper, an improved fuzzy particle swarm optimization (IFPSO) algorithm is proposed and used to solve the optimization problem for WTRS under frequency and load disturbances conditions. The novel algorithm which is based on the standard particle swarm optimization (PSO) algorithm can speed up the convergence speed and improve convergence precision with combination of the fuzzy control thought and the crossover thought in genetic algorithm (GA). The fuzzy control is employed to get better dynamics of balance between global and local search capabilities, and the crossover operator is introduced to enhance the diversity of particles. Two different types of WTRS systems are built and analyzed in the simulation experiments. Furthermore, the sum of regulating time and another number that is the integral of sum for absolute value of system error and the squared governor output signal is considered as the fitness function of this algorithm. The simulation experiments for parameter optimization problem of WTRS system are carried out to confirm the validity and superiority of the proposed IFPSO, as compared to standard PSO, Ziegler Nichols (ZN) algorithm and fuzzy PID algorithm in terms of parameter optimization accuracy and convergence speed. The simulation results reveal that IFPSO significantly improves the dynamic performance of system under all of the running conditions. © Gonggui et al.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

Handwritten character recognition based on weighted integral image and probability model 8th

Handwritten character recognition based on weighted integral...

引用

8th International Conference on Image and Graphics, ICIG 2015

作者： Wu, Jia Da, Feipeng Wang, Chenxing Gai, Shaoyan College of Automation Southeast University Nanjing Jiangsu210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9783319219622

A system of the off-line handwritten character recognition based on weighted integral image and probability model is built in this paper, which is divided into image preprocessing and character recognition. The objects of recognition are digitals and letters. In the image preprocessing section, an adaptive binarization method based on weighted integral image is proposed, which overcomes the drawbacks in the classic binarization algorithms: noise sensitivity, edge coarseness, artifacts etc.;In the character recognition section, combined with statistical features and structural features, an probability model based on the Bayes classifier and the principle of similar shapes is developed. This method achieves a high recognition rate with rapid processing, strong anti-interference ability and fault tolerance. © Springer International Publishing Switzerland 2015.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Robust Decentralized control of Interconnected Nonlinear systems Subject to Uncertainties and Disturbances via Generalized Extended State Observers 34

Robust Decentralized Control of Interconnected Nonlinear Sys...

引用

第三十四届中国控制会议

作者： ZHANG Chuanlin YANG ning HE Shuaipeng JIA Ruting Shanghai Engineering Research Center of Intelligent Management and Control for Power Process College of Automation EngineeringShanghai University of Electric Power Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Electrical and Computer Engineering Department California State University

ISBN: (纸本)9789881563897

This paper studies the problem of robust decentralized control for a class of large-scale interconnected systems subject to uncertainties and disturbances via a generalized active disturbance rejection control method. First, a novel extended state observer(ESO) is constructed separately for each subsystem with less dependence of the precise system information and structure. Second, an explicit formula of the decentralized active disturbance rejection control(DADRC) law is presented by utilizing the output feedback domination approach. It is shown that by a delicate analysis procedure, the closed-loop system can be rendered semi-globally asymptotically stable only using decentralized output feedback anti-disturbance controller. Numerical simulations show the efficiency of the proposed method.

关键词： output feedback control global stabilization disturbance rejection control extended state observer

来源：评论

学校读者我要写书评

暂无评论

Reactive power compensation in microgrids via distributed control strategy

Reactive power compensation in microgrids via distributed co...

引用

World Congress on Intelligent control and Automation (WCICA)

作者： Xiong Hu Hong Zhou Zhi-Wei Liu Zhi-Hong Guan Ming Chi Department of Automation Wuhan University P. R. China Ministry of Education Key Laboratory of Measurement and Control of Complex Systems of Engineering Nanjing P. R. China College of Automation Huazhong University of Science and Technology Wuhan P. R. China

ISBN: (纸本)9781467384155

To minimize power losses in microgrids, we concentrate on reactive power compensation by microgenerators connected to microgrid via electronic interfaces. Comparing exits works, not only the constraint of power balance, but also the bounded capacity of microgenerator is taken into account. We propose a distributed algorithm for the reactive power compensation problem with a fully connected communication network, to solve the optimal reactive power compensation problem in microgrids. Case study illustrates the proposed algorithm can effectively solve the reactive power compensation problem.

关键词： Reactive power Microgrids Distributed algorithms Topology Linear programming Algorithm design and analysis Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Exploring Optimal Frequency Caps in Real Time Bidding Advertising

Exploring Optimal Frequency Caps in Real Time Bidding Advert...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Rui Qin Yong Yuan Fei-Yue Wang Beijing Engineering Research Center of Intelligent Systems and Technology Beijing China The State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China Research Center of Military Computational Experiments and Parallel System National University of Defense Technology Changsha China

ISBN: (纸本)9781509039371

Benefited from the high-speed development of Internet and the popularization of big data technology, Real Time Bidding (RTB) emerged and developed quickly, and has become one of the most important and popular model for online computational advertising. In the pay-per-impression based RTB advertising, frequency capping is undoubtedly one of the most crucial issues faced by advertisers and Demand Side Platforms (DSPs), since there are generally vast amount of ad requests in RTB markets, among which many may be triggered by the same target audience. As such, choosing the optimal frequency cap considering all the advertisers becomes a critical issue faced by DSPs. Considering that displaying one advertisement multiple number of times to the same user will diminish the advertising effect, we introduce the concept of discount factor and establish an optimization model of frequency capping to seek for the optimal frequency cap for each advertiser. We also design some experiments to validate our proposed model by utilizing the computational experiment approach, and the experimental results show that the optimal frequency cap can be influenced by the values of the discount factors, and higher value of the discount factor can deduce the advertising effect of larger frequency cap. Moreover, when the discount factors of the advertisers take different values, there also exists an optimal frequency cap, at which the advertisers can get the expected maximum revenue in the long run.

关键词： Advertising Digital signal processing Computational modeling Big data Time-frequency analysis Radio spectrum management Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Optimizing Market Segmentation Granularity in RTB Advertising: A Computational Experimental Study

Optimizing Market Segmentation Granularity in RTB Advertisin...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

ISBN: (纸本)9781509039371

Real Time Bidding (RTB) is a novel business model of online computational advertising with the integration of Internet economy and big data analysis. It can help advertisers achieve the precision marketing through the market segmentation strategies of Demand Side Platforms (DSPs). Based on a mathematical programming approach, this paper studied DSPs' strategies for market segmentation, and established a selection model of the granularity for segmenting RTB advertising markets. We proposed to validate our model using the computational experiment approach, and the experimental results show that: 1) with the increasing refinement of the market segmentation granularity, the total revenue has a tendency of a rise first followed by a decline, 2) the optimal granularity of market segmentation will be significantly influenced by the number of advertisers on the DSP, but less influenced by the number of ad requests. Our findings show the crucial role of market segmentation on the RTB advertising effect, and indicate that the DSPs should adjust their market segmentation strategies according to their total number of advertisers. Our findings also highlight the importance of advertisers as well as the characteristics of the target audiences in DSPs' market segmentation decisions.

关键词： Digital signal processing Computational modeling Advertising Numerical models Big data complex systems Automation

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor fusion robust localization for indoor mobile robots based on a set-membership estimator

Multi-sensor fusion robust localization for indoor mobile ro...

引用

IEEE International Conference on Cyber Technology in Automation, control, and Intelligent systems

作者： Bo Zhou Kun Qian Fang Fang Xudong Ma Xianzhong Dai Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University Nanjing P. R. China Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University China

Autonomous localization is a primary and crucial issue in mobile robot navigation tasks. In this article, the long-distance robust localization problem of indoor mobile robots is studied and solved by a combination style of using a laser scanner and an odometer. Firstly, a point-to-line iterative closest point(PLICP) approach is adopted to match the successive environmental information collected by a laser scanner to estimate the relative pose transformation of the robot. And then the multi-sensor fusion technology based on bounded-error set-membership estimator is proposed to to use scan matching results to correct the cumulative error of the odometer periodically to achieve precious location of the robot in indoor environments. Experimental results show that the accuracy and robustness of the proposed localization system has been improved greatly with respect to the single odometer localization approach.

关键词： Ellipsoids Iterative closest point algorithm Mobile robots Noise measurement Robot kinematics

来源：评论

学校读者我要写书评

暂无评论

Expression-robust 3D face recognition using region-based multiscale wavelet feature fusion

引用

Journal of Computational Information systems 2015年第15期11卷 5509-5517页

作者： Deng, Xing Da, Feipeng Shao, Haijian Department of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control for Complex System of Ministry of Education Southeast University Nanjing China

In order to eliminate the impact of facial expressions and improve the efficiency of calculation, this paper proposes a novel expression-robust 3D face recognition algorithm using region-based feature fusion technique based on multiscale wavelet transformations. The discrete wavelet transformation is applied to extract frequency component features of geometric image based on the semi-rigid face region as well as the non-rigid face region in order to reduce the influence from the facial expression using the Coherent Point Drift non-rigid point set registration. The dimensionality reduction methods are utilized to promote the computational efficiency, and the experimental results show that our algorithm outperforms state-of-the-art methods based on FRGC v2.0. Copyright © 2015 Binary Information Press.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Research on panoramie vision system of mobile robot 27

Research on panoramie vision system of mobile robot

引用

27th Chinese control and Decision Conference, CCDC 2015

作者： Yao, Qiaobing Yu, Hualong Yang, Wankou Sun, Changyin School of Autmation Southeast University Nanjing China Key Lab of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast Univerity Nanjing China Key Laboratory of Child Development and Learning Science of Ministry of Education Southeast University Nanjing China

ISBN: (纸本)9781479970179

This paper presents an imaging method for 360-degree panoramic view based on four wide angle cameras. In order to complete the image mosaic, all the parameters such as focal length, principal point and distortion coefficients, etc are calibrated by our proposed calibration toolbox. Then, our approach does not adopt the scheme which stitching all the images to the surrounding view after distortion correction. The proposed method directly calculates the mapping relationship between the wide-angle lens images and cylindrical projection images to generate lookup tables which can greatly simplifies the computation and reduces the loss of information in each image. Finally, panoramic image is composed by image registration and image fusion. Experimental results show that this method is valid. © 2015 IEEE.

关键词： Cylindrical projection Image mosaic. Camera calibration LUTs

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：