检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing

作者： Eunjung Chae Eunsung Lee Wonseok Kang Younghoon Lim Junghoon Jung Taechan Kim Aggelos K. Katsaggelos Joonki Paik Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul Korea System LSI Samsung Electronics Co. Ltd Suwon Korea Department of Electrical Engineering and Computer Science Northwestern University Evanston IL 60208 USA

ISBN: (纸本)9781479923427

We present an antialiasing method using combined wavelet-Fourier transform and spatially adaptive shrinkage of the transform coefficients. Traditional antialiasing methods employ a simple low-pass filter onto the entire image, so the resulting image loses not only aliasing artifacts but also high-frequency components such as edges and ridges. The proposed algorithm analyzes the property of the LL subband of the discrete wavelet transform (DWT), and reduces aliasing artifacts using patch-adaptive shrinkage of the DWT coefficients. More specifically, an antialiased LL subband is obtained using adaptive patch-based aliasing reduction. To detect an aliased region, we subtract the discrete Fourier transform (DFT) coefficients of the LL subband from the DFT coefficients of antialiased LL subband. The detected aliasing artifacts in the LH, HL, and HH subbands are reduced by patch-wise adaptive shrinkage of the transform coefficients. The resulting antialiased image is obtained using the inverse DWT. The aliasing artifacts can be efficiently reduced by adaptively shrinking wavelet transform coefficients for preserving high-frequency image details. The proposed antialiasing algorithm is suitable for removing aliasing artifacts which frequently occur in imaging sensors with limited resolution.

关键词： Anti-aliasing wavelet-Fourier transform image enhancement patch-adaptive shrinkage antialiasing image enhancement Aliasing shrinkage Artifacts subband domain analysis Coefficients Sensors (image) Frequency-domain analysis discrete Fourier transform

来源：评论

学校读者我要写书评

暂无评论

Graphic Processing Unit-Accelerated Neural Network Model for Biological Species Recognition

引用

Journal of Donghua University(English Edition) 2012年第1期29卷 5-8页

作者：温程璐潘伟陈晓熹祝青园 Department of Cognitive Science Xiamen University Fujian Provincial Key Laboratory of Brain-Like Intelligent Systems Department of Computer Science Xiamen University Department of Mechanical and Electrical Engineering Xiamen University

A graphic processing unit (GPU)-accelerated biological species recognition method using partially connected neural evolutionary network model is introduced in this paper. The partial connected neural evolutionary network adopted in the paper can overcome the disadvantage of traditional neural network with small inputs. The whole image is considered as the input of the neural network, so the maximal features can be kept for recognition. To speed up the recognition process of the neural network, a fast implementation of the partially connected neural network was conducted on NVIDIA Tesla C1060 using the NVIDIA compute unified device architecture (CUDA) framework. Image sets of eight biological species were obtained to test the GPU implementation and counterpart serial CPU implementation, and experiment results showed GPU implementation works effectively on both recognition rate and speed, and gained 343 speedup over its counterpart CPU implementation. Comparing to feature-based recognition method on the same recognition task, the method also achieved an acceptable correct rate of 84.6% when testing on eight biological species.

关键词： graphic processing unit(GPU) compute unified device architecture (CUDA) neural network species recognition

来源：评论

学校读者我要写书评

暂无评论

SmartParks for short term power flow control in smart grids

SmartParks for short term power flow control in smart grids

引用

2012 IEEE International Electric Vehicle Conference, IEVC 2012

作者： Venayagamoorthy, Ganesh Kumar Real-Time Power and Intelligent Systems Laboratory Holcombe Department of Electrical and Computer Engineering Clemson University SC 29634 United States

ISBN: (纸本)9781467315623

Among other functions, the smart grid is a vehicle to maximize the penetration of wind power by exploiting the use of energy storage devices in order to maximize the utilization of renewable energy and bring about maximum reduction in emissions. Large number of electric vehicles in a parking lot enabled to carry out vehicle-to-grid (V2G) transactions has been termed as a 'SmartPark' by the author. The use of vehicle-to-grid technology, information technology and advanced computational methods can provide short term real and reactive power support to overcome the drawback of the intermittent nature of renewable sources of electricity. This paper presents the intelligent control of SmartParks to enhance a smart grid's capability to compensate and mitigate active and reactive power fluctuations caused by the variability in wind power penetration in selected transmission lines and network buses. © 2012 IEEE.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

Stochastic search strategies in 2D using agents with limited perception

Stochastic search strategies in 2D using agents with limited...

引用

10th IFAC Symposium on Robot Control, SYROCO 2012

作者： Puljiz, David Varga, Maja Bogdan, Stjepan Department of Control and Computer Engineering Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Laboratory of Intelligent Systems Ecole Polytechnique Federale de Lausanne 1015 Lausanne Switzerland

ISBN: (纸本)9783902823113

Animals use stochastic search strategies to find a potential nest or to localize the food source. Animals do not rely much on the environmental cues or their sensory inputs. Since their cognitive capabilities are rather limited, search strategies are usually simplistic and stochastic. And yet such simple search strategies result in high efficiency in finding potential targets in limited time intervals. Similar problems with perception of the environment and limited computational power and sensory inputs are observed on the mobile robots used in search scenarios. In spite of their limitations, such robotic systems usually perform deterministic search strategies which heavily depend on environmental cues and sensory input. The research question we are addressing in this paper is which stochastic search strategy has the best performance in terms of area coverage and can stochastic search strategies outperform deterministic search strategies. © 2012 IFAC.

关键词： Sensory perception

来源：评论

学校读者我要写书评

暂无评论

Robot ontologies for sensor- and Image-guided surgery

Robot ontologies for sensor- and Image-guided surgery

引用

International Workshop on Robot Sensing (ROSE)

作者： Tamás Haidegger Marcos Barreto Paulo J. S. Goncalves Maki K. Habib S. Veera Ragavan Howard Li Alberto Vaccarella Roberta Perrone Edson Prestes Austrian Center for Medical Innov. and Techn. (ACMIT) Wiener Neustadt Austria UFBA Distributed Systems Laboratory (LaSiD) Brazil IDMEC Center of Intelligent Systems Portugal The American University in Cairo Cairo Egypt Monash University Selangor Malaysia Dept. of Electrical and Computer Engineering University of New Brunswick Canada Dept. of Electronics Information and Bioengineering (DEIB) NearLab Medical Robotics Milan Italy UFRGS Instituto de Informática Brazil

Robots and robotics are becoming more complex and flexible, due to technological advancement, improved sensing capabilities and machine intelligence. Service robots target a wide range of applications, relying on advanced Human-Robot Interaction. Medical robotics is becoming a leading application area within, and the number of surgical, rehabilitation and hospital assistance robots is rising rapidly. However, the complexity of the medical environment has been a major barrier, preventing a wider use of robotic technology, thus mostly teleoperated, human-in-the-loop control solutions emerged so far. Providing smarter and better medical robots requires a systematic approach in describing and translating human processes for the robots. It is believed that ontologies can bridge human cognitive understanding and robotic reasoning (machine intelligence). Besides, ontologies serve as a tool and method to assess the added value robotic technology brings into the medical environment. The purpose of this paper is to identify relevant ontology research in medical robotic, and to review the state-of-the-art. It focuses on the surgical domain, fundamental terminology and interactions are described for two example applications in neurosurgery and orthopaedics.

关键词： Robot sensing systems Surgery Lead Ontologies Biomedical optical imaging

来源：评论

学校读者我要写书评

暂无评论

Potential Function Based Multi-Agent Formation Control in 3D Space

引用

IFAC Proceedings Volumes 2012年第22期45卷 682-689页

作者： Marko Bunic Stjepan Bogdan University of Zagreb Faculty of Electrical Engineering and Computing Department of Control and Computer Engineering LARICS–Laboratory for Robotics and Intelligent Control Systems Zagreb Croatia

This paper presents the extension of the previously proposed method for multi-agent formation control based on potential function. The method derived for 2D space is extended to 3D. It has been shown that the control algorithm keeps all the properties of the original scheme in case of multi-agent formation moving in 3D. An adaptation mechanism that assures avoidance of unwanted stable equilibria, used in 2D, is implemented in the same form for 3D formations. The obtained simulation results demonstrate stable behavior of the system for various sets of parameters - the desired 3D formation is reached in finite time and maintained during trajectory execution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recent advances on the energy management of a Hybrid Electric vehicle

Recent advances on the energy management of a Hybrid Electri...

引用

2012 20th Mediterranean Conference on Control and Automation, MED 2012

作者： Efstathiou, D.S. Petrou, A.K. Spanoudakis, P. Tsourveloudis, N.C. Valavanis, K.P. Intelligent Systems and Robotics Lab Technical University of Crete Chania Greece Machine Tools Laboratory Technical University of Crete Chania Greece Department of Electrical and Computer Engineering University of Denver Denver CO 80208 United States

ISBN: (纸本)9781467325318

This paper presents new innovative subsystems of the ER11 prototype urban vehicle which is powered by hydrogen fuel cells and ultra-capacitors. The subsystems described here are: 1) the energy management system, which is responsible for the optimization of the fuel efficiency and the increased mileage of the vehicle, 2) the driver's monitoring and control panel and 3) the power transmission system, which offers the possibility of continuous change of gear. The powertrain of the test-bed vehicle consists of an electric motor, a fuel (H2) cell system, an ultra-capacitor bank and a DC/DC converter. Testing verified that the proposed energy management system is benefitted by the variable transmission of power leading to less fuel consumption. © 2012 IEEE.

关键词： Hybrid vehicles

来源：评论

学校读者我要写书评

暂无评论

Tracker design using composite nonlinear feedback with application to a DC servomotor

Tracker design using composite nonlinear feedback with appli...

引用

Power Electronic and Drive systems and Technologies Conference (PEDSTC)

作者： Saleh Mobayen Vahid Johari Majd Intelligent Control Systems Laboratory School of Electrical and Computer Engineering Tarbiat Moalem University Tehran Iran

In this paper, the theory of a nonlinear control technique, i.e., the composite nonlinear feedback control is considered for robust tracking of a class of linear systems with time varying uncertain parameters and disturbances. This controller can guarantee that the tracking error decreases asymptotically to zero in the presence of time varying uncertain parameters and disturbances. For performance improvement of dynamical system, this proposed robust tracking controller consists of linear and nonlinear feedback parts without any switching element. The linear feedback law is designed to yield a closed loop system with a small damping ratio for the existence of a quick response. On the other hand, the nonlinear feedback law is designed to increase the damping ratio as the system output approaches the output of the reference model. Finally, the simulations of applying the control law on a DC servomotor positioning system are given to illustrate the validity of the results developed in this paper.

关键词： Servomotors

来源：评论

学校读者我要写书评

暂无评论

A Scalable Wide Area Monitoring System using Cellular Neural Networks

A Scalable Wide Area Monitoring System using Cellular Neural...

引用

International Joint Conference on Neural Networks

作者： Karthikeyan Balasubramaniam Bipul Luitel Ganesh Kumar Venayagamoorthy Real-Time Power and Intelligent Systems Laboratory Holcombe Department of Electrical and Computer Engineering Clemson University

ISBN: (纸本)9781467314886

Synchrophasor systems make power grids more observable by collecting data from various locations, time-align and process them as a coherent data set. Better observability results in better control actions. A limiting factor to this approach is communication delays. Power system wide area communication delays range from several milliseconds to several seconds depending on the communication media and distance. One way to deal with this is to have an intelligent system which can predict state values for one or more time steps ahead of time. A novel four dimensional scalable multirate cellular neural network (CNN) architecture for use as wide area monitoring system (WAMS) is proposed. Recurrent neural network (RNN) is used as computational engine for each cell as RNNs have dynamic memory. By using information from phasor measurement units (PMUs) that are optimally located in a power system, each layer predicts a state variable for one or more time steps. Data from remote PMUs are replaced by the respective CNN cells' time delayed predicted state values for next time step. This enables local controllers to take real-time control action with system wide information. A 12-bus test power system is used to develop and demonstrate the effectiveness of the proposed CNN framework for WAMS.

关键词： Cellular neural networks Recurrent neural networks State estimation Synchrophasors Wide area monitoring and control Cellular neural networks Wide area measurement systems Communications Media Phasor measurement units recurrent neural nets area monitoring State variable power systems Dynamic storage local controller Power grids intelligent systems Data Collection Methods Scalability MILLISECOND

来源：评论

学校读者我要写书评

暂无评论

Stochastic search strategies in 2D using agents with limited perception

引用

IFAC Proceedings Volumes 2012年第22期45卷 650-654页

作者： David Puljiz Maja Varga Stjepan Bogdan University of Zagreb Faculty of Electrical Engineering and Computing Department of Control and Computer Engineering LARICS–Laboratory for Robotics and Intelligent Control Systems Zagreb Croatia Laboratory of Intelligent Systems Ecole Polytechnique Federale de Lausanne 1015 Lausanne Switzerland

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：