检索结果-内蒙古大学图书馆

International CSI Computer Conference, CSICC

作者： A. R. Koushki M. Nosrati Maralloo C. Lucas A. Kalhor Department of Computer Engineering Science and Research Branch Islamic Azad University Tehran Iran Control and Intelligent Processing Center of Excellence Electrical and Computer Engineering Department University of Tehran Tehran Iran

One of the important requirements for operational planning of electrical utilities is the prediction of hourly load up to several days, known as short term load forecasting (STLF). Considering the effect of its accuracy on system security and also economical aspects, there is an on-going attention toward putting new approaches to the task. Recently, neuro fuzzy modeling has played a successful role in various applications over nonlinear time series prediction. This paper presents a neuro-fuzzy model for the application of short-term load forecasting. This model is identified through locally liner model tree (LoLiMoT) learning algorithm. The model is compared to a multilayer perceptron and Kohonen classification and intervention analysis. The models are trained and assessed on load data extracted from EUNITE network competition.

关键词： Predictive models Load forecasting Multilayer perceptrons Economic forecasting Power system modeling Power generation economics Fuel economy Artificial neural networks Power system economics Temperature

来源：评论

学校读者我要写书评

暂无评论

Long term electrical load forecasting via a neurofuzzy model

Long term electrical load forecasting via a neurofuzzy model

引用

International CSI Computer Conference, CSICC

作者： M. Nosrati Maralloo A. R. Koushki C. Lucas A. Kalhor Department of Computer Engineering Science and Research Branch Islamic Azad University Tehran Iran Control and Intelligent Processing Center of Excellence Electrical and Computer Engineering Department University of Tehran Tehran Iran

Long-term forecasting of load demand is necessary for the correct operation of electric utilities. There is an on-going attention toward putting new approaches to the task. Recently, Neurofuzzy modeling has played a successful role in various applications over nonlinear time series prediction. This paper presents a neurofuzzy model for long-term load forecasting. This model is identified through Locally Linear Model Tree (LoLiMoT) learning algorithm. The model is compared to a multilayer perceptron and hierarchical hybrid neural model (HHNM). The models are trained and assessed on load data extracted from a North-American electric utility.

关键词： Load forecasting Predictive models Multilayer perceptrons Power industry Economic forecasting Multi-layer neural network Power system planning Power generation Neural networks Data mining

来源：评论

学校读者我要写书评

暂无评论

Rapid automatic segmentation and visualization of teeth in CT-scan data

引用

Journal of Applied Sciences 2009年第11期9卷 2031-2044页

作者： Akhoondali, H. Zoroofi, R.A. Shirani, G. Control and Intelligent Processing Center of Excellence Faculty of Engineering School of Electrical and Computer Engineering University of Tehran Tehran Iran Department of Oral and Maxillofacial Surgery Faculty of Dentistry Medical Science University of Tehran Tehran Iran

In this study, a fast automatic method is proposed for the segmentation and visualization of teeth in multi-slice CT-scan data of the head. The algorithm consists of five main procedures. In the first part, the mandible and maxilla are separated using maximum intensity projection in the y direction and a step like region separation algorithm. In the second part, the dental region is separated using maximum intensity projection in the z direction, thresholding and cropping. In the third part, the teeth are rapidly segmented using a region growing algorithm based on four thresholds which are used to distinguish between seed points, teeth and none teeth tissue. In the fourth part, the results are visualized using iso-surface extraction and surface and volume rendering. A semi-automatic method is also proposed for rapid metal artifact removal. Results on multiple dadasets have shown the success of the algorithm with the dental region separation and segmentation procedure taking an average of only 2.4 sec to complete for each jaw making it at least tens of times faster than any previously proposed method. © 2009 Asian Network for Scientific Information.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Fully automatic extraction of panoramic dental images from CT-scan volumetric data of the head

引用

Journal of Applied Sciences 2009年第11期9卷 2106-2114页

In this study, a fully automatic technique is proposed for the extraction of panoramic dental images from CT-scan images of the teeth. The process is performed in three steps: Mandibular region isolation, mandibular curve creation and panoramic image extraction. First the mandibular region is isolated. To do this the maxilla and mandible are separated from each other by finding the slice separating them. Then an image of the maximum intensity projection of the slices containing the mandible is obtained. The projection of the mandible is then isolated from the other bones. Using the isolated mandible region an initial curve is created. Nine control points are then selected on the curve. These control points are used to create a fine curve using cubic splines. The formula for each spline segment is used to find the perpendicular lines to the spline on each point on the spline. These perpendicular lines are then used in all slices (mandible and maxilla) to create the panoramic images. The algorithm has many advantages over earlier methods. Results using multiple datasets have shown that the algorithm is robust. © 2009 Asian Network for Scientific Information.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Optimal waypoint placement for road surveillance using unmanned aerial vehicles

Optimal waypoint placement for road surveillance using unman...

引用

作者： McDonald, Suzanne Holsapple, Raymond W. Kingston, Derek University of Maryland College Park MD 20742 United States Air Force Research Laboratory Wright-Patterson AFB OH 45433 United States Department of Electrical and Computer Engineering College Park MD 20742 United States Control Science Center of Excellence Wright-Patterson AFB OH 45433 United States

ISBN: (纸本)9781563479786

In this paper we consider an intelligence, surveillance and reconnaissance (ISR) mission where a human operator and a team of unmanned aerial vehicles (UAVs) are tasked to patrol a road. There are numerous inherent ISR benefits for patrolling a road. For example it might be beneficial to track the suspected movements of enemy troops in a forward operating location. Another example might be to gather intelligence that could then be used, possibly not in real time, to perform change detection, a method that might help with the detection of improvised explosive devices (IEDs). The layout of the road, with respect to a fixed known reference point, is assumed to be known a priori. For example the latitude and longitude coordinates of various points along the road would be sufficient. Most UAV autopilots make use of waypoint navigation to control the vehicle. This work investigates one method of optimally choosing the waypoints for the UAVs along the road. The cost function used minimizes the cross-track area error.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Interior permanent magnet synchronous motor (IPMSM), with a developed brain emotional learning based intelligent controller (BELBIC)

Interior permanent magnet synchronous motor (IPMSM), with a ...

引用

IEEE International Conference on Electric Machines and Drives (IEMDC)

作者： E. Daryabeigi Gh. Arab Markadeh C. Lucas Electrical Engineering Department of Islamic Najafabad branch Islamic Azad University슠 Isfahan Iran Faculty of engineering Department Shahrekord University Shahrekord Iran Iranian Control & Intelligent Processing Center of Excellence Electrical and Computer Engineering Department University of Tehran Tehran Iran

In this paper, a modern intelligent control based on computational model of mammalian limbic system and emotional processes (BELBIC) is presented for speed control of interior magnet synchronous motor (IPMSM). In this work, a novel and simple model of IPMSM motor drive control plant is achieved by using the intelligent control system, which controls motor speed accurately, without needing to using any conventional controllers and also, quite independent of motor parameters. This work was successfully implemented in real time for a laboratory 1-hp IPMSM drive, but this time it is done in simulation by a new control plant for that, which compared with together. Achieved results of the proposed plant show better operating control than the previous plant. The results show excellent control characteristics especially very fast response, simple implementation and robustness with respect to disturbances and manufacturing imperfections. This type of intelligent controllers that has high auto learning speed with simple structure shows superior praxis for industrial scale utilization.

关键词： Permanent magnet motors Synchronous motors Intelligent control Computational intelligence Computational modeling Velocity control Motor drives control system synthesis Laboratories Robust control

来源：评论

学校读者我要写书评

暂无评论

Reliability evaluation of HV substations in the presence of Fault Current Limiter

Reliability evaluation of HV substations in the presence of ...

引用

Power Tech Conference

作者： I. Rahmati M. Fotuhi-Firuzabad Privatization Bureau of Ministry of Energy of Iran Tehran Iran Center of Excellence in Power System Control and Management Department of Electrical Engineering Sharif University of Technology Tehran Iran

Short circuit current is one of the major threats for power system stability. Power system should have the ability to detect and clear these faults within a specified time. The protection system can clear the faults only if the interruption capability of the circuit breakers is higher than the fault level. Expansion of the grid and installation of new power on the scale that is envisaged will require practical solutions to a number of technical challenges. One of the technical challenges is fault level management as system expansion often results in increased fault levels beyond the design limits of the existing switchgears. Replacing the old equipments particularly circuit breakers with the new ones having higher interruption capability is one way to overcome this problem. This, however, is not a cost-effective management of fault levels. Using Fault Current Limiters can be an alternative to avoid this high investment cost. In this paper, application of fault current limiter in substation reliability enhancement is presented. The result of the investigations carried out to assess the impacts of FCL application on substation reliability.

关键词： Substations Fault current limiters Circuit faults Power system reliability Power system stability Power system protection Circuit breakers Short circuit currents Power system faults electrical fault detection

来源：评论

学校读者我要写书评

暂无评论

Neuro-fuzzy based fault diagnosis of a Steam Generator

Neuro-fuzzy based fault diagnosis of a Steam Generator

引用

7th IFAC International Symposium on Fault Detection, Supervision and Safety of Technical Systems, SAFEPROCESS'09

作者： Razavi-Far, Roozbeh Davilu, Hadi Palade, Vasile Lucas, Caro Department of Nuclear Engineering Amirkabir University of Technology P.O. Box 15875 4413 Tehran Iran Computing Laboratory Oxford University Wolfson Building Parks Road Oxford OX1 3QD United Kingdom Center of Excellence on Control and Intelligent Processing Department of Electrical and Computer Engineering University of Tehran P.O. Box 14395 1515 Tehran Iran

ISBN: (纸本)9783902661463

This paper focuses on the development and application of a Neuro-Fuzzy (NF) networks-based scheme for Fault Detection and Isolation (FDI) in a U-tube Steam Generator (UTSG). First, a NF network is trained with data collected from a full scale UTSG simulator, and residuals are generated for fault detection. To identify the UTSG, a Locally Linear Neuro-Fuzzy (LLNF) model is used. This model is trained using the Locally Linear Model Tree (LOLIMOT) algorithm which is an incremental tree structure algorithm. Then, an evolutionary algorithm is used to train a Mamdani type NF network to classify the residuals. The residuals are analyzed by using this NF classifier for fault isolation purposes. © 2009 IFAC.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Image error concealment using edge map and linear prediction residue watermarking and spatial smoothing

Image error concealment using edge map and linear prediction...

引用

IEEE International Conference on Image Processing

作者： Shabnam Sodagari Peyman Hesami Alireza Nasiri Avanaki Department of Electrical Engineering Pennsylvania State University University Park PA USA Control and Intelligent Processing Center of Excellence School of ECE University of Tehran Tehran Iran

A very efficient and simple method for error concealment in image communication over packet loss networks is presented. The method involves embedding a combination of edge map and linear prediction residue of each image block as a robust watermark within the original image at the transmitter and using the extracted watermark along with spatial smoothing at the receiver in order to reconstruct the lost parts. The performance of the proposed scheme shows a 2 dB improvement over state of the art error concealment algorithms.

关键词： Watermarking Smoothing methods Transmitters Computer errors Discrete cosine transforms Data mining Image communication Robustness Image reconstruction Transform coding

来源：评论

学校读者我要写书评

暂无评论

The Application of the Locally Linear Model Tree on Customer Churn Prediction

The Application of the Locally Linear Model Tree on Customer...

引用

International Conference of Soft Computing and Pattern Recognition (SOCPAR)

作者： Amineh Ghorbani Fattaneh Taghiyareh Caro Lucas Faculty of Technology Policy and Management Delft University of Technnology Delft Netherlands Department of Electrical and Computer Engineering University of Tehran Tehran Iran Control and Intelligent Processing Center of Excellence Electrical and Computer Engineering Department University of Tehran Tehran Iran

Acquiring new customers in any business is much more expensive than trying to keep the existing ones. Thus many prediction models are presented to detect churning customers. The objective of this paper was to improve the predictive accuracy and interpretability of churn detection. For this purpose, the application of the locally linear model tree (LOLIMOT) algorithm, which integrates the advantage of neural networks, tree model and fuzzy modeling, was experimented. Applied to the data of a major telecommunication company, the method is found to improve prediction accuracy significantly compared to other algorithms, such as artificial neural networks, decision trees, and logistic regression. The results also indicate that LOLIMOT can have accurate outcome in extremely unbalanced datasets.

关键词： Predictive models Decision trees Neural networks Accuracy Artificial neural networks Logistics Regression tree analysis Pattern recognition Application software Conference management

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：