检索结果-内蒙古大学图书馆

International CSI Computer Conference, CSICC

作者： Bahareh Atoufi Ali Zakerolhosseini Caro Lucas Department of Electrical and Computer Engineering University of Shahid Beheshti Iran Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Iran

Being able to predict the coming seizure can impressively improve the quality of the patients' lives since they can be warned to avoid doing risky activities via a prediction system. Here, a locally linear neuro fuzzy model is used to predict the EEG time series. Subsequently, this model is utilized in accompany with Singular Spectrum Analysis for prediction. Afterward, an information theoretic criterion is used to select a reliable subset of input variables which contain more information about the target signal. Comparison of three mentioned methods on one hand shows that SSA enables our prediction model to extract the main patterns of the EEG signal and highly improves the prediction accuracy. On the other hand, applying the method of channel selection to the model yields more accurate prediction. It is shown that fusion of some certain signals provides more information about the target and considerably improves the prediction ability.

关键词： Electroencephalography Brain modeling Predictive models Epilepsy Signal analysis Electrodes Statistics Frequency Information analysis Signal processing

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

Abstract Concept Learning Approach Based on Behavioural Feature Extraction

Abstract Concept Learning Approach Based on Behavioural Feat...

引用

International Conference on Computer and Electrical Engineering, ICCEE

作者： Babak Hosseini Majid Nili Ahmadabadi Babak Nadjar Araabi Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran School of Cognitive Sciences Institute for Research in Fundamental Sciences Tehran Iran

In this paper, we propose a novel approach in which an intelligent agent can learn complex concepts in abstract forms. This approach provides a useful tool for non-episodic problems, where agent must search the environment to find special concepts; in addition, yielded abstract representation of the concepts can be used in further high level planning tasks. In order to perform concept learning process in this framework, agent utilizes its own actions according to limitations of sensory data and complexity of related analysis. It extracts required features from environment according to complexity of concepts and their distinctions. These features are composed of sequences of agent's primitive actions. The proposed method is tested on a mobile robot benchmark, and learned concepts are used for a path planning problem. The simulation results demonstrate the capability of our approach in abstracting concepts.

关键词： Feature extraction Mobile robots Process control intelligent control Bayesian methods Learning systems intelligent agent Performance analysis Data mining Testing

来源：评论

学校读者我要写书评

暂无评论

Graph signature for self-reconfiguration planning of modules with symmetry

Graph signature for self-reconfiguration planning of modules...

引用

2009 IEEE/RSJ International Conference on intelligent Robots and Systems

作者： Masoud Asadpour Mohammad Hassan Zokaei Ashtiani Alexander Sproewitz Auke Ijspeert Control and Intelligent Processing Center of Excellence ECE Department University of Tehran Iraq Bio Inspired Robotics Group BIRG. Ecole Polytechnique Federale de Lausanne Switzerland

In our previous works we had developed a framework for self-reconfiguration planning based on graph signature and graph edit-distance. The graph signature is a fast isomorphism test between different configurations and the graph edit-distance is a similarity metric. But the algorithm is not suitable for modules with symmetry. In this paper we improve the algorithm in order to deal with symmetric modules. Also, we present a new heuristic function to guide the search strategy by penalizing the solutions with more number of actions. The simulation results show the new algorithm not only deals with symmetric modules successfully but also finds better solutions in a shorter time.

关键词： Orbital robotics Switches intelligent robots USA Councils Testing Computational efficiency Computational modeling Algorithm design and analysis Stability Table lookup

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

Designing linear phase FIR filters with particle swarm optimization and harmony search

Designing linear phase FIR filters with particle swarm optim...

引用

作者： Shirvani, Abdolreza Khezri, Kaveh Razzazi, Farbod Lucas, Caro Computer Engineering Department Islamic Azad University of Tehran Science Research Branch Iran Biomedical Engineering Department Islamic Azad University of Tehran Science Research Branch Iran Electrical Engineering Department Islamic Azad University of Tehran Science Research Branch Iran Electrical and Computer Engineering Department Control and Intelligent Processing Center of Excellence University of Tehran Iran

ISBN: (纸本)9783642105456

In recent years, evolutionary methods have shown great success in solving many combinatorial optimization problems such as FIR (Finite Impulse Response) filter design. An ordinary method in FIR filter design problem is Parks-McClellan, which is both difficult to implement and computationally expensive. The goal of this paper is to design a near optimal linear phase FIR filter using two recent evolutionary approaches;Particle Swarm Optimization (PSO) and Harmony Search (HS). These methods are robust, easy to implement, and they would not trap in local optima due to their stochastic behavior. In addition, they have distinguishing features such as less variance error and smaller overshoots in both stop and pass bands. To prove these benefits, two case studies are presented and obtained results are compared with previous implementations. In both cases, better and reliable results are achieved. © 2009 Springer-Verlag Berlin Heidelberg.

关键词： FIR filters

来源：评论

学校读者我要写书评

暂无评论

A New Approach to White Blood Cell Nucleus Segmentation Based on Gram-Schmidt Orthogonalization

A New Approach to White Blood Cell Nucleus Segmentation Base...

引用

International Conference on Digital Image processing, ICDIP

作者： S.H. Rezatofighi H. Soltanian-Zadeh R. Sharifian R.A. Zoroofi Control and Intelligent Processing Center of Excellence University of Tehran Tehran Iran Henry Ford Hospital Detroit MI USA Hematology-Oncology and BMT Research Center Tehran University of Medical Sciences Tehran Iran

The differential counting of white blood cells provides invaluable information to hematologist for diagnosis and treatment of many diseases. Manually counting of white blood cells is a tiresome, time-consuming and susceptible to error procedure. Due to the tedious nature of this process, an automatic system is preferable. In this automatic process, Segmentation of white blood cells is one of the most important stages. The nucleus of white blood cells has the most information about the type of white blood cells, thus an exact segmentation seems to be helpful for other stages of automatic recognition of white blood cells. In this paper, we introduced a novel method based on orthogonality theory and Gram-Schmidt process for segmenting the nuclei of white blood cells. For evaluation of results, we compared our proposed method with a hematologist manual segmentation. Results show robustness of this technique for segmentation of nuclei, while this method is very simple to implement.

关键词： White blood cells Image segmentation Process control intelligent control Microscopy Diseases Cells (biology) Cancer Image recognition Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Concept extraction using temporal-difference network EUROCON2009

Concept extraction using temporal-difference network EUROCON...

引用

Eurocon

作者： Habib Karbasian Majid N. Ahmadabadi Babak N. Araabi Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran School of Cognitive Sciences Institute for Studies Theoretical Physics and Mathematics (IPM) Tehran Iran

In this paper, we propose a novel framework to extract temporally extended concepts in a grid world environment using a probable data structure named temporal-difference network. First a reinforcement-learning agent tries to learn its environment for the task of wall following. After that we train a newly introduced temporal-difference network (TDN) in the brain of the agent in order to gain a predictive model of the environment. At last the most promising sequences of action-observation of the given environment will be sorted out based on their probability.

关键词： Robot sensing systems Learning Data mining intelligent agent intelligent robots intelligent sensors Stochastic processes Data structures Predictive models Process control

来源：评论

学校读者我要写书评

暂无评论

Application of neuro-fuzzy models in short term electricity load forecast

Application of neuro-fuzzy models in short term electricity ...

引用

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

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：