检索结果-内蒙古大学图书馆

International Conference on Intelligent and Advanced Systems, ICIAS

作者： Mahdi Ramezani Amin Heidari Emad Fatemizadeh Hamid Soltanian-Zadeh Biomedical Signal and Image Processing Laboratory Sharif University of Technology Tehran Iran Radiology Image Analysis Laboratory Henry Ford Health System Detroit MI USA Control and Intelligent Processing Center of Excellence Electrical and Computer Engineering Department University of Tehran Iran

The aim of this study is to assess the functional connectivity from resting state functional magnetic resonance imaging (fMRI) data. Spectral clustering algorithm was applied to the realistic and real fMRI data acquired from a resting healthy subject to find functionally connected brain regions. In order to make computation of the spectral decompositions of the entire brain volume feasible, the similarity matrix has been sparsified with the t-nearest-neighbor approach. Realistic data were created to investigate the performance of the proposed algorithm and comparing it to the recently proposed spectral clustering algorithm with the Nystrom approximation and also with some well-known algorithms such as the Cross Correlation Analysis (CCA) and the spatial Independent Component Analysis (sICA). To enhance the performance of the methods, a variety of data pre and post processing steps, including data normalization, outlier removal, dimensionality reduction by using wavelet coefficients, estimation of number of clusters and optimal number of independent components (ICs). Results demonstrate the applicability of the proposed algorithm for functional connectivity analysis.

关键词： Clustering algorithms Algorithm design and analysis Correlation Approximation methods Independent component analysis Time series analysis Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Application of bhattacharyya distance as a dissimilarity index for automated prediction of epileptic seizures in rats

Application of bhattacharyya distance as a dissimilarity ind...

引用

International Conference on Intelligent and Advanced Systems, ICIAS

作者： M. Niknazar B. Vosoughi Vahdat M. B. Shamsollahi M. Sayyah Biomedical Signal and Image Processing Laboratory (BiSIPL) School of Electrical Engineering Sharif University of Technology Tehran Iran Physiology and Pharmacology Department Pasteur Institute of Iran Tehran Iran

Seizures are defined as manifest of excessive and hypersynchronous activity of neurons in the cerebral cortex and represent a frequent malfunction of the human central nervous system. Therefore, the search for precursors and predictors of a seizure is of utmost clinical relevance and may even guide us to a deep understanding of the seizure generating mechanisms. In this study we analyzed invasive electroencephalogram (EEG) recordings in rats with experimentally induced generalized epilepsy with a nonlinear method called, dissimilarity index. In order to predict epileptic seizures automatically, Bhattacharyya distance between trajectory matrix of reference window, during an interval quite distant in time from any seizure, and trajectory matrix of present window is employed to measure dynamical dissimilarity index. It is found that employed the method can detect the dissimilarity changes of the neural activity prior to epileptic seizures.

关键词： Electroencephalography Rats Indexes Trajectory Epilepsy Artificial neural networks Phase detection

来源：评论

学校读者我要写书评

暂无评论

引用

International Symposium on Communications Control and signal processing (ISCCSP)

作者： M. Niknazar S. R. Mousavi B. Vosoughi Vahdat M. B. Shamsollahi M. Sayyah Biomedical Signal and Image Processing Laboratory (BiSIPL) School of Electrical Engineering Sharif University of Technology Tehran Iran Biomedical Engineering Laboratory School of Electrical Engineering Sharif University of Technology Tehran Iran Physiology and Pharmacology Department Pasteur Institute of Iran Tehran Iran

Epileptic seizures are generated by an abnormal synchronization of neurons. Since epileptic seizures are unforeseeable for the patients, epileptic seizures detection is an interesting issue in epileptology, that novel approaches to understand the mechanism of epileptic seizures. In this study we analyzed invasive electroencephalogram (EEG) recordings in patients suffering from medically intractable focal epilepsy with a nonlinear method called, dissimilarity index. In order to detect epileptic seizures Bhattacharyya distance between trajectory matrix of reference window during an interval quite distant in time from any seizure and trajectory matrix of present window is employed to measure dynamical dissimilarity index. The data were recorded during an invasive pre-surgical epilepsy monitoring at the ¿Epilepsy Center of the University Hospital of Freiburg¿, Germany. Results show a significant increase in Bhattacharyya distance values between trajectory matrix of reference window and trajectory matrix of present window during seizure. Our results suggest that this technique is useful to detect changes due to epileptic seizures in the EEG.

关键词： Electroencephalography Epilepsy signal processing Brain Frequency synchronization Inspection Transient analysis Neurons Medical treatment Process control

来源：评论

学校读者我要写书评

暂无评论

image encryption using the reciprocal-orthogonal parametric transform

Image encryption using the reciprocal-orthogonal parametric ...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Saad Bouguezel M. Omair Ahmad M. N. S. Swamy Scientific Instrumentation Laboratory Department of Electronics Faculty of Engineering University Farhat Abbas of Setif Setif Algeria Center of Signal processing and Communications Department of Electrical and Computer Engineering Concordia University Montreal Canada

Discrete transforms have been widely used in various signal processing applications. Specifically, transform-based data encryption techniques have become attractive for many recent communication systems. In this paper, we propose a fast and efficient image encryption method based on the reciprocal-orthogonal parametric (ROP) transform. By exploiting the properties of the ROP transform, we show that its independent parameters can successfully be used as an additional secret key for encryption. Experiments results carried clearly show the efficiency of the proposed encryption method.

关键词： Cryptography Discrete transforms signal processing Watermarking Instruments Laboratories image coding Application software Matrix decomposition Software algorithms

来源：评论

学校读者我要写书评

暂无评论

Techniques for automatic magnetic resonance image classification

Techniques for automatic magnetic resonance image classifica...

引用

International Conference on Genetic and Evolutionary Computing

作者： Chen, Hsian-Min Chen, Shih-Yu Chai, Jyh Wen Chen, Clayton Chi-Chang Wu, Chao-Cheng Ouyang, Yen-Chieh Tsai, Ching Tsorng Yang, Ching-Wen Lee, San-Kan Chang, Chein-I Department of Biomedical Engineering Hungkuang University Taichung Taiwan Department of Electrical Engineering National Chung Hsing University Taichung Taiwan Section of Radiology College of Medicine China Medical University Taichung Taiwan Department of Radiology Taichung Veterans General Hospital Taichung Taiwan Department of Radiological Technology Central Taiwan University of Science and Technology Taichung Taiwan Department of Electrical Engineering National Taipei University of Technology Taipei Taiwan Computer Science Department Tunghai University Taichung Taiwan Computer Center Taichung Veterans General Hospital Taichung Taiwan Remote Sensing Signal and Image Processing Laboratory Department of Computer Science and Electrical Engineering University of Maryland Baltimore County Baltimore MD 21250 United States

ISBN: (纸本)9780769542812

Designing and developing automatic techniques for magnetic resonance images (MR) for data analysis is very challenging. One popular and public available method, FAST (FMRIB Automatic Segmentation Tool) has been widely used for automatic brain tissue segmentation for this purpose. This paper investigates limitations of this software algorithm on implementation and further develops a new approach to automatic MR brain tissue classification. The proposed new technique first implements an unsupervised training sample generation process (UTSGP) which includes a Pixel Purity Index (PPI) to generate an initial set of training samples that are further refined by a Support Vector Machine. The resulting training samples are then as a set of training samples for an Iterative Fisher's Linear Discriminant Analysis (IFLDA) which implements FLDA iteratively to improve classification. In order to conduct a fair comparison synthetic images are used for performance evaluation. Experimental results show that our proposed technique is superior in practical implementation to this software algorithm in several aspects of generalization ability, flexibility of choosing number of classes to be classified, avoidance of inconsistent results caused by different initial conditions. © 2010 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Volume-based magnetic resonance brain image classification

Volume-based magnetic resonance brain image classification

引用

International Conference on Genetic and Evolutionary Computing

作者： Chiou, Yaw-Jiunn Chai, Jyh-Wen Chen, Clayton Chi-Chang Chen, Shih-Yu Chen, Hsian-Min Ouyang, Yen-Chieh Su, Wu-Chung Tsai, Ching Tsorng Yang, Ching-Wen Lee, San-Kan Chang, Chein-I Department of Electrical Engineering National Chung Hsing University Taichung Taiwan Section of Radiology College of Medicine China Medical University Taichung Taiwan Department of Radiology Taichung Veterans General Hospital Taichung Taiwan Department of Radiological Technology Central Taiwan University of Science and Technology Taichung Taiwan Department of Biomedical Engineering Hungkuang University Taichung Taiwan Computer Science Department Tunghai University Taichung Taiwan Computer Center Taichung Veterans General Hospital Taichung Taiwan Remote Sensing Signal and Image Processing Laboratory Department of Computer Science and Electrical Engineering University of Maryland Baltimore County Baltimore MD 21250 United States

ISBN: (纸本)9780769542812

This paper develops a volume-based technique, called Volume Sphering Analysis (VSA) which can process all acquired Magnetic Resonance (MR) image slices-formed image cube using only one set of training samples obtained from an image slice. So, several significant advantages and benefits can be gained from our proposed VSA. In the past, when MR image classification is performed, each image slice requires its own specific training samples and training samples obtained from one slice are not applied to another slice. The VSA allows users to reduce computational time. In addition, it saves significant effort in selecting training samples for each of image slices. Thirdly, it is robust to all image slices compared to the traditional one-slice MR image classification which is sensitive to each image slice. Experimental results demonstrate that the VSA performs as well as does that using specifically selected training samples for individual image slices. © 2010 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

3-D video coding using depth transition data

3-D video coding using depth transition data

引用

Picture Coding Symposium, PCS

作者： Woo-Shik Kim Antonio Ortega Jaejoon Lee HoCheon Wey Samsung Electronics Company Limited South Korea Signal and Image Processing Institute Ming Hsieh Department of Electrical Engineering University of Southern California Los Angeles CA USA Multimedia Lab Samsung Advanced Institute of Technology Samsung Electronics Company Limited South Korea

The objective of this work is to develop a new 3-D video coding system which can provide better coding efficiency with improved subjective quality as compared to existing 3-D video systems. We have analyzed the distortions that occur in rendered views generated using depth image based rendering (DIBR) and classified them in order to evaluate their impact on subjective quality. As a result, we found that depth map coding distortion leads to “erosion artifacts” at object boundaries, which lead to significant degradation in perceptual quality. To solve this problem, we propose a solution in which depth transition data is encoded and transmitted to the decoder. Depth transition data for a given pixel indicates the camera position for which this pixel's depth will change. A main reason to consider transmitting explicitly this information is that it can be used to improve view interpolation at many different intermediate camera positions. Simulation results show that the subjective quality can be significantly improved by reducing the effect of erosion artifacts, using our proposed depth transition data. Maximum PSNR gains of about 0.5 dB can also be observed.

关键词： Pixel Cameras Encoding Interpolation Decoding Rendering (computer graphics) image coding

来源：评论

学校读者我要写书评

暂无评论

Enhanced Interval Approach for encoding words into interval type-2 fuzzy sets and convergence of the word FOUs

Enhanced Interval Approach for encoding words into interval ...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Simon Coupland Jerry M. Mendel Dongrui Wu Centre of Computational Intelligence De Montfort University Leicester UK Signal and Image Processing Institute Ming Hsieh Department of Electrical Engineering University of Southern California Los Angeles CA USA Institute of Creative Technologies and the Signal Analysis and Interpretation Laboratory Viterbi School of Engineering University of Southern California Los Angeles CA USA

The Interval Approach (IA) [4] is a method for synthesizing an interval type-2 fuzzy set (IT2 FS) model for a word from data that are collected from a group of subjects. A key assumption made by the IA is: each person's data interval is random and uniformly distributed. This means, of course, that the IT2 FS model for the word is random. Consequently, one can question whether or not the IT2 FS model for the word converges in a stochastic sense. This paper focuses on this question. As a part of our study, we have had to modify some steps of the IA, the resulting being an Enhanced IA (EIA). The paper shows by means of some simulations, that the IT2 FS word models that are obtained from the EIA are converging in a mean-square sense. This provides substantial credence for using the EIA to obtain T2 FS word models.

关键词： Convergence Frequency selective surfaces Mathematical model Stochastic processes Fuzzy sets Probability distribution Context

来源：评论

学校读者我要写书评

暂无评论

Multiscale information modelling for heart morphogenesis

引用

Journal of Physics: Conference Series 2010年第1期238卷

作者： T Abdulla R Imms J M Schleich R Summers Department of Electronic and Electrical Engineering Loughborough University Loughborough UK LTSI Signal and Image Processing Laboratory University of Rennes 1 Rennes France

Science is made feasible by the adoption of common systems of units. As research has become more data intensive, especially in the biomedical domain, it requires the adoption of a common system of information models, to make explicit the relationship between one set of data and another, regardless of format. This is being realised through the OBO Foundry to develop a suite of reference ontologies, and NCBO Bioportal to provide services to integrate biomedical resources and functionality to visualise and create mappings between ontology terms. Biomedical experts tend to be focused at one level of spatial scale, be it biochemistry, cell biology, or anatomy. Likewise, the ontologies they use tend to be focused at a particular level of scale. There is increasing interest in a multiscale systems approach, which attempts to integrate between different levels of scale to gain understanding of emergent effects. This is a return to physiological medicine with a computational emphasis, exemplified by the worldwide Physiome initiative, and the European Union funded Network of Excellence in the Virtual Physiological Human. However, little work has been done on how information modelling itself may be tailored to a multiscale systems approach. We demonstrate how this can be done for the complex process of heart morphogenesis, which requires multiscale understanding in both time and spatial domains. Such an effort enables the integration of multiscale metrology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Volume-based Magnetic Resonance Brain image Classification

Volume-based Magnetic Resonance Brain Image Classification

引用

International Conference on Genetic and Evolutionary Computing (ICGEC)

作者： Yaw-Jiunn Chiou Jyh-Wen Chai Clayton Chi-Chang Chen Shih-Yu Chen Hsian-Min Chen Yen-Chieh Ouyang Wu-Chung Su Ching Tsorng Tsai Ching-Wen Yang San-Kan Lee Chein-I Chang Department of Electrical Engineering National Chung Hsing University Taichung Taiwan Department of Radiology Taichung Veterans General Hospital Taichung Taiwan Section of Radiology College of Medicine China Medical University Taichung Taiwan Department of Radiological Technology Central Taiwan University of Science and Technology Taichung Taiwan Department of Biomedical Engineering Hungkuang University Taichung Taiwan Computer Science Department Tunghai University Taichung Taiwan Computer Center Taichung Veterans General Hospital Taichung Taiwan Remote Sensing Signal and Image Processing Laboratory Department of Computer Science and Electrical Engineering University of Maryland Baltimore MD USA

This paper develops a volume-based technique, called Volume Sphering Analysis (VSA) which can process all acquired Magnetic Resonance (MR) image slices formed image cube using only one set of training samples obtained from an image slice. So, several significant advantages and benefits can be gained from our proposed VSA. In the past, when MR image classification is performed, each image slice requires its own specific training samples and training samples obtained from one slice are not applied to another slice. The VSA allows users to reduce computational time. In addition, it saves significant effort in selecting training samples for each of image slices. Thirdly, it is robust to all image slices compared to the traditional one-slice MR image classification which is sensitive to each image slice. Experimental results demonstrate that the VSA performs as well as does that using specifically selected training samples for individual image slices.

关键词： Training Support vector machine classification image classification Vectors Volume measurement Magnetic resonance

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：