检索结果-内蒙古大学图书馆

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Evanthia E. Tripoliti Dimitrios I. Fotiadis Maria Argyropoulou Department of Computer Science Unit of Medical Technology and Intelligent Information Systems University of Ioannina and Biomedical Research Institute Loannina Greece Department of Radiology Medical School University of Ioannina (UoI) Loannina Greece

The aim of this work is the development of a method to assist the diagnosis and classification of the status of Alzheimer's Disease (AD) using information that can be extracted from fMRI. The method consists of five stages: a) preprocessing of fMRI data to remove non-task related variability, b) modeling BOLD response depending on stimulus, c) feature extraction from fMRI data, d) feature selection and e) classification using the Random Forests (RF) algorithm. The proposed method is evaluated using data from 41 subjects (14 young adults, 14 non demented older adults and 13 demented older adults.

关键词： Feature extraction Functional magnetic resonance imaging Alzheimer's disease Radio frequency Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Wavelet-based contourlet in quality evaluation of digital images

引用

Neurocomputing 2008年第1-3期72卷 378-385页

作者： Xinbo Gao Wen Lu Xuelong Li Dacheng Tao School of Electronic Engineering Xidian University Xi’an 710071 China School of Computer Science and Information Systems Birkbeck University of London London WC1E 7HX UK Biometrics Research Centre Department of Computing The Hong Kong Polytechnic University Hung Hom Kowloon Hong Kong

Feature extraction is probably the most important stage in image quality evaluation—effective features can well reflect the quality of digital images and vice versa. As a non-redundant sparse representation, contourlet transform can effectively reflect visual characteristics of images, and it can be employed to perceptually capture the difference between images. Motivated by this, this paper first proposes an objective reduced-reference image quality evaluation metric based on contourlet transform. Experiments demonstrate that this new objective metric achieves consistent image quality evaluation results with what gained by subjective evaluation.

关键词： Digital image processing Quality evaluation Reduced-reference Visual perception Contourlet transform

来源：评论

学校读者我要写书评

暂无评论

A unifying framework for spectral analysis based dimensionality reduction

A unifying framework for spectral analysis based dimensional...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Tianhao Zhang Dacheng Tao Xuelong Li Tie Yang Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China Biometrics Research Centre Department of Computing Hong Kong Polytechnic University Hong Kong China School of Computer Science and Information Systems University of London UK

Past decades, numerous spectral analysis based algorithms have been proposed for dimensionality reduction, which plays an important role in machine learning and artificial intelligence. However, most of these existing algorithms are developed intuitively and pragmatically, i.e., on the base of the experience and knowledge of experts for their own purposes. Therefore, it will be more informative to provide some a systematic framework for understanding the common properties and intrinsic differences in the algorithms. In this paper, we propose such a framework, i.e., ldquopatch alignmentrdquo, which consists of two stages: part optimization and whole alignment. With the proposed framework, various algorithms including the conventional linear algorithms and the manifold learning algorithms are reformulated into a unified form, which gives us some new understandings on these algorithms.

关键词： Algorithm design and analysis Optimization Spectral analysis Weight measurement Classification algorithms Artificial neural networks Level measurement

来源：评论

学校读者我要写书评

暂无评论

Geometrically invariant watermarking using affine covariant regions

Geometrically invariant watermarking using affine covariant ...

引用

IEEE International Conference on Image Processing

作者： Cheng Deng Xinbo Gao Dacheng Tao Xuelong Li Lab of Video & Image Processing System School of Electronic Engineering Xidian University Xi'an China Department of computing Hong Kong Polytechnic University Hung Hom Hong Kong China School of Computer Science and Information Systems Birkbeck University of London London UK

In this paper, we present a robust approach to digital watermarking embedding and retrieval for digital images. The affine-invariant point detector is used to extract feature regions of the given host image. Image normalization and dominant gradient orientation alignment are applied to these feature regions to achieve scaling and rotation invariance. Thereafter, watermarks are embedded in these feature regions. The advantage of this proposed approach is demonstrated by a large amount of experiments, which can against different attacks, such as common image processing, rotation, scaling, cropping, and several other affine transformations.

关键词： Watermarking Detectors Image processing Feature extraction Robustness Covariance matrix Image retrieval Content based retrieval computer vision computer science

来源：评论

学校读者我要写书评

暂无评论

Enhanced Biologically Inspired Model

Enhanced Biologically Inspired Model

引用

26th IEEE Conference on computer Vision and Pattern Recognition (CVPR 2008), vol.7

作者： Yongzhen Huang Kaiqi Huang Liangsheng Wang Dacheng Tao Tieniu Tan Xuelong Li National Laboratory of Pattern Recognition Institute of Automation Chinese Academy and Sciences Beijing China Biometrics Research Centre Department of Computing Hong Kong Polytechnic University Hong Kong China School of Computer Science and Information Systems Birkbeck University of London London UK

It has been demonstrated by Serre et al. that the biologically inspired model (BIM) is effective for object recognition. It outperforms many state-of-the-art methods in challenging databases. However, BIM has the following three problems: a very heavy computational cost due to dense input, a disputable pooling operation in modeling relations of the visual cortex, and blind feature selection in a feedforward framework. To solve these problems, we develop an enhanced BIM (EBIM), which removes uninformative input by imposing sparsity constraints, utilizes a novel local weighted pooling operation with stronger physiological motivations, and applies a feedback procedure that selects effective features for combination. Empirical studies on the CalTech5 database and CalTech101 database show that EBIM is more effective and efficient than BIM. We also apply EBIM to the MIT-CBCL street scene database to show it achieves comparable performance in comparison with the current best performance. Moreover, the new system can process images with resolution 128 × 128 at a rate of 50 frames per second and enhances the speed 20 times at least in comparison with BIM in common applications.

关键词： Biological system modeling Spatial databases Image databases Brain modeling Object recognition Visual databases Computational efficiency Feedforward systems Feedback Layout

来源：评论

学校读者我要写书评

暂无评论

Intelligent patient profiling for diagnosis, staging and treatment selection in colon cancer

Intelligent patient profiling for diagnosis, staging and tre...

引用

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： Yorgos Goletsis Themis P. Exarchos Nikolaos Giannakeas Dimitrios I. Fotiadis Department of Economics University of Ioannina (UoI) Ioannina Greece Department of Medical Physics Medical School University of Ioannina (UoI) Ioannina Greece Institute of Biomedical Technology CERETETH Larissa Greece Panepistimio Ioanninon Ioannina GR Unit of Medical Technology and Intelligent Information Systems Department of Computer Science University of Ioannina (UoI) Ioannina Greece

The selection of a personalized treatment plan for a patient with cancer can be of critical importance for his health or even survival. A Decision Support Platform that can associate the patient clinical situation with the patient DNA Single Nucleotide Polymorphisms (SNPs) can provide the oncologist with a better understanding of the personalized conditions of every single patient. In this paper we present the MATCH platform which performs data integration between medicine and molecular biology, by developing a framework where, clinical and genomic features are appropriately combined in order to handle colon cancer diseases. The core of the platform is based on clustering techniques which provide profiles of patients with similar clinical features and genetic predispositions to cancer. The patients which share the same profile should probably have similar treatment plan and follow up. Through the integration of the clinical and genetic data of a patient, real time conclusions can be drawn for his early diagnosis, staging and more effective colon cancer treatment. Intelligent components are designed and developed which identify single nucleotide polymorphisms (SNPs) from the gene sequences and combine them with the clinical situation of the patient. The produced clinico-genomic profiles are used as a decision support tool for newly sequenced patients.

关键词： Cancer Medical treatment Colon Genetics DNA Medical diagnostic imaging Genomics Bioinformatics Diseases Sequences

来源：评论

学校读者我要写书评

暂无评论

Diabetes and the Tortuosity of Vessels of the Bulbar Conjunctiva

引用

Ophthalmology 2008年第6期115卷 e27-e32页

作者： Owen, Christopher G. Newsom, Richard S.B. Rudnicka, Alicja R. Barman, Sarah A. Woodward, E. Geoffrey Ellis, Tim J. Division of Community Health Sciences St. George's University of London London United Kingdom Southampton Eye Unit Southampton United Kingdom School of Computing Information Systems and Mathematics Kingston University Kingston-upon-Thames Surrey United Kingdom Department of Optometry and Visual Science City University London United Kingdom

Objectives: Diabetes is associated with loss of capillaries and macrovessel dilation in the conjunctiva, similar to well-known vessel changes in the retina. However, little is known about the effect of diabetes on the tortuosity of vessels of the conjunctiva. The authors examined the tortuosity of conjunctival vessels in participants with and without diabetes. Design: Case-control study. Participants and Controls: Fifty-three patients with diabetes (17 with type 1 diabetes, 36 with type 2 diabetes) and 60 controls (all aged 20-94 years). Methods: Digital red-free images of conjunctivae were analyzed using an automated computer algorithm to identify vessel axes and to quantify vessel tortuosity. Differences in vessel tortuosity were adjusted for age, gender, blood pressure, and smoking status. Main Outcome Measures: Tortuosity was expressed in units of curve energy (the square of the radian angular change between subsequent locations identified by the algorithm, standardized by vessel length). Results: A longer duration of diabetes was associated with a reduction in overall vessel tortuosity (-2.8%;95% confidence interval [CI], -4.3% to -1.3% per decade). This inverse association was driven by changes in larger vessels (40 μm in width or more), whereas increased tortuosity was observed in capillary sized vessels (<25 μm, 4.0%;95% CI, -0.2% to 8.2% per decade). Compared with controls, those with type 1 diabetes (median duration of disease, 26 years) showed a 17.9% increase (95% CI, 4.7% to -31.0%) in capillary tortuosity. Conversely, those with type 1 diabetes showed a 7% decrease (95% CI, -11.8% to -2.3%) in tortuosity among vessels 40 to 80 μm or less in size and a 26.8% decrease (95% CI, -66.2% to 12.7%) in the fewer number of vessels more than 80 μm in size compared with controls. Similar, but smaller differences were seen in those with type 2 diabetes with shorter duration of diabetes (median, 7 years). Conclusions: Macrovessel dilation associated with diabetes m

关键词： DIABETES CONJUNCTIVA SMOKING computer algorithms

来源：评论

学校读者我要写书评

暂无评论

A metadata-based architectural model for dynamically resilient systems

Proceedings of the ACM Symposium on Applied Computing

引用

Proceedings of the ACM Symposium on Applied computing 2007年 566-572页

作者： Di Marzo Serugendo, Giovanna Fitzgerald, John Romanovsky, Alexander Guelfi, Nicolas School of Computer Science and Information Systems Birkbeck College London United Kingdom School of Computing Science University of Newcastle NE1 7RU Newcastle upon Tyne United Kingdom Laboratory for Advanced Software Systems University of Luxembourg Luxembourg Luxembourg

ISBN: (纸本)1595934804;9781595934802

Designing open and distributed systems that can dynamically adapt in a predictable way to unexpected events is a challenging issue still not solved. Achieving this objective is a very complex task since it implies reasoning at run-time, explicitly and in a combined way, on a system's functional and non-functional characteristics. This paper proposes a service-oriented architectural model allowing the dynamic enforcement of formally expressed metadata-based resilience policies. It also describes preliminary dynamic resilience experiments acting as proof of concept. Copyright 2007 ACM.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

SBLAST: Structural basic local alignment searching tools using geometric hashing

SBLAST: Structural basic local alignment searching tools usi...

引用

7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE

作者： Milledge, Tom Zheng, Gaolin Mullins, Tim Narasimhan, Giri BioRG School of Computing and Information Science Florida International University Department of Mathematics and Computer Science North Carolina Central University IBM Systems and Technology Group Rochester MN 55901 United States

ISBN: (纸本)1424415098

While much research has been done on finding similarities between protein sequences, there has not been the same progress on finding similarities between protein structures. Here we report a new algorithm (SBLAST) which discovers the largest common substructures between two proteins using a triangle-based variant of the geometric hashing of protein structures algorithm. The algorithm selects triples (triangles) of selected C atoms from all proteins in a protein structure database and creates a hash table using a key based on the three inter-atomic distances. Hash table hits from the triangles of a query protein are extended recursively to determine the largest common substructures less than a threshold deviation level (rmsd). Comparisons between a query protein and a preprocessed protein database can be performed in parallel. Because SBLAST does not rely on protein sequence alignment, common substructures can be detected in the absence of sequence conservation. SBLAST has been tested using the ASTRAL subset of the PDB. ©2007 IEEE.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

An approach to validating translation correctness from SAM to Java

An approach to validating translation correctness from SAM t...

引用

19th International Conference on Software Engineering and Knowledge Engineering, SEKE 2007

作者： Fu, Yujian Dong, Zhijiang Argote-Garcia, Gonzalo Shi, Leyuan He, Xudong School of Computing and Information Science Florida International University United States Department of Computer Science Middle Tennessee State University United States Department of Industrial and Systems Engineering University of Wisconsin Madison United States

ISBN: (纸本)9781627486613

SAM is a formal software architecture description model based on Petri nets and temporal logic. SAM Parser is a tool to automatically translate a SAM architecture design into a program in ArchJava/Java/AspectJ with run-time verification capability. In this paper, we present an approach to show the correctness of the translation algorithm implemented in SAM Parser. Our approach requires a restricted Petri net model with an interleaving semantics, defines the operational semantics of a Java program using communication traces, and shows the consistency between an execution sequence of a Petri net and a communication trace of the corresponding Java program. Copyright © (2007) by Knowledge systems Institute (KSI).

关键词： Petri nets

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：