检索结果-内蒙古大学图书馆

International Conference on Machine Learning and Applications (ICMLA)

作者： Huilin Xiong Ya Zhang Xue-wen Chen Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China Department of Electrical Engineering and Computer Science University of Kansas Lawrence KS USA

With microarray data being dramatically accumulated, integrating data from related studies represents a natural way to increase sample size so that more reliable statistical analysis may be performed. However, inherent variation among different microarray platforms makes the data integration not a trivial task. In this paper, we present a simple and effective integration scheme, called normalized linear transform (NLT), to combine data from different microarray platforms. The NLT scheme is compared with three other integration schemes for two tasks: classification analysis and gene marker selection. Our experiments demonstrate that the NLT scheme performs best in terms of classification accuracy under various classification settings, and leads to more biologically significant marker genes.

关键词： Costs Gene expression Support vector machines Support vector machine classification Machine learning Application software image processing pattern recognition Computer science Statistical analysis

来源：评论

学校读者我要写书评

暂无评论

A Multiphase Car-Following Model of Traffic Flow and Numerical Tests

A Multiphase Car-Following Model of Traffic Flow and Numeric...

引用

2007 IEEE International Conference on Automation and Lofistics

作者： Zhipeng Li Fuqiang Liu Yuncai Liu Department of Information and Communication Engineering Tongji University Shanghai 201804China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 200240

ISBN: (纸本)9781424415304

we present in this paper an empirical desired headway model for a single lane car-following theory based on the equation of motion of each *** this new model,traffic situation is suggested to be divided into car-following and free travel regions,and in car-following area the stimulus is a function of space difference between the current headway and the empirical desired headway with a constant *** investigate this model with numerical method and it demonstrates some complex physical features observed in real traffic such as existence of three phases:free,synchronized,and jam flow;spontaneous formation of traffic jams;sudden flow drop in flow- density plane;local cluster effects in synchronized regime;traffic hysteresis in transition between the free and the synchronized ***,the proposed model also predicts that in the synchronized flow regime there exists a unique stable state to relative density,which is insusceptible to noise.

关键词： car-following models inter-vehicle spacing traffic flow

来源：评论

学校读者我要写书评

暂无评论

A Flexible Fully-Multiplicative Orthogonal-Group Based ICA Algorithm

A Flexible Fully-Multiplicative Orthogonal-Group Based ICA A...

引用

IEEE Symposium on Computational Intelligence and Bioinformatics and Computational Biology (CIBCB)

作者： Yalan Ye Jing Wan Zhi-Lin Zhang Chen Jia Wu Lei School of Computer Science and Engineering University of Electronic Science and Technology Chengdu China Institute of Image Processing and Pattern Recognition Shanghai JiaoTong University Shanghai China

In this paper, we propose a flexible fully-multiplicative orthogonal-group based ICA (FlexibleOgICA) algorithm, which can instantaneously separate the mixture of sub-Gaussian and super-Gaussian source signals. It adopts a self-adaptive nonlinear function, which adjusts its parameter to achieve better performance based on the estimation of the kurtosis of super-Gaussian source signals. We also have successfully applied the algorithm to obtain the fetal electrocardiogram (FECG) signal, showing its fast convergence speed and high separation performance

关键词： Independent component analysis Signal processing algorithms Convergence Computational intelligence Bioinformatics Computational biology Signal processing Multidimensional signal processing Biomedical signal processing Switches

来源：评论

学校读者我要写书评

暂无评论

Camera Calibration for 3D Color Scanning System Using Virtual 3D Model

引用

Computer Aided Drafting,Design and Manufacturing 2007年第2期17卷 77-81页

作者： SUN Xian-bin LI De-hua YIN Jie YAO Xun State Key Laboratory for Image Processing and Intelligent Control Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China Hubei University of Technology Wuhan 430068 China

Instead of traditionally using a 3D physical model with many control points on it, a calibration plate with printed chess grid and movable along its normal direction is implemented to provide large area 3D control points with variable Z values. Experiments show that the approach presented is effective for reconstructing 3D color objects in computer vision system.

关键词： computer vision 3D scan camera calibration calibration plate

来源：评论

学校读者我要写书评

暂无评论

A CI feature-based pulmonary nodule segmentation using three-domain mean shift clustering

A CI feature-based pulmonary nodule segmentation using three...

引用

International Conference on Wavelet Analysis and pattern recognition (ICWAPR)

作者： Sheng-Dong Nie Li-Hong LI Zhao-Xue Chen Institute of Medical Imaging Engineering School of Medical Instrumentation & Foodstuff University of Shanghai for Science and Technology Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University China

A novel and more effective algorithm used for segmenting pulmonary nodules in thoracic spiral CT images was presented. The algorithm is based on mean shift clustering method and CI (Convergence Index) features, which can represent the multiple Gaussian model of pulmonary nodules both for solid and sub-solid, substantially. The algorithm has the following steps: (1) calculating the CI features of all pixels in the region of interest (ROI), (2) combining the CI features with the intensity range and the spatial position of the pixels to form a feature vector set, (3) grouping the feature vector set to clusters with mean shift clustering algorithm. Owing to our algorithm can represent the multiple Gaussian model both for solid and sub-solid nodules, it can be used in any user interested nodule regions, especially suitable for the segmentation of sub-solid nodules. Experiments demonstrated that our algorithm can figure out the outline of pulmonary nodules of different forms more precisely.

关键词： Clustering algorithms image segmentation Lungs Computed tomography Cancer pattern recognition Biomedical imaging Solid modeling Wavelet analysis image analysis

来源：评论

学校读者我要写书评

暂无评论

Efficient greedy algorithm for schema matching

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2007年第11期44卷 1903-1911页

作者： Zhang, Zhi Shi, Pengfei Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai 200030 China

Schema matching is the task of finding semantic correspondences between elements of two schemas, which plays a key role in many database applications, such as data integration, electronic commerce, data warehouse, semantic query processing, and XML message exchange, etc. Especially, it is a basic research issue in metadata management. Unfortunately, it still remains largely a manual, labor-intensive, and expensive process. In this paper, the schema matching problem is treated as a combinatorial problem. Firstly, schemas are transformed into multi-labeled graphs, which are the internal schema model for schema matching. Therefore, the schema matching problem is reduced to the labeled graph matching problem. Secondly, a generic graph similarity measure is discussed, which uses the labels of nodes and the edges to compute the similarity between the two schemas. Then, an objective function based on the multi-labeled graph similarity is proposed. Based on the objective function, a greedy matching algorithm is designed to find the desired matching state for schema matching. A prominent characteristic of this method is that the algorithm combines the feasible matching information to obtain optimal matching. Finally, some schema samples are used to test the greedy matching algorithm. The test results confirm that the algorithm is effective, which can obtain mapping results with high quality.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Remote sensing image matching based on corner structures

Remote sensing image matching based on corner structures

引用

International Conference on image and Graphics (ICIG)

作者： Hongya Tuo Zhongliang Jing Yuncai Liu Institute of Aerospace Sci. & Tech. Shanghai Jiaotong University Shanghai China Inst. of Image Processing & Pattern Recognition Shanghai Jiaotong University Shanghai China

In this paper, we propose a matching method for remote sensing images based on corner structures. Firstly corner angle vector is defined to analysis corner structure, and the process of how to obtain it is discussed in detail. Then some measures are given to eliminate the false corners. Finally a relaxation matching scheme is presented. The experiments show the effectiveness and feasibility of our matching method.

关键词： Remote sensing image matching Arm Computer vision Detectors Bismuth pattern recognition image edge detection Graphics image processing

来源：评论

学校读者我要写书评

暂无评论

Color Active Contour Models Based Tongue Segmentation in Traditional Chinese Medicine

Color Active Contour Models Based Tongue Segmentation in Tra...

引用

The 1st International Conference on Bioinformatics and Biomedical Engineering(iCBBE 2007)(首届IEEE生物信息与生物医学工程国际会议)

作者： Jie Yang Yonggang Wang Shengyang Yu Yan Zhang Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Dept.of Dept of Computer Science Nanjing University of Science & Technology Nanjing China

Automated tongue image segmentation in tongue diagnosis system of traditional Chinese medicine is difficult due to two factors: There are lots of pathological details on the surface of tongue, and the shapes of tongue bodies are quite different By adequately considering color information of tongue images, knowledge-based initial tongue body boundary detection and a color gradient are introduced into the gradient vector flow snake. The roughly detected tongue body boundary is employed to lead the usage of color gradient and the convergence of *** experiments results show robustness and accuracy of the algorithm. This work establishes a solid foundation for feature analysis of tongue diagnosis.

关键词： tongue diagnosis tongue segmentation gradient vector flow (GVF) color gradient active contours

来源：评论

学校读者我要写书评

暂无评论

A comparision of Model-based methods for knee cartilage segmentation

A comparision of Model-based methods for knee cartilage segm...

引用

2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007

作者： Cheong, J. Faggian, N. Langs, G. Suter, D. Cicuttini, F. Dept. of Electrical Dept. of Computer Systems Engineering Monash University Australia Clayton School of Information Technology Monash University Australia Institute for Computer Graphics and Vision Graz University of Technology Austria Pattern Recognition and Image Processing Group Vienna University of Technology Austria Dept. of Epidemiology Dept. of Preventive Medicine Monash University Australia

Osteoarthritis is a chronic and crippling disease affecting an increasing number of people each year. With no known cure, it is expected to reach epidemic proportions in the near future. Accurate segmentation of knee cartilage from magnetic resonance imaging (MRI) scans facilitates the measurement of cartilage volume present in a patient's knee, thus enabling medical clinicians to detect the onset of osteoarthritis and also crucially, to study its effects. This paper compares four model-based segmentation methods popular for medical data segmentation, namely Active Shape Models (ASM) (Cootes et al., 1995), Active Appearance Models (AAM) (Cootes et al., 2001), Patch-based Active Appearance Models (PAAM) (Faggian et al., 2006), and Active Feature Models (AFM) (Langs et al., 2006). A comprehensive analysis of how accurately these methods segment human tibial cartilage is presented. The results obtained were benchmarked against the current "gold standard" (cartilage segmented manually by trained clinicians) and indicate that modeling local texture features around each landmark provides the best results for segmenting human tibial cartilage.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Novel V-system descriptor in shape recognition

引用

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics 2007年第7期19卷 920-926页

作者： Zhang, Bo Zou, Jiancheng Liu, Xuli Institute of Image Processing and Pattern Recognition North China University of Technology Beijing 100041 China

In this paper, we present a novel V-system descriptor for 2D models;the descriptor is invariant against the rotation, translation, scale transform, and can remove the effect of the arbitrary start point of the shape through the principal orientation. We show that V-system descriptor can be computed efficiently by the fast V-system transformation, and be good at using multi resolution analysis through weighted Euclidean distance. So the new V-system descriptor has some resistance to slightly occlusion, and may achieve good recognition property according to the actual situation.

关键词： Multiresolution analysis (MRA) Polygon approximation Shape's main orientation V-system descriptor

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：