检索结果-内蒙古大学图书馆

Multispectral digital microscopy for in vivo monitoring of oral neoplasia in the hamster cheek pouch model of carcinogenesis

引用

OPTICS EXPRESS 2005年第3期13卷 749-762页

作者： Park, SY Collier, T Aaron, J Markey, MK Richards-Kortum, R Sokolov, K Mackinnon, N MacAulay, C Coghlan, L Milbourne, A Follen, M Univ Texas Dept Biomed Engn Austin TX 78712 USA Univ Texas MD Anderson Canc Ctr Dept Imaging Phys Houston TX 77030 USA British Columbia Canc Res Ctr Dept Canc Imaging Vancouver BC V5Z 4E6 Canada Univ Texas MD Anderson Canc Ctr Div Res Smithville TX 78957 USA Univ Texas MD Anderson Canc Ctr Dept Gynecol Oncol Houston TX 77030 USA Univ Texas Hlth Sci Ctr Dept Obstet Gynecol & Reprod Sci Houston TX 77030 USA

In this study we use a multi-spectral digital microscope (MDM) to measure multi-spectral auto-fluorescence and reflectance images of the hamster cheek pouch model of DMBA ( dimethylbenz[ a] anthracene)induced oral carcinogenesis. The multi-spectral images are analyzed both in the RGB ( red, green, blue) color space as well as in the YCbCr ( luminance, chromatic minus blue, chromatic minus red) color space. Mean image intensity, standard deviation, skewness, and kurtosis are selected as features to design a classification algorithm to discriminate normal mucosa from neoplastic tissue. The best diagnostic performance is achieved using features extracted from the YCbCr space, indicating the importance of chromatic information for classification. A sensitivity of 96% and a specificity of 84% were achieved in separating normal from abnormal cheek pouch lesions. The results of this study suggest that a simple and inexpensive MDM has the potential to provide a cost-effective and accurate alternative to standard white light endoscopy. (C) 2005 Optical Society of America.

关键词： .hamster reflectance multispectral RGB image intensity Richards-Kortum Anderson Cancer Center oral neoplasia cheek pouch DMBA YCbCr chromatic standard deviation skewness kurtosis classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Isomorph-free exhaustive generation of designs with prescribed groups of automorphisms

引用

SIAM JOURNAL ON DISCRETE MATHEMATICS 2005年第3期19卷 664-690页

作者： Kaski, P Aalto Univ Lab Theoret Comp Sci FI-02015 Helsinki Finland

We develop an algorithm framework for isomorph-free exhaustive generation of designs admitting a group of automorphisms from a prescribed collection of pairwise nonconjugate groups, where each prescribed group has a large index relative to its normalizer in the isomorphism-inducing group. We demonstrate the practicality of the framework by producing a complete classification of the Steiner triple systems of order 21 admitting a nontrivial automorphism group. The number of such pairwise nonisomorphic designs is 62336617, where 958 of the designs are anti-Pasch. We also develop consistency checking methodology for gaining confidence in the correct operation of the algorithm implementation.

关键词： classification algorithm combinatorial search consistency checking isomorph rejection isomorph-free generation Kramer-Mesner method Steiner triple system symmetry reduction

来源：评论

学校读者我要写书评

暂无评论

Greylevel Difference classification algorithm in Fractal Image Compression

引用

Journal of Computer Science & Technology 2002年第2期17卷 236-240页

作者：陈毅松卢坚孙正兴张福炎 State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing 210093 P.R. China

This paper proposes the notion of a greylevel difference classification algorithm in fractal image compression. Then an example of the greylevel difference classification algo rithm is given as an improvement of the quadrant greylevel and variance classification in the quadtree-based encoding algorithm. The algorithm incorporates the frequency feature in spatial analysis using the notion of average quadrant greylevel difference, leading to an enhancement in terms of encoding time, PSNR value and compression ratio.

关键词： image coding fractal classification algorithm greylevel differenceclassifica- tion

来源：评论

学校读者我要写书评

暂无评论

OCEC: A novel classification algorithm based on evolutionary computation 6

OCEC: A novel classification algorithm based on evolutionary...

引用

6th International Conference on Signal Processing

作者： Liu, J Zhong, WC Liu, F Jiao, LC Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China

A novel classification algorithm, OCEC, based on evolutionary computation for data mining is proposed. It is compared to GA-based and non GA-based algorithms on 8 datasets from the UCI machine learning repository. Res... 详细信息

ISBN: (纸本)0780374886

关键词： classification data mining evolutionary computation learning (artificial intelligence) classification algorithm evolutionary computation organizational coevolutionary algorithm data mining UCI machine learning repository prediction accuracy

来源：评论

学校读者我要写书评

暂无评论

An Experimental Comparative Study on Three classification algorithms

引用

Journal of Shanghai Jiaotong university(Science) 2003年第2期8卷 133-136页

作者：蔡巍王永成李伟尹中航 Dept. of Computer Science & Eng. Shanghai Jiaotong Univ. Shanghai 200030 China

classification algorithm is one of the key techniques to affect text automatic classification system’s performance, play an important role in automatic classification research area. This paper comparatively analyzed k-NN. VSM and hybrid classification algorithm presented by our research group. Some 2000 pieces of Internet news provided by ChinaInfoBank are used in the experiment. The result shows that the hybrid algorithm’s performance presented by the groups is superior to the other two algorithms.

关键词： classification algorithm k-NN VSM hybrid algorithm

来源：评论

学校读者我要写书评

暂无评论

An assessment of the effectiveness of decision tree methods for land cover classification

引用

REMOTE SENSING OF ENVIRONMENT 2003年第4期86卷 554-565页

作者： Pal, M Mather, PM Univ Nottingham Sch Geog Nottingham NG7 2RD England

Choice of a classification algorithm is generally based upon a number of factors, among which are availability of software, ease of use, and performance, measured here by overall classification accuracy. The maximum likelihood (ML) procedure is, for many users, the algorithm of choice because of its ready availability and the fact that it does not require an extended training process. Artificial neural networks (ANNs) are now widely used by researchers, but their operational applications are hindered by the need for the user to specify the configuration of the network architecture and to provide values for a number of parameters, both of which affect performance. The ANN also requires an extended training phase. In the past few years, the use of decision trees (DTs) to classify remotely sensed data ha's increased. Proponents of the method claim that it has a number of advantages over the ML and ANN algorithms. The DT is computationally fast, make no statistical assumptions, and can handle data that are represented on different measurement scales. Software to implement DTs is readily available over the Internet. Pruning of DTs can make them smaller and more easily interpretable, while the use of boosting techniques can improve performance. In this study, separate test and training data sets from two different geographical areas and two different sensors-multispectral Landsat ETM+ and hyperspectral DAIS-are used to evaluate the performance of univariate and multivariate DTs for land cover classification. Factors considered are: the effects of variations in training data set size and of the dimensionality of the feature space, together with the impact of boosting, attribute selection measures, and pruning. The level of classification accuracy achieved by the DT is compared to results from back-propagating ANN and the ML classifiers. Our results indicate that the performance of the univariate DT is acceptably good in comparison with that of other classifiers, except wit

关键词： decision tree land cover classification algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel sensorless 60°-clamping vector classification pwm technique for switching losses reduction in three-phase PFC converters

A novel sensorless 60°-clamping vector classification pwm t...

引用

15th IEEE Canadian Conference on Electrical and Computer Engineering

作者： Yazdani, D Bakhshai, AR Jain, P Joos, G Isfahan Univ Technol Dept ECE Esfahan Iran

ISBN: (纸本)0780377818

Performance criteria of three-phase PFC converters improve significantly with increasing the switching frequency, and highly depend on the control strategy used This paper introduces a novel sensorless 60degrees-clamping vector classification PWM technique for three-phase PFC converters. The proposed scheme needs no current sensor and extra calculation for identification the highest current carrying phase that must not be switched. In addition, classification algorithm offers exact positioning of the switching instants. with less computational efforts and therefore shorter sampling period and higher switching frequency are possible, when compared with conventional SVM algorithms. In addition, to reduce the switching and conduction losses a novel switching pattern is presented in this paper. Simulation results on PSCAD/EMTDC software program, confirm the validity of the analytical work.

关键词： space vector modulation technique rectifiers classification algorithm

来源：评论

学校读者我要写书评

暂无评论

A load balance service based on probabilistic neural network

A load balance service based on probabilistic neural network

引用

International Conference on Machine Learning and Cybernetics

作者： Jia, Y Sun, JZ Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China

ISBN: (纸本)0780378652

For widely supporting the group communication in the WAN environment, client/server cluster architecture is introduced in our protocol. In order to balance the loads on servers, a novel method for characterizing the workload is presented to replace the traditional workload descriptor - the CPU queue length. The combination of the CPU queue length and other five workload indices are used to determine the load levels. A modified Probabilistic Neural Network is adopted to classify the server load states into six types with the index combination as the input vector. The experiment proves that the shorter mean response time can be obtained in the new method. Based on it, load balancing policy is executed in the system to balance loads on servers.

关键词： classification algorithm probabilistic neural network workload description load balance

来源：评论

学校读者我要写书评

暂无评论

Text categorization method based on Extension Theory

Text categorization method based on Extension Theory

引用

International Conference on Natural Language Processing and Knowledge Engineering

作者： Yi, Y Zheng, Y He, ZS Wu, ZF Chongqing Univ Inst Comp Sci Chongqing 400044 Peoples R China

ISBN: (纸本)0780379020

This paper introduces a new text categorization method utilizing Machine Learning based on Extension Theory. This dependent degree based on the Extension Theory represents the extent to which the element belongs to the predefined categories. The "closeness degree" between the input document vector and standard range of each predefined category can be calculated. The new method is conceptually simple;it can be used with relatively low complexity, and high flexibility: The algorithm is highly scalable. It can be effectively applied to text categorization, of which various features are consecutive values. Furthermore, this algorithm can be widely applied to computational linguistics.

关键词： text categorization extension theory classification algorithm machine learning

来源：评论

学校读者我要写书评

暂无评论

A simple and efficient control strategy for three-phase boost rectifiers

A simple and efficient control strategy for three-phase boos...

引用

15th IEEE Canadian Conference on Electrical and Computer Engineering

作者： Yazdani, D Bakhshai, AR Jain, P Isfahan Univ Technol Dept ECE Esfahan Iran

ISBN: (纸本)0780377818

Performance criteria of three-phase boost rectifiers improve significantly with increasing the switching frequency, and highly depend on the control strategy used. This paper introduces a modified vector classification SVM-based control strategy for three-phase boost rectifiers. By means of the proposed technique abc-dq and dy-alphabeta transformation carried out in conventional SVM-based strategies are avoided. Therefore current regulators in d-q frame and also control difficulties associated with them are removed. In addition, the proposed technique maintains the advantages of other schemes. Simulation results provided, confirm the validity of the analytical work.

关键词： PWM techniques boost rectifier classification algorithm

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：