检索结果-内蒙古大学图书馆

A combined Classification Algorithm Based on C4.5 and NB

3rd International Conference on Intelligence Computation and Applications

作者： Jiang, Liangxiao Li, Chaoqun Wu, Jia Zhu, Jian China Univ Geosci Fac Comp Sci Wuhan 430074 Peoples R China China Univ Geosci Fac Math Wuhan 430074 Peoples R China

ISBN: (纸本)9783540921363

When our learning task is to build a model with accurate classification, C4.5 and NB are two very important algorithms for achieving this task because of their simplicity and high performance. In this paper, we present a combined classification algorithm based on C4.5 and NB, simply C4.5-NB. In C4.5-NB, the class probability estimates of C4.5 and NB are weighted according to their classification accuracy on the training data. We experimentally tested C4.5-NB in Weka system using the whole 36 UCI data sets selected by Weka, and compared it with C4.5 and NB. The experimental results show that C4.5-NB significantly outperforms C4.5 and NB in terms of classification accuracy. Besides, we also observe the ranking performance of C4.5-NB in terms of AUC (the area under the Receiver Operating Characteristics curve). Fortunately, C4.5-NB also significantly outperforms C4.5 and NB.

关键词： decision trees naive Bayes combined algorithms weights classification ranking data mining

来源：评论

学校读者我要写书评

暂无评论

Ladder network parameters identification of an isolated winding by combining the intelligent optimisation algorithm and GNIA

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2019年第2期13卷 296-304页

作者： Ren, Fuqiang Xiao, Yao Zhan, Cao Liu, Yong Yang, Fan Ji, Shengchang Zhu, Lingyu Xi An Jiao Tong Univ State Key Lab Elect Insulat & Power Equipment Xian 710049 Shaanxi Peoples R China Zhongyuan Univ Technol Sch Elect Informat Zhengzhou 450007 Henan Peoples R China China Elect Power Res Inst High Voltage Res Inst Beijing 100192 Peoples R China

The ladder network parameter identification for transformer winding is crucial for the interpretation of the frequency response function data. The traditional identification method, mainly based on intelligent optimisation algorithm, is generally very time-consuming due to a large amount of computation. This study proposes to combine the intelligent algorithm and Gauss-Newton iteration algorithm (GNIA) to improve the optimisation efficiency notably with a sharply dropped calculation workload. These two methods are well-complementary since the intelligent algorithm holds excellent global search ability while the search of the GNIA is directional and quantitative. This study solves three key problems for the combined algorithms. The first problem is the calculation of the least-square correction solution to the network parameters in the iteration algorithm. The treatment of the ill-conditioned Jacobian matrix in the iteration algorithm is the second challenge. Another issue is the determination of the network parameter with zero sensitivity. The identification results on an isolated winding show that the combined algorithms can obtain a more precise solution with far less amount of computation.

关键词： least squares approximations Jacobian matrices Newton method transformer windings optimisation genetic algorithms frequency response search problems parameter estimation iterative methods combined algorithms ladder network parameters identification intelligent optimisation algorithm GNIA ladder network parameter identification transformer winding frequency response function data traditional identification method intelligent algorithm Gauss-Newton iteration algorithm optimisation efficiency sharply dropped calculation workload excellent global search ability identification results isolated winding show

来源：评论

学校读者我要写书评

暂无评论

DISCRETE TECHNIQUES FOR COMPUTER-TRANSFORMATIONS OF DIGITAL IMAGES AND PATTERNS

引用

PATTERN RECOGNITION 1990年第11期23卷 1249-1273页

作者： LI, ZC CONCORDIA UNIV CTR PATTERN RECOGNIT & MACHINE INTELLIGENCEMONTREAL H3G 1M8QUEBECCANADA

Images and patterns through a cycle conversion T−1T are discussed and facilitated by the combined algorithms, where the transformation is T:(ξ,η)→(x,y) with the linear or nonlinear functions x = x(ξ,η) and y = y(ξ,η). A new Area Method is presented for images through T and T−1T of linear transformations, and three combinations of the Splitting-Shooting Method and the Splitting-Integrating Method are proposed for images through T−1T of linear and nonlinear transformations. Furthermore, both error analysis and graphical experiments given prove the importance of those combinations to computer vision, image processing, graphs and pattern recognition.

关键词： Shape transformation Nonlinear model The splitting-shooting method The splitting-integrating method combined algorithms Multi-grey-image Numerical methods Error analysis Computer algorithm Computer vision Image processing Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Efficient and Effective KNN Sequence Search with Approximate n-grams

引用

PROCEEDINGS OF THE VLDB ENDOWMENT 2013年第1期7卷 1-12页

作者： Wang, Xiaoli Ding, Xiaofeng Tung, Anthony K. H. Zhang, Zhenjie Natl Univ Singapore Dept Comp Sci Singapore Singapore Huazhong Univ Sci & Technol Dept Comp Sci Wuhan Hubei Peoples R China Univ South Australia Dept Comp Sci Adelaide SA Australia Adv Digital Sci Ctr Singapore Singapore

In this paper, we address the problem of finding k-nearest neighbors (KNN) in sequence databases using the edit distance. Unlike most existing works using short and exact n-gram matchings together with a filter-and-refine framework for KNN sequence search, our new approach allows us to use longer but approximate n-gram matchings as a basis of KNN candidates pruning. Based on this new idea, we devise a pipeline framework over a two-level index for searching KNN in the sequence database. By coupling this framework together with several efficient filtering strategies, i.e. the frequency queue and the well-known combined Algorithm (CA), our proposal brings various enticing advantages over existing works, including 1) huge reduction on false positive candidates to avoid large overheads on candidate verifications;2) progressive result update and early termination;and 3) good extensibility to parallel computation. We conduct extensive experiments on three real datasets to verify the superiority of the proposed framework.

关键词： Nearest neighbor search Computational efficiency combined algorithms Early termination Filtering strategies K nearest neighbor (KNN) New approaches Parallel Computation Real data sets Sequence database

来源：评论

学校读者我要写书评

暂无评论

Methods for real number representation and their application in data-measuring devices

引用

Measurement 1991年第2期9卷 61-72页

作者： Yakushev, V Institute for Physics and Mechanics of the Academy of Sciences of the Ukr. SSR ul. Nauchnaya 5 Lvov USSR

Methods for representation of real numbers by Cantor, Lurote, Engel series as well as Ostrogradsky algorithms and combined ones are considered. The combined algorithms are given a physical interpretation. Their performance in terms of error probability is analysed, and the representations of real numbers by the series mentioned above are compared. Analogue-to-digital conversion methods based on combined algorithms for real number representation are described. © 1991.

关键词： algorithms combined algorithms data measurement Real number representation

来源：评论

学校读者我要写书评

暂无评论

A Methodological Study of Document Layout Analysis

A Methodological Study of Document Layout Analysis

引用

International Conference on Virtual Reality, Human-Computer Interaction and Artificial Intelligence (VRHCIAI)

作者： Zhang, Chunhu Ibrayim, Mayire Hamdulla, Askar Xinjiang Key Lab Signal Detect & Proc Urumqi 830017 Peoples R China Xinjiang Univ Sch Informat Sci & Engn Urumqi Xinjiang Peoples R China

ISBN: (纸本)9781665491822

Document layout analysis is an important part of document information processing systems, which is essential for many applications such as optical character recognition (OCR) systems, machine translation, information retrieval, and document structured data extraction, as well as for digitizing paper documents and classifying and identifying document image regions. Document-like images contain a wealth of information, and in order to automatically extract and classify regions of interest in document images, the document images are programmed to analyze the layout content for subsequent OCR and automatic transcription. However, the proposed algorithms still have more limitations due to various document layouts and variations of block positions, inter-class and within-class variations, and background noise. This paper first summarizes the traditional learning algorithms based on tour smoothing and segmentation projection, deep learning algorithms using recurrent convolutional neural networks and twin networks, and algorithms combining traditional learning and deep learning proposed in recent years. The current mainstream algorithms and common datasets in experiments for deep learning and their access are highlighted. As well as the comparison of some algorithms on benchmark datasets, and some experimental results with good robustness are given. Finally, the future research areas are prospected for further development.

关键词： Layout analysis deep learning traditional learning datasets combined algorithms

来源：评论

学校读者我要写书评

暂无评论

The Construction of an Individual Credit Risk Assessment Method: Based on the Combination algorithms 1

引用

International Conference on Information Computing and Applications

作者： Li, Jiajun Qin, Liping Zhao, Jia NW Polytech Univ Econ Res Ctr Xian 710129 Shaanxi Peoples R China

ISBN: (数字)9783642161674

ISBN: (纸本)9783642161667

As the rapid growth of personal credit business, we have always been seeking to establish an effective risk assessment model to achieve low costs and better accuracy of decision-making. Over the past few years, the so-called combined algorithms have appeared in many fields, but they are always useless in the field of individual credit risk assessment. So we constructed a practical method based on combined algorithms, and we tested it empirically. The result shows that the application of the method can achieve better accuracy than the BP neural network.

关键词： risk assessments combined algorithms accuracy

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：