检索结果-内蒙古大学图书馆

An efficient node ordering method using the conditional frequency for the k2 algorithm

PATTERN RECOGNITION LETTERS 2014年第1期40卷 80-87页

作者： ko, Song kim, Dae-Won Chung Ang Univ Sch Comp Sci & Engn Seoul 156756 South Korea

In Bayesian networks, the k2 algorithm is one of the most effective structure-learning methods. However, because the performance of the k2 algorithm depends on node ordering, more effective node ordering inference methods are needed. In this paper, we therefore introduce a new node ordering algorithm based on a novel scoring function. Because a child has a better conditional frequency or probability under a correct parent than an incorrect one, we have designed a novel scoring function to evaluate this conditional frequency. Given two variables, our scoring function infers which is the better parent variable. Consequently, the proposed method infers candidate parents by considering all pairs of variables;it then uses these parents as input for the k2 algorithm. Experimental results indicate that our proposed method outperforms previous methods. (C) 2014 Elsevier B. V. All rights reserved.

关键词： Bayesian networks Causal relation Scoring function Node ordering k2 algorithm

来源：评论

学校读者我要写书评

暂无评论

Operational failure analysis of high-speed electric multiple units: A Bayesian network-k2 algorithm-expectation maximization approach

引用

RELIABILITY ENGINEERING & SYSTEM SAFETY 2021年 205卷 107250-107250页

作者： Huang, Wencheng kou, Xingyi Zhang, Yue Mi, Rongwei Yin, Dezhi Xiao, Wei Liu, Zhanru Southwest Jiaotong Univ Sch Transportat & Logist China 611756 Sichuan Peoples R China Southwest Jiaotong Univ Inst Syst Sci & Engn Chengdu 611756 Sichuan Peoples R China Southwest Jiaotong Univ Natl United Engn Lab Intergrated & Intelligent Tr Chengdu 611756 Sichuan Peoples R China Southwest Jiaotong Univ Natl Engn Lab Integrated Transportat Big Data App Chengdu 611756 Sichuan Peoples R China China Railway Eryuan Engn Grp Co LTD China 610031 Sichuan Peoples R China

In this paper, a Bayesian Network-k2 algorithm-Expectation Maximization (BN-k2-EM) approach is proposed to quantify the intensity of coupling influence among the operational failures and find out the specific failure propagation chains in accidents of high-speed electric multiple units, quantitatively. k2 is applied to learn the BN structure because it can effectively learn the structure based on small scale data sets, EM is applied to learn the parameter in BN because it can accurately reflect the probability value among nodes with fast convergence speed. BN-k2-EM belongs to a data-driven method which overcomes the limitation of the logic-based BN approach. BN-k2-EM has 6 steps: establish the failures data matrix;determine the priority of nodes priority based on expanded average causal effect;learn the structure of BN based on k2 algorithm;learn the parameter of BN based on EM algorithm;causal reasoning and predication;reverse reasoning and diagnosis. Finally, a case study is conducted by using the historical high-speed EMU accidents happened in China from 2008 to 2019 as background. The influence strength and sensitivity of each failure mode in the case study are analyzed, and the sensitivity analysis of nodes in each system or sub-system is also conducted.

关键词： High-speed electric multiple units Operational failure analysis Bayesian network k2 algorithm Expectation maximization Failure propagation chain

来源：评论

学校读者我要写书评

暂无评论

Improved Bayesian Network Structure Learning with Node Ordering via k2 algorithm

Improved Bayesian Network Structure Learning with Node Order...

引用

10th International Conference on Intelligent Computing (ICIC)

作者： Wei, Zhongqiang Xu, Hongzhe Li, Wen Gui, Xiaolin Wu, Xiaozhou Xi An Jiao Tong Univ Shaanxi Key Lab Comp Network Xian 710049 Peoples R China

ISBN: (纸本)9783319093390;9783319093383

The precise construction of Bayesian network classifier from database is an NP-hard problem and still one of the most exciting challenges. k2 algorithm can reduce search space effectively, improve learning efficiency, but it requires the initial node ordering as input, which is very limited by the absence of the priori information. On the other hand, search process of k2 algorithm uses a greedy search strategy and solutions are easy to fall into local optimization. In this paper, we present an improved Bayesian network structure learning with node ordering via k2 algorithm. This algorithm generates an effective node ordering as input based on conditional mutual information. The k2 algorithm is also improved combining with Simulated Annealing algorithm in order to avoid falling into the local optimization. Experimental results over two benchmark networks Asia and Alarm show that this new improved algorithm has higher classification accuracy and better degree of data matching.

关键词： Bayesian Network Classifier Structure Learning Search Strategy Conditional Mutual Information k2 algorithm

来源：评论

学校读者我要写书评

暂无评论

A New Approach for Bayesian Classifier Learning Structure via k2 algorithm

A New Approach for Bayesian Classifier Learning Structure vi...

引用

8th International Conference on Intelligent Computing (ICIC)

作者： Bouhamed, Heni Masmoudi, Afif Lecroq, Thierry Rebai, Ahmed Univ Rouen LITIS EA 4108 1 Rue Thomas Becket F-76821 Mont St Aignan France Fac Sci Sfax Dept Math Sfax Tunisia Ctr Biotechnol Sfax Bioinformat Unit Sfax Tunisia

ISBN: (纸本)9783642318368

It is a well-known fact that the Bayesian Networks' (BNs) use as classifiers in different fields of application has recently witnessed a noticeable growth. Yet, the Naive Bayes' application, and even the augmented Naive Bayes', to classifier-structure learning, has been vulnerable to certain limits, which explains the practitioners' resort to other more sophisticated types of algorithms. Consequently, the use of such algorithms has paved the way for raising the problem of super-exponential increase in computational complexity of the Bayesian classifier learning structure, with the increasing number of descriptive variables. In this context, the present work's major objective lies in setting up a further solution whereby a remedy can be conceived for the intricate algorithmic complexity imposed during the learning of Bayesian classifiers' structure with the use of sophisticated algorithms. Noteworthy, the present paper's framework is organized as follows. We start, in the first place, by to propose a novel approach designed to reduce the algorithmic complexity without engendering any loss of information when learning the structure of a Bayesian classifier. We, then, go on to test our approach on a car diagnosis and a Lymphography diagnosis databases. Ultimately, an exposition of our conducted work's interests will be a closing step to this work.

关键词： Bayesian Classifier structure learning classification clustering modeling algorithmic complexity k2 algorithm

来源：评论

学校读者我要写书评

暂无评论

A Simple Node Ordering Method for the k2 algorithm based on the Factor Analysis 6

A Simple Node Ordering Method for the K2 Algorithm based on ...

引用

6th International Conference on Pattern Recognition Applications and Methods (ICPRAM)

作者： Tabar, Vahid Rezaei Allameh Tabatabai Univ Dept Stat Fac Math & Comp Sci Tehran Iran

ISBN: (纸本)9789897582226

In this paper, we use the Factor Analysis (FA) to determine the node ordering as an input for k2 algorithm in the task of learning Bayesian network structure. For this purpose, we use the communality concept in factor analysis. Communality indicates the proportion of each variable's variance that can be explained by the retained factors. This method is much easier than ordering-based approaches which do explore the ordering space. Because it depends only on the correlation matrix. As well, experimental results over benchmark networks 'Alarm' and 'Hailfinder' show that our new method has higher accuracy and better degree of data matching.

关键词： Bayesian Network Factor Analysis k2 algorithm Node Ordering Communality

来源：评论

学校读者我要写书评

暂无评论

Expectation maximization based ordering aggregation for improving the k2 structure learning algorithm

引用

INTELLIGENT DATA ANALYSIS 2015年第5期19卷 1003-1018页

作者： Amirkhani, Hossein Rahmati, Mohammad Amirkabir Univ Technol Comp Engn & Informat Technol Dept Tehran Iran

Some of the basic algorithms for learning the structure of Bayesian networks, such as the well-known k2 algorithm, require a prior ordering over the nodes as part of the input. It is well known that the accuracy of the k2 algorithm is highly sensitive to the initial ordering. In this paper, we introduce the aggregation of ordering information provided by multiple experts to obtain a more robust node ordering. In order to reduce the effect of novice participants, the accuracy of each person is used in the aggregation process. The accuracies of participants, not known in advance, are estimated by the expectation maximization algorithm. Any possible contradictions occurred in the resulting aggregation are resolved by modelling the result as a directed graph and avoiding the cycles in this graph. Finally, the topological order of this graph is used as the initial ordering in the k2 algorithm. The experimental results demonstrate the effectiveness of the proposed method in improving the structure learning process.

关键词： Bayesian network structure learning k2 algorithm node ordering knowledge aggregation expectation maximization approach

来源：评论

学校读者我要写书评

暂无评论

Reliabilities analysis of evacuation on offshore platforms: A dynamic Bayesian Network model

引用

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION 2021年 150卷 179-193页

作者： Wang, Yanfu Wang, kun Wang, Tao Li, Xi Yan khan, Fasial Yang, Zaili Wang, Jin China Univ Petr Coll Mech & Elect Engn Dept Safety Sci & Engn Qingdao Peoples R China Liverpool John Moores Univ Liverpool Logist Offshore & Marine LOOM Res Inst Liverpool Merseyside England Mem Univ Newfoundland Fac Engn & Appl Sci Ctr Risk Integr & Safety Engn C RISE St John NF A1B 3X5 Canada

An offshore platform is naturally vulnerable to accidents, such as the leakage of dangerous chemicals, fire and explosion. Oil and gas are explosive and all the equipment and pipes are squeezed into a limited area on a platform. Escape, Evacuation, and Rescue (EER) plans play a vital role as the last barrier to ensure the safety of personnel in the event of a major accident. As a result, the main contributors leading to evacuation failure need to be analyzed to prioritize technology development and select a robust EER strategy. This research aims to undertake the quantitative reliability analysis of various EER strategies on offshore platforms. First, a reliability prediction model of emergency evacuation is established for offshore platforms based on the k2 structure learning algorithm and a Bayesian network parameter learning method. The conditional probability table of each node is determined by combining the Bayesian estimation method and a junction tree reasoning engine. The reliability of emergency evacuation on a platform is predicted using a dynamic Bayesian network model. The transition probability is determined through a Markov method. The main factors leading to evacuation failure are investigated using the diagnostic reasoning method of Bayesian Network. The findings can provide insights for the development of cost effective EER strategies for an offshore platform. (c) 2021 Institution of Chemical Engineers. Published by Elsevier B.V. All rights reserved.

关键词： k2 algorithm Dynamic Bayesian network Reliability prediction of successful evacuation Analysis of influencing factors

来源：评论

学校读者我要写书评

暂无评论

Classification of fluorescence in situ hybridization images using belief networks

引用

PATTERN RECOGNITION LETTERS 2004年第16期25卷 1777-1785页

作者： Malka, R Lerner, B Ben Gurion Univ Negev Dept Elect & Comp Engn Pattern Anal & Machine Learning Lab IL-84105 Beer Sheva Israel

The structure and parameters of a belief network are learned in order to classify images enabling the detection of genetic abnormalities. We compare a structure learned from the data to another structure obtained utilizing expert knowledge and to the naive Bayesian classifier and study quantization in comparison to density estimation in parameter learning. (C) 2004 Elsevier B.V. All rights reserved.

关键词： belief networks fluorescence in situ hybridization (FISH) image classification naive Bayesian classifier k2 algorithm

来源：评论

学校读者我要写书评

暂无评论

A missing value imputation method using a Bayesian network with weighted learning

引用

ELECTRONICS AND COMMUNICATIONS IN JAPAN 2012年第12期95卷 1-9页

作者： Miyakoshi, Yoshihiro kato, Shohei Nagoya Inst Technol Nagoya Aichi Japan

With the development of computer networks, it has become easy to have huge databases. Accordingly, it is becoming difficult for users to extract knowledge from such databases. In this paper we focus on data mining, especially classification. In real-world data mining, the missing value problem occurs in cases such as speech containing noise, facial occlusion, and the like. When a test sample has missing values, a classification system cannot handle them. In previous studies, various imputation methods have been developed, with the objective of solving the missing value problem with numerous explanatory variables, even if some explanatory variables were ineffective for imputation. It has been said that the use of many variables degrades learning efficiency, and thus we believe that imputation methods should be developed considering the relations among explanatory variables. It is also effective to consider the relations between the test sample and each of the training samples. Therefore, we have proposed an imputation method using a Bayesian network with weighted learning. Experiments have confirmed that the proposed method imputes missed values with approximate values, and the classification system successfully classified test samples in which missed values were imputed by the proposed method, with better success than some conventional imputation methods. (C) 2012 Wiley Periodicals, Inc. Electron Comm Jpn, 95(12): 19, 2012;Published online in Wiley Online Library (***). DOI 10.1002/ecj.11449

关键词： classification missing value Bayesian network weighted learning k2 algorithm

来源：评论

学校读者我要写书评

暂无评论

Construction of Customer Classification Model Based on Bayesian Network

引用

JOURNAL OF COMPUTERS 2013年第5期8卷 1200-1206页

作者： Zhu, Qian Zhang, Yingying Hebei Finance Univ Dept Econ & Business Baoding 071051 Peoples R China

At present, the researches on customer segmentation model based on Bayesian network are few. This paper makes a research on the classification problems based on Bayesian network. First of all, it used literature search and case study to describe the related knowledge and classification principles on Bayesian network. After that, combining with Adventure Works Cycles company's customer data, we made the use of k2 learning algorithm to search the best network structure and got two more reasonable Bayesian network topologies. Thereafter, we calculated the posterior probability and selected the largest one of Bayesian network. Then, we adopted 10 - fold stratified cross-validation method to verify the correctness of classification model, and the results are satisfactory. Finally, this paper finds out Bayesian network classification has greater advantages than other classification methods.

关键词： Bayesian network Customer classification k2 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：