發(fā)布時(shí)間：2018-04-26 00:39

  本文選題：貝葉斯網(wǎng)絡(luò) + 結(jié)構(gòu)學(xué)習(xí)��； 參考：《中國(guó)科學(xué)技術(shù)大學(xué)》2017年碩士論文

【摘要】：信息時(shí)代的蓬勃發(fā)展使人們積累了大量數(shù)據(jù),將貝葉斯網(wǎng)絡(luò)用于數(shù)據(jù)挖掘,從海量數(shù)據(jù)中挖掘蘊(yùn)含的知識(shí)、邏輯,抽取具有使用價(jià)值的信息,具有重要意義。貝葉斯網(wǎng)絡(luò)是圖論和概率論相結(jié)合的圖形化網(wǎng)絡(luò)模型,該模型直觀明了,在不完備數(shù)據(jù)、不確定信息上具有較強(qiáng)的處理能力,廣泛應(yīng)用于數(shù)據(jù)分析以及不確定性信息處理等領(lǐng)域,值得研究推廣。構(gòu)建貝葉斯網(wǎng)絡(luò)涉及結(jié)構(gòu)和參數(shù)的學(xué)習(xí),其中結(jié)構(gòu)學(xué)習(xí)是技術(shù)關(guān)鍵,直接關(guān)系到參數(shù)學(xué)習(xí)的結(jié)果,繼而影響應(yīng)用效果,研究結(jié)構(gòu)學(xué)習(xí)算法具有很強(qiáng)的必要性。本文主要工作如下:1.針對(duì)主流結(jié)構(gòu)學(xué)習(xí)方法——基于評(píng)分搜索的方法普遍存在精確度不高、結(jié)構(gòu)返回不穩(wěn)定、容易陷入局部最優(yōu)等問(wèn)題,本文首次將飛蛾-燭火優(yōu)化(Moth-Flame Optimization,MFO)算法引入結(jié)構(gòu)學(xué)習(xí),提出了基于MFO的結(jié)構(gòu)學(xué)習(xí)算法(Bayesian Network Structure Learning using MFO,BN-MFO)。BN-MFO 保留了MFO的整體框架,通過(guò)借鑒遺傳算法的雜交、變異等操作,替換了 MFO中的曲線位置更新方法。在變異操作時(shí),參考節(jié)點(diǎn)間互信息,對(duì)不同的節(jié)點(diǎn)采用不同的變異動(dòng)作,使搜索趨向于數(shù)據(jù)蘊(yùn)含的潛在結(jié)構(gòu)。實(shí)驗(yàn)研究了 BN-MFO中評(píng)分函數(shù)和搜索策略的關(guān)系及R函數(shù)關(guān)系對(duì)于收斂性能的影響,分析了 BN-MFO的有效性。在經(jīng)典的Cancer網(wǎng)絡(luò)和Asia網(wǎng)絡(luò)上的對(duì)比實(shí)驗(yàn)結(jié)果表明BN-MFO普遍優(yōu)于同類(lèi)型的對(duì)比算法,具有較強(qiáng)的優(yōu)越性。2.將貝葉斯網(wǎng)絡(luò)應(yīng)用于銀行營(yíng)銷(xiāo)數(shù)據(jù)分析中,運(yùn)用BN-MFO學(xué)習(xí)網(wǎng)絡(luò)結(jié)構(gòu),在實(shí)際應(yīng)用中檢驗(yàn)了算法有效性。貝葉斯網(wǎng)絡(luò)具有分類(lèi)能力,本文實(shí)驗(yàn)對(duì)比了和KNN、SVM的分類(lèi)準(zhǔn)確率,效果較優(yōu),從側(cè)面反映了 BN-MFO的有效性。為了便于模型的使用,還設(shè)計(jì)了基于Matlab的GU1軟件。綜上所述,本文研究解決了基于評(píng)分搜索的結(jié)構(gòu)學(xué)習(xí)方法中普遍存在的問(wèn)題,給出了一種穩(wěn)定返回最優(yōu)結(jié)構(gòu)集合的方法。本文的研究工作,拓寬了貝葉斯網(wǎng)絡(luò)模型的構(gòu)建方式,對(duì)推動(dòng)貝葉斯網(wǎng)絡(luò)理論發(fā)展和拓寬貝葉斯網(wǎng)絡(luò)的應(yīng)用領(lǐng)域有一定意義。
[Abstract]:The vigorous development of the information age has made people accumulate a lot of data. It is of great significance to use the Bias network for data mining, mining the knowledge, logic, and extracting the useful information from the massive data. The Bias network is a graphical network model combining the graph theory with the probability theory. The model is intuitive and incomplete. Data and uncertain information have strong processing ability, which are widely used in data analysis and uncertainty information processing. It is worth studying and popularizing. The construction of Bayesian networks involves the learning of structure and parameters. Structure learning is a key technology, which is directly related to the results of reference learning, and then influences the application effect and research structure. The main work of this paper is as follows: 1. in view of the mainstream structure learning method, the method based on the score search is generally not high in accuracy, the structure is unstable and easy to fall into the local optimal problem. In this paper, the Moth-Flame Optimization (MFO) algorithm is introduced to structural learning for the first time. The MFO based architecture learning algorithm (Bayesian Network Structure Learning using MFO, BN-MFO).BN-MFO retained the overall framework of MFO, replacing the curve position updating method in MFO by using the hybrid and mutation operations of genetic algorithms. In the mutation operation, the information between the reference nodes and the different nodes are different. The variation action that makes the search tend to the potential structure of the data implication. The experiment studies the relationship between the scoring function and the search strategy in BN-MFO and the effect of the R function relationship on the convergence performance, and analyzes the validity of the BN-MFO. The comparison experiment results on the classical Cancer network and the Asia network show that BN-MFO is generally superior to the same type. The algorithm has strong superiority.2. to apply the Bias network to the analysis of bank marketing data. Using BN-MFO to learn network structure, the effectiveness of the algorithm is tested in the practical application. The Bias network has the ability of classification. This paper compares the experiment with KNN, and the accuracy of the classification of SVM is better, and the effectiveness of BN-MFO is reflected from the side. In order to facilitate the use of the model, the GU1 software based on Matlab is also designed. To sum up, this paper studies and solves the common problems in the structure learning method based on the score search, and gives a method to return the optimal set of optimal structures. The development of Juliu network theory and broadening the application area of Bayesian network are of some significance.

【學(xué)位授予單位】：中國(guó)科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 劉寶寧;章衛(wèi)國(guó);李廣文;劉小雄;;一種改進(jìn)遺傳算法的貝葉斯網(wǎng)絡(luò)結(jié)構(gòu)學(xué)習(xí)[J];西北工業(yè)大學(xué)學(xué)報(bào);2013年05期

2 許金超;曾國(guó)蓀;王偉;;一種基于貝葉斯理論的軟件可靠度評(píng)估方法[J];同濟(jì)大學(xué)學(xué)報(bào)(自然科學(xué)版);2012年07期

3 杜敏杰;蔡金燕;劉利民;陳鵬;;基于貝葉斯網(wǎng)絡(luò)模型的電子裝備故障診斷研究[J];計(jì)算機(jī)測(cè)量與控制;2011年11期

4 王越;譚暑秋;劉亞輝;;基于互信息的貝葉斯網(wǎng)絡(luò)結(jié)構(gòu)學(xué)習(xí)算法[J];計(jì)算機(jī)工程;2011年07期

5 任佳;高曉光;茹偉;;數(shù)據(jù)缺失的小樣本條件下BN參數(shù)學(xué)習(xí)[J];系統(tǒng)工程理論與實(shí)踐;2011年01期

6 陳海洋;高曉光;樊昊;;變結(jié)構(gòu)DDBNs的推理算法與多目標(biāo)識(shí)別[J];航空學(xué)報(bào);2010年11期

7 虞欣;鄭肇葆;;基于語(yǔ)義特征和貝葉斯網(wǎng)絡(luò)的航空影像建筑物及灌木分類(lèi)[J];測(cè)繪學(xué)報(bào);2010年03期

8 任佳;高曉光;趙歡歡;;基于目標(biāo)狀態(tài)估計(jì)的UAV路徑重規(guī)劃決策模型[J];控制與決策;2009年07期

9 冀俊忠;張鴻勛;胡仁兵;劉椿年;;一種基于獨(dú)立性測(cè)試和蟻群優(yōu)化的貝葉斯網(wǎng)學(xué)習(xí)算法(英文)[J];自動(dòng)化學(xué)報(bào);2009年03期

10 俞奎;王浩;吳信東;姚宏亮;;貝葉斯網(wǎng)絡(luò)的并行EM學(xué)習(xí)算法[J];模式識(shí)別與人工智能;2008年05期

相關(guān)博士學(xué)位論文 前2條

1 朱明敏;貝葉斯網(wǎng)絡(luò)結(jié)構(gòu)學(xué)習(xí)與推理研究[D];西安電子科技大學(xué);2013年

2 賈海洋;貝葉斯網(wǎng)學(xué)習(xí)若干問(wèn)題研究[D];吉林大學(xué);2008年

，

本文編號(hào)：1803731