本文選題：貝葉斯網(wǎng)絡(luò)　切入點(diǎn)：隱變量　出處：《合肥工業(yè)大學(xué)》2014年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：隱變量指的是觀察不到的變量,包含了關(guān)于事物本質(zhì)的關(guān)鍵信息,這些變量能夠簡(jiǎn)化結(jié)構(gòu),匯聚顯變量之間的依賴(lài)關(guān)系。隱變量的發(fā)現(xiàn)有利于人們對(duì)于事物真實(shí)狀態(tài)和特性的認(rèn)知,貝葉斯網(wǎng)絡(luò)的隱變量學(xué)習(xí)是數(shù)據(jù)挖掘和知識(shí)發(fā)現(xiàn)研究領(lǐng)域中的一個(gè)重要研究?jī)?nèi)容。論文結(jié)合因果分析技術(shù)和不確定性技術(shù)研究隱變量發(fā)現(xiàn)問(wèn)題,并基于復(fù)雜系統(tǒng)從能量的角度開(kāi)展隱變量的應(yīng)用研究,項(xiàng)目的研究工作具有較高的現(xiàn)實(shí)意義及應(yīng)用價(jià)值。具體研究工作如下：第一,結(jié)構(gòu)分析的隱變量發(fā)現(xiàn)方法難以有效地發(fā)現(xiàn)隱變量且可解釋性較差,提出一種基于局部因果關(guān)系分析的隱變量發(fā)現(xiàn)算法(LCAHD)。LCAHD算法的基本思想：首先尋找目標(biāo)變量的馬爾科夫毯提取局部依賴(lài)結(jié)構(gòu),然后基于擾動(dòng)學(xué)習(xí)獲得擾動(dòng)數(shù)據(jù),聯(lián)合擾動(dòng)數(shù)據(jù)和觀測(cè)數(shù)據(jù)學(xué)習(xí)局部依賴(lài)結(jié)構(gòu)中的因果關(guān)系；進(jìn)而,利用給出的因果結(jié)構(gòu)熵計(jì)算模型對(duì)局部因果結(jié)構(gòu)中因果關(guān)系的不確定性進(jìn)行度量,并利用隱變量和因果關(guān)系不確定性之間的相關(guān)性判定條件,確定隱變量的存在性；最后,利用因果非對(duì)稱(chēng)信息熵對(duì)隱變量的重要性進(jìn)行衡量,并給出隱變量發(fā)現(xiàn)算法。第二,股市中的數(shù)據(jù)具有海量、多源等特點(diǎn),使得數(shù)據(jù)的維數(shù)較高,導(dǎo)致預(yù)測(cè)的準(zhǔn)確性下降,針對(duì)這一缺點(diǎn),提出了基于特征融合的隱變量學(xué)習(xí)及在金融網(wǎng)絡(luò)的研究(LHFF)。該算法的基本思想是：首先,收集影響股市能量的特征,利用互信息對(duì)特征之間的關(guān)聯(lián)度進(jìn)行計(jì)算,并依據(jù)關(guān)聯(lián)度的大小進(jìn)行特征提取；然后,利用對(duì)提取的特征賦權(quán)值,進(jìn)行特征融合,融合后成為隱變量即股市的能量,建立最終的能量計(jì)算模型；最后,利用能量計(jì)算模型計(jì)算能量的大小,根據(jù)能量的大小對(duì)大盤(pán)指數(shù)進(jìn)行預(yù)測(cè)分析。根據(jù)股市的實(shí)踐案例表明該算法具有很強(qiáng)的實(shí)用性。在標(biāo)準(zhǔn)網(wǎng)絡(luò)和股票網(wǎng)絡(luò)進(jìn)行了算法的實(shí)驗(yàn),結(jié)果表明該方法能準(zhǔn)確地確定隱變量的位置,且具有較好的解釋性。在金融網(wǎng)絡(luò)上的實(shí)驗(yàn)效果表明,隱變量在實(shí)際生活領(lǐng)域中的廣泛應(yīng)用性。
[Abstract]:Implicit variables are unobserved variables that contain key information about the nature of things that simplify the structure. The discovery of hidden variables is beneficial to people's cognition of the real state and characteristics of things. The hidden variable learning of Bayesian networks is an important research content in the field of data mining and knowledge discovery. And based on the complex system from the perspective of energy to carry out the application of hidden variables, the research of the project has a higher practical significance and application value. The specific research work is as follows: first, It is difficult to find hidden variables effectively in structural analysis and can not be explained effectively. A new implicit variable discovery algorithm based on local causality analysis (LCAHDN. LCAHD) is proposed. Firstly, the Markov blanket of the target variable is found to extract the local dependency structure, and then the disturbance data is obtained based on the perturbation learning. The joint disturbance data and observation data are used to study the causality in the local dependency structure, and then, the uncertainty of the local causality in the local causality structure is measured by using the given entropy calculation model of the causality structure. The existence of hidden variables is determined by using the correlation judgment condition between hidden variables and causal uncertainties. Finally, the importance of hidden variables is measured by causal asymmetric information entropy, and the algorithm of hidden variable discovery is given. The data in the stock market have the characteristics of mass, multi-source and so on, which make the dimension of the data higher and lead to the decline of the accuracy of prediction. The hidden variable learning based on feature fusion and its research in financial network are proposed. The basic idea of this algorithm is as follows: firstly, the features affecting the energy of the stock market are collected, and the correlation degree between the features is calculated by mutual information. And according to the magnitude of the correlation degree of feature extraction; then, using the extracted feature weighting value, the feature fusion, fusion into a hidden variable, that is, the energy of the stock market, establish the final energy calculation model; finally, The energy calculation model is used to calculate the energy, and the large market index is forecasted and analyzed according to the energy size. The practical cases of the stock market show that the algorithm is very practical. The experiments of the algorithm are carried out in the standard network and the stock network. The results show that this method can accurately determine the location of hidden variables and has a good explanation. The experimental results on financial networks show that the hidden variables are widely used in real life.
【學(xué)位授予單位】：合肥工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：F832.51;F224

【相似文獻(xiàn)】

相關(guān)期刊論文 前2條

1 楊智勇;劉金蘭;;基于隱變量分析的IT投資回報(bào)模型研究[J];統(tǒng)計(jì)與決策;2007年18期

2 ;[J];;年期

相關(guān)會(huì)議論文 前1條

1 瞿英;賈建;吳祈宗;;基于灰色關(guān)聯(lián)聚類(lèi)的隱變量學(xué)習(xí)算法研究[A];2009中國(guó)控制與決策會(huì)議論文集（3）[C];2009年

相關(guān)重要報(bào)紙文章 前1條

1 李興春;二次對(duì)沖投資法：把一個(gè)雞蛋放在幾個(gè)籃子里[N];證券日?qǐng)?bào);2010年

相關(guān)博士學(xué)位論文 前4條

1 王秀美;隱變量模型的建模與優(yōu)化[D];西安電子科技大學(xué);2010年

2 薛曉川;含隱變量的生物系統(tǒng)動(dòng)力學(xué)：從單分子到細(xì)胞[D];清華大學(xué);2009年

3 李萬(wàn)益;基于隱變量概率統(tǒng)計(jì)模型的人體運(yùn)動(dòng)形態(tài)估計(jì)[D];華南理工大學(xué);2015年

4 池清華;PLS隱變量空間模型預(yù)測(cè)控制算法研究[D];浙江大學(xué);2015年

，

本文編號(hào)：1650593