本文關(guān)鍵詞： 概率分布 復(fù)雜網(wǎng)絡(luò) 模塊化 吉布斯采樣 LDA主題模型　出處：《微電子學(xué)與計(jì)算機(jī)》2017年06期 　論文類型：期刊論文

【摘要】：提出基于概率分布的復(fù)雜網(wǎng)絡(luò)結(jié)構(gòu)模塊化方法.復(fù)雜網(wǎng)絡(luò)結(jié)構(gòu)模塊化擁有一個(gè)專屬流程,分為模塊變量分配和結(jié)構(gòu)化索引兩個(gè)步驟.在模塊變量分配中,所提方法構(gòu)建出復(fù)雜網(wǎng)絡(luò)模塊概率分布模型,通過(guò)吉布斯采樣獲取模型學(xué)習(xí)樣本.對(duì)樣本進(jìn)行監(jiān)督,以獲取模塊條件概率函數(shù)真實(shí)解.用真實(shí)解表示模塊比重,真實(shí)解的數(shù)量表示復(fù)雜網(wǎng)絡(luò)結(jié)構(gòu)模塊數(shù).在結(jié)構(gòu)化索引中,所提方法利用LDA主題模型確定以上構(gòu)建的模塊化復(fù)雜網(wǎng)絡(luò)是否成立.實(shí)驗(yàn)結(jié)果表明,所體方法構(gòu)建出的模塊化復(fù)雜網(wǎng)絡(luò)具備較強(qiáng)線性.
[Abstract]:The modularization method of complex network structure based on probability distribution is proposed. The modularization of complex network structure has a special process, which is divided into two steps: module variable allocation and structured index. The proposed method is used to construct the probability distribution model of the complex network module and obtain the model learning samples by Gibbs sampling. The sample is supervised to obtain the real solution of the conditional probability function of the module, and the specific gravity of the module is expressed by the real solution. The number of real solutions represents the number of complex network modules. In the structured index, the proposed method uses the LDA topic model to determine whether the modular complex network constructed above is valid. The experimental results show that, The modular complex network constructed by the volume method has strong linearity.
【作者單位】： 鄭州財(cái)經(jīng)學(xué)院信息工程學(xué)院;
【分類號(hào)】：O157.5

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 刁洪祥;肖健;陳義明;;蛋白質(zhì)交互網(wǎng)絡(luò)模塊化的數(shù)據(jù)分析[J];計(jì)算機(jī)工程與應(yīng)用;2010年33期

，

本文編號(hào)：1520150