發(fā)布時(shí)間：2018-02-23 19:39

  本文關(guān)鍵詞： 機(jī)會(huì)網(wǎng)絡(luò) 鏈路預(yù)測 相似性指標(biāo) 條件深度信念網(wǎng)絡(luò)　出處：《南昌航空大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：鏈路預(yù)測的目標(biāo)是根據(jù)節(jié)點(diǎn)間已知鏈路及節(jié)點(diǎn)的屬性,估計(jì)節(jié)點(diǎn)間鏈路存在的可能性。近年來,鏈路預(yù)測問題正受到越來越多國內(nèi)外學(xué)者的關(guān)注,這是因?yàn)闇?zhǔn)確的鏈路預(yù)測算法可為研究一些基本的網(wǎng)絡(luò)演化機(jī)制及路由等上層協(xié)議提供支撐,并能應(yīng)用于推薦系統(tǒng)、公共安全領(lǐng)域的輿情監(jiān)控等領(lǐng)域。由于機(jī)會(huì)網(wǎng)絡(luò)具有節(jié)點(diǎn)移動(dòng)性、節(jié)點(diǎn)間間歇性連接和節(jié)點(diǎn)資源有限等特點(diǎn),機(jī)會(huì)網(wǎng)絡(luò)的鏈路預(yù)測是機(jī)會(huì)網(wǎng)絡(luò)研究中的熱點(diǎn)和難點(diǎn)。本文研究機(jī)會(huì)網(wǎng)絡(luò)的鏈路預(yù)測方法,針對機(jī)會(huì)網(wǎng)絡(luò)拓?fù)潆S時(shí)間變化頻繁的特點(diǎn),論文結(jié)合網(wǎng)絡(luò)中鏈路歷史信息及二階鄰居信息,構(gòu)建了反映機(jī)會(huì)網(wǎng)絡(luò)鏈路隨時(shí)間動(dòng)態(tài)變化的相似性指標(biāo)O_AA;采用條件深度信念網(wǎng)絡(luò)(Conditional Deep Belief Network,CDBN)構(gòu)建鏈路預(yù)測模型,提取鏈路隨時(shí)間變化的特征;以所提出的相似性指標(biāo)作為基礎(chǔ)樣本,采用時(shí)間序列法構(gòu)造樣本空間;通過實(shí)驗(yàn)確定網(wǎng)絡(luò)參數(shù),提出單層自適應(yīng)學(xué)習(xí)率,以優(yōu)化訓(xùn)練過程;采用Logistic Regression分類器對機(jī)會(huì)網(wǎng)絡(luò)的鏈路進(jìn)行預(yù)測。論文采用受試者工作特征曲線(Receiver Operating Characteristic Curve,ROC)中的AUC和Precision作為評(píng)價(jià)指標(biāo),在MIT Reality和Infocom05數(shù)據(jù)集下,對本文提出的相似性指標(biāo)O_AA的可行性進(jìn)行了驗(yàn)證;采用ROC中的Precision、Accuracy作為評(píng)價(jià)指標(biāo),在MIT Reality和Infocom05數(shù)據(jù)集下設(shè)計(jì)多組對比實(shí)驗(yàn),驗(yàn)證CDBN預(yù)測模型的有效性。實(shí)驗(yàn)結(jié)果表明,相似性指標(biāo)O_AA能夠更好地反應(yīng)機(jī)會(huì)網(wǎng)絡(luò)鏈路的變化情況;單層自適應(yīng)學(xué)習(xí)率能夠加快CDBN預(yù)測模型的收斂速度,提高了CDBN預(yù)測模型的計(jì)算效率;與深度信念網(wǎng)絡(luò)模型相比,CDBN預(yù)測模型能夠更好地提取鏈路隨時(shí)間變化的特征,獲得了更好的預(yù)測效果。
[Abstract]:The goal of link prediction is to estimate the possibility of the existence of links between nodes according to the known links between nodes and the attributes of nodes. In recent years, the problem of link prediction has been paid more and more attention by scholars at home and abroad. This is because accurate link prediction algorithms can provide support for the study of some basic network evolution mechanisms and routing protocols, and can be applied to recommendation systems. Public opinion monitoring in the field of public safety. Because of the mobility of nodes, intermittent connection between nodes and limited resources of nodes, the opportunistic network is characterized by the mobility of nodes, the intermittent connection between nodes, and the limited resources of nodes, etc. The link prediction of opportunistic networks is a hot and difficult point in the research of opportunistic networks. In this paper, the link prediction methods of opportunistic networks are studied, and the topology of opportunistic networks varies frequently with time. Combining the link history information and the second-order neighbor information in the network, this paper constructs a link prediction model using conditional Deep Belief Network (CDBNs), which reflects the dynamic changes of the opportunistic network links with time, and uses the conditional Deep Belief Network (CDBNs) to construct a link prediction model. The feature of link changing with time is extracted, the time series method is used to construct the sample space based on the proposed similarity index, the network parameters are determined by experiments, and the single-layer adaptive learning rate is proposed to optimize the training process. Logistic Regression classifier is used to predict the link of opportunistic network. In this paper, the AUC and Precision in receiver Operating Characteristic Curveroc are used as evaluation indexes under MIT Reality and Infocom05 data sets. In this paper, the feasibility of the similarity index O 'AA-presented is verified, and the prediction accuracy in ROC is used as the evaluation index. Under the MIT Reality and Infocom05 data sets, the validity of the CDBN prediction model is verified by designing a number of comparative experiments. The similarity index can better reflect the change of the opportunistic network link, and the single-layer adaptive learning rate can accelerate the convergence speed of the CDBN prediction model and improve the computational efficiency of the CDBN prediction model. Compared with the deep belief network model, the CDBN prediction model can extract the characteristics of the link with time better and obtain better prediction results.
【學(xué)位授予單位】：南昌航空大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TN929.5;TP181

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 宋宇翔;;非平穩(wěn)網(wǎng)絡(luò)鏈路延遲率估計(jì)過程仿真分析[J];計(jì)算機(jī)仿真;2013年06期

2 祝光波;李淑君;;企業(yè)網(wǎng)絡(luò)鏈路負(fù)載均衡設(shè)計(jì)[J];現(xiàn)代計(jì)算機(jī)(專業(yè)版);2009年10期

3 劉朝霞;馬力;;移動(dòng)基站網(wǎng)絡(luò)鏈路質(zhì)量比對分析[J];移動(dòng)通信;2011年16期

4 鄭博;黃國策;張衡陽;;三維移動(dòng)Ad hoc網(wǎng)絡(luò)鏈路動(dòng)態(tài)性研究[J];電子與信息學(xué)報(bào);2011年11期

5 高晗;張翠玲;;基于XMLHTTP實(shí)現(xiàn)網(wǎng)絡(luò)鏈路連通性的實(shí)時(shí)監(jiān)控[J];遼寧省交通高等�？茖W(xué)校學(xué)報(bào);2006年02期

6 丁旭陽;范明鈺;羅惠瓊;;無線Mesh網(wǎng)絡(luò)鏈路非相關(guān)多徑發(fā)現(xiàn)算法[J];計(jì)算機(jī)研究與發(fā)展;2007年10期

7 張興;韋潛;馬戈;;基于鄰居列表的傳感器網(wǎng)絡(luò)鏈路安全方案[J];微計(jì)算機(jī)信息;2010年16期

8 韋琳;張紅娟;鄒玲;徐帆;;無線網(wǎng)絡(luò)鏈路質(zhì)量評(píng)估[J];微型機(jī)與應(yīng)用;2014年01期

9 黃立威;李德毅;馬于濤;鄭思儀;張海粟;付鷹;;一種基于元路徑的異質(zhì)信息網(wǎng)絡(luò)鏈路預(yù)測模型[J];計(jì)算機(jī)學(xué)報(bào);2014年04期

10 姜衛(wèi);網(wǎng)絡(luò)鏈路備份的優(yōu)化[J];華南金融電腦;2005年08期

相關(guān)會(huì)議論文 前1條

1 高建軍;朱立江;趙杰;張威;;IP網(wǎng)絡(luò)鏈路擴(kuò)容技術(shù)的選擇與實(shí)現(xiàn)[A];中國新聞技術(shù)工作者聯(lián)合會(huì)2008年學(xué)術(shù)年會(huì)論文集（下）[C];2008年

相關(guān)重要報(bào)紙文章 前1條

1 河南 葉新平 汪艷華;用活Ping命令[N];電子報(bào);2003年

相關(guān)碩士學(xué)位論文 前9條

1 陸金杏;空天中繼網(wǎng)絡(luò)鏈路仿真的設(shè)計(jì)與實(shí)現(xiàn)[D];華中科技大學(xué);2015年

2 陳琦帆;基于深度學(xué)習(xí)的機(jī)會(huì)網(wǎng)絡(luò)鏈路預(yù)測方法研究[D];南昌航空大學(xué);2017年

3 蔣小勇;基于端到端測量的網(wǎng)絡(luò)鏈路特征參數(shù)估計(jì)[D];電子科技大學(xué);2011年

4 姜云漢;網(wǎng)絡(luò)鏈路傳輸控制的隨機(jī)Petri網(wǎng)建模與性能分析[D];大連海事大學(xué);2007年

5 范亞國;基于sFlow的網(wǎng)絡(luò)鏈路流量采集與分析[D];武漢理工大學(xué);2008年

6 劉皓;IP網(wǎng)絡(luò)鏈路權(quán)重優(yōu)化方法研究[D];電子科技大學(xué);2011年

7 秦博;網(wǎng)絡(luò)鏈路丟包率層析成像的應(yīng)用研究[D];電子科技大學(xué);2010年

8 張志勇;Ad Hoc網(wǎng)絡(luò)鏈路穩(wěn)定性研究與應(yīng)用[D];山東大學(xué);2013年

9 顧翔;無線網(wǎng)絡(luò)鏈路相關(guān)性研究[D];華南理工大學(xué);2011年

，

本文編號(hào)：1527370