復(fù)雜網(wǎng)絡(luò)中節(jié)點暫態(tài)中心性預(yù)測研究
發(fā)布時間:2018-08-11 14:49
【摘要】:對復(fù)雜網(wǎng)絡(luò)中節(jié)點的3種暫態(tài)中心性進(jìn)行了預(yù)測研究。通過在真實數(shù)據(jù)集中分析節(jié)點不同時刻的暫態(tài)中心性值發(fā)現(xiàn),不同時刻節(jié)點的暫態(tài)中心性具有很強(qiáng)的相關(guān)性;诖,提出幾種預(yù)測方法對真實數(shù)據(jù)集中節(jié)點未來的暫態(tài)中心性值進(jìn)行預(yù)測。通過對真實值與預(yù)測值進(jìn)行誤差分析,比較了不同預(yù)測方法在不同真實數(shù)據(jù)中的預(yù)測性能。結(jié)果表明,在MIT數(shù)據(jù)集中,最近時窗加權(quán)平均方法的性能最好;在Infocom 06數(shù)據(jù)集中,最近時窗平均方法的性能最好。
[Abstract]:In this paper, three kinds of transient centrality of nodes in complex networks are predicted. By analyzing the transient centrality of nodes at different times in real data sets, it is found that the transient centrality of nodes at different times is highly correlated. Based on this, several prediction methods are proposed to predict the future transient centrality of nodes in real data sets. Through the error analysis of real value and forecast value, the prediction performance of different prediction methods in different real data is compared. The results show that the performance of the nearest window weighted averaging method is the best in the MIT dataset, and the nearest window averaging method is the best in the Infocom 06 dataset.
【作者單位】: 三峽大學(xué)計算機(jī)與信息學(xué)院;
【基金】:國家重點研發(fā)計劃(2016YFB0800403) 國家自然科學(xué)基金(61174177,61602272,41172298) 湖北省自然科學(xué)基金(2017CFB594)資助
【分類號】:O157.5
[Abstract]:In this paper, three kinds of transient centrality of nodes in complex networks are predicted. By analyzing the transient centrality of nodes at different times in real data sets, it is found that the transient centrality of nodes at different times is highly correlated. Based on this, several prediction methods are proposed to predict the future transient centrality of nodes in real data sets. Through the error analysis of real value and forecast value, the prediction performance of different prediction methods in different real data is compared. The results show that the performance of the nearest window weighted averaging method is the best in the MIT dataset, and the nearest window averaging method is the best in the Infocom 06 dataset.
【作者單位】: 三峽大學(xué)計算機(jī)與信息學(xué)院;
【基金】:國家重點研發(fā)計劃(2016YFB0800403) 國家自然科學(xué)基金(61174177,61602272,41172298) 湖北省自然科學(xué)基金(2017CFB594)資助
【分類號】:O157.5
【相似文獻(xiàn)】
相關(guān)期刊論文 前9條
1 付立東;高琳;馬小科;;基于社團(tuán)檢測的復(fù)雜網(wǎng)絡(luò)中心性方法[J];中國科學(xué):信息科學(xué);2012年05期
2 李靜茹;喻莉;趙佳;;加權(quán)社交網(wǎng)絡(luò)節(jié)點中心性計算模型[J];電子科技大學(xué)學(xué)報;2014年03期
3 江健;淦文燕;趙東杰;張海粟;;基于拓?fù)鋭莸纳鐣ㄐ啪W(wǎng)局域中心性分析[J];系統(tǒng)工程學(xué)報;2010年06期
4 陳國強(qiáng);陳亮;;一種基于資源分配策略的復(fù)雜網(wǎng)絡(luò)中心性測度[J];計算機(jī)科學(xué);2011年08期
5 邵浩;陳東方;劉欣;;復(fù)雜網(wǎng)絡(luò)算法中K-shell與介數(shù)中心性算法的實現(xiàn)[J];現(xiàn)代計算機(jī)(專業(yè)版);2014年17期
6 徐健;;基于復(fù)雜網(wǎng)絡(luò)的節(jié)點影響力評價模型研究[J];軟件導(dǎo)刊;2014年03期
7 周濤;;專欄評述[J];電子科技大學(xué)學(xué)報;2014年03期
8 李澤荃;張瑞新;楊w,
本文編號:2177311
本文鏈接:http://sikaile.net/kejilunwen/yysx/2177311.html
最近更新
教材專著