【摘要】：社區(qū)發(fā)現(xiàn)是復(fù)雜網(wǎng)絡(luò)領(lǐng)域的研究熱點(diǎn)問題。為了提高復(fù)雜網(wǎng)絡(luò)中劃分社區(qū)結(jié)構(gòu)的質(zhì)量,提出了一種新的基于局部相似度的社區(qū)發(fā)現(xiàn)算法。首先,考慮到目前研究者們普遍基于共同鄰居節(jié)點(diǎn)的自身特性來構(gòu)建局部相似指標(biāo),通過引入節(jié)點(diǎn)對(duì)及其共同鄰居間相互聯(lián)絡(luò)的親密程度,定義了新的相似度指標(biāo);接著,基于網(wǎng)絡(luò)節(jié)點(diǎn)相似度矩陣,結(jié)合改進(jìn)的K-means算法對(duì)網(wǎng)絡(luò)節(jié)點(diǎn)進(jìn)行相似性聚類,實(shí)現(xiàn)網(wǎng)絡(luò)的社區(qū)發(fā)現(xiàn)。在真實(shí)網(wǎng)絡(luò)數(shù)據(jù)重構(gòu)的網(wǎng)絡(luò)上進(jìn)行實(shí)驗(yàn),結(jié)果表明,所提算法能夠更準(zhǔn)確、有效地發(fā)現(xiàn)復(fù)雜網(wǎng)絡(luò)中的社區(qū)結(jié)構(gòu)。
[Abstract]:Community discovery is a hot topic in the field of complex networks. In order to improve the quality of partitioning community structure in complex networks, a new community discovery algorithm based on local similarity is proposed. Firstly, considering that the researchers generally construct the local similarity index based on the characteristics of the common neighbor nodes, a new similarity index is defined by introducing the closeness degree between the nodes and their common neighbors. Then, based on the similarity matrix of network nodes, the improved K-means algorithm is used to cluster the network nodes to realize the community discovery. Experiments on real network data reconstruction show that the proposed algorithm is more accurate and effective in finding community structures in complex networks.
【作者單位】： 南京郵電大學(xué)自動(dòng)化學(xué)院;
【基金】：教育部人文社會(huì)科學(xué)研究規(guī)劃基金(15YJAZH016) 江蘇省普通高校研究生創(chuàng)新計(jì)劃(SJZZ16_0151)資助項(xiàng)目
【分類號(hào)】：O157.5

【相似文獻(xiàn)】

相關(guān)期刊論文 前8條

1 馮成進(jìn);;0—1規(guī)劃新算法的改進(jìn)[J];曲阜師范大學(xué)學(xué)報(bào)(自然科學(xué)版);1988年02期

2 歐陽普仁,楊叔子;一種改進(jìn)的Marple算法[J];南京理工大學(xué)學(xué)報(bào)(自然科學(xué)版);1988年01期

3 劉新亮;張濤;郭波;;基于分布估計(jì)算法的備件優(yōu)化配置[J];系統(tǒng)工程理論與實(shí)踐;2009年02期

4 楊大志;崔勇;閆忠文;;博弈的期望算法[J];河北科技師范學(xué)院學(xué)報(bào);2005年04期

5 陳煜聰;楊斌;杜海峰;邵，

本文編號(hào)：2302325