改進(jìn)的自適應(yīng)譜聚類NJW算法
發(fā)布時(shí)間：2018-09-05 11:36
【摘要】：聚類算法是近年來國際上機(jī)器學(xué)習(xí)領(lǐng)域的一個(gè)新的研究熱點(diǎn)。為了能在任意形狀的樣本空間上聚類,學(xué)者們提出了譜聚類和圖論聚類等優(yōu)秀的算法。首先介紹了圖論聚類算法中的譜聚類經(jīng)典NJW算法和NeiMu圖論聚類算法的基本思路,提出了改進(jìn)的自適應(yīng)譜聚類NJW算法。提出的自適應(yīng)NJW算法的優(yōu)點(diǎn)在于無需調(diào)試參數(shù),即可自動(dòng)求出聚類個(gè)數(shù),克服了經(jīng)典NJW算法需要事先設(shè)置聚類個(gè)數(shù)且需反復(fù)調(diào)試參數(shù)δ才能得出數(shù)據(jù)分類結(jié)果的缺點(diǎn)。在UCI標(biāo)準(zhǔn)數(shù)據(jù)集及實(shí)測數(shù)據(jù)集上對(duì)自適應(yīng)NJW算法與經(jīng)典NJW算法、自適應(yīng)NJW算法與NeiMu圖論聚類算法進(jìn)行了比較。實(shí)驗(yàn)結(jié)果表明,自適應(yīng)NJW算法方便快捷,且具有較好的實(shí)用性。
[Abstract]:Clustering algorithm is a new research hotspot in the field of machine learning in the world in recent years. In order to cluster on arbitrary shape sample space, scholars have proposed spectral clustering and graph theory clustering algorithms. Firstly, the basic ideas of spectral clustering classical NJW algorithm and NeiMu graph theory clustering algorithm in graph theory clustering algorithm are introduced. An improved adaptive spectral clustering NJW algorithm is proposed. The advantage of the proposed adaptive NJW algorithm is that the number of clusters can be automatically calculated without debugging parameters. The disadvantage of the classical NJW algorithm is that the number of clusters needs to be set in advance and the parameter delta needs to be debugged repeatedly to get the classification results. The adaptive NJW algorithm is compared with the classical NJW algorithm and the adaptive NJW algorithm is compared with the NeiMu graph theory clustering algorithm.
【作者單位】： 大連理工大學(xué)計(jì)算機(jī)科學(xué)與技術(shù)學(xué)院;
【基金】：國家大學(xué)生創(chuàng)新創(chuàng)業(yè)訓(xùn)練項(xiàng)目(2016101410168)資助
【分類號(hào)】：O157.5;TP311.13
本文編號(hào)：2224150
[Abstract]:Clustering algorithm is a new research hotspot in the field of machine learning in the world in recent years. In order to cluster on arbitrary shape sample space, scholars have proposed spectral clustering and graph theory clustering algorithms. Firstly, the basic ideas of spectral clustering classical NJW algorithm and NeiMu graph theory clustering algorithm in graph theory clustering algorithm are introduced. An improved adaptive spectral clustering NJW algorithm is proposed. The advantage of the proposed adaptive NJW algorithm is that the number of clusters can be automatically calculated without debugging parameters. The disadvantage of the classical NJW algorithm is that the number of clusters needs to be set in advance and the parameter delta needs to be debugged repeatedly to get the classification results. The adaptive NJW algorithm is compared with the classical NJW algorithm and the adaptive NJW algorithm is compared with the NeiMu graph theory clustering algorithm.
【作者單位】： 大連理工大學(xué)計(jì)算機(jī)科學(xué)與技術(shù)學(xué)院;
【基金】：國家大學(xué)生創(chuàng)新創(chuàng)業(yè)訓(xùn)練項(xiàng)目(2016101410168)資助
【分類號(hào)】：O157.5;TP311.13
【相似文獻(xiàn)】
相關(guān)期刊論文 前3條
1 徐步東;;基于譜聚類的社團(tuán)發(fā)現(xiàn)算法[J];濰坊工程職業(yè)學(xué)院學(xué)報(bào);2013年04期
2 張振宇;張珍;楊文忠;吳曉紅;;復(fù)雜網(wǎng)絡(luò)中重疊社區(qū)檢測[J];計(jì)算機(jī)工程與科學(xué);2013年12期
3 ;[J];;年期
相關(guān)碩士學(xué)位論文 前3條
1 陳昭彤;基于拓?fù)鋭莺妥V聚類的社區(qū)發(fā)現(xiàn)研究[D];中國礦業(yè)大學(xué);2015年
2 郭敏;基于譜聚類的復(fù)雜網(wǎng)絡(luò)社團(tuán)結(jié)構(gòu)發(fā)現(xiàn)算法[D];西安電子科技大學(xué);2014年
3 杜鵬;基于譜聚類和CHSMM的非線性系統(tǒng)的剩余壽命預(yù)測[D];哈爾濱工業(yè)大學(xué);2011年
，本文編號(hào)：2224150
本文鏈接：http://sikaile.net/kejilunwen/yysx/2224150.html
最近更新
教材專著
