本文選題：演化聚類　切入點(diǎn)：時(shí)間平滑性　出處：《中國(guó)科學(xué)技術(shù)大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著互聯(lián)網(wǎng)的蓬勃發(fā)展和人們采集數(shù)據(jù)能力的增強(qiáng),實(shí)際生活中出現(xiàn)了越來(lái)越多的隨時(shí)間變化的數(shù)據(jù),我們稱這類數(shù)據(jù)為演化數(shù)據(jù)(EvolutionaryData)。近年來(lái),演化數(shù)據(jù)的聚類問(wèn)題引起了很多研究者的興趣。一般地,演化聚類的要求有兩個(gè)方面:1)每個(gè)時(shí)刻發(fā)現(xiàn)的聚類結(jié)構(gòu)要盡可能好地劃分當(dāng)前時(shí)刻的快照數(shù)據(jù);2)每個(gè)時(shí)刻發(fā)現(xiàn)的聚類結(jié)構(gòu)要盡可能保持時(shí)間平滑性,即和上個(gè)時(shí)刻相比,當(dāng)前時(shí)刻發(fā)現(xiàn)的聚類結(jié)構(gòu)盡量不發(fā)生太大的變化。演化數(shù)據(jù)聚類有很廣泛的應(yīng)用背景,其研究有著很重要的意義。本文從核心節(jié)點(diǎn)和參考點(diǎn)的角度來(lái)研究演化聚類。本文的主要內(nèi)容包括三個(gè)方面。1)受靜態(tài)社區(qū)發(fā)現(xiàn)算法Top Leaders啟發(fā),我們提出一個(gè)基于核心節(jié)點(diǎn)(LeaderNodes)的演化社區(qū)發(fā)現(xiàn)算法(EvoLeaders)。首先,我們基于結(jié)合時(shí)間信息的更新策略來(lái)得到每個(gè)時(shí)刻的初始核心節(jié)點(diǎn)。通過(guò)保持發(fā)現(xiàn)的初始核心節(jié)點(diǎn)集合與上個(gè)時(shí)刻核心節(jié)點(diǎn)集合的時(shí)間平滑性,來(lái)保證由這些核心節(jié)點(diǎn)發(fā)現(xiàn)的社區(qū)跟以前的結(jié)構(gòu)盡量保持平滑。然后,通過(guò)一組分裂合并操作提高社區(qū)質(zhì)量。在兩個(gè)實(shí)際數(shù)據(jù)集上的實(shí)驗(yàn)結(jié)果表明,EvoLeaders算法比Top Leaders算法效果更好。該工作表明了從核心節(jié)點(diǎn)的角度進(jìn)行演化社區(qū)發(fā)現(xiàn)的可行性。2)Top Leaders算法的主要缺點(diǎn)是需要人工輸入社區(qū)數(shù)目�；诰W(wǎng)絡(luò)中每個(gè)節(jié)點(diǎn)與其鄰居節(jié)點(diǎn)之間度的關(guān)系,以及節(jié)點(diǎn)之間共同鄰居的重疊程度,我們改進(jìn)了 Top Leaders算法,并提出了能夠自動(dòng)發(fā)現(xiàn)社區(qū)數(shù)目的AutoLeaders算法。在三個(gè)經(jīng)典數(shù)據(jù)集上的實(shí)驗(yàn)結(jié)果表明,AutoLeaders算法不僅能夠發(fā)現(xiàn)合理的社區(qū)數(shù)目,還能夠發(fā)現(xiàn)合理的社區(qū)結(jié)構(gòu)。進(jìn)一步,基于兩種時(shí)間平滑性策略,我們提出了在動(dòng)態(tài)網(wǎng)絡(luò)中發(fā)現(xiàn)社區(qū)的新的解決方案,即EvoAutoLeaders算法。在兩個(gè)實(shí)際數(shù)據(jù)集上的結(jié)果表明EvoAutoLeaders算法的效果比較好。3)我們從參考點(diǎn)的角度來(lái)處理演化聚類問(wèn)題。首先,我們引入了三種不同的參考點(diǎn),以及相應(yīng)的計(jì)算個(gè)體到參考點(diǎn)距離的策略。然后,基于r-dominance關(guān)系和多目標(biāo)演化算法,提出了一個(gè)演化聚類算法(即rEvoC算法)。實(shí)驗(yàn)結(jié)果證明,與經(jīng)典算法相比,rEvoC算法更適合聚類演化數(shù)據(jù),而且能夠取得更好的效果�？偟膩�(lái)說(shuō),我們從核心節(jié)點(diǎn)和參考點(diǎn)的角度來(lái)處理演化數(shù)據(jù)聚類問(wèn)題,并且通過(guò)實(shí)驗(yàn)證明了其有效性,而且效果比經(jīng)典算法更優(yōu)。本文的工作對(duì)演化社區(qū)發(fā)現(xiàn)和演化數(shù)據(jù)聚類方法研究方面具有一定的參考價(jià)值。
[Abstract]:With the rapid development of the Internet and the enhancement of people's ability to collect data, more and more data have changed over time in real life, which we call evolutionary data in recent years. The clustering of evolutionary data has aroused the interest of many researchers. The evolutionary clustering requirement has two aspects: 1) the cluster structure discovered at each moment should be as well divided as possible into the snapshot data of the current moment. (2) the clustering structure discovered at each moment should be as smooth as possible, that is, compared with the previous moment. The clustering structure discovered at present is as little as possible. Evolutionary data clustering has a wide range of applications. This paper studies evolutionary clustering from the point of view of core nodes and reference points. The main contents of this paper include three aspects. 1) inspired by the static community discovery algorithm Top Leaders. We propose an evolutionary community discovery algorithm based on core node LeaderNodes.First, We obtain the initial core nodes at each moment based on the update strategy combined with time information, by maintaining the temporal smoothness of the initial core node set and the core node set at the last moment. To ensure that the community found by these core nodes remains as smooth as possible from the previous structure. Then, The experimental results on two real data sets show that the EvoLeaders algorithm is more effective than the Top Leaders algorithm. This work shows that the EvoLeaders algorithm can be found in the evolutionary community from the point of view of the core nodes. The main drawback of the row. 2n Leaders algorithm is the need to manually input the number of communities. Based on the degree relationship between each node in the network and its neighbor node, And the degree of overlap of the common neighbors between nodes, we improve the Top Leaders algorithm, The experimental results on three classical data sets show that the AutoLeaders algorithm can not only find the reasonable number of communities, but also find the reasonable community structure. Based on two time smoothing strategies, we propose a new solution for community discovery in dynamic networks. That is, EvoAutoLeaders algorithm. The results on two actual data sets show that the effect of EvoAutoLeaders algorithm is better. 3) We deal with the evolutionary clustering problem from the point of view of reference points. First, we introduce three different reference points. Then, based on r-dominance relation and multi-objective evolutionary algorithm, an evolutionary clustering algorithm (i.e. rEvoC algorithm) is proposed. Compared with the classical algorithm, the rEvoC algorithm is more suitable for clustering evolutionary data and can achieve better results. In general, we deal with the problem of evolutionary data clustering from the point of view of core nodes and reference points, and the experimental results show that the algorithm is effective. And the result is better than the classical algorithm. The work of this paper has some reference value for the research of evolutionary community discovery and evolutionary data clustering method.
【學(xué)位授予單位】：中國(guó)科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP311.13

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 劉秀燕;消除參考點(diǎn)接近失敗報(bào)警方法[J];機(jī)床電器;2002年01期

2 劉韜;;數(shù)控車床回參考點(diǎn)與回參考點(diǎn)的故障排除[J];機(jī)電產(chǎn)品開(kāi)發(fā)與創(chuàng)新;2009年01期

3 劉建峰;;關(guān)于西門(mén)子810系統(tǒng)機(jī)床返回參考點(diǎn)的故障分析[J];機(jī)械工人.冷加工;2006年01期

4 李可心;;關(guān)于機(jī)床回參考點(diǎn)的維修與診斷探究[J];科技傳播;2012年11期

5 樊留群,羅建軍,姜迪剛;機(jī)床參考點(diǎn)的研究[J];機(jī)械制造;1997年06期

6 劉瑞已;現(xiàn)代數(shù)控機(jī)床回參考點(diǎn)的故障分析與排除[J];現(xiàn)代制造工程;2005年03期

7 劉瑞已;數(shù)控機(jī)床回參考點(diǎn)故障分析與診斷[J];設(shè)備管理與維修;2005年01期

8 李晗靜;李生;趙鐵軍;;漢語(yǔ)中方位參考點(diǎn)恢復(fù)研究[J];計(jì)算機(jī)研究與發(fā)展;2007年02期

9 胡慶;王龍;;3G終端中S參考點(diǎn)的實(shí)現(xiàn)研究[J];電信科學(xué);2007年03期

10 鄭宇;;加工中心回參考點(diǎn)的特殊故障及處理[J];制造技術(shù)與機(jī)床;2007年04期

相關(guān)會(huì)議論文 前7條

1 李剛斌;;數(shù)控機(jī)床參考點(diǎn)的設(shè)置與維修[A];第八屆全國(guó)設(shè)備與維修工程學(xué)術(shù)會(huì)議、第十三屆全國(guó)設(shè)備監(jiān)測(cè)與診斷學(xué)術(shù)會(huì)議論文集[C];2008年

2 黃萬(wàn)長(zhǎng);;帶距離編碼標(biāo)記的線性測(cè)量系統(tǒng)返參考點(diǎn)[A];第三屆數(shù)控機(jī)床與自動(dòng)化技術(shù)專家論壇論文集[C];2012年

3 徐平;;西門(mén)子840D系統(tǒng)伺服軸參考點(diǎn)調(diào)整方法研究[A];2011年“天山重工杯”全國(guó)機(jī)電企業(yè)工藝年會(huì)暨第五屆機(jī)械工業(yè)節(jié)能減排工藝技術(shù)研討會(huì)論文集[C];2011年

4 王春來(lái);;數(shù)控機(jī)床回參考點(diǎn)報(bào)警類故障及實(shí)例分析[A];綠色制造與低碳經(jīng)濟(jì)——2010年海南省機(jī)械工程學(xué)會(huì)、海南省機(jī)械工業(yè)質(zhì)量管理協(xié)會(huì)“年會(huì)”暨機(jī)械工程科技學(xué)術(shù)報(bào)告會(huì)論文集[C];2010年

5 王春來(lái);;數(shù)控機(jī)床回參考點(diǎn)報(bào)警類故障及實(shí)例分析[A];“綠色制造 質(zhì)量管理”——海南省機(jī)械工程學(xué)會(huì)、海南省機(jī)械工業(yè)質(zhì)量管理協(xié)會(huì)2011年會(huì)論文集[C];2011年

6 李震;江億;劉曉華;陳曉陽(yáng);;濕空氣熱力過(guò)程的，

本文編號(hào)：1599880