【摘要】：隨著人類進入大數(shù)據(jù)時代,通過數(shù)據(jù)挖掘技術(shù)將時間序列數(shù)據(jù)庫中隱藏的、有價值的知識挖掘出來得到了愈多的關(guān)注,其相關(guān)技術(shù)己被成功地運用到各個領(lǐng)域。時間序列相似性度量可以衡量時間序列之間相似程度的方法,其度量結(jié)果可用于分類、聚類、相似性搜索等數(shù)據(jù)挖掘任務中。時間序列聚類是時間序列數(shù)據(jù)挖掘領(lǐng)域中重要的挖掘任務之一,不同的時間序列聚類方法,可以挖掘出不同的隱含信息。本文以時間序列為研究對象,探討時間序列的相似性度量方法和聚類方法,促使方法可以充分與靈活地應用到時間序列數(shù)據(jù)挖掘中,然后擷取潛在珍貴的信息和知識。本文的主要研究內(nèi)容如下:(1)以數(shù)值分布特性和趨勢波動特征為出發(fā)點,提出基于數(shù)值符號和形態(tài)特征的相似性度量方法。新方法能夠充分反映時間序列數(shù)值分布和形態(tài)特征,有效地提高了時間序列相似性的度量效果。(2)針對傳統(tǒng)聚類方法通常需要確定具體聚類數(shù)目,及未能充分反映時間序列整體空間結(jié)構(gòu)和相互影響關(guān)系的問題,提出一種基于中心度的標簽傳播時間序列聚類方法。該方法無需指定具體聚類數(shù)目即可實現(xiàn)自動聚類,并且根據(jù)不同參數(shù)構(gòu)建不同的網(wǎng)絡空間結(jié)構(gòu),聚類數(shù)目能夠?qū)Υ诉M行相應地調(diào)整,提高其在時間序列聚類的性能。(3)動態(tài)時間彎曲和時間序列聚類在金融領(lǐng)域的應用。一方面,以動態(tài)時間彎曲和經(jīng)典時間序列聚類方法為基礎(chǔ),在金融領(lǐng)域進行進一步探索。針對股票聯(lián)動性的研究,挖掘股票的隱含信息,對監(jiān)管部門和投資者決策起著一定幫助作用。另一方面,以滬深300指數(shù)為標的指數(shù),利用新的相似性度量方法和聚類方法對現(xiàn)貨股票進行聚類分析,選定追蹤成分股,并建立優(yōu)化模型來獲得成分股在投資組合中的優(yōu)化權(quán)重,并使得新方法確定的成分股更能準確地模擬標的指數(shù),且能夠滿足不同投資喜好的投資者投資要求。研究內(nèi)容通過數(shù)值實驗分析,并且通過比較研究領(lǐng)域的相關(guān)方法,檢驗了新方法的性能,進一步完善時間序列相似性度量和聚類的研究,同時在一定程度上擴展了時間序列數(shù)據(jù)挖掘相關(guān)理論和提升了方法在金融時間序列數(shù)據(jù)領(lǐng)域中的應用性能。
[Abstract]:With the entry of big data era, the more attention has been paid to mining the valuable knowledge hidden in time series database through data mining technology, the more attention has been paid to it, and its related technology has been successfully applied to various fields. The similarity measurement of time series can be used to measure the degree of similarity among time series, and the results can be used in data mining tasks such as classification, clustering, similarity search and so on. Time series clustering is one of the important mining tasks in the field of time series data mining. Different time series clustering methods can mine different hidden information. Taking time series as the research object, this paper discusses the similarity measurement method and clustering method of time series, so that the method can be fully and flexibly applied to time series data mining, and then extract potentially precious information and knowledge. The main contents of this paper are as follows: (1) the similarity measurement method based on numerical symbols and morphological features is proposed based on numerical distribution characteristics and trend fluctuation characteristics as the starting point. The new method can fully reflect the numerical distribution and morphological characteristics of time series and effectively improve the effect of measuring the similarity of time series. (2) in view of the traditional clustering methods, it is usually necessary to determine the number of specific clusters. In this paper, a clustering method of label propagation time series based on centrality is proposed, which fails to fully reflect the global spatial structure and interaction relationship of time series. This method can realize automatic clustering without specifying the number of clusters, and construct different spatial structure of network according to different parameters, which can be adjusted accordingly. Improve its performance in time series clustering. (3) the application of dynamic time bending and time series clustering in financial field. On the one hand, based on dynamic time bending and classical time series clustering methods, further exploration is carried out in the field of finance. In view of the research of stock association, mining the implicit information of stock plays a certain role in the decision-making of regulators and investors. On the other hand, taking the Shanghai-Shenzhen 300 index as the target index, we use the new similarity measure method and the clustering method to cluster the spot stock and select the tracking component stock. The optimization model is established to obtain the optimal weight of the component stocks in the portfolio, and make the component stocks determined by the new method can more accurately simulate the underlying index, and can meet the investment requirements of investors with different investment preferences. The research contents are analyzed by numerical experiments, and the performance of the new method is tested by comparing the related methods in the field of research, and the research on similarity measurement and clustering of time series is further improved. At the same time, the theory of time series data mining is extended to a certain extent and the application performance of the method in the field of financial time series data is improved.
【學位授予單位】：華僑大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP311.13

【參考文獻】

相關(guān)期刊論文 前10條

1 張翔;閆鑌;李磊;連敬東;席曉琦;陳思宇;張峰;李建新;;基于動態(tài)時間彎曲的X射線變電流投影融合方法[J];光子學報;2017年01期

2 徐健鋒;湯濤;嚴軍峰;劉真;;基于多機器學習競爭策略的短時交通流預測[J];交通運輸系統(tǒng)工程與信息;2016年04期

3 李海林;梁葉;;分段聚合近似和數(shù)值導數(shù)的動態(tài)時間彎曲方法[J];智能系統(tǒng)學報;2016年02期

4 黃令賀;朱慶華;沈超;;差異與穩(wěn)定:網(wǎng)絡百科用戶興趣動態(tài)變化研究[J];圖書情報知識;2016年02期

5 嵇敏;范玉濤;謝福鼎;;一種基于正交函數(shù)系的時間序列聚類方法[J];系統(tǒng)科學與數(shù)學;2016年01期

6 萬�；�;李海林;;基于特征表示的金融多元時間序列數(shù)據(jù)分析[J];統(tǒng)計與決策;2015年23期

7 華昕佳;張帥;李鳳榮;趙魯陽;;帶狀無線傳感器網(wǎng)絡間歇性故障檢測[J];計算機工程;2015年12期

8 朱承治;李題印;李先鋒;張靜;王健;王強鋼;周念成;;基于動態(tài)時間彎曲和云模型的電能計量動態(tài)誤差估計[J];電網(wǎng)技術(shù);2015年11期

9 金秀;姜超;孟婷婷;莊霄威;;我國股票市場拓撲性及加權(quán)網(wǎng)絡中行業(yè)主導性分析[J];東北大學學報(自然科學版);2015年10期

10 鐘禮山;李滿春;伍陽;夏南;程亮;;利用SAR影像時間序列的耕地提取研究[J];地理科學進展;2015年07期

相關(guān)博士學位論文 前5條

1 李海林;時間序列數(shù)據(jù)挖掘中的特征表示與相似性度量方法研究[D];大連理工大學;2012年

2 蘇木亞;譜聚類方法研究及其在金融時間序列數(shù)據(jù)挖掘中的應用[D];大連理工大學;2011年

3 孫吉紅;長時間序列聚類方法及其在股票價格中的應用研究[D];武漢大學;2011年

4 陳佐;時間序列相空間重構(gòu)數(shù)據(jù)挖掘方法及其在證券市場的應用[D];湖南大學;2007年

5 駱科東;短時間序列挖掘方法研究[D];清華大學;2004年

，

本文編號：2439843