國立高雄大學圖資館 |

Language: English

Back

在靜態與串流資料中的高效率間接關聯探勘 = Efficient Mini...

國立高雄大學資訊工程學系碩士班

在靜態與串流資料中的高效率間接關聯探勘 = Efficient Mining of Indirect Associations from Static Data and Streaming Data

Record Type:	Language materials, printed : monographic
Paralel Title:	Efficient Mining of Indirect Associations from Static Data and Streaming Data
Author:	陳憶清,
Secondary Intellectual Responsibility:	國立高雄大學
Place of Publication:	[高雄市]
Published:	撰者;
Year of Publication:	民99[2010]
Description:	74面圖，表 : 30公分;
Subject:	串流資料探勘
Subject:	Data stream mining
Online resource:	http://handle.ncl.edu.tw/11296/ndltd/70528030718627659600
Summary:	間接關聯是一種新型態的非高頻率樣式，用來提供一種對於非高頻率樣式的新解釋，並且可以有效的減少哪些我們不感興趣的非高頻率樣式。間接關聯的概念是間接地連結兩個很少一起出現的項目，而這個連結是透過一個叫”中間項” (mediator)的項目來連結。如果適當地運用它，可以幫助我們從資料庫中識別真正有趣的非高頻率項目對(infrequent itempairs)。目前所有的研究都僅限於在靜態資料的環境中探勘間接關聯，還沒有研究是針對在串流資料的環境裡探勘間接關聯。在這篇論文中，我們提出三個有效的方法演算法來探勘間接關聯，包括針對靜態資料的EMIA演算法，以及針對串流資料的MIA-LM及EMIA-LM演算法。我們提出的MIA-LM及EMIA-LM演算方法不僅有效率而且還保證在串流環境中高頻項目的錯誤率不會超過使用者設定的錯誤率。經過使用合成及真實的資料集進行實驗分析，其結果都顯示我們提出的演算法是有效且效率極佳的方法。 Indirect association is a new type of infrequent pattern, which provides a new way for interpreting the value of infrequent patterns and can effectively reduce the number of uninteresting infrequent patterns. The concept of indirect association is to “indirectly” connect two rarely co-occurred items via a frequent itemset called mediator, and if appropriately utilized it can help to identify real interesting “infrequent itempairs” from databases. All of the literature on indirect association mining, to our best knowledge, is confined to the traditional, relatively static database environment; no research work has been conducted on mining indirect associations over data streams. In this thesis, we propose three very efficient approaches, one, namely EMIA (Efficient Mining of Indirect Association), for mining indirect associations on static data, and two, namely MIA-LM and EMIA-LM, for streaming data. We also show that the proposed MIA-LM and EMIA-LM algorithms can not only discover indirect associations over data streams efficiently, but also guarantee the error of derived itemsets not exceeding a user-specified threshold. Experiments on real world streaming datasets are also made to show the effectiveness of the proposed approaches.

在靜態與串流資料中的高效率間接關聯探勘 = Efficient Mining of Indirect Associations from Static Data and Streaming Data
陳, 憶清

在靜態與串流資料中的高效率間接關聯探勘 = Efficient Mining of Indirect Associations from Static Data and Streaming Data / 陳憶清撰 - [高雄市] : 撰者, 民99[2010]. - 74面 ; 圖，表 ; 30公分.
參考書目：面.
串流資料探勘Data stream mining

在靜態與串流資料中的高效率間接關聯探勘 = Efficient Mining of Indirect Associations from Static Data and Streaming Data
LDR:03501nam0a2200277 450 001 272978
005 20170214092703.0
009 272978
010 0 $b 精裝
010 0 $b 平裝
100 $a 20170214y2010 k y0chiy05 b
101 1 $a eng $d chi $d eng
102 $a tw
105 $a ak am 000yy
200 1 $a 在靜態與串流資料中的高效率間接關聯探勘 $d Efficient Mining of Indirect Associations from Static Data and Streaming Data $f 陳憶清撰
210 $a [高雄市] $c 撰者 $d 民99[2010]
215 0 $a 74面 $c 圖，表 $d 30公分
314 $a 指導教授：林文揚博士
320 $a 參考書目：面
328 $a 碩士論文--國立高雄大學資訊工程學系碩士班
330 $a 間接關聯是一種新型態的非高頻率樣式，用來提供一種對於非高頻率樣式的新解釋，並且可以有效的減少哪些我們不感興趣的非高頻率樣式。間接關聯的概念是間接地連結兩個很少一起出現的項目，而這個連結是透過一個叫”中間項” (mediator)的項目來連結。如果適當地運用它，可以幫助我們從資料庫中識別真正有趣的非高頻率項目對(infrequent itempairs)。目前所有的研究都僅限於在靜態資料的環境中探勘間接關聯，還沒有研究是針對在串流資料的環境裡探勘間接關聯。在這篇論文中，我們提出三個有效的方法演算法來探勘間接關聯，包括針對靜態資料的EMIA演算法，以及針對串流資料的MIA-LM及EMIA-LM演算法。我們提出的MIA-LM及EMIA-LM演算方法不僅有效率而且還保證在串流環境中高頻項目的錯誤率不會超過使用者設定的錯誤率。經過使用合成及真實的資料集進行實驗分析，其結果都顯示我們提出的演算法是有效且效率極佳的方法。 Indirect association is a new type of infrequent pattern, which provides a new way for interpreting the value of infrequent patterns and can effectively reduce the number of uninteresting infrequent patterns. The concept of indirect association is to “indirectly” connect two rarely co-occurred items via a frequent itemset called mediator, and if appropriately utilized it can help to identify real interesting “infrequent itempairs” from databases. All of the literature on indirect association mining, to our best knowledge, is confined to the traditional, relatively static database environment; no research work has been conducted on mining indirect associations over data streams. In this thesis, we propose three very efficient approaches, one, namely EMIA (Efficient Mining of Indirect Association), for mining indirect associations on static data, and two, namely MIA-LM and EMIA-LM, for streaming data. We also show that the proposed MIA-LM and EMIA-LM algorithms can not only discover indirect associations over data streams efficiently, but also guarantee the error of derived itemsets not exceeding a user-specified threshold. Experiments on real world streaming datasets are also made to show the effectiveness of the proposed approaches.
510 1 $a Efficient Mining of Indirect Associations from Static Data and Streaming Data
610 0 $a 串流資料探勘 $a 間接關聯 $a 標的物窗模式
610 1 $a Data stream mining $a indirect association $a indirect itempair $a landmark window model.
681 $a 008M/0019 $b 464103 7593 $v 2007年版
700 1 $a 陳 $b 憶清 $4 撰 $3 483126
712 0 2 $a 國立高雄大學 $b 資訊工程學系碩士班 $3 353878
801 0 $a tw $b 國立高雄大學 $c 20101224 $g CCR
856 7 $z 電子資源 $2 http $u http://handle.ncl.edu.tw/11296/ndltd/70528030718627659600