跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 林佳生
Chia-Sheng Lin
論文名稱： 利用多重門檻值挖掘序列規則
Mining Sequential Patterns with Multiple Minimum Supports
指導教授： 林熙禎
Shi-Jen Lin
口試委員:
學位類別： 碩士
Master
系所名稱： 管理學院 - 資訊管理學系
Department of Information Management
畢業學年度： 91
語文別： 英文
論文頁數： 47
中文關鍵詞： 資料挖礦 、序列規則 、多重門檻值
外文關鍵詞： PrefixSpan, Multiple Minimum Supports, Data Mining, Sequential Patterns
相關次數： 點閱：5  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 近年來序列規則越來越重要了，傳統挖掘序列規則的方法都是建構在相同的方式上，也就是利用單一門檻值來挖掘那些出現次數超過門檻值的序列規則。利用單一門檻值的方法意味著所有的項目有著相似的特性，或者說它們出現在資料庫中的頻率類似，真實世界中並不常發生這樣的情形。
    我們在這篇論文中首先延伸傳統單一門檻值來挖掘那些滿足不同門檻值的序列規則，接著設計了一個叫做MS-PrefixSpan的演算法。MS-PrefixSpan最主要的想法是以條件最小支持度當作門檻值來過濾投影資料庫中的項目，如果項目在投影資料庫中出現的次數超過門檻值，則將項目視為候選且長度為一的序列規則。條件最小支持度會依據每個投影資料庫逐漸調整以反映出每個最大序列規則實際的最小支持度。此外為了強調MS-PrefixSpan恰好可以找到所有的最大序列規則，我們提供了一個定理來說明MS-PrefixSpan的正確性。最後，我們的實驗結果顯示MS-PrefixSpan的確可以大量地減少時間和產生出的序列規則。

    Sequential mining is becoming more and more important recently. Traditional sequential pattern mining algorithms used the same model, i.e., finding all sequential patterns that satisfy one user-specified minimum support. However, using only one single minimum support implies that all items in the data are of the same nature and/or have similar frequencies in the database. This is not often the case in real-life applications.
    In this paper, first we extended traditional one minimum support for all sequential patterns with multiple item supports. Second, we developed an effective algorithm called MS-PrefixSpan. Its general idea is using a conditional minimum support as a threshold to qualify items in each projected database for candidate length-1 sequential patterns. According to each projected database the conditional minimum support is gradually adjusted to reflect the actual minimum support of each maximal sequential pattern. Besides, in order to claim that MS-PrefixSpan can find all and only all maximal sequential patterns satisfying their own MSSP, we also provide a theorem to prove the correctness of MS-PrefixSpan. Third, our experimental result shows that MS-PrefixSpan indeed can substantially reduce the execution time and the number of produced sequential patterns.

    Abstract III Table of Contents IV List of Illustrations V List of Tables VI 1. Introduction 1 2. Background 5 2.1 Mining sequential patterns 5 2.1.1 Problem statement 5 2.1.2 The concept of GSP 6 2.2 PrefixSpan 8 2.2.1 The concept of PrefixSpan 9 2.3 Mining association rules with multiple minimum supports 12 2.3.1 The extend model 13 2.3.2 The concept of MSapriori 14 3. Mining sequential pattern with multiple minimum supports 17 3.1 The extended model 17 3.2 Why don’t we base on Apriori-like algorithm? 19 3.3 MS-PrefixSpan 21 3.3.1 Definitions in MS-PrefixSpan 21 3.3.2 MS-PrefixSpan algorithm 22 3.3.3 Examples of MS-PrefixSpan 25 3.3.4 Correctness of MS-PrefixSpan 30 4. Experiment 34 4.1 Synthetic data generation & setting of MIS value of each items 34 4.2 Different betas with different minimum supports 36 4.3 BackCheck of MS-PrefixSpan 40 4.4 Scale up 41 5. Conclusion 45 Reference 46

    [1] Agarwall R.C., Aggarwal C. and V.V.V. Prasad. A tree projection algorithm for generation of frequent itemsets. In Journal of Parallel and Distributed Computing, 2000.
    [2] Agrawal R. and Srikant R., Fast algorithms for mining association rules. In Proc. 1994 Int. Conf. Very Large Data Bases (VLDB’94), pages 487-499, Santiago, Chile, Sept. 1994.
    [3] Agrawal R. and Srikant R., Mining sequential patterns. In Proc. 1995 Int. Conf. Data Engineering (ICDE’95), pages 3-14, Taipei, Taiwan, Mar. 1995.
    [4] Chen Y. L., Chiang M. C., Kao M. T., A New Approach for Discovering Time-Intervals in Sequential patterns. In Expert Systems with Applications, 2003.
    [5] Chen M. S., Han J., Yu P. S., Data Mining: An Overview from Database Perspective. In IEEE Trans. On Knowledge And Data Engineering, 1997.
    [6] Chen M.S., Park J.S. and Yu P.S., Efficient data mining for PathTraversal Patterns. In Proc. of IEEE Trans. Knowledge and DataEngineering (IEEE’98), Vol.10 No.2 pages 209-221, March 1998.
    [7] Guralnik V., Garg N. and Karypis G., Parallel Tree Projection Algorithm for Sequence Mining, 7th International European Conference on Parallel Processing (Euro-Par 2001), Pages 310-320, Manchester, UK, Aug. 2001.
    [8] Han J., Pei J., Mortazavi-Asl B., Chen Q., Dayal U. and Hsu M-C., FreeSpan: Frequent Pattern-Projected Sequential Pattern Mining. In Proc. 2000 Int. Conf. Knowledge Discovery and Data Mining (KDD’00), 355-359, Boston, MA, Aug. 2000.
    [9] Liu B. and Hsu W. and Ma Y., Mining Association Rules with Multiple Minimum Supports. ACM SIGKDD International Conderence on Knowledge Discovery & Data Mining (KDD-99). August 15-18, 1999, San Diego, CA, USA.
    [10] Mannila H., Toivonen H., and Inkeri A. Verkamo., Discovering Frequent Episodes in Sequences. In Proc. 1995 Int. Conf. on Knowledge Discovery and Data Mining (KDD''95), pages 210-215, Montreal, Canada, August 1995.
    [11] Pei J., Han J., Mortazavi-Asl B., Pinto H., Chen Q., Dayal U. and Hsu M-C., PrefixSpan: Mining Sequential Patterns Efficiently by Prefix-Projected Pattern Growth. In. Proc. 2001 Int. Conf. Data Engineering (ICDE’01), pages 215-224, Heidelberg, Germany, April 2001.
    [12] Pei J., Han J., Mortazavi-Asl B., and Zhu H., Mining Access Patterns Efficiently from Web Logs. In Proc. 2000 Pacific-Asia Conf. on Knowledge Discovery and Data Mining (PAKDD''00), Pages 396-407, Kyoto, Japan, April 2000.
    [13] Srikant R. and Agrawal R., Mining sequential patterns: Generalizations and performance improvements. In Proc. 5th Int. Conf. ExtendingDatabase Technology (EDBT’96), pages 3-17, Avignon, France, March 1996.
    [14] Yan X., Han J., Afshar R., CloSpan Mining Closed Sequential Patterns in Large Datasets. In Proc. 2003 SIAM Int.Conf. on Data Mining (SDM''03), San Fransisco, CA, May 2003
    [15] Zaki M. J., SPADE: An Efficient Algorithm for Mining Frequent Sequences. In Proc. of Machine Learning Journal, special issue on Unsupervised Learning (Doug Fisher, ed.), Vol. 42 Nos. 1/2, pages 31-60, Jan/Feb 2001.

    QR CODE
    :::