未來發展

本研究的未來發展，主要可以分成四點。

第一點，資料的前處理，一直是資料挖掘中的重要課題。良好的資料前處理可以使 得資料挖掘所分析的結果更有可信度。而本研究的資料前處理，將資料分為漲平跌三 類，可以再被改良，已提高分群的有效性與預測的正確性。

第二點，動態時間扭曲法的再改良，使得改良後距離度量更接近傳統的動態時間扭 曲法，並且加速運算速度，仍是本研究未來持續發展的方向。Trie 結構概念的再延伸，

如把兩個比對相同的序列當成一個點，以更大的尺度來看待trie 結構，則是本研究未來 的另一個重要方向。而同時，從輸入資料的面向、演算法執行的面向、硬體改良的面向，

這三個面向去研究如何改良動態時間扭曲法。

第三點，分群法是掌握行為的方法之一，尋找更加有效的分群法，並確實掌握『有 意義』的圖形(Patterns)，進一步的提升預測的正確率，是未來發展的另一個方向。

第四點，雖然本研究方法應用於分群預測上，執行時間較於動態時間扭曲法並未大 幅度的減低，但是應用於相似度搜尋時，卻可以降低大部分的搜尋時間。因此，應用本 研究方法於相似度搜尋，再由相似度搜尋延伸至預測的應用上，是本研究積極延展的一 個方向。

參考文獻

[1] Henry Gleitman著，心理學，洪蘭譯，遠流出版社，台北，1991，民國 86 年。

[2] Wong, P.H.W., et al., “Reducing Computational Complexity of Dynamic Time Warping-based Isolated Word Recognition with Time Scale Modification”, Signal Processing Proceedings, Pages:722 - 725 vol.1, 1998.

[3] 蔡文智，『以隱藏式馬可夫模型應用於股市單日交易預測上』，國立交通大學，碩士 論文，民國91 年。

[4] 劉科成，『使用動態規劃搜尋股市線形之探討與實作』，暨南國際大學，碩士論文，

民國89 年。

[5] J. T. Tou, “Feature Extraction in Pattern Recognition”, Journal of pattern recognition, Vol1, pp3-11, 1968.

[6] C. W. Therrien, Decision estimation and Classification : an Introduction to Pattern Recognition and Related Topics, John Wiley & Sons, New York,1989.

[7] 李上銘，『語音辨認中基於主成份分析之進一步技術』，國立台灣大學，碩士論文，

民國90 年。

[8] 丁鎮權，『指紋辨識系統設計』，淡江大學，碩士論文，民國 92 年。

[9] Jiawei Han, Micheline Kamber, Data Mining: Concept and Techniques, Morgan Kaufmann), p418-427,2002.

[10] C. Chartfield. The Analysis of Time Series: An Introduction, 3rd ed. New York, Chapman and Hall, 1984.

[11] R. H. Shumway, Applied Statistical Time Series Analysis. Eaglewood Cliffs, NJ:

Prentice Hall, 1988.

[12] R. Agrawal, et al., ”Efficient Similarity Search in Sequence Databases”. In Proc. 4th Int.

Conf. Foundation of data organization and algorithms, Chicago, II, Oct. 1993.

[13] R. Agrawal, et al., “Fast Similarity Search in the Presence of Noise, Scaling, and Translation in Time Series Databases”, In Proc. 1995 Int. Conf. Very Large Data Bases(VLDB’95), page 490-501, Zurich, Switzerland, Sept. 1995.

[14] R. Agrawal, et al.,.”Query Shapes of Histories”. In Proc. 1995 Int. Conf. Very Large Data Bases(VLDB’95), page 502-514, Zurich, Switzerland, Sept. 1995.

[15] S. Park et al., “Efficient Searches for Similar Subsequences of Different Lengths in Sequence Databases”, In Proc. 2000 Int. Conf. Data Engineering(ICDE’00), pages 23-32, San Diego, CA, Feb. 2000.

[16] C.-S. Perng, et al., “Landmarks: A New Model for Similarity-based Pattern Querying in Time Series databases”, In Proc. 2000 Int. Conf. Data Engineering(ICDE’00), pages 33-42, San Diego, CA, Feb. 2000.

[17] R. Agrawal, and R. Srikant, “Mining Sequential Patterns”. In Proc. 1995 Int. Conf. Data Engineering (ICDE’95), pages 3-14, Taipei, Taiwan, Mar. 1995.

[18] C. Faloutsos, et al., “Fast Subsequence Matching in Time Series Databases” In Proc.

1994 ACM-SIGMOD Conf. Management of data, pages 419-429, Minneapolis, MN, May 1994.

[19] M. J. Zaki, et al., “PLANMINE: Sequential Mining for Plan Failures”, In Proc. 1998 Int.

Conf. Knowledge discovery and data mining(KDD’98), pages 369-373, New York, Aug.1998.

[20] J. Han, et al., “Efficient Mining of Partial Periodic Patterns in Time-series Database”, In Proc. 1999 Int. Conf. Data Engineering(ICDE’99), pages 106-115, Sydney, Australia, Apr.

1999.

[21] Keogh, E. and Kasetty, S.,. “On the Need for Time-series Data Mining Benchmarks: A Survey and Empirical Demonstration” In the 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp 102-111 July 23 - 26, 2002.

[22] Robert Goodell Brown, Smoothing, Forecasting, and Prediction of Discrete Time Series, Prentice Hall, 1962

[23] Brain Everitt, Cluster Analysis 2rd, p17, Heinemann Educational Books, London,1980.

[24] Augustine H. Gray Jr., John D. Markei, “Distance Measures for Speech Recognition”, IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. Assp-24, No. 5, pages 380-391, Oct. 1976.

[25] Phillip Juffs, et al., “A Multiresolution Distance Measure for Images”, IEEE Signal Processing Letters, Vol. 5, No. 6, June, 1998

[26] Das G.,et al., “Rule Discovery from Time Series”, International Conference of Knowledge Discovery and Data Mining, pages 16-22, 1998.

[27] 劉致和，『臺灣地區燙傷住院治療型態之研究－－應用階層式集群分析於全民健保 資料庫』，台北醫學院，碩士論文，民國91 年。

[28] Berndt, D., Clifford, J., ”Using Dynamic Time Warping to Find patterns in Time Series”, AAAI-94 Workshop on Knowledge Discovery in Database, pages 229-248, 1994.

[29] Keogh, E., “Exact Indexing of Dynamic Time Warping”, In 28th International Conference on Very Large Data Bases, pages 406-417, 2002.

[30] Gregory, N. Stainhaouer, George Carayannis, “New Parrallel implementations for DTW algorithms”, IEEE Transactions on Acoustics, Speech, and Signal Processing, vol 38 april 4 pages 705-711, 1990.

[31] Kurt Maly, “Compressed Tries”, Communications of the ACM, Vol 19, No. 7, July,pages 409-415, 1976

[32] Chen A. P., et al., “Applying Trie-Structure to Improve Dynamic Time Warping on Time-Series Stock Data Analysis”, International Conference on Artificial Intelligence and

[33] Cormack, R. M., ”A review of Classification”,. Journal of the Royal Statistical Society, Series A, 134, No. 4, pages 321-367, 1971

[34] Johnson, S. C., “Hierarchical Clustering Schemes”, Psychometrika, 32, 241-254, 1967 [35] Tapas Kanungo, et al., “An Efficient k-Means Clustering Algorithm: Analysis and

Implementation”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.

24, No.7, July, 2002

[36] Carmichael, J. W., et al., “Finding Nature Clusters”, Syst. Zool., 17, pages144-150, 1968.

[37] Needham, R. M., “Automatic Classification in Linguistics”, The Statistician, 17, pages 45-54, 1967.

[38] Sawrey, W. L., et al., “An Objective Method of Grouping Profiles by Distance Function”, Educ. Psychol. Measur., 20, pages 651-674, 1960.

[39] Gower J. C. and Ross, G. J. S., “Minimum Spanning Trees and Single Linkage Cluster Analysis”, Applied Statistics, 18, pages 54-64, 1969.

[40] 吳勝修，『應用股票趨勢技術分析於動態投資組合保險中之操作策略』，國立交通大 學，碩士論文，民國92 年。

[41] 曾士育，『以自組織映射網路探勘金融投資決策之研究』，國立高雄第一科技大學，

碩士論文，民國92 年

[42] 王湘蕙，『時間數列資料分群方法—在探討台灣上市電子公司股票特性之應用』，國 立台北大學，碩士論文，民國91 年。

[43] S. Benninga and B., Czaczkes, Financial Modeling, Cambridge, MA:MIT Press, 1997 [44] 許育嘉，『結合小波分解和小波神經網路於非定性財務時間序列之預測』，國立交通

大學，碩士論文，民國91 年