進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-2107201617104900
論文名稱(中文) 資料流之模糊時間序列預測模式
論文名稱(英文) A Stream Fuzzy Time Series Forecasting Model
校院名稱 成功大學
系所名稱(中) 資訊管理研究所
系所名稱(英) Institute of Information Management
學年度 104
學期 2
出版年 105
研究生(中文) 蔡如欣
研究生(英文) Ju-Hsin Tsai
電子信箱 martian17218@hotmail.com
學號 R76034103
學位類別 碩士
語文別 英文
論文頁數 65頁
口試委員 指導教授-李昇暾
口試委員-林清河
口試委員-耿伯文
口試委員-郭淑靜
中文關鍵字 模糊時間序列預測  資料流時間序列  模糊推論 
英文關鍵字 fuzzy time series forecasting  streaming time series  fuzzy inference 
學科別分類
中文摘要 時間序列分類至今已發展約十年,並且在資料探勘領域有相當多的研究方法能夠明顯提升其分類準確度。而近年來資訊科技的演進,使得資料的儲存型態有所改變,大量的資料持續被蒐集、儲存,資料分析者無法一次性地將所有數據儲存於單一記憶體中,而是改採序列的形式將資料點依循時間單位輸入,此種資料處理方式稱為資料流(streaming data)。如今資料流被應用的領域甚廣,例如財務應用、網路監控、資訊安全、通訊管理與製造流程等皆為資料流經常被使用之範圍,其優勢為面臨未知時間長度的大量資料時,仍能有效處理數據並進行分析。
然而資料流輸入快速、大量、時變性(time-varying)與不可預測等特性也造成新的資料處理問題衍生:傳統的資料庫管理系統並無法有效針對上述的資料流特性進行處理(Babcock, Babu, Datar, Motwani, & Widom, 2002)。故為了解決有別於傳統模式的數據分析,我們使用線上學習(on-line learning)對資料進行即時性的處理,包含以動態調整機制進行模糊規則的更新、新增與刪除,使預測模型能更適用於資料流特性的模糊時間序列。
本研究將聚焦於過去較少學者深入探究的領域──將資料流架構加入模糊時間序列。我們以遞迴式密度更新方法持續更新訓練規則庫,同時新增規則或修改規則;進行動態調整之目的在於使訓練規則庫使用率提升、刪去不需要的規則,並且有效改善模糊時間序列預測模式的準確度。其次本研究參考Millán-Giraldo, Sánchez, and Traver (2011)學者提出的預測策略,針對資料傳輸過程中,因人為因素使資料產生部分遺漏之情境提出修正預測模式的方法,以兩種資料輸入策略進行預測,以克服資料流傳輸可能發生的資料延遲情況。
英文摘要 Time series classification has been studied for over a decade and is now widely used in the sphere of data mining to increase the forecasting accuracy. In recent years, the evolution of information technology has caused a change in the data-storage approach. As volume data is collected and stored continuously and rapidly, a data analyzer is not able to efficiently retrieve the information from it over time. Thus a new data-processing approach called ‘streaming’ was proposed, which entails inputting data elements as sequences. The advantage of streaming data is that data points can still be used to forecast future values while the total length is unknown.
Streaming data is diverse, continuous, rapid and time-varying, thus it is not compatible with the conventionally stored data model. To construct a novel approach that differs from a traditional forecasting model, we used on-line learning to process data instantly. We used a dynamic-adjusting mechanism to detect when to add a rule, update a rule or delete a rule. With these steps, we can make our fuzzy time-series forecasting model conform with streaming data well.
In this research, we focused on the combination of streaming data and fuzzy time series. The recursive density updating algorithm is used in our model to decide the rule-updated or rule-added timing. The purpose of using a dynamic-adjusting mechanism is to raise the rule-usage ratio, and to remove redundant rules. In addition, it is also our goal to improve the forecasting accuracy of our model. In doing so, we refer to the on-line learning strategies of Millán-Giraldo, Sánchez, and Traver (2011), who proposed classifying the incoming data with missing attributes. We used two strategies to simulate how to forecast value when parts of the data are delayed.
論文目次 摘要 I
Abstract II
誌謝 III
CONTENTS IV
List of Tables VI
List of Figures VIII
Chapter I Introduction 1
1.1 Background and Motivation 1
1.2 Research Objectives and Contribution 4
1.3 Structure of Research 5
Chapter II Literature Review 7
2.1 Fuzzy Theory and Fuzzy Time Series 7
2.1.1 Fuzzy Set Theory 7
2.1.2 Fuzzy Time Series 8
2.2 Forecasting Model of Fuzzy Time Series 9
2.2.1 Define Universe of Discourse (U) 10
2.2.2 Partition the Universe of Discourse 11
2.2.3 Define Fuzzy Set and Linguistic Values 13
2.2.4 Fuzzify Historical Data 14
2.2.5 Establish Fuzzy Relations 15
2.2.6 Forecast and Defuzzification 16
2.3 Stream Time Series 18
2.3.1 Stream Data Definitions 18
2.3.2 Stream Data Classification Strategies 20
2.4 Fuzzy Rules Simplification 21
Chapter III Methodology 23
3.1 High-Order Fuzzy Time Series Establishment 24
3.2 Streaming Fuzzy Time Series (SFTS) Forecast Model 27
Chapter IV Experiment and Evaluation 33
4.1 Research Premise 33
4.1.1 Datasets 33
4.1.2 Evaluation Indicators 34
4.2 The Experiment Procedure 35
4.3 Evaluation and Comparison 40
4.3.1 Monthly Taipei Temperature Dataset 40
4.3.2 Texas Air Quality Index Dataset 44
4.3.3 Residential Property Prices for Japan Dataset 47
4.3.4 Real Gross Domestic Product for US Dataset 50
4.3.5 USD/EUR Exchange Rate Dataset 53
4.3.6 NASDAQ Index Dataset 56
Chapter V Conclusion and Future Work 59
5.1 Conclusion 59
5.2 Future Work 61
Reference 63
參考文獻 Babcock, B., Babu, S., Datar, M., Motwani, R., & Widom, J. (2002). Models and issues in data stream systems. In Proceedings of the twenty-first ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems (pp. 1-16). ACM.
Babuška, R., Setnes, M., Kaymak, U., & van Nauta Lemke, H. R. (1996). Rule base simplification with similarity measures. In Fuzzy Systems, 1996., Proceedings of the Fifth IEEE International Conference on (Vol.3, pp. 1642-1647). IEEE.
Chen, S.-M. (1996). Forecasting enrollments based on fuzzy time series. Fuzzy sets and systems, 81(3), 311-319.
Chen, S.-M., & Chen, C.-D. (2011). Handling forecasting problems based on high-order fuzzy logical relationships. Expert Systems with Applications, 38(4), 3857-3864.
Ha, N. V., Ishikawa, T., & Abe, A. (2000). An inference mechanism under incomplete knowledge based on rule similarity considering viewpoint. In Knowledge-Based Intelligent Engineering Systems and Allied Technologies, 2000. Proceedings. Fourth International Conference on (Vol.2, pp. 750-755). IEEE.
Huarng, K. (2001). Effective lengths of intervals to improve forecasting in fuzzy time series. Fuzzy sets and systems, 123(3), 387-394.
Huarng, K., & Yu, T. H.-K. (2006). Ratio-based lengths of intervals to improve fuzzy time series forecasting. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 36(2), 328-340.
Hwang, J.-R., Chen, S.-M., & Lee, C.-H. (1998). Handling forecasting problems using fuzzy time series. Fuzzy sets and systems, 100(1), 217-228.
Kaymak, U., & Babuška, R. (1995). Compatible cluster merging for fuzzy modelling. In Fuzzy Systems, 1995. International Joint Conference of the Fourth IEEE International Conference on Fuzzy Systems and The Second International Fuzzy Engineering Symposium., Proceedings of 1995 IEEE Int (Vol.2, pp. 897-904). IEEE.
Li, S.-T., & Cheng, Y.-C. (2007). Deterministic fuzzy time series model for forecasting enrollments. Computers & Mathematics with Applications, 53(12), 1904-1920.
Liu, H.-T., Wei, N.-C., & Yang, C.-G. (2009). Improved time-variant fuzzy time series forecast. Fuzzy Optimization and Decision Making, 8(1), 45-65.
Millán-Giraldo, M., Sánchez, J. S., & Traver, V. J. (2009). Exploring early classification strategies of streaming data with delayed attributes. In Neural Information Processing (pp. 875-883). Springer.
Millán-Giraldo, M., Sánchez, J. S., & Traver, V. J. (2011). On-line learning from streaming data with delayed attributes: a comparison of classifiers and strategies. Neural Computing and Applications, 20(7), 935-944.
Moshtaghi, M., Bezdek, J. C., Leckie, C., Karunasekera, S., & Palaniswami, M. (2015). Evolving fuzzy rules for anomaly detection in data streams. Fuzzy Systems, IEEE Transactions on, 23(3), 688-700.
Setnes, M., Babuška, R., Kaymak, U., & van Nauta Lemke, H. R. (1998). Similarity measures in fuzzy rule base simplification. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 28(3), 376-386.
Song, Q., & Chissom, B. S. (1993). Forecasting enrollments with fuzzy time series—part I. Fuzzy sets and systems, 54(1), 1-9.
Vo, V., Luo, J., & Vo, B. (2013). Stream Time Series Approach for Supporting Business Intelligence. International Journal of Database Theory and Application, 6(2), 1-18.
Wong, W.-K., Bai, E., & Chu, A. W.-C. (2010). Adaptive time-variant models for fuzzy-time-series forecasting. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 40(6), 1531-1542.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2021-12-31起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw