博碩士論文 etd-0720113-140400 詳細資訊


[回到前頁查詢結果 | 重新搜尋]

姓名 魏嘉慶(Chia-Ching Wei) 電子郵件信箱 E-mail 資料不公開
畢業系所 電機工程學系研究所(Electrical Engineering)
畢業學位 碩士(Master) 畢業時期 101學年第2學期
論文名稱(中) 以kNN為基礎之模糊類神經系統應用於時間序列預測
論文名稱(英) A kNN based neuro-fuzzy system for time series prediction
檔案
  • etd-0720113-140400.pdf
  • 本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。
    請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
    論文使用權限

    紙本論文:5 年後公開 (2018-08-20 公開)

    電子論文:使用者自訂權限:校內 5 年後、校外 5 年後公開

    論文語文/頁數 中文/62
    統計 本論文已被瀏覽 5632 次,被下載 367 次
    摘要(中) 時間序列預測已經被廣泛的應用於許多領域,逐漸受到重視。近來許多人工智慧技術已成功地應用於預測技術。相較於傳統統計方法,人工智慧技術更適合應用在真實資料,預測效能也優於統計方法。因此,我們提出一個結合kNN、基因演算法與模糊類神經網路的時間序列預測系統。該系統不只可應用於單步預測,更可拓展到多步預測。
    傳統的模型建立方式是以一個完整的訓練資料集產生一個預測模型,並以此模型進行預測。有別於傳統的模型建立方式,我們使用kNN從訓練資料集中挑選出與輸入資料相似的資料作為訓練資料集,因此針對每筆輸入資料皆產生不同的預測模型。藉由kNN可有效縮短訓練時間、降低預測誤差。
    時間序列預測是藉由過去的歷史資訊建立輸入與輸出的關係產生預測結果,大多數的時間序列預測方法僅選取鄰近時間點的資料作為輸入,但不同的資料具有不同的週期,並非所有的資料皆適用這種方式,因此我們選擇以基因演算法來挑選適當的歷史資訊,最佳化單步預測的效能。系統模型採用回授式的模糊類神經網路,將預測步進由單步延伸到多步預測。我們提出一個新的回授式架構的模型訓練方式,此方法可以同時最小化每筆預測預測誤差,降低誤差擴散的情形。
    最後我們以幾個常用的效能評估資料來比較我們的方法與其他方法的預測能力,由實驗可得知我們的方法可以提供更準確地預測。
    摘要(英) Time series prediction have been used in many fields. Forecasting the future behavior of a real-world time series data is an important research and application area.
    Recently, many soft computing methods have been proposed for time series forecasting. In this paper, a kNN based neuro-fuzzy multi steps ahead predictor is developed for time series prediction.
    In general, we use all historical data to create a global model. Instead of using all training data to training a model, we utilize the kNN method to dynamically select k most similar data as the training set to create a local model at each prediction. In this way, the training set each time is more relevant to the prediction to be done than the global model approach.
    Many method use nearby historical data as input. We use genetic algorithm to choose optimal input for neuro-fuzzy system and optima one step ahead prediction.
    We use a recurrent neuro-fuzzy system to generate prediction results, training a one step ahead prediction model, and iterates it by taking the predicted values as a part of the input. In this paper, we propose a new training method to minimum prediction error for each prediction.
    Experimental results have shown that our approach can provide more accurate predictions than other methods.
    關鍵字(中)
  • 模糊類神經網路
  • 局部模型
  • 多步預測
  • 時間序列
  • 基因演算法
  • 關鍵字(英)
  • neuro-fuzzy system
  • local model
  • multi-step ahead prediction
  • time series
  • genetic algorithm
  • 論文目次 致謝 i
    摘要 ii
    Abstract iii
    圖目錄 vii
    表目錄 viii
    第一章 導論 1
    1.1. 研究背景與目的 1
    1.2. 論文架構 2
    第二章 文獻探討 3
    2.1. 時間序列 3
    2.2. 單步預測 3
    2.2.1. ARMA 3
    2.2.2. 類神經網路 4
    2.2.3. SVM 5
    2.2.4. 多元迴歸分析 7
    2.3. 多步預測 8
    2.3.1. 直接預測 8
    2.3.2. 遞迴式預測 8
    第三章 研究方法 10
    3.1. 系統架構 10
    3.2. 基因演算法 12
    3.2.1. 編碼與族群初始化 14
    3.2.2. 選擇 15
    3.2.3. 突變 16
    3.2.4. 交配 16
    3.3. 局部模型 17
    3.4. 單步預測 19
    3.4.1. 模糊類神經網路架構 19
    3.4.2. 混合式學習演算法 22
    3.5. 多步預測 25
    第四章 實驗結果與分析 29
    4.1. 單步預測 29
    4.1.1. 台灣加權指數預測 29
    4.1.2. 波蘭電力負載預測 34
    4.2. 多步預測 36
    4.2.1. 雷射強度預測 36
    4.2.2. ENUITE電力負載預測 38
    4.3. 討論 40
    第五章 結論與未來展望 45
    5.1. 結論 45
    5.2. 未來研究方向 45
    參考文獻 46
    參考文獻 [1] S. F. Crone, "Artificial neural network & computational intelligence forecasting competition," ed: http://www.neural-forecasting-competition.com/, 2010.
    [2] M. N. Maralloo, A. R. Koushki, C. Lucas, and A. Kalhor, "Long term electrical load forecasting via a neurofuzzy model," ed, 2009, pp. 35-40.
    [3] V. H. Ferreira and A. P. A. da Silva, "Toward Estimating Autonomous Neural Network-Based Electric Load Forecasters," IEEE TRANSACTIONS ON POWER SYSTEMS, vol. 22, pp. 1554-1562, November 2007.
    [4] G. E. P. Box and G. M. Jenkins, Time Series Analysis: Forecasting And Control: WILEY, 2008.
    [5] R. F. Engle, "Autoregressive conditional heteroscedasticity with estimates of the variance of united kingdom inflation," Econometrica, vol. 50, pp. 987-1008, July 1982.
    [6] T. Bollerslev, "Generalized autoregressive conditional heteroscedasticity," Journal of Econometrics, vol. 31, pp. 307-327, April 1986.
    [7] Y. Yoon, J. G. Swales, and T. M. Margavio, "A Comparison of Discriminant Analysis versus Artificial Neural Networks," The Journal of the Operational Research Society, vol. 44, pp. 51-60, January 1993.
    [8] E. W. Saad, D. V. Prokhorov, I. Donald, and C. Wunsch, "Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks," IEEE Transactions on Neural Networks, vol. 9, pp. 1456-1470, November 1998.
    [9] J. C. Principe, N. R. Euliano, and W. C. Lefebvre, Neural and Adaptive Systems: Fundamentals through Simulations. New York, USA: John Wiley & Sons, 1999.
    [10] K.-J. Kim and I. Han, "Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index," Expert Systems with Applications, vol. 19, pp. 125-132, August 2000.
    [11] M. Ghiassi and H. Saidane, "A dynamic architecture for artificial neural networks," Neurocomputing, vol. 63, pp. 397-413, January 2005.
    [12] K. Huarng and T. H.-K. Yu, "The application of neural networks to forecast fuzzy time series," Physica A: Statistical Mechanics and its Applications, vol. 363, pp. 481-491, May 2006.
    [13] Y.-K. Kwon and B.-R. Moon, "A hybrid neurogenetic approach for stock forecasting," IEEE Transactions on Neural Networks, vol. 18, pp. 851-864, May 2007.
    [14] H.-J. Kim and K.-S. Shin, "A hybrid approach based on neural networks and genetic algorithms for detecting temporal patterns in stock markets," Applied Soft Computing, vol. 7, pp. 569-576, March 2007.
    [15] T.-J. Hsieh, H.-F. Hsiao, and W.-C. Yeh, "Forecasting stock markets using wavelet transforms and recurrent neural networks: an integrated system based on artificial bee colony algorithm," Applied Soft Computing, vol. 11, pp. 2510-2525, March 2011.
    [16] M. Khashei and M. Bijari, "A novel hybridization of artificial neural networks and Arima models for time series forecasting," Applied Soft Computing, vol. 11, pp. 2664-2675, March 2011.
    [17] F.-J. Chang, Y.-M. Chiang, and L.-C. Chang, "Multi-step-ahead neural networks for flood forecasting," Hydrological Sciences Journal, vol. 52, pp. 114-130, January 2007.
    [18] A. Sorjamaa, J. Hao, N. Reyhani, Y. Ji, and A. Lendasse, "Methodology for long-term prediction of time series," NEUROCOMPUTING, vol. 70, pp. 2861-2869, October 2007.
    [19] T. V. Gestel, J. A. K. Suykens, D. E. Baestaens, A. Lambrechts, G. Lanckriet, B. Vandaele, et al., "Financial time series prediction using least squares support vector machines within the evidence framework," IEEE Transactions on Neural Networks, vol. 12, pp. 809-821, July 2001.
    [20] L. J. Cao and F. E. H. Tay, "Support vector machine with adaptive parameters in financial time series forecasting," IEEE Transactions on Neural Networks, vol. 14, pp. 1506-1518, November 2003.
    [21] G. Valeriy and B. Supriya, "Support vector machine as an efficient framework for stock market volatility forecasting," Computational Management Science, vol. 3, pp. 147-160, April 2006.
    [22] C.-Y. Yeh, C.-W. Huang, and S.-J. Lee, "A multiple-kernel support vector regression approach for stock market price forecasting," Expert Systems with Applications, vol. 38, pp. 2177-2186, March 2011.
    [23] Q. Song and B. S. Chissom, "Fuzzy time series and its model," Fuzzy Sets and Systems, vol. 54, pp. 269-277, March 1993.
    [24] Q. Song and B. S. Chissom, "Forecasting enrollments with fuzzy time series Part I," Fuzzy Sets and Systems, vol. 54, pp. 1-9, February 1993.
    [25] Q. Song and B. S. Chissom, "Forecasting enrollments with fuzzy time series Part II," Fuzzy Sets and Systems, vol. 62, pp. 1-7, February 1994.
    [26] C.-F. Liu, C.-Y. Yeh, and S.-J. Lee, "Application of type-2 neuro-fuzzy modeling in stock price prediction," Applied Soft Computing, vol. 12, pp. 1348-1358, April 2012.
    [27] K.-H. Huarng, T. H.-K. Yu, and Y. W. Hsu, "A multivariate heuristic model for fuzzy time-series forecasting," IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, vol. 37, pp. 836-846, August 2007.
    [28] National Association of Securities Dealers Automated Quotations. Available: http://www.nasdaq.com/
    [29] Dow Jones Indexes. Available: http://www.djindexes.com/
    [30] Central Bank of the Republic of China. Available: http://www.cbc.gov.tw/
    [31] Taiwan Futures Exchange Corporation. Available: http://www.taifex.com.tw/.
    [32] T. H.-K. Yu and K.-H. Huarng, "Weighted fuzzy time-series models for TAIEX forecasting," Expert Systems with Applications, vol. 34, pp. 2945-2952, 2008.
    [33] S.-M. Chen and C.-D. Chen, "TAIEX forecasting based on fuzzy time series and fuzzy variation groups," IEEE Transactions on Fuzzy Systems, vol. 19, pp. 1-12, February 2011.
    [34] S.-M. Chen, H.-P. Chu, and T.-W. Sheu, "TAIEX Forecasting Using Fuzzy Time Series and Automatically Generated Weights of Multiple Factors," IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS¡XPART A: SYSTEMS AND HUMANS, vol. 42, pp. 1485-1495, November 2012.
    [35] R. J. Kuo, C. H. Chen, and Y. C. Hwang, "An intelligent stock trading decision support system through integration of genetic algorithm based fuzzy neural network and artificial neural network," Fuzzy Sets and Systems, vol. 118, pp. 21-45, February 2001.
    [36] M. T. Hagan, H. B. Dcmuth, and M. Beale, Neural Network Design: Vikas Publishing House, 2003.
    [37] C. Cortes and V. Vapnik, "Support-Vector Networks," Machine Learning, vol. 20, pp. 273-297, September 1995.
    [38] J. H. Holland, Adaptation in natural and artificial systems: MIT Press, 1992.
    [39] A. H. Wright, "Genetic Algorithms for Real Parameter Optimization," in Foundations of Genetic Algorithms, ed: Morgan Kaufmann, 1991, pp. 205-218.
    [40] Z. Michalewicz, Genetic Algorithms + Data Structures = Evolution Programs. New York: Springer-Verlag.
    [41] Z. Huang and M.-L. Shyu, "k-NN based LS-SVM framework for long-term time series prediction," ed, 2010.
    [42] S.-J. Lee and C.-S. Ouyang, "A neuro-fuzzy system modeling with self-constructing rule generationand hybrid SVD-based learning," IEEE TRANSACTIONS ON FUZZY SYSTEMS, vol. 11, pp. 341-353, June 2003.
    [43] C.-S. Ouyang, W.-J. Lee, and S.-J. Lee, "A TSK-Type Neurofuzzy Network Approach to System Modeling Problems," IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS¡XPART B: CYBERNETICS, vol. 35, pp. 751-767, August 2005.
    [44] T. H.-K. Yu and K.-H. Huarng, "A bivariate fuzzy time series model to forecast the taiex," Expert Systems with Applications, vol. 34, pp. 2945-2952, May 2008.
    [45] Poland Electricity Load data website. Available: http://research.ics.aalto.fi/eiml/
    [46] V. H. Ferreira and A. P. A. d. Silva, "ANFIS: Adaptive-Networkbased Fuzzy Inference Systems," IEEE Transactions on Systems, Man, and Cybernetics, vol. 23, pp. 665-685, 1993.
    [47] Santa Fe Laser time series. Available: http://www-psych.stanford.edu/~andreas/Time-Series/SantaFe.html
    [48] Electricity Load Forecasting Using Intelligent and Adaptive technologies. Available: http://neuron-ai.tuke.sk/competition/
    [49] B.-J. Chen, M.-W. Chang, and C.-J. Lin, "Load forecasting using support vector machines: A study on EUNITE competition 2001," IEEE Transactions on Power System, vol. 19, pp. 1821-1830, November 2004.
    口試委員
  • 蔡賢亮 - 召集委員
  • 侯俊良 - 委員
  • 劉志峰 - 委員
  • 林永申 - 委員
  • 李錫智 - 指導教授
  • 口試日期 2013-07-25 繳交日期 2013-08-20

    [回到前頁查詢結果 | 重新搜尋]


    如有任何問題請與論文審查小組聯繫