English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文筆數/總筆數 : 117578/148609 (79%)
造訪人次 : 70935891      線上人數 : 10702
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    政大機構典藏 > 理學院 > 應用數學系 > 學位論文 >  Item 140.119/158367
    請使用永久網址來引用或連結此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/158367


    題名: 利用模糊邏輯加強LSTM的預測準確性
    Enhancing the predictive accuracy of LSTM using fuzzy logic
    作者: 吳宗翰
    Wu, Tsung-Han
    貢獻者: 曾正男
    吳宗翰
    Wu, Tsung-Han
    關鍵詞: LSTM預測
    模糊邏輯
    高斯模糊系統修正
    三角模糊系統修正
    股價預測
    Long Short-Term Memory
    Fuzzy Logic System
    Gaussian membership functions
    Triangular membership functions
    Stock price prediction
    日期: 2025
    上傳時間: 2025-08-04 13:10:16 (UTC+8)
    摘要: 本研究主旨在透過結合長短期記憶(Long Short-Term Memory, LSTM)模型與模糊邏輯系統(Fuzzy Logic System),提升股價預測之準確性與穩定性。以三種不同價位的股票台灣鴻海精密工業股份有限公司(股票代號:2317.TW);台灣積體電路製造股份有限公司(股票代號:2330.TW);陽明海運股份有限公司(股票代號:2609.TW)之歷史股價作為研究範例,建立雙層 LSTM 模型,並於預測誤差上導入高斯隸屬函數(Gaussian Membership Function)與三角形隸屬函數(Triangular Membership Function)所構成之模糊邏輯系統進行誤差修正。實驗結果顯示,融合模糊邏輯的 LSTM 模型在多次隨機預測中,其平均均方根誤差(Root Mean Square Error, RMSE)明顯低於單純使用 LSTM 的模型。該混合模型展現出更佳的預測穩定性,並提供更具彈性與可解釋性的預測結果。本研究顯示深度學習與模糊邏輯結合的潛力,未來可進一步應用於多種金融預測場景,以提升預測的準確度與模型透明度。
    This study aims to enhance the accuracy and stability of stock price prediction by integrating the Long Short-Term Memory (LSTM) model with a Fuzzy Logic System (FLS). Historical stock price data from three Taiwanese companies with varying price levels—Hon Hai Precision Industry Co., Ltd. (2317.TW), Taiwan Semiconductor Manufacturing Company Limited (2330.TW), and Yang Ming Marine Transport Corporation (2609.TW)—are used as case studies. A two-layer LSTM model is constructed, and a fuzzy logic correction mechanism based on Gaussian and triangular membership functions is applied to adjust the prediction errors. Experimental results show that the LSTM model integrated with fuzzy logic consistently achieves lower average Root Mean Square Error (RMSE) across multiple randomized prediction trials compared to the standalone LSTM model. The proposed hybrid model demonstrates superior forecasting stability and provides more flexible and interpretable results. This study highlights the potential of combining deep learning with fuzzy logic systems and suggests future applications in various financial forecasting scenarios to improve predictive accuracy and model transparency.
    參考文獻: • Chen, S.-M., & Lee, L.-C. (2010). Fuzzy time-series models for forecasting enrolments. Applied Soft Computing, 10(4), 1497–1504.
    • Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder–decoder for statistical machine translation. Proceedings of EMNLP 2014, 1724–1734.
    • Fischer, T., & Krauss, C. (2018). Deep learning with long short term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654–669.
    • Gers, F. A., & Schmidhuber, J. (2000). Recurrent nets that time and count. Proceedings of the IJCNN, 189–194.
    • Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2017). LSTM: A search space odyssey. IEEE Transactions on Neural Networks and Learning Systems, 28(10), 2222–2232.
    • Gulmez, A., Erdem, H., & Yilmaz, E. (2023). GA-attention-fuzzy-stock-net: Hybrid deep fuzzy system for intraday trading. Neurocomputing, 515, 310–324.
    • Hochreiter, S., & Schmidhuber, J. (1997). Long short‑term memory. Neural Computation, 9(8), 1735–1780.
    • Huang, P., Chen, T., & Kuo, Y. (2024). Gaussian versus triangular fuzzy post-compensation on deep neural stock predictors. Expert Systems with Applications (in press).
    • Klir, G. J., & Yuan, B. (1995). Fuzzy sets and fuzzy logic: Theory and applications. Prentice Hall.
    • Mamdani, E. H., & Assilian, S. (1975). An experiment in linguistic synthesis with a fuzzy logic controller. International Journal of Man‑Machine Studies, 7(1), 1–13.
    • Merity, S., Keskar, N. S., & Socher, R. (2018). Regularizing and optimizing LSTM language models. ICLR.
    • Porru, S., Pinna, A., & Marchesi, M. (2018). A fuzzy-rule-based portfolio selection system with dynamic risk adjustment. Expert Systems with Applications, 104, 113–123.
    • Ragab, A., Abdel-Aziz, M., & Ibrahim, H. (2024). Fuzzy BiLSTM with improved CPSO for cryptocurrency volatility forecasting. Applied Soft Computing, 146, 111226.
    • Ross, T. J. (2010). Fuzzy logic with engineering applications (3rd ed.). Wiley.
    • Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. Advances in NIPS, 27, 3104–3112.
    • Takagi, T., & Sugeno, M. (1985). Fuzzy identification of systems and its applications to modeling and control. IEEE Transactions on Systems, Man, and Cybernetics, 15(1), 116–132.
    • Wang, W., Liu, F., & Zhang, J. (2021). Fuzzy inference-based LSTM for long-term wind speed forecasting. Renewable Energy, 179, 1184–1198.
    • Zadeh, L. A. (1965). Fuzzy sets. Information and Control, 8(3), 338–353.
    • Zadeh, L. A. (1975). The concept of a linguistic variable and its application to approximate reasoning—I. Information Sciences, 8(3), 199–249.
    描述: 碩士
    國立政治大學
    應用數學系
    107751016
    資料來源: http://thesis.lib.nccu.edu.tw/record/#G0107751016
    資料類型: thesis
    顯示於類別:[應用數學系] 學位論文

    文件中的檔案:

    檔案 大小格式瀏覽次數
    index.html0KbHTML11檢視/開啟


    在政大典藏中所有的資料項目都受到原著作權保護.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,惟仍請適度,合理使用本網站之內容,以尊重著作權人之權益。商業上之利用,則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作,已盡力防止侵害著作權人之權益,如仍發現本網站之數位內容有侵害著作權人權益情事者,請權利人通知本網站維護人員(nccur@nccu.edu.tw),維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回饋