簡易檢索 / 詳目顯示

回結果列表
研究生： 林文凱
Lin, Wen-Kai
論文名稱： 應用時間序列統計學習於民生公共物聯網空氣品質之研究---以豐原地區為例
Application of Time Series Statistical Learning to Air Quality of Civil Internet of Things --- Taking Fengyuan Area as an Example
指導教授： 李坤洲
Lee, Kun-Chou
學位類別： 碩士
Master
系所名稱： 工學院 - 系統及船舶機電工程學系
Department of Systems and Naval Mechatronic Engineering
論文出版年： 2024
畢業學年度： 112
語文別： 中文
論文頁數： 78
中文關鍵詞： LSTM 、GRU 、ARIMAX 、Transformer 、DTW
外文關鍵詞： LSTM, GRU, ARIMAX, Transformer, DTW
相關次數： 點閱：62  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
    • 摘要 I Extended Abstract II 誌謝 V 目錄 VI 表目錄 VIII 圖目錄 IX 第一章 緒論 1 1.1 研究動機與目的 1 1.2 文獻回顧 2 1.3 研究架構 3 第二章 時間序列預測之模型理論及方法 7 2.1 循環神經網路(Recurrent Neural Network，RNN) 7 2.2 長短期記憶神經網路(Long Short-Term Memory，LSTM) 7 2.2.1 遺忘門(Forget Gate) 8 2.2.2 輸入門(Input Gate) 8 2.2.3 輸出門(Output Gate) 8 2.3 閘式循環神經網路(Gated Recurrent Unit，GRU) 9 2.3.1 更新門(Update gate) 9 2.3.2 重置門(Reset gate) 9 2.3.3 候選隱藏狀態(Candidate Hidden State) 9 2.3.4 最終隱藏狀態(Final Hidden State) 10 2.4 多變數整合移動平均自迴歸模型(Autoregressive Integrated Moving Average with Explanatory Variable Model，ARIMAX) 10 2.4.1 自迴歸模型(Autoregressive ，AR) 11 2.4.2 移動平均模型(Moving Average ，MA) 11 2.4.3 差分(Differencing) 11 2.4.4 外生變數(Exogenous Variables) 12 2.4.5 時間序列分析 12 2.4.6 ADF檢驗 13 2.4.7 赤池訊息量準則(Akaike information criterion，AIC) 13 2.5 基於Transformer的架構 13 2.5.1 Input Embedding 14 2.5.2 Positional Encoding 14 2.5.3 Multi-Head Attention 14 2.5.4 Feed Forward Neural Network 15 2.5.5 Addition and Normalization layer 15 第三章 公共物聯網空污數據之資料擷取與時序相關性處理 20 3.1 網路爬蟲空氣品質數據 20 3.1.1 環境部國家空品測站之空氣品質彙整資料 20 3.1.2 網路爬蟲 20 3.2 DTW時間序列差異分析 21 3.2.1 DTW分析方法 21 3.2.2 時間序列相似度比較 21 3.2.3 外部因素對空氣品質的影響 22 第四章 具機器學習處理之實驗過程 32 4.1 資料預處理 32 4.2 模型建立與訓練 33 4.2.1 LSTM及GRU 34 4.2.2 ARIMAX 35 4.2.3 Transformer 35 4.3 空氣品質指標驗證與評估 36 4.3.1 評估指標 36 4.3.2 空氣品質指標訓練及預測結果 37 第五章 結論與未來展望 61 5.1 結論 61 5.2 未來展望 62 參考文獻 64

    [1] 111年國人死因統計結果, https://www.mohw.gov.tw/cp-16-74869-1.html (Retrieved on May 3,2024).
    [2] 空氣品質指標 (AQI) 與健康影響及活動建議, https://airtw.moenv.gov.tw/CHT/Information/Standard/AirQualityIndicator.aspx (Retrieved on May 3, 2024).
    [3] M. A. Zaytar and C. El Amrani, "Machine learning methods for air quality monitoring," 2020 Proceedings of the 3rd International Conference on Networking, Information Systems & Security, Marrakech, Morocco, March 31-April 2, 2020.
    [4] A. Zeng, M. Chen, L. Zhang, and Q. Xu, "Are transformers effective for time series forecasting?," In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 9, pp. 11121-11128, 2023.
    [5] C.H. Hsu and F.Y. Cheng, "Synoptic weather patterns and associated air pollution in Taiwan," Aerosol and Air Quality Research, vol. 19, no. 5, pp. 1139-1151, 2019.
    [6] B. Dissanayake, O. Hemachandra, N. Lakshitha, D. Haputhanthri, and A. Wijayasiri, "A comparison of ARIMAX, VAR and LSTM on multivariate short-term traffic volume forecasting," In Proceedings of the 28th Conference of FRUCT Association, pp. 564-570, 2021.
    [7] T. Han, Q. Peng, Z. Zhu, Y. Shen, H. Huang, and N. N. Abid, "A pattern representation of stock time series based on DTW," Physica A: Statistical Mechanics and its Applications, vol. 550, no. 124161, 2020.
    [8] Understanding LSTM Networks. [online]. http://colah.github.io/posts/2015-08-Understanding-LSTMs (Retrieved on May 6, 2024).
    [9] S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural Computation, vol. 9, no. 8, pp. 1735-1780, November 1997.
    [10] J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, "Gated feedback recurrent neural networks," In Proceedings of the 32nd International Conference on Machine Learning, Lille, France, 2015.
    [11] G. E. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time series analysis: forecasting and control, 3rd ed., NJ: John Wiley & Sons, 2015.
    [12] D. A. Dickey and W. A. Fuller, "Distribution of the estimators for autoregressive time series with a unit root," Journal of the American statistical association, vol. 74, no. 366a, pp. 427-431, 1979.
    [13] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, "Attention is all you need," 2017 Advances in Neural Information Processing Systems, 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, 2017.
    [14] 民生公共物聯網資料服務平台, https://ci.taiwan.gov.tw/dsp/ (Retrieved on Mar 1, 2024).
    [15] M. Müller, "Dynamic time warping," Information Retrieval for Music and Motion, pp. 69-84, Berlin: Springer, 2007.
    [16] 空氣品質監測網, https://airtw.moenv.gov.tw/cht/Encycslopedia/pedia08/pedia8_2.aspx (Retrieved on Mar 1, 2024).
    [17] R. J. Hyndman and A. B. Koehler, "Another look at measures of forecast accuracy," International Journal of Forecasting, vol. 22, no. 4, pp. 679-688, 2006.
    [18] W.-L. Cheng, J.-L. Pai, B.-J. Tsuang, and C.-L. Chen, "Synoptic patterns in relation to ozone concentrations in west-central Taiwan," Meteorology and Atmospheric Physics, vol. 78, no. 1, pp. 11-21, 2001.
    [19] S. Selvin, V. R. Vinayakumar, E. A. Gopalakrishnan, V. K. Menon, and K. P. Soman, "Stock price Prediction using LSTM,RNN and CNN-sliding window model," 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Udupi, India, September 2017.
    [20] E. Kristiani, H. Lin, J. R. Lin, Y. H. Chuang, C. Y. Huang, and C. T. Yang, "Short-Term Prediction of PM2.5 Using LSTM Deep Learning Methods," Sustainability, vol. 14, no. 4, pp. 2068, February 2022.
    [21] P. Ďurka and P. Silvia, "ARIMA vs. ARIMAX–which approach is better to analyze and forecast macroeconomic time series?," Proceedings of 30th international conference mathematical methods in economics, vol. 2, pp. 136-140, September 2012.
    [22] G. Mani, J. K. Viswanadhapalli, and A. A. Stonie, "Prediction and forecasting of air quality index in Chennai using regression and ARIMA time series models," Journal of Engineering Research, vol. 10, no. 2A, pp. 179-194, August 2021.
    [23] H. HE and F. LUO, "Study of LSTM Air Quality Index Prediction Based on Forecasting Timeliness," IOP Conference Series: Earth and Environmental Science, vol. 446, no. 3, pp. 032113, 2020.
    [24] R. Fu, Z. Zhang, and L. Li, "Using LSTM and GRU Neural Network Methods for Traffic Flow Prediction," 2016 31st Youth academic annual conference of Chinese association of automation (YAC), pp. 324-328, IEEE, 2016.
    [25] S. Sridhar and S. Sanagavarapu, "Multi-Head Self-Attention Transformer for Dogecoin Price Prediction," 2021 14th International Conference on Human System Interaction (HSI), pp. 1-6, IEEE, 2021.
    [26] 李坤洲，應用統計學習及公共物聯網於空氣污染防制之研究，環境部112年度補助空氣污染防制基金科技研究計畫結案報告，2024年1月。
    [27] 陳大田、陳美心、周天穎、陳耀鐘、甯方璽，「機器學習建構PM2.5濃度模型之研究-以台中市為例」，中正嶺學報，第52卷第2期，41-53頁，2023年11月。
    [28] 林澔、陳源安、楊朝棟、姜自強，「基於深度學習技術應用於空氣品質 PM2.5預測」，TANET2019臺灣網際網路研討會，2019年12月。
    [29] 柯亘重，「台灣冬夏季季風及短期氣候變遷研究」，環境與世界，第2卷第13期，23-34頁，2006年6月。
    [30] 洪致文、施明甫，「以測站長期觀測數據分析之臺灣各季節降水垂直分布氣候特徵」，大氣科學，第1卷第51期，1-29頁，2023年6月。

    無法下載圖示 校內：2029-08-29公開
    校外：2029-08-29公開
    電子論文尚未授權公開，紙本請查館藏目錄
    QR CODE