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 U0026-0708201811531300
論文名稱(中文) 基於長短期記憶模型的懸浮微粒2.5預測
論文名稱(英文) PM 2.5 Prediction based on LSTM Model
校院名稱 成功大學
系所名稱(中) 工程科學系
系所名稱(英) Department of Engineering Science
學年度 106
學期 2
出版年 107
研究生(中文) 林彥良
研究生(英文) Yen-Liang Lin
電子信箱 alksjdf12384@gmail.com
學號 N96044086
學位類別 碩士
語文別 英文
論文頁數 28頁
口試委員 指導教授-廖德祿
口試委員-顏錦柱
口試委員-簡尊彝
口試委員-郭瀚鴻
中文關鍵字 遞迴神經網路  長短期記憶模型 
英文關鍵字 Long Short Term Memory  PM 2.5  Backpropagatopn Through Time  time series forecasting 
學科別分類
中文摘要 近年來,台灣地區的PM2.5空氣污染狀況日益嚴重。亞洲的大城市如北京、德里等也正面臨同樣的空污問題,引起了政府和專家學者的關注。由於亞洲地區的工業化、畜牧等人為活動,空氣污染的狀況更加嚴重,增加民眾罹患心血管疾病的機率。PM2.5的污染已經變成了現今社會不可忽視的問題。目前,官方氣象單位對於大氣動向的預測仍然使用傳統的統計模型。傳統的統計模型例如ARIMA對於時間序列資料的預測有一定的準確率。然而近年來隨著電腦和晶片計算能力的進步,神經網路和深度學習的應用領域也愈來愈廣。遞迴神經網路被發展來用於處理時間序列問題。長短期記憶模型擁有比遞迴神經網路更大時間幅度的記憶能力,同時也常被用於對現實中的序列資料進行預測分析。本論文使用長短期記憶模型預測未來的PM2.5小時平均濃度,希望政府和相關單位能針對此污染現象做出應對,改善空氣污染的問題。
英文摘要 Recently, pollution conditions of particulate matter 2.5 in Taiwan have become more severe day by day. Several other cities in Asia such as Beijing and Delhi are also facing the same pollution problem, which draws attention to government and experts. Due to the human activities in Asia such as industrialization and animal husbandry, air pollution condition has been getting worse, increases the possibility of population suffering from cardiovascular disease. Particular matter pollution has become a problem we cannot ignore in modern society. Currently, official meteorological department applies traditional statistic model to predict meteorology trend. Traditional statistic model such like ARIMA has certain accuracy on time series data. However, nowadays along with the calculate ability of computer and chips progressing, application field of neural network and deep learning has become much more extensive. Recurrent neural network had been developed to deal with time sequence data. Long short term memory model has a longer time range memorize ability than recurrent neural network, meanwhile has been frequently applied on forecasting and analyzation. This thesis utilizes the long short term memory model to predict future particular matter hourly average concentration, in hope that government and the departments concerned could take actions on the pollution phenomenon, improve the air pollution problem.
論文目次 Outline
摘要…………………………………………………………………………………………I
Abstract……………………………………………………………………………………II
誌謝…………………………………………………………………………………………IV
Outline ……………………………………………………………………………………V
LIST OF FIGURE………………………………………………………………………………VII
CHAPTER 1 INTRODUCTION……………………………………………………………………1
1.1 Background……………………………………………………………………………1
1.2 Motivation……………………………………………………………………………2
1.3 Thesis Organization………………………………………………………………2
CHAPTER 2 HISTORICAL LITERATURE REVIEW………………………………………………4
2.1 Historical Study for PM2.5 Forecasting………………………………………4
2.2 Historical Study for LSTM Model………………………………………………5
CHAPTER 3 LONG SHORT TERM MEMORY………………………………………………………7
3.1 Artificial Neural Network…………………………………………………………7
3.2 Recurrent Neural Network…………………………………………………………8
3.2.1 Backpropagation Through Time………………………………………………10
3.2.2 Gradient Vanishing Problem…………………………………………………11
3.3 Long Short Term Memory……………………………………………………………13
3.3.1 Adam Optimization Algorithm………………………………………………15
CHAPTER 4 EXPERIMENTAL RESULTS…………………………………………………………17
4.1 Data Description……………………………………………………………………17
4.2 Experimental Design…………………………………………………………………18
CHAPTER 5 CONCLUSION AND FUTURE WORK......................................24
5.1 Conclusion……………………………………………………………………………24
5.2 Future Work…………………………………………………………………………24
REFERENCE……………………………………………………………………………………26
參考文獻 [1] J. H. Chang and C. Y. Tseng, “Analysis of Correlation Between Secondary PM2.5 and Factory Pollution Sources by Using ANN and the Correlation Coefficient” IEEE Access: Special Section on Key Technologies for Smart Factory of Industry 4.0, vol. 5, pp. 22812 – 22822, Oct. 2017
[2] Y. Zheng, Ch. Z. Zhu, ”A Prediction Method of Atmospheric PM2. 5 Based on DBNs”, in Journal of Shandong University (Engineering Science), vol.4, no.6, Dec. 2014
[3] Pope C. A. , Burnett R. T. , Thun M. J. , et al., ”Lung cancer, Cardiopulmonary Mortality, and Long-Term Exposure to Fine Particulate Air Pollution[J]” Journal of the American Medical Association, vol. 287, no. 9, pp. 1132-1141, Mar. 2002
[4] Z. Qi, T. Wang, G. Song, W. Hu, X. Li, et al. “Deep Air Learning: Interpolation, Prediction, and Feature Analysis of Fine-grained Air Quality”, in : CoRR abs/1711.00939 (2017). arXiv:1711.00939.URL: http://arxiv.org/abs/1711.00939
[5] X. Li., L. Peng, X. Yao, S. Cui, Y. Hu, C. You, and T. Chi, “Long Short-Term Memory Neural Network for Air Pollutant Concentration Predictions: Method Development and Evaluation” in Environmental Pollution, vol. 231 (2017) pp.997-1004, 2017
[6] D. Reid; H. Tawfik; A. J. Hussain; H. A. Askar, “Forecasting Weather Signals Using a Polychronous Spiking Neural Network”, in Intellegent Conference on Intellegent Computing, Fuzhou. CHINA, , p116~124, 2015
[7] M. Oprea1, M. Popescul and S. F. Mihalache, “A Neural Network Based Model for PM2.5 Air Pollutant Forecasting”, in International Conference on System Theory, Control and Computing .ICSTCC, Sinaia. ROMANIA , Oct. 2016, pp. 776-781
[8] P. Jiang, Q. Dong, P. Li, “A Novel Hybrid Strategy for PM2.5 Concentration Analysis and Prediction”, in Journal of Environmental Management , vol. 196, nol. 1, pp. 443-457, Mar. 2017
[9] W. Yang, M. Deng, F. Xu, H. Wang, “Prediction of Hourly PM2.5 Using a Space-Time Support Vector Regression Model” in Atmospheric Environment, pp. 12-19, 2018
[10] M. Oprea1, M. Popescul and S. F. Mihalache, “Applying Artificial Neural Networks to Short-Term PM2.5 Forecasting Modeling”, IFIP WG 12.5 International Conference and Workshops, AIAI 2016 Thessaloniki, Greece, Sept. 2016
[11] W. Wang, Y. Guo, “Air Pollution PM2.5 Data Analysis In Los Angeles Long Beach With Seasonal ARIMA Model” in IEEE Internaltional Conference on Energy and Environment Technology, 2009
[12] S. Mahajan, L. J. Chen, T. C. Tsai, “An Empirical Study of PM2.5 Forecasting Using Neural Network” in IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications Cloud & Big Data Computing, Internet of People and Smart City Innovation, 2017
[13] R. Pascanu, T. Mikolov, Y. Bengio, “On the Difficulty of Training Recurrent Neural Networks”, in Proceedings of the 30th International Conference on Machine Learning, ICML. Atlanta, GA, USA, 16-21 June 2013, pp. 1310–1318, 2013
[14] S. Hochreiter, “Long Short-term Memory” in Neural Computation, Dec. 1997
[15] G. Kurata, B. Ramabhadran, G. Saon, and A. Sethy, “Language Modeling with Highway LSTM,” in arXiv preprint arXiv:1709.06436
[16] G. Parascandolo, H. Huttunen, and T. Virtanen, “Recurrent Neural Networks for Polyphonic Sound Event Detection in Real Life Recordings,” in IEEE International Conference on Acoustics, Speech and Signal Processing .ICASSP. 2016, pp. 6440–6444
[17] K. Xu, H. Wang, and P. Tang, “Image Captioning with Deep LSTM Based on Sequential Residual,” in Proceedings of IEEE International Conference on Multimedia and Expo (ICME), 2017, pp. 361–366
[18] Y. Peng, L., H. Di, B. Junpeng, Q. Yong, “Multi-step Ahead Time Series Forecasting for Different Data Patterns Based on LSTM Recurrent Neural Network”, Web Information Systems and Applications Conference (WISA), pp. 305–310, Nov. 2017
[19] J. Guo, “Backpropagation Through Time”, Technical Report, 2013
[20] DP Kingma, Jimmy Ba, “Adam: A Method for Stochastic Optimization”, in International Conference for Learning Representations, San Diego, 2015
[21] https://taqm.epa.gov.tw/taqm/tw/default.aspx, Environmental Protection Administration Executive Yuan R.O.C.
[22] L. Donghui., W. Peng, M.Yan, H. Weizhen, Z. Yuhuan, X. Hua, Z. Ying, L. Kaitao, L. Zhengqiang, “Using Support Vector Regression to Predict PM10 and PM2.5”, In Interational Symposium on Remote Sensing of Environment .ISRSE35. vol.17, 2014
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2023-07-01起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2023-07-04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