跳到主要內容

臺灣博碩士論文加值系統

(44.222.64.76) 您好!臺灣時間:2024/06/16 04:38
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:范謙弘
研究生(外文):Fan, Chien-Hung
論文名稱:基於空汙數據及機器學習之PM2.5預測分析
論文名稱(外文):Analysis of PM2.5 Prediction Based on Gas Emission Data and Machine Learning
指導教授:戴立嘉
指導教授(外文):Tai, Li-Chia
口試委員:林顯易黃聖傑
口試委員(外文):Lin, Shean-YihHuang, Sheng-Chieh
口試日期:2023-06-19
學位類別:碩士
校院名稱:國立陽明交通大學
系所名稱:電控工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2023
畢業學年度:111
語文別:中文
論文頁數:49
中文關鍵詞:PM2.5預測機器學習時間序列資料長短期記憶神經網路CNN-LSTM
外文關鍵詞:PM2.5 forecastingMachine learningTime series dataLSTMCNN-LSTM
相關次數:
  • 被引用被引用:0
  • 點閱點閱:158
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
隨著科技進步及人口增加,人類對於環境的破壞日益遽增,空氣汙染已然成高度重視的議題之一,而PM2.5作為空氣汙染的評估指標之一,若暴露在高濃度的PM2.5環境下會引起人體不適,甚至引發呼吸道疾病,對健康造成影響。為了有效防患PM2.5,除了尋找減少汙染的方法以外,如何精準的預測未來環境變化,即時做好對空氣汙染的防範也是重要的課題之一,因此本研究著重於研究大數據及資料科學,搭配人工智慧的發展將技術應用到PM2.5的監測任務,建立空氣品質的預測系統,進一步做到防患未來的效果。
本文採用行政院環保署的新竹測站蒐集數據,利用過去24小時內的空氣品質資訊預測未來的PM2.5濃度變化,比較CNN-LSTM、LSTM、XGBoost、SVR、KNN等不同演算法的模型預測結果,同時根據關聯度分析,也比較了採取不同空氣品質特徵對模型效能的影響,接著透過觀察PM2.5季節性週期變化提出適應季節性的預測方法,結合分類與回歸算法的架構,利用特徵相似性區分數據後個別訓練,使模型能適應特定的資料,進而對該類別有更準確的預測,最後提出採取PM2.5單變量的預測模式,建立快速的預測模型,不僅節省了訓練模型的時間,同時降低感測裝置的需求,採用單一測項來對未來的PM2.5濃度變化進行預測。
With the advancement of technology and the growth of population, the destruction of the environment by human beings increase rapidly. Air pollution has become a prevalent issue, and PM2.5, as one of the evaluation indicators of air pollution, will cause discomfort and respiratory diseases to the human. In order to effectively prevent PM2.5, in addition to finding ways to reduce pollution, how to accurately forecast future environmental changes and prevent air pollution in advance is also one of the important topics. Therefore, this research focuses on improving the PM2.5 forecasting method by the data science and artificial intelligence.
We use the air quality information in the past to predict the future PM2.5 concentration changes, and compare the model of different algorithms such as CNN-LSTM, LSTM, XGBoost, SVR, and KNN Regression. Based on correlation analysis, the influence of different air quality features on model performance is also compared. Furthermore, we propose an adaptive seasonal prediction method and the framework of the classification and regression algorithms to make forecasting by using the similarity to distinguish the data and train individually, which improving the model to adapt to specific data and make more accurate predictions. Finally, a prediction model that adopts the change of the single variable of PM2.5 is proposed to establish a fast prediction, which saves training time and reduces the demand for sensing devices.
摘要 i
Abstract ii
誌謝 iii
目錄 iv
圖目錄 v
表目錄 viii
第一章、緒論 1
1.1 研究背景 1
1.2 研究目的 2
1.3 研究貢獻 2
1.4 論文架構 3
第二章、相關研究 4
2.1 懸浮微粒相關介紹 4
2.2 演算法介紹 5
2.3 文獻討論 20
第三章、研究方法 22
3.1 開發環境 22
3.2 研究流程 23
3.3 資料處理 24
3.4 預測模型及評估指標 26
第四章、研究結果 28
4.1 特徵選取 28
4.2 演算法比較 31
4.3 PM2.5週期性分析 36
4.4 K-means 聚類分析 40
4.5 PM2.5單變量預測方法 43
第五章、結論與未來展望 45
5.1 結論 45
5.2 未來展望 46
參考文獻 47
[1] C.-C. Chen, P.-S. Chen, and C.-Y. Yang "Relationship between fine particulate air pollution exposure and human adult life expectancy in Taiwan," J. Toxicology and Environmental Health, vol. 82, no. 14, pp. 826-832, Aug. 2019.
[2] Gelencsér, A., May, B., Simpson, D, "Source apportionment of PM2.5 organic aerosol over Europe: Primary/secondary, natural/anthropogenic, and fossil/biogenic origin." Journal of Geophysical Research: Atmospheres (1984–2012), vol. 112. 2007.
[3] Hecht-Nielsen, Robert. "Theory of the backpropagation neural network." Neural networks for perception, pp. 65-93, 1992.
[4] Y.LeCun, L.Jackel, L.Bottou, A.Brunot, C.Cortes, J.Denker, H.Drucker, I.Guyon, U. A.Muller, E.Sackinger, andothers, “Comparison of learning algorithms for handwritten digit recognition.” International conference on artificial neural networks. vol. 60, pp. 53–60. 1995.
[5] Tran, Du, et al. "Learning spatiotemporal features with 3d convolutional networks." Proceedings of the IEEE international conference on computer vision. 2015.
[6] Tang, Wensi, et al. "Rethinking 1d-cnn for time series classification: A stronger baseline." arXiv preprint arXiv: 2002.10061, pp. 1-7, Feb, 2020.
[7] S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," in Neural Computation, vol. 9, no. 8, pp. 1735-1780, 15 Nov. 1997.
[8] A. H. Bukhari, M. A. Z. Raja, M. Sulaiman, S. Islam, M. Shoaib and P. Kumam, "Fractional Neuro-Sequential ARFIMA-LSTM for Financial Market Forecasting," in IEEE Access, vol. 8, pp. 71326-71338, 2020.
[9] X. Du et al., "An Efficient LSTM Network for Emotion Recognition From Multichannel EEG Signals," in IEEE Transactions on Affective Computing, vol. 13, no. 3, pp. 1528-1540, 2022.
[10] S. Mai, S. Xing and H. Hu, "Analyzing Multimodal Sentiment Via Acoustic- and Visual-LSTM With Channel-Aware Temporal Convolution Network," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 1424-1437, 2021.
[11] Shi, Xingjian, et al. "Convolutional LSTM network: A machine learning approach for precipitation nowcasting." Advances in neural information processing systems, vol. 28, 2015.
[12] Li, Taoying, Miao Hua, and X. U. Wu. "A hybrid CNN-LSTM model for forecasting particulate matter (PM2. 5)." Ieee Access, vol. 8, pp. 26933-26940, 2020.
[13] H. Zheng, F. Lin, X. Feng and Y. Chen, "A Hybrid Deep Learning Model With Attention-Based Conv-LSTM Networks for Short-Term Traffic Flow Prediction," in IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 11, pp. 6910-6920, 2021.

[14] O. Koller, N. C. Camgoz, H. Ney and R. Bowden, "Weakly Supervised Learning with Multi-Stream CNN-LSTM-HMMs to Discover Sequential Parallelism in Sign Language Videos," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 9, pp. 2306-2320, 2020.
[15] T. Akilan, Q. J. Wu, A. Safaei, J. Huo and Y. Yang, "A 3D CNN-LSTM-Based Image-to-Image Foreground Segmentation," in IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 3, pp. 959-971, 2020.
[16] Cortes, C., Vapnik, V, "Support-vector networks." Mach Learn, vol 20, pp 273–297, 1995.
[17] N. S. Altman, "An introduction to kernel and nearest-neighbor nonparametric regression," The American Statistician, vol. 46, no. 3, pp. 175-185, 1992.
[18] S. Zhang, "Challenges in KNN Classification," in IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 10, pp. 4663-4675, 2022.
[19] Chen, Tianqi, and Carlos Guestrin. "Xgboost: A scalable tree boosting system." Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp. 785–794, 2016.
[20] Hartigan, John A., and Manchek A. Wong. "Algorithm AS 136: A k-means clustering algorithm." Journal of the royal statistical society, vol. 28, pp100-108, 1979
[21] K. P. Sinaga and M. -S. Yang, "Unsupervised K-Means Clustering Algorithm," in IEEE Access, vol. 8, pp. 80716-80727, 2020.
[22] T. Y. Wen and S. A. Mohd Aris, "Hybrid Approach of EEG Stress Level Classification Using K-Means Clustering and Support Vector Machine," in IEEE Access, vol. 10, pp. 18370-18379, 2022.
[23] Z. Sun, S. Zhao and J. Zhang, "Short-Term Wind Power Forecasting on Multiple Scales Using VMD Decomposition, K-Means Clustering and LSTM Principal Computing," in IEEE Access, vol. 7, pp. 166917-166929, 2019.
[24] Ho, Siu Lau, and Min Xie. "The use of ARIMA models for reliability forecasting and analysis." Computers & industrial engineering, vol. 35, no. 1-2, pp. 213-216, 1998.
[25] S. Mehrmolaei and M. R. Keyvanpour, "Time series forecasting using improved ARIMA," 2016 Artificial Intelligence and Robotics (IRANOPEN), pp. 92-97, 2016.
[26] Tominaga, Yoshihide, and Ted Stathopoulos. "CFD simulation of near-field pollutant dispersion in the urban environment: A review of current modeling techniques." Atmospheric Environment, vol. 79, pp. 716-730, 2013.
[27] Rakowska, Agata, et al. "Impact of traffic volume and composition on the air quality and pedestrian exposure in urban street canyon." Atmospheric Environment, vol. 98, pp. 260-270, 2014.
[28] Luo, Cyuan-Heng, et al. "A fast PM2. 5 forecast approach based on time-series data analysis, regression and regularization." 2018 conference on technologies and applications of artificial intelligence (TAAI). IEEE, 2018.

[29] Brook, J.R., Dann, T.F., Rurnett, R.T., 1997, “The Relationship Among TSP, PM10, PM2.5, and Inorganic Constituents of Atmospheric Particulate Matter at Multiple Canadian Locations”, JAPCA-the Journal of the Air and Waste Management Association, vol. 47, no. 1, pp. 2-19, 1997.
[30] Mahanta, Soubhik, et al. "Urban air quality prediction using regression analysis." TENCON 2019-2019 IEEE Region 10 Conference (TENCON). IEEE, 2019.
[31] Chen, Yuan, Hui Qin, and ZhiGang Zhou. "A comparative study on multi-regression analysis and BP neural network of PM2. 5 index." 2014 10th International Conference on Natural Computation (ICNC). IEEE, 2014.
[32] Chen, Yinan, Shichong Yang, and Qiyuan Wang. "Prediction of PM2. 5 concentration in Guangzhou based on LSTM neural network." 2021 2nd International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI). IEEE, 2021.
[33] Li, Taoying, Miao Hua, and X. U. Wu. "A hybrid CNN-LSTM model for forecasting particulate matter (PM2. 5)." Ieee Access, vol. 8, pp. 26933-26940, 2020.
[34] Qiao, Weibiao, et al. "The forecasting of PM2. 5 using a hybrid model based on wavelet transform and an improved deep learning algorithm." IEEE Access, vol. 7, pp. 142814-142825, 2019.
[35] Mahajan, Sachit, et al. "Improving the accuracy and efficiency of PM2. 5 forecast service using cluster-based hybrid neural network model." IEEE Access, vol. 6, pp 19193-191204, 2018.
[36] Liu, Fayao, Chunhua Shen, and Guosheng Lin. "Deep convolutional neural fields for depth estimation from a single image." Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
[37] Chakma, Avijoy, et al. "Image-based air quality analysis using deep convolutional neural network." 2017 IEEE international conference on image processing (ICIP). IEEE, 2017.
[38] Yue, Guanghui, Ke Gu, and Junfei Qiao. "Effective and efficient photo-based PM2.5 concentration estimation." IEEE Transactions on instrumentation and measurement, vol. 68, no. 10, pp. 3962-3971, 2019.
[39] Collado, José, and Cristian Pinzon. "Air Pollution Prediction Using Machine Learning Algorithms: A Literature Review." 2022 V Congreso Internacional en Inteligencia Ambiental, Ingeniería de Software y Salud Electrónica y Móvil (AmITIC). IEEE, 2022.
[40] L. Bo et al., "Feature Scaling for Kernel Fisher Discriminant Analysis Using Leave-one-out Cross Validation."Neural Computation (NECO), vol. 18, no. 4, pp. 961-978, 2006.
[41] https://chtseng.wordpress.com/2017/09/12/%E5%88%9D%E6%8E%A2%E5%8D%B7%E7%A9%8D%E7%A5%9E%E7%B6%93%E7%B6%B2%E8%B7%AF/
電子全文 電子全文(網際網路公開日期:20240817)
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊