(3.238.186.43) 您好!臺灣時間:2021/03/01 09:02
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:顧芷瑄
研究生(外文):Ku, Chih-Hsuan
論文名稱:探討能源決策管理: 應用機器學習於空氣汙染預測之研究
論文名稱(外文):A Study on Energy Decision-Making: Machine Learning Approaches for Air Pollution Forecasting
指導教授:廖崇碩
指導教授(外文):Liao, Chung-Shou
口試委員:侯建良林春成
口試委員(外文):Hou, Jiang-LiangLin, Chun-Cheng
口試日期:2018-07-12
學位類別:碩士
校院名稱:國立清華大學
系所名稱:工業工程與工程管理學系所
學門:工程學門
學類:工業工程學類
論文種類:學術論文
論文出版年:2018
畢業學年度:106
語文別:英文
論文頁數:36
中文關鍵詞:能源管理空氣污染預測模型支援向量機隱馬可夫模型
外文關鍵詞:Energy ManagementAir PollutionForecast ModelSVMHMM
相關次數:
  • 被引用被引用:1
  • 點閱點閱:163
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
近年來空氣污染一直是大家關注的議題,空氣污染嚴重地影響了人們的生活,以及對人體造成各種不同的危害。然而考量到現實層面,我們很難在空氣品質和經濟發展之中取得平衡。本研究探討了近年來的能源決策議題,並且針對台灣中部的空氣污染進行預測。
根據行政院環境保護署提供的PM2.5數值與相關的化學及氣象因子等長期時間序列 (time-series) 資料,我們使用了幾種不同類型的機器學習模型去預測PM2.5之濃度,包含了監督式學習的支援向量機 (SVM)、非監督式學習的隱馬可夫模型 (HMM) 及自迴歸隱馬可夫模型 (AR-HMM)。其中,由於自迴歸隱馬可夫模型在觀察值中彼此有相依的關係存在,此結構符合本研究的觀察值之時間序列資料型態,因此相較於其他的機器學習模型,使用自迴歸隱馬可夫模型在PM2.5的濃度預測上擁有較好的預測表現。本研究針對台灣中部地區進行研究,實驗結果顯示了模型的有效性,並提供政府其資訊,以利制定能源政策。
In recent decades, the air quality issue has caught everyone’s attention and become a significant problem for everybody. It has influenced human living and brought a variety of risks to the health of people. However, it is always difficult to balance air quality and economic development. In this study, we consider the recent debate on energy policy making and investigate the forecast of air pollution in Central Taiwan.
Based on long-term time-series past data of PM2.5 and relevant chemical and meteorological factors, we use several different types of popular machine learning approaches for predicting the concentration levels of PM2.5. In particular, the autoregressive hidden Markov model (AR-HMM), which admits the existence of dependency between time-series observations, has a relatively better prediction performance. The empirical studies in Taichung area, Taiwan demonstrate the effectiveness of the model, which can be used to assist the government for setting appropriate energy policies.
摘要 I
Abstract II
致謝 III
Contents IV
List of Figures and Tables V
1. Introduction 1
1.1 Background 1
1.2 Literature Review 4
1.3 Objective 5
1.4 Research Structure 6
2. Preliminary and Terminology 7
2.1 Support Vector Machine 7
2.1.1 Support Hyperplane: Linear Separable 8
2.1.2 Support Hyperplane: Nonlinear Separable 9
2.2 Hidden Markov Model 10
2.2.1 Three Problems of Hidden Markov Model 11
2.2.2 Solutions to Each Problem 12
2.3 Autoregressive Hidden Markov Model 15
3. Methodology and Discussion 17
3.1 Methodology 17
3.2 Discussion on Factors 20
3.2.1 Data Characteristics and PM2.5 Trends 20
3.2.2 Factors Selection 24
3.2.2.1 Basic Chemical Precursors and Meteorological Factors 24
3.2.2.2 The Correlations Between Each Factor 26
3.2.2.3 The Data of PM2.5 in China 27
3.2.2.4 Thermal Power Stations 28
3.2.3 Observations Summary 30
4. Results 31
5. Conclusion 34
Reference 35
1. USEPA, 2017. Particulate Matter (PM) Pollution, retrieved from
https://www.epa.gov/pm-pollution/particulate-matter-pm-basics#PM
2. KENT RO SYSTEMS, 2017. How to Ensure Your Kid’s Good Health with KENT Air Purifier? retrieved from https://www.kent.co.in/blog/how-to-ensure-your-kids-good-health-with-kent-air-purifier/
3. WHO, 2016. Ambient (outdoor) air quality and health, retrieved from
http://www.who.int/mediacentre/factsheets/fs313/en/
4. Environmental Protection Administration Executive Yuan R.O.C. (Taiwan), 2012. Taiwan Air Quality Monitoring Network, The Air Quality Standard, retrieved from https://taqm.epa.gov.tw/taqm/tw/b0206.aspx
5. Environmental Protection Administration Executive Yuan R.O.C. (Taiwan), 2018. The definition of air pollution indicators, retrieved from
https://taqm.epa.gov.tw/taqm/tw/b0201.aspx
6. Taiwan Power Company, 2018. Household Electricity Consumption Guide, from https://www.taipower.com.tw/tc/page.aspx?mid=212&cid=118&cchk=2b7682d9-46f8-4103-b636-02a5afeda67c
7. 台灣電力公司, 2018。 歷年發電量及結構。取自:https://www.taipower.com.tw/TC/chart_m/a01_電力供需資訊_電源開發規劃_歷年發電量及結構.html
8. James Conca, 2012. How Deadly Is Your Kilowatt? We Rank the Killer Energy Sources. Retrieved from https://www.forbes.com/sites/jamesconca/2012/06/10/energys-deathprint-a-price-always-paid/#aabee84709b7
9. 鄭睿合、陳冠翰、林文祥,2017。因應電力短缺之服務業應變機制,經濟前瞻。
10. 張立農、江孟玲、林昭遠,2015。台灣交通空氣品質監測站PM10變異影響因素之研究,中興大學水土保持學報,第47卷 第01期。
11. 洪若雅,2017。臺灣大氣背景 PM2. 5 質量濃度之推估。
12. Lin, Y., Zou, J., Yang, W., & Li, C. Q. (2018). A Review of Recent Advances in Research on PM2. 5 in China. International journal of environmental research and public health, 15(3), 438.
13. Niharika, V. M., & Rao, P. S. (2014). A survey on Air Quality Forecasting Techniques. International Journal of Computer Science and Information Technologies, 5(1), 103-107.
14. Feng, X., Li, Q., Zhu, Y., Hou, J., Jin, L., & Wang, J. (2015). Artificial neural networks forecasting of PM2. 5 pollution using air mass trajectory based geographic model and wavelet transformation. Atmospheric Environment, 107, 118-128.
15. Lu, W. Z., & Wang, W. J. (2005). Potential assessment of the “support vector machine” method in forecasting ambient air pollutant trends. Chemosphere, 59(5), 693-701.
16. Weizhen, H., Zhengqiang, L., Yuhuan, Z., Hua, X., Ying, Z., Kaitao, L., ... & Yan, M. (2014). Using support vector regression to predict PM10 and PM2. 5. In IOP Conference Series: Earth and Environmental Science (Vol. 17, No. 1, p. 012268). IOP Publishing.
17. Dong, M., Yang, D., Kuang, Y., He, D., Erdal, S., & Kenski, D. (2009). PM2. 5 concentration prediction using hidden semi-Markov model-based times series data mining. Expert Systems with Applications, 36(5), 9046-9055.
18. Sun, W., Zhang, H., Palazoglu, A., Singh, A., Zhang, W., & Liu, S. (2013). Prediction of 24-hour-average PM2. 5 concentrations using a hidden Markov model with different emission distributions in Northern California. Science of the total environment, 443, 93-103.
19. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3), 273-297.
20. Juang, B. H., & Rabiner, L. (1985). Mixture autoregressive hidden Markov models for speech signals. IEEE Transactions on Acoustics, Speech, and Signal Processing, 33(6), 1404-1413.
21. Tang, X. (2005). Autoregressive hidden markov model with application in an El Nino study (Doctoral dissertation).
22. Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257-286.
23. Donalek, C. (2011). Supervised and Unsupervised learning. In Astronomy Colloquia. USA.
24. Environmental Protection Administration Executive Yuan R.O.C. (Taiwan), Taiwan Air Quality Monitoring Network 2012, History Data Download, retrieved from
https://taqm.epa.gov.tw/taqm/tw/YearlyDataDownload.aspx
25. Mission China air quality monitoring program, 2018, retrieved from
http://www.stateair.net/web/historical/1/3.html
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
系統版面圖檔 系統版面圖檔