(35.175.212.130) 您好!臺灣時間:2021/05/15 09:49
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:::

: 
twitterline
研究生:周黃文耀
研究生(外文):Chouhuang, Wen-Yao
論文名稱:應用類神經網路模型預測屏東市區次日PM2.5小時濃度
論文名稱(外文):1-day ahead prediction of the hourly PM2.5 concentrations in Pingtung city using the neural network modeling
指導教授:吳繼澄吳繼澄引用關係
指導教授(外文):Wu, Ji-Cheng
學位類別:碩士
校院名稱:國立屏東科技大學
系所名稱:工業管理系所
學門:商業及管理學門
學類:其他商業及管理學類
論文種類:學術論文
論文出版年:2013
畢業學年度:101
語文別:中文
論文頁數:81
中文關鍵詞:細懸浮微粒類神經網路田口方法
外文關鍵詞:fine particulate matterneural networkTaguchi's method
相關次數:
  • 被引用被引用:2
  • 點閱點閱:399
  • 評分評分:
  • 下載下載:33
  • 收藏至我的研究室書目清單書目收藏:0
空氣品質的良窳與民眾的健康息息相關,國內外相關研究皆指出空氣污染物中細懸浮微粒(PM2.5)對人體呼吸道及支氣管炎的傷害最為嚴重,以PM2.5為重心的空氣品質管制策略已逐漸成為國際趨勢。近年已有許多學者利用迴歸分析(regression analysis)、時間序列(time series)及類神經網路(neural network)等各種數量方法建構模型進行PM2.5的預測與監控。其中類神經網路只要有充分的歷史資料,不需前提假設,即可建模進行預測工作,惟輸入變數的選擇需要試誤法累積經驗或是輔以專業領域知識方能決定。本研究考慮以田口方法(Taguchi’s method)決定類神經網路預測次日PM2.5小時濃度之最佳輸入變數組合,訓練資料集為行政院環保署2010年7月1日至2011年12月31日屏東測站所監測之每日每小時氣象因子與PM2.5濃度歷史數據,以多層感知器(Multilayer Perceptron, MLP)建構PM2.5濃度預測模型,透過預測2012年1月至4月的PM2.5濃度進行模型測試,並以平均絕對誤差百分比(Mean Absolute Percentage Error, MAPE)評估模型其預測性能之優劣。研究結果顯示,類神經網路預測模型之最佳輸入變數為前一小時UVB、RAINFALL、AMB_TEMP與PM2.5,前二小時WIND_DIREC與WIND_SPEED,前三小時RH。
The quality of air has direct relationship with one’s health. Many studies had supported that fine particulate matter (PM2.5) suspended in the air are harmful to the human respiratory system and could further lead to severe cases of bronchitis. It had become an international trend to use the measurement of these fine particulates as the regulatory strategy of air quality control. In order to monitor and predict the PM2.5 concentration, there were many models, such as time series, regression and neural network, have been developed. Among them, it doesn’t need any assumption to establish the predicting model by using neural network only if we have enough data. However, one must select the proper input variables. In this study, the optimal input variable was decided by Taguchi’s method. This study used published data obtained from the Environmental Protection Administration website that collected the concentration of PM2.5 at every hour at stations in Ping-Tung city from July 1st, 2010 to December 31st, 2011. We adopted MLP neural network to create a model and then hourly prediction of was made to predict the PM2.5 concentration at the Ping-Tung city district from January to April of year 2012. Finally, the research considered using MAPE as criteria to decide the optimal input variables. The results shown the optimal input variables were given by an hour before UVB, RAINFALL, AMB_TEMP and PM2.5; two hour before WIND_DIREC and WIND_SPEED; three hour before RH.
摘要 I
Abstract III
誌謝 V
目錄 VI
圖索引 IX
表索引 X
1.緒論 1
1.1研究背景與動機 1
1.2研究目的 2
1.3研究範圍與限制 3
1.4研究流程 4
2.文獻探討 6
2.1大氣懸浮微粒 6
2.1.1懸浮微粒(PM10) 6
2.1.2細懸浮微粒(PM2.5) 7
2.1.3台灣屏東市區PM2.5近年概況 8
2.2細懸浮微粒對人體健康之影響 12
2.2.1台灣屏東地區歷年疾病就診情況 14
2.3空氣汙染預測模型 16
2.4小結 24
3.研究方法 25
3.1資料蒐集與整理 25
3.2無效值與遺漏值插補 28
3.3類神經網路簡介 28
3.3.1生物神經元模型 29
3.3.2人工神經元模型 30
3.4多層感知器簡介 32
3.4.1多層感知器之演算法 33
3.4.2多層感知器之活化函數 34
3.5田口式實驗設計法 35
3.5.1直交表(Orthogonal Arrays) 36
3.5.2田口品質特性 37
4.資料分析 39
4.1實驗1 39
4.1.1不考慮所有因子是否皆達到顯著性 44
4.1.2僅考慮顯著因子 47
4.1.3確認實驗 49
4.2實驗2 51
4.2.1不考慮所有因子是否皆達到顯著性 54
4.2.2僅考慮顯著因子 57
4.2.3確認實驗 59
4.3實驗1與2之比較 61
4.4本研究MLP模型與EWMA模型之比較 67
5.結論與建議 68
5.1結論 68
5.2建議 69
參考文獻 70
附錄一 75
附錄二 78
作者簡介 81

1.行政院衛生署,http://www.doh.gov.tw/cht2006/index_populace.aspx。
2.行政院環境保護署,http://www.epa.gov.tw/。
3.林逸塵,類神經網路應用於空氣品質預測之研究,碩士論文,國立中山大學環境工程研究所,(2002)。
4.張斐章和張麗秋,類神經網路,台灣東華書局股分有限公司,(2005)。
5.陳柏佑,利用指數加權法預測具有季節循環之每小時細懸浮微粒濃度,碩士論文,國立屏東科技大學工業管理研究所,(2012)。
6.溫燿旭,屏東市區細懸浮微粒PM2.5之預測模型,碩士論文,國立屏東科技大學工業管理研究所,(2011)。
7.葉怡成,類神經網路模式應用與實作,儒林圖書有限公司,(2009)。
8.鄭尊仁,細懸浮微粒的健康效應及法規制訂,生態台灣,第35期,pp.6-9,(2012)。
9.簡家宏,應用基因類神經網路於空氣品質短期預測及監測資料異常值診斷之研究-以台中縣沙鹿空品測站為例,碩士論文,國立雲林科技大學環境與安全衛生工程研究所,(2004)。
10.Backes, C. H., Nelin, T., Gorr, M. W., and Wold, L. E., “Early life exposure to air pollution: How bad is it?,” Toxicology Letters, Vol. 216, pp. 47-53, (2013).
11.Boldo, E., Linares, C., Lumbreras, J., Borge, R., Narros, A., García-Pérez, J., Fernández-Navarro, P., Pérez-Gómez, B., Aragonés, N., Ramis, R., Pollán, M., Moreno, T., Karanasiou, A., and López-Abente, G., “Health impact assessment of a reduction in ambient PM2.5 levels in Spain,” Environment International, Vol. 37 pp. 342-348, (2011).
12.Cakmak, S., Dales, R. E., and Coates, F., “Does air pollution increase the effect of aeroallergens on hospitalization for asthma,” Journal of Allergy and Clinical Immunology, Vol. 129, pp. 228-231, (2012).
13.Cobourn, W.G., “An enhanced PM2.5 air quality forecast model based on nonlinear regression and back-trajectory concentrations,” Atmospheric Environment, Vol. 44, pp. 3015-3023, (2010).
14.Díaz-Robles, L. A., Orteg, J. C., Fu, J. S., Reed, G. D., Chow, J. C. Watson, J. G., and Moncada-Herrera, J. A., “A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: The case of Temuco, Chile,”Atmospheric Environment, Vol. 42, pp. 8331-8340, (2008).
15.Domańska, D., and Wojtylak, M., “Application of fuzzy time series models for forecasting pollution concentrations,” Expert Systems with Applications, Vol. 39, pp. 7673-7679, (2012).
16.Dong, M., Yang, D., Kuang, Y., He, D., Erdal, S., and Kenski, D., “PM2.5 concentration prediction using hidden semi-Markov model-based times series data mining,” Expert Systems with Applications, Vol. 36, pp. 9046-9055, (2009).
17.Fernando, H. J. S., Mammarella, M.C., Grandoni, G., Fedele, P., Marco, R. D., Dimitrova, R.,and Hyde, P., “Forecasting PM10 in metropolitan areas: Efficacy of neural networks,” Environmental Pollution, Vol. 163, pp. 62-67, (2012).
18.Hoi, K. I., Yuen, K. V., and Mok, K. M., “Prediction of daily averaged PM10 concentrations by statistical time-varying model,” Atmospheric Environment, Vol. 43, pp. 2579-2581, (2009).
19.Kampa, M., and Castanas, E., “Human health effects of air pollution,”Environmental Pollution, Vol. 151, pp. 362-367, (2008).
20.Krishnan, R. M., Adar, S. D., Szpiro, A. A., Jorgensen, N. W., Van Hee, V. C., Graham Barr, R., O’Neill, M. S., Herrington, D. M., Polak, J. F., and Kaufman, J. D.,“Vascular Responses to Long- and Short-Term Exposure to Fine Particulate Matter,” Endothelial Dysfunction and Air Pollution, Vol. 60, pp. 2158-2166, (2012).
21.Kurt, A., and Oktay, A. B., “Forecasting air pollutant indicator levels with geographic models 3 days in advance using neural networks,” Expert Systems with Applications, Vol. 37, pp. 7986-7992, (2010).
22.Lewis, C. D., “Industrial and business forecasting methods: a practical guide to exponential smoothing and curve fitting,”London:Butterworth Scientific,(1982).
23.Lira, T. S., Barrozo, M. A. S., and Assis, A. J., “Air quality prediction in Uberlândia, Brazil, using linear models and neural networks,”Computer Aided Chemical Engineering, Vol. 24, pp. 51-56, (2007).
24.Maté, T., Guaita, R., Pichiule, M., Linares, C., and Díaz, J.,“Short-term effect of fine particulate matter (PM2.5) on daily mortality due to diseases of the circulatory system in Madrid (Spain),” Science of the Total Environment, Vol. 408, pp. 5750-5757, (2010).
25.O’Connor, G. T., Neas, L., Vaughn, B., Kattan, M., Mitchell, H., Crain, E. F., Evans, R., Gruchalla, R., Morgan, W., Stout, J., Adams, G. K., and Lippmann, M., “Acute respiratory health effects of air pollution on children with asthma in US inner cities,” Journal of Allergy and Clinical Immunology, Vol. 121, pp. 1133-1139, (2008).
26.Pan, J. N., and Chen, S. T., “Monitoring long-memory air quality data using ARFIMA model,” Environmetrics, Vol. 19, pp. 209-219, (2008).
27.Perez, P., “Combined model for PM10 forecasting in a large city,” Atmospheric Environment, Vol. 60, pp. 271-276, (2012).
28.Perez, P., and Reyes, J., “An integrated neural network model for PM10 forecasting,” Atmospheric Environment, Vol. 40, pp. 2845-2851, (2006).
29.Perez, P., and Salini, G., “PM2.5 forecasting in a large city: Comparison of three methods,” Atmospheric Environment, Vol. 42, pp. 8219-8224, (2008).
30.Pope, C. A., Burnett, R. T., Thun, M. J., Calle, E. E., Krewski, D., Ito, K., and Thurston, G. D., “Lung cancer, cardiopulmonary mortality, and long-term exposure to fine particulate air pollution, “ Journal of the American Medical Association, Vol. 287, pp. 1132-1141, (2002).
31.Silverman, R. A., and Ito, K., “Age-related association of fine particles and ozone with severe acute asthma in New York City,” Journal of Allergy and Clinical Immunology, Vol. 125, pp. 367-373, (2010).
32.Stadlober, E., Hörmann, S., and Pfeiler, B., “Quality and performance of a PM10 daily forecasting model,” Atmospheric Environment, Vol. 42, pp. 1098-1109, (2008).
33.Voukantsis, D., Karatzas, K., Kukkonen, J., Räsänen, T., Karppinen, A., and Kolehmainen, M., “Intercomparison of air quality data using principal component analysis, and forecasting of PM10 and PM2.5 concentrations using artificial neural networks, in Thessaloniki and Helsinki,” Science of the Total Environment, Vol. 409, pp. 1266-1276, (2011).
34.Yorifuji, T., Kawachi, I., Kaneda, M., Takao, S., Kashima, S., and Doi, H., “Diesel vehicle emission and death rates in Tokyo, Japan: A natural experiment,”Science of the Total Environment, Vol. 409, pp. 3620-3627, (2011).

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