本研究主要目的是利用偵測器時/空資料插補遺漏值，嘗試找出一最佳遺漏值插補組合與績效。首先在空間上採單一偵測器與累積偵測器輸入兩種模式，取上游、下游與上下游三種方式進行空間插補，藉此建立一個最佳的空間插補範圍。接著在時間上分為無待插補偵測器資料與含待插補偵測器資料兩種模式，將歷史資料以單一時間、累積時間與移動平均時間三種資料型態進行時間插補，最後經由插補績效評估得到一最佳時/空插補組合。本研究在分析插補績效前，先利用K-means把偵測器資料分群再以回饋式類神經網路針對流量、速率與占有率進行插補遺漏值的實證分析。結果發現：以流量插補，取上下游累積至第6組偵測器含自我資料的前20分鐘平均歷史資料，可以獲得最佳插補績效；以速率插補，取上下游累積至第7組偵測器含自我資料的前20分鐘平均歷史資料，可以獲得最佳插補績效；以占有率插補，取上下游累積至第6組偵測器含自我資料的前15分鐘平均歷史資料，可以獲得最佳插補績效。

The main purpose of this study is the use of detector temporal/spatial data to imput missing values, try to find a best combination and the performance of missing value imputation. At first, in spatial we adopted two modes：single detector datas and accumulation detector datas imputing miss values, and then get three spatial imputatiol ways:upstream, downstream,upstream and downstream detector, to establish an optimal range of spatial imputation. After that, in temporal we assign two modes:non-include interpolated detector data mode and include interpolated detector data mode, and we handled the historical data to a single time interval, accumulated time intervals and time interval moving average of three data types for temporal imputation, the final to get a performance evaluation by the best combination of temporal/spatial imputation.In this study, before analysis the imputation performance, we using K-means method to cluster detector datas, then the information(flow,speed and occupancy) using recurrent neural network to imput missing values and analysis.
The results showed that:the flow of imputation, taking the upstream and downstream cumulative detectors to no.6 set with self-information the 20 minutes ago mean historical datas could get the best imputation performance; the speed of imputation, taking the upstream and downstream cumulative detectors to no.7 set with self-information the 20 minutes ago mean historical datas could get the best imputation performance; the occupancy of imputation, taking the upstream and downstream cumulative detectors to no.6 set with self-information the 15 minutes ago mean historical datas could get the best imputation performance.

1. 陳立信譯，「變異數分析」，初版，華泰書局，1997。
2. 黃俊英，「多變量分析」，七版，翰蘆圖書，2000。
3. 吳啓聰譯，「商用統計學－入門與應用」，初版，美商麥格羅希爾，2002。
4. 黃文龍、黃龍，「統計學」，初版，滄海書局，2004。
5. 石村貞夫、陳耀茂，「變異數分析入門」，初版，鼎茂圖書，2004。
6. 林惠玲、陳正倉，「應用統計學」，四版，雙葉書廊，2009。
7. 林昇甫、洪成安，「神經網路入門與圖樣辨識」，三版，全華科技圖書，2002。
8. 羅華強，「類神經網路－MATLAB的應用」，初版，清蔚科技股份有限公司，2001。
9. 牛田一雄、高井勉、木暮大輔，「資料採礦利用Clementine使用手冊」，初版，鼎茂圖書，2006。
10. 張云濤、龔玲，「資料探勘原理與技術」，初版，五南圖書，2007。
11. 廖述賢、溫志皓，「資料採礦與商業智慧」，初版，雙葉書廊，2009。
12. 張斐章、張麗秋，「類神經網路導論：原理與應用」，初版，滄海書局，2010。
13. 林茂文，「時間數列分析與預測」，三版，華泰文化，2006。
14. 張堂賢、黃宏仁，「車輛偵測器資料遺失之在線插補技術研究」，運輸學刊，第二十卷第四期，頁377-404，2008。
15. 廖梓淋，「利用資料填補概念探討車輛偵測器佈設間距」，國立中央大學土木工程學系研究所碩士論文，2009。
16. 吳冠宏、吳信宏、郭廣洋，「應用分群技術於交通事故資料分析」，品質學報，第十三卷第三期，頁305-312，2006。
17. 張慶麟，「應用自動車輛辨識預測高速公路路段旅行時間」，國立中央大學土木工程學系研究所碩士論文，2003。
18. Brian L. Smith, William T. Scherer, James H. Conklin,“Exploring Imputation Techniques for Missing Data in Transportation Management Systems”, Transportation Research Board, Vol. 1836, pp. 132-142, 2003.
19. Chen, D., Muller, S. G., Mussone, L. and Montgomey, F. , “A Study of Hybrid Neural Network Approaches and the Effects of Missing Data on Traffic Forecasting,” Neural Computing & Applications, pp. 277-286, 2001.
20. Chen, C., Kwon, J., Rice, J., Skabardonis, A. and Varaiya, P. , “Detecting Errors And Imputing Missing Data For Single Loop Surveillance Systems,” Transportation Research Board January, Washington, D.C, 2002.
21. Delurgio, S. A., Forecasting principles and applications, McGraw-Hill, 1998.
22. Gold, D. L., Turner, S. M., Gajewski, B. J. and Spiegelman, C., “Imputing Missing Values In ITS Data Archives For Intervals Under 5 Minutes,” Transportation Research Board 80th Annual Meeting January 7-11, Washington, D.C, 2001.
23. Huang, X. L. and Zhu, Q. M., “A Pseudo-nearest-neighbor Approach For Missing Data Recovery On Gaussian Random Data Sets,” Pattern Recognition Letters , Vol.23, pp. 1613-1622, 2002.
24. Huang, C. C. and Lee, H. M., “A Grey-based Nearest Neighbor Approach For Missing Attribute Value Prediction,” Applied Intelligent, Vol.20, No.3, pp. 239-252, 2004.
25. Li Qu, Li Li, Yi Zhang, Jianming Hu,“PPCA-Based Missing Data Imputation for Traffic Flow Volume: A Systematical Approach”, IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, Vol. 10, No. 3, pp. 512-522, 2009.
26. Mei Chen, Jingxin Xia, Rongfang Liu,“Developing a Strategy for Imputing Missing Traffic Volume Data”, JOURNAL of the TRANSPORTATION RESEARCH FORUM, Vol. 45, No. 3, pp. 57-76, 2006.
27. Manoel Castro-Neto, Young-Seon Jeong, Myong-Kee Jeong, Lee D. Han, “Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions”, Expert Systems with Applications, Vol. 36, Issue. 3, Part 2, pp.6164-6173, 2009.
28. Satish Sharma, Pawan Lingras, Ming Zhong,“Effect of Missing Value Imputations on Traffic Parameters Estimations from Permanent Traffic Counts”, Transportation Research Board the 82nd Annual Meeting, 2003.
29. Wen, Y. H., Lee, T. T. and Cho, H. T., “Missing Data Treatment And Data Fusion Toward Travel Time Estimation For ATIS,” Journal of the Eastern Asia Society for Transportation Studies, Vol.6, pp. 2546-2560, 2005.
30. Yang Zhang, Yuncai Liu ,“Missing Traffic Flow Data Prediction using Least Squares Support Vector Machines in Urban Arterial Streets”, IEEE Symposium on Computational Intelligence and Data Mining, pp. 76-83, 2009.
31. Zhong, M., Lingras, P. and Sharma, S., “Estimation of missing traffic counts using factor, genetic, neural, and regression techniques,” Transportation Research Part C, No.12, pp. 139-166, 2004.
32. Zhaobin Liu, Satish Sharma, Sandeep Datla,“Imputation of Missing Traffic Data during Holiday Periods”, Transportation Planning and Technology, Vol. 31, No. 5, pp. 525-544, 2008.