手機信令資料探勘於改善觀光旅客公共運輸服務之研究－以花蓮縣臺灣好行路線為例

IMPROVING PUBLIC TRANSPORTATION SERVICES FOR TOURISTS BY MINING CELLULAR-BASED VEHICLE PROBE DATA - A CASE STUDY OF TAIWAN TOURIST SHUTTLE IN HUALIEN COUNTY

王晉元(Jin-Yuan Wang)；盧宗成(Chung-Cheng Lu)；李晟豪(Cheng-Hao Li)；陳其華(Chi-Hwa Chen)；吳東凌(Tung-Ling Wu)；陳翔捷(Siang-Jie Chen)

信令資料 ； 大數據 ； 公共運輸 ； 觀光管理 ； 資料探勘 ； Cellular-based vehicle probe data ； Big data ； Public transportation ； Tourism management ； Data mining

運輸計劃季刊

48卷2期（2019 / 06 / 30）

105 - 131

繁體中文

花蓮縣豐富的生態資源、多元的族群文化特色，每年皆吸引眾多的國內外觀光客前往旅遊，但是由於對外交通不便，仰賴臺鐵東部幹線提供有限的公共運輸服務，縣內公共運輸亦不發達，導致外來觀光客在花蓮旅遊時大多以自行開車或是租賃車輛的方式在縣內觀光。目前交通部觀光局提供兩條臺灣好行路線服務花蓮地區的遊客，然而這兩條路線是否能滿足多數前往花蓮地區旅遊觀光客的公共運輸需求是個值得探討的議題。為了了解花蓮地區觀光旅客的潛在公共運輸需求，本研究利用資料探勘方法，分析花蓮地區觀光旅客的手機信令資料，比較潛在公共運輸旅客的觀光旅運需求樣態，以及現有兩條臺灣好行路線，找出服務缺口，並提出改善建議。從資料探勘結果發現，文化創意產業園區吸引相當多的遊客，但是臺灣好行路線並未經過這個景點，如果臺灣好行路線能夠繞駛，將能滿足超過八成以上潛在公共運輸旅客的觀光旅運需求。本研究結果可協助主管單位檢視當前的觀光公共運輸服務是否符合旅客的需求，進而對既有路線進行新增站點等相關改善措施。

Characterized by its rich natural resources and diverse cultures of different ethnic groups, Hualien county has attracted many domestic and foreign tourists. However, most tourists travel by driving their own cars or rental cars in Hualien, because public transportation access to the county relies merely on the limited capacity provided by the Eastern Line of Taiwan Railway; the transit service inside the county is also inconvenient. Although the Tourism Bureau of MOTC provides two Taiwan Tourist Shuttle routes servicing tourists in Hualien, it remains a topic worth of investigation whether or not the public transportation demand of tourists in Huanlein can be satisfied by these two routes. In order to explore tourists' potential demand of public transportation in Hualien, this study utilizes data miniming techniques to analyze Cellular-based Vehicle Probe data of the tourists in Hualien. We compare the travel demand patterns of potential public transportation users with the two Taiwan Tourist Shuttle routes in Hualien. The service gaps are identified and improvement suggestions are proposed accordingly. The data mining results reveal that Hualien Cultural Creative Industries Park is a popular scenic spot, but it is not covered by the two Taiwan Tourist Shuttle routes. Had the routes included this spot, more than 80% of the potential public transportation demand of the touirsts can be satisfied. The findings of this study can assist the authorities to examine whether or not existing tourist transit services are able to meet tourists' demands and to provide suggestions to improve the services, such as adding new stops to the existing routes.

1. Ahas, R.,Aasa, A.,Silm, S.,Tiru, M.(2007).Mobile Positioning Data in Tourism Studies and Monitoring: Case Study in Tartu, Estonia.Information and Communication Technologies in Tourism 2007,Vienna:
2. Alexander, L.,Jiang, S.,Murga, M.,González, M. C.(2015).Origin-Destination Trips by Purpose and Time of Day Inferred from Mobile Phone Data.Transportation Research Part C: Emerging Technologies,58,240-250.
3. Bekhor, S.,Cohen, Y.,Solomon, C.(2013).Evaluating Long-Distance Travel Patterns in Israel by Tracking Cellular Phone Positions.Journal of Advanced Transportation,47,435-446.
4. Chen, Q.,Hu, Z.,Su, H.,Tang, X.,Yu, K.(2018).Understanding Travel Patterns of Tourists from Mobile Phone Data: A Case Study in Hainan.2018 IEEE International Conference on Big Data and Smart Computing
5. Demissie, M. G.,Phithakkitnukoon, S.,Sukhvibul, T.,Francisco, A.,Rui, G.,Carlos, B.(2016).Inferring Passenger Travel Demand to Improve Urban Mobility in Developing Countries Using Cell Phone Data: A Case Study of Senegal.IEEE Transactions on Intelligent Transportation Systems,17(9),2466-2478.
6. Holleczek, T.,Anh, D. T.,Yin, S.,Jin, Y.,Antonatos, S.,Goh, H. L.,Low, S.,ShiNash, A.(2015).Traffic Measurement and Route Recommendation System for Mass Rapid Transit (MRT).KDD '15 Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,New York:
7. Holleczek, T.,Yu, L.,Lee, J. K.,Senn, O.,Ratti, C.,Jaillet, P.(2014).Detecting Weak Public Transport Connections from Cellphone and Public Transport Data.Proceedings of the Third ASE International Conference on Big Data Science and Computing (BigDataScience 2014),Beijing, China:
8. Iqbal, M. S.,Choudhury, C. F.,Wang, P.,González, M. C.(2014).Development of Origin-Destination Matrices Using Mobile Phone Call Data.Transportation Research Part C: Emerging Technologies,40,63-74.
9. Mamei, M.,Colonna M.(2018).Analysis of Tourist Classification from Cellular Network Data.Journal of Location Based Services,12(1),19-39.
10. Trasarti, R.,Olteanu-Raimond, A-M.,Nanni, M.,Couronné, T.,Furletti, B.,Giannotti, F.,Smoreda, Z.,Ziemlicki, C.(2015).Discovering Urban and Country Dynamics from Mobile Phone Data with Spatial Correlation Patterns.Telecommunications Policy,39,347-362.
11. 交通部運輸研究所(2017).旅運時空資料分析與公共運輸服務應用發展計畫.
12. 國家發展委員會，106 年持有手機民眾數位機會調查報告，民國 106 年。

1. 簡佑勳,盧宗成,陳翔捷,周翔淳,吳東凌(2023)。多元交通行動服務使用者之套票購買行為分析－以高雄市MaaS系統為例。運輸計劃季刊，52(3)，161-190。
2. 蘇昭銘,吳冠廷(2023)。運用改良基因演算法求解時間窗越野尋蹤問題及應用於自助旅遊路線規劃。運輸學刊，35(2)，193-225。