應用手機信令資料預測觀光景點拜訪人數

APPLYING CELLULAR-BASED VEHICLE PROBE DATA TO PREDICT NUMBER OF VISITORS AT ATTRACTIONS

盧宗成(Chung-Cheng Lu)；梁竣凱(Jyun-Kai Liang)；曲平(Ping Cyu)；王晉元(Jin-Yuan Wang)；吳東凌(Tung-Ling Wu)；陳翔捷(Siang-Jie Chen)

信令資料 ； 旅次鏈 ； 旅次起迄矩陣 ； 馬可夫鏈 ； 觀光景點拜訪人次 ； cellular-based vehicle probe data ； trip chain ； origin-destination (OD) matrix ； Markov Chain ； number of visitors at attractions

運輸計劃季刊

50卷2期（2021 / 06 / 30）

145 - 176

繁體中文

了解遊客在觀光景點間的移動行為與景點的拜訪人次，對於改善觀光地區公共運輸服務與觀光管理當局之資源配置具有極大助益。隨著科技發展的日新月異，以及人們使用手機行動上網的普及率提升，在人口移動預測上，手機信令資料有著樣本數量大、涵蓋範圍廣且蒐集成本相對低廉的優點。手機信令資料分析可以有效建構使用者的時空軌跡，進而得到使用者在景點間潛在的移動型態。本研究建立一套有系統的景點拜訪人數預測方法，首先透過分析使用者的信令資料建立旅次鏈與旅次起迄矩陣，作為景點間轉移矩陣推估的基礎，再利用馬可夫鏈預測每小時觀光景點拜訪人次。本研究以花蓮縣作為研究場域，以交通部觀光局推薦的59個主要觀光景點為對象，透過由電信公司取得觀光客的信令資料，評估所提出預測方法的績效。結果顯示預測之平均絕對百分比誤差約為20%，屬於實務上可接受的範圍，表示本研究之預測方法具有不錯的成效。

Understanding the movement of tourists between attractions and the number of visitors at attractions is helpful for the authorities to improve the public transportation services in scenic areas and to allocate resources. With the rapid development of technology and the increasing popularity of people using mobile phones to access the Internet, cellular-based vehicle probe (CVP) data has the advantages of larger sample size, broader coverage and lower collection cost in human mobility prediction. Users' spatial-temporal trajectories can be effectively constructed by analyzing CVP data. The potential movement pattern of users can be extracted from those trajectories. This study develops a systematic approach to predict the number of visitors at attractions. Firstly, trip chains and origin-destination (OD) matrix are constructed by analyzing users' CVP data. The OD matrix is used as the basis for estimating the transition matrix between attractions. Then, a Markov Chain model is established to predict the number of tourists at each attraction in each hour. The proposed method is applied to predict the numbers of tourists at 59 major attractions, recommended by the Tourism Bureau, in Hualien county. The CVP data is provided by a major telecom in Taiwan. The mean absolute percentage error of the prediction results is about 20%, which is practically acceptable. The evaluation results indicate that the proposed method has a good prediction performance.

1. 臺北大眾捷運股份有限公司，https://www.metro.taipei/，2020。
2. 交通部觀光局觀光統計資料庫，https://stat.taiwan.net.tw/，2020。
3. 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.
4. Almannaa, M.,Elhenawy, M.,Rakha, H.(2019).Identifying Optimum Bike Station Initial Conditions using Markov Chains Modeling.Transport Findings
5. Ashbrook, D.,Starner, T.(2003).Using GPS To Learn Significant Locations And Predict Movement Across Multiple Users.Personal and Ubiquitous Computing,7(5),275-286.
6. Demissie, M. G.,Phithakkitnukoon, S.,Sukhvibul, T.,Antunes, F.,Gomes, R.,Bento, C.(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.
7. Gambs, S.,Killijian, M. O.,del Prado Cortez, M. N.(2012).Next Place Prediction using Mobility Markov Chains.MPM '12：Proceedings of the First Workshop on Measurement, Privacy, and Mobility
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. Jiang, J.,Pan, C.,Liu, H.,Yang, G.(2016).Predicting Human Mobility based on location data modeled by Markov chains.Ubiquitous Positioning, Indoor Navigation and Location Based Services (UPINLBS), 2016 Fourth International Conference
10. Li, W.,Cheng, X.,Duan, Z.,Yang, D.,Guo, G.(2014).A Framework For Spatial Interaction Analysis Based On Large-Scale Mobile Phone Data.Computational intelligence and neuroscience,2014,1-11.
11. Ma, J.,Li, H.,Yuan, F.,Bauer, T.(2013).Deriving Operational Origin-Destination Matrices From Large Scale Mobile Phone Data.International Journal of Transportation Science and Technology,2(3),183-204.
12. Mathivaruni, R. V.,Vaidehi, V.(2008).An Activity Based Mobility Prediction Strategy Using Markov Modeling for Wireless Networks.Proceedings of the World Congress on Engineering and Computer Science
13. Norris, J. R.(1998).Markov chains.Cambridge:Cambridge university press.
14. Qian, C.,Li, W.,Yang, D.,Ran, B.,Li, F.(2019).Measuring Spatial Distribution of Tourist Flows Based on Cellular Signalling Data：A Case Study of Shangha.2019 IEEE Intelligent Transpodation Systems Conference (ITSC),Auckland, New Zealand:
15. Xia, J. C.,Zeephongsekul, P.,Arrowsmith, C.(2009).Modelling Spatio-Temporal Movement of Tourists Using Finite Markov Chains.Mathematics and Computers in Simulation,79(5),1544-1553.
16. Ying, L.,Baorui, H.,Yimin, L.(2015).Bus Scheduling Feasibility Study of Rainy Day Based on the Mobile Phone Signal Data.2015 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS),Halong Bay, Vietnam:
17. 王以萱(2018)。交通大學運輸與物流管理學系。
18. 交通部運輸研究所(2018).旅運時空資料分析與公共運輸服務應用發展計畫.
19. 邱裕鈞,謝志偉(2016)。應用行動通訊資料於道路交通資訊之蒐集與分析。中華民國運輸學會 105 年年會暨學術論文國際研討會論文集
20. 施冠毅(2018)。交通大學運輸與物流管理學系。
21. 洪琮博(2017)。交通大學運輸與物流管理學系。

1. 賴威宇,黃怡婷,陳逸瑄,陳怡升,林昭邑,王鴻龍,賴威宇,黃怡婷,陳逸瑄,陳怡升,林昭邑,王鴻龍(2023)。運用電信資料推估靜態人口參數之研究。中國統計學報，61(2)，152-177。