空間資訊一直都是備受關注的議題，大量的學者應用不同的空間資訊在各種的層面上，例如市民生活行為、商業、旅遊等。但許多時候我們需要預測的空間資料其本身同時也會具有時間序列資訊。其中這類型資料又以大眾交通運輸工具為最大宗。交通運輸永遠是最為熱門的主題，交通直接反映了城市的發展，也是對於所有市民生活中不能缺少的元素，因此大量的學者致力研究交通相關的主題，當中最為人熟悉包含路段車流量預測、交通路線規劃、計程車共乘安排、交通事故預測等等。而現今網路之發達，網路更可以反應出一個地點的熱門程度，進而影響到一個地點內交通工具的流通量。本篇論文的目的就是同時考量時間、空間與網路上的資訊，針對公共運輸系統做出流量預測。運用時間與空間資訊搭配網路聲量，進而輔助我們的預測。後續提供了實驗數據，顯示我們可以將站點依照特性分群並預測出借用量。除此之外，也能發現時間資訊、空間資訊與網路聲量與借用量的相關性。

Spatial data is crucial to the analysis of a wide range of phenomena, from behavioral patterns to business opportunities. However, much of the spatial data required for predictions varies over time (i.e., time-series data). This problem is particularly evident when dealing with issues related to public transportation, such as the forecasting of traffic flow, planning traffic routes, and organizing taxi sharing systems.
In the current study, we used statistics related to internet usage as a proxy by which to determine the number of individuals in specific areas at specific times in order to chart changes in those values and thereby characterize movement patterns. Our objective was to enhance the efficiency of public transportation systems by considering spatial data as well as network volume data. In experiments, we identified correlations between temporal data, spatial data, network usage, and rental volumes. The proposed system also proved highly effective in the grouping of bicycle rental stations based on spatial characteristics, as well as predicting rental volumes based on temporal fluctuations in usage behavior.

[1] Y. Lv, Y. Duan, W. Kang, Z. Li, F.-Y. Wang, “Traffic Flow Prediction With Big Data: A Deep Learning Approach,” IEEE Transaction on Intelligent Transportation Systems, vol. 16, no. 2, pp. 865-873, 2015.
[2] H. Yu, Z. Wu, S. Wang, Y. Wang, X. Ma, “Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks,” Sensors, vol. 17, pp.1051, 2017.
[3] J. Jiang, F. Lin, J. Fan, H. Lv, J. Wu, “A destination prediction network based on spatiotemporal data for bike sharing,” Complexity, 2019.
[4] J. Carvalho, M. Marques, J.P. Costeira, “Understanding people flow in transportation hubs,” IEEE Transaction on Intelligent Transportation Systems, vol. 19, no. 10, pp. 1-10, 2018.
[5] E. Come and O. Latifa, “Model-Based Count Series Clustering for Bike Sharing System Usage Mining: A Case Study with the Velib’ System of Paris,” ACM Transactions on Intelligent Systems and Technology, vol. 5, no. 3, pp. 1–21, 2014.
[6] Y. Li, Y. Zheng, H. Zhang, and L. Chen, “Traffic prediction in a bike-sharing system,” in Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM, Seattle, WA, USA, 2015.
[7] K. Higashiyama, Y. Fujimoto, and Y. Hayashi, “Feature extraction of numerical weather prediction results toward reliable wind power prediction,” in 2017 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), pp. 1–6, Sept. 2017.
[8] R. Sevlian and R. Rajagopal, "Detection and statistics of wind power ramps," in IEEE Transactions on Power Systems, vol. 28, no. 4, pp. 3610-3620, Nov. 2013.
[9] S. S. Soman, H. Zareipour, O. Malik, and P. Mandal, "A review of wind power and wind speed forecasting methods with different time horizons," North American Power Symposium 2010, Arlington, TX, pp. 1-8, 2010.
[10] S. Lin, J. Li, L. Zhang, Y. Lu, “Precipitation prediction in ShenZhen city based on WNN,” in 14th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) Conference, 2017.
[11] C. Y. Chang, T. H. Woo, S. F. Wang, M. J. Kuo, “Survey and Analysis of Walking Speeds for the Elderly and Children at Crosswalks”, in Urban Traffic, vol. 25, no. 1, 2010
[12] C. Kunjumon, S. S. Nair, D. S. S, L.P. Suresh, P. S. L, “Survey on Weather Forecasting Using Data Mining,” in IEEE Conference on Emerging Devices and Smart Systems. 2018.
[13] P. Lv and L. Yue, “Short-term wind speed forecasting based on non-stationary time series analysis and ARCH model,” in Proc. Int. Conf. Multimedia Technol., pp. 2549–2553, 2011.
[14] S. Kothapalli and S. G. Totad, “A real-time weather forecasting and analysis,” IEEE Int. Conf. Power, Control. Signals Instrum. Eng. ICPCSI 2017, pp. 1567-1570, 2018.
[15] X. Chao, “Research on Logistics Facilities Location Based on GIS”, 2nd International Conference on Data Science and Business Analytics. 2018
[16] M. Eames, T. Kershaw, D. Coley, “The Appropriate Spatial Resolution of Future Weather Files for Building Simulation.” Journal of Building Performance Simulation, vol.5, no. 6, pp. 347–358, 2011.
[17] J. Lin, H. Wan, Y, Cui, “Analyzing the spatial factors related to the distributions of building heights in urban areas: A comparative case study in Guangzhou and Shenzhen,” Sustainable Cities and Society,52 (2020) 101854.
[18] K. A. Schmid, C. Frey, F. Peng, M. Weiler, A. Züfle, L. Chen, M. Renz, “TrendTracker: Modelling the Motion of Trends in Space and Time,” 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW), pp. 1145-1152, 2016.
[19] D. S. Sundar and M. Kankanala, “Analyzing and Predicting Lifetime of Trends Using Social Networks,” In International Conference on Computer Communication and Informatics (ICCCI), 2015.
[20] Z. Doshi, S. Nadkarni, K. Ajmera, and N. Shah, “TweerAnalyzer: Twitter Trend Detection and Visualization,” in 2017 International Conference on Computing, Communication, Control and Automation (ICCUBEA), pp. 1-6, 2017.
[21] L. Song, S. Pang, I. Longley, G. Olivares, A. Sarrafzadeh, “Spatio-temporal PM2.5 prediction by spatial data aided incremental support vector regression,” in Proceedings of the 2014 International Joint Conference on Neural Networks (IJCNN), pp. 623–630, Beijing, China, 6–11 July 2014.
[22] C. W. J. Granger, “Investigating Causal Relations by Econometric Models and CrossSpectral Methods,” Econometrica, vol. 37, no. 3, pp. 424-38, July 1969.
[23] K. He, X. Zhang, S. Ren, and J. Sun. “Deep residual learning for image recognition,” In Conference on Computer Vision and Pattern Recognition, 2016.
[24] J. Zhang, Y. Zheng, and D. Qi, “Deep spatio-temporal residual networks for citywide crowd flows prediction,” in Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence., pp. 1655–1661, 2017.
[25] P. K. Simpson, “Fuzzy min-max neural networks—Part I: Classification,” IEEE Trans. Neural Networks, vol. 3, pp. 776–786, Sept. 1992.
[26] J. Wang, “Fault diagnosis of underwater vehicle with fnn.” In 2012 10th world congress on intelligent control and automation (WCICA), pp. 2931–2934, 2012.
[27] Y. Chen, H. Fan, B. Xu, Z. Yan, Y. Kalantidis, M. Rohrbach, S. Yan, and J. Feng, “Drop an Octave: Reducing spatial redundancy in convolutional neural networks with octave convolution,’’arXiv:1904.05049, Apr. 2019.
[28] S. Zhao, S. Lin, J. Xu, “Time Series Traffic Prediction via Hybrid Neural Networks,” in IEEE Intelligent Transportation Systems Conference (ITSC), 2019.
[29] L. Breiman, “Random forests,” Mach. Learn., pp. 5–32, 2001.
[30] M. Pal, “Random forest classifier for remote sensing classification,” Int. J. Remote Sens. vol. 26, pp.217-222, 2015.
[31] J. Sexton and P. Laake. “Standard errors for bagged and random forest estimators,” Computational Statistics and Data Analysis, vol. 53, no. 3, pp. 801-811, 2009.
[32] N. S. Altman. “An introduction to kernel and nearest-neighbor nonparametric regression.” The American Statistician, vol. 46, no. 3, pp.175-185, 1992.
[33] K. Fukunaga and P. M. Narendra, “A Branch and Bound Algorithm for Computing k-Nearest Neighbors,” in IEEE Transactions on Computers, vol. C-24, no. 7, pp. 750-753, July 1975.
[34] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagation errors,” Nature, vol. 323, pp. 533-536, 1986.
[35] J. Lin, T. Chen, Q. Han, “Simulating and Predicting the Impacts of Light Rail Transit Systems on Urban Land Use by Using Cellular Automata: A Case Study of Dongguan, China,” Sustainability, vol. 10, pp. 1293, 2018.
[36] Z. Y. Hou ,W. X. Lu, S. M. Chen, “Research on precipitation prediction based on WNN”, Water saving irrigation, vol. 3, pp. 31-34, 2012.
[37] H. Khodadadi, S. E. Razavi, “A comparison between neural networks and wavelet networks in nonlinear system identification,” Research Journal of Applied Sciences, Engineering and Technology, 2012.
[38] Z. Zhan, M. Xu and S. Xu, “Predicting Cyber Attack Rates With Extreme Values,” in IEEE Transactions on Information Forensics and Security, vol. 10, no. 8, pp. 1666-1677, Aug. 2015,
[39] N. Ranjan, S. Bhandari, H. P. Zhao, H. Kim and P. Khan, “City-Wide Traffic Congestion Prediction Based on CNN, LSTM and Transpose CNN,” in IEEE Access, vol. 8, pp. 81606-81620, 2020.
[40] C. Song, H. Lee, C. Kang, W. Lee, Y. B. Kim and S. W. Cha, “Traffic speed prediction under weekday using convolutional neural networks concepts,” 2017 IEEE Intelligent Vehicles Symposium (IV), Los Angeles, CA, pp. 1293-1298, 2017.
[41] D. B. Nelson, “ARCH models as diffusion approximations,” Journal of Econometrics, vol. 45, pp. 7-38, 1990.
[42] M. Sharma, L. Mathew, S. Chatterji, “Weather Forecasting using Soft Computing and Statistical Techniques,” IJAREEIE, vol.3 , issue 7, pp.11285-11290, 2014.
[43] B. Priambodo and Y. Jumaryadi, “Time Series Traffic Speed Prediction Using k-Nearest Neighbour Based on Similar Traffic Data,” MATEC Web Conf., vol. 218, pp. 3021, 2018.
[44] S. H. Hosseini, B. Moshiri, A. Rahimi-Kian and B. N. Araabi, “Traffic speed prediction using mutual information,” 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), Montreal, QC, 2012, pp. 1-4.
[45] N. Garg, K. Soni, T.K. Saxena, S. Maji, “Applications of AutoRegressive Integrated Moving Average (ARIMA) approach in time-series prediction of traffic noise pollution,” Noise Control Engineering Journal, vol. 63, pp. 182-194, 2015.
[46] T. Alghamdi, K. Elgazzar, M. Bayoumi, T. Sharaf and S. Shah, “Forecasting Traffic Congestion Using ARIMA Modeling,” 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC), Tangier, Morocco, 2019, pp. 1227-1232.
[47] D. Xu, Y. Wang, L. Jia et al. “Real-time road traffic state prediction based on ARIMA and Kalman filter,” Frontiers Inf Technol Electronic Eng, vol. 18, pp. 287–302, 2017.
[48] J. F. Li and Z. Qun, “The Forecasting of the Elevator Traffic Flow Time Series Based on ARIMA and GP,” Advanced Materials Research, vol. 588–589, pp. 1466–1471, 2012.
[49] M. Raeesi et al. “Traffic Time Series Forecasting by Feedforward Neural Network: a Case Study Based on Traffic Data of Monroe.” International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (ISPRS), pp. 219-223, 2014.
[50] N. Gabdrakhmanova and A. Gabdrakhmanov, “Neural Network Models of Time Series of Network Traffic Intensities,” Procedia Computer Science, vol. 103, pp. 483-488, 2017.
[51] S. Hochreiter, J. Schmidhuber. “Long short-term memory”, Neural Computation, vol. 9, no. 8, pp. 1735, 1997.
[52] R. S. Tomar, S. V. and G. S. Tomar, “SVM Base Trajectory Predictions for Lane Changing Vehicles,” in IEEE International Conference on Computational Intelligence and Communication Networks, pp. 716-721, 2011.
[53] L. Vanajakshi and L. Rilett, “Support vector machine technique for the short term prediction of travel time,” in Proc. IEEE Intell. Veh. Symp., pp. 600–605, 2017.
[54] P. Cortez, L.M. Matos, P.J. Pereira, N. Santos, D. Duque, “Forecasting Store Foot Traffic Using Facial Recognition, Time Series and Support Vector Machines,” SOCO-CISIS-ICEUTE, pp.267-276, 2016.
[55] F. Wen, G. Zhang, L. Sun, X. Wang, X. Xu, “A Hybrid Temporal Association Rules Mining method for Traffic Congestion Prediction.” Computers & Industrial Engineering, vol. 130, pp. 779-787, 2019.
[56] M. perumal and B. Velumani, “Design and development of a Spatial DBSCAN Clustering framework for location prediction- An optimization approach,” 2018 3rd International Conference on Communication and Electronics Systems (ICCES), Coimbatore, India, pp. 942-947, 2018.
[57] C.Qiu, H. Xu, Y. Bao, “Modified-DBSCAN Clustering for Identifying Traffic Accident Prone Locations,” International Conference on Intelligent Data Engineering and Automated Learning, vol. 9937, pp. 99-105, 2016.
[58] S. Yu, Y. Li, G. Sheng, J. Lv, “Research on Short-Term Traffic Flow Forecasting Based on KNN and Discrete Event Simulation,” International Conference on Advanced Data Mining and Applications, vol. 11888, pp. 853-862, 2019.
[59] X. Luo, D. Li, Y. Yang, S. Zhang, “Spatiotemporal traffic flow prediction with KNN and LSTM,” Journal of Advanced Transportation, 2019.
[60] P. Raktrakulthum and C. Netramai, “Vehicle Classification in Congested Traffic Based on 3D Point Cloud using SVM and KNN,” in 9th International Conference on Information Technology and Electrical Engineering (ICITEE), Phuket, Thailand, pp. 1-6, 2017.
[61] “CWB Observation Data Inquire System,” https://e-service.cwb.gov.tw/HistoryDataQuery/
[62] “Open Street Map,” https://www.openstreetmap.org/.
[63] “Google Trends,” https://trends.google.com/trends.