隨著經濟發展，私有車輛數量逐漸龐大，交通預測成為一個重要議題。其重要性在推動智慧城市、智慧運輸系統（ITS）等相關政策中佔有一席之地。除此之外，在這個網路發達、人手一機的時代，許多人在日常生活中高度仰賴路徑規劃、行車時間預估等服務，而準確的交通預測能強化這些服務的功能。在過往的交通預測相關研究中，使用圖神經網路（GNN）方法的表現較為突出。不過多數研究使用的是同質圖，它們將會影響交通的因素皆視為道路的屬性，而忽略了因素之間可能會相互作用並對交通產生影響。因此，在本研究中，我們利用Uber的車速資料、天氣資料與交通事件資料，將路段與事件視為兩種類型的節點而形成異質圖，並用異質圖訓練圖神經網路以進行交通預測。透過本研究，我們期望能藉由加入事件之間的影響，做出更準確的交通預測。

Traffic prediction plays a significant role in policies related to smart cities, intelligent transportation systems, and other initiatives. Furthermore, accurate traffic prediction can improve traffic services such as route planning and estimation of traveling time. In previous research of traffic prediction, Graph Neural Networks (GNN) have shown remarkable performance. However, those studies utilized homogeneous graphs, considering only historical traffic while neglecting factors like events and weather that can also influence traffic speed.
Therefore, we utilize Uber Movement’s dataset of speeds, weather data, and traffic incident data and employ a heterogeneous graph to train a Heterogeneous Graph Neural Network for traffic prediction. We hope to achieve precise traffic prediction by incorporating the interactions between different events.

第一章 緒論 1
第二章 文獻探討 5
第三章 研究方法 11
第四章 實驗結果 17
第五章 結論 21

[1] 全國首創！北市府推「台北市智慧城市產業場域實驗試辦計畫」 廣邀民間提案打造永續宜居城市, https://doit.gov.taipei/News_Content.aspx?n=4B2B1AB4B23E7EA8&sms=72544237BBE4C5F6&s=65BA107A61D25B3C, retrieved on 2022/12/30.
[2] 台北智慧城市專案辦公室, https://smartcity.taipei/?lang=zh-Hant, retrieved on 2022/12/30.
[3] Q. Xie, T. Guo, Y. Chen, Y. Xiao, X. Wang, and B.Y. Zhao, “"How do urban incidents affect traffic speed?" A Deep Graph Convolutional Network for Incident-driven Traffic Speed Prediction,” ArXiv abs/1912.01242 ,2019
[4] F. Rodrigues, I. Markou, and F.C. Pereira, “Combining time-series and textual data for taxi demand prediction in event areas: A deep learning approach,” Information Fusion. 49, C (Sep 2019), 120–129. https://doi.org/10.1016/j.inffus.2018.07.007
[5] S. Shekhar, and B. M. Williams, “Adaptive seasonal time series models for forecasting short-term traffic flow,” Transportation Research Record, pp. 116–125, 2007.
[6] B. Pan, U. Demiryurek, and C. Shahabi, "Utilizing Real-World Transportation Data for Accurate Traffic Prediction," in Proc. 2012 IEEE 12th International Conference on Data Mining, 2012, pp. 595-604, doi: 10.1109/ICDM.2012.52.
[7] M. Lippi, M. Bertini, and P. Frasconi, "Short-Term Traffic Flow Forecasting: An Experimental Comparison of Time-Series Analysis and Supervised Learning," IEEE Transactions on Intelligent Transportation Systems, vol. 14, no. 2, pp. 871-882, June 2013, doi: 10.1109/TITS.2013.2247040.
[8] B. Yu, H. Yin, and Z. Zhu, “Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting,” in Proc. the 27th International Joint Conference on Artificial Intelligence, 2018, pp. 3634–3640.
[9] W. Jiang, and L. Zhang, "Geospatial data to images: A deep-learning framework for traffic forecasting," Tsinghua Science and Technology, vol. 24, no. 1, pp. 52-64, Feb. 2019, doi: 10.26599/TST.2018.9010033.
[10] M. Zhang, Y. Li, F. Sun, D. Guo, and P. Hui, "Adaptive Spatio-Temporal Convolutional Network for Traffic Prediction," in Proc. 2021 IEEE International Conference on Data Mining (ICDM), 2021, pp. 1475-1480, doi: 10.1109/ICDM51629.2021.00191.
[11] M. A. Ali, S. Venkatesan, V. Liang, and H. Kruppa, "TEST-GCN: Topologically Enhanced Spatial-Temporal Graph Convolutional Networks for Traffic Forecasting," 2021 IEEE International Conference on Data Mining, 2021, pp. 982-987, doi: 10.1109/ICDM51629.2021.00110.
[12] S. Yang, J. Liu, and K. Zhao, "Space Meets Time: Local Spacetime Neural Network For Traffic Flow Forecasting," 2021 IEEE International Conference on Data Mining, 2021, pp. 817-826, doi: 10.1109/ICDM51629.2021.00093.
[13] W. Liao, B. Zeng, J. Liu, J. Liu, P. Wei, and X. Cheng, “Taxi demand forecasting based on the temporal multimodal information fusion graph neural network,” Applied Intelligence 52, 12077–12090, 2022.
[14] F. Scarselli, M. Gori, AC. Tsoi, M. Hagenbuchner, and G. Monfardini, “The graph neural network model,” IEEE Transactions on Neural Networks 2009 Jan;20(1):61-80. doi: 10.1109/TNN.2008.2005605. Epub 2008 Dec 9. PMID: 19068426.
[15] C. Gallicchio and A. Micheli, "Graph Echo State Networks," in Proc. The 2010 International Joint Conference on Neural Networks, 2010, pp. 1-8, doi: 10.1109/IJCNN.2010.5596796.
[16] Y. Li, D. Tarlow, M. Brockschmidt, and R. Zemel, “Gated graph sequence neural networks,” in Proc. International Conference on Learning Representations, 2015.
[17] H. Dai, Z. Kozareva, B. Dai, A. Smola, and L. Song, “Learning steadystates of iterative algorithms over graphs,” in Proc. International Conference on Machine Learning, 2018, pp.1114–1122.
[18] J. Bruna, W. Zaremba, A. Szlam, and Y. LeCun, “Spectral networks and locally connected networks on graphs,” in Proc. International Conference on Learning Representations, 2014.
[19] R. Li, S. Wang, F. Zhu, and J. Huang, “Adaptive graph convolutional neural networks,” in Proc. The National Conference on Artificial Intelligence, 2018, pp. 3546–3553.
[20] A. Micheli, "Neural Network for Graphs: A Contextual Constructive Approach," IEEE Transactions on Neural Networks, vol. 20, no. 3, pp. 498-511, March 2009, doi: 10.1109/TNN.2008.2010350.
[21] P. Velickovic, G. Cucurull, A. Casanova, A. Romero, P. Lio, and Y. Bengio, “Graph attention networks,” in Proc. International Conference on Learning Representations, 2017.
[22] D. Wang, P. Cui, and W. Zhu, “Structural deep network embedding,” in Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '16), 2016, pp. 1225–1234.
[23] T. N. Kipf and M. Welling, “Variational graph auto-encoders,” NIPS Workshop on Bayesian Deep Learning, 2016.
[24] Y. Li, O. Vinyals, C. Dyer, R. Pascanu, and P. Battaglia, “Learning deep generative models of graphs,” in Proc. International Conference on Machine Learning, 2018.
[25] J. You, R. Ying, X. Ren, W. L. Hamilton, and J. Leskovec, “Graphrnn: A deep generative model for graphs,” in Proc. International Conference on Machine Learning, 2018.
[26] Y. Li, R. Yu, C. Shahabi, and Y. Liu, “Diffusion convolutional recurrent neural network: Data-driven traffic forecasting,” in Proc. International Conference on Learning Representations, 2018.
[27] A. Jain, A. R. Zamir, S. Savarese, and A. Saxena, “Structural-rnn: Deep learning on spatio-temporal graphs,” in Proc. Computer Vision and Pattern Recognition Conference, 2016, pp. 5308–5317.
[28] B. Yu, H. Yin, and Z. Zhu, “Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting,” in Proc. International Joint Conference on Artificial Intelligence, 2018, pp. 3634–3640.
[29] Z. Wu, S. Pan, G. Long, J. Jiang, and C. Zhang, “Graph wavenet for deep spatial-temporal graph modeling,” in Proc. International Joint Conference on Artificial Intelligence, 2019.
[30] L. Bai, L. Yao, C. Li, X. Wang, and C. Wang,” Adaptive graph convolutional recurrent network for traffic forecasting,” in Proc. Advances in Neural Information Processing Systems, 2020
[31] T. Bogaerts, A. D. Masegosa, J. S. Angarita-Zapata, E. Onieva, and P. Hellinckx, “A graph cnn-lstm neural network for short and long-term traffic forecasting based on trajectory data,” Transportation Research Part C:Emerging Technologies, 112 , 2020, 62–77.
[32] C. Zhang, C. Song, C. Huang, A. Swami, and N. V. Chawla, “Heterogeneous Graph Neural Network,” in Proc. the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD ’19, 2019 doi:10.1145/3292500.3330961
[33] Uber Movement, https://movement.uber.com, retrieved on 2023/1/2.
[34] overpass turbo, https://overpass-turbo.eu/, retrieved on 2023/6/11.
[35] Weather Spark, https://weatherspark.com, retrieved on 2023/1/2.
[36] NYC OpenData Motor Vehicle Collisions - Crashes, https://data.cityofnewyork.us/Public-Safety/Motor-Vehicle-Collisions-Crashes/h9gi-nx95, retrieved on 2023/2/19.
[37] Lewis, C. D., “Industrial and business forecasting methods : a practical guide to exponential smoothing and curve fitting.”
[38] E. Chaerun Nisa and Y-D. Kuan, “Comparative Assessment to Predict and Forecast Water-Cooled Chiller Power Consumption Using Machine Learning and Deep Learning Algorithms,” Sustainability. 2021; 13(2):744. https://doi.org/10.3390/su13020744