請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97535完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 黃乾綱 | zh_TW |
| dc.contributor.advisor | Chien-Kang Huang | en |
| dc.contributor.author | 林子傑 | zh_TW |
| dc.contributor.author | Zih-Jie Lin | en |
| dc.date.accessioned | 2025-07-02T16:20:51Z | - |
| dc.date.available | 2025-07-03 | - |
| dc.date.copyright | 2025-07-02 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-06-16 | - |
| dc.identifier.citation | [1] 林冠廷. 運用兩階段資料探勘建構YouBike 站點需求量與還車量預測之研究. Thesis, 2018.
[2] Haoran Jie, Hetai Zou, and Qinneng Xu. Forecasting daily mrt passenger flow in taipei based on google search queries. In 2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC), pages 46–50. IEEE. [3] Billy M Williams and Lester A Hoel. Modeling and forecasting vehicular traffic flow as a seasonal arima process: Theoretical basis and empirical results. Journal of transportation engineering, 129(6):664–672, 2003. [4] You-Shyang Chen, Chien-Ku Lin, Su-Fen Chen, and Shang-Hung Chen. Two advanced models of the function of mrt public transportation in taipei. Electronics, 10(9):1048, 2021. [5] 温柏淳. 結合地理資訊系統與機器學習於公共自行車租賃站缺車預測—以臺北市YouBike 為例. Thesis, 2019. [6] 邱鉦懿. 以外掛式類神經網路預測區域YouBike 站點之租借量. Thesis, 2023. [7] 楊子瑢. 臺北市YouBike 共享單車車數預測系統之實作. Thesis, 2022. [8] 吳冠毅. 分類式支援向量迴歸結合粒子群演算法預測Youbike 車位及車輛數. Thesis, 2018. [9] Young-Seon Jeong, Young-Ji Byon, Manoel Mendonca Castro-Neto, and Said M Easa. Supervised weighting-online learning algorithm for short-term traffic flow prediction. IEEE Transactions on Intelligent Transportation Systems, 14(4):1700–1707, 2013. [10] Huaxiu Yao, Fei Wu, Jintao Ke, Xianfeng Tang, Yitian Jia, Siyu Lu, Pinghua Gong, Jieping Ye, and Zhenhui Li. Deep multi-view spatial-temporal network for taxi demand prediction. In Proceedings of the AAAI conference on artificial intelligence, volume 32. [11] Junbo Zhang, Yu Zheng, Dekang Qi, Ruiyuan Li, Xiuwen Yi, and Tianrui Li. Predicting citywide crowd flows using deep spatio-temporal residual networks. Artificial Intelligence, 259:147–166, 2018. [12] Shih-Hsiung Lee and Hsuan-Chih Ku. A dual attention-based recurrent neural network for short-term bike sharing usage demand prediction. IEEE Transactions on Intelligent Transportation Systems, 24(4):4621–4630, 2022. [13] Hsuan-Jui Chang and Jin-Tsong Jen. Comparing the prediction accuracy with passenger time series of taipei mrt under different deep rnns. In 2022 IET International Conference on Engineering Technologies and Applications (IET-ICETA), pages 1–2. IEEE. [14] Shengnan Guo, Youfang Lin, Ning Feng, Chao Song, and Huaiyu Wan. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 922–929. [15] Chao Song, Youfang Lin, Shengnan Guo, and Huaiyu Wan. Spatial-temporal synchronous graph convolutional networks: A new framework for spatial-temporal network data forecasting. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 914–921. [16] Mengzhang Li and Zhanxing Zhu. Spatial-temporal fusion graph neural networks for traffic flow forecasting. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 4189–4196. [17] K. Tian, J. Guo, K. Ye, and C. Z. Xu. St-mgat: Spatial-temporal multi-head graph attention networks for traffic forecasting. In 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI), pages 714–721. [18] Cheonbok Park, Chunggi Lee, Hyojin Bahng, Yunwon Tae, Kihwan Kim, Seungmin Jin, Sungahn Ko, and Jaegul Choo. St-grat: A novel spatio-temporal graph attention network for accurately forecasting dynamically changing road speed. arXiv e-prints, page arXiv:1911.13181, 2019. [19] Jiandong Bai, Jiawei Zhu, Yujiao Song, Ling Zhao, Zhixiang Hou, Ronghua Du, and Haifeng Li. A3t-gcn: Attention temporal graph convolutional network for traffic forecasting. ISPRS International Journal of Geo-Information, 10(7):485, 2021. [20] Junho Song, Jiwon Son, Dong-hyuk Seo, Kyungsik Han, Namhyuk Kim, and Sang-Wook Kim. St-gat: A spatio-temporal graph attention network for accurate traffic speed prediction. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pages 4500–4504. [21] Bing Yu, Haoteng Yin, and Zhanxing Zhu. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv preprint arXiv:1709.04875, 2017. [22] Lei Bai, Lina Yao, Salil Kanhere, Xianzhi Wang, and Quan Sheng. Stg2seq: Spatialtemporal graph to sequence model for multi-step passenger demand forecasting. arXiv preprint arXiv:1905.10069, 2019. [23] F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, and G. Monfardini. The graph neural network model. IEEE Transactions on Neural Networks, 20(1):61–80, 2009. [24] Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems, 29, 2016. [25] Zhengke Sun and Yuliang Ma. Ma2gcn: Multi adjacency relationship attention graph convolutional networks for traffic prediction using trajectory data. arXiv preprint arXiv:2401.08727, 2024. [26] Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, and Maosong Sun. Graph neural networks: A review of methods and applications. AI open, 1:57–81, 2020. [27] Pau Riba, Andreas Fischer, Josep Lladós, and Alicia Fornés. Learning graph distances with message passing neural networks. In 2018 24th International Conference on Pattern Recognition (ICPR), pages 2239–2244. IEEE. [28] Yujia Li, Chenjie Gu, Thomas Dullien, Oriol Vinyals, and Pushmeet Kohli. Graph matching networks for learning the similarity of graph structured objects. In International conference on machine learning, pages 3835–3845. PMLR. [29] Xiaotong Zhang, Han Liu, Qimai Li, and Xiao-Ming Wu. Attributed graph clustering via adaptive graph convolution. arXiv preprint arXiv:1906.01210, 2019. [30] Zhitao Ying, Jiaxuan You, Christopher Morris, Xiang Ren, Will Hamilton, and Jure Leskovec. Hierarchical graph representation learning with differentiable pooling. Advances in neural information processing systems, 31, 2018. [31] Hao Peng, Jianxin Li, Yu He, Yaopeng Liu, Mengjiao Bao, Lihong Wang, Yangqiu Song, and Qiang Yang. Large-scale hierarchical text classification with recursively regularized deep graph-cnn. In Proceedings of the 2018 world wide web conference, pages 1063–1072. [32] Liang Yao, Chengsheng Mao, and Yuan Luo. Graph convolutional networks for text classification. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 7370–7377. [33] Lei Bai, Lina Yao, Can Li, Xianzhi Wang, and Can Wang. Adaptive graph convolutional recurrent network for traffic forecasting. Advances in neural information processing systems, 33:17804–17815, 2020. [34] Bowen Wang and Jingsheng Wang. St-mgat:spatio-temporal multi-head graph attention network for traffic prediction. Physica A: Statistical Mechanics and its Applications, 603:127762, 2022. [35] Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017. [36] Shiyong Lan, Yitong Ma, Weikang Huang, Wenwu Wang, Hongyu Yang, and Pyang Li. Dstagnn: Dynamic spatial-temporal aware graph neural network for traffic flow forecasting. In International Conference on Machine Learning, pages 11906–11917. PMLR. [37] Bin Lu, Xiaoying Gan, Haiming Jin, Luoyi Fu, and Haisong Zhang. Spatiotemporal adaptive gated graph convolution network for urban traffic flow forecasting, 2020. [38] Chuanpan Zheng, Xiaoliang Fan, Cheng Wang, and Jianzhong Qi. Gman: A graph multi-attention network for traffic prediction. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 1234–1241. [39] Xue Ye, Shen Fang, Fang Sun, Chunxia Zhang, and Shiming Xiang. Meta graph transformer: A novel framework for spatial–temporal traffic prediction. Neurocomputing, 491:544–563, 2022. [40] Yanjie Wen, Zhihong Li, Xiaoyu Wang, and Wangtu Xu. Traffic demand prediction based on spatial-temporal guided multi graph sandwich-transformer. Information Sciences, 643:119269, 2023. [41] Huaiyu Wan, Shengnan Guo, Kang Yin, Xiaohui Liang, and Youfang Lin. Cts-lstm: Lstm-based neural networks for correlatedtime series prediction. Knowledge-Based Systems, 191:105239, 2020. [42] Junbo Zhang, Yu Zheng, and Dekang Qi. Deep spatio-temporal residual networks for citywide crowd flows prediction. In Proceedings of the AAAI conference on artificial intelligence, volume 31. [43] Bowen Du, Xiao Hu, Leilei Sun, Junming Liu, Yanan Qiao, and Weifeng Lv. Traffic demand prediction based on dynamic transition convolutional neural network. IEEE Transactions on Intelligent Transportation Systems, 22(2):1237–1247, 2020. [44] Y. Wang, J. Zheng, Y. Du, C. Huang, and P. Li. Traffic-ggnn: Predicting traffic flow via attentional spatial-temporal gated graph neural networks. IEEE Transactions on Intelligent Transportation Systems, 23(10):18423–18432, 2022. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97535 | - |
| dc.description.abstract | 交通運輸已成為現今社會生活中不可或缺的一部分，各國皆致力於發展大眾運輸與共享式載具，以減少交通壅塞並降低運輸成本。準確預測交通狀態有助於優化運輸規劃，提高交通效率。
近年來，許多研究利用圖神經網路（Graph Neural Network, GNN）來預測交通狀態，GNN 能夠同時捕捉時間與空間上的關聯性，為交通狀態預測帶來重大進展。然而，由於大眾運輸與共享式載具站點之間的關係高度動態，如何有效定義空間關係仍是一大挑戰，但現有的 GNN 模型尚未充分考慮空間關係的多樣性。 本研究提出多圖時空轉換器（Multi Graph Spatial Temporal Transformer，MGSTT），能夠有效捕捉不同空間關係下的特徵，並透過將外部因素轉換為嵌入，以提升模型的預測能力。實驗方面，本研究不僅使用常被用於評估的高速公路交通資料集，還自行收集台灣的大眾運輸與共享式交通資料集進行測試，藉此評估模型在不同類型交通數據上的適用性與廣泛性。 | zh_TW |
| dc.description.abstract | Nowadays, transportation has become a part of daily life in modern society. Many countries develop Transportation has become an essential part of modern society. Many countries are actively developing public transportation and shared mobility solutions to reduce traffic congestion and transportation costs. Accurate traffic state prediction plays a crucial role in optimizing transportation planning and improving efficiency.
In recent years, Graph Neural Networks (GNNs) have been widely used for traffic state prediction due to their ability to capture both spatial and temporal dependencies, leading to significant advancements in this field. However, public transportation and shared mobility systems exhibit highly dynamic relationships between stations, making it challenging to define spatial relationships effectively. Existing GNN-based models have yet to fully consider the diversity of spatial relationships, which limits their predictive performance. This study proposes the Multi Graph Spatial Temporal Transformer (MGSTT), which effectively captures features under various spatial relationships and enhances predictive performance by embedding external factors. In the experiments, in addition to using commonly adopted highway traffic datasets, this study also collects public transportation and shared mobility datasets from Taiwan to evaluate the model's adaptability and generalizability across different types of traffic data. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-07-02T16:20:51Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-07-02T16:20:51Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 致謝 II
摘要 III Abstract IV 目次 VI 圖目次 IX 表目次 XII 演算法目次 XV 第一章緒論 1 1.1 研究背景 1 1.2 研究動機 2 1.3 研究目標與貢獻 2 1.4 論文架構 3 第二章相關背景知識及文獻 5 2.1 交通狀態預測問題 5 2.2 圖神經網路 6 2.3 時空同步圖形卷積網路 7 2.4 時空融合圖形卷積網路 8 2.5 圖多重注意力網路 8 2.6 時空圖注意力網路 9 2.7 多圖空間注意力機制 10 2.8 整合外部因素 10 第三章研究方法13 3.1 實驗流程 13 3.2 建立關係圖 14 3.2.1 空間相鄰圖 14 3.2.2 流量連結圖 14 3.2.3 流量變化相似圖 14 3.2.4 流量分布相似圖 17 3.3 提出模型：多圖時空轉換器 19 3.3.1 強化特徵提取能力 20 3.3.2 替換空間嵌入 21 3.3.3 多圖空間注意力區塊 22 3.3.4 輸出層調整 22 3.3.5 改進測試機制 23 3.3.6 損失函數 24 第四章研究結果及討論 25 4.1 比較模型 25 4.2 實驗設置 25 4.3 評估指標(Mertic) 26 4.4 在高速公路資料集的比較 27 4.4.1 高速公路資料集—PEMS04、PEMS08 27 4.4.2 PEMS04 資料集的統計分析 32 4.4.3 PEMS08 資料集的統計分析 35 4.4.4 PEMS04 和PEMS08 資料集實驗結果 39 4.4.5 關係圖對PEMS04 和PEMS08 資料集預測結果的影響 41 4.4.6 時空嵌入對PEMS04 和PEMS08 資料集預測結果的影響 42 4.4.7 PEMS04 與PEMS08 資料集於不同預測時間間距下之結果分析 43 4.5 在大眾運輸和共享式交通的比較 49 4.5.1 大眾運輸資料集—MRT 49 4.5.2 MRT 資料集的統計分析 53 4.5.3 共享式交通資料集—Youbike 56 4.5.4 Youbike 資料集的統計分析 59 4.5.5 天氣資料 62 4.5.6 MRT 和Youbike 資料集實驗結果. 65 4.5.7 關係圖對MRT 和Youbike 資料集預測結果的影響 65 4.5.8 時空嵌入對MRT 和Youbike 資料集預測結果的影響 67 4.5.9 MRT 與YouBike 資料集於不同預測時間間距下之結果分析 68 4.5.10 MRT 案例分析 72 4.5.11 Youbike 案例分析 76 第五章結論與未來展望81 參考文獻82 附錄A — 不同預測時間間距之結果詳細資料89 A.1 PEMS04 車流量預測 89 A.2 PEMS04 車速預測 90 A.3 PEMS08 車流量預測 91 A.4 PEMS08 車速預測 92 A.5 MRT 人流量預測 93 A.6 Youbike 借出量預測 94 A.7 Youbike 還入量預測 95 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 圖神經網路 | zh_TW |
| dc.subject | 時空資料預測 | zh_TW |
| dc.subject | 交通資料預測 | zh_TW |
| dc.subject | 高速公路 | zh_TW |
| dc.subject | 大眾運輸 | zh_TW |
| dc.subject | 共享式交通 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | Shared Mobility | en |
| dc.subject | Deep Neural Network | en |
| dc.subject | Graph Neural Network | en |
| dc.subject | Spatial-Temporal Data Forecasting | en |
| dc.subject | Traffic Data Forecasting | en |
| dc.subject | Highway | en |
| dc.subject | Public Transportation | en |
| dc.title | 基於圖神經網路之城市交通狀態預測研究：以三種交通系統為例 | zh_TW |
| dc.title | Graph Neural Network Approach for Urban Traffic State Prediction: Three Transportation Systems Analysis | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 張瑞益;張恆華;張信宏 | zh_TW |
| dc.contributor.oralexamcommittee | Ray-I Chang;Herng-Hua Chang;Shin-Hung Chang | en |
| dc.subject.keyword | 深度學習,圖神經網路,時空資料預測,交通資料預測,高速公路,大眾運輸,共享式交通, | zh_TW |
| dc.subject.keyword | Deep Neural Network,Graph Neural Network,Spatial-Temporal Data Forecasting,Traffic Data Forecasting,Highway,Public Transportation,Shared Mobility, | en |
| dc.relation.page | 95 | - |
| dc.identifier.doi | 10.6342/NTU202501115 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2025-06-17 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 工程科學及海洋工程學系 | - |
| dc.date.embargo-lift | 2025-07-03 | - |
| 顯示於系所單位： | 工程科學及海洋工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf | 11.12 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。