簡易檢索 / 詳目顯示

回結果列表
研究生： 陳柏全
Po-Chaun Chen
論文名稱： 利用循環類神經網路實現公共自行車各站台需求預測之研究
Using Recurrent Neural Networks to Predict Station Level Demand in a Bike Sharing System
指導教授： 呂政修
Jenq-Shiou Leu
口試委員: 石維寬
Wei-Kuan Shih
孫敏德
Min-Te Sun
陳維美
Wei-Mei Chen　
鄭欣明
Shin-Ming Cheng
學位類別： 碩士
Master
系所名稱： 電資學院 - 電子工程系
Department of Electronic and Computer Engineering
論文出版年： 2016
畢業學年度： 104
語文別： 英文
論文頁數： 44
中文關鍵詞： Bike Sharing System 、Demand Prediction 、Station Level Prediction 、Machine Learning 、Deep Learning 、Recurrent Neural Networks 、Bi-directional RNN 、Soft Attention Mechanism
外文關鍵詞： Bike Sharing System, Demand Prediction, Station Level Prediction, Machine Learning, Deep Learning, Recurrent Neural Networks, Bi-directional RNN, Soft Attention Mechanism
相關次數： 點閱：395  下載：4 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • Bike sharing systems have been widely applied to many cities and bringing convenience to their local citizens for short-term transportation. One of the biggest challenges in bike sharing systems is the bike rebalancing problem due to the unbalance of bikes distribution. In this thesis, we focus on station level prediction for each bike station. We propose four architectures based on recurrent neural networks and use only one model to predict both rental and return demand for every station at once which is very efficiency for online rebalance strategies used. Without taking the global level bike distribution into consideration, the MAPE/RMSLE of the sum over the demand of each station may be too high for rebalance strategies used even the MAE/RMSE are satisfied at station level. Our evaluation shows that the propose methods achieve not only satisfied results at station level, but also at global level on New York Citi Bike dataset.

    Bike sharing systems have been widely applied to many cities and bringing convenience to their local citizens for short-term transportation. One of the biggest challenges in bike sharing systems is the bike rebalancing problem due to the unbalance of bikes distribution. In this thesis, we focus on station level prediction for each bike station. We propose four architectures based on recurrent neural networks and use only one model to predict both rental and return demand for every station at once which is very efficiency for online rebalance strategies used. Without taking the global level bike distribution into consideration, the MAPE/RMSLE of the sum over the demand of each station may be too high for rebalance strategies used even the MAE/RMSE are satisfied at station level. Our evaluation shows that the propose methods achieve not only satisfied results at station level, but also at global level on New York Citi Bike dataset.

    Abstract I 誌謝 II List of Figures V List of Tables VII 1 Introduction 1 2 Related Works 3 2.1 System Design 3 2.2 System Pattern 3 2.3 System Prediction 4 2.4 System Operation 4 3 Neural Networks 5 3.1 Linear Layer 6 3.2 Activation Function 8 3.3 Loss Function 9 3.4 Backpropagation 10 3.5 Optimizer 12 3.5.1 Gradient Descent 12 3.5.2 Mini-batch Stochastic Gradient Descent 12 3.5.3 Adagrad 13 3.5.4 Rmsprop 13 3.5.5 Adam 14 3.6 Regularization 14 3.7 Dropout 15 4 Recurrent Neural Networks 16 4.1 Backpropagation Through Time 17 4.2 Vanishing Gradient Problem 17 4.3 Long Short-Term Memory 17 4.4 Gated Recurrent Units 18 5 Data Exploration 20 5.1 Data Attributes and Basic Analysis 20 5.2 Distribution of Trip Duration 22 5.3 Patterns in Days of the Week 23 5.4 Relationship between Weather and Bike Demand 24 6 Proposed Methods 27 6.1 Data Preprocessing 27 6.2 Loss Function 29 6.3 Proposed Architectures 29 6.3.1 Architecture One 29 6.3.2 Architecture Two 30 6.3.3 Architecture Three 30 6.3.4 Architecture Four 31 7 Evaluation 32 7.1 Settings of Proposed Architectures 32 7.2 Baseline Approaches 32 7.3 Evaluation Metrics 33 7.4 Results 33 8 Conclusion 37 Appendix 38 Bibliography 41

    [1] Peter Midgley. "Bicycle-sharing schemes: enhancing sustainable mobility in urban areas." United Nations, Department of Economic and Social Affairs (2011): 1-12.
    [2] Janet Larsen. "Bike-sharing programs hit the streets in over 500 cities worldwide." Earth Policy Institute 25 (2013): 1.
    [3] Citi Bike. New York City Bike Sharing System Data. https://www.citibikenyc.com/system-data
    [4] Rahul Nair, Elise Miller-Hooks, Robert C. Hampshire, and Ana Busic´. "Large-scale vehicle sharing systems: analysis of Vélib'." International Journal of Sustainable Transportation 7.1 (2013): 85-106.
    [5] Amada M Burden, and Richard Barth. "Bike-Share Opportunities in New York City." Department of City Planning, New York (2009).
    [6] LDA Consulting Washington. "2013 Capital Bike-share Member Survey Report." Technical Report 202, 2013.
    [7] Ahmadreza Faghih-Imani, Naveen Eluru, Ahmed M. El-Geneidy, Michael Rabbat, Usama Haq. "How land-use and urban form impact bicycle flows: evidence from the bicycle-sharing system (BIXI) in Montreal." Journal of Transport Geography 41 (2014): 306-314.
    [8] Luigi Dell'Olio, Angel Ibeas, and Jose Luis Moura. "Implementing bike-sharing systems." Proceedings of the Institution of Civil Engineers-Municipal Engineer. Vol. 164. No. 2. Thomas Telford Ltd, 2011.
    [9] Luis M. Martinez, Luís Caetano, Tomás Eiró, Francisco Cruz. "An optimisation algorithm to establish the location of stations of a mixed fleet biking system: an application to the city of Lisbon." Procedia-Social and Behavioral Sciences 54 (2012): 513-524.
    [10] V. Prem Kumar and Michel Bierlaire. "Optimizing locations for a vehicle sharing system." Swiss Transport Research Conference.(Cited on pages 2, 8, and 24.). 2012.
    [11] Jenn-Rong Lin, and Ta-Hui Yang. "Strategic design of public bicycle sharing systems with service level constraints." Transportation research part E: logistics and transportation review 47.2 (2011): 284-294.
    [12] Longbiao Chen, Daqing Zhang, Gang Pan, Xiaojuan Ma, Dingqi Yang, Kostadin Kushlev, Wangsheng Zhang, Shijian Li. "Bike sharing station placement leveraging heterogeneous urban open data." Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. ACM, 2015.
    [13] Juan Carlos García-Palomares, Javier Gutiérrez, and Marta Latorre. "Optimizing the location of stations in bike-sharing programs: a GIS approach." Applied Geography 35.1 (2012): 235-246.
    [14] Alicia Bargar, et al. "Interactive visual analytics for multi-city bikeshare data analysis." Proc. of. 2014.
    [15] Patrick Vogel, Torsten Greiser, and Dirk Christian Mattfeld. "Understanding bike-sharing systems using data mining: Exploring activity patterns." Procedia-Social and Behavioral Sciences 20 (2011): 514-523.
    [16] Pierre Borgnat, C´eline Robardet, Patrice Abry, Patrick Flandrin, Jean-Baptiste Rouquier, and Nicolas Tremblay. "A dynamical network view of lyon’s vélo’v shared bicycle system." Dynamics On and Of Complex Networks, Volume 2. Springer New York, 2013. 267-284.
    [17] Jon Froehlich, Joachim Neumann, and Nuria Oliver. "Sensing and Predicting the Pulse of the City through Shared Bicycling." IJCAI. Vol. 9. 2009.
    [18] Andreas Kaltenbrunner, Rodrigo Meza, Jens Grivolla, Joan Codina, Rafael Banchs. "Urban cycles and mobility patterns: Exploring and predicting trends in a bicycle-based public transport system." Pervasive and Mobile Computing 6.4 (2010): 455-466.
    [19] Ji Won Yoon, Fabio Pinelli, and Francesco Calabrese. "Cityride: a predictive bike sharing journey advisor." 2012 IEEE 13th International Conference on Mobile Data Management. IEEE, 2012.
    [20] Patrick Vogel, and Dirk C. Mattfeld. "Strategic and operational planning of bike-sharing systems by data mining–a case study." International Conference on Computational Logistics. Springer Berlin Heidelberg, 2011.
    [21] Pierre Borgnat, C´eline Robardet, Jean-Baptiste Rouquier, Patrice Abry, Patrick Flandrin, Eric Fleury. "Shared bicycles in a city: A signal processing and data analysis perspective." Advances in Complex Systems 14.03 (2011): 415-438.
    [22] Yexin Li, Yu Zheng, Huichu Zhang, Lei Chen. "Traffic prediction in a bike-sharing system." Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems. ACM, 2015.
    [23] Zidong Yang, Ji Hu, Yuanchao Shu, Peng Cheng, Jiming Chen, Thomas M. “Mobility Modeling and Prediction in Bike-Sharing Systems” ACM MobiSys. 2016
    [24] Jiawei Zhang, Xiao Pan, Moyin Li, Philip S. Yu. "Bicycle-Sharing System Analysis and Trip Prediction." arXiv preprint arXiv:1604.00664 (2016).
    [25] Raviv Tal, Michal Tzur, and Iris A. Forma. "Static repositioning in a bike-sharing system: models and solution approaches." EURO Journal on Transportation and Logistics 2.3 (2013): 187-229..
    [26] Claudio Contardo, Catherine Morency, and Louis-Martin Rousseau. Balancing a dynamic public bike-sharing system. Vol. 4. Cirrelt, 2012.
    [27] Mike Benchimol, Pascal Benchimol, Benoふıt Chappert, Arnaud de la Taille, Fabien Laroche, Fred´ eric Meunier ´ and Ludovic Robinet. "Balancing the stations of a self service “bike hire” system." RAIRO-Operations Research 45.1 (2011): 37-61.
    [28] Daniel Chemla, Frédéric Meunier, and Roberto Wolfler-Calvo. "Balancing a bike-sharing system with multiple vehicles." Proceedings of Congress annual de la société Française de recherche opérationelle et d’aidea la décision, ROADEF2011, Saint-Etienne, France. 2011.
    [29] Jasper Schuijbroek, Robert Hampshire, and Willem-Jan van Hoeve. "Inventory rebalancing and vehicle routing in bike sharing systems." (2013).
    [30] Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012.
    [31] Le, Quoc V. "Building high-level features using large scale unsupervised learning." 2013 IEEE international conference on acoustics, speech and signal processing. IEEE, 2013.
    [32] David Silver , Aja Huang *, Chris J. Maddison , Arthur Guez , Laurent Sifre , George van den Driessche , Julian Schrittwieser , Ioannis Antonoglou , Veda Panneershelvam , Marc Lanctot , Sander Dieleman , Dominik Grewe , John Nham , Nal Kalchbrenner , Ilya Sutskever , Timothy Lillicrap , Madeleine Leach , Koray Kavukcuoglu , Thore Graepel & Demis Hassabis "Mastering the game of Go with deep neural networks and tree search." Nature 529.7587 (2016): 484-489.
    [33] Xavier Glorot and Yoshua Bengio. "Understanding the difficulty of training deep feedforward neural networks." Aistats. Vol. 9. 2010.
    [34] Mart´ın Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Jozefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenberg, Dan Mane, Rajat Monga, Sherry Moore, Derek Murray, ´ Chris Olah, Mike Schuster, Jonathon Shlens, Benoit Steiner, Ilya Sutskever, Kunal Talwar, Paul Tucker, Vincent Vanhoucke, Vijay Vasudevan, Fernanda Viegas, Oriol Vinyals, ´ Pete Warden, Martin Wattenberg, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. "Tensorflow: Large-scale machine learning on heterogeneous distributed systems." arXiv preprint arXiv:1603.04467 (2016).
    [35] Vinod Nair, and Geoffrey Hinton. "Rectified linear units improve restricted boltzmann machines." Proceedings of the 27th International Conference on Machine Learning (ICML-10). 2010.
    [36] John Duchi, Elad Hazan, and Yoram Singer. "Adaptive subgradient methods for online learning and stochastic optimization." Journal of Machine Learning Research 12.Jul (2011): 2121-2159.
    [37] Tijmen Tieleman, and Geoffrey Hinton. "Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude." COURSERA: Neural Networks for Machine Learning 4.2 (2012).
    [38] Diederik Kingma, and Jimmy Ba. "Adam: A method for stochastic optimization." arXiv preprint arXiv:1412.6980 (2014).
    [39] Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. "Dropout: a simple way to prevent neural networks from overfitting." Journal of Machine Learning Research 15.1 (2014): 1929-1958.
    [40] Paul J. Werbos. "Backpropagation through time: what it does and how to do it." Proceedings of the IEEE 78.10 (1990): 1550-1560.
    [41] Yoshua Bengio, Patrice Simard, and Paolo Frasconi. "Learning long-term dependencies with gradient descent is difficult." IEEE transactions on neural networks 5.2 (1994): 157-166.
    [42] Sepp Hochreiter, and Jürgen Schmidhuber. "Long short-term memory." Neural computation 9.8 (1997): 1735-1780.
    [43] Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, Yoshua Bengio. "Empirical evaluation of gated recurrent neural networks on sequence modeling." arXiv preprint arXiv:1412.3555 (2014).
    [44] YouBike. Taipei City Bike Sharing System Data.
    http://data.taipei/opendata/datalist/datasetMeta?oid=8ef1626a-892a-4218-8344-f7ac46e1aa48
    [45] Alex Graves. "Generating sequences with recurrent neural networks." arXiv preprint arXiv:1308.0850 (2013).
    [46] Mike Schuster, and Kuldip K. Paliwal. "Bidirectional recurrent neural networks." IEEE Transactions on Signal Processing 45.11 (1997): 2673-2681.
    [47] Leo Breiman. "Random forests." Machine learning 45.1 (2001): 5-32.

    QR CODE