簡易檢索 / 詳目顯示

回結果列表
研究生： 陳昱任
Chen, Yu-Ren
論文名稱： 運用CGAN產生未來時刻人流分布
Simulate Crowd Flow Distribution via Conditional Generative Adversarial Network
指導教授： 李強
Lee, Chiang
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年： 2021
畢業學年度： 109
語文別： 英文
論文頁數： 58
中文關鍵詞： 時空間資料庫 、人流資料 、條件生成式對抗模型
外文關鍵詞： Spatio-Temporal Database, Crowd Flow Dataset, Conditional Generative Adversarial Network
相關次數： 點閱：153  下載：0 
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

    • 在災害防治的領域中，未來時刻人流分布是相當有價值的，這是因為這些模擬的人流分布提供在未來可能發生的樣式，所以我們就能夠針對災害做出預防性的分析，或是強化發生災害後的反應能力。為此，我們提出Crowd Flow Conditional Generative Adversarial Network(CF-CGAN)來解決這項問題，該模型能夠提供未來於特定時間下的基礎人流分布，並且，我們針對訓練資料進行多項前處理來增加生成人流分布的品質與多樣性。在實驗中，我們統計生成人流分布於各個數值區間的比例來量化其品質，並且，我們討論生成資料是否符合真實世界的情況，最後，結果證明我們的模型能夠提供有價值的人流分布於模擬情境。

    In the field of disaster protection, future crowd flow distribution is valuable. This is because these simulated crowd flow distributions provide patterns that may occur in the future. Thus, we can make a preventive analysis of specific events and strengthen the ability to react to them. We propose the Crowd Flow Conditional Generative Adversarial Network (CF-CGAN) to generate simulated crowd flow distribution and it can provide the basic crowd flow distribution at a specific time in the future. We also propose three preprocessing on the training data to improve the effect. In the experiment, we statistic the proportion of the generated crowd flow distribution in each numerical interval to quantify. And, we discuss whether the generated data conforms to the real-world situation. Finally, the results prove that our model can provide valuable data in the simulated situation.

    摘 要 i Abstract ii Acknowledgments iii Outline iv List of Tables vi List of Figures vii 1 Introduction 1 2 Related Work 7 2.1. Research for Crowd Flow Data 7 2.1.1. The prediction of the short-term crowd flows distribution 7 2.1.2. The prediction of the human-mobility trajectory 8 2.1.3. The statistics of the crowd number 8 2.2. Spatio-Temporal Prediction Model 9 2.2.1. ST-ResNet 9 2.3. Research for Generative Adversarial Network 11 2.3.1. Generative Adversarial Network 11 2.3.2. Conditional Generative Adversarial Network 13 2.4. Application of Spatio-Temporal Data with CNN 14 2.4.1. Classification Task 15 2.4.2. Anomaly Detection Task 15 3 Definition and Dataset 17 3.1. Definition 17 3.2. An Example of the Proposed Work 18 3.3. Crowd Flow Dataset 18 4 Algorithm 20 4.1. System Framework 20 4.2. Dataset Scale Transform 21 4.3. Space-SMOTE 23 4.4. Normalization Slicing 26 4.5. Training Model 28 4.5.1. Crowd Flow Conditional Generative Adversarial Network 28 4.5.2. Loss Function 29 4.5.2.1. Adversarial Loss 29 4.5.2.2. Condition Classification Loss 29 4.5.2.3. Pixel-Wise Loss 30 4.5.3. Discriminator architecture 32 4.5.3.1. CONV(Convolution Layer) 33 5.3.2. MaxPool(MaxPool Layer) 34 4.5.3.3. LeakyRELU 34 4.5.3.4. BN(Batch Normalization Layer)[5] 35 4.5.3.5. FC(Fully Connect Layer) 36 4.5.4. Generator architecture 36 4.5.4.1. UPCONV(Transpose Convolution Layer) 37 4.5.4.2. Residual Connection 38 5 Experiment 39 5.1. Quantitative Analysis Process 39 5.2. Training 40 5.3. A discussion of parameter of sub-experiments 40 5.3.1. Group 1 41 5.3.2. Group 2 42 5.3.3 Group 3 43 5.4. Conditional GAN 44 5.4.1. Quantitative Analysis for Conditional GAN 45 5.4.2. Qualitative Analysis for Conditional GAN 45 6 Conclusion 52 References 54

    J. Yuan, Y. Zheng, C. Zhang, W. Xie, X. Xie, G. Sun, and Y. Huang, “T-drive: driving directions based on taxi trajectories,” In Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, GIS '10, 2010, pp. 99.
    I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” in Proc. Adv. Neural Inf. Process. Syst., 2014, pp. 2672-2680.
    M. Mirza and S. Osindero, “Conditional Generative Adversarial Nets,” 2014, arXiv: 1411.1784.
    C. Zhang, H. Li, X. Wang and X. Yang, “Cross-scene Crowd Counting via Deep Convolutional Neural Networks,” in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 833-841, doi: 10.1109/CVPR.2015.7298684.
    S. Ioffe and C. Szegedy, “Batch normalization: accelerating deep network training by reducing internal covariate shift,” in ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning, 2015, pp. 448-456.
    K. He, X. Zhang, S. Ren and J. Sun, “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778, doi: 10.1109/CVPR.2016.90.
    J. Zhang, Y. Zheng, D. Qi, R. Li, and X. Yi, “DNN-based prediction model for spatio-temporal data,” in Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, 2016, pp. 1-4.
    L. Boominathan, S. S Kruthiventi and R. Venkatesh Babu, “CrowdNet: A Deep Convolutional Network for Dense Crowd Counting,” in MM '16: Proceedings of the 24th ACM International conference on Multimedia, 2016, pp. 640-644.
    O. Mogren, “C-RNN-GAN Continuous recurrent neural networks with adversarial training,” in Proc. Constructive Mach. Learn. Workshop NIPS, Dec. 2016, pp. 1-6.
    Y. Liu, E. Racah, Prabhat, J. Correa, A. Khosrowshahi, D. Lavers, K. Kunkel, M. Wehner, and W. Collins, “Application of deep convolutional neural networks for detecting extreme weather in climate datasets,” 2016, arXiv:1605.01156.
    A. Odena, C. Olah and J. B Shlens, “Conditional Image Synthesis with Auxiliary Classifier GANs,” in ICML '17: Proceeding of the 34th International Conference on Machine Learning, 2017, pp. 2642-2651.
    . Esteban, S. L. Hyland, and G. Rätsch, “Real-valued (medical) time series generation with recurrent conditional GANs,” Jun. 2017.
    D. Babu Sam, S. Surya and R. Venkatesh Babu, “Switching Convolutional Neural Network for Crowd Counting,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 5744-5752.
    E. Racah, C. Beckham, T. Maharaj, S. E. Kahou, M. Prabhat, and C. Pal, “Extremeweather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events,” In Advances in Neural Information Processing Systems, 2017, pp. 3402-3413.
    J. Y. Zhu, T. Park, P. Isola, and A. A. Efros, ‘‘Unpaired image-to-image translation using cycle-consistent adversarial networks,’’ in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2017, pp. 2242–2251.
    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, 2017, pp. 1655-1661.
    N. C. Dvornek, P. Ventola, K. A. Pelphrey, and J. S. Duncan, “Identifying autism from resting-state fmri using long short-term memory networks,” In International Workshop on Machine Learning in Medical Imaging, 2017, pp. 362-370.
    P. Isola, J. Y. Zhu, T. Zhou and, A. A. Efros, “Image-to-image translation with conditional adversarial networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 5967–5976.
    R. J. Meszlenyi, K. Buza, and Z. Vidny ´ anszky, “Resting state fmri ´ functional connectivity-based classification using a convolutional neural network architecture,” Frontiers in neuroinformatics, 2017.
    S. Korolev, A. Safiullin, M. Belyaev, and Y. Dodonova, “Residual and plain convolutional neural networks for 3d brain mri classification,” In Biomedical Imaging (ISBI 2017), 2017 IEEE 14th International Symposium on, 2017, pp. 835-838.
    S. Kim, S. Ames, J. Lee, C. Zhang, A. C. Wilson, and D. Williams, “Resolution reconstruction of climate data with pixel recursive model,” In Data Mining Workshops (ICDMW), 2017 IEEE International Conference on, 2017, pp. 313-321.
    X. Guo, K. C. Dominick, A. A. Minai, H. Li, C. A. Erickson, and L. J. Lu, “Diagnosing autism spectrum disorder from brain restingstate functional connectivity patterns using a deep neural network with a novel feature selection method,” Frontiers in neuroscience, 2017.
    Z. Chu, Y. Cheng, S. Zhai, Z. Sun, Y.Liu, “Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Records,” In IEEE International Conference on Data Mining(ICDM). IEEE, 2017, pp 787-792.
    A. S. Heinsfeld, A. R. Franco, R. C. Craddock, A. Buchweitz, and F. Meneguzzi, “Identification of autism spectrum disorder using deep learning and the abide dataset,” NeuroImage: Clinical, vol. 17, 2018, pp. 16-23.
    C. Zhang, S. R. Kuppannagari, R. Kannan, and V. K. Prasanna, “Generative Adversarial Network for Synthetic Time Series Data Generation in Smart Grids,” 2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), Aalborg, 2018, pp. 1-6, doi: 10.1109/SmartGridComm.2018.8587464.
    D. Wen, Z. Wei, Y. Zhou, G. Li, X. Zhang, and W. Han, “Deep learning methods to process fmri data and their application in the diagnosis of cognitive impairment: A brief overview and our opinion,” Frontiers in neuroinformatics, 2018.
    H. Yao, F. Wu, J. Ke, X. Tang, Y. Jia, S. Lu, P. Gong, J. Ye, and Z. Li, “Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction,” in Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018, pp. 2588-2595.
    K.Ouyang, R. Shokri, D. S.Rosenblum and W. Yang, “A Non-Parametric Generative Model for Human Trajectories,” in IJCAI '18: Proceedings of the 27th International Joint Conference on Artificial Intelligence, 2018, pp.3812-3817.
    K. G. Hartmann, R. T. Schirrmeister, and T. Ball, “EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signals,” 2018, arXiv:1806.01875.
    M. Yin, M. Sheehan, S. Feygin, J. Paiement and A. Pozdnoukhov, “A Generative Model of Urban Activities from Cellular Data,” in IEEE Transactions on Intelligent Transportation Systems, vol. 19, no. 6, pp. 1682-1696, June 2018, doi: 10.1109/TITS.2017.2695438.
    Y. Zhao, Q. Dong, S. Zhang, W. Zhang, H. Chen, X. Jiang, L. Guo, X. Hu, J. Han, and T. Liu, “Automatic recognition of fmri-derived functional networks using 3-d convolutional neural networks,” IEEE Transactions on Biomedical Engineering, vol. 65, no. 9, pp. 1975-1984, 2018.
    Y. Liang, S. Ke, J. Zhang, X. Yi, and Y. Zheng, “Geoman: Multilevel attention networks for geo-sensory time series prediction,” in IJCAI '18: Proceedings of the 27th International Joint Conference on Artificial Intelligence, 2018, pp. 3428–3434.
    D. Saxena and J. Cao, “D-GAN: Deep Generative Adversarial Nets for Spatio-Temporal Prediction,” 2019, arXiv: 1907.08556.
    H. Yu, X. Chen, Z. Li, G. Zhang, P. Liu, J. Yang, and Y. Yang, “Taxi-Based Mobility Demand Formulation and Prediction Using Conditional Generative Adversarial Network-Driven Learning Approaches” in IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 10, 2019, pp. 3888-3899.
    R. Jiang, X. Song, D. Huang, X. Song, T. Xia, Z. Cai, Z. Wang, K. Kim and R. Shibasaki, “DeepUrbanEvent: A System for Predicting Citywide Crowd Dynamics at Big Events,” in KDD '19: Proceeding of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019, pp. 2114-2122.
    S. Harada, H. Hayashi, and S. Uchida, “Biosignal Generation and Latent Variable Analysis With Recurrent Generative Adversarial Networks,” in IEEE Access, vol. 7, 2019, pp. 144292-144302, doi: 10.1109/ACCESS.2019.2934928.
    S. Wang, J. Cao, and P. S. Yu, “Deep learning for spatio-temporal data mining: a survey,” 2019, arXiv:1906.04928.
    Y. Zhou, J. Yang, H. Li, T. Cao and S. -Y. Kung, “Adversarial Learning for Multiscale Crowd Counting Under Complex Scenes,” in IEEE Transactions on Cybernetics, 2020, pp. 2168-2267, doi: 10.1109/TCYB.2019.2956091.
    H. Bao, X. Zhou, Y. Zhang, Y. Li and Y. Xie, “COVID-GAN: Estimating Human Mobility Responses to COVID-19 Pandemic through Spatio-Temporal Conditional Generative Adversarial Networks,” in Proceedings of the 28th International Conference on Advances in Geographic Information, 2020, pp. 273-282.
    H. Yu, Z. Li, G. Zhang, P. Liu and J. Wang, “Extracting and Predicting Taxi Hotspots in Spatiotemporal Dimensions Using Conditional Generative Adversarial Neural Networks,” in IEEE Transactions on Vehicular Technology, vol. 69, no. 4, pp. 3680-3692, April 2020, doi: 10.1109/TVT.2020.2978450.
    J. Zhang, Y. Zheng, J. Sun and D. Qi, “Flow Prediction in Spatio-Temporal Networks Based on Multitask Deep Learning,” in IEEE Transactions on Knowledge and Data Engineering, vol. 32, no. 3, pp. 468-478, 1 March 2020, doi: 10.1109/TKDE.2019.2891537.
    J. Feng, Z. Yang, F. Xu, H. Yu, M. Wang and Y. Li, “Learning to Simulate Human Mobility,” in KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020, pp.3426-3433.
    K. Ouyang, Y, Liang, Y. Liu, Z. Tong, S. Ruan, Y. Zheng and D. S.Rosenblum, “Fine-Grained Urban Flow Inference,” in IEEE Transactions on Knowledge and Data Engineering, 2020, doi: 10.1109/TKDE.2020.3017104.
    S.Wang, J. Cao, H. Chen, H. Peng, and Z. Huang, “SeqST-GAN: Seq2Seq Generative Adversarial Nets for Multi-step Urban Crowd Flow Prediction,” ACM Trans. Spatial Algorithms Syst.,vol. 6, no. 4, Jun. , 2020. doi:https://doi.org/10.1145/3378889.
    T. Golany, D. Freedman, and K. Radinsky, “SimGANs: Simulator-Based Generative Adversarial Networks for ECG Synthesis to Improve Deep ECG Classification,” Proceedings of the 37 th International Conference on Machine Learning , 2020.
    Y. Zhang, Y. Li, X. Zhou, X. Kong and J. Luo, “Curb-GAN: Conditional Urban Traffic Estimation through Spatio-Temporal Generative Adversarial Networks,” in KDD´20: Proceeding of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020, pp. 842-852.
    L. Zhang, J. Wu, J. Shen, M. Chen, R. Wang, X. Zhou, C. Xu, Q. Yao and Q. Wu, “SATP-GAN: self-attention based generative adversarial network for traffic flow prediction,” in Transportmetrica B: Transport Dynamics, 2021, https://doi.org/10.1080/21680566.2021.1916646.
    M. Luca, G. Barlacchi, B. Lepri and L. Pappalardo, “Deep Learning for Human Mobility: a Survey on Data and Models,” 2021, arXiv: 2012.02825.

    下載圖示
    2026-08-18公開
    QR CODE