计算机科学 ›› 2025, Vol. 52 ›› Issue (6A): 240600017-5.doi: 10.11896/jsjkx.240600017
郜新军1, 张梅欣2, 朱力2
GAO Xinjun1, ZHANG Meixin2, ZHU Li2
摘要： 随着城市化进程的加快,地铁客流量的动态变化及不确定性带来的扰动会影响我国城市轨道交通运营服务质量。本研究面向轨道交通网络化运营提出一种基于生成对抗网络(GAN)的客流数据增强方法,通过利用少量的原始客流数据生成大量特征相同的可用数据,进行数据增强。在客流数据增强基础上,进一步研究基于时空多维的轨道交通运营态势精准预测方法,提出基于长短期记忆网络((LSTM))、卷积神经网络(CNN)和图神经网络(GCN)的客流数据预测方法,分别从时间维度和时空维度实现对轨道交通的客流量数据进行精准预测。短时客流数据的生成和预测能够为列车运行调整提供坚实基础,为提升轨道交通运营服务质量保驾护航,为未来城市发展规划提供理论支撑。
中图分类号:
| [1]NI J,YU L,JIN X N.Forecast and research of urban rail transit passenger flow based on ARIMA model[J].Intelligent Compu-ter and Applications,2021,11(4):135-138. [2]CHENG H,XU X.Short-term passenger flow prediction of rail transit based on BP neural network[J].Electronic Techno-logy & Software Engineering,2021(22):163-164. [3]ZONG J Z.Research on Urban Rail Transit Passenger Flow Forecasting Based on BP Neural Network[J].Western China Communications Science & Technology,2021(9):163-164. [4]LIU D,WU Z,SUN S.Study on Subway passenger flow prediction based on deep recurrent neural network[J].Multimed Tools Sppl,2022,81(14):18979-18992. [5]HUANG J,SHAO F,YANG S.Passenger Flow Prediction based on Recurrent Neural Networks and Wavelet Transform[J].Journal of physics.Conference series,2020,1486(2):22021. [6]ZHANG Y W,CHEN R F,LIU X Y.Passenger flow prediction of passenger stations based on gated recurrent neural network[J].Railway Transport and Economy,2022,44(9):96-102. [7]SHEN C,ZHU L,HUA G,et al.A Deep Convolutional Neural Network Based Metro Passenger Flow Forecasting System Using a Fusion of Time and Space[J].2020 IEEE 23RD International Conference on Intelligent Transportation Systems(ITSC),2020. [8]LI Y,WU C,YOSHINAGA T,et al.Traffic Flow Prediction with Compact Neural Networks[C]//IEEE 17th Int. Conf. on Dependable,Autonom and Secure Comp/IEEE 17th Int. conf. on pervas intelligence and Comp/IEEE 5th Int. Conf. on Cloud and Big Data Comp/IEEE 4th Cyber Science and Technology Congress(dasc/picom/cbdcom/cyberscitech).2019:1072-1076. [9]ZHANG J,CHEN F,GUOY,et al.Multi-graph convolutional network for short-term passenger flow forecasting in urban rail transit[J].IET Intell. Transp. SY,2020,14(10):1210-1217. [10]DROSOULI I,VOULODIMOS A,MASTOROCOSTAS P,et al.A Spatial-Temporal Graph Convolutional Recurrent Network for Transportation Flow Estimation[J].SENSORS-BASEL,2023,23(17):7534. [11]TRONG T N,MEHTONEN J,GONZÁLEZ G,et al.Semisu-pervised generative autoencoder for single-cell data[J].Journal of Computational Biology,2020,27(8):1190-1203. [12]ZHANG X,YANG Y,YUAN S,et al.Syntax-infused variational autoencoder for text generation[J].arXiv:1906.02181,2019. [13]BENGIO Y,YAO L,ALAIN G,et al.Generalized denoising auto-encoders as generative models[J].arXiv:1305.6663,2013. [14]VAN OORD A,KALCHBRENNER N,KAVUKCUOGLU K.Pixel recurrent neural networks[C]//International Conference on Machine Learning.PMLR,2016:1747-1756. [15]VAN DEN OORD A,KALCHBRENNER N,ESPEHOLT L,et al.Conditional image generation with pixelcnn decoders[J].arXiv:1606.05328,2016. [16]GOODFELLOW I,POUGET-ABADIE J,MIRZAM,et al.Ge-nerative adversarial nets[J].arXiv:1406.2661,2014. [17]DENG B,RAN Z,CHEN J,et al.Adversarial Examples Generation Algorithm through DCGAN[J].Intelligent Automation and Soft Computing,2021,30(3):889-898. [18]ADLER J,LUNZ S.Banach wasserstein gan[J].arXiv:1806.06621,2018. [19]HAIDERBHAI M,LEDESMA S,NAVABN,et al.Generating X-ray Images from Point Clouds Using Conditional Generative Adversarial Networks[C]//2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society(EMBC).IEEE,2020:1588-1591. [20]TODA R,TERAMOTO A,TSUJIMOTOM,et al.Synthetic CT image generation of shape-controlled lung cancer using semi-conditional InfoGAN and its applicability for type classification[J].International Journal of Computer Assisted Radiology and Surgery,2021,16(2):241-251. |
|
||
首页