计算机科学 ›› 2024, Vol. 51 ›› Issue (4): 165-173.doi: 10.11896/jsjkx.221200171
林滨伟1, 於志勇1,2, 黄昉菀1,2, 郭贤伟1,2
LIN Binwei1, YU Zhiyong1,2, HUANG Fangwan 1,2, GUO Xianwei1,2
摘要: 随着城市汽车数量的持续增长,街道停车难已经成为一个热点问题。解决街道停车问题的关键在于准确预测街道未来的停车位信息。移动群智感知方式(CrowdSensing)通过在车辆上安装声呐以感知路边的停车位情况,是一种低成本、高效益的感知停车位的方式,然而这种方式感知的停车位数据在时间上存在高稀疏性问题,传统模型无法直接用于预测。针对此问题,提出了一种基于Transformer的停车位序列补全和预测网络,此网络通过编码器生成缺失停车位序列的记忆,进而解码器以自回归的方式补全停车位序列中缺失的部分,同时预测出未来的停车位信息。实验结果表明,所提方法在两个高缺失的街道停车位数据集上的补全和预测效果都优于传统的机器学习和深度学习方法。
中图分类号:
[1]SHOUP D C.Cruising for parking[J].Transport policy,2006,13(6):479-486. [2]孙霞,胡小飞,张昕,等.基于信息素优化蚁群算法下的停车场系统设计[J].重庆工商大学学报(自然科学版),2022,39(2):1-7. [3]REN Q L,ZHANG H F.Driver parking choice model in central business district[J].Journal of Chongqing University of Technology(Natural Science),2022,36(7):170-176. [4]CHENG G Z,FENG S H,FENG T J.Setting condition of on-street parking space occupied vehicle lane[J].Journal of Jilin University(Engineering and Technology Edition),2019,49(6):1858-1864. [5]LIN T,RIVANO H,LE MOUËL F.A survey of smart parking solutions[J].IEEE Transactions on Intelligent Transportation Systems,2017,18(12):3229-3253. [6]MA S,WOLFSON O,XU B.Updetector:Sensing parking/unparking activities using smartphones[C]//Proceedings of the 7th ACM SIGSPATIAL International Workshop on Computational Transportation Science.2014:76-85. [7]MATHUR S,JIN T,KASTURIRANGAN N,et al.Parknet:drive-by sensing of road-side parking statistics[C]//Proceedings of the 8th International Conference on Mobile Systems,Applications,and Services.2010:123-136. [8]ROMAN C,LIAO R,BALL P,et al.Detecting on-street parking spaces in smart cities:Performance evaluation of fixed and mobile sensing systems[J].IEEE Transactions on Intelligent Transportation Systems,2018,19(7):2234-2245. [9]XU B,WOLFSON O,YANG J,et al.Real-time street parkingavailability estimation[C]//2013 IEEE 14th International Conference on Mobile Data Management.IEEE,2013:16-25. [10]BOCK F,MARTINO S D,SESTER M.What are the potentialities of crowdsourcing for dynamic maps of on-street parking spaces?[C]//Proceedings of the 9th ACM SIGSPATIAL International Workshop on Computational Transportation Science.2016:19-24. [11]BOCK F,DI MARTINO S,ORIGLIA A.Smart parking:Using a crowd of taxis to sense on-street parking space availability[J].IEEE Transactions on Intelligent Transportation Systems,2019,21(2):496-508. [12]ZHONG W,SUO Q,GUPTA A,et al.MetaTP:Traffic Prediction with Unevenly-Distributed Road Sensing Data via Fast Adaptation[J].Proceedings of the ACM on Interactive,Mobile,Wearable and Ubiquitous Technologies,2021,5(3):1-28. [13]CHE Z,PURUSHOTHAM S,CHO K,et al.Recurrent neural networks for multivariate time series with missing values[J].Scientific Reports,2018,8(1):1-12. [14]WELLS B J,CHAGIN K M,NOWACKI A S,et al.Strategies for handling missing data in electronic health record derived data[J].Egems,2013,1(3):1035. [15]PRATAMA I,PERMANASARI A E,ARDIYANTO I,et al.A review of missingvalues handling methods on time-series data[C]//Proceedings of 2016 International Conference on Information Technology Systems and Innovation(ICITSI).IEEE,2016:1-6. [16]MASINI R P,MEDEIROS M C,MENDES E F.Machine lear-ning advances for time series forecasting[J].Journal of Econo-mic Surveys,2023,37(1):76-111. [17]YU Y,SI X,HU C,et al.A review of recurrent neural networks:LSTM cells and network architectures[J].Neural Computation,2019,31(7):1235-1270. [18]SAROJ A J,GUIN A,HUNTER M.Deep LSTM recurrent neural networks for arterial traffic volume data imputation[J].Journal of Big Data Analytics in Transportation,2021,3(2):95-108. [19]ROY K,ISHMAM A,TAHER K A.Demand Forecasting inSmart Grid Using Long Short-Term Memory[C]//2021 International Conference on Automation,Control and Mechatronics for Industry 4.0(ACMI).IEEE,2021:1-5. [20]FLORES A,TITO-CHURA H,YANA-MAMANI V.WindSpeed Time Series Imputation with a Bidirectional Gated Recurrent Unit(GRU) Model[C]//Proceedings of the Future Technologies Conference.Cham:Springer,2021:445-458. [21]ALTHELAYA K A,EL-ALFY E S M,MOHAMMED S.Stock market forecast using multivariate analysis with bidirectional and stacked(LSTM,GRU)[C]//2018 21st Saudi Computer Society National Computer Conference(NCC).IEEE,2018:1-7. [22]CHEN W,ZHAO J,WANG W,et al.Towards missing traffic data imputation using attention-based temporal convolutional networks[C]//2022 IEEE 25th International Conference on Intelligent Transportation Systems(ITSC).IEEE,2022:3733-3739. [23]LARA-BENÍTEZ P,CARRANZA-GARCÍA M,LUNA-RO-MERA J M,et al.Temporal convolutional networks applied to energy-related time series forecasting[J].Applied Sciences,2020,10(7):2322. [24]LUO Y,CAI X,ZHANG Y,et al.Multivariate time series imputation with generative adversarial networks[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems.2018:1603-1614. [25]LUO Y,ZHANG Y,CAI X,et al.E2gan:End-to-end generative adversarial network for multivariate time series imputation[C]//AAAI Press.2019:3094-3100. [26]ZHANG K,ZHONG G,DONG J,et al.Stock marketprediction based on generative adversarial network[J].Procedia Computer Science,2019,147:400-406. [27]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[J].arXiv:1706.03762,2017. [28]SONG X,YE Y,YU J J Q.TINet:Multi-dimensional Traffic DataImputation via Transformer Network[C]//International Conference on Artificial Neural Networks.Cham:Springer,2021:306-317. [29]WU N,GREEN B,BEN X,et al.Deep transformer models for time series forecasting:The influenza prevalence case[J].arXiv:2001.08317,2020. [30]CAO W,WANG D,LI J,et al.Brits:Bidirectional recurrent imputation for time series[J].arXiv:1805.10572,2018. [31]AXER S,PASCUCCI F,FRIEDRICH B.Estimation of traffic signal timing data and total delay for urban intersections based on low-frequency floating car data[C]//Proceedings of the 6th mobility TUM.2015. |
|