Similar articles

Abstract: Traffic flow prediction is crucial for intelligent transportation and aids in route planning and navigation. However, existing studies often focus on prediction accuracy improvement, while neglecting external influences and practical issues like resource constraints and data sparsity on edge devices. We propose an online transfer learning (OTL) framework with a multi-layer perceptron (MLP)-assisted graph convolutional network (GCN), termed OTL-GM, which consists of two parts: transferring source-domain features to edge devices and using online learning to bridge domain gaps. Experiments on four data sets demonstrate OTL’s effectiveness; in a comparison with models not using OTL, the reduction in the convergence time of the OTL models ranges from 24.77% to 95.32%.

在线迁移学习与多层感知机辅助图卷积网络用于交通流预测：面向边缘智能设备的解决方案

[1]Asim M, Wang Y, Wang KZ, et al., 2020. A review on computational intelligence techniques in cloud and edge computing. IEEE Trans Emerg Top Comput Intell, 4(6):742-763.

[2]Bai L, Yao LN, Li C, et al., 2020. Adaptive graph convolutional recurrent network for traffic forecasting. Proc 34^th Annual Conf on Neural Information Processing Systems, Article 1494.

[3]Bando M, Hasebe K, Nakayama A, et al., 1995. Dynamical model of traffic congestion and numerical simulation. Phys Rev E, 51(2):1035-1042.

[4]Bojan TM, Kumar UR, Bojan VM, 2014. An Internet of Things based intelligent transportation system. Proc IEEE Int Conf on Vehicular Electronics and Safety, p.174-179.

[5]Bruna J, Zaremba W, Szlam A, et al., 2014. Spectral networks and locally connected networks on graphs. Proc 2^nd Int Conf on Learning Representations, p.1-14.

[6]Chen C, Li KL, Teo SG, et al., 2020. Citywide traffic flow prediction based on multiple gated spatio-temporal convolutional neural networks. ACM Trans Knowl Discov Data, 14(4):42.

[7]Cong PJ, Zhou JL, Li LY, et al., 2021. A survey of hierarchical energy optimization for mobile edge computing: a perspective from end devices to the cloud. ACM Comput Surv, 53(2):38.

[8]Crammer K, Dekel O, Keshet J, et al., 2006. Online passive-aggressive algorithms. J Mach Learn Res, 7(3):515-585.

[9]Datla S, Sharma S, 2008. Impact of cold and snow on temporal and spatial variations of highway traffic volumes. J Transp Geogr, 16(5):358-372.

[10]Defferrard M, Bresson X, Vandergheynst P, 2016. Convolutional neural networks on graphs with fast localized spectral filtering. Proc 30^th Int Conf on Neural Information Processing Systems, p.3844-3852.

[11]Derawi M, Dalveren Y, Cheikh FA, 2020. Internet-of-Things-based smart transportation systems for safer roads. Proc 6^th World Forum on Internet of Things, p.1-4.

[12]Diao ZL, Wang X, Zhang DF, et al., 2019. Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting. Proc 33^rd AAAI Conf on Artificial Intelligence, p.890-897.

[13]Gentile C, 2000. A new approximate maximal margin classification algorithm. Proc 14^th Int Conf on Neural Information Processing Systems, p.479-485.

[14]Gräber T, Lupberger S, Unterreiner M, et al., 2019. A hybrid approach to side-slip angle estimation with recurrent neural networks and kinematic vehicle models. IEEE Trans Intell Veh, 4(1):39-47.

[15]Guo G, Yuan W, Liu JY, et al., 2023. Traffic forecasting via dilated temporal convolution with peak-sensitive loss. IEEE Intell Transp Syst Mag, 15(1):48-57.

[16]Guo SN, Lin YF, Wan HY, et al., 2022. Learning dynamics and heterogeneity of spatial-temporal graph data for traffic forecasting. IEEE Trans Knowl Data Eng, 34(11):5415-5428.

[17]Hamed MM, Al-Masaeid HR, Said ZMB, 1995. Short-term prediction of traffic volume in urban arterials. J Transp Eng, 121(3):249-254.

[18]Han PC, Wang SQ, Leung KK, 2020. Adaptive gradient sparsification for efficient federated learning: an online learning approach. Proc 40^th Int Conf on Distributed Computing Systems, p.300-310.

[19]Hashemi H, Abdelghany K, 2015. Real-time traffic network state prediction for proactive traffic management: simulation experiments and sensitivity analysis. Transp Res Rec, 2491(1):22-31.

[20]Jeong YS, Byon YJ, Castro-Neto MM, et al., 2013. Supervised weighting-online learning algorithm for short-term traffic flow prediction. IEEE Trans Intell Transp Syst, 14(4):1700-1707.

[21]Jia YH, Wu JP, Du YM, 2016. Traffic speed prediction using deep learning method. Proc 19^th Int Conf on Intelligent Transportation Systems, p.1217-1222.

[22]Kashyap AA, Raviraj S, Devarakonda A, et al., 2022. Traffic flow prediction models—a review of deep learning techniques. Cog Eng, 9(1):2010510.

[23]Kipf TN, Welling M, 2017. Semi-supervised classification with graph convolutional networks. Proc 5^th Int Conf on Learning Representations.

[24]Krizhevsky A, Sutskever I, Hinton GE, 2017. ImageNet classification with deep convolutional neural networks. Commun ACM, 60(6):84-90.

[25]Kwon YD, Chauhan J, Mascolo C, 2021. FastICARL: fast incremental classifier and representation learning with efficient budget allocation in audio sensing applications. Proc 22^nd Annual Conf of the International Speech Communication Association, p.356-360.

[26]Lee M, Choi YY, Park SW, et al., 2024. A gated MLP architecture for learning topological dependencies in spatio-temporal graphs. https://arxiv.org/html/2401.15894v1

[27]Li Y, Long PM, 1999. The relaxed online maximum margin algorithm. Proc 13^th Int Conf on Neural Information Processing Systems, p.361-387.

[28]Li YG, Yu R, Shahabi C, et al., 2018. Diffusion convolutional recurrent neural network: data-driven traffic forecasting. Proc 6^th Int Conf on Learning Representations.

[29]Liu HC, Dong Z, Jiang RH, et al., 2023. Spatio-temporal adaptive embedding makes vanilla Transformer SOTA for traffic forecasting. Proc 32^nd ACM Int Conf on Information and Knowledge Management, p.4125-4129.

[30]Liu J, Guan W, 2004. A summary of traffic flow forecasting methods. J High Transp Res Dev, 21(3):82-85 (in Chinese).

[31]Lu B, Gan XY, Zhang WN, et al., 2022. Spatio-temporal graph few-shot learning with cross-city knowledge transfer. Proc 28^th ACM SIGKDD Conf on Knowledge Discovery and Data Mining, p.1162-1172.

[32]Lv YS, Duan YJ, Kang WW, et al., 2014. Traffic flow prediction with big data: a deep learning approach. IEEE Trans Int Transp Syst, 16(2):865-873.

[33]Mallick T, Balaprakash P, Rask E, et al., 2021. Transfer learning with graph neural networks for short-term highway traffic forecasting. Proc 25^th Int Conf on Pattern Recognition, p.10367-10374.

[34]Nellore K, Hancke GP, 2016. A survey on urban traffic management system using wireless sensor networks. Sensors, 16(2):157.

[35]Qadri YA, Nauman A, Zikria YB, et al., 2020. The future of healthcare Internet of Things: a survey of emerging technologies. IEEE Commun Surv Tut, 22(2):1121-1167.

[36]Rosenblatt F, 1958. The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev, 65(6):386-408.

[37]Rumelhart DE, Hinton GE, Williams RJ, 1986. Learning representations by back-propagating errors. Nature, 323(6088):533-536.

[38]Singh R, Sharma R, Akram SV, et al., 2021. Highway 4.0: digitalization of highways for vulnerable road safety development with intelligent IoT sensors and machine learning. Saf Sci, 143:105407.

[39]Sun JR, Peng M, Jiang HB, et al., 2022. HMIAN: a hierarchical mapping and interactive attention data fusion network for traffic forecasting. IEEE Int Things J, 9(24):25685-25697.

[40]Sutskever I, Vinyals O, Le QV, 2014. Sequence to sequence learning with neural networks. Proc 28^th Int Conf on Neural Information Processing Systems, p.3104-3112.

[41]Tang C, Sun JR, Sun YC, et al., 2020. A general traffic flow prediction approach based on spatial-temporal graph attention. IEEE Access, 8:153731-153741.

[42]Tzeng E, Hoffman J, Darrell T, et al., 2015. Simultaneous deep transfer across domains and tasks. Proc IEEE Int Conf on Computer Vision, p.4068-4076.

[43]van Lint H, van Hinsbergen C, 2012. Short-term traffic and travel time prediction models. Artif Intell Appl Crit Transp Iss, 22(E-C168):22-41.

[44]Vaswani A, Shazeer N, Parmar N, et al., 2017. Attention is all you need. Proc 31^st Int Conf on Neural Information Processing Systems, p.6000-6010.

[45]Wang SZ, Miao H, Li JY, et al., 2022. Spatio-temporal knowledge transfer for urban crowd flow prediction via deep attentive adaptation networks. IEEE Trans Intell Transp Syst, 23(5):4695-4705.

[46]Williams BM, Hoel LA, 2003. Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results. J Transp Eng, 129(6):664-672.

[47]Yao ZX, Xia SC, Li Y, et al., 2023. Transfer learning with spatial-temporal graph convolutional network for traffic prediction. IEEE Trans Intell Transp Syst, 24(8):8592-8605.

[48]Yu B, Yin HT, Zhu ZX, 2017. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. Proc 27^th Int Joint Conf on Artificial Intelligence, p.3634-3640.

[49]Zhang CY, Patras P, 2018. Long-term mobile traffic forecasting using deep spatio-temporal neural networks. Proc 18^th ACM Int Symp on Mobile Ad Hoc Networking and Computing, p.231-240.

[50]Zhang H, Lu XX, 2020. Vehicle communication network in intelligent transportation system based on Internet of Things. Comput Commun, 160:799-806.

[51]Zhang T, Guo G, 2022. Graph attention LSTM: a spatiotemporal approach for traffic flow forecasting. IEEE Intell Transp Syst Mag, 14(2):190-196.

[52]Zhao L, Song YJ, Zhang C, et al., 2020. T-GCN: a temporal graph convolutional network for traffic prediction. IEEE Trans Intell Transp Syst, 21(9):3848-3858.

[53]Zhao PL, Hoi SCH, Jin R, 2011. Double updating online learning. J Mach Learn Res, 12:1587-1615.

[54]Zhu JW, Wang QJ, Tao C, et al., 2021. AST-GCN: attribute-augmented spatiotemporal graph convolutional network for traffic forecasting. IEEE Access, 9:35973-35983.

[55]Zivot E, Wang JH, 2006. Vector autoregressive models for multivariate time series. In: Modeling Financial Time Series with S-PLUS. Springer, New York, p.385-429.