Abstract
Accurate and timely traffic flow information is important for the successful deployment of intelligent transportation systems. Over the last few years, traffic data have been exploding, and we have truly entered the era of big data for transportation. Existing traffic flow prediction methods mainly use shallow traffic prediction models and are still unsatisfying for many real-world applications. This situation inspires us to rethink the traffic flow prediction problem based on deep architecture models with big traffic data. In this paper, a novel deep-learning-based traffic flow prediction method is proposed, which considers the spatial and temporal correlations inherently. A stacked autoencoder model is used to learn generic traffic flow features, and it is trained in a greedy layerwise fashion. To the best of our knowledge, this is the first time that a deep architecture model is applied using autoencoders as building blocks to represent traffic flow features for prediction. Moreover, experiments demonstrate that the proposed method for traffic flow prediction has superior performance.
- [1] , “ DynaCAS: Computational experiments and decision support for ITS,” IEEE Intell. Syst., vol. 23, no. 6, pp. 19– 23, Nov./Dec. 2008.Google ScholarDigital Library
- [2] , “ Data-driven intelligent transportation systems: A survey,” IEEE Trans. Intell. Transp. Syst., vol. 12, no. 4, pp. 1624– 1639, Dec. 2011.Google ScholarDigital Library
- [3] , “ Data-intensive applications, challenges, techniques and technologies: A survey on Big Data,” Inf. Sci., vol. 275, pp. 314– 347, Aug. 2014.Google ScholarCross Ref
- [4] , “ Learning deep architectures for AI,” Found. Trends Mach. Learn., vol. 2, no. 1, pp. 1– 127, Jan. 2009.Google ScholarDigital Library
- [5] , “ Reducing the dimensionality of data with neural networks,” Science, vol. 313, no. 5786, pp. 504– 507, Jul. 2006.Google ScholarCross Ref
- [6] , “ A unified architecture for natural language processing: Deep neural networks with multitask learning,” in Proc. 25th ICML, 2008, pp. 160– 167.Google Scholar
- [7] , “ Multi-digit number recognition from street view imagery using deep convolutional neural networks,” arXiv preprint arXiv:1312.6082, 2013.Google Scholar
- [8] , “ Deep learning for class-generic object detection,” , 2013, arXiv preprint arXiv:1312.6885.Google Scholar
- [9] , “ Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4D patient data,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 8, pp. 1930– 1943, Aug. 2013.Google ScholarDigital Library
- [10] , “ Analysis of freeway traffic time-series data by using Box–Jenkins techniques,” Transp. Res. Rec., no. 722, pp. 1– 9, 1979.Google Scholar
- [11] , “ On forecasting freeway occupancies and volumes,” Transp. Res. Rec., no. 773, pp. 47– 49, 1980.Google Scholar
- [12] , “ Short-term prediction of traffic volume in urban arterials,” J. Transp. Eng., vol. 121, no. 3, pp. 249– 254, May 1995.Google ScholarCross Ref
- [13] , “ Combining Kohonen maps with ARIMA time series models to forecast traffic flow,” Transp. Res. C, Emerging Technol., vol. 4, no. 5, pp. 307– 318, Oct. 1996.Google Scholar
- [14] , “ Application of subset autoregressive integrated moving average model for short-term freeway traffic volume forecasting,” Transp. Res. Rec., vol. 1678, pp. 179– 188, 1999.Google ScholarCross Ref
- [15] , “ Multivariate vehicular traffic flow prediction—Evaluation of ARIMAX modeling,” Transp. Res. Rec., no. 1776, pp. 194– 200, 2001.Google Scholar
- [16] , “ Forecasting traffic flow conditions in an urban network—Comparison of multivariate and univariate approaches,” Transp. Res. Rec., no. 1857, pp. 74– 84, 2003, Transporation Network Modeling 2003: Planning and Administration.Google Scholar
- [17] , “ Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: Theoretical basis and empirical results,” J. Transp. Eng., vol. 129, no. 6, pp. 664– 672, Nov./Dec. 2003.Google ScholarCross Ref
- [18] , “ Multivariate short-term traffic flow forecasting using time-series analysis,” IEEE Trans. Intell. Transp. Syst., vol. 10, no. 2, pp. 246– 254, Jun. 2009.Google ScholarDigital Library
- [19] , “ Nonparametric regression and short-term freeway traffic forecasting,” J. Transp. Eng., vol. 117, no. 2, pp. 178– 188, Mar./Apr. 1991.Google ScholarCross Ref
- [20] , “ Dynamic near-term traffic flow prediction: System oriented approach based on past experiences,” IET Intell. Transport Syst., vol. 6, no. 3, pp. 292– 305, Sep. 2012.Google ScholarCross Ref
- [21] , “ Nonparametric traffic flow prediction using kernel estimator,” in Proc. 13th ISTTT, 1996, pp. 41– 54.Google Scholar
- [22] , “ Use of local linear regression model for short-term traffic forecasting,” Transp. Res. Rec., no. 1836, pp. 143– 150, 2003, Initiatives in Information Technology and Geospatial Science for Transportation: Planning and Administration.Google Scholar
- [23] , “ A Bayesian network approach to traffic flow forecasting,” IEEE Intell. Transp. Syst. Mag., vol. 7, no. 1, pp. 124– 132, Mar. 2006.Google ScholarDigital Library
- [24] , “ Supervised weighting-online learning algorithm for short-term traffic flow prediction,” IEEE Trans. Intell. Transp. Syst., vol. 14, no. 4, pp. 1700– 1707, Dec. 2013.Google ScholarDigital Library
- [25] , “ Optimized and meta-optimized neural networks for short-term traffic flow prediction: A genetic approach,” Transp. Res. C, Emerging Technol., vol. 13, no. 3, pp. 211– 234, Jun. 2005.Google ScholarCross Ref
- [26] , “ Neural-network-based models for short-term traffic flow forecasting using a hybrid exponential smoothing and Levenberg–Marquardt algorithm,” IEEE Trans. Intell. Transp. Syst., vol. 13, no. 2, pp. 644– 654, Jun. 2012.Google ScholarDigital Library
- [27] , “ Short-term freeway traffic volume forecasting using radial basis function neural network,” Transp. Res. Rec., no. 1651, pp. 39– 47, 1998.Google Scholar
- [28] , “ Short-term freeway traffic flow prediction: Bayesian combined neural network approach,” J. Transp. Eng., vol. 132, no. 2, pp. 114– 121, Feb. 2006.Google ScholarCross Ref
- [29] , “ Short-term traffic prediction on different types of roads with genetically designed regression and time delay neural network models,” J. Comput. Civil Eng., vol. 19, no. 1, pp. 94– 103, Jan. 2005.Google ScholarCross Ref
- [30] , “ An object-oriented neural network approach to short-term traffic forecasting,” Eur. J. Oper. Res., vol. 131, no. 2, pp. 253– 261, Jun. 2001.Google ScholarCross Ref
- [31] , “ Neural network multitask learning for traffic flow forecasting,” in Proc. IEEE IJCNN (IEEE World Congr. Comput. Intell.), Jun. 1–8, 2008, pp. 18971901.Google Scholar
- [32] , “ Urban traffic flow prediction using a fuzzy-neural, approach,” Transp. Res. C, Emerging Technol., vol. 10, no. 2, pp. 85– 98, Apr. 2002.Google ScholarCross Ref
- [33] , “ Short term traffic flow prediction for a non urban highway using artificial neural network,” Proc. Soc. Behav. Sci., vol. 104, pp. 755– 764, Dec. 2013.Google ScholarCross Ref
- [34] , “ A review of neural networks applied to transport,” Transp. Res. C, Emerging Technol., vol. 3, no. 4, pp. 247– 260, Aug. 1995.Google ScholarCross Ref
- [35] , “ An aggregation approach to short-term traffic flow prediction,” IEEE Trans. Intell. Transp. Syst., vol. 10, no. 1, pp. 60– 69, Mar. 2009.Google ScholarDigital Library
- [36] , “ A computational intelligence-based approach for short-term traffic flow prediction,” Expert Syst., vol. 29, no. 2, pp. 124– 142, May 2012.Google Scholar
- [37] , “ Short-term traffic flow prediction with regime switching models,” Transp. Res. Rec., vol. 1965, pp. 23– 31, 2006.Google ScholarCross Ref
- [38] , “ Adaptive hybrid fuzzy rule-based system approach for modeling and predicting urban traffic flow,” Transp. Res. C, Emerging Technol., vol. 16, no. 5, pp. 554– 573, Oct. 2008.Google Scholar
- [39] , “ Dynamic prediction of traffic volume through Kalman filtering theory,” Trans. Res. B, Methodol., vol. 18, no. 1, pp. 1– 11, Feb. 1984.Google ScholarCross Ref
- [40] , “ Online recursive algorithm for short-term traffic prediction,” Transp. Res. Rec., vol. 1879, pp. 1– 8, 2004.Google Scholar
- [41] , “ Modeling and forecasting the urban volume using stochastic differential equations,” IEEE Trans. Intell. Transp. Syst., vol. 15, no. 1, pp. 250– 259, Feb. 2014.Google ScholarDigital Library
- [42] , “ An online change-point-based model for traffic parameter prediction,” IEEE Trans. Intell. Transp. Syst., vol. 14, no. 3, pp. 1360– 1369, Sep. 2013.Google ScholarDigital Library
- [43] , “ Type-2 fuzzy logic approach for short-term traffic forecasting,” Proc. Inst. Elect. Eng.—Intell. Transp. Syst., vol. 153, no. 1, pp. 33– 40, Mar. 2006.Google ScholarCross Ref
- [44] , “ Variational inference for infinite mixtures of Gaussian processes with applications to traffic flow prediction,” IEEE Trans. Intell. Transp. Syst., vol. 12, no. 2, pp. 466– 475, Jun. 2011.Google Scholar
- [45] , “ High performance microscopic simulation for traffic forecasting,” in Proc. IEE Colloq. Strategic Control Inter-Urban Road Netw. (Dig. No 1997/055), 1997, pp. 4/1– 4/3.Google Scholar
- [46]
, “
An on-line dynamic traffic prediction model for an inter-urban motorway network ,” in Urban Traffic Networks , Eds., Berlin, Germany: Springer-Verlag, 1995, pp. 83– 122.Google Scholar - [47] , “ Using traffic prediction models for providing predictive traveller information,” Int. J. Technol. Manage., vol. 20, no. 3/4, pp. 326– 339, 2000.Google Scholar
- [48]
, “
Short term traffic flow prediction,” presented at the
24th Australian Transportation Research Forum,
Hobart, Tasmania , 2001.Google Scholar - [49] , “ Comparison of parametric and nonparametric models for traffic flow forecasting,” Transp. Res. C, Emerging Technol., vol. 10, no. 4, pp. 303– 321, Aug. 2002.Google ScholarCross Ref
- [50] , “ A multivariate state space approach for urban traffic flow modeling and prediction,” Transp. Res. C, Emerging Technol., vol. 11, no. 2, pp. 121– 135, Apr. 2003.Google ScholarCross Ref
- [51] , “ Short-term traffic flow forecasting: An experimental comparison of time-series analysis and supervised learning,” IEEE Trans. Intell. Transp. Syst., vol. 14, no. 2, pp. 871– 882, Jun. 2013.Google ScholarDigital Library
- [52] , “ The retrieval of intra-day trend and its influence on traffic prediction,” Transp. Res. C, Emerging Technol., vol. 22, pp. 103– 118, Jun. 2012.Google ScholarCross Ref
- [53] , “ Traffic flow forecasting: Comparison of modeling approaches,” J. Transp. Eng., vol. 123, no. 4, pp. 261– 266, Jul./Aug. 1997.Google ScholarCross Ref
- [54] , “ Urban freeway traffic flow prediction—Application of seasonal autoregressive integrated moving average and exponential smoothing models,” Transp. Res. Rec., no. 1644, pp. 132– 141, 1998.Google Scholar
- [55] , “ Should we use neural networks or statistical models for short-term motorway traffic forecasting?,” Int. J. Forecast., vol. 13, no. 1, pp. 43– 50, Mar. 1997.Google ScholarCross Ref
- [56] , “ Short-term traffic forecasting: Overview of objectives and methods,” Transp. Rev., vol. 24, no. 5, pp. 533– 557, Sep. 2004.Google ScholarCross Ref
- [57]
, “
Short term traffic prediction models,” presented at the
ITS World Congress,
Beijing, China , 2007.Google Scholar - [58] , “ A fast learning algorithm for deep belief nets,” Neural Comput., vol. 18, no. 7, pp. 1527– 1554, Jul. 2006.Google ScholarDigital Library
- [59] , “ Greedy layer-wise training of deep networks,” in Proc. Adv. NIPS, 2007, pp. 153– 160.Google Scholar
- [60] , “ Prediction as a candidate for learning deep hierarchical models of data”, Technical Univ. Denmark, Palm, Denmark2012.Google Scholar
- [61] Caltrans, Performance Measurement System (PeMS), 2014. [Online]. Available: http://pems.dot.ca.gov.Google Scholar
Index Terms
- Traffic Flow Prediction With Big Data: A Deep Learning Approach
Recommendations
A Survey of Hybrid Deep Learning Methods for Traffic Flow Prediction
ICAIP '19: Proceedings of the 2019 3rd International Conference on Advances in Image ProcessingTraffic flow prediction using big data and deep learning attracts great attentions in recent years. Researchers show that DNN models can provide better traffic prediction accuracy than the traditional shallow models. Since the traffic flow reveals both ...
Deep Architecture for Traffic Flow Prediction
ADMA 2013: Part II of the Proceedings of the 9th International Conference on Advanced Data Mining and Applications - Volume 8347Traffic flow prediction is a fundamental problem in transportation modeling and management. Many existing approaches fail at providing favorable results duo to 1shallow in architecture;2hand engineered in features. In this paper, we propose a deep ...
A novel fuzzy deep-learning approach to traffic flow prediction with uncertain spatial–temporal data features
AbstractPredicting traffic flow is one of the fundamental needs to comfortable travel, but this task is challenging in vehicular cyber–physical systems because of ever-increasing uncertain traffic big data. Although deep-learning (DL) methods ...
Highlights- The FDCN approach is proposed to lessen the impact of data uncertainty.
- A model ...
Comments