New Perspectives on the Use of Online Learning for Congestion Level Prediction over Traffic Data

This work focuses on classification over time series data. When a time series is generated by non-stationary phenomena, the pattern relating the series with the class to be predicted may evolve over time (concept drift). Consequently, predictive models aimed to learn this pattern may become eventually obsolete, hence failing to sustain performance levels of practical use. To overcome this model degradation, online learning methods incrementally learn from new data samples arriving over time, and accommodate eventual changes along the data stream by implementing assorted concept drift strategies. In this manuscript we elaborate on the suitability of online learning methods to predict the road congestion level based on traffic speed time series data. We draw interesting insights on the performance degradation when the forecasting horizon is increased. As opposed to what is done in most literature, we provide evidence of the importance of assessing the distribution of classes over time before designing and tuning the learning model. This previous exercise may give a hint of the predictability of the different congestion levels under target. Experimental results are discussed over real traffic speed data captured by inductive loops deployed over Seattle (USA). Several online learning methods are analyzed, from traditional incremental learning algorithms to more elaborated deep learning models. As shown by the reported results, when increasing the prediction horizon, the performance of all models degrade severely due to the distribution of classes along time, which supports our claim about the importance of analyzing this distribution prior to the design of the model.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[3]  M. Cassidy,et al.  Some traffic features at freeway bottlenecks , 1999 .

[4]  Fei-Yue Wang,et al.  Long short-term memory model for traffic congestion prediction with online open data , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[5]  Koby Crammer,et al.  Online Passive-Aggressive Algorithms , 2003, J. Mach. Learn. Res..

[6]  Javier Del Ser,et al.  Understanding daily mobility patterns in urban road networks using traffic flow analytics , 2016, NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium.

[7]  Geoffrey I. Webb,et al.  Extremely Fast Decision Tree , 2018, KDD.

[8]  Geoff Hulten,et al.  Mining time-changing data streams , 2001, KDD '01.

[9]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[10]  Yaxin Bi,et al.  KNN Model-Based Approach in Classification , 2003, OTM.

[11]  Attila Matyas Nagy,et al.  Survey on traffic prediction in smart cities , 2018, Pervasive Mob. Comput..

[12]  Marcus A. Maloof,et al.  Dynamic Weighted Majority: An Ensemble Method for Drifting Concepts , 2007, J. Mach. Learn. Res..

[13]  Geoff Holmes,et al.  MEKA: A Multi-label/Multi-target Extension to WEKA , 2016, J. Mach. Learn. Res..

[14]  João Gama,et al.  A survey on concept drift adaptation , 2014, ACM Comput. Surv..

[15]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[16]  Ricard Gavaldà,et al.  Adaptive Learning from Evolving Data Streams , 2009, IDA.

[17]  Guangquan Zhang,et al.  Learning under Concept Drift: A Review , 2019, IEEE Transactions on Knowledge and Data Engineering.

[18]  Ugur Demiryurek,et al.  Deep Learning: A Generic Approach for Extreme Condition Traffic Forecasting , 2017, SDM.

[19]  Ricard Gavaldà,et al.  Learning from Time-Changing Data with Adaptive Windowing , 2007, SDM.

[20]  Zhiyong Cui,et al.  Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction , 2018, ArXiv.

[21]  Heiko Wersing,et al.  Incremental on-line learning: A review and comparison of state of the art algorithms , 2018, Neurocomputing.

[22]  Yunpeng Wang,et al.  Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks , 2017, Sensors.

[23]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[24]  Joelle Pineau,et al.  Online Bagging and Boosting for Imbalanced Data Streams , 2013, IEEE Transactions on Knowledge and Data Engineering.

[25]  Boris S. Kerner Three-phase traffic theory and highway capacity , 2002 .

[26]  João Gama,et al.  Very fast decision rules for classification in data streams , 2013, Data Mining and Knowledge Discovery.

[27]  Eric Horvitz,et al.  Prediction, Expectation, and Surprise: Methods, Designs, and Study of a Deployed Traffic Forecasting Service , 2005, UAI.

[28]  Yu Zheng,et al.  Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction , 2016, AAAI.

[29]  Éric Gaussier,et al.  A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation , 2005, ECIR.

[30]  Narasimhan Sundararajan,et al.  A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks , 2006, IEEE Transactions on Neural Networks.

[31]  Talel Abdessalem,et al.  Adaptive random forests for evolving data stream classification , 2017, Machine Learning.

[32]  Pouria Kaviani,et al.  Short Survey on Naive Bayes Algorithm-IJAERD , 2017 .

[33]  Talel Abdessalem,et al.  Scikit-Multiflow: A Multi-output Streaming Framework , 2018, J. Mach. Learn. Res..

[34]  Mykola Pechenizkiy,et al.  An Overview of Concept Drift Applications , 2016 .

[35]  Albert Bifet,et al.  Spiking Neural Networks and Online Learning: An Overview and Perspectives , 2019, Neural Networks.

[36]  Marcus A. Maloof,et al.  Using additive expert ensembles to cope with concept drift , 2005, ICML.

[37]  Eleni I. Vlahogianni,et al.  Road Traffic Forecasting: Recent Advances and New Challenges , 2018, IEEE Intelligent Transportation Systems Magazine.

[38]  Stuart J. Russell,et al.  Online bagging and boosting , 2005, 2005 IEEE International Conference on Systems, Man and Cybernetics.

[39]  Eleni I. Vlahogianni,et al.  Short-term traffic forecasting: Where we are and where we’re going , 2014 .

[40]  Wei Xie,et al.  An Online-Traffic-Prediction Based Route Finding Mechanism for Smart City , 2015, Int. J. Distributed Sens. Networks.

[41]  GamaJoão,et al.  Very fast decision rules for classification in data streams , 2015 .