A Deep Learning Model for Off-Ramp Hourly Traffic Volume Estimation

This paper addresses estimation of traffic volume of freeway off-ramps. Freeways are the transportation network’s main corridors, serving a large portion of the traffic volume. This traffic passes into the lower-level roads through off-ramps. Therefore, the traffic condition of the off-ramps is an essential factor affecting the operation of the transportation network. The continuous collection of volume data is impractical, and transportation authorities install vehicle detectors permanently on only a few off-ramps and temporarily (e.g., a week) on some others. Thus, traffic volume is the most challenging to estimate among various traffic measures. Moreover, the existing literature on volume estimation is mainly concerned with evaluating traffic on the main road segments. However, the distinct characteristics of the connection links, such as off-ramps, demands specified modeling. This study estimates the hourly traffic volume of off-ramps using a deep learning model. It evaluates the advantages of inputting the connected lower-level road features to the model, and explores various detector installation strategies on the model training process. The primary data sources are volume counts, probe speeds, and road segment infrastructure characteristics. The model results indicate that the incorporation of traffic flow characteristics and infrastructure attributes of the lower-level road connected to the freeway significantly improves the accuracy of estimation off-ramp traffic volume. Further, analysis illustrated that the model trained with data from temporarily installed detectors on all interchanges outperformed models trained with permanently installed detectors on 90% of the interchanges, indicating the model’s ability in extracting temporal correlations significantly more than spatial correlations.

[1]  Kaveh Farokhi Sadabadi,et al.  Dynamic Toll Prediction Using Historical Data on Toll Roads: Case Study of the I-66 Inner Beltway , 2021, ArXiv.

[2]  Mahdi Ebnali,et al.  Using Augmented Holographic UIs to Communicate Automation Reliability in Partially Automated Driving , 2020, AutomationXP@CHI.

[3]  Atorod Azizinamini,et al.  Factors affecting injury severity in vehicle-pedestrian crashes: A day-of-week analysis using random parameter ordered response models and Artificial Neural Networks , 2020 .

[4]  Wenhao Huang,et al.  Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning , 2014, IEEE Transactions on Intelligent Transportation Systems.

[5]  Athanasios K. Ziliaskopoulos,et al.  Foundations of Dynamic Traffic Assignment: The Past, the Present and the Future , 2001 .

[6]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[7]  Fulvio Simonelli,et al.  Limits and perspectives of effective O-D matrix correction using traffic counts , 2009 .

[8]  H. V. van Zuylen,et al.  Predicting Urban Arterial Travel Time with State-Space Neural Networks and Kalman Filters , 2006 .

[9]  Lu Feng,et al.  DeepTake: Prediction of Driver Takeover Behavior using Multimodal Data , 2020, CHI.

[10]  Kaveh Farokhi Sadabadi,et al.  Localization of Autonomous Vehicles: Proof of Concept for A Computer Vision Approach , 2021, ArXiv.

[11]  Przemysław Sekuła,et al.  Estimating Hourly Traffic Volumes using Artificial Neural Network with Additional Inputs from Automatic Traffic Recorders , 2020 .

[12]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[13]  Liang Li,et al.  An innovative information fusion method with adaptive Kalman filter for integrated INS/GPS navigation of autonomous vehicles , 2018 .

[14]  L. Vanajakshi,et al.  A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[15]  Guido Gentile,et al.  Section 7.5 - Dynamic traffic assignment with non separable link cost functions and queue spillovers , 2009 .

[16]  Mathieu Joerger,et al.  A New Data Association Method Using Kalman Filter Innovation Vector Projections , 2020, 2020 IEEE/ION Position, Location and Navigation Symposium (PLANS).

[17]  Nikola Markovic,et al.  Estimating Historical Hourly Traffic Volumes via Machine Learning and Vehicle Probe Data: A Maryland Case Study , 2017, Transportation Research Part C: Emerging Technologies.

[18]  Tara N. Sainath,et al.  Improving deep neural networks for LVCSR using rectified linear units and dropout , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[19]  Nikola Markovic,et al.  Inferencing hourly traffic volume using data-driven machine learning and graph theory , 2021, Comput. Environ. Urban Syst..

[20]  Josep Perarnau,et al.  Minimising GEH in static OD estimation , 2013 .

[21]  M. Maher.  INFERENCES ON TRIP MATRICES FROM OBSERVATIONS ON LINK VOLUMES: A BAYESIAN STATISTICAL APPROACH , 1983 .

[22]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[23]  Zhirui Ye,et al.  Short‐Term Traffic Volume Forecasting Using Kalman Filter with Discrete Wavelet Decomposition , 2007, Comput. Aided Civ. Infrastructure Eng..

[24]  B. Ran,et al.  Theoretical Research on Longitudinal Profile Design of Superhighways , 2020 .

[25]  Markos Papageorgiou,et al.  A Novel Approach to Estimating Missing Pairs of On/Off Ramp Flows , 2021, IEEE Transactions on Intelligent Transportation Systems.

[26]  S. Bera,et al.  Estimation of origin-destination matrix from traffic counts: the state of the art , 2011 .

[27]  Ennio Cascetta,et al.  Dynamic Estimators of Origin-Destination Matrices Using Traffic Counts , 1993, Transp. Sci..

[28]  Yong Qi,et al.  Freeway Traffic Speed Estimation of Mixed Traffic Using Data from Connected and Autonomous Vehicles with a Low Penetration Rate , 2020, Journal of Advanced Transportation.

[29]  Karin Baier,et al.  Transportation Systems Analysis Models And Applications , 2016 .

[30]  Sybil Derrible,et al.  Real-time accident detection: Coping with imbalanced data. , 2019, Accident; analysis and prevention.

[31]  Markos Papageorgiou,et al.  Real-time freeway traffic state estimation based on extended Kalman filter: a general approach , 2005 .

[32]  Abolfazl Mohammadian,et al.  A dynamic approach to predict travel time in real time using data driven techniques and comprehensive data sources , 2020 .

[33]  L. Chu.  Adaptive Kalman Filter Based Freeway Travel time Estimation , 2004 .

[34]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[35]  Hani S. Mahmassani,et al.  Dynamic origin-destination demand estimation using automatic vehicle identification data , 2006, IEEE Transactions on Intelligent Transportation Systems.

[36]  A. Ng.  Feature selection, L1 vs. L2 regularization, and rotational invariance , 2004, Twenty-first international conference on Machine learning - ICML '04.

[37]  Yao-Jan Wu,et al.  Short-Term Traffic Flow Forecasting for Urban Roads Using Data-Driven Feature Selection Strategy and Bias-Corrected Random Forests , 2017 .

[38]  Zhao Zhang,et al.  Identifying High Crash Risk Highway Segments Using Jerk-Cluster Analysis , 2019 .

[39]  Nikola Marković,et al.  Review of Methods for Estimating Construction Work Zone Capacity , 2021, Transportation Research Record: Journal of the Transportation Research Board.

[40]  Taghi M. Khoshgoftaar,et al.  Deep learning applications and challenges in big data analytics , 2015, Journal of Big Data.

[41]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .