Driving Behaviour Style Study with a Hybrid Deep Learning Framework Based on GPS Data

Innovative technologies and traffic data sources provide great potential to extend advanced strategies and methods in travel behaviour research. Considering the increasing availability of real-time vehicle trajectory data and stimulated by the advances in the modelling and analysis of big data, this paper developed a hybrid unsupervised deep learning model to study driving bahaviour and risk patterns. The approach combines Autoencoder and Self-organized Maps (AESOM), to extract latent features and classify driving behaviour. The specialized neural networks are applied to data from 4032 observations collected from Global Positioning System (GPS) sensors in Shenzhen, China. In two case studies, improper vehicle lateral position maintenance, speeding and inconsistent or excessive acceleration and deceleration have been identified. The experiments have shown that back propagation through multi-layer autoencoders is effective for non-linear and multi-modal dimensionality reduction, giving low reconstruction errors from big GPS datasets.

[1]  Catherine T. Lawson,et al.  Evaluating the feasibility of a passive travel survey collection in a complex urban environment: Lessons learned from the New York City case study , 2010 .

[2]  Changsheng Li,et al.  Autoencoder Regularized Network For Driving Style Representation Learning , 2017, IJCAI.

[3]  Huachun Tan,et al.  Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework , 2016, ArXiv.

[4]  Vijaya Kumar,et al.  SELF-ORGANIZED MAPPING BASED MAPREDUCE TECHNIQUE IN BIG DATA ANALYTICS : A NEURAL NETWORK APPROACH , 2016 .

[5]  Leo Breiman,et al.  Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author) , 2001, Statistical Science.

[6]  Masayoshi Tomizuka,et al.  An Overview on Study of Identification of Driver Behavior Characteristics for Automotive Control , 2014 .

[7]  Raja Sengupta,et al.  The Quantified Traveler: Using personal travel data to promote sustainable transport behavior , 2011 .

[8]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[9]  Jean-Claude Thill,et al.  TRIP DISTRIBUTION FORECASTING WITH MULTILAYER PERCEPTRON NEURAL NETWORKS: A CRITICAL EVALUATION , 2000 .

[10]  Fridulv Sagberg,et al.  A Review of Research on Driving Styles and Road Safety , 2015, Hum. Factors.

[11]  Liang Liu,et al.  Uncovering cabdrivers' behavior patterns from their digital traces , 2010, Comput. Environ. Urban Syst..

[12]  George Yannis,et al.  A review of the effect of traffic and weather characteristics on road safety. , 2014, Accident; analysis and prevention.

[13]  Jouko Lampinen,et al.  Clustering properties of hierarchical self-organizing maps , 1992, Journal of Mathematical Imaging and Vision.

[14]  Sim Heng Ong,et al.  Colour image segmentation using the self-organizing map and adaptive resonance theory , 2005, Image Vis. Comput..

[15]  Frank Gauterin,et al.  Online driving style recognition using fuzzy logic , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[16]  Tomás Ruiz,et al.  Travel Behavior Characterization Using Raw Accelerometer Data Collected from Smartphones , 2014 .

[17]  Tadahiro Taniguchi,et al.  Essential feature extraction of driving behavior using a deep learning method , 2015, 2015 IEEE Intelligent Vehicles Symposium (IV).

[18]  David W Soole,et al.  Effects of average speed enforcement on speed compliance and crashes: a review of the literature. , 2013, Accident; analysis and prevention.

[19]  Marthinus J. Booysen,et al.  Survey of smartphone-based sensing in vehicles for intelligent transportation system applications , 2015 .

[20]  Richard J. Hanowski,et al.  21 Using Naturalistic Driving Research to Design, Test and Evaluate Driver Assistance Systems , 2012 .

[21]  Leo Breiman,et al.  Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author) , 2001 .

[22]  Marco Botta,et al.  Real-Time Detection System of Driver Distraction Using Machine Learning , 2013, IEEE Transactions on Intelligent Transportation Systems.

[23]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[24]  Mohan M. Trivedi,et al.  Looking at Humans in the Age of Self-Driving and Highly Automated Vehicles , 2016, IEEE Transactions on Intelligent Vehicles.

[25]  Eleni I. Vlahogianni,et al.  Statistical methods versus neural networks in transportation research: Differences, similarities and some insights , 2011 .

[26]  Zongben Xu,et al.  Model-driven deep-learning , 2018 .

[27]  Yoshua Bengio,et al.  Scaling learning algorithms towards AI , 2007 .

[28]  Y. Nie.  How can the taxi industry survive the tide of ridesourcing? Evidence from Shenzhen, China , 2017 .

[29]  Thierry Derrmann,et al.  Driver Behavior Profiling Using Smartphones: A Low-Cost Platform for Driver Monitoring , 2015, IEEE Intelligent Transportation Systems Magazine.

[30]  Kay W. Axhausen,et al.  Processing Raw Data from Global Positioning Systems without Additional Information , 2009 .

[31]  Gys Albertus Marthinus Meiring,et al.  A Review of Intelligent Driving Style Analysis Systems and Related Artificial Intelligence Algorithms , 2015, Sensors.

[32]  Andries P. Engelbrecht,et al.  Introduction to Computational Intelligence , 2007 .

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

[34]  Nathalie Japkowicz,et al.  Nonlinear Autoassociation Is Not Equivalent to PCA , 2000, Neural Computation.

[35]  Mark Stevenson,et al.  Identifying behavioural change among drivers using Long Short-Term Memory recurrent neural networks , 2018 .

[36]  D. Potoglou,et al.  Factors associated with urban non-fatal road-accident severity , 2018, International journal of injury control and safety promotion.

[37]  Min Zhao,et al.  Classifying driving mental fatigue based on multivariate autoregressive models and kernel learning algorithms , 2010, 2010 3rd International Conference on Biomedical Engineering and Informatics.

[38]  Wolfram Burgard,et al.  Learning driving styles for autonomous vehicles from demonstration , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[39]  Kees Maat,et al.  Deriving and validating trip purposes and travel modes for multi-day GPS-based travel surveys: A large-scale application in the Netherlands , 2009 .

[40]  Eva Ericsson,et al.  Independent driving pattern factors and their influence on fuel-use and exhaust emission factors , 2001 .

[41]  Dejan Mitrovic,et al.  Reliable method for driving events recognition , 2005, IEEE Transactions on Intelligent Transportation Systems.

[42]  K Anbarasan,et al.  Sen Speed: Sensing Driving Conditions to Estimate Vehicle Speed in Urban Environment , 2017 .

[43]  Waldin Stone,et al.  Automated transportation transfer detection using GPS enabled smartphones , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.

[44]  Maurice Milgram,et al.  Transformation Invariant Autoassociation with Application to Handwritten Character Recognition , 1994, NIPS.

[45]  Vadim Sokolov,et al.  Clusters of Driving Behavior From Observational Smartphone Data , 2017, IEEE Intelligent Transportation Systems Magazine.

[46]  Hampton C. Gabler,et al.  Methodology for identifying car following events from naturalistic data , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[47]  Liuqing Yang,et al.  Big Data for Social Transportation , 2016, IEEE Transactions on Intelligent Transportation Systems.

[48]  Mohan M. Trivedi,et al.  Driver classification and driving style recognition using inertial sensors , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[49]  Fernando García,et al.  Data Fusion for Driver Behaviour Analysis , 2015, Sensors.