Traffic Flow Multi-model with Machine Learning Method based on Floating Car Data

The traffic flow measurement is one of the most important components in the traffic management systems. The existing traditional measurement methods are highly time-consuming and costly to continuously gather the required data, such as loop detectors and video cameras. However the travel duration provided by the emerging Floating Car Data (FCD) on Google Maps offers a novel way to estimate traffic flows. Therefore, this work presents a novel multi-model for urban traffic flows by applying a Gaussian Process Regressor (GPR) tuned using machine learning method based on FCD. The FCD on roads, requested through the Google Maps API, only provides information as congestion and travel duration. Traffic flows is estimated with GPR, including different models built by aggregating together data from days sharing similar configuration. The aggregation is performed manually or using unsupervised classification. At last, a series of experiments are conducted to compare the estimated traffic flow and the real one from actual sensors data. The obtained results show that, the proposed modeling can always reproduce and capture the tendency of real traffic flow. The aggregation permits effectively to increase the performance and to conclude on the capability of the approach to replace traditional loop detectors for the measurement of traffic flows.

[1]  Hironori Suzuki,et al.  Application of Probe-Vehicle Data for Real-Time Traffic-State Estimation and Short-Term Travel-Time Prediction on a Freeway , 2003 .

[2]  T. VaisaghViswanathan,et al.  Traffic State Estimation Using Floating Car Data , 2016, ICCS.

[3]  W. P. van den Haak,et al.  Validation of Google Floating Car Data for Applications in Traffic Management , 2016 .

[4]  John M. Hancock,et al.  K -Means Clustering. , 2010 .

[5]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[6]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[7]  Shuguang He,et al.  AN ALGORITHM FOR MULTI-CLASS NETWORK EQUILIBRIUM PROBLEM IN PCE OF TRUCKS: APPLICATION TO THE SCAG TRAVEL DEMAND MODEL , 2006 .

[8]  Xin Jin,et al.  K-Means Clustering , 2010, Encyclopedia of Machine Learning.

[9]  Zhongya Wei,et al.  Spatial and Temporal Analysis of Probe Vehicle-based Sampling for Real-time Traffic Information System , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[10]  D. F. W. Yap,et al.  Medical image compression using block-based PCA algorithm , 2014, 2014 International Conference on Computer, Communications, and Control Technology (I4CT).

[11]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[12]  Tobias Jeske.  Floating Car Data from Smartphones : What Google and Waze Know About You and How Hackers Can Control Traffic , 2013 .

[13]  Hai-Jun Huang,et al.  Calibration of the combined trip distribution and assignment model for multiple user classes , 1992 .

[14]  Martin A. Ferman,et al.  A simulation evaluation of a real-time traffic information system using probe vehicles , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[15]  Yasuo Asakura,et al.  Incident Detection Methods Using Probe Vehicles with On-board GPS Equipment , 2015 .

[16]  S. Turksma.  The various uses of floating car data , 2000 .

[17]  David Mackay,et al.  Gaussian Processes - A Replacement for Supervised Neural Networks? , 1997 .

[18]  B.S. Kerner,et al.  Traffic state detection with floating car data in road networks , 2005, Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005..

[19]  Xiang Li,et al.  Online Gaussian process regression for time-varying manufacturing systems , 2014, 2014 13th International Conference on Control Automation Robotics & Vision (ICARCV).

[20]  K. Srinivasa Rao,et al.  Social Media Analysis using Optimized K-Means Clustering , 2019, International Journal of Trend in Scientific Research and Development.

[21]  Ying Sun,et al.  Gaussian Processes for Short-Term Traffic Volume Forecasting , 2010 .

[22]  Neil D. Lawrence,et al.  Fast Forward Selection to Speed Up Sparse Gaussian Process Regression , 2003, AISTATS.

[23]  David Beymer,et al.  A real-time computer vision system for vehicle tracking and traffic surveillance , 1998 .

[24]  Tsuyoshi Idé,et al.  Travel-Time Prediction Using Gaussian Process Regression: A Trajectory-Based Approach , 2009, SDM.

[25]  Mingyan Liu,et al.  Surface street traffic estimation , 2007, MobiSys '07.

[26]  Jianzhou Wang,et al.  Short-term wind speed prediction using empirical wavelet transform and Gaussian process regression , 2015 .

[27]  I. Jolliffe.  Principal Component Analysis , 2002 .

[28]  Sinem Coleri,et al.  Traffic Measurement and Vehicle Classification with a Single Magnetic Sensor , 2004 .

[29]  Gaetano Valenti,et al.  Traffic Estimation And Prediction Based On Real Time Floating Car Data , 2008, 2008 11th International IEEE Conference on Intelligent Transportation Systems.

[30]  Joachim Selbig,et al.  Principal components analysis. , 2013, Methods in molecular biology.

[31]  Toshiyuki Yamamoto,et al.  EN-ROUTE UPDATING METHODOLOGY OF TRAVEL TIME PREDICTION USING ACCUMULATED PROBE-CAR DATA , 2004 .