Travel time prediction on signalised urban arterials by applying SARIMA modelling on Bluetooth data

Travel time prediction has long been the topic of transportation research. But most relevant prediction models in the literature are limited to motorways. Travel time prediction on arterial networks is challenging due to involving traffic signals and significant variability of individual vehicle travel time. The limited availability of traffic data from arterial networks makes travel time prediction even more challenging. Recently, there has been significant interest of exploiting Bluetooth data for travel time estimation. This research analysed the real travel time data collected by the Brisbane City Council using the Bluetooth technology on arterials. Databases, including experienced average daily travel time are created and classified for approximately 8 months. Thereafter, based on data characteristics, Seasonal Auto Regressive Integrated Moving Average (SARIMA) modelling is applied on the database for short-term travel time prediction. The SARMIA model not only takes the previous continuous lags into account, but also uses the values from the same time of previous days for travel time prediction. This is carried out by defining a seasonality coefficient which improves the accuracy of travel time prediction in linear models. The accuracy, robustness and transferability of the model are evaluated through comparing the real and predicted values on three sites within Brisbane network. The results contain the detailed validation for different prediction horizons (5 min to 90 minutes). The model performance is evaluated mainly on congested periods and compared to the naive technique of considering the historical average.

[1]  Haitham Al-Deek,et al.  Travel Time Prediction with Non-Linear Time Series , 1998 .

[2]  J. V. van Lint,et al.  Improving a Travel-Time Estimation Algorithm by Using Dual Loop Detectors , 2003 .

[3]  Rod Troutbeck,et al.  Travel Time and Origin-Destination Data Collection using Bluetooth MAC Address Readers , 2010 .

[4]  Holger R. Maier,et al.  Neural Network Models for Forecasting Univariate Time Series , 1996 .

[5]  Darcy M. Bullock,et al.  Real-Time Measurement of Travel Time Delay in Work Zones and Evaluation Metrics Using Bluetooth Probe Tracking , 2010 .

[6]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[7]  Rajesh Krishnan,et al.  Application of Bluetooth Technology for Mode- Specific Travel Time Estimation on Arterial Roads: Potentials and Challenges , 2012 .

[8]  Ursula Gather,et al.  Methods and Algorithms for Robust Filtering , 2004 .

[9]  Ashish Bhaskar,et al.  Empirical evaluation of Bluetooth and Wifi scanning for road transport , 2013 .

[10]  Bruce N. Janson.  Transportation systems: Theory and application of advanced technology. A postprint volume from the IFAC Symposium, Tianjin, People's Republic of China, 24–26 August, 1994 , 1997 .

[11]  Stephen G. Ritchie,et al.  Use of vehicle signature analysis and lexicographic optimization for vehicle reidentification on freeways , 1999 .

[12]  Ashish Bhaskar,et al.  Analysis for the Use of Cumulative Plots for Travel Time Estimation on Signalized Network , 2010, Int. J. Intell. Transp. Syst. Res..

[13]  Yinhai Wang,et al.  Pedestrian Travel Pattern Discovery Using Mobile Bluetooth Sensors , 2012 .

[14]  Darcy M. Bullock,et al.  Analysis of Freeway Travel Time Variability Using Bluetooth Detection , 2011 .

[15]  Le Minh Kieu,et al.  On the use of Bluetooth MAC Scanners for live reporting of the transport network , 2013 .

[16]  Panos G Michalopoulos,et al.  ON-LINE DIVERSION PREDICTION FOR DYNAMIC CONTROL AND VEHICLE GUIDANCE IN FREEWAY CORRIDORS , 1990 .

[17]  Ashish Bhaskar,et al.  Arterial traffic congestion analysis using Bluetooth Duration data , 2011 .

[18]  Vassilis Kostakos,et al.  Instrumenting the City: Developing Methods for Observing and Understanding the Digital Cityscape , 2006, UbiComp.

[19]  Fritz Busch,et al.  The Short-Term Prediction of Link Travel Times in Signal Controlled Road Networks , 1994 .

[20]  Ashish Bhaskar,et al.  Fusing Loop Detector and Probe Vehicle Data to Estimate Travel Time Statistics on Signalized Urban Networks , 2011, Comput. Aided Civ. Infrastructure Eng..

[21]  Ashish Bhaskar,et al.  Average Travel Time Estimations for Urban Routes that Consider Exit Turning Movements , 2012 .

[22]  V. Reisen,et al.  ESTIMATION OF THE FRACTIONAL DIFFERENCE PARAMETER IN THE ARIMA(p, d, q) MODEL USING THE SMOOTHED PERIODOGRAM , 1994 .

[23]  I Okutani,et al.  Dynamic prediction of traffic volume through Kalman Filtering , 1984 .

[24]  Laurence R. Rilett,et al.  Spectral Basis Neural Networks for Real-Time Travel Time Forecasting , 1999 .

[25]  Carlos Carmona,et al.  Travel Time Forecasting and Dynamic Origin-Destination Estimation for Freeways Based on Bluetooth Traffic Monitoring , 2010 .

[26]  H. Mahmassani,et al.  Travel time estimation based on piecewise truncated quadratic speed trajectory , 2008 .

[27]  Jun Chen,et al.  Investigation with Bluetooth Sensors of Bicycle Travel Time Estimation on a Short Corridor , 2012, Int. J. Distributed Sens. Networks.

[28]  Darcy M. Bullock,et al.  Estimating Route Choice and Travel Time Reliability with Field Observations of Bluetooth Probe Vehicles , 2011 .

[29]  Jaume Barceló,et al.  A Kalman Filter Approach for the Estimation of Time Dependent OD Matrices Exploiting Bluetooth Traffic Data Collection , 2012 .

[30]  Ashish Bhaskar,et al.  Estimation of Travel Time on Urban Networks with Midlink Sources and Sinks , 2009 .

[31]  Steven I-Jy Chien,et al.  Dynamic Bus Arrival Time Prediction with Artificial Neural Networks , 2002 .

[32]  Steven I-Jy Chien,et al.  APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN PREDICTION OF TRANSIT ARRIVAL TIMES , 1999 .

[33]  Ashish Bhaskar,et al.  Bluetooth and Wi-Fi MAC address based crowd data collection and monitoring: benefits, challenges and enhancement , 2013 .

[34]  Ali Haghani,et al.  Bluetooth Sensor Data and Ground Truth Testing of Reported Travel Times , 2012 .

[35]  J. W. C. van Lint,et al.  Improving a Travel-Time Estimation Algorithm by Using Dual Loop Detectors , 2003 .

[36]  Lee-Ing Tong,et al.  Forecasting field failure data for repairable systems using neural networks and SARIMA model , 2005 .

[37]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[38]  Lee,et al.  Error Modeling and Analysis for Travel Time Data Obtained from Bluetooth MAC Address Matching , 2011 .

[39]  Jih-Jeng Huang,et al.  Model identification of ARIMA family using genetic algorithms , 2005, Appl. Math. Comput..

[40]  Thomas Adler,et al.  Generating Route-Specific Origin–Destination Tables Using Bluetooth Technology , 2012 .

[41]  S. Delurgio.  Forecasting Principles and Applications , 1998 .

[42]  Michael J Demetsky,et al.  SHORT-TERM TRAFFIC FLOW PREDICTION: NEURAL NETWORK APPROACH , 1994 .