scientific papers

Travel Time Prediction on Highways

August 29, 2016

by BT Group plc, UK; and Jožef Stefan Institute, Slovenia

We describe the development of a predictive model for vehicle journey time on highways. Accurate travel time prediction is an important problem since it enables planning of cost effective vehicle routes and departure times, with the aim of saving time and fuel while reducing pollution. The main information source used is data from roadside double inductive loop sensors which measure vehicle speed, flow and density at specific locations. We model the spatiotemporal distribution of travel times by using local linear regression. The use of real-time data is very accurate for shorter journeys starting now and less reliable as journey times increase. Local linear regression can be used to optimally balance the use of historical and real time data. The main contribution of the paper is the extension of local linear models with higher order autoregressive travel time variables, namely vehicle flow data, and density data. Using two years of UK Highways Agency (HA) loop sensor data we found that the extended model significantly improves predictive performance while retaining the main benefits of earlier work: interpretability of linear models as well as computationally simple predictions.


From mobility patterns to behavioural change
Using persuasive technology and reward schemes to promote sustainable travel choices
Behavioural Change Support Intelligent Transportation Applications
Persuasive Technologies for Sustainable Mobility: State of the Art and Emerging Trends
Providing Intermodal Route Alternatives
Making Big Data Real in Upcoming Future: the Dynamic Toll Prices in the Portuguese Highways
Real-Time Monitoring of Road Traffic using Data Stream Mining
How to not be Annoying: Adjusting Persuasive Interventions Intensity when Nudging for Sustainable Travel Choices
Big data proceedings and storage framework for ITS – A case study on dynamic tolling
OPTIMUM Project: Geospatial data analysis for sustainable mobility
Persuasive Interventions for Sustainable Travel Choices Leveraging Users’ Personality and Mobility Type
Understanding Personal Mobility Patterns for Proactive Recommendations
Incident Detection Using Data from Social Media
Curious Cat – Mobile, Context-Aware Conversational Crowdsourcing Knowledge Acquisition
A Big Data Architecture for Traffic Forecasting Using Multi-Source Information
Exploring the Links between Persuasion, Personality and Mobility Types in Personalised Mobility Applications
Towards System-Aware Routes
Proactive Charging Schemes for Freight Transport: Dynamic Toll Discounts as a Tool to Reduce National Road Traffic
Big Data Processing and Storage Framework for ITS: A Case Study on Dynamic Tolling
Personalised Persuasion for Sustainable Mobility
Persuasive Technologies for Sustainable Urban Mobility
Estimating the State of Battery Charge in an Intelligent Mobile Home
Near Real-Time Transportation Mode Detection Based on Accelerometer Readings
Spatio-temporal Clustering Methods
Big Data Harmonization for Intelligent Mobility: a Dynamic Toll-charging Scenario
An architecture for big data processing on intelligent transportation systems. An application scenario on highway traffic flows
Memory Priming and User Preferences
Smart Cargo for Multimodal Freight Transport: When “Cloud” becomes “Fog”
Curious Cat2 – Conversational Crowd-Based and Context-Aware Knowledge Acquisition Chat Bot
TensiStrength – Stress and Relaxation Magnitude Detection for Social Media Texts
Proactive recommendations for Intelligent Mobility - An approach based on real-time big data processing
Personalized Persuasion Services for Route Planning Applications
Understanding Personal Mobility Patterns for Proactive Recommendations