IEEE Transactions on Intelligent Transportation Systems · 2004 · 1.4K citations · 22 references
ComputingComputer ScienceData ScienceMachine LearningTime Series AnalysisTransportationComputational Time Series AnalysisIntelligent Transportation SystemsPredictive ModelingSupport Vector MachinesTime Series ForecastingTime Series PredictionIntelligent Transportation Systems AnalyticsMachine Learning-based ForecastingMean Squared ErrorRoot Mean Squared Error AnalysisSupport Vector RegressionTraffic AnalysisTravel Time PredictionTraveler Information Systems
Travel time is a fundamental measure in transportation, and accurate prediction is crucial for intelligent transportation systems and advanced traveler information systems, with support vector machines believed to perform well for time series analysis because of their generalization ability and guaranteed global minima. The study applies support vector regression (SVR) to predict travel time and compares its performance to baseline methods using real highway traffic data. SVR was employed to model travel‑time prediction on real highway traffic data, and its performance was benchmarked against other baseline methods. Compared to other baseline predictors, SVR significantly reduces relative mean errors and root‑mean‑squared errors of predicted travel times, demonstrating its feasibility and strong performance for traffic data analysis.
Travel time is a fundamental measure in transportation. Accurate travel-time prediction also is crucial to the development of intelligent transportation systems and advanced traveler information systems. We apply support vector regression (SVR) for travel-time prediction and compare its results to other baseline travel-time prediction methods using real highway traffic data. Since support vector machines have greater generalization ability and guarantee global minima for given training data, it is believed that SVR will perform well for time series analysis. Compared to other baseline predictors, our results show that the SVR predictor can significantly reduce both relative mean errors and root-mean-squared errors of predicted travel times. We demonstrate the feasibility of applying SVR in travel-time prediction and prove that SVR is applicable and performs well for traffic data analysis.
22
An overview of statistical learning theory
Vladimir Vapnik · IEEE Transactions on Neural Networks · 1999 · 6.2K citations
Support Vector Machines for Classification and Regression
S.R. Gunn · 1998 · 2.8K citations