Dynamical functional prediction and classification, with application to traffic flow prediction

Abstract

Motivated by the need for accurate traffic flow prediction in transportation management, we propose a functional data method to analyze traffic flow patterns and predict future traffic flow. In this study we approach the problem by sampling traffic flow trajectories from a mixture of stochastic processes. The proposed functional mixture prediction approach combines functional prediction with probabilistic functional classification to take distinct traffic flow patterns into account. The probabilistic classification procedure, which incorporates functional clustering and discrimination, hinges on subspace projection. The proposed methods not only assist in predicting traffic flow trajectories, but also identify distinct patterns in daily traffic flow of typical temporal trends and variabilities. The proposed methodology is widely applicable in analysis and prediction of longitudinally recorded functional data.

Published in at http://dx.doi.org/10.1214/12-AOAS595 the Annals of Applied Statistics (http://www.imstat.org/aoas/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (4)

• Functional linear regression analysis for longitudinal data
• Multilevel functional principal component analysis
• Degradation modeling applied to residual lifetime prediction using functional data analysis
• The mortality of the Italian population: Smoothing techniques on the Lee--Carter model

Cited by in corpus (13)

• Deep Learning on Traffic Prediction: Methods, Analysis and Future Directions
• STGC-GNNs: A GNN-based traffic prediction framework with a spatial-temporal Granger causality graph
• Streamflow forecasting using functional regression
• Bayesian Particle Tracking of Traffic Flows
• Mortality and life expectancy forecasting for a group of populations in developed countries: A multilevel functional data method
• Multi-dimensional Functional Principal Component Analysis
• Bayesian analysis of traffic flow on interstate I-55: The LWR model
• Functional time series prediction under partial observation of the future curve
• Forecasting Australian subnational age-specific mortality rates
• Multipopulation mortality modelling and forecasting: The multivariate functional principal component with time weightings approaches
• Section on the special year for mathematics of planet earth (MPE 2013)
• Forecasting high-dimensional functional time series with dual-factor structures
• Uncovering predictability in the evolution of the WTI oil futures curve