Sparse Travel Time Estimation from Streaming Data

Abstract

We address two shortcomings in online travel time estimation methods for congested urban traffic. The first shortcoming is related to the determination of the number of mixture modes, which can change dynamically, within day and from day to day. The second shortcoming is the wide-spread use of Gaussian probability densities as mixture components. Gaussian densities fail to capture the positive skew in travel time distributions and, consequently, large numbers of mixture components are needed for reasonable fitting accuracy when applied as mixture components. They also assign positive probabilities to negative travel times. To address these issues, this paper derives a mixture distribution with Gamma component densities, which are asymmetric and supported on the positive numbers. We use sparse estimation techniques to ensure parsimonious models and propose a generalization of Gamma mixture densities using Mittag-Leffler functions, which provides enhanced fitting flexibility and improved parsimony. In order to accommodate within-day variability and allow for online implementation of the proposed methodology (i.e., fast computations on streaming travel time data), we introduce a recursive algorithm which efficiently updates the fitted distribution whenever new data become available. Experimental results using real-world travel time data illustrate the efficacy of the proposed methods.

References in corpus (6)

• Fast Image Recovery Using Variable Splitting and Constrained Optimization
• The path inference filter: model-based low-latency map matching of probe vehicle data
• Estimator selection: a new method with applications to kernel density estimation
• Traffic state estimation using stochastic Lagrangian dynamics
• Arriving on time: estimating travel time distributions on large-scale road networks
• Recursive Compressed Sensing

Cited by in corpus (13)

• Position weighted backpressure intersection control for urban networks
• Traffic state estimation using stochastic Lagrangian dynamics
• Traffic Data Imputation using Deep Convolutional Neural Networks
• Backpressure Control with Estimated Queue Lengths for Urban Network Traffic
• Learning Traffic Flow Dynamics using Random Fields
• Power laws and phase transitions in heterogenous car following with reaction times
• Traffic flow with multiple quenched disorders
• Incorporating Kinematic Wave Theory into a Deep Learning Method for High-Resolution Traffic Speed Estimation
• Learning Traffic Speed Dynamics from Visualizations
• Generalized adaptive smoothing based neural network architecture for traffic state estimation
• Nonlinear Traffic Prediction as a Matrix Completion Problem with Ensemble Learning
• Generalized Adaptive Smoothing Using Matrix Completion for Traffic State Estimation
• Short-Term Traffic Forecasting Using High-Resolution Traffic Data