DeepIST: Deep Image-based Spatio-Temporal Network for Travel Time Estimation

TL;DR

DeepIST introduces a novel image-based neural network framework that leverages CNNs to accurately estimate travel times by capturing spatial and temporal patterns from path representations in urban transportation systems.

Contribution

The paper proposes a new neural network framework, DeepIST, which transforms paths into images and uses specialized CNNs to improve travel time estimation accuracy.

Findings

Outperforms state-of-the-art models by 24.37% to 25.64% in MAE.

Utilizes a novel image-based path representation for better pattern extraction.

Employs a two-dimensional CNN for spatial features and a one-dimensional CNN for temporal features.

Abstract

Estimating the travel time for a given path is a fundamental problem in many urban transportation systems. However, prior works fail to well capture moving behaviors embedded in paths and thus do not estimate the travel time accurately. To fill in this gap, in this work, we propose a novel neural network framework, namely {\em Deep Image-based Spatio-Temporal network (DeepIST)}, for travel time estimation of a given path. The novelty of DeepIST lies in the following aspects: 1) we propose to plot a path as a sequence of "generalized images" which include sub-paths along with additional information, such as traffic conditions, road network and traffic signals, in order to harness the power of convolutional neural network model (CNN) on image processing; 2) we design a novel two-dimensional CNN, namely {\em PathCNN}, to extract spatial patterns for lines in images by regularization and adopting multiple pooling methods; and 3) we apply a one-dimensional CNN to capture temporal patterns among the spatial patterns along the paths for the estimation. Empirical results show that DeepIST soundly outperforms the state-of-the-art travel time estimation models by 24.37\% to 25.64\% of mean absolute error (MAE) in multiple large-scale real-world datasets.