Fine-Grained Trajectory-based Travel Time Estimation for Multi-city Scenarios Based on Deep Meta-Learning

TL;DR

This paper introduces MetaTTE, a meta-learning framework with a deep neural network, to accurately estimate travel times in multi-city scenarios by capturing complex spatial-temporal dependencies and adapting to changing traffic conditions.

Contribution

The paper proposes MetaTTE, a novel meta-learning based approach with a deep encoder-decoder model for fine-grained, adaptable travel time estimation across multiple cities.

Findings

MetaTTE outperforms six state-of-the-art baselines.

Achieves 29.35% and 25.93% accuracy improvements on Chengdu and Porto datasets.

Enhances generalization ability with small sample learning.

Abstract

Travel Time Estimation (TTE) is indispensable in intelligent transportation system (ITS). It is significant to achieve the fine-grained Trajectory-based Travel Time Estimation (TTTE) for multi-city scenarios, namely to accurately estimate travel time of the given trajectory for multiple city scenarios. However, it faces great challenges due to complex factors including dynamic temporal dependencies and fine-grained spatial dependencies. To tackle these challenges, we propose a meta learning based framework, MetaTTE, to continuously provide accurate travel time estimation over time by leveraging well-designed deep neural network model called DED, which consists of Data preprocessing module and Encoder-Decoder network module. By introducing meta learning techniques, the generalization ability of MetaTTE is enhanced using small amount of examples, which opens up new opportunities to increase the potential of achieving consistent performance on TTTE when traffic conditions and road networks change over time in the future. The DED model adopts an encoder-decoder network to capture fine-grained spatial and temporal representations. Extensive experiments on two real-world datasets are conducted to confirm that our MetaTTE outperforms six state-of-art baselines, and improve 29.35% and 25.93% accuracy than the best baseline on Chengdu and Porto datasets, respectively.