Large-Scale Traffic Congestion Prediction based on Multimodal Fusion and Representation Mapping

TL;DR

This paper introduces an end-to-end convolutional neural network framework that effectively predicts large-scale traffic congestion at precise locations by fusing multimodal data and mapping representations, improving accuracy and efficiency.

Contribution

It presents a novel multimodal fusion and representation mapping framework for large-scale, location-specific traffic congestion prediction using deep learning.

Findings

Achieves significant prediction accuracy on real-world datasets.

Enables predictions at arbitrary locations on large-scale maps.

Demonstrates efficient inference in large-scale traffic scenarios.

Abstract

With the progress of the urbanisation process, the urban transportation system is extremely critical to the development of cities and the quality of life of the citizens. Among them, it is one of the most important tasks to judge traffic congestion by analysing the congestion factors. Recently, various traditional and machine-learning-based models have been introduced for predicting traffic congestion. However, these models are either poorly aggregated for massive congestion factors or fail to make accurate predictions for every precise location in large-scale space. To alleviate these problems, a novel end-to-end framework based on convolutional neural networks is proposed in this paper. With learning representations, the framework proposes a novel multimodal fusion module and a novel representation mapping module to achieve traffic congestion predictions on arbitrary query locations on a large-scale map, combined with various global reference information. The proposed framework achieves significant results and efficient inference on real-world large-scale datasets.