Decentralized Data Fusion and Active Sensing with Mobile Sensors for Modeling and Predicting Spatiotemporal Traffic Phenomena

TL;DR

This paper introduces a decentralized algorithm for mobile sensors to efficiently model and predict urban traffic patterns, scaling well with many sensors and observations, and matching centralized methods in accuracy.

Contribution

The paper proposes a novel decentralized data fusion and active sensing algorithm that is scalable, efficient, and provides theoretical guarantees comparable to centralized Gaussian process models.

Findings

D2FAS scales well with many sensors and observations

Achieves similar predictive accuracy to centralized models

Significantly more time-efficient and scalable than existing methods

Abstract

The problem of modeling and predicting spatiotemporal traffic phenomena over an urban road network is important to many traffic applications such as detecting and forecasting congestion hotspots. This paper presents a decentralized data fusion and active sensing (D2FAS) algorithm for mobile sensors to actively explore the road network to gather and assimilate the most informative data for predicting the traffic phenomenon. We analyze the time and communication complexity of D2FAS and demonstrate that it can scale well with a large number of observations and sensors. We provide a theoretical guarantee on its predictive performance to be equivalent to that of a sophisticated centralized sparse approximation for the Gaussian process (GP) model: The computation of such a sparse approximate GP model can thus be parallelized and distributed among the mobile sensors (in a Google-like MapReduce paradigm), thereby achieving efficient and scalable prediction. We also theoretically guarantee its active sensing performance that improves under various practical environmental conditions. Empirical evaluation on real-world urban road network data shows that our D2FAS algorithm is significantly more time-efficient and scalable than state-of-the-art centralized algorithms while achieving comparable predictive performance.