Spatiotemporal Tensor Completion for Improved Urban Traffic Imputation

TL;DR

This paper introduces an advanced tensor completion method for urban traffic data that incorporates urban and temporal features, significantly improving missing data recovery in smart city traffic management.

Contribution

The paper proposes a novel spatiotemporal tensor completion approach that integrates urban similarity and temporal periodicity into an enhanced CP framework for traffic data imputation.

Findings

Achieves up to 26% better recovery than traditional CP methods.

Outperforms generative model-based approaches by 35%.

Effective in scenarios with random and area-specific missing data.

Abstract

Effective management of urban traffic is important for any smart city initiative. Therefore, the quality of the sensory traffic data is of paramount importance. However, like any sensory data, urban traffic data are prone to imperfections leading to missing measurements. In this paper, we focus on inter-region traffic data completion. We model the inter-region traffic as a spatiotemporal tensor that suffers from missing measurements. To recover the missing data, we propose an enhanced CANDECOMP/PARAFAC (CP) completion approach that considers the urban and temporal aspects of the traffic. To derive the urban characteristics, we divide the area of study into regions. Then, for each region, we compute urban feature vectors inspired from biodiversity which are used to compute the urban similarity matrix. To mine the temporal aspect, we first conduct an entropy analysis to determine the most regular time-series. Then, we conduct a joint Fourier and correlation analysis to compute its periodicity and construct the temporal matrix. Both urban and temporal matrices are fed into a modified CP-completion objective function. To solve this objective, we propose an alternating least square approach that operates on the vectorized version of the inputs. We conduct comprehensive comparative study with two evaluation scenarios. In the first one, we simulate random missing values. In the second scenario, we simulate missing values at a given area and time duration. Our results demonstrate that our approach provides effective recovering performance reaching 26% improvement compared to state-of-art CP approaches and 35% compared to state-of-art generative model-based approaches.