IGANI: Iterative Generative Adversarial Networks for Imputation with Application to Traffic Data

TL;DR

This paper introduces IGANI, an iterative GAN-based method for imputing missing traffic data, demonstrating improved accuracy over previous GAN approaches in real-world traffic datasets.

Contribution

The paper proposes a novel iterative GAN architecture for traffic data imputation that ensures convergence and improves accuracy over existing GAN-based methods.

Findings

IGANI outperforms previous GAN-based imputation methods in traffic data accuracy.

The method effectively imputes multi-variable traffic data with varying missing rates.

Imputed data enables more accurate short-term traffic prediction models.

Abstract

Increasing use of sensor data in intelligent transportation systems calls for accurate imputation algorithms that can enable reliable traffic management in the occasional absence of data. As one of the effective imputation approaches, generative adversarial networks (GANs) are implicit generative models that can be used for data imputation, which is formulated as an unsupervised learning problem. This work introduces a novel iterative GAN architecture, called Iterative Generative Adversarial Networks for Imputation (IGANI), for data imputation. IGANI imputes data in two steps and maintains the invertibility of the generative imputer, which will be shown to be a sufficient condition for the convergence of the proposed GAN-based imputation. The performance of our proposed method is evaluated on (1) the imputation of traffic speed data collected in the city of Guangzhou in China, and the training of short-term traffic prediction models using imputed data, and (2) the imputation of multi-variable traffic data of highways in Portland-Vancouver metropolitan region which includes volume, occupancy, and speed with different missing rates for each of them. It is shown that our proposed algorithm mostly produces more accurate results compared to those of previous GAN-based imputation architectures.