Missing Data in Traffic Estimation: A Variational Autoencoder Imputation Method

Abstract

Road traffic forecasting systems are in scenarios where sensor or system failure occur. In those scenarios, it is known that missing values negatively affect estimation accuracy although it is being often underestimate in current deep neural network approaches. Our assumption is that traffic data can be generated from a latent space. Thus, we propose an online unsupervised data imputation method based on learning the data distribution using a variational autoencoder (VAE). This is used as an independent pre-processing step prior to traffic forecasting which is then evaluated against missing data of a real-world dataset. Compared to other methods, we show that VAE improves post-imputation traffic forecasting performance while allowing for data augmentation, data compression and traffic classification at the same time.