Traffic Flow Imputation Using Parallel Data and Generative Adversarial Networks

• Published in: IEEE transactions on intelligent transportation systems Vol. 21; no. 4; pp. 1624 - 1630
• Main Authors: Chen, Yuanyuan, Lv, Yisheng, Wang, Fei-Yue
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.04.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Biological system modeling; data augmentation; Data mining; Data models; deep learning; Gallium nitride; Generative adversarial networks; Generators; Intelligent transportation systems; Loss measurement; Model accuracy; Parallel data; Performance enhancement; Standardization; Time dependence; Traffic flow; traffic flow imputation; Traffic information; Traffic models; Training; Transportation networks
• ISSN: 1524-9050; 1558-0016
• DOI: 10.1109/TITS.2019.2910295

Traffic data imputation is critical for both research and applications of intelligent transportation systems. To develop traffic data imputation models with high accuracy, traffic data must be large and diverse, which is costly. An alternative is to use synthetic traffic data, which is cheap and easy-access. In this paper, we propose a novel approach using parallel data and generative adversarial networks (GANs) to enhance traffic data imputation. Parallel data is a recently proposed method of using synthetic and real data for data mining and data-driven process, in which we apply GANs to generate synthetic traffic data. As it is difficult for the standard GAN algorithm to generate time-dependent traffic flow data, we made twofold modifications: 1) using the real data or the corrupted ones instead of random vectors as latent codes to generator within GANs and 2) introducing a representation loss to measure discrepancy between the synthetic data and the real data. The experimental results on a real traffic dataset demonstrate that our method can significantly improve the performance of traffic data imputation.