New Results on Multi-Step Traffic Flow Prediction
This work addresses a challenging problem in traffic management by enhancing prediction accuracy for multiple future time steps, though it appears incremental as it builds on existing recursive and multi-output frameworks.
The paper tackles the problem of multi-step traffic flow prediction, which suffers from performance degradation over longer time horizons, by introducing two methods: a recursive prediction model incorporating temporal context and a conditional GAN-based data augmentation for multi-output settings, with experiments on a real-world dataset showing improved performance.
In its simplest form, the traffic flow prediction problem is restricted to predicting a single time-step into the future. Multi-step traffic flow prediction extends this set-up to the case where predicting multiple time-steps into the future based on some finite history is of interest. This problem is significantly more difficult than its single-step variant and is known to suffer from degradation in predictions as the time step increases. In this paper, two approaches to improve multi-step traffic flow prediction performance in recursive and multi-output settings are introduced. In particular, a model that allows recursive prediction approaches to take into account the temporal context in term of time-step index when making predictions is introduced. In addition, a conditional generative adversarial network-based data augmentation method is proposed to improve prediction performance in the multi-output setting. The experiments on a real-world traffic flow dataset show that the two methods improve on multi-step traffic flow prediction in recursive and multi-output settings, respectively.