Attention-LSTM for Multivariate Traffic State Prediction on Rural Roads

TL;DR

This paper introduces an Attention-based LSTM model for predicting traffic volume and speed on rural roads, demonstrating improved accuracy over traditional LSTM, especially at 15-minute intervals, with cyclic feature encoding further enhancing performance.

Contribution

The study proposes a novel A-LSTM model for rural traffic prediction and compares its performance with LSTM, highlighting the benefits of cyclic feature encoding for temporal data.

Findings

A-LSTM outperforms LSTM at 5 and 15-minute intervals.

15-minute horizon yields the lowest MSE of 0.0032.

Cyclic feature encoding improves model accuracy over one-hot encoding.

Abstract

Accurate traffic volume and speed prediction have a wide range of applications in transportation. It can result in useful and timely information for both travellers and transportation decision-makers. In this study, an Attention based Long Sort-Term Memory model (A-LSTM) is proposed to simultaneously predict traffic volume and speed in a critical rural road segmentation which connects Tehran to Chalus, the most tourist destination city in Iran. Moreover, this study compares the results of the A-LSTM model with the Long Short-Term Memory (LSTM) model. Both models show acceptable performance in predicting speed and flow. However, the A-LSTM model outperforms the LSTM in 5 and 15-minute intervals. In contrast, there is no meaningful difference between the two models for the 30-minute time interval. By comparing the performance of the models based on different time horizons, the 15-minute horizon model outperforms the others by reaching the lowest Mean Square Error (MSE) loss of 0.0032, followed by the 30 and 5-minutes horizons with 0.004 and 0.0051, respectively. In addition, this study compares the results of the models based on two transformations of temporal categorical input variables, one-hot or cyclic, for the 15-minute time interval. The results demonstrate that both LSTM and A-LSTM with cyclic feature encoding outperform those with one-hot feature encoding.