Attention-based Gated Recurrent Unit for Links Traffic Speed Forecasting

Khodabandelou, Ghazaleh; Katranji, Mehdi; Kraïem, Sami; Kheriji, Walid; Fouad, HadjSelem

doi:10.1109/itsc.2019.8917027

Cited by 5 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We identified two statistical models which are specifically suitable for double seasonality data, that is, double seasonal Holt-Winter (DSHW) and trigonometric seasonality, Box-Cox transformation, autoregressive integrated moving average (ARIMA) errors, trend and seasonal components (TBATS). Further, five ML models (MLP) [6] (LSTM) [15,16], gated recurrent unit (GRU) [17,18], convolutional-neural networks (CNN) [19,20] and CNN-LSTM [21,22] were also implemented. Seasonal autoregressive integrated moving average (SARIMA) was used as the benchmark.…”

mentioning

confidence: 99%

Traffic speed prediction of high‐frequency time series using additively decomposed components as features

Ali

Yusof

Wilson³

et al. 2022

IET Smart Cities

View full text Add to dashboard Cite

Traffic speed prediction is an integral part of an Intelligent Transportation System (ITS) and the Internet of Vehicles (IoV). Advanced knowledge of average traffic speed can help take proactive preventive steps to avoid impending problems. There have been studies for traffic speed prediction in which data has been decomposed into components using various decomposition techniques such as empirical mode decomposition, wavelets, and seasonal decomposition. As far as the authors are aware, no research has used additively decomposed components as input features. In this study, we used additive decomposition on 21,843 samples of traffic speed data. We implemented two statistical techniques designed for double seasonality (i) Double Seasonal Holt‐Winter, and (ii) Trigonometric seasonality, Box‐Cox transformation, autoregressive integrated moving average errors, trend, and Seasonal components (TBATS), and five machine learning (ML) techniques, (i) Multi‐Layer Perceptron, (ii) Convolutional‐Neural Network, (iii) Long Short‐Term Memory, (iv) Gated Recurrent Unit and (v) Convolutional‐Neural Network‐LSTM. Machine learning techniques are used in univariate mode with raw time series as features and then with decomposed components as features in multivariate mode. This study demonstrates that using decomposed components (trend, seasonal, and residual), as features, improves prediction results for multivariate ML techniques. This becomes a significant advantage when no other features are available.

show abstract