Using LSTM and GRU neural network methods for traffic flow prediction

Fu, Rui; Zuo, Zhigang; Li, Li

doi:10.1109/yac.2016.7804912

Cited by 1,002 publications

(487 citation statements)

References 8 publications

Supporting

Mentioning

472

Contrasting

Unclassified

Order By: Relevance

“…Model accuracy is the opposite measure of the MAPE values. Equation 16 represents the formula of accuracy of the model. For each ATR, we compare 21 different models based on the type of missing data treatment method and the variety of transfer functions used in the repeater block of the RNN model.…”

Section: Analysis and Resultsmentioning

confidence: 99%

Development and Evaluation of Recurrent Neural Network-Based Models for Hourly Traffic Volume and Annual Average Daily Traffic Prediction

Khan

Chowdhury

et al. 2019

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Word count: Abstract = 244 words, Text 7025 + 5 Tables 1250 + 17 Figures = 8275 words, Reference = 712 words Initial Paper ABSTRACTThe prediction of high-resolution hourly traffic volumes of a given roadway is essential for transportation planning. Traditionally, Automatic Traffic Recorders (ATR) are used to collect this hourly volume data. These large datasets are time series data characterized by long-term temporal dependencies and missing values. Regarding the temporal dependencies, all roadways are characterized by seasonal variations that can be weekly, monthly or yearly, depending on the cause of the variation. Regarding the missing data in a time-series sequence, traditional time series forecasting models perform poorly under the influence of seasonal variations. To address this limitation, robust, Recurrent Neural Network (RNN) based, multi-step ahead forecasting models are developed for time-series in this study. The simple RNN, the Gated Recurrent Unit (GRU) and the Long Short-Term Memory (LSTM) units are used to develop the model and evaluate its performance. Two approaches are used to address the missing value issue: masking and imputation, in conjunction with the RNN models. Six different imputation algorithms are then used to identify the best model. The analysis indicates that the LSTM model performs better than simple RNN and GRU models, and imputation performs better than masking to predict future traffic volume. Based on analysis using 92 ATRs, the LSTM-Median model is deemed the best model in all scenarios for hourly traffic volume and AADT prediction, with an average RMSE of 274 and MAPE of 18.91% for hourly traffic volume prediction and average RMSE of 824 and MAPE of 2.10% for AADT prediction. The hourly traffic volume roadway data is an important high-resolution dataset used to describe the operational characteristics of a transportation system. Accurate hourly traffic volumes can be utilized in calculating the Average Annual Daily Traffic (AADT). AADT is an essential parameter in many transportation models and decisions. Moreover, the prediction of future hourly traffic volumes of a given roadway is even more important than current data because it can be used to estimate future growth. Here, the volume growth factor of a roadway can be combined with other external data to predict the overall growth pattern of an area. Moreover, the high-resolution data provides insight into the factors contributing to growth, as it may be a gradual growth pattern or a sudden peak. The roadway volume can increase at a very specific time next year due to some special events, and a predictive model can predict this change. This means that the special event is a phenomenon that has occurred before. However, if a predictive model is unable to capture this event, then it is a new phenomenon that has not been previously observed. Therefore, the detection of special events or anomalies is also an application of high-resolution hourly volumes.Transportation planning is characterized by many projects that are relate...

show abstract

Section: Analysis and Resultsmentioning

confidence: 99%

Development and Evaluation of Recurrent Neural Network-Based Models for Hourly Traffic Volume and Annual Average Daily Traffic Prediction

Khan

Chowdhury

et al. 2019

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…Notably, an influence function was designed to help recognize congestion sources. Two RNN models, namely, LSTM and gated recurrent units, were used by Fu, Zhang, and Li () to predict short‐term traffic flow. It should be noted that the data of these online hailing vehicles contain both spatial and temporal features that are often neglected in traffic state prediction, leading to a waste of valuable information.…”

Section: Literature Reviewmentioning

confidence: 99%

A spatio‐temporal ensemble method for large‐scale traffic state prediction

Liu

et al. 2019

Computer aided Civil Eng

View full text Add to dashboard Cite

How to effectively ensemble multiple models while leveraging the spatio‐temporal information is a challenging but practical problem. However, there is no existing ensemble method explicitly designed for spatio‐temporal data. In this paper, a fully convolutional model based on semantic segmentation technology is proposed, termed as spatio‐temporal ensemble net. The proposed method is suitable for grid‐based spatio‐temporal prediction in dense urban areas. Experiments demonstrate that through spatio‐temporal ensemble net, multiple traffic state prediction base models can be combined to improve the prediction accuracy.

show abstract

“…In [17] the authors proposed the use of LSTM and GRU networks for forecasting of traffic flow time series, comparing the results achieved with an ARIMA model. The LSTM and GRU results are better than ARIMA for this type of time series.…”

Section: Long Short-term Memory (Lstm)mentioning

confidence: 99%

Improving Gated Recurrent Unit Predictions with Univariate Time Series Imputation Techniques

Flores¹,

Tito²,

Centty³

2019

IJACSA

View full text Add to dashboard Cite

The work presented in this paper has its main objective to improve the quality of the predictions made with the recurrent neural network known as Gated Recurrent Unit (GRU). For this, instead of making different adjustments to the architecture of the neural network in question, univariate time series imputation techniques such as Local Average of Nearest Neighbors (LANN) and Case Based Reasoning Imputation (CBRi) are used. It is experimented with different gap-sizes, from 1 to 11 consecutive NAs, resulting in the best gap-size of six consecutive NA values for LANN and for CBRi the gap-size of two NA values. The results show that both imputation techniques allow improving prediction quality of Gated Recurrent Unit, being LANN better than CBRi, thus the results of the best configurations of LANN and CBRi allowed to surpass the techniques with which they were compared.

show abstract

Using LSTM and GRU neural network methods for traffic flow prediction

Cited by 1,002 publications

References 8 publications

Development and Evaluation of Recurrent Neural Network-Based Models for Hourly Traffic Volume and Annual Average Daily Traffic Prediction

Development and Evaluation of Recurrent Neural Network-Based Models for Hourly Traffic Volume and Annual Average Daily Traffic Prediction

A spatio‐temporal ensemble method for large‐scale traffic state prediction

Improving Gated Recurrent Unit Predictions with Univariate Time Series Imputation Techniques

Contact Info

Product

Resources

About