An Improved Bayesian Combination Model for Short-Term Traffic Prediction With Deep Learning

Gu, Yuanli; Lu, Wenqi; Xu, Xinyue; Qin, Lingqiao; Shao, Zhuangzhuang; Zhang, Hanyu

doi:10.1109/tits.2019.2939290

Cited by 124 publications

(65 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wu et al [14] established a hybrid deep neural network, which employs a convolutional neural network to mine the spatial features and uses the recurrent neural network to mine the temporal features of traffic flow, to predict traffic flow in a long-term horizon. Gu et al [4] put forward an improved Bayesian combination method which fuses a traditional parametric model, a non-parametric model, and an RNN-based model to take advantage of each method. Wang et al [46] combined the empirical mode decomposition (EMD) with the ARIMA model to predict traffic speeds in varying scenarios such as mixed traffic flow.…”

Section: Hybrid Modelsmentioning

confidence: 99%

“…However, with the rapid improvement of the connected automated vehicle highway (CAVH) system [3], short-term traffic flow forecasting has been gradually shifting from the section-based or network-based methods to lane-based methods [4]. In the environment of the CAVH system, the traffic flow on the road is generally mixed with human-driven vehicles (HDVs) and connected automated vehicles (CAVs) [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Hybrid Model for Lane-Level Traffic Flow Forecasting Based on Complete Ensemble Empirical Mode Decomposition and Extreme Gradient Boosting

Rui

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Accurate and efficient lane-level traffic flow prediction is a challenging issue in the framework of the connected automated vehicle highway system. However, most existing traffic flow forecasting methods concentrate on mining the spatio-temporal characteristics of the traffic flow rather than increasing predictability of traffic flow. In this paper, we propose a novel hybrid model (CEEMDAN-XGBoost) for lane-level traffic flow prediction based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and extreme gradient boosting (XGBoost). The CEEMDAN method is introduced to decompose the raw traffic flow data into several intrinsic mode function components and one residual component. Then, the XGBoost methods are trained and make predictions on the decomposed components respectively. The final prediction results are obtained by integrating the prediction outputs of the XGBoost methods. For illustrative purposes, the ground-truth lane-level traffic flow data captured by remote traffic microwave sensors installed on the 3 rd Ring Road of Beijing are utilized to evaluate the effectiveness of the CEEMDAN-XGBoost model. The experimental results confirm that the CEEMDAN-XGBoost model is capable of fitting the complex volatility of traffic flow efficiently at different types of lane sections. Moreover, the proposed model outperforms the state-of-the-art models (e.g., artificial neural networks and long shortterm memory neural network) and other XGBoost-based models in terms of prediction accuracy and stability. INDEX TERMS Data mining, lane-level traffic flow, short-term prediction, hybrid model, extreme gradient boosting, complete ensemble empirical mode decomposition, urban expressways.

show abstract

Section: Hybrid Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Hybrid Model for Lane-Level Traffic Flow Forecasting Based on Complete Ensemble Empirical Mode Decomposition and Extreme Gradient Boosting

Rui

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Yu et al [47] proposed forecasted road traffic speeds by considering area‐wide spatio‐temporal dependencies based on a graph convolutional neural network. Gu et al [48] utilised an improved Bayesian combination model with deep learning to predict the traffic volume by assigning appropriate weights to different sub‐predictors by considering their performance during the several past time intervals. Niu et al [49] utilised the temporal–spatial model to predict the speed of the road network, which is also suitable for long‐term traffic flow prediction.…”

Section: Related Workmentioning

confidence: 99%

Efficient deep learning based method for multi‐lane speed forecasting: a case study in Beijing

Wan

et al. 2020

IET intell. transp. syst

Self Cite

View full text Add to dashboard Cite

Real-time and accurate multi-lane traffic condition forecasting is of great importance to the connected and automated vehicle highway system. However, the majority of existing deep learning based traffic prediction methods focus on pursuing the precision of the methods while neglect to improve the efficiency of the methods. To achieve the high accuracy and high efficiency of multi-lane traffic flow prediction simultaneously, this study proposes a novel combination method via the integration of the clockwork recurrent neural network (CWRNN) and random forest (RF) method, which is RF-CWRNN. To the best of the authors' knowledge, this is the first time that the CWRNN is introduced to capture the temporal feature of lane-level traffic flow and make traffic speed prediction. Meanwhile, the RF method is employed to measure the temporal relevance of the traffic flow and determine the optimal input time window. To verify the performance of the RF-CWRNN method, the ground-truth data of the expressways in Beijing were utilised to carry out experiments. The results indicate that the RF-CWRNN method is superior to the baseline models in terms of accuracy and robustness. Besides, the proposed method can save plenty of training time compared with the classical long short-term memory neural network.

show abstract

“…Ding et al [31] integrated the outputs of ARIMA and generalized autoregressive conditional heteroskedasticity (GARCH) to estimate the volatility of the passenger demand. Also, Gu et al [32] used the Bayesian method to combine the outputs of the three sub-predictors, including the gated recurrent unit neural network (GRUNN), ARIMA, and radial basis function neural network (RBFNN). Peyman et al [33] combined the prediction of the state-space model and dynamic factor model, which shows promising performance for abnormal passenger flow prediction.…”

Section: Introductionmentioning

confidence: 99%

Short-Term Passenger Flow Prediction With Decomposition in Urban Railway Systems

Zhao

Yang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Accurate prediction of short-term passenger flow is vital for real-time operations control and management. Identifying passenger demand patterns and selecting appropriate methods are promising to improve prediction accuracy. This paper proposes a hybrid prediction model with time series decomposition and explores its performance for different types of passenger flows with varied characteristics in urban railway systems. The Seasonal and Trend decomposition using Loess (STL) is used to decompose the passenger flow into the seasonal, trend, and residual time series, representing the constant, long-term fluctuant, and stochastic passenger demand patterns. The approximate entropy (ApEn) is utilized to quantify the predictability of each component. After that, the Holt-Winters (HW) method is developed to predict the seasonal and trend components that both with high predictability. The long short-term memory networks (LSTM NN) are proposed to predict the residual with low predictability. The outputs from these models are combined to predict the short-term passenger flow. We assess the model performance with entry, exit, and transfer passenger flows at the target stations, which are selected via the agglomerative hierarchical clustering (AHC) algorithm in the Shanghai Metro. Compared with three representative models, the results show that 1) the decomposition-based hybrid model performs well for both one-step and multi-step predictions in terms of accuracy and robustness; 2) ApEn is useful for choosing appropriate prediction models. INDEX TERMS Short-term metro passenger flow prediction, Seasonal and Trend decomposition using Loess (STL)-based model, approximate entropy (ApEn), agglomerative hierarchical clustering (AHC) algorithm I. Yangyang Zhao received the B.E. degree and the M.E. degree in transportation engineering from Chang'an University, Xi'an, Shaanxi, China, in 2014 and 2017. He is currently pursuing the Ph.D. degree in transportation planning and management with the school of transportation and logistics,

show abstract

An Improved Bayesian Combination Model for Short-Term Traffic Prediction With Deep Learning

Cited by 124 publications

References 51 publications

A Hybrid Model for Lane-Level Traffic Flow Forecasting Based on Complete Ensemble Empirical Mode Decomposition and Extreme Gradient Boosting

A Hybrid Model for Lane-Level Traffic Flow Forecasting Based on Complete Ensemble Empirical Mode Decomposition and Extreme Gradient Boosting

Efficient deep learning based method for multi‐lane speed forecasting: a case study in Beijing

Short-Term Passenger Flow Prediction With Decomposition in Urban Railway Systems

Contact Info

Product

Resources

About