Traffic flow prediction by an ensemble framework with data denoising and deep learning model

Abstract Accurate traffic flow data is important for traffic flow state estimation, real-time traffic management and control, etc. Raw traffic flow data collected from inductive detectors may be contaminated by different noises (e.g., sharp data increase/decrease, trivial anomaly oscillations) under various unexpected interference (caused by roadway maintenance, loop detector damage, etc.). To address the issue, we introduced data denoising schemes (i.e., Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD) and Wavelet (WL)) to suppress the potential data outliers. After that, the Long Short-Term Memory (LSTM) neural network was introduced to fulfill the traffic flow prediction task. We have tested the proposed framework performance on three traffic flow data sets, which were downloaded from Caltrans Performance Measurement System (PeMS). The experimental results showed that the LSTM+EEMD scheme obtained higher accuracy considering that the average Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) are 0.79, 0.60 and 2.14.

[1]  Jinjun Tang,et al.  Ship Type Recognition via a Coarse-to-Fine Cascaded Convolution Neural Network , 2020, Journal of Navigation.

[2]  Tao Ma,et al.  Dynamic factor model for network traffic state forecast , 2018, Transportation Research Part B: Methodological.

[3]  Jinjun Tang,et al.  Anomaly Detection and Cleaning of Highway Elevation Data from Google Earth Using Ensemble Empirical Mode Decomposition , 2018 .

[4]  Jayashri Vajpai,et al.  Seasonal Time Series Forecasting by Group Method of Data Handling , 2018, 2018 IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS).

[5]  Jonas Lüßmann,et al.  Controller Independent Software-in-the-Loop Approach to Evaluate Rule-Based Traffic Signal Retiming Strategy by Utilizing Floating Car Data , 2019, IEEE Transactions on Intelligent Transportation Systems.

[6]  Jinjun Tang,et al.  A Denoising Scheme-Based Traffic Flow Prediction Model: Combination of Ensemble Empirical Mode Decomposition and Fuzzy C-Means Neural Network , 2020, IEEE Access.

[7]  Afshin Shariat Mohaymany,et al.  A new methodology for vehicle trajectory reconstruction based on wavelet analysis , 2017 .

[8]  Yong Liu,et al.  Two-echelon location-routing optimization with time windows based on customer clustering , 2018, Expert Syst. Appl..

[9]  Junjie Yang,et al.  A noise-immune Kalman filter for short-term traffic flow forecasting , 2019 .

[10]  Zhirui Ye,et al.  Short‐Term Traffic Volume Forecasting Using Kalman Filter with Discrete Wavelet Decomposition , 2007, Comput. Aided Civ. Infrastructure Eng..

[11]  Fang Liu,et al.  An Improved Fuzzy Neural Network for Traffic Speed Prediction Considering Periodic Characteristic , 2017, IEEE Transactions on Intelligent Transportation Systems.

[12]  Helai Huang,et al.  Statistical and machine-learning methods for clearance time prediction of road incidents: A methodology review , 2020, Analytic Methods in Accident Research.

[13]  Wenwu Wang,et al.  Short-Term Traffic Flow Prediction With Wavelet and Multi-Dimensional Taylor Network Model , 2021, IEEE Transactions on Intelligent Transportation Systems.

[14]  Zhongren Wang,et al.  Implementing a pavement management system: The Caltrans experience , 2019, International Journal of Transportation Science and Technology.

[15]  Jinjun Tang,et al.  Traffic flow prediction based on combination of support vector machine and data denoising schemes , 2019, Physica A: Statistical Mechanics and its Applications.

[16]  Yanni Peng,et al.  Short-term traffic volume prediction using GA-BP based on wavelet denoising and phase space reconstruction , 2020 .

[17]  Gao Fei,et al.  Identifying activities and trips with GPS data , 2018, IET Intelligent Transport Systems.

[18]  Hai Le Vu,et al.  An effective spatial-temporal attention based neural network for traffic flow prediction , 2019, Transportation Research Part C: Emerging Technologies.

[19]  Petros A. Ioannou,et al.  Traffic Flow Prediction for Road Transportation Networks With Limited Traffic Data , 2015, IEEE Transactions on Intelligent Transportation Systems.

[20]  Zheng Hu,et al.  Short-Term Traffic Flow Prediction Considering Spatio-Temporal Correlation: A Hybrid Model Combing Type-2 Fuzzy C-Means and Artificial Neural Network , 2019, IEEE Access.

[21]  Philip S. Yu,et al.  Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting , 2020, Inf. Sci..

[22]  Ren Wang,et al.  Comparing traffic state estimators for mixed human and automated traffic flows , 2017 .

[23]  Mayara Condé Rocha Murça,et al.  Identification, Characterization, and Prediction of Traffic Flow Patterns in Multi-Airport Systems , 2019, IEEE Transactions on Intelligent Transportation Systems.

[24]  Huafeng Wu,et al.  Robust Ship Tracking via Multi-view Learning and Sparse Representation , 2018, Journal of Navigation.

[25]  Ching-Yao Chan,et al.  Real-time estimation of freeway travel time with recurrent congestion based on sparse detector data , 2018 .

[26]  Li-Der Chou,et al.  Congestion Prediction With Big Data for Real-Time Highway Traffic , 2018, IEEE Access.

[27]  Fang Zong,et al.  Taxi Drivers’ Cruising Patterns—Insights from Taxi GPS Traces , 2019, IEEE Transactions on Intelligent Transportation Systems.

[28]  Dazhi Jiang,et al.  Hybrid dual Kalman filtering model for short‐term traffic flow forecasting , 2019, IET Intelligent Transport Systems.

[29]  Pengwen Xiong,et al.  Robust Visual Ship Tracking with an Ensemble Framework via Multi-View Learning and Wavelet Filter , 2020, Sensors.

[30]  Yong Qi,et al.  Markov Chains based route travel time estimation considering link spatio-temporal correlation , 2020 .

[31]  Gurcan Comert,et al.  An Online Change-Point-Based Model for Traffic Parameter Prediction , 2013, IEEE Transactions on Intelligent Transportation Systems.

[32]  Y. Shrivastava,et al.  A comparative study of EMD and EEMD approaches for identifying chatter frequency in CNC turning , 2019, European Journal of Mechanics - A/Solids.

[33]  Jian Wang,et al.  Construction of traffic state vector using mutual information for short-term traffic flow prediction , 2018, Transportation Research Part C: Emerging Technologies.

[34]  Yong Wang,et al.  Profit distribution in collaborative multiple centers vehicle routing problem , 2017 .

[35]  Feng Shu,et al.  Short-term traffic flow prediction based on spatio-temporal analysis and CNN deep learning , 2019, Transportmetrica A: Transport Science.

[36]  Neeraj Kumar,et al.  Convolutional neural networks for 5G-enabled Intelligent Transportation System : A systematic review , 2020, Comput. Commun..

[37]  Huafeng Wu,et al.  Augmented Ship Tracking Under Occlusion Conditions From Maritime Surveillance Videos , 2020, IEEE Access.

[38]  Yinhai Wang,et al.  Speed Prediction Based on a Traffic Factor State Network Model , 2021, IEEE transactions on intelligent transportation systems (Print).