Short-term traffic flow prediction based on empirical mode decomposition and long short-term memory neural network

doi:10.11772/j.issn.1001-9081.2020060919

Abstract

Abstract: Traffic flow prediction is an important part of intelligent transportation. The traffic data to be processed by it are non-linear, periodic, and random, as a result, the unstable traffic flow data depend on long-term data range during data prediction. At the same time, due to some external factors, the original data often contain some noise, which may further lead to the degradation of prediction performance. Aiming at the above problems, a prediction algorithm named EMD-LSTM that can denoise and process long-term dependence was proposed. Firstly, Empirical Mode Decomposition (EMD) was used to decompose different scale components in the traffic time series data gradually to generate a series of intrinsic mode functions with the same feature scale, thereby removing certain noise influence. Then, with the help of Long Short-Term Memory (LSTM) neural network, the problem of long-term dependence of data was solved, so that the algorithm performed more outstanding in long-term field prediction. Experimental results of short-term prediction of actual datasets show that EMD-LSTM has the Mean Absolute Error (MAE) 1.916 32 lower than LSTM, and the Mean Absolute Percentage Error (MAPE) 4.645 45 percentage points lower than LSTM. It can be seen that the proposed hybrid model significantly improves the prediction accuracy and can solve the problem of traffic data effectively.

Key words: traffic time series data, noise, Empirical Mode Decomposition (EMD), Long Short-Term Memory (LSTM) neural network, traffic flow control strategy

摘要： 交通流量预测作为智能交通的重要一环，所要处理的交通数据具有非线性、周期性和随机性的特点，导致在数据预测时，不稳定的交通流量数据依赖于长期数据范围，且由于一些外部因素使得原始数常包含一些噪声，可能导致预测性能的进一步下降。针对上述问题提出了一种能够去噪且能处理长时依赖的预测算法——EMD-LSTM。首先，通过经验模态分解（EMD）算法将交通时序数据中的不同尺度分量逐级分解出来，生成一系列具有相同特征尺度的本征模函数，从而去除一定的噪声影响；然后，借助长短期记忆（LSTM）神经网络解决数据的长期依赖问题，从而使所提算法在长时间视野预测方面表现更为突出。对实际数据集进行短期预测的实验结果表明，EMD-LSTM的平均绝对误差（MAE）比LSTM低了1.916 32，平均绝对百分误差（MAPE）比LSTM降低了4.645 45个百分点，可见所提出的混合模型使预测准确性得到显著提高，能够有效解决交通数据的问题。

关键词: 交通时序数据, 噪声, 经验模态分解, 长短期记忆神经网络, 交通流量控制策略

CLC Number:

TP181

ZHANG Xiaohan, FENG Aimin. Short-term traffic flow prediction based on empirical mode decomposition and long short-term memory neural network[J]. Journal of Computer Applications, 2021, 41(1): 225-230.

张晓晗, 冯爱民. 基于经验模态分解和长短期记忆神经网络的短期交通流量预测[J]. 计算机应用, 2021, 41(1): 225-230.

References

[1] ZHOU T,HAN G,XU X,et al. A learning-based multimodel integrated framework for dynamic traffic flow forecasting[J]. Neural Processing Letters,2019,49(1):407-430.
[2] ZENG B,LI C. Improved multi-variable grey forecasting model with a dynamic background-value coefficient and its application[J]. Computers and Industrial Engineering,2018,118:278-290.
[3] WILLIAMS B M, DURVASULA P K, BROWN D E. Urban freeway traffic flow prediction:application of seasonal autoregressive integrated moving average and exponential smoothing models[J]. Transportation Research Record,1998,1644(1):132-141.
[4] XIE Y C,ZHANG Y,YE Z. Short-term traffic volume forecasting using Kalman filter with discrete wavelet decomposition[J]. Computer-Aided Civil and Infrastructure Engineering,2007,22(5):326-334.
[5] GUO J,HUANG W,WILLIAMS B M. Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification[J]. Transportation Research Part C:Emerging Technologies,2014,43(Pt 1):50-64.
[6] WANG Y,VAN SCHUPPEN J H,VRANCKEN J. Prediction of traffic flow at the boundary of a motorway network[J]. IEEE Transactions on Intelligent Transportation Systems,2014,15(1):214-227.
[7] COMERT G,BEZUGLOV A. An online change-point-based model for traffic parameter prediction[J]. IEEE Transactions on Intelligent Transportation Systems,2013,14(3):1360-1369.
[8] ZHANG X,PANG Y,CUI M,et al. Forecasting mortality of road traffic injuries in China using seasonal autoregressive integrated moving average model[J]. Annals of Epidemiology,2015,25(2):101-106.
[9] MIN W,WYNTER L. Real-time road traffic prediction with spatiotemporal correlations[J]. Transportation Research Part C:Emerging Technologies,2011,19(4):606-616.
[10] MA T,ZHOU Z,ABDULHAI B. Nonlinear multivariate timespace threshold vector error correction model for short term traffic state prediction[J]. Transportation Research Part B:Methodological,2015,76:27-47.
[11] TCHRAKIAN T T,BASU B,O'MAHONY M,et al. Real-time traffic flow forecasting using spectral analysis[J]. IEEE Transactions on Intelligent Transportation Systems,2012,13(2):519-526.
[12] ZHANG Y,ZHANG Y,HAGHANI A. A hybrid short-term traffic flow forecasting method based on spectral analysis and statistical volatility model[J]. Transportation Research Part C:Emerging Technologies,2014,43(Pt 1):65-78.
[13] GHOSH B,BASU B,O'MAHONY M. Multivariate short-term traffic flow forecasting using time-series analysis[J]. IEEE Transactions on Intelligent Transportation Systems,2009,10(2):246-254.
[14] HU X, XU X, XIAO Y, et al. SINet:a scale-insensitive convolutional neural network for fast vehicle detection[J]. IEEE Transactions on Intelligent Transportation Systems,2019,20(3):1010-1019.
[15] CAI P,WANG Y,LU G,et al. A spatiotemporal correlative knearest neighbor model for short-term traffic multistep forecasting[J]. Transportation Research Part C:Emerging Technologies, 2016,62:21-34.
[16] ABU ARQUB O,ABO-HAMMOUR Z S. Numerical solution of systems of second-order boundary value problems using continuous genetic algorithm[J]. Information Sciences,2014,279:396-415.
[17] ABU ARQUB O,AL-SMADI M,MOMANI S,et al. Application of reproducing kernel algorithm for solving second-order,two-point fuzzy boundary value problems[J]. Soft Computing,2017,21(23):7191-7206.
[18] CAI W,YU D,WU Z,et al. A hybrid ensemble learning framework for basketball outcomes prediction[J]. Physica A:Statistical Mechanics and its Applications, 2019, 528:No. 121461.
[19] CHENG A,JIANG X,LI Y,et al. Multiple sources and multiple measures based traffic flow prediction using the chaos theory and support vector regression method[J]. Physica A:Statistical Mechanics and its Applications,2017,466:422-434.
[20] XIAO J,WEI C,LIU Y. Speed estimation of traffic flow using multiple kernel support vector regression[J]. Physica A:Statistical Mechanics and its Applications,2018,509:989-997.
[21] 刘明宇, 吴建平, 王钰博, 等. 基于深度学习的交通流量预测[J]. 系统仿真学报,2018,30(11):4100-4105,4114.(LIU M Y,WU J P,WANG Y B,et al. Traffic flow prediction based on deep learning[J]. Journal of System Simulation,2018,30(11):4100-4105,4114.)
[22] 罗文慧, 董宝田, 王泽胜. 基于CNN-SVR混合深度学习模型的短时交通流预测[J]. 交通运输系统工程与信息,2017,17(5):68-74.(LUO W H,DONG B T,WANG Z S. Short-term traffic flow prediction based on CNN-SVR hybrid deep learning model[J]. Journal of Transportation Systems Engineering and Information Technology,2017,17(5):68-74.)
[23] HUANG N E,SHEN Z,LONG S R,et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and nonstationary time series analysis[J]. Proceedings of the Royal Society A:Mathematical Physical and Engineering Sciences, 1998,454(1971):903-995.
[24] NUNES J C,BOUAOUNE Y,DELECHELLE E,et al. Image analysis by bidimensional empirical mode decomposition[J]. Image and Vision Computing,2003,21(12):1019-1026.
[25] 叶林, 刘鹏. 基于经验模态分解和支持向量机的短期风电功率组合预测模型[J]. 中国电机工程学报,2011,31(31):102-108.(YE L,LIU P. Combined model based on EMD-SVM for short-term wind power prediction[J]. Proceedings of the CSEE, 2011,31(31):102-108.)
[26] LIU B,RIEMENSCHNEIDER S,XU Y. Gearbox fault diagnosis using empirical mode decomposition and Hilbert spectrum[J]. Mechanical Systems and Signal Processing, 2006, 20(3):718-734.
[27] YILDIRIM S,JOTHIMANI D,KAVAKLIOĞLU C,et al. Deep learning approaches for sentiment analysis on financial microblog dataset[C]//Proceeding of the 2019 IEEE International Conference on Big Data. Piscataway:IEEE,2019:5581-5584.