TY - JOUR
T1 - A noise-immune Kalman filter for short-term traffic flow forecasting
AU - Cai, Lingru
AU - Zhang, Zhanchang
AU - Yang, Junjie
AU - Yu, Yidan
AU - Zhou, Teng
AU - Qin, Jing
N1 - Funding Information:
This work is supported by the NSFC, China (Grant No. 61902232 ), the Natural Science Foundation of Guangdong Province, China (No. 2018A030313291 , 2018A030313889 ), the Education Science Planning Project of Guangdong Province, China ( 2018GXJK048 ), the STU Scientific Research Foundation for Talents ( NTF18006 ), the Science and Technology Planning Project of Guangdong Province, China ( 2016B010124012 , 2019B010116001 ), and the grant from the Hong Kong Polytechnic University, China (No. 1ZE8J ).
Publisher Copyright:
© 2019 Elsevier B.V.
PY - 2019/12/15
Y1 - 2019/12/15
N2 - This paper formulates the traffic flow forecasting task by introducing a maximum correntropy deduced Kalman filter. The traditional Kalman filter is based on minimum mean square error, which performs well under Gaussian noises. However, the real traffic flow data are fulfilled with non-Gaussian noises. The traditional Kalman filter may rot under this situation. The Kalman filter deduced by maximum correntropy criteria is insensitive to non-Gaussian noises, meanwhile retains the optimal state mean and covariance propagation of the traditional Kalman filter. To achieve this, a fix-point algorithm is embedded to update the posterior estimations of maximum correntropy deduced Kalman filter. Extensive experiments on four benchmark datasets demonstrate the outperformance of this model for traffic flow forecasting.
AB - This paper formulates the traffic flow forecasting task by introducing a maximum correntropy deduced Kalman filter. The traditional Kalman filter is based on minimum mean square error, which performs well under Gaussian noises. However, the real traffic flow data are fulfilled with non-Gaussian noises. The traditional Kalman filter may rot under this situation. The Kalman filter deduced by maximum correntropy criteria is insensitive to non-Gaussian noises, meanwhile retains the optimal state mean and covariance propagation of the traditional Kalman filter. To achieve this, a fix-point algorithm is embedded to update the posterior estimations of maximum correntropy deduced Kalman filter. Extensive experiments on four benchmark datasets demonstrate the outperformance of this model for traffic flow forecasting.
KW - Intelligent transportation systems
KW - Kalman filter
KW - Time series analysis
KW - Traffic flow forecasting
UR - http://www.scopus.com/inward/record.url?scp=85072207056&partnerID=8YFLogxK
U2 - 10.1016/j.physa.2019.122601
DO - 10.1016/j.physa.2019.122601
M3 - Journal article
AN - SCOPUS:85072207056
SN - 0378-4371
VL - 536
JO - Physica A: Statistical Mechanics and its Applications
JF - Physica A: Statistical Mechanics and its Applications
M1 - 122601
ER -