Abstract :
Previous approaches used to perform online flow predictions included time-series models, nonparametric regression, simple moving average, and adaptive filtering. This paper explores the statistical nature of traffic flows aggregated at short time interval and investigate the potential of using the dynamic generalized linear model (DGLM) for traffic flow predictions. Specifically, recursive algorithms for weighted least square (WLS) estimators resulted from the generalized linear model family, including Poisson, binomial, and negative binomial distributions were derived based on the quasi-likelihood and prediction error minimization principles. The Kalman filter interpretation of the recursive WLS is also described. The resulted formulations are distinct from the existing DGLM and suitable for multivariate case implementation
Keywords :
Kalman filters; least squares approximations; online operation; prediction theory; recursive estimation; road traffic; time series; DGLM; Kalman filter; Poisson distributions; WLS estimators; dynamic generalized linear model framework; negative binomial distributions; online flow predictions; prediction error minimization; quasi-likelihood minimization; recursive WLS; recursive traffic flow predictor; statistics; weighted least-square estimators; Adaptive filters; History; Least squares approximation; Prediction algorithms; Predictive models; Random variables; Recursive estimation; Traffic control; Vehicle detection; Vehicle dynamics;
