Prediction of trajectory based on modified Bayesian inference
Sun Dechang · Journal of Computer Applications · 2013
The existing algorithms for trajectory prediction have very low prediction accuracy when there are a limited number of available trajectories.To address this problem,the Modified Bayesian Inference(MBI) approach was proposed,which constructed the Markov model to quantify the correlation between adjacent locations.MBI decomposed historical trajectories into sub-trajectories to get more precise Markov model and the probability formula of Bayesian inference was obtained.The experimental results based on real datasets show that MBI approach is two to three times faster than the existing algorithm,and it has higher prediction accuracy and stability.MBI makes full use of the available trajectories and improves the efficiency and accuracy for the prediction of trajectory.