Multisimi-Markov: An Improved Markov Position Prediction Method

摘要

As indoor positioning accuracy becomes higher, location data become more reliable, indoor location data mining has gradually become the research direction of many scholars and researchers. The research of pedestrian prediction in indoor environment is becoming more popular. Aiming at the issue that 2-order Markov method's low accuracy resulted by considering little of similarity of history trajectories, this paper presents a developed Markov Model called Multisimi-Markov Algorithm, taking the history similarity into 2-order Markov Model and find a solution to the problem of probability conflict, the forecast accuracy can be up to 71.6%.