Abstract
As localization systems have recently increased in popularity, several different techniques and algorithms have been proposed by researchers and developers to achieve high accuracy and an effective localization system. However, there are certain factors that can directly affect the system’s accuracy, regardless of the proposed model or algorithm, such as variation of the environment’s structure and received signal strength (RSS) data over long time durations. In this paper, we analyse the impact of RSS over a long time duration to predict the user location in indoor environments using a Bayesian network. The results show the average of the distance errors of different time durations of RSS is inconsistent, due to the multipath effect, and the structure of the indoor environment. However, the overall system accuracy is 3.6 m using 15 training points for both time durations.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have