Machine Learning Model for Indoor Localization Algorithm using GPS and Smart Watch

Acceleration sensor is considered to this research because it is less affected by the surrounding environment. The behavioral patterns of users wearing smart watches are trained using the proposed model in indoor or outdoor spaces. This paper proposes a machine learning model for indoor localization algorithm using global positioning system (GPS) and smart watch. In addition to this, the state transition probability matrix of Hidden Markov model (HMM) on the movement path of smart watch is measured and analyzed in this paper. It can be seen that the changed GPS coordinates can predict the next coordinates using HMM.