The ontology driven SLAM based indoor localization technique

The proposed technique facilitates time-consuming procedure for setting up Wi-Fi or Bluetooth access points, indoor map building and signal propagation model calibration. The technique based on OWL ontology and the SLAM method includes the phase of forming a training sample, as well as the phase of simultaneous navigation and mapping. The SLAM method implements The Gaussian Process Latent Variable Model (GP-LVM). The proposed method is based on solving the regression problem using machine learning methods to form a training sample, as well as solving the problem of reducing the dimension for simultaneous navigation and map building. As a training sample, the smartphone's internal sensor readings (steps and rotation angles) and Wi-Fi received signal strength values obtained using crowd calculations are used. The resulting training sample is used to determine the parameters of the correlation function that sets the correlation between the user's localization points. The proposed ontology is intended to determine different events occurring during user's movement and involve the appropriate phase of the proposed technique.