APPLICATION OF MULTIAGENT SYSTEMS TO THREE-DIMENSIONAL POSITIONING PROBLEM IN INDOOR ENVIRONMENTS BASED ON IEEE 802.11

In recent years, wireless indoor positioning systems have attracted significant research interest. However, maximizing system precision remains challenging, especially for three-dimensional (3D) estimates. In this paper, a novel hybrid approach to resolving this problem is proposed through the development of a multiagent system composed of a Bayesian network and a deep neural network for 3D indoor positioning. The proposed system is based on a combination of the multilateration and fingerprint methods in order to reduce the acquisition region of the received signal strength vectors. In addition, the relationship between the quality of the received signal and the noise level, which is influenced by the increase in the number of access points and the number of persons moving within the environment, is considered by the system. The proposed approach exhibits a better performance than other algorithms with an average positioning error of less than 0.9 m. This result represents a difference of more than 22 cm with respect to the most similar algorithm.