LOCALIZATION OF WIRELESS LAN CLIENT IN MULTISTORY BUILDING BASED ON LAYERED NEURAL NETWORK

摘要

This paper describes a method for localizing wireless mobile clients in multistory buildings using a public wireless LAN system. Data pertaining to the physical positions of personal electronic devices or mobile robots are important for information services and robotic applications. By integrating the data and stored information about objects and places, people and robots can be provided with information about device locations. This paper presents a localization method for a wireless LAN client in a multistory building with a wide open-ceiling area based on the fingerprinting method. The proposed method uses public wireless LAN access points that are installed throughout the building. The application of this method involves the assumption that the human or robot carrying the mobile client moves horizontally on each floor in the building. The method simultaneously estimates the position of the mobile client and its floor number. Experimental results show that the proposed method is feasible.