Decision Tree Approach to Estimate User Location in WLAN Based on Location Fingerprinting

Abstract

The estimation of user location using modern communication technology like WLAN based on radio signal strength, is a recent interesting area. There are many indoor positioning techniques to estimate user location; location fingerprinting, time of arrival (TOA), time difference of arrival (TDOA), angle of arrival (ADA) and others. LocationfFingerprinting technique is more suitable than other techniques, because TOA, TDOA or AOA is suffer from non-line-of sight error and multi path, especially in urban and suburban area. In this paper we study the fingerprinting technique using neural network, nearest neighbor and decision tree to estimate the location. The results of the experiment show that using DT technique is the best to estimate the location of the user.