IoT-Aided Wi-Fi Based Fingerprint Indoor Positioning Using Random Forest Classifier

Abstract

Wi-Fi based fingerprint indoor positioning technology is known as one of the most popular indoor positioning technologies. In this work, an internet of things (IoT) aided fingerprint indoor positioning system using Random Forest classifier has been proposed. The fingerprint database is constructed with IoT device and developed program. Then database is used to train machine learning classifier to be able to predict user position in a real indoor environment with 74 target locations. The simulation results show that Random Forest classifier is more powerful than KNN classifier and SVM classifier with positioning accuracy up to 94%. The real-time experiment verified that Random Forest classifier applied system can achieve 4 meters precision indoor positioning with 91% success rate.