Indoor location estimation based on IEEE 802.15.7 visible light communication and decision trees

Abstract

Indoor positioning estimation has become an attractive research topic due to the growing interest in location-aware services. Many research works have been proposed on solving this problem by using wireless networks. Nevertheless, there is still much work needed to achieve high accuracy levels. In the last years, the emergence of visible light communication brings a brand new approach to high accuracy indoor positioning. Among its advantages, this new technology is immune to electromagnetic interference and also allows knowing the received optical power accurately. In this paper, we propose a fingerprinting indoor location estimation methodology based on decision trees. Along with the method, we also share some experimental results using the received signal strength obtained from an IEEE 802.15.7 simulator developed by our research group. Results are encouraging. The tested model (classifier) yielded a 93% accuracy, with an average error distance for misclassified instances of 37 centimeters.