WLAN indoor positioning algorithm based on sub-regions information gain theory

As a very popular positioning system, WLAN positioning attracts widely researches and investigations throughout the world. It implements the fingerprint technique to realize indoor navigation. The fingerprinting technique which employs the KNN algorithm has to make use of RSS (Received Signal Strength) from the Access Points (APs) without any classification. However, not all of the APs provide the contributions but interference, which will not only burden the positioning system but also results in poor positioning accuracy. To increase the positioning accuracy and decrease the computation cost of Wireless Local Area Network (WLAN), a novel algorithm is proposed by implementing the KNN algorithm and Information Gain Theory to bridge the gap between the Access Point selection and positioning accuracy. The experiment results indicates that, the positioning accuracy is improved by 4.76% within 2m, and meanwhile the time for positioning is decreased by 23.81%, which means the proposed algorithm successfully achieves higher positioning accuracy with less computational cost. Besides, it is also proved in this paper that contrary to the traditional concept, more APs do not always mean higher positioning accuracy; on the opposite, in our experimental environment, a relatively small scale of APs can achieve higher positioning accuracy than that of large scale of APs.