Improving RSS-Based Indoor Positioning Algorithm via K-Means Clustering

Advances in mobile technologies and devices has changed the way users interact with devices and other users. These new interaction methods and services are offered by the help of intelligent sensing capabilities, using context, location and motion sensors. However, indoor location sensing is mostly achieved by utilizing radio signal (Wi-Fi, Bluetooth, GSM etc.) and nearest neighbor identification. The most common algorithm adopted for Received Signal Strength (RSS)-based location sensing is K Nearest Neighbor (KNN), which calculates K nearest neighboring points to mobile users (MUs). Accordingly, in this paper, we aim to improve the KNN algorithm by enhancing the neighboring point selection by applying k-means clustering approach. In the proposed method, k-means clustering algorithm groups nearest neighbors according to their distance to mobile user. Then the closest group to the mobile user is used to calculate the MU's location. The evaluation results indicate that the performance of clustered KNN is closely tied to the number of clusters, number of neighbors to be clustered and the initiation of the center points in k-mean algorithm.