Indoor Visible-Light Location Based on a Fusion Clustering Algorithm

A new fingerprint-location method based on a clustering algorithm was proposed to address the problem of large positioning errors in an indoor boundary area. This clustering-based method embodies the idea of a rough location and then a fine location. First, the edge regions of the received signal strength (RSS) samples, which are greatly affected by reflection, are divided using the k-medoids algorithm. Then, the center part is clustered using density-based spatial clustering of applications with noise (DBSCAN). In the actual location-estimation stage, the points to be measured can only be located in one of the classified areas and are combined with the weighted-optimum k-nearest-neighbor algorithm (WOKNN) to match the location. The results showed that the average positioning error of the algorithm was 13 cm in an indoor environment measuring 5 m × 5 m × 3 m. Compared with the traditional method without clustering, the positioning accuracy of the edge area increased by 21%, and the overall improvement was 33.8%. This proves that the proposed algorithm effectively improves the efficiency of real-time indoor-positioning accuracy.