An Improved WKNN Algorithm Using in Indoor Positioning

Aiming at the difference of positioning accuracy caused by the heterogeneity of terminal equipment in WLAN indoor positioning, a method is proposed to satisfy device independence. The original fingerprint database is calibrated based on the pearson correlation coefficient and the spearman rank correlation, as well, the spearman distance is used as the weight for WKNN algorithm. The experimental results show that compared with the traditional positioning algorithm, the average positioning error is reduced by about 7%, at the same time, the heterogeneity of the terminal equipment such as mobile device is well solved, which can meet the requirements of indoor positioning.