Abstract: To enhance the performance of fingerprinting positioning,it is significantly necessary to rapidly and accurately match between the received signal strength (RSS) measured by the users and the pre-stored fingerprinting database.Therefore,a fingerprinting cluster algorithm was proposed to reduce the number of search points and optimize the search path,improving the performance of matching in rapidity and accuracy.Four different tests were designed to verify the proposed algorithm by evaluating the positioning accuracy and the rapidity,taking into consideration different shape of cluster.Our results show that the proposed algorithm reduces the number of search points by 60%,and has the same positioning accuracy with that of the traditional fingerprinting algorithm.By comparison of the performance of the different shape of clusters,the cellular cluster is optimal.

Key words: Indoor positioning,RSS,Cluster of fingerprinting,Cellular cluster