An accurate fingerprinting based indoor positioning algorithm

Recently, many studies of indoor positioning system using wireless signals such as WiFi, Bluetooth, have been researched actively. There are three types of indoor positioning system, triangulation method, fingerprinting technique and Cell-ID technique. Triangulation method has advantages in searching locations in wide environment, but its accuracy deteriorates in narrow indoor environment due to physical obstacles and signal interference. Fingerprinting technique results less error because it determines position based on reference in actual environment, but it has disadvantage in determining precise position in selected cell size. This study proposes an accurate fingerprinting based indoor positioning algorithm. To improve accuracy, K-NN algorithm and moving average filter is used. The performance of triangulation method, fingerprinting technique, and our proposed technique is analyzed under same situation. Experimental results show that the accuracy of the proposed method is 86%, which is better than the accuracy of fingerprinting method 72.58%, and triangulation method 45.63%.