An Indoor positioning method based on Improved Elman neural network using sparrow search

N owadays, indoor positioning algorithms have attracted comprehensive attention and research. Due to multipath effect in the complex indoor environment, it is difficult to position with high precision. In this paper a BLE(Bluetooth Low Energy) indoor positioning algorithm based on ISSA(Improved Sparrow Search Algorithm) with Cat chaotic mapping is proposed. Firstly the abnormal data are removed by BDOR(Bilateral Direction Outlier Removal) algorithm before establishing the database of the collected BLE data. Then the rest of data are filtered by improved Kalman filter. The ISSA-Elman models are studied to predict the horizontal and vertical coordinates of the point to be tested. Results of experiments reveal that the proposed algorithm performs precisely in indoor positioning. The minimal position error is nearly 2cm.