Research On Indoor Localization Algorithm Based On WLAN

With the continuous development of mobile Internet technology,Location-based Services(LBS)has been applied more and more widely,people's demand for location information is getting stronger and faster.The traditional GPS and cellular network technology can achieve high positioning accuracy in outdoor,but in indoor environment,due to the influence of buildings on signal,the positioning ability is greatly limited.Wireless Local Area Network(WLAN)has been widely deployed in indoor environment to provide users with communication services because of its simple layout and low cost,indoor localization based on WLAN has become the research focus.This paper mainly studies fingerprint localization based on WLAN's Received Signal Strength(RSS),and then combines support vector regression and Kalman filter to design corresponding indoor localization algorithm.The main work of this paper is as follows:(1)Aiming at the problem that the wireless signal of wireless local area network is unstable in the indoor environment,and the traditional support vector regression(SVR)based positioning method may lead to the reduction of the correlation between the position coordinates and signal strength,this paper proposes an improved support vector regression(ISVR)based indoor positioning method.Firstly,the ISVR carries on logarithmic processing for the received signal strength(RSS)to make it more consistent with the normal distribution,and then uses the Gaussian filter to filter the small probability of fingerprints before building the fingerprint database.Secondly,in order to reduce the error of constructing X and Y coordinate model separately,a calibration coordinate z = x * y is trained at the training stage,which can improve the correlation between RSS and X-Y position information.Finally,the optimal position coordinates are obtained by weighted inverse K-nearest neighbor(WIKNN)method.The experimental results show that the proposed algorithm can reduce the noise caused by the complicated environment in the room,and improve the localization accuracy by 30% compared with the traditional support vector regression algorithm.(2)Aiming at the problem that indoor moving and real-time positioning only collect less RSS and it has higher real-time requirements,this paper proposes a real-time localization algorithm for indoor moving targets based on Kalman filter by considering the time correlation between the previous position and the last one.Firstly,the algorithm calculates the current position's coordinates based on ISVR algorithm as inputs of Kalman filter.Secondly,according to the map information in the room,different state noise and observation noise of Kalman filter are set up at turning at the corner or going straight.Finally,the final localization results are derived by combining the observed value of ISVR with the prediction value of Kalman filter.The experimental results show that the proposed algorithm can reduce the fluctuation of positioning and the localization accuracy is improved by more than 20% over ISVR's one.