WLAN Indoor Localization Method Using Angle Estimation

With the rapid development of science and technology,especially the rapid development of mobile communication and wireless LAN technology,location-based services(LBS)are paid more and more attention.People are growing demand for positioning and navigation.In complex indoor environments,such as airport halls,exhibition halls,warehouses,supermarkets,libraries,underground parking,etc.,the locations of mobile terminal or its holders,facilities and items are often needed to determine.However,compared with the outdoor environment,the indoor environment is effecting by positioning time,positioning accuracy,indoor environment and other complex conditions.So the more complete positioning technology is still not be well used.In addition,because of the complex environment of the indoor positioning in the underground rescue,intelligent home and large exhibition hall have important application background;the study of indoor positioning can improve the quality of life to a certain extent,to protect the safety of life and property.At present,there are some commonly used indoor positioning technology,including radio frequency identification technology,Bluetooth positioning technology,ZigBee positioning technology,WLAN positioning technology.Because of its high positioning speed,high precision,low cost,WLAN positioning technology has been becoming the best choice for indoor positioning in the eyes of the public.WLAN positioning system is usually based on the machine learning positioning program.This program is divided into two stages:offline stage and online stage.At offline stage,the task is the collection of adequate training data,the establishment of environmental models and the distribution of WLAN signals.At online stage,collect the real-time data,import to the established model and get the current positioning result.In WLAN Indoor localization systems,an improved position fingerprinting algorithm is proposed to obtain higher accuracy.The algorithm constructs the nonlinear relationship between received signal strength indication(RSSI)values and the angles formed by horizontal line and the line from transmitters to receivers,instead of traditionally training the relationship between RSSI values and physical coordinates.The localization area is divided into a number of small rectangular areas,and the test points are sorted out by K-Nearest-Neighbor(KNN)algorithm.In a small rectangular area,RSSI values and the angles are trained by support vector machine(SVM),so as to estimate the angles formed by horizontal line and the line from test points to each access point(AP).Finally,coordinates of the test points are estimated using the geometric relationship.Two experimental sections have been conducted under different conditions:one is in the laboratory,and the other in a typical office space.The proposed algorithm is compared with v-SVM algorithm,KNN algorithm and ML algorithm.Experimental results prove that our proposed algorithm outperforms other methods in term of localization accuracy under various situations.