Research And Simulation Of Indoor Location Technology Based On Android

In recent years, the demand of Based Service Located (LBS) is increasing, with the development of society and the improvement of science and technology. The theory of outdoor positioning technology is more mature, it can achieve precise positioning. However,due to the complexity of the indoor environment, indoor positioning error is large, it is difficult to meet the needs of indoor accurate positioning. With the popularization of WiFi and mobile intelligent terminal in the indoor environment, the indoor WiFi positioning technology based on the Android platform becomes the research hotspot in the field of indoor positioning.Therefore, this paper deeply research the position fingerprint positioning method, combining with the actual environment, this paper proposes a new method that improved the positioning accuracy and accelerated positioning speed, it make up the shortcomings of the traditional fingerprint positioning algorithm.Firstly, through reading of a large number of indoor positioning documents and studying the various positioning technology and positioning method. This paper determined to adopt the technology of WiFi positioning and the method of location fingerprint, on the basis of the advantages and disadvantages of various indoor positioning method.Secondly, this paper used the filtering algorithm to eliminate the error of the larger signal strength. Furthermore, introduce the data clustering that make similar data become "a cluster",in order to improve the off-line training phase positioning speed. In real-time localization stage, the traditional location matching algorithm is based on the nearest neighbor (NN), K nearest neighbor (KNN) and K weighted nearest neighbor (WKNN). The paper proposes an improved K weighted nearest neighbor method. At last, Through Simulation and comparative of the cumulative error of various nearest neighbor algorithm, this paper determine that the K weighted nearest neighbor method is used as the matching algorithm in this paper. In order to accelerate the localization speed, this paper also introduces the bloom filter.Finally, this paper created the WiFi fingerprint database. Then analyzed the WiFi signal of the test area. At last, this paper tested some points, the positioning error of each test point is recorded and analyzed.