WLAN Location Method Techniques Based On Hierarchical Clustering

With the rapid development of GPS equipment and computers, location-based services become(LBS) is increasingly important. With the development of the Global Positioning System(GPS) technology, it can be positioned outdoors, but because of many factors in the indoor environment of the satellite signal interference,GPS can not achieve precise positioning within buildings. Therefore, in high-rise buildings, how to achieve the floor positioning is become an urgent problem.Location fingerprinting targeting mainly divided into two parts, one is the establishment of a fingerprint database offline, the other part is to achieve floor positioning online. Offline training phase requires the establishment of a fingerprint database, the database is the role of the WLAN signal strength vectors, and establish the corresponding relation between the actual position of the vector with. In order to save a lot of manpower and material resources, the first man-made collection of fingerprint data, as well as the method of data collection crowdsourcing for data collection. During data collection, the collected data may have some problems, then you need to preprocess data, on the one hand because of the indoor environment can not collect a signal, you can consider deleting the sub-sample data or other data padded; the one hand, consider the process of abnormal data, the introduction of high-quality fingerprint database to build density-based clustering methods, targeting the use of floor-based hierarchical clustering method proposed in this paper in realtime positioning stage.As traditional floor identification method is very time-consuming, while the accuracy rate needs to be improved. In this paper, based on hierarchical clustering WLAN floor positioning method enables the floor positioning accuracy has improved, and quickly locate the user which floors. If the user can quickly know which floor, and then determine the specific location within the floor, can largelyimprove the positioning accuracy of test points. As used herein, matlab simulation experiment results show that this method will help improve the floor positioning accuracy, while reducing the time to determine the positioning of the floor.