Journal of Computational Information Systems 6:14 (2010) 4627-4636 Available at http://www.Jofcis.com
1553-9105/ Copyright © 2010 Binary Information Press December, 2010
A Novel Two-Step WLAN Indoor Positioning Method
Lin MA†, Yubin XU, Di WU
Communication Research Center, Harbin Institute of Technology, Harbin 100080, China
Recently, due to the proliferation and no requirement for extra infrastructure investments, WLAN indoor positioning has received more and more attention. As the most famous pattern matching based method, KNN algorithm is widely implemented. However, the extensive computing and poor positioning accuracy trouble the practical application. This paper proposes a novel two-step WLAN indoor positioning method to improve on the KNN algorithm, which is very effective in the environment with a large area, such as a long corridor. In the off-line phase, the K-means clustering algorithm is carried out to divide the target area into sub-regions. This process will effectively resolve the extensive computing. In the on-line phase, the first step is to use the SVM classifier to decide which the sub-region the test point belongs to. And the second step the KNN algorithm is implemented to calculate the precise position. The experimental results show that the proposed method can increase the positioning accuracy effectively about 0.3m in average positioning accuracy, 17% within 2m and 11% within 3m in cumulative error probability respectively.
Keywords: WLAN; Positioning; KNN; K-means Clustering; SVM Classifier
Nowadays, with the development of radio technology and WLAN technology, the demand for the indoor position is increasing rapidly. The indoor position will be widely used in the airport, exhibition hall, offices, school library, warehouses, underground parking, prisons, military base and so on, which uses the accurate indoor position information to realize a resource management.
Generally, there are two kinds of methods for the indoor positioning, which are the propagation based method and the pattern matching based method. For the propagation based method, not only the signal fading induced by the building wall materials, but also the multi-path effects of the building structure, absorptions of the human body, interferences of the neighboring devices and extra expensive infrastructure investments significantly restrict the wide applications of this method in indoor environment [1,2], such as ultra-wide band (UWB) system, global positioning system (GPS), cellular systems, which consequently fail the proximity detection (PD), time of arrival (TOA), time difference of arrival (TDOA) and angle of arrival (AOA) to be employed in the indoor positioning system. In contrast, because of the relative high positioning accuracy and no need for extra hardware investment, the pattern matching based method is achieved in the WLAN environments, which has receives more attention and becomes a wide research focus....