In this paper, a novel RSS (received signal strength) based indoor localization scheme is proposed based on multiple antennas cooperation with designed CAA (cylindrical antenna array). The CAA is composed of twelve directional antennas and could receive the signal of twelve dimensions for one tag at the same time. In the offline phase, the RBF (Radial Basis Function) neural network is trained to construct the relationship between received data of twelve dimensions and AOA (angle of arrival). The online positioning phase consists of two steps. In the first step, the AOA is obtained with the trained neural network and subarea is determined to which the unknown tag belongs. In the second step, the triangle localization algorithm is used in the determined subarea to get the accurate tag position. The experiment results show that the proposed approach not only reduces the miss hit rate for the subarea determination to 6.2%, but also provides comparable location accuracy to that of other two conventional RSS-based locating algorithms.
CITATION STYLE
Jie, W., Minghua, Z., & Bo, X. (2018). MAC-ILoc: Multiple Antennas Cooperation Based Indoor Localization Using Cylindrical Antenna Arrays. In Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST (Vol. 252, pp. 286–295). Springer Verlag. https://doi.org/10.1007/978-3-030-00916-8_27
Mendeley helps you to discover research relevant for your work.