Experimental Verification of Shadowing Classification for Radio Map

To reduce the registered data size and maintain the estimation accuracy of a radio map, we have proposed a shadowing classifier-based radio map. On the other hand, the radio map has been widely utilized in various systems, such as a spatial spectrum sharing, spectrum sensing, and localization. Thus, it is necessary to clarify the appropriate classification method of the shadowing components in various environments. In this paper, we evaluate the accuracy of the shadowing classification using two kinds of datasets and two comparison methods. The emulation results show that it is necessary to appropriately choose the classification method according to the presence or absence of outliers of the average received signal power.