Positioning in WLAN Networks Based on SVM Algorithms and Space Segmentation

Due to the widespread availability of WLAN networks, positioning techniques in these environments have become a subject of intense research. In this paper, a combination of Support Vector Classification (SVC) and Support Vector Regression (SVR) machine learning algorithms was used, along with space segmentation, to solve the problem of user localization in a WLAN network. The proposed technique was thoroughly tested in a real WLAN environment. The lowest mean positioning error was achieved when the space was divided into 6 subspaces, amounting to 7.69m.