Refining ground classification for the distribution of LTE users using supervised learning techniques

International audience Several studies have shown that the layout of an area’s infrastructure has a strong impact on the mobility of the mobile network users. Each district in a city has one or more different type of activity areas. Depending on the type of activity areas that a district covers, several profiles emerge. These profiles are closely linked to the impact a district can have on LTE users mobility. In the current work, we propose a first approach to determine the profile of a district in a territory. The territory under study is the city of Lom ́e, the data used for this analysis come from the geographical data of the OSM database. An alternative approach is proposed that, in the case of missing data, determines the profile of a new district from knowledge built from other districts in the same study area. To validate the proposed approach, evaluations were conducted considering several types of distance (Mahalanobis distance, Euclidian distance, ...). It appears that with the K-NN algorithm, using manhattan distance, we have 61% accuracy in determining the profile of a new district based on the nearest district’s profiles.