Efficient Classification based on Multi‐Scale Traffic Data Extraction Patterns of Cellular Network
Résumé
Africa has witnessed an incredible boom in the number of mobile subscribers in mobile networks across Africa. With the rise in demand for capacity in cellular networks, greater pressure is being placed on the network planner. Customer segmentation has been traditionally used in cellular network planning to better understand customer demands and needs. By developing more accurate profiling methods, operators are in a better position to market products and forecast future demand more accurately. This work looks at the extraction of frequency patterns from traffic signals originating from a typical mobile network using multiscale analysis. By studying the features extracted, the classification of typical subscribers in the network can be conducted more efficiently and with greater granularity.