Mobile Path Loss Prediction with Image Segmentation and Classification

This paper presents an intelligent radio wave propagation prediction model by using the 2-dimension aerial image which is taken from the actual area. An suburban area is used as examples. The prediction procedure is done in three steps. First, the image segmentation is employed to divide the area image into subgroups by using Maximum Likelihood algorithm. The second step uses the subgroup images from step 1 to determine the parameters for the fuzzy model that we use to classify the propagation areas. The final step is to plot the path loss contour on the image so the cellular cell site can be chosen. The research results show that the proposed segmentation provides an accuracy of 80-90% compared with the actual area. Therefore, cell site selection can be designed on the 2-dimension aerial map with the error less than 8 dB.