A New Fuzzy Bayesian Clustering Algorithm to Enhance Radio Planning Tool Predictions

To enhance the quality and the precision of our radio network planning tool, we have decided to use measurements taken on real network. A learning scheme between the a-priori information, contained in the simulations, and the a-posteriori knowledge of the measurements is used. A preprocessing of data is required and involves the use of a clustering algorithm that divides the whole learning space into subspaces to ensure better generalization capabilities. In this paper we propose a new fuzzy clustering algorithm based on a Bayesian framework and we apply it to a prediction tool of a third generation (3G) cellular radio network. Results show that the differences observed between simulations and measurements can be considerably diminished. The generalization capacity is enhanced thanks to the proposed Bayesian clustering. We can then predict with enhanced accuracy 'unobserved' configurations as long they are not very different from 'learned' configurations.