Unsupervised connectionist clustering algorithms for a better supervised prediction: application to a radio communication problem

Most models concerned with real-world applications can be improved in structuring data and incorporating knowledge about the domain. In our problem of radio electrical wave dying down prediction for mobile communication, a geographic database can be divided in contextual subsets, each representing an homogeneous domain where a predictive model performs better. More precisely, by clustering the input space, a predictive model (here a multilayer perceptron) can be trained on each subspace. Various unsupervised algorithms for clustering were evaluated (Kohonen´s maps, Desieno´s algorithm 1988, neural gas, growing neural gas, Buhmann´s algorithm 1992) to obtain classes homogeneous enough to decrease the predictive error of the radio electrical wave prediction