ENHANCING CELLULAR NETWORK PERFORMANCE THROUGH MOBILE USER POSITION AND SERVICE PREDICTION

摘要

Humans are creatures of habits. They tend to repeat their behaviors. Neural network techniques are powerful tools that can be used to extract such behaviors from historical data and as such can predict where the user is expected to go next if we model his behavior correctly. In our experiments, we compare results of the proposed Bayesian Neural Network with 5 standard neural network techniques in predicting both next location and next service to request. Bayesian learning for Neural Networks predicts both location and service better than standard neural network techniques since it uses well founded probability model to represent uncertainty about the relationship being learned. The result of Bayesian training is a posterior distribution over network weights. We use Markov chain Monte Carlo methods (MCMC) to sample N values from the posterior weights distribution. These N samples vote for the best prediction.