Algorithm Selectors for Providing Location Estimation Services within a Cellular Radio Network

Mobile location estimation is becoming an important value-added service for mobile phone operators. Many mobile location estimation algorithms based on the cellular radio networks have been proposed but there exists no general solution since each algorithm has its own advantage depending on specific terrain and environmental factors. In this paper, we propose and investigate three algorithm selectors, one with a LDA Classifier and the other two with Bayes Classifiers using either a Naive Bayes Probabilistic Model or a Bayes Probabilistic Model, to select the best mobile location estimation algorithms from our previous work in order to combine their merits, and provide a more accurate estimation for location services. We have tested these three algorithm selectors with real data taken in Hong Kong. Experiment results have shown that they are all useful in particular, and the one with a Bayes Probabilistic Model outperforms all other existing location algorithms among different kinds of terrains in terms of average errors.