Ubiquitous deployment configuration of indoor location services

The development of services in Ubiquitous Computing is a hard task. Services must adapt to context information about users. One of the most important pieces of context is user location, which allows Location Based Services (LBS) to adapt their functionality regarding the users nearest features of interest. In this paper, we will propose a hybrid system to solve the problem of finding the best configuration of antennas within an intelligent environment that minimizes cost and intrusion but maximizes the accuracy of the LBS in the prediction task. The approach combines Hidden Markov Models (HMM) for user location prediction with a multiobjective genetic algorithm which is able to get suboptimal configurations of the number and position of the antennas in the intelligent building. In the experiments, our system has given configurations of antennas which provide high accuracy to predict the location (based on Radio Frequency Identification, RFID) of the user while a minimal deployment of antennas in the building is needed.