Services in ambient intelligence (AmI) environments should adapt to contextual information (context-aware) of users and environment in a nonintrusive and natural way. Location-aware, i.e., the user location, is one of the most important pieces in context-aware. According to this premise, a location-based service (LBS) using radio frequency identification technology is presented. The service is based on hidden Markov models for location within an intelligent building. This problem leads to a multiobjective optimization problem, in which, the best configuration of antennas that minimizes the set of antennas but maximizes the precision of the prediction should be found. Specifically, this study presents a memetic approach for multiobjective improvement of LBS in AmI environments. The memetic algorithm provides, in this problem, the exploitation of domain knowledge and the combination of metaheuristics. Experimental results show that the approach obtains a configuration of antennas which optimally configures the number and position of the antennas while keeping a high quality of the precision of the location prediction.