Engineering Ambient Intelligence Services by Means of MABS

In this work, the methodology AmISim to test and to deployment of Ambient Intelligence (AmI) system is presented. The development of AmI systems is a complex task because this technology must adapt to users and contextual information as well as unpredictable and changeable behaviours. So, we focused in how the methodology AmISim can help to the engineering of adaptative services for users. In this case, we propose a predictor of location based on Hidden Markov Models (HMMs). So, the system can offer Location-Based Services(LBS) that adapt to the users. To this end, we propose a methodology based on a previous social multi-agent based simulation (MABS) and a following deployment of the service in a real environment.