User behavior prediction in the “offline” smart home solutions

Smart Home products spread is restrained due to several reasons including poor usability and fears of the personal data security [1,2]. Our research team suggested Smart Home solutions based on the user behavior analysis and modeling [3]. We also studied application of this approach to different householder needs (like healthcare or imitation of the user's presence [4]). We showed that the approach also critically improve the usability of the Smart Home. Finally, we described the methodology for analysis of the householder's behavior and simulation of his activities. So “offline” solutions based on this approach allows protecting privacy and provide good usability (“offline” means here partly or completely disconnected from the external operating signals and observations). At the same time they have some disadvantages including relatively low quality of predictions [5]. In this paper we discuss how the tuning of parameters of the previously suggested methodology provides improvement of the user needs predictions. The results of primal tests of this approach are presented and analyzed.