An ontology-driven context-aware recommender system for indoor shopping based on cellular automata

Nowadays, large shopping malls provide tools to help and boost customers to buy products. Some of these tools melt down digital operations with physical ones executed by customers into blended commerce experiences. On the other hand, Ambient Intelligence (AmI) represents a paradigm focused on equipping physical environments to define ergonomic spaces for people interacting with computer-based localized services which are ubiquitously accessible. In this context, we propose a Context-Aware Recommender System to assist indoor shopping by localizing shoppers and provide them with suggestions on where to find suitable offerings related to products that meet their wishlists. Recommendations are generated by means of an Indoor Navigation System. The system lies on two well-known formal models: the Computational Ontologies and the Cellular Automata. Ontologies are based on Description Logic and defined by means of languages, methodologies and tools of the Semantic Web Stack provided by W3C. Cellular Automata is a very well known formal computational model, suitable to abstract services deployed into an AmI-based environment along with the paradigm of Pervasive Computing. The integration of the capabilities provided by such two models offers a set of desirable features like adaptivity, scalability, low-costs, and robustness.