Machine learning with the internet of virtual things

Peripheral devices working in the context of the Internet of Things, specifically sensors, produce large amounts of data that can be used to infer knowledge. In this area, machine learning technologies are increasingly used to establish versatile models. In this article, we present a new architecture capable of running machine learning algorithms in a sensor network. This approach has advantages in terms of confidentiality and energy efficiency-related data transfer. First, we argue that some types of machine learning algorithms are consistent with this approach, particularly those based on the use of generative algorithms. Subsequently we detail our proposed architecture based on Internet of Things and Web of Things paradigms facilitating the integration in sensor networks. The convergence of generative models and Web Objects leads to the concept of virtual sensors exposing high-level knowledge using data from various sensors. Finally, we demonstrate the feasibility and performance of our proposal using a real scenario.