A Model-Driven Methodology for the Design of Autonomic and Cognitive IoT-Based Systems: Application to Healthcare

Abstract

Due to its abilities to capture real-time data concerning the physical world, the Internet of Things (IoT) phenomenon is fast gaining momentum in different applicative domains. Its benefits are not limited to connecting things, but lean on how the collected data are transformed into insights and interact with domain experts for better decisions. Nonetheless, a set of challenges including the complexity of IoT-based systems and the management of the ensuing big and heterogeneous data and as well as the system scalability need to be addressed for the development of flexible smart IoT-based systems that drive the business decision-making. Consequently, inspired from the human nervous system and cognitive abilities, we have proposed a set of autonomic cognitive design patterns that alleviate the design complexity of smart IoT-based systems, while taking into consideration big data and scalability management. The ultimate goal of these patterns is providing generic and reusable solutions for elaborating flexible smart IoT-based systems able to perceive the collected data and provide decisions. These patterns are articulated within a model-driven methodology that we have proposed to incrementally refine the system functional and nonfunctional requirements. Following the proposed methodology, we have combined and instantiated a set of patterns for developing a flexible cognitive monitoring system to manage patients’ health based on heterogeneous wearable devices. We have highlighted the gained flexibility and demonstrated the ability of our system to integrate and process heterogeneous large-scale data streams. Finally, we have evaluated the system performance in terms of response time and scalability management.