A self-adaptive IoT architecture to support computational resource allocation in an e-health environment

Abstract

Intelligent environments are complex interaction spaces between people, sensors, devices, and systems. The Internet of Things (IoT) has gradually exposed society to these environments in recent years. However, Software Engineering requires specific techniques to deal with the development of these systems. Therefore, Software Engineering must address intrinsic characteristics of devices and sensors, complex interactions in intelligent environments, quality aspects, scalability and interoperability, and the ability to consolidate good development practices. Using computational resources can help support the construction of contemporary IoT systems, dealing with the complexities and quality requirements presented. The main objective of this work is to define a self-adaptive IoT architecture for allocating computational resources in an intelligent e-health environment with the help of artificial intelligence. The proposal concerns how architectural modules cooperate and interact to develop new applications. The work was developed through a real case study in an e-health environment. The research methodology used was Design Science. The results showed the efficiency of the proposed self-adaptive architecture using artificial intelligence. Through the results acquired: (i) it was possible to observe how the architecture behaves in an intelligent e-health environment; (ii) how computing resources self-adapt according to the needs of the environment; (iii) how artificial intelligence can support the use of computational resources in intelligent e-health environments; (iv) how real case studies can be carried out in e-health environments to help companies make decisions about the management of their physical space. Furthermore, the results demonstrate how a self-adaptive architecture using artificial intelligence can support the management of an intelligent physical e-health space. With this, it was possible to observe how data collection, environmental monitoring, prediction of the use of computational resources, and environmental management optimization can occur.