A taxonomy for decision making in IoT systems

Abstract

Semantic knowledge representations in the IoT can enable the vision of autonomic computing by providing a specification that enables interoperability and reasoning. Nevertheless, semantic representations in IoT have focused on describing the elements that compose it and their interactions, without addressing the challenges of the logical evolution of a system (updating and design of new algorithms). This work focuses on this gap, proposing the Taxonomy for Decision Making in IoT Systems (TDMIoT), a high-level characterization of decision-making processes in IoT developed following a conceptual-empirical methodological approach. TDMIoT considers a decision-making process a problem-solution association aiming to deliver a semantic representation that can be used as a design framework to support changes or even the design of new decision processes. A systematic review of the literature on decision-making processes in IoT application domains was conducted to evaluate the taxonomy as a classification scheme. A summary of the state-of-the-art decision-making process design approaches was generated from the classification of the selected studies through the systematic review. The classification showed design bias regarding the decision processes. For instance, most studies have focused on decision processes with prediction as an objective, and the most widely used algorithmic approach has been data-driven. In addition, the taxonomy was used to develop the COVID-19 Crowd Management project to test its usefulness as a design framework. In this regard, TDMIoT narrowed the search for decision models, validating its effectiveness in selecting an algorithmic approach for a given objective.