Role of Computational Intelligence and Genetic Programming for Enhancing WSNs in Biomedical Monitoring and Applications

Abstract

Wireless sensor networks (WSNs) are event-monitoring and distributed autonomous data-collecting devices that are tightly distributed, lightweight nodes deployed in large numbers to monitor physical or environmental conditions cooperatively. WSNs face many challenges related to communication failures, storage and computational constraints, and limited power supply; in this context, different Computational Intelligence (CI) techniques provide adaptive mechanisms to alter WSN's dynamic nature and provide autonomous behavior, flexibility, scenario changes, robustness against communication failure and topology changes. Paradigms of CI have been successfully used in recent years to address various challenges in medical domains, such as data aggregation and fusion, energy-aware routing, task scheduling, security, optimal deployment, and localization. In this review, we intend to close the computational gap and foster collaboration by offering a detailed introduction to WSNs and their properties based on genetic programming approaches for investigating biomedical problems. Furthermore, an extensive survey of CI applications to various problems in WSNs from various biomedical research areas and publication venues is presented. Besides, a discussion on the advantages and disadvantages of CI algorithms over traditional WSN solutions is offered. Also, it explores the benefits of CI techniques in real-time disease monitoring and how they may be used to solve various problems associated with WSNs in healthcare systems. In addition, a general evaluation of CI algorithms is presented, which will serve as a guide for using CI algorithms for WSNs to treat computational health applications. The most common CI paradigms, such as fuzzy systems, evolutionary algorithms, artificial neural networks, swarm intelligence, and artificial immune systems, are explored to introduce Real-Time Disease Monitoring systems in time, space, complexity and cost optimization. Finally, a short conclusion and future recommendations are provided.