Computational Intelligence in Wireless Sensor and Actuator Networks: A Thorough Review

Abstract

Wireless sensor and actuator networks (WSANs) can be referred to as a derivative of wireless sensor networks (WSNs), which comprise nodes with different functionality and ability (i.e., the heterogeneous ones). WSANs can cooperatively sense the environment, decide the doable, and act accordingly to alter the environment's state as per the need of the application. Being an extension of WSNs, WSANs suffer from the additional challenges of WSNs along with their own. These challenges are basically due to the very nature of the network in which a large number of sensor nodes sense the surrounding, resulting in a variety of data that might be imprecise as well. In addition, it might require optimization techniques to obtain accurate and desirable network operations. In this work, a detailed survey of techniques supported by the concept of computational intelligence in the domain of WSANs is presented. The work reviews the application of various intelligent techniques such as neural networks, evolutionary algorithms, swarm intelligence, fuzzy system, and learning systems in the aforesaid domain. Finally, the work concludes with a discussion on the future research directions in the concerned domain of WSANs.