Comparative Study on Energy-Efficiency for Wireless Body Area Network using Machine Learning Approach

Awareness of one's own health needs is a quickly spreading revolution in contemporary living. Wireless Body Area Network (WBAN), that uses smart IoT devices for device evaluation, enables affordable healthcare services. WBANs offer a wide range of applications in telemedicine, the military, sports, entertainment, and other areas that call for ongoing Quality of Service (QoS) optimization with relation to dependability, energy use, delay and ease. The communication phase of WBANs presents energy optimization problems for low-powered battery devices. The prediction models for energy consumption were properly designed in conjunction with machine learning (ML) techniques. Improvements in QoS parameters are seen in ML models, along with accuracy, resilience, and precision. Artificial Neural Networks (ANN), Support Vector Regression (SVR), Deep Neural Networks (DNN), K-nearest neighbours (KNN), among other existing ML approaches, are acknowledged as the best method for preserving energy usage and performance. The objective of this paper is to further the understanding of WBAN with ML and its practical application among readers and academics. By methodically examining the results and limitations of previous research, this review paper seeks to provide an overview of the present practical challenges associated with using machine-learning models to improve building energy efficiency.