Multi-objective Chaotic Butterfly Optimization with Deep Neural Network based Sustainable Healthcare Management Systems

Abstract

Sustainable healthcare systems are developed to priorities healthcare services involving difficult decision-making processes. Besides, wearables, internet of things (IoT), and cloud computing (CC) concepts are involved in the design of sustainable healthcare systems. In this study, a new Multi-objective Chaotic Butterfly Optimization with Deep Neural Network (MOCBOA-DNN) is presented for sustainable healthcare management systems. The goal of the MOCBOA-DNN technique aims to cluster the healthcare IoT devices and diagnose the disease using the collected healthcare data. The MOCBOA technique is derived to perform clustering process and also to tune the hyperparameters of the DNN model. Primarily, the clustering of IoT healthcare devices takes place using a fitness function to select an optimal set of cluster heads (CHs) and organize clusters. Followed by, the collected healthcare data are sent to the cloud server for further processing. Furthermore, the DNN model is used to investigate the healthcare data and thereby determine the presence of disease or not. In order to ensure the betterment of the MOCBOA-DNN technique, an extensive simulation analysis take place. The experimental results portrayed the supremacy of the MOCBOA-DNN technique over the other existing techniques interms of diverse evaluation parameters.