Energy efficient clustering with disease diagnosis model for IoT based sustainable healthcare systems

Sustainable energy efficient networking models are needed to satisfy the increasing demands of the information and communication technologies (ICT) applications like healthcare, smart cities, education, and so on. The futuristic sustainable computing solutions in e-healthcare applications are based on the Internet of Things (IoT) and cloud computing platform, has offered numerous features and real time services. Several studies revealed that the amount of energy spent on transmitting data from IoT devices to a cloud server is considerably high and resulted in rapid energy depletion. In this view, this paper presents an Energy Efficient Particle Swarm Optimization (PSO) based Clustering (EEPSOC) technique for the effective selection of cluster heads (CHs) among diverse IoT devices. The IoT devices used for sensing healthcare data are grouped into a form of clusters and a CH will be elected by the use of EEPSOC. The elected CH will forward the data to the cloud server. Then, the CH is responsible for transmitting data of the IoT devices to the cloud server through fog devices. Next to that, an artificial neural network (ANN) based classification model is applied to diagnose the healthcare data in the cloud server to identify the severity of the diseases. For experimentation, a systematic student perspective healthcare data is produced utilizing UCI dataset and medicinal gadgets to foresee the diverse student levels of disease severity. A detailed comparative analysis is carried out and the simulation outcome ensured the goodness of the EEPSOC-ANN model over the compared methods under various aspects.