Development of Medical Internet of Things with Big Data using RF-BFA and DL in Healthcare System

Abstract

Internet of Things (IoT) developments in biomedical and health care technology have opened up exciting new avenues for innovation. A wide range of principles and fascinating examples are explored in this chapter, including theoretical, methodological, conceptual, and empirical aspects of the subject. This research study is initiated with a description on how IoT and big data are being used to analyze a massive image database created daily from diverse sources using big data, machine learning, and other kinds of artificial intelligence to produce structured data for remote diagnosis. Health care providers may rely on the heterogeneous IoT platform to manage their data reliably, thanks to dedicated computing equipment. It is critical to healthcare service reliability that varied data streams are effectively managed owing to variations and errors. To make sense of the gathered data, a Chi-square-based term feature extraction method was employed. Outliers in sensor data are filtered out and unwanted features are removed with the use of density-based spatial clustering (DBSCAN) and random forest (RF)-backward feature elimination (BFE) as RF-BFE. The pre-trained model of Convolutional Neural Network (CNN) is used to make predictions based on these features. Finally, experiments are run to determine the effectiveness of the suggested model based on a number of different criteria.