An Intelligent IoT-Based Smart Healthcare Monitoring System Using Machine Learning

Abstract

One of the most significant phases of human life is health. Every society is paying more consideration to and implementing knowledge in the areas of health and healthcare. Artificial intelligence (AI) is increasingly being used in the healthcare industry to provide accurate and rapid outcomes. Predictions about the onset of disease help doctors save the lives of their patients by intervening early. Smart health monitoring systems are becoming a reality thanks to the IoT. The IoT is functioning as a catalyst for artificial intelligence applications in healthcare. IoT sensors collect patient information, which is then analyzed with machine learning (ML) programs. In this chapter, we present a novel and intelligent healthcare monitoring system based on cutting-edge technologies like the IoT, optimization methods, and machine learning, with the goal of providing early and accurate diagnosis of a wide range of diseases. In this section, we examine the pros and cons of several IoT and ML-based healthcare monitoring systems. ML strategies are utilized to make predictions based on the medical sensor data that has been uploaded to the cloud. Using data from the UCI repository, this chapter describes the common frameworks for developing AI-based machine learning techniques for the Internet of Things. When compared to conventional methods, the proposed IoT-ONN model is 4–15 percentage points more precise. In addition, the IoT-ONN model cuts training time by 15% to 52% compared to ANNs trained with the BPN algorithm. Results show that when various healthcare data sets are utilized for training, the proposed IoT-ONN model performs well in terms of accuracy.