IoT-Based Health Risk Prediction by Collecting and Analyzing HIIT Data in Real Time Using Edge Computing

Abstract

Increased awareness of the benefits of physical exercise has motivated people to improve physical fitness by doing high-intensity interval training (HIIT). HIIT (where one needs to work at 70-85% of one's maximum heart rate) and forceful exercise sessions can lead to health risks such as cardiac arrest, heat strokes, or lung diseases because people are unaware of their body health and endurance status. It is essential that the health parameters of people who exercise outside controlled environments like the gym be acquired and analyzed during workout sessions. This chapter aims to design an IoT-based timely warning system based on edge computing responsible for identifying unusual patterns in the monitored health parameters and alerting the person involved in an exercise about any deviation from expected behavior. The authors collect real-time data from individuals during the exercise sessions. The data analysis provides an assessment of the health parameters and predicts any health risks during the HIIT session.