Prediction of health monitoring with deep learning using edge computing

Abstract

Today's modern computing environment provides a smart healthcare monitoring system for early prediction of fall detection. The Internet of Things-based health model plays a significant role in the health care service area and helps to improve the processing of data and its prediction. Transferring reports or data from one place to another takes too much time and energy, and it will cause high latency and energy issues. To handle these kinds of hazards, edge computing provides solutions. In this paper w presents smart healthcare system issues, services, and applications. Furthermore, propose a CNN-based prediction model with the use of edge computing and IoT paradigms. Edge computing is a distributed environment framework that enables rapid resource availability and response time through local edge servers computed at the end of IoT devices. The CNN model is used to analyse the health data collected by IoT devices. Furthermore, the role of edge devices is to provide doctors and patients with timely health-prediction reports via edge servers. The proposed mechanism can be analysed using accuracy and error rate performance parameters. In the proposed mechanism, the accuracy is 99.23% in comparison with other techniques.