Internet of Medical Things (IoMT) optimization for healthcare: A deep learning-based interference avoidance model

Abstract

The Internet of Medical Things (IoMT) is a significant component of the broader Internet of Things (IoT), IoMT is responsible for monitoring, collecting, and transmitting critical medical data to central medical computer centers. IoMT faces significant challenges, including energy efficiency, interference from other devices in the spectrum, latency, and security and privacy concerns. As a result, in hospital settings, the development of a precise and dependable IoMT system is crucial. Consequently, this investigation offered an innovative, accurate, and dependable IoMT method. The suggested model intends to reduce or eliminate interference caused by other transmitting devices sharing the same IoMT spectrum within hospitals or medical institutions. It also presents an interference-avoidance distributed deep learning model for IoMT to medical receptionists. This model uses data from the Lagrange optimization technique to determine the ideal distance between interfering devices and medical receptions. As a result, the required system signal-to-interference-plus-noise (SINRth) is met while maintaining the highest energy efficiency (EE) and system achievable data rate (R). The proposed analytical model and deep learning model demonstrate the efficacy of the proposed approach by achieving the required system signal-to-interference-plus-noise (SINRth) with the best energy efficiency (EE) and system achievable data rate (R) while suppressing interference to any medical receptions.