Improving Healthcare Facility Safety with Electronic Monitoring by a Machine Learning Framework Based on the Internet of Things

Abstract

Hacks, unauthorised access, and other problems have increased the risk to the healthcare system dependent on data analytics in recent years. When a system is kept in its factory settings, it provides an easier target for hackers who wish to get access to the server and steal data. In order to protect the privacy of patients, we use an innovative encryption approach called the Whale-based Random Forest (WbRF) Scheme in this research. Furthermore, ciphertext is made by layering micro-electronic sensors and employing Identity-based Encryption (IBE) on plaintext. The purpose of this surveillance is to ensure the model’s continued health while keeping a vigilant eye out for threats. Therefore the framework is programmed into the Python tool, and the system is trained on more than 200 patient datasets. Medical records for patients can be encrypted and stored safely in the cloud using nano-electronic jargon, in the end. The generated model is subjected to various attacks in order to determine how secure and effective it really is. Energy consumption, execution time, encryption time, latency, accuracy, and decryption time are compared between the created framework and conventional methods.