Development of Explainable AI Models for Healthcare Applications

Abstract

IoT networks are used in SHM systems, and they generate enormous amounts of data every second that must be
handled. Exercise and room temperature are examples of wearable, wireless, and ambient IoT sensors. Therefore,
the massive volume of data needs significant processing skills. To collect, handle, and evaluate the intricate big data
produced by these devices, a business intelligence and analytics platform has been required. Unconventional deep
learning techniques have gained popularity for assessing and diagnosing the massive amounts of medical data we deal
with. To facilitate patient monitoring, a Smart Health Management (SHM) system often incorporates Wireless Sensor
Networks (WSN), Wireless Body Area Networks (WBAN), and the Internet of Things (IoT). It also introduces
additional technologies like artificial intelligence (AI) and machine learning (ML) to help with the diagnosis,
identification, and prediction of medical diseases. Additionally, as data volume, speed, and variety continue to rise,
technologies like cloud computing and edge/fog computing become essential. The literature contains a number of
surveys that examine SHM. These review and survey studies' main goal is to analyse the systems in certain situations,
examining elements such as architecture, applications, diseases, issues, difficulties, and new trends.