An Improvised Machine Learning Approach for Wireless Sensor-Based Healthcare Applications

Abstract

Medical Cyber-Physical Systems, health cloud, the Internet of Health Things (IoHT), perceptive algorithms, block chain, big data analytics, health fog, and machine learning are the examples of innovative innovations that have been creatively integrated and employed in the healthcare industry. Healthcare professionals benefit from decision support provided by machine learning algorithms that analyzes a vast collection of medical data. These technologies send the collected data for storage and processing to a cloud-based platform. The main aim is to give patients a better, extra merit, and inexpensive healthcare service, while enhancing the system's overall effectiveness. Medical Cyber-Physical Systems (MCPS) is an innovative new solution aimed at allowing advanced health systems to track, control, and make accurate decisions without the involvement of physicians or guardians. However, present MCPS face many key problems where one of the most significant problem is maintaining hospital equipment, which has a strong relationship with patient welfare. Edge computing and cloud computing also known as fog computing can be used to improve MCPS protection by enabling the investment at the data centers. This research work concentrates on a survey of artificial intelligence algorithms for healthcare applications and also provides a detailed record of the saturation oxygen (SpO2), respiration rate (RR), heart rate (HR), pulse, and blood pressure (BP).