In RPM systems, this is a hardware component that receives data from various sensors attached to a patient, performs preliminary data analysis, and acts as a local processing hub. This reduces the need for continuous high-bandwidth communication with the main system.
Published in Chapter:
Human-Centric AI Applications for Remote Patient Monitoring
Sunil Kadyan (Manav Rachna University, Faridabad, India),
Yogita Sharma (Manav Rachna University, Faridabad, India),
Atul Kumar Agnihotri (University Institute of Engineering and Technology, Kanpur, India), Veer Bhadra Pratap Singh (Symbiosis Skills and Professional University, India),
Rakshit Kothari (College of Technology and Engineering, Maharana Pratap University of Agriculture and Technology, India), and Fateh Bahadur Kunwar (Geetanjali Institute of Technical Studies, India)
Copyright: © 2024
|Pages: 21
DOI: 10.4018/979-8-3693-1662-7.ch006
Abstract
This research analyses the deployment of a human-centric IoT gadget for remote impacted person monitoring, employing sophisticated technology to beautify healthcare operations. The suggested approach incorporates a community of sensors, together with temperature, stress, coronary heart charge, and oxygen sensors, strategically situated at the afflicted person's frame. These sensors capture actual-time physiological information, which is processed via a signal converter, delivered to character controllers, and consolidated within the cloud for complete analysis. Subsequently, machine studying styles, including artificial neural network (ANN), decision tree (DT), random forest (RF), and naive bayes (NB), are used to anticipate impacted person fitness outcomes based at the accumulated dataset. The analysis assesses each version's performance using a dataset of 3233 items, of which 70% are designated for learning and 30% for experimentation. Results suggest that the proposed ANN model achieves an outstanding accuracy of 97.5%, outperforming DT, RF, and NB. Decision tree and random forest comply closely with accuracies of 92.33% and 91.22%, correspondingly, while naive bayes demonstrates a superb accuracy of 86.5%. These outcomes underline the potential of sophisticated machine learning models, notably ANN, within the field of remote affected person monitoring, giving a transformational method to healthcare. The merger of human-centric layout ideas, IoT technologies, and device learning contributes to the continuous dialogue on improving affected person care, opening the way for extra proactive, customized, and successful healthcare treatments. This investigation suggests a leap forward in utilising generation to alter healthcare practices, highlighting the crucial significance of facts-driven decision-making in making sure best patient impacts.