An intensive healthcare monitoring paradigm by using IoT based machine learning strategies

• Published in: Multimedia tools and applications 2022-11, Vol.81 (26), p.36891-36905
• Main Authors: Kondaka, Lakshmi Sudha, Thenmozhi, M., Vijayakumar, K., Kohli, Rashi
• Format: Article
• Language: English
• Subjects: 1211: AIoT Support and Applications with Multimedia; Algorithms; Blood flow; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Data transfer (computers); Deep learning; Health care; Heart rate; Internet of Things; Machine learning; Monitoring; Multimedia Information Systems; Norms; Patients; Performance evaluation; Principles; Repositories; Special Purpose and Application-Based Systems; Telemedicine; Training
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-021-11111-8

Internet of Things (IoT) in association with cloud technologies are the raising stars in information technology industry, which provides a lot of innovative gadgets to several industries to automate their needs as well as monitoring the events properly without any human interventions. The most common and emerging needs now-a-days is the development of new gadgets to support healthcare industry to rectify the medical flaws and save the human life. In one side the booming technologies such as Internet of Things and Cloud platforms are available and the other hand a drastic need to introduce an intelligent gadget for medical oriented needs to save one’s life in critical situations. This paper aims to create a bridge between the two and introduce a new device to combine healthcare with recent technological developments. The proposed approach introduces a new algorithm called iCloud Assisted Intensive Deep Learning (iCAIDL), which provides support to healthcare medium as well as patients by means of applying the intelligent cloud system along with machine learning strategies and this proposed algorithm is derived from the base of deep learning norms. An iCloud Assisted Intensive Deep Learning algorithm initially begins with the flow of collecting the existing health records from the data repository and train the system with deep learning principles. Once the data training phase ends the proposed algorithm begins to get the live data from patient and this data is assumed as a testing data, which will be processed by using intensive deep learning principles and store the resulting summary into the Cloud repository by means of enabling Internet of Things feature in association with the proposed algorithm called iCAIDL. This is transparent in both the state of users like doctors as well as the patients to monitor the health records in intelligent manner. A Smart Medical Gadget is designed to collect the health record from patients and maintain it into the medical repository for testing phase, in which it collects the patient heart rate, pressure level, blood flow in intensive manner. The logic of IoT is connected with the machine learning process such as: the data accumulated from the smart Medical Gadget needs to be send to the Server end for processing, here the processing is mentioned as the machine learning based processing, in which the received data is considered to be the testing data and the results are emulated accordingly. Once the results are emulated th