An Enhanced Cloud-IoMT-based and Machine Learning for Effective COVID-19 Diagnosis System

• Published in: Intelligence of Things: AI-IoT Based Critical-Applications and Innovations pp. 55 - 76
• Main Authors: Awotunde, Joseph Bamidele, Ajagbe, Sunday Adeola, Idowu, Ifedotun Roseline, Ndunagu, Juliana Ngozi
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2021; Springer International Publishing
• Subjects: Cloud computing; Coronavirus; COVID-19 pandemic; Diagnosis; Extra Trees; Internet of Things; Light gradient boosting machine; Machine learning; Random forest; XGBoost
• ISBN: 3030827992; 9783030827991
• DOI: 10.1007/978-3-030-82800-4_3

The biosphere has been exaggerated adversely with the emerging of the COVID-19 at the end of 2019. It is anticipated that the present pandemic will be tackle with precautionary steps since there is no reliable vaccine that can be used to combat the outbreak globally. Hence, the newly emerging technologies will have noticeable roles to play during this pandemic. Therefore, this chapter proposes real-time diagnosis system to combat the spread of COVID-19 outbreak. A Cloud-IoMT-based framework was developed to collect real-time data for early diagnosing patients in real time. Four distinct machine learning: Extra Trees, Random Forest (RF), XGBoost, and Light Gradient Boosting Machine (LGBM) were used for quick and better identification of potential COVID-19 cases. The dataset used contains COVID-19 symptoms and selects the relevant symptoms of the diagnosis of a suspect person. The results show that LGBM performs better with an accuracy of 91%, and the least of all the four algorithms shown an accuracy of 75%. The real-time usage of capture data would provide accurate and effective diagnosis and monitoring of COVID-19 patient during this outbreak.