Classification of COVID-19 Patients Using Deep Learning Architecture of InceptionV3 and ResNet50

This paper aims to compare the deep learning Convolutional Neural Network (CNN) model for a case study of 3 classes chest x-ray classification of patients with "COVID-19", "pneumonia", and "normal people"using 2 architectures, namely InceptionV3 and ResNet50. This model was created using the GoogleColab platform with the Python programming language. This comparison aims to find the best results using 4 evaluation metrics and several scenarios for dividing the number of datasets used for training and validation. The evaluation metrics used include accuracy, precision, recall, and F1-score. The best accuracy is generated on a model with the ResNet50 architecture with a training accuracy value of 98.62% and accuracy validation of 96.53%. While in the InceptionV3 architecture, the resulting value for training accuracy is 96.13% and accuracy validation is 91.52%. © 2021 IEEE.

An Internet of Things (IoT) Reference Model for an Infectious Disease Active Digital Surveillance System

Internet of Things (IoT) technological assistance for infectious disease surveillance is urgently needed when outbreaks occur, especially during pandemics. The IoT has great potential as an active digital surveillance system, since it can provide meaningful time-critical data needed to design infectious disease surveillance. Many studies have developed the IoT for such surveillance;however, such designs have been developed based on authors' ideas or innovations, without consideration of a specific reference model. Therefore, it is essential to build such a model that could encompass end-to-end IoT-based surveillance system design. This paper proposes a reference model for the design of an active digital surveillance system of infectious diseases with IoT technology. It consists of 14 attributes with specific indicators to accommodate IoT characteristics and to meet the needs of infectious disease surveillance design. The proof of concept was conducted by adopting the reference model into an IoT system design for the active digital surveillance of the Covid-19 disease. The use-case of the design was a communitybased surveillance (CBS) system utilizing the IoT to detect initial symptoms and prevent closed contacts of Covid-19 in a nursing home. We then elaborated its compliance with the 14 attributes of the reference model, reflecting how the IoT design should meet the criteria mandated by the model. The study finds that the proposed reference model could eventually benefit engineers who develop the complete IoT design, as well as epidemiologists, the government or the relevant policy makers who work in preventing infectious diseases from worsening. © 2021. All Rights Reserved.