ABSTRACT
The COVID-19 epidemic has highlighted the requirement for accurate and reliable disease detection methods. In this chapter, we present an early COVID-19 detection method enabled by deep learning for a fog-cloud healthcare network. The suggested method uses a combination of convolutional neural networks (CNNs) and long short-term memory (LSTM) networks to categorize COVID-19 patients based on chest X-ray images. The fog-cloud healthcare network is made up of Internet of Medical Things (IoMT) devices linked to a cloud-based platform that enables efficient data sharing and analysis. The goal of this study is to develop a COVID-19 early detection system with deep learning capabilities for fog-cloud healthcare on the Internet of Medical Things (IoMT) (LPWAN). The suggested method integrates edge computing, cloud computing, and deep learning techniques to provide an accurate diagnosis of COVID-19 in patients. Our technique is to provide a more reliable and accurate method for COVID-19 detection, especially in areas with limited access to medical care or testing facilities. Using a COVID-19 chest X-radiation dataset that is available to the public, we evaluate our suggested technique. By contrasting our strategy with current state-of-the-art methods, we show how effective it is. The model was trained on images of chest X-ray both infected and non-infected subjects for 100 epochs, resulting in an accuracy of 0.98 and decreased operational expenses. However, to utilize this model for professional diagnosis, it is advised to enhance it with additional images and restructuring to attain greater accuracy, facilitating timely interventions, and lowering the spread of the disease. The study outlines research challenges and future possibilities, providing a comprehensive and exceptional perspective on LPWAN and highlighting its potential advantages.
