An Adaptive Fuzzy Neural Network Technique for Coronavirus-based Bio-nano Communication Systems

Abstract

Background: At the end of December 2019, a case of pneumonia of unknown cause was reported in Wuhan, China. A new coronavirus was then identified as the leading cause of this controversial pneumonia, changing how people worldwide live. Although science has achieved significant advances in COVID-19 during the last two years, the world must do much more to prepare for the emergence and development of viruses that may spread rapidly. Methods: This COVID-19 research project proposes a diagnosis component, an adaptive fuzzy neural network technique, serving as a virus-based bio-nano communication network system that can understand the behavior of the biological and nonbiological processes of COVID-19 virusbased disease diagnosis and detect the pandemic at the early stage. The proposed method also integrates multiple new communication technologies, allowing doctors to monitor and test patients remotely. Results: As an outcome of this technique, the receiver biological nanomachines can adjust the 1/0-bit detection threshold according to the viruses previously encountered. This adjustment contributes to the resolution of the intersymbol interference issue caused by residual particles that arrive at the receiver owing to previous bit transmission and reception noise. Diffusionbased coronavirus nanonetwork systems are evaluated using MATLAB simulations that consider each detection strategy’s most crucial characteristics of the communication system environment. The proposed technique’s performance is evaluated in the presence of different noisy channel sources, which demonstrate a significant increase in uncoded bit error rate performance when compared to the previous threshold detection systems. Conclusion: Thus, diffusion-based coronavirus nanonetwork systems can be the future tool to investigate the existence of a specific type of virus that spreads through lung cells in the respiratory system.