The Implementation of a Real-time Monitoring and Prediction System of PM2.5 and Influenza-Like Illness Using Deep Learning

Abstract

Nowadays, deep learning is very popular and has excellent application performance in various fields. Specifically, in predicting disease outbreaks. It is possible to quickly and accurately predict disease outbreaks, lead to a significant research project in the medical field. However, there is a lack of technological development particularly in real-time monitoring of influenza-like illness (ILI). Moreover, there are still not sufficient ILI prediction models and results, while the incidence of ILI itself is high. In this paper, we propose an analysis and prediction of ILI outbreaks. In this case, deep learning analysis is applied to predict the ILI outbreaks to provide relevant information for relevant areas. The LSTM model is implemented to obtain information on AQI and ILI incident by using government open source data, research, and analysis of ILI and air quality indicators AQI. The visualization model using Highchart’s with Django framework to present regional air quality and predicts whether influenza in the area will be outbreaks or not.