Epidemic Outbreak Prediction Using SIR Model

The pace at which viruses are being transferred by individuals is rapidly rising, which has resulted in the loss of human life. The majority of those who get this covid-19 virus are likely to have hereditary disorders. This study examined how long it will take a patient to recover from a virus. This will assess the length of time a patient will need to recover from a virus using Deep Learning techniques. The combination of DBSCAN clustering and the SIR model is utilized to estimate the time required for a patient to recover from a virus. The dataset is first subjected to analysis using the DBSCAN clustering algorithm, which groups the data based on age as the primary criterion. The resulting cluster output is then inputted into the SIR model to assess accuracy. However, the accuracy of the cluster output is not satisfactory when compared to previous results. Therefore, the cluster output will be rechecked using different clustering algorithms to obtain more reliable results. By utilizing the more precise results obtained from the cluster output as a parameter, and integrating natural death and death caused by the disease as additional parameters in the SIR model, the project can obtain the most accurate outcomes. These parameters will facilitate the creation of a dependable visual predictor. The SIR model outcomes are presented through a web interface, which enables users to input population size, infection rate, and a COVID-19 dataset. Utilizing a Flask application, the SIR model output is visualized on a webpage.