Determining epidemiological patterns in disease identification using mathematical models on machine learning based multilayer structures

The object of the study is epidemiological grouping using the SEIR mathematical model on a machine learning-based multilayer network. The problems in this research are related to managing epidemiological data on a large scale to determine disease patterns and identification such as the number of recovered cases, number of infected cases and number of deaths and demographic factors. In the process, traditional methods make it difficult to carry out processes such as determining patterns and identifying diseases. So, it is necessary to use machine learning and the SEIR (Susceptible-Exposed-Infectious-Recovered) mathematical model which can be integrated with multilayer networks to increase accuracy and effectiveness in identifying diseases and determining patterns. The results obtained from this research are a model that can identify and determine patterns of disease spread in large-scale epidemiological data. In its application, the SEIR mathematical model combined into a social layer and an environmental layer in a multilayer network. This research is research with a level of novelty in the application of the SEIR mathematical model to multilayer networks and machine learning so that the model formed can be used to view the distribution of epidemiological data for disease-related information. Machine learning aims to process large-scale data in minimal time resulting in clustering and identification of diseases such as flu, Covid-19 and pneumonia. This research has an accuracy of 94 % using the MAPE evaluation technique. It is hoped that the resulting model can be used in the world of health for disease mapping in certain areas as a reference for mitigating the spread of disease