New coronavirus propagation prediction method based on long short-term memory (LSTM) network model

Abstract

The invention discloses a new coronavirus propagation prediction method based on a long short-term memory (LSTM) network model, and the method comprises the following steps: 1, collecting the propagation data of covid-19 virus as the basic data of research, and intercepting the data at the initial stage of virus outbreak to obtain a data set; 2, segmenting the data set into a training data set and a test data set; 3, training a long short-term memory (LSTM) network model by using the training data set obtained in the step 2; 4, predicting future data by using the model trained in the step 3, and comparing the future data with real data in the test data set; and 5, quantifying a prediction error, and evaluating the accuracy of the model. The invention belongs to the technical field of virus propagation models, and particularly relates to a covid-19 virus propagation prediction method based on a long short-term memory (LSTM) network model, the law of data change is obtained from data, the prediction purpose is achieved, and the larger the training data volume is, the model can learn more laws, and a better prediction effect can also be achieved.

Description

technical field [0001] The invention belongs to the technical field of virus transmission models, and specifically refers to a method for predicting the transmission of new coronaviruses based on a long-short-term memory network LSTM model. Background technique [0002] The outbreak of the new coronavirus COVID-19, due to the lack of sufficient understanding of SARS CoV-2 and the super infectiousness of the virus, caused the outbreak of COVID-19. In the past, the prediction of the transmission trend of infectious diseases mostly used the mechanism prediction method based on the compartment model , the warehouse model was born in the 19th century. It takes the number of infected people as the research object, establishes a differential equation model according to the transmission mechanism, and finally obtains the functional relationship between the number of infected people and time through analysis. From this functional relationship, we can get when the epidemic will enter t...

AI Technical Summary

Problems solved by technology

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a method for predicting the spread of the new coronavirus based on the long short-term memory network LSTM model, which solves the problem that the prediction results in the prior art lack practical application value

Images