Abstract: Objective This study will analyze the feasibility, advantages and disadvantages of the application of BP neural network in TCM physique identification based on the characteristics of TCM physique identification, so as to obtain a more accurate physique typing, which makes the use of TCM for identifying diseases more widely and convenient. science. Methods The feedforward BP neural network model was used to operate the data to construct a BP neural network model suitable for TCM physique identification. We will carry out a questionnaire survey on community people aged 40 to 70 years old in Longjiang Town, Shunde District, Foshan City, Guangdong Province, collect data models through the TCM physique identification form and make predictions on the population's physique; then match the questionnaire content with the final results Among them, 525 sets of data are used as the training set input model, and the remaining 132 sets of data are used as the test set. After error testing and comparison analysis with the classic prediction model. The results show that the BP neural network method can predict the TCM constitution type of the community based on the questionnaire results of the TCM Constitution Identification Form. Conclusion The application of BP neural network in the classification of TCM constitutions has high reliability, simple operation, low cost, and convenient methods suitable for community promotion.Abstract: Objective This study will analyze the feasibility, advantages and disadvantages of the application of BP neural network in TCM physique identification based on the characteristics of TCM physique identification, so as to obtain a more accurate physique typing, which makes the use of TCM for identifying diseases more widely and convenient. science. ...Show More
