Related Experiment Video
Updated: May 29, 2026

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data
Published on: December 9, 2015
[Application of wavelet neural networks model to forecast incidence of syphilis]
Xian-Feng Zhou1, Zi-Jian Feng, Wei-Zhong Yang
1Department of Health Statistics, West China School of Public Health, Sichuan University, Chengdu 610041, China.
Objective:
To apply Wavelet Neural Networks (WNN) model to forecast incidence of Syphilis.
Methods:
Back Propagation Neural Network (BPNN) and WNN were developed based on the monthly incidence of Syphilis in Sichuan province from 2004 to 2008. The accuracy of forecast was compared between the two models.
Results:
In the training approximation, the mean absolute error (MAE), rooted mean square error (RMSE) and mean absolute percentage error (MAPE) were 0.0719, 0.0862 and 11.52% respectively for WNN, and 0.0892, 0.1183 and 14.87% respectively for BPNN. The three indexes for generalization of models were 0.0497, 0.0513 and 4.60% for WNN, and 0.0816, 0.1119 and 7.25% for BPNN.
Conclusion:
WNN is a better model for short-term forecasting of Syphilis.
Related Concept Videos
Steps in Outbreak Investigation
Sexually Transmitted Infections
Statistical Methods for Analyzing Epidemiological Data
Prevalence and Incidence
Prevalence indicates the proportion of individuals in a population who have a specific disease or health condition at a...

