A transfer learning-based multivariate control chart for dengue surveillance in Hong Kong

Dengue is a severe mosquito-borne epidemic disease. There no effective vaccine for dengue, so real-time surveillance system becomes crucial to detect dengue outbreaks. Control charts have been widely used as efficient tools identify changes in health-related data. In Hong Kong, the environmental protection department uses area ovitrap index survey monthly number of mosquitoes different areas. Some areas limited historic records since started only recently. Parameter estimation designing control challenging with little This paper proposes transfer learning-based estimator increase parameter accuracy data points. We study questions on what and how useful knowledge from related source A multivariate chart based transfer-learned parameters developed online monitoring. real example demonstrates its effectiveness application.