Imputation-based Multimodal Data Integration
Real-life mobility data and brain structure data sets have been successfully collected in previous DynAge projects. This raised researchers’ interest in the relationship between the two data collections. However, the real-life mobility and brain structure datasets are distinct and cannot be simply mapped. The goal of this project is to integrate these two collections into one dataset containing both types of data by imputing the missing variable of one dataset. Specifically, we intend to explore training imputation models based on large-scale third-party datasets.