Imputation of Human Mobility Data for Comprehensive Risk Models

Abstract

Sensor-equipped wearable devices are becoming increasingly popular in the healthcare industry, with some equipped with GPS and Proximity sensors as well. Raw (GPS) trajectories obtained through human-centric systems like body worn senors, and enriched with semantic annotations generate huge actionable insights for downstream domain specific applications like epidemic risk modeling. However, trajectory data suffer from missing data problem owing to various technical as well as behavioral factors. Our paper shows that, for a semantic trajectory dataset and using coarse grain semantic location for both prediction and imputation purposes, a simple ensemble classifier-based model can outperform the existing deep models where trajectory imputation is almost real-time delay.