Smartphone Data

Smartphone data, encompassing passively collected sensor data and actively reported information via apps, is increasingly used to address diverse research questions across various fields. Current research focuses on developing machine learning models, including neural networks and ensemble methods like XGBoost and SVMs, to analyze this data for applications such as disease monitoring (using digital biomarkers), behavioral analysis (e.g., assessing auditory hallucinations), and resource allocation (e.g., optimizing electrification infrastructure). This approach offers significant potential for improving healthcare, understanding human behavior, and informing public policy decisions by leveraging the ubiquity and data richness of smartphones.