3 Questions about STAG – project in the «DSI Infrastructures & Labs» series
DSI Infrastructures & Labs are shareable infrastructures or structural vessels for creating collaborative research environments related to digital transformation. Prof. Dr. Jürgen Bernard briefly introduces STAG, one of the projects in this series.
What is STAG?
STAG (Statistical Timeseries Analysis Guide) is a modular, iterative framework for building case-specific pipelines to preprocess timeseries data in preparation for machine learning and data-driven decision-making (e.g., for preparing ECG signals for some cardiac event detection by an ML classifier). We are designing and developing STAG based on several real-world cases, with collaborators from DSI Community Health.
What could be a specific benefit of STAG?
Imagine refining timeseries data from fitness trackers to spot anomalies in your study's participant cohort. STAG can handle missing values, segment signals, and document each of your data analysis choices, revealing unexpected patterns and inspiring new hypotheses. Our iterative approach streamlines data cleaning and analysis, while generating valuable domain insights.
Which research areas will benefit most from STAG?
STAG benefits any field handling timeseries data – especially clinical research, wearable-tech studies, and health monitoring. Its iterative, insight-driven framework and thorough logging of operations enable rigorous, replicable workflows. Where raw signals must be transformed into meaningful, actionable insights, STAG is an ideal fit.
All projects of the series «DSI Infrastructures & Labs» can be found here.
Prof. Dr. Jürgen Bernard is an assistant professor for «Interacting with Data» at the Department of Informatics, head of the Interactive Visual Data Analysis (IVDA) research group and, as a DSI professor, part of the Digital Society Initiative (DSI). Since his time at the UZH, Jürgen has been honored with the EuroVis Young Researcher Award (2021) and the Eurographics Young Researcher Award (2022).