Posts

We recently published a paper at the 2023 CHI Conference on Human Factors in Computing Systems, presenting an in-vehicle machine learning system designed to predict critical blood alcohol concentration (BAC) levels in real-time. This system leverages driver monitoring cameras—now mandated in many countries—to assess a driver’s BAC. Our evaluation involved a simulator study with 30 participants, demonstrating that the system reliably detected any alcohol influence while driving with an area under the ROC-curve (AUROC) of 0.88. It also identified drivers exceeding the WHO-recommended limit of 0.05 g/dL BAC with an AUROC of 0.79. Model inspection revealed that the system relies on pathophysiological effects associated with alcohol consumption. ...

Exciting advancements are underway in the field of diabetes management with the introduction of HEADWIND, an advanced in-vehicle hypoglycemia warning system. This cutting-edge technology, funded by the Swiss National Science Foundation (SNF), aims to detect hypoglycemia in drivers with diabetes early and accurately by utilizing existing automotive sensors and data. The system integrates high-resolution, real-time driving data, physiological sensors, and driver camera video streams for eye and head pose tracking to identify hypoglycemic episodes. ...

FLIRT is a feature generation toolkit for wearable data such as that from your smartwatch or smart ring. With FLIRT you can easily transform wearable data into meaningful features which can then be used for example in machine learning or AI models. In contrast to other existing toolkits, FLIRT (1) focuses on physiological data recorded with (consumer) wearables and (2) calculates features based on a sliding-window approach. FLIRT is an easy-to-use, robust and efficient feature generation toolkit for your wearable device! ...