Fatigue and drowsiness can play an important role in Conditional Automation (CA), as drowsy drivers may fail to properly recover control. In order to provide better insight in the effects of drowsy driving in Take Over Request (TOR), we designed a driving experiment that extends related literature in drowsiness research CA with self-rated subjective drowsiness, and analyze TOR performance adopting methods from recent TOR publications. Results show that under certain conditions, drivers are very prone to drowsiness. Specifically, in this study the majority of subjects reported a high level of drowsiness before 15 minutes. Furthermore, this self-perceived drowsiness was followed by a decrement in vehicle lateral control during TOR. In this time frame, remaining driving performance and eye-Tracking related metrics did not show significant decrements traditionally associated with fatigue and drowsiness, suggesting self-report to be more indicative of drowsiness than eye-based metrics.@en

Objectives: Hand hygiene has long been promoted as the most effective way to prevent the transmission of infection. However, due to low compliance and low quality of hand hygiene reported in previous studies, constant monitoring of hand hygiene compliance and quality among healthcare workers is crucial. This study investigated the feasibility of using a thermal camera with an RGB camera to detect hand coverage of alcohol-based formulation, thereby monitoring the quality of hand rubbing. Methods: In total, 32 participants were recruited to participate in this study. Participants were required to perform four types of hand rubbing to achieve different coverage of the alcohol-based formulation. After each task, participants' hands were photographed under a thermal camera and an RGB camera, while an ultraviolet (UV) test was used to provide the ground truth of hand coverage of alcohol-based formulation. U-Net was used to segment areas exposed to alcohol-based formulation from thermal images, and system performance was evaluated by comparing differences in coverage between thermal images and UV images in terms of accuracy and Dice coefficient. Results: This system found promising results in terms of accuracy (93.5%) and Dice coefficient (87.1%) when observations took place 10 s after hand rubbing. At 60 s after hand rubbing, accuracy and Dice coefficient were 92.4% and 85.7%. Conclusions: Thermal imaging has potential for accurate, constant and systematic monitoring of the quality of hand hygiene.@en