This research utilized vehicle-based measures from a naturalistic driving dataset to detect distraction as indicated by long off-path glances (≥ 2 s) and whether the driver was engaged in a secondary (non-driving) task or not, as well as to estimate motor control difficulty associated with the driving environment (i.e. curvature and poor surface conditions). Advanced driver assistance systems can exploit such driver behavior models to better support the driver and improve safety. Given the temporal nature of vehicle-based measures, Hidden Markov Models (HMMs) were utilized; GPS speed and steering wheel position were used to classify the existence of off-path glances (yes vs. no) and secondary task engagement (yes vs. no); lateral (x-axis) and longitudinal (y-axis) acceleration were used to classify motor control difficulty (lower vs. higher). Best classification accuracies were achieved for identifying cases of long off-path glances and secondary task engagement with both accuracies of 77%.
Distractions can interfere with surgical tasks and may negatively impact task performance, surgery duration, and mood of surgical team members. A mixed-methods study was conducted to examine the prevalence and potential effects of distractions during general surgery, in particular during the surgical procedure and post-operative counts. An audio-video recording platform named the OR BlackBox® was used to record data from 40 surgical cases, which was in turn coded by multiple raters. Supporting qualitative data was collected through interviews with four OR staff members. The audio-video data revealed that distractions occurred on the average about every three minutes during the surgical procedure, and most frequently observed effect was distracted members not noticing other members’ requests. Twenty-nine of the cases had at least one changeover during the surgical procedure whereas overall four changeovers occurred during post-operative counts; in one of these cases the count was repeated, resulting in a delay of almost 15 minutes. Other distractions (OR traffic, communication, and others) were frequent both during the surgical procedure (M=0.39 per minute per case, SD=0.15) and post-operative counts (M=0.75 per minute per case, SD=0.44). The interviews were preliminary in nature and provided additional insights on the effects of OR distractions and potential mitigation strategies to inform future OR distraction research.
Training for advanced driver assistance systems (ADAS) generally aims to teach drivers various system limitations. However, limitation-focused training has disadvantages, such as drivers having difficulty remembering a long list of limitations over time. The current study compared limitation-focused training with responsibility-focused training, which aims to teach drivers how they should be using ADAS and the consequences if they do not use the systems appropriately. We asked 62 participants several open-ended questions after they watched either a limitation-focused ( n = 32) or responsibility-focused ( n = 30) training video to investigate the effects of each training approach on driver attitudes toward ADAS and how they intend to use ADAS. We also elicited feedback about the training itself. Thematic analysis of the interview transcripts showed that drivers in both training groups thought the videos were helpful and both training approaches were associated with reduced intention to engage in distractions while using ADAS. Results also showed that decreased interest in ADAS and reports of not wanting to use ADAS were more common after the limitation-focused training, with drivers in the limitation-focused group highlighting the number of limitations and unclear benefits as reasons why they would not use ADAS. Given the drawbacks associated with limitation-focused training, our results suggest that the responsibility-focused approach may be a reasonable alternative that should be investigated further with behavioral studies. Participant feedback about the training is also summarized in the paper, which can inform the design of future ADAS training.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.