What a difference a year makes: Objective rest/activity patterns, circadian phase markers, and sleep quality before and during the COVID-19 pandemic.

OBJECTIVES: The COVID-19 pandemic led to numerous changes in sleep duration, quality, and timing. The goal of this study was to examine objective and self-reported changes in sleep and circadian timing before and during the pandemic. METHODS: Data were utilized from an ongoing longitudinal study of sleep and circadian timing with assessments at baseline and 1-year follow-up. Participants had baseline assessment between 2019 and March 2020 (before pandemic) and 12-month follow-up between September 2020 and March 2021 (during pandemic). Participants completed 7 days of wrist actigraphy, self-report questionnaires, and laboratory-collected circadian phase assessment (dim light melatonin onset). RESULTS: Actigraphy and questionnaire data were available for 18 participants (11 women and 7 men, Mean = 38.8 years, SD = 11.8). Dim light melatonin onset was available for 11 participants. Participants demonstrated statistically significant decreases in sleep efficiency (Mean = -4.11%, SD = 3.22, P = .001), worse scores on Patient-Reported Outcome Measurement Information System sleep disturbance scale (Mean increase = 4.48, SD = 6.87, P = .017), and sleep end time delay (Mean = 22.4 mins, SD = 44.4 mins, P = .046). Chronotype was significantly correlated with change in dim light melatonin onset (r = 0.649, P = .031). This suggests that a later chronotype is associated with a greater delay in dim light melatonin onset. There were also non-significant increases in total sleep time (Mean = 12.4 mins, SD = 44.4 mins, P = .255), later dim light melatonin onset (Mean = 25.2 mins, SD = 1.15 hrs, P = .295), and earlier sleep start time (Mean = 11.4 mins, SD = 48 mins, P = .322). CONCLUSION: Our data demonstrate objective and self-reported changes to sleep during the COVID-19 pandemic. Future studies should look at whether some individuals will require intervention to phase advance sleep when returning to previous routines such as returning to office and school settings.

Detection of Mask Wearing in Dim Light Based on Attention Mechanism

Since the outbreak of COVID-19, the detection of wearing masks has become a necessary measure for epidemic prevention and control. To solve the problem about low accuracy of mask wearing detection under dim lighting conditions, a method of mask wearing detection combining attention mechanism with YOLOv5 network model is proposed, which uses image enhancement algorithm to pre-process the training set pictures, and then put these pictures to YOLOv5 network with attention mechanism for iterative training. After training, the optimal weight is saved and the best model is used to test the accuracy on the test set. The experimental results show that the YOLOv5 network model with attention mechanism can effectively enhance the extraction of key points such as face and mask and improve the robustness of the model. The accuracy of mask wearing can reach 92% under dim lighting conditions, which can effectively meet the actual needs. Copyright ©2022 Journal of University of Electronic Science and Technology of China. All rights reserved.