Search

Prolonged sitting and inadequate sleep can impact driving performance. Therefore, objective knowledge of a driver's recent sitting and sleep history could help reduce safety risks. This study aimed to apply deep learning to raw accelerometry data collected during a simulated driving task to classify recent sitting and sleep history. Participants (n = 84, Mean ± SD age = 23.5 ± 4.8, 49% Female) completed a seven-day laboratory study. Raw accelerometry data were collected from a thigh-worn accelerometer during a 20-min simulated drive (8:10 h and 17:30 h each day). Two convolutional neural networks (CNNs; ResNet-18 and DixonNet) were trained to classify accelerometry data into four classes (sitting or breaking up sitting and 9-h or 5-h sleep). Accuracy was determined using five-fold cross-validation. ResNet-18 produced higher accuracy scores: 88.6 ± 1.3% for activity (compared to 77.2 ± 2.6% from DixonNet) and 88.6 ± 1.1% for sleep history (compared to 75.2 ± 2.6% from DixonNet). Class activation mapping revealed distinct patterns of movement and postural changes between classes. Findings demonstrate the suitability of CNNs in classifying sitting and sleep history using thigh-worn accelerometer data collected during a simulated drive. This approach has implications for the identification of drivers at risk of fatigue-related impairment. [ABSTRACT FROM AUTHOR]

Firefighters are exposed to numerous stressors during wildfire suppression, including working in hot temperatures and sleep restricted conditions. Research has shown that when sleep restricted, individuals choose foods higher in carbohydrates, fat, and sugar, and have increased cravings for calorie dense foods. However, there is currently no research on the combined effect of heat and sleep restriction on snacking behaviour. Conducting secondary analyses from a larger study, the current study aimed to investigate the impact of heat and sleep restriction on snacking behaviour and food cravings. Sixty-six firefighters completed three days of simulated physically demanding firefighting work and were randomly allocated to either the control (n = 18, CON; 19 °C, 8 h sleep opportunity), sleep restricted (n = 16, SR; 19 °C, 4-h sleep opportunity), hot (n = 18, HOT; 33 °C, 8 h sleep opportunity), or hot and sleep restricted (n = 14 HOT + SR; 33 °C, 4-h sleep opportunity) condition. During rest periods firefighters were able to self-select sweet, savoury, or healthy snacks from a ration pack and were asked to rate their hunger, fullness, and cravings every two hours (eating block). Mixed model analyses revealed no difference in total energy intake between conditions, however there was a significant interaction between eating block and condition, with those in the CON, HOT, and HOT + SR condition consuming significantly more energy between 1230 and 1430 compared to the SR condition (p = 0.002). Sleep restriction and heat did not impact feelings of hunger and fullness across the day, and did not lead to greater cravings for snacks, with no differences between conditions. These findings suggest that under various simulated firefighting conditions, it is not the amount of food that differs but the timing of food intake, with those that are required to work in hot conditions while sleep restricted more likely to consume food between 1230 and 1430. This has potential implications for the time of day in which a greater amount of food should be available for firefighters. [ABSTRACT FROM AUTHOR]