Deep learning shows promise for automating detection and classification of wildlife from digital aerial imagery to support cost-efficient remote sensing solutions for wildlife population monitoring. To support in-flight orthorectification and machine learning processing to detect and classify wildlife from imagery in near real-time, we evaluated deep learning methods that address hardware limitations and the need for processing efficiencies to support the envisioned in-flight workflow. We developed an annotated dataset for a suite of marine birds from high-resolution digital aerial imagery collected over open water environments to train the models.
View Article and Find Full Text PDFThe job demands-resources model (JD-R) has shown an ability to predict worker engagement and exhaustion, yet to our knowledge, research has not been conducted that assesses the JD-R model with physiological indicators of chronic stress and burnout. Using the JD-R model, we assessed if occupational stress and burnout were related to dysregulated cortisol and salivary alpha-amylase awakening responses (sAA-AR). Professional apprentice jockeys comprising of males (n = 14) and females (n = 18) provided morning saliva samples and completed self-report measures relating to job demands and resources, burnout, and perceived mental and physical health.
View Article and Find Full Text PDFPsychoneuroendocrinology
October 2017
The inverse relationship between acute stress and decision-making is well documented, but few studies have investigated the impact of chronic stress. Jockeys work exhaustive schedules and have extremely dangerous occupations, with safe performance requiring quick reaction time and accurate decision-making. We used the effort reward imbalance (ERI) occupational stress model to assess the relationship of work stress with indices of stress physiology and decision-making and reaction time.
View Article and Find Full Text PDFEffort-reward imbalance in the workplace is linked to a variety of negative health and organisational outcomes, but it has rarely been assessed experimentally. We manipulated reward (while keeping effort constant) in a within-subjects design with female participants (N=60) who were randomly assigned to high and standard reward conditions within a simulated office environment. Self-report, behavioural (task performance), and physiological (heart rate variability, salivary alpha amylase) measures assessed the impact of increased financial reward.
View Article and Find Full Text PDF