Percorrer por autor "Marchetti, Jacqueline"
A mostrar 1 - 1 de 1
Resultados por página
Opções de ordenação
- A deep learning approach to monitoring workers stress at officePublication . Marchetti, Jacqueline; Rodrigues, Maria de Fátima CoutinhoIdentifying stress in people is not a trivial or straightforward task, as several factors are involved in detecting the presence or absence of stress. Since there are few tools on the market that companies can use, new models have been created and developed that can be used to detect stress. In this study, we propose developing a stress detection application using deep learning models to analyze images obtained in the workplace. It will provide information from these analyses to the company so they can use it for occupational health management. The proposed solution uses deep learning algorithms to create prediction models and analyze images. The new non-invasive application is designed to help detect stress and educate people to control their health conditions. The model trained achieved an F1=79.9% with a binary dataset of stress/non-stress that have an imbalanced ratio of 0.49