Description
- Abstract:
- Sleep deprivation in high-stress work environments can compromise safety, cause health issues, and negatively impact the work being done. Our research focuses on the detection and analysis of sleep deprivation to foster safer and more efficient work environments. We are using machine learning to develop a pipeline to identify a sleep-impaired state from physiological data. In the past, eye and face tracking, heart rate, electrodermal activity (EDA), motion, and voice recordings have all been used to identify sleep deprivation. We aim to further optimize the accuracy of our prediction model by feeding it multiple types of data such as heart rate, EDA, and potentially motion tracking. While shown to be effective, we had concerns that eye and face tracking or voice recording would be difficult to carry out in an active or loud environment. Currently, we are in the process of preliminary data collection to better understand the data and determine the best approach for a larger study. This involves collecting heart rate, EDA, and motion data over multiple days using the Empatica E4 sensor. This data is paired with results from the Psychomotor Vigilance Task (PVT), which has been proven to be very effective in identifying sleep deprivation. Interpreting the data will involve preprocessing, including dimensionality reduction, cleaning, and standardization of the dataset. Next, we will train a model to classify data as corresponding to either a sleep-deprived state or a normal state. Past studies have used Convolutional Neural Networks, Time Batched Long Short-Term Memory (TB-LSTM) networks, Recurrent Neural Networks, Linear Discriminant classification models, Naive Bayes classifiers, and Random Forest classifiers to model similar problems. As we move forward, we will experiment with different models and determine the best to apply to this challenge.
Access Conditions
- Use and Reproduction
- All rights reserved
- Rights
- In Copyright
- Restrictions on Use
- All Rights Reserved
Citation
Magavi, Maya, and Yeh, Kyle,
"Detecting Sleep Deprivation in Working Environments"
(2024).
Summer Research Symposium.
Brown Digital Repository. Brown University Library.
https://repository.library.brown.edu/studio/item/bdr:dfe8a2w7/
Relations
Collection:
-
Summer Research Symposium
Each year, Brown University showcases the research of its undergraduates at the Summer Research Symposium. More than half of the student-researchers are UTRA recipients, while others receive funding from a variety of Brown-administered and national programs and fellowships and go …...