2990. Identification of Circadian Cycle Disruptors in Night Shift Workers Using Machine Learning Models
Invited abstract in session WC-34: Business Applications of Knowledge and Technology, stream Advancements of OR-analytics in statistics, machine learning and data science.
Wednesday, 12:30-14:00Room: Michael Sadler LG10
Authors (first author is the speaker)
| 1. | Karen Nino
|
| Universidad Militar Nueva Granada | |
| 2. | Julián Calixto
|
| Industrial Engineering, Universidad Militar Nueva Granada | |
| 3. | Sepideh Abolghasem
|
| Industrial Engineering, Universidad de los Andes |
Abstract
Globalization and the expansion of industries have accelerated over time, leading to a growing demand for continuous operations in sectors such as healthcare, security, and manufacturing. This latter has raised the need of night shifts of workers disrupting the natural biological rhythm of them, which is known as circadian cycle. This cycle regulates essential bodily functions such as body temperature, digestion, and sleep. Disruptions to this cycle can have short, medium, and long-term consequences on job performance, health, and safety.
This study focuses on identifying the key factors that most significantly impact the circadian cycle using machine learning techniques. Various classification algorithms such as Decision Tree, Artificial Neural Network, Random Forest, CATBoost, XGBoost, and k-Nearest Neighbors, are employed to analyze large datasets, detect patterns, and identify influential variables. Data is processed, evaluated, and filtered based on its relevance to identify the most accurate model for forecasting the factors and their combinations that influence circadian rhythm disturbances. The insights gained from this study could contribute to improved shift scheduling strategies and workplace policies aimed at mitigating the adverse effects of night shifts on workers' well-being and productivity.
Keywords
- Machine Learning
- Forecasting
- Health Care
Status: accepted
Back to the list of papers