A Machine Learning Approach to Analyze Manpower Sleep Disorder
Introduction: Human resources play a pivotal role in determining the efficiency of a workplace and an organization. One major issue that significantly influences workforce productivity is sleep disorders. Machine learning can be applied to predict sleep disorders and analyze how various factors, suc...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SBMU Journals
2024-01-01
|
| Series: | Archives of Advances in Biosciences |
| Subjects: | |
| Online Access: | https://journals.sbmu.ac.ir/aab/article/view/44853 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Introduction: Human resources play a pivotal role in determining the efficiency of a workplace and an organization. One major issue that significantly influences workforce productivity is sleep disorders. Machine learning can be applied to predict sleep disorders and analyze how various factors, such as lifestyle and environmental conditions, contribute to the development of these disorders, paving the way for more effective interventions and solutions.
Materials and Methods: In this research, by utilizing data analytic methods, some physical and medical-related features of manpower are investigated to make beneficial observations. Moreover, a combination of machine learning and metaheuristic algorithms such as eXtreme Gradient Boosting and particle swarm optimization are used to make an accurate predictive model. Also, the accuracy, recall, precision, and F1-score metrics are utilized to evaluate the model. The Python and Scikit-learn package are used to analyze the problem and implement algorithms.
Results: The outcome is a predictive model with 93.1% accuracy to predict the type of sleep disorder and some useful insights like the relationship of different variables like job and physical characteristics with the sleep disorder. It is observed that one’s occupation has the most impact on insomnia (1.25) and BMI has the most effect on sleep apnea (1).
Conclusion: The implementation of a predictive model helps identify existing issues and enables proactive measures to prevent potential problems, allowing decision-makers to design targeted interventions and wellness programs. Continuous monitoring and adjustments based on the model’s predictions ensure adaptive strategies that improve employee health and workplace efficiency, fostering a resilient workforce and enhancing overall organizational performance.
|
|---|---|
| ISSN: | 2783-1264 |