Prediction of sleep pattern for university students using machine learning
Sleep patterns significantly affect the health and academic performance of university students. This study aims to predict sleep patterns among university students using machine learning techniques, focusing on the classification of regular and irregular sleep behaviors. Data was collected through a...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | en |
| Published: |
IEEE
2026
|
| Subjects: | |
| Online Access: | https://umpir.ump.edu.my/id/eprint/47001/1/Prediction_of_Sleep_Pattern_for_University_Students_using_Machine_Learning-2.pdf https://umpir.ump.edu.my/id/eprint/47001/ https://doi.org/10.1109/COMNETSAT68601.2025.11324868 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Sleep patterns significantly affect the health and academic performance of university students. This study aims to predict sleep patterns among university students using machine learning techniques, focusing on the classification of regular and irregular sleep behaviors. Data was collected through an online survey of 286 respondents, covering features related to demographics, daily habits, and personal perceptions. The Random Forest algorithm was employed for classification, evaluated using a 5-Fold Cross-Validation protocol, and achieved an average accuracy of 81.46%. Key predictive features included Sleep Hours, Late Night Frequency (per-week), Sleep Quality, Fatigue Ratio, and Illness Frequency (per-month) are the most influential features. These results demonstrate the potential of machine learning in identifying key behavioral and demographic factors influencing sleep patterns, which can be used to support targeted health and academic interventions for students. |
|---|