Addressing Behavioral Patterns of Late Sleepers Using a Supervised Learning Approach

DOI

10.2991/978-94-6239-664-7_24How to use a DOI?

Keywords

Machine Learning; Sleep Pattern; Classification; Health Prediction; Supervised Learning

Abstract

Sleep disorders become a public health issue in view of the association with numerous detrimental physical, cognitive, and emotional outcomes. The problem has been focused on toward predicting and classifying medical conditions related to late-night sleeping habits through supervised machine learning applied on behavioral and lifestyle data. Anonymized secondary data on self-reported sleep routines, psychological symptoms, and related demographic variables were pre processed to counter class imbalance by oversampling employing SMOTE. Feature selection is done using Mutual Information. The four classifiers considered include Random Forest, XGBoost, Decision Tree, and K-Nearest Neighbor, which are compared. The XGBoost had the highest classification accuracy of 97.06%, followed by Random Forest at 96.30% and Decision Tree at 95.79%, showing the capabilities of ensemble classifiers in dealing with heterogeneous health data prediction problems. A rule-based recommendation engine was also added to the system to provide personalized recommendations for sleep based on predicted risk classes, user sleep patterns, and BMI score. The data tends to acknowledge that data-driven machine-learning systems can empower large-scale early detection and individualized intervention for sleep disorder health problems, especially in resource-constrained academic environments. Such results add to the body of literature extolling digital behavioral health analytics and point to possible avenues of appeal for tech-enabled health promotion among at risk students. The developed ML pipeline has high reproducibility and generalization capability to be deployed in scalable and interpretable manner for behavioral health analytics.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Neloy Pramanik Supto
AU  - Rajat Chowdhury
AU  - Mushfiqur Rahman
PY  - 2026
DA  - 2026/06/08
TI  - Addressing Behavioral Patterns of Late Sleepers Using a Supervised Learning Approach
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 341
EP  - 357
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_24
DO  - 10.2991/978-94-6239-664-7_24
ID  - Supto2026
ER  -