Fog-Cloud Integrated Sleep Monitoring and Detection Framework
Bibliographic Data
| ID | 22106971 |
|---|---|
| Authors | Kriti Mahajan (0009-0007-9341-8690, Thapar Institute of Engineering & Technology), Mandeep Kaur (0000-0001-5163-4001, Thapar Institute of Engineering & Technology) |
| Year | 2026 |
| Volume | 13 |
| Issue | 2 |
| Pages | 2165-2174 |
| Publication date | 2026-04-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | IEEE Transactions on Computational Social Systems (JOURNAL) |
| Journal identifiers | ISSN: 2329-924X • E-ISSN: 2373-7476 |
| Publisher | Institute of Electrical and Electronics Engineers (IEEE) (PUBLISHER) |
| DOI | 10.1109/tcss.2025.3633885 |
| OpenAlex | W4417438802 |
| Language | EN |
| References cited | 16 |
Sleep plays a crucial role in cognitive, emotional, and physical health. Due to limitations in existing monitoring methods, less than 30% of people affected by sleep disorders receive proper care. However, sleep detection and monitoring require an efficient approach to improve sleep patterns. Wearable accelerometers are a widely used, cost-effective, and noninvasive method to track sleep through body movements. Detecting precise sleep-wake transitions remains challenging due to the lack of a proper existing pipeline. This article proposes a fog-cloud-assisted framework to detect and monitor sleep patterns. In the proposed approach, raw data from the wearable accelerometer collected in the data accumulation layer is preprocessed in the fog layer to extract meaningful features. Missing values are handled using KNN imputation and feature engineering is performed using temporal derivatives and power transformations. A random forest model is implemented in the cloud layer for sleep–wake classification, with its hyperparameters optimized through RandomizedSearchCV using 5-fold stratified cross-validation. The findings reveal that the model attained the best performance with an F1 score of 0.8846 and an accuracy of 0.8852. The performance analysis demonstrates the reliability and effectiveness of the proposed approach for real-world sleep tracking
Accelerometer · Actigraphy · Cloud computing · Hyperparameter · Polysomnography · Random forest · Wearable computer · EEG and Brain-Computer Interfaces · Non-Invasive Vital Sign Monitoring · Sleep and related disorders
| Highly cited | No |
|---|