Analysis of the capabilities of an information system for improving sleep quality based on biometric data analysis
The paper analyses the capabilities of an information system for improving sleep quality based on the analysis of biometric data using Ambient Intelligence (AmI) technology. In the context of modern stressful realities, in particular the impact of the COVID-19 pandemic and social upheavals that sign...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Zhytomyr Polytechnic State University
2024-12-01
|
| Series: | Технічна інженерія |
| Subjects: | |
| Online Access: | http://ten.ztu.edu.ua/article/view/319158 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The paper analyses the capabilities of an information system for improving sleep quality based on the analysis of biometric data using Ambient Intelligence (AmI) technology. In the context of modern stressful realities, in particular the impact of the COVID-19 pandemic and social upheavals that significantly worsen the psychophysical state of people, improving sleep quality is of particular relevance. AmI systems allow you to automatically adjust environmental parameters such as temperature, lighting and humidity based on individual biometric parameters of the user, which helps to maintain natural circadian rhythms and improve overall comfort during sleep. The article discusses current research in the field of adaptive sleep management systems that take into account human biorhythms and physiological needs. Particular attention is paid to the capabilities of AmI systems to autonomously adjust environmental parameters according to data collected from sensors, such as body temperature, heart rate, and sleep phases. The study shows that these technologies not only improve sleep conditions, but also have a positive impact on the user's overall health and reduce stress levels. The system is able to function independently thanks to the use of machine learning algorithms, including LSTM for prediction, Kalman filter for data cleaning, Isolation Forest for anomaly detection, and K-means for clustering sleep patterns. |
|---|---|
| ISSN: | 2706-5847 2707-9619 |