International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | A Machine Learning Approach for Sleep Disorder Detection, Diagnosis, and Optimization |
|---|---|
| ABSTRACT | Effective identification of sleep disorders is fundamental to preserving physical health, psychological well-being, and overall quality of life. Traditional diagnostic techniques, such as polysomnography, remain reliable but demand manual interpretation, making them both time-consuming and resource-intensive. This work describes a technique for machine learning that makes use of behavioural and physiological data to automatically identify sleep issues. The system classifies sleep states into three categories: Normal, Sleep Apnea, and Insomnia It achieves excellent predicted accuracy by evaluating characteristics including body motions, Heart rate variability and oxygen saturation, and length of sleep using supervised learning. To optimize performance, feature engineering and selection are employed to reduce redundancy, improve computational efficiency, and enhance precision. Unlike conventional rule-based methods, the framework captures complex, non-linear interactions among sleep parameters. A trust-aware mechanism further strengthens reliability by filtering noisy or inconsistent sensor inputs. The trained model is deployed via a web-based interface, enabling real-time detection, interpretability, and user interaction. This approach reduces clinical workload, improves diagnostic efficiency, and facilitates early intervention. Future extensions may include integrating additional physiological signals, analysing long-term sleep trends, and leveraging real-time data from wearable devices to enhance adaptability and accuracy. |
| AUTHOR | AMULYA H S, NASEERHUSEN ANKALAGI PG Student, Dept. of MCA, City Engineering College, Bengaluru, India Assistant Professor, Dept. of MCA, City Engineering College, Bengaluru, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312058 |
| pdf/58_A Machine Learning Approach for Sleep Disorder Detection, Diagnosis, and Optimization.pdf | |
| KEYWORDS | |
| References | 1. Ga whale, S., Upasani, D. E., Khankal, D. V., Chaudhari, L., Kumar, J. R. R., & Upadhye, V. A. (2023). EEG signal processing using an ensemble machine learning classifier and hybrid deep learning for the diagnosis of sleep disorders. Intelligent Systems and Applications in Engineering International Journal. 2. [Author(s)]. (2025). A thorough study of artificial intelligence's diagnostic precision for identifying obstructive sleep apnoea. BMC Decision Making and Medical Informatics. 3. [Author(s)]. (2025). Deep Learning for Sleep Apnoea Prediction. PubMed 4. [Author(s)]. (2025). A systematic review of wearable sensors and artificial intelligence for the detection of sleep apnoea. PubMed. 5. [Author(s)]. (2022). A thorough systematic assessment of machine learning techniques based on ECG signals for the detection of sleep apnoea. Applications for Expert Systems. |
