Makine Öğrenimi Teknikleriyle Uyku Bozukluklarına Yönelik Derinlemesine Analiz ve Sınıflandırma

Abstract

Bu çalışma, uyku kalitesi ile yaşam tarzı faktörleri arasındaki bağlantıyı derinleme-sine incelemektedir. Araştırma, cinsiyet, yaş ve meslek gibi demografik özellikler ile uyku süresi, kalitesi, fiziksel aktivite düzeyleri ve stres gibi yaşam tarzı değişken-lerinin uyku bozukluklarına etkisini makine öğrenimi teknikleri kullanarak analiz etmektedir. Çalışmada, Lojistik Regresyon, En yakın komşular, Naive Bayes, Rastgele Orman, AdaBoostClassifier ve Destek Vektör Makinesi (SVM) gibi çeşitli makine öğrenimi modelleri uygulanmıştır. Özellikle Rastgele Orman ve SVM mod-elleri, yüksek doğruluk oranları sayesinde uyku bozukluklarını belirlemede etkili oldukları gözlemlenmiştir. Ayrıca, meslek ve stres düzeyleri ile uyku bozuklukları arasındaki ilişkiler üzerine detaylı analizler yapılarak, uyku sağlığının iyileştirilmesi için öneriler sunulmuştur.

Keywords

• Uyku sağlığı
• Uyku bozuklukları
• Makine öğrenimi
• Random Forest
• Destek Vektör Makinesi

In-depth Analysis and Classification of Sleep Disorders with Machine Learning Techniques

Abstract

This study investigates the link between sleep quality and lifestyle factors in depth. The study analyses the effect of demographic characteristics such as gender, age, and occupation and lifestyle variables such as sleep duration, quality, physical activity levels, and stress on sleep disorders using machine learning techniques. In the study, various machine learning models such as logistic regression, nearest neighbors, naive bayes, random forest, adaBoost classifier, and support vector machine (SVM) were applied. In particular, Random Forest and SVM models were found to be effective in identifying sleep disorders due to their high accuracy rates. In addition, detailed analyses on the relationships between occupation, stress levels, and sleep disorders were performed, and recommendations were presented to improve sleep health.

Keywords

• Sleep health
• Sleep disorders
• Machine learning
• Random Forest
• Support Vector Machine

References

1. St-Onge, M., Grandner, M. A., Brown, D. L., Conroy, M. B., Jean-Louis, G., Coons, M. J., … & Bhatt, D. L. (2016). Sleep duration and quality: impact on lifestyle behaviors and cardiometabolic health: a scientific statement from the american heart association. Circulation, 134(18), 367-386.
2. Bruce, E., Lunt, L., & McDonagh, J. E. (2017). Sleep in adolescents and young adults. Clinical Medicine, 17(5), 424-428.
3. Chattu, V. K., Manzar, M. D., Kumary, S., Burman, D., Spence, D. W., & Pandi-Perumal, S. R. (2018). The global problem of insufficient sleep and its serious public health implications. Healthcare, 7(1), 1-16.
4. Allen, S., Akram, U., & Ellis, J. (2020). Examination of sleep health dimensions and their as-sociations with perceived stress and health in a uk sample. Journal of Public Health. 28, 42(1), 34-41.
5. Urtnasan, E., Joo, E. Y., & Lee, K. (2021). Ai-enabled algorithm for automatic classification of sleep disorders based on single-lead electrocardiogram. Diagnostics, 11(11), 2054.
6. Kwon, K., Kwon, S., & Yeo, W. (2022). Automatic and accurate sleep stage classification via a convolutional deep neural network and nanomembrane electrodes. Biosensors, 12(3), 155.
7. Rakhonde, M. A., Wagh, K., & Mante, R. V. (2020). Sleep stage classification for prediction of human sleep disorders by using machine learning approach. International Journal of Innovative Science and Research Technology, 5(7), 1268-1272.
8. Pradeepkumar, J., Anandakumar, M., Vinith, K., Suntharalingham, D., Kappel, S. L., Silva, A. C. D., … & Edussooriya, C. U. S. (2022). Towards interpretable sleep stage classification using cross-modal transformers.

9. Sundararajan, K., Georgievska, S., Lindert, B. H. W. T., Gehrman, P., Ramautar, J., Mazzotti, D. R., … & Hees, V. T. v. (2021). Sleep classification from wrist-worn accelerometer data using random forests. Scientific Reports, 11(1), 24.
10. Delimayanti, M. K., Purnama, B., Nguyen, N. M., Faisal, M. R., Mahmudah, K. R., Indriani, F., … & Satou, K. (2020). Classification of brainwaves for sleep stages by high-dimensional fft features from eeg signals. Applied Sciences, 10(5), 1797.
11. Yulita, I. N., Fanany, M. I., & Arymurthy, A. M. (2018). Fast convolutional method for automatic sleep stage classification. Healthcare Informatics Research, 24(3), 170.
12. Cho, T., Sunarya, U., Yeo, M. S., Hwang, B. K., Koo, Y. S., & Park, C. (2019). Deep-actinet: end-to-end deep learning architecture for automatic sleep-wake detection using wrist actigraphy. Electronics, 8(12), 1461.
13. KaggleVeriseti, https://www.kaggle.com/datasets/uom190346a/sleep-health-and-lifestyle-dataset
14. Saxena, R., Sharma, S. K., Gupta, M., & Sampada, G. C. (2022). A novel approach for feature selection and classification of diabetes mellitus: machine learning methods. Computational Intelligence and Neuroscience, 2022, 1-11.
15. Battineni, G., Chintalapudi, N., Amenta, F., & Traini, E. (2020). A comprehensive ma-chine-learning model applied to magnetic resonance imaging (mri) to predict alzheimer’s disease (ad) in older subjects. Journal of Clinical Medicine, 9(7), 2146.
16. Yang, Z., Chen, C., Li, H., Yao, L., & Zhao, X. (2020). Unsupervised classifications of depression levels based on machine learning algorithms perform well as compared to traditional norm-based classifications. Frontiers in Psychiatry, 11.
17. Sharma, A. (2021). Guided parallelized stochastic gradient descent for delay compensation. Applied Soft Computing, 102, 107084.
18. Karasek, R. (1979). Job demands, job decision latitude and mental strain: Implications for job redesign. Administrative Science Quarterly, 24, 285-306.
19. Siegrist, J. (1996). Adverse health effects of high-effort/low-reward conditions. Journal of Oc-cupational Health Psychology, 1, 27–41.
20. Yperen, N. W. V. (2000). A multilevel analysis of the demands–control model: is stress at work determined by factors at the group level or the individual level?. Journal of Occupational Health Psychology, 5(1), 182-190.
21. Pelfrene, E., Vlerick, P., Kittel, F., Mak, R., Kornitzer, M., & Backer, G. D. (2002). Psychosocial work environment and psychological well‐being: assessment of the buffering effects in the job demand–control (–support) model in belstress. Stress and Health, 18(1), 43-56.
22. Rubino, C., Perry, S. J., Milam, A., Spitzmüeller, C., & Zapf, D. (2012). Demand–control–person: integrating the demand–control and conservation of resources models to test an expanded stressor–strain model.. Journal of Occupational Health Psychology, 17(4), 456-472.
23. Spiegelaere, S. D., Ramioul, M., & Gyes, G. V. (2017). Good employees through good jobs. Employee Relations, 39(4), 503-522.
24. Gemert, J. C. v., Snoek, C. G. M., Veenman, C. J., & Smeulders, A. (2006). The influence of cross-validation on video classification performance. Proceedings of the 14th ACM International Conference on Multimedia.
25. Schaffer, C. (1993). Selecting a classification method by cross-validation. Machine Learning, 13(1), 135-143.
26. Wichard, J., Cammann, H., Stephan, C., & Tolxdorff, T. (2008). Classification models for early detection of prostate cancer. Journal of Biomedicine and Biotechnology, 2008, 1-7.
27. LeDell, E., Petersen, M., & Laan, M. J. v. d. (2015). Computationally efficient confidence in-tervals for cross-validated area under the roc curve estimates. Electronic Journal of Statistics, 9(1).
28. Westerhuis, J. A., Hoefsloot, H. C. J., Smit, S., Vis, D. J., Smilde, A. K., Velzen, E. J. J. v., … & Dorsten, F. A. v. (2008). Assessment of plsda cross validation. Metabolomics, 4(1), 81-89.