Sleeping Pattern Analysis Using Extreme Gradient Boosting and Logistic Regression

For the purpose of analyzing sleep, this research combines CNN (Convolutional Neural Network), XGB Classifier (Extreme Gradient Boosting) and Bi-LSTM (Bidirectional Long Short-Term Memory) techniques. For both physical and mental health, sleep is essential. Important sleep metrics like heart rate, body movement, and brainwave activity are included in the current dataset. In order to prepare this raw data for further analysis, data pre-processing fills in the gaps and addresses anomalies. Relevant sleep metrics are chosen through feature engineering. This research classifies sleep patterns and habits using machine learning techniques, such as classification and clustering, revealing the variables influencing sleep quality, such as daily routines and environmental conditions. The results enable early detection of sleep disorders and personalized sleep management, which is beneficial for both individuals and healthcare professionals.