Integration of a feature selection techniques using a sleep quality dataset
Автор: Machinel Learning Insights
Загружено: 2025-05-21
Просмотров: 23
📊 Predicting Stress from Sleep: Machine Learning with Feature Selection Techniques
In this video, we explore the integration of feature selection methods with regression algorithms to predict stress levels from sleep quality data. Using a dataset from Kaggle that includes physiological sleep metrics (like heart rate, oxygen levels, and hours of sleep), we apply advanced machine learning techniques to identify which features are most critical for accurate prediction.
✨ What You’ll Learn:
Importance of sleep data in health analytics
Feature selection methods: SelectKBest, PCA, Chi-Squared, Mutual Information, RFE
Regression models: Linear Regression, Ridge, Lasso, Random Forest, XGBoost
Evaluation metrics: RMSE, R²
Insights into which models and features work best
🔬 Conclusion Highlights:
XGBoost and Random Forest outperformed Ridge Regression, with “number of hours slept” and “blood oxygen levels” emerging as top predictors of stress.
📁 Dataset: Sourced from Kaggle
📚 Tools Used: Python, Scikit-learn, XGBoost
👨🔬 Research by: Prashant Basavaraj Police Patil
📧 Contact: [email protected]
🔔 Like, share, and subscribe for more machine learning research videos!
#MachineLearning #FeatureSelection #SleepQuality #Regression #XGBoost #RandomForest #DataScience #StressPrediction #Kaggle #ScikitLearn
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке:
