Smart Home Automation with IoT-driven IR Blasters: Enhancing Control of Legacy Appliances with Predictive Usage Pattern using Machine Learning

This research study demonstrates an advanced smart home automation system with IoT based IR blasters to control conventional appliances to improve their usage models. Data were collected from an IoT driven Blaster and supplemented with synthetic dataset. By performing predictive analytics with RandomForestClassifier, the system has managed to realize a high accuracy rate of predicting appliance use pattern. The correlation analysis reveals significant relationships among usage features, highlighting patterns such as the positive correlation between frequency of use and total usage time. Time series analysis revealed stabilized trends on the utilization of products for the recent years whereas distribution analysis showed a prevalent behavior regarding usage. In predicting the lifespan of appliances, XGBoost model was utilized demonstrating minimal variation and high confidence in predictions, ensuring reliable appliance management.