Optimization of IoT-Enabled Physical Location Monitoring Using DT and VAR

This study shows an enhancement of IoT which gets sensor data and performs real-time face recognition to screen physical areas find strange situations send alarm mail the client make remedial moves avoid any potential misfortune in environment. Sensor is pushed onto local system GoDaddy Cloud, whenever camera detects a person optimize Physical Location Monitoring System by reducing bandwidth requirement storage cost Cloud using edge computation. The reveals that Decision Tree (DT) Random Forest give reasonably similar macro average f1-score predict data. Experimental results show DT most reliable predictive model for datasets three different locations timestamp with accuracy 83.99%, 88.92%, 80.97%. also explains multivariate time series prediction Vector Auto Regression gives good Root Mean Squared Error Temperature, Humidity, Light Dependent Resistor, Gas series.