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

TL;DR

This paper enhances IoT-based physical location monitoring by integrating real-time face recognition, edge computation, and predictive modeling with decision trees and vector auto regression, improving accuracy and reducing cloud costs.

Contribution

It introduces a hybrid system combining face recognition, edge computing, and predictive models for efficient IoT-based environment monitoring.

Findings

Decision tree achieves up to 88.92% accuracy in person prediction.

Edge computation reduces bandwidth and storage costs.

Vector auto regression effectively predicts environmental sensor data.

Abstract

This study shows an enhancement of IoT that gets sensor data and performs real-time face recognition to screen physical areas to find strange situations and send an alarm mail to the client to make remedial moves to avoid any potential misfortune in the environment. Sensor data is pushed onto the local system and GoDaddy Cloud whenever the camera detects a person to optimize the physical location monitoring system by reducing the bandwidth requirement and storage cost onto the cloud using edge computation. The study reveals that decision tree (DT) and random forest give reasonably similar macro average f1-scores to predict a person using sensor data. Experimental results show that DT is the most reliable predictive model for the cloud datasets of three different physical locations to predict a person using timestamp with an accuracy of 83.99%, 88.92%, and 80.97%. This study also explains multivariate time series prediction using vector auto regression that gives reasonably good root mean squared error to predict temperature, humidity, light-dependent resistor, and gas time series.