Dempster Shafer-Empowered Machine Learning-Based Scheme for Reducing Fire Risks in IoT-Enabled Industrial Environments

Abstract

In high-risk IoT-enabled Industrial Environments such as oil and gas industries, early and accurate fire detection is crucial to prevent catastrophic damage. Traditional fire detection systems that rely on single IoT sensors, like heat or smoke detectors, are prone to inaccuracies and delayed responses, particularly in noisy or complex industrial environments. This research proposes an advanced fire prediction approach aiming to enhance decision-making accuracy with uncertain or incomplete fire sensor data in an edge computing IoT complex industrial environment that integrates multiple supervised machine learning algorithms for each sensor types and Dempster-Shafer theory (DST) with multi-sensor fusion. By combining data from multiple different types of sensors (RGB, thermal, gas, smoke, and flame), the proposed architecture enhances the reliability of fire prediction and detection as each sensor detects different parameters of a fire and this ensures every parameter is considered for fire detection ensuring early detection and it reduces false positives. By preprocessing sensor data and by combining machine learning algorithms (MobileNet, EfficientNet, Random Forest, SVM, and Decision Trees) where each ML processes different sensor data types, this supports providing more accurate data to DST. The D-S theory helps in handling uncertainty by fusing conflicting multi-sensor data to generate a more reliable decision. The results demonstrate that this multi-integrated methodology proposed significantly outperforms traditional methods in predicting and detecting fires early and accurately, even under challenging and complex environmental conditions of Oil and Gas Industries. The goal of this research contribute to the development of advanced fire prediction protocols offering a robust solution for managing and mitigating fire risks in dynamic, data-rich IoT environments. Predicting fire and reducing Fire in a critical oil and gas IoT industrial environment remains a critical challenge. The proposed method aims to enhance fire prediction and detection accuracy through algorithms developed using sensor preprocessing, machine learning, and Dempster Shafer fusion handling uncertain and varying multi-sensor data and demonstrates real-time, data-driven decision-making in critical industrial environments. The results show an accuracy of 98.2%, a precision of 98.5%, and a recall of 98.3% significantly confirming the prediction over other models.