Multi-Objective Neuroevolution-Based Xception for Fault Detection in Edge System

This research paper introduces a novel approach to fault detection in edge systems using a multi-objective neuroevolution-based Xception model. Edge systems play a crucial role in various applications, including Internet of Things (IoT) and real-time data processing. Ensuring the reliability of these systems is essential for maintaining seamless operation. Traditional fault detection methods often struggle with the dynamic and resource-constrained nature of edge systems. To address this challenge, we propose a multi-objective neuroevolution approach that leverages the Xception architecture. The proposed model aims to simultaneously optimize multiple objectives, including fault detection accuracy and computational efficiency. By utilizing neuroevolution, the model architecture and parameters are automatically adapted to achieve optimal performance for fault detection. Experimental results demonstrate the effectiveness of the proposed approach compared to existing methods, showcasing its ability to enhance fault detection accuracy while efficiently utilizing edge system resources.