Enhancing Trust Computation in Wireless Sensor Networks through DeEGAG-Net: A Hybrid Model Integrating Deep Graph, AlexNet, and GRU

Wireless Sensor Networks (WSNs) play a critical role in a wide range of applications, making it necessary to have strong trust management systems in place to guarantee secure and dependable operations. This study presents DeEGAG-Net, a sophisticated trust model that combines DeepGraph, AlexNet, and GRU components to improve trust calculation in Wireless Sensor Networks (WSNs). The model utilizes DeepGraph to analyze relational data, AlexNet to extract high-level features, and GRU to handle temporal dependencies. DeEGAG-Net utilizes methodologies such as the Dempster-Shafer theory, neural networks, and energy trust evaluation to generate accurate and reliable trust predictions. The model utilizes a hybrid approach with the LEACH protocol to enhance cluster head selection and maintain continuous updates using trust-related features and network topology. The results of our study clearly indicate that the model significantly enhances network performance and reliability.