An Efficient E-Waste Management System through Energy-Aware Routing and Hybrid Optimization Deep Learning Routing on an IoT-Cloud Platform

This research tackles the growing complexity and high resource demand of electronic‑waste (e‑waste) management by proposing an intelligent, IoT‑cloud classification and routing framework. The paper introduces a hybrid optimization method called **Fractional Horse Herd Gas Optimization‑based Shepherd Convolutional Neural Network (FrHHGO‑based ShCNN)**. In this system, IoT nodes capture images of e‑waste and send them to cloud storage using an energy‑aware routing scheme driven by the FrHHGO algorithm, which combines **Fractional Henry Gas Optimization (FHGO)** and the **Horse Herd Optimization Algorithm (HOA)**. For classification, the model extracts key visual features with three techniques: – Gray Level Co‑occurrence Matrix (GLCM) – Local Gabor Binary Pattern (LGBP) – Histogram of Oriented Gradient (HOG)

Data augmentation is also applied to enlarge the feature space. The results show that this hybrid model raises classification accuracy compared with several baselines: – Standard deep learning: **+19.49 %** – TensorFlow‑based deep learning: **+18.05 %** – Cuckoo‑search neural networks: **+12.77 %** – Traditional machine learning models: **+7.89 %** For M.Tech researchers, the framework offers a solid base for testing energy‑efficient routing protocols and for evaluating advanced deep‑learning classifiers in sustainable waste‑management systems.

Message: Hi FE, I need help with “An Efficient E-Waste Management System through Energy-Aware Routing and Hybrid Optimization Deep Learning Routing on an IoT-Cloud Platform” in “Environmental Engineering”