Eco-Evolution: Transforming Waste Management Through Convolutional Neural Network Parameter Evolution With Optimizers

Recycling waste materials is critical to reducing the environmental effects of increased waste production. Proper waste separation is critical for speeding recycling procedures. This research uses advanced optimization algorithms to handle the difficulty of classifying waste materials. The complexity of waste material composition and diversity pose a significant challenge for accurate classification, requiring advanced classification algorithms. Convolutional neural networks (CNNs) have developed as effective methods for image classification, such as waste material sorting. However, adjusting CNN parameters to optimize classification accuracy remains a key area of study. This paper suggests using genetic algorithms (GA) and particle swarm optimization (PSO) to improve the performance of CNNs in waste material classification. The goal is to improve classification accuracy while minimizing loss by fine-tuning CNN's dense layer, which includes the number of dense layers, number of neurons, and activation functions. A dataset containing images of 12 waste material types, such as food, plastic, cardboard, glass, metal, paper, and others, is used for experimental assessment. Based on the results of this research finding, it can be concluded that GA and PSO have succeeded in optimizing and increasing the accuracy of the test to 85.32% and 85.42%, respectively, compared to the baseline of 76.78%. PSO also converged more rapidly and completed the optimization process only about 10% faster and with the lower final loss (0.545 against 0.579), whereas in the only final generation, the closer ties of losses were seen by GA. The proposed technique can enhance waste management process through better sorting and recycling of the waste materials. Future studies will be conducted on hybrid metaheuristic strategies and continue optimization to the convolutional layers in classifying waste.