Advancing Recycling Efficiency: A Comparative Analysis of Deep Learning Models in Waste Classification
This work addresses waste management challenges by improving recycling efficiency through deep learning, but it is incremental as it builds on existing models.
The research tackled waste classification for recycling by comparing deep learning models, finding that a novel ResNet50+SVM hybrid significantly boosts accuracy in complex categories and transformers achieve the highest average accuracy.
With the ongoing increase in the worldwide population and escalating consumption habits,there's a surge in the amount of waste produced.The situation poses considerable challenges for waste management and the optimization of recycling operations.The research tackles the pressing issue of waste classification for recycling by analyzing various deep learning models,including Convolutional Neural Network(CNN),AlexNet,ResNet,ResNet50 plus Support Vector Machine(SVM),and transformers,across a wide array of waste categories.The research meticulously compares these models on several targets like parameters settings,category accuracy,total accuracy and model parameters to establish a uniform evaluation criterion.This research presents a novel method that incorporates SVM with deep learning frameworks,particularly ResNet50.The results indicate the method significantly boosts accuracy in complex waste categories.Moreover,the transformer model outshines others in average accuracy,showcasing its aptitude for intricate classification tasks.To improve performance in poorly performing categories,the research advocates for enlarging the dataset,employing data augmentation,and leveraging sophisticated models such as transformers,along with refining training methodologies.The research paves the way for future advancements in multi-category waste recycling and underscores the pivotal role of deep learning in promoting environmental sustainability.