Transfer learning-based method for automated ewaste recycling in smart cities
2026-06-22 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionMachine Learning
AI summaryⓘ
The authors explore how artificial intelligence (AI) can help sort electronic waste (ewaste) faster and more accurately, focusing on smartphones as an example. They use a method called transfer learning by adapting a pre-trained AI model (AlexNet) to recognize different smartphone brands from a small dataset. By adjusting model settings like learning rate and optimizer, they achieved about 98% accuracy in classification. Their work shows that AI can improve ewaste recycling by making sorting more reliable and efficient.
Artificial IntelligenceCircular EconomyEwaste RecyclingTransfer LearningAlexNetSmartphone ClassificationStochastic Gradient DescentLearning RateData AugmentationModel Optimization
Authors
Nermeen Abou Baker, Paul Szabo-Müller, Uwe Handmann
Abstract
Sorting a huge stream of waste accurately within a short period can be done with the support of digitalization, particularly Artificial Intelligence, instead of traditional methods. The overlap of Artificial Intelligence and Circular Economy can flourish many services in the environmental technology domain, in particular smart ewaste recycling, resulting in enabling circular smart cities. We analyse the growing need for automated ewaste recycling as an essential requirement to cope with the fast growing ewaste stream and we shed the light on the impact of Artificial Intelligence in supporting the recycling process through smart classification of devices, where the smartphone is our case study. Our study applies transfer learning as a special technique of Artificial Intelligence by finetuning the output layers of AlexNet as a pretrained model and perform the implementation on a small size dataset that contains 12 classes from 6 smartphone brands. We evaluate the performance of our model by tuning the learning rate, choosing the best optimizer, and augmenting the original dataset to avoid overfitting. We found that the optimizer of Stochastic Gradient Descent with Momentum and 3e-4 as a learning rate brings almost 98% model accuracy with generalization. Our study supports automated ewaste recycling in decreasing the error rate of ewaste sorting and investigates the advantages of applying transfer learning as the best scenario to overcome the rising challenges.