| Abstrakt: |
In this study, we present an electronic component classification system with a classification accuracy exceeding 98%, achieved by utilizing state-of-the-art deep learning architectures. We employed EfficientNetV2B3, EfficientNetV2S, EfficientNetB0, InceptionV3, MobileNet, and Vision Transformer (ViT) models for the classification task. Our dataset comprises various electronic components, and it has been meticulously organized and labeled to provide high-quality training data. We conducted extensive experiments, utilizing data augmentation techniques and transfer learning, to fine-tune and optimize the models for the given task. The high classification accuracy achieved by our system indicates its readiness for real-world applications. It can be applied to advance automation and efficiency in the electronics industry. [ABSTRACT FROM AUTHOR] |
