Can I read Sensors 22 09783 on EtoBox?

Sensors 22 09783 by david.kaz22.5.2002 is a document available to read on EtoBox.

What is Sensors 22 09783 about?

This article presents an automated machine learning (AutoML) system for detecting defects on cylindrical metal surfaces using convolutional neural networks (CNNs). The study compares the performance of various CNN architectures, including VGG-16, ResNet-50, and MobileNet v1, and introduces a retraining criterion for improving model accuracy. The AutoKeras model achieved the highest accuracy of 99.83%, while the self-designed AutoML model reached 95.50%, demonstrating effective defect recognition with low tr

Author

david.kaz22.5.2002

Language

EN