@article{ref1,
title="Study of the number of types on the identification method of bridge damage using CNN",
journal="Structural safety and reliability",
year="2023",
author="Yamada, Ryota and Iwasaki, Atsushi and Endo, Yoshihide and Nakano, Kazuhisa and Tsujimoto, Keisuke and Yamagishi, Takatoshi",
volume="10",
number="",
pages="328-329",
abstract="This study concerns a method for diagnosing bridge anomalies using machine learning. In this study, bridge abnormality diagnosis method using convolutional neural network (CNN) from acceleration responses is proposed. Spectrogram images of acceleration responses are applied to image classification by CNN. By classifying spectrograms for each bridge condition, bridge anomalies are detected and the condition is identified. In order to improve the accuracy of damage classification, a two-step classification method is used: first, a classification is performed in the major damage category, and then the sub-categories are identified within the major category. The two-step classification improved the accuracy of damage identification in the sub-category of girder damage, indicating that the two-step classification is effective in improving the identification accuracy of this method.   Proceedings of the Japan Conference on Structural Safety and Reliability (JCOSSAR)<p /> <p>Language: en</p>",
language="en",
issn="2759-0909",
doi="10.60316/jcossar.10.0_328",
url="http://dx.doi.org/10.60316/jcossar.10.0_328"
}