Identification analysis of defect topologies by self-attention based machine learning (Effect of the number of training data on identification accuracy)-Reference-Cited by-同舟云学术

Identification analysis of defect topologies by self-attention based machine learning (Effect of the number of training data on identification accuracy)

Published:2024 Issue:0 Volume:16 Page:17-20
ISSN:1883-0609
Container-title:JSIAM Letters
language:en
Short-container-title:JSIAM Letters

Author:

Yamamoto Kazuki¹,Kurahashi Takahiko²,Murakami Yuki³,Ikeda Fujio⁴,Ihara Ikuo²

Affiliation:

1. Department of Mechanical Engineering, Graduate School of Nagaoka University of Technology

2. Department of Mechanical Engineering, Institute of GIGAKU, Nagaoka University of Technology

3. Department of Civil Engineering, National Institute of Technology, Nagaoka College

4. Department of Mechanical Engineering, National Institute of Technology, Nagaoka College

Publisher

The Japan Society for Industrial and Applied Mathematics

Link

https://www.jstage.jst.go.jp/article/jsiaml/16/0/16_17/_pdf

Reference5 articles.

1. [1] National Institute of Advanced Industrial Science and Technology, Development of a system that prevents inspection leakage by using artificial intelligence, https://www.aist.go.jp/aist_j/press_release/pr2017/pr20170601/pr20170601.html (accessed 25 Oct. 2023).

2. [2] A. Nouchi, Y. Murakami, T. Iyama and F. Ikeda, Evaluation of defect area inside concrete structures by self-organizing map in hammering test with a fixed acquiring response signal position (in Japanese), in: Proc. of JCI 2018, pp. 1755–1760, Japan Concrete Institute, 2018.

3. [3] H. Zhao, J. Jia and V. Koltun, Exploring self-attention for image recognition, arXiv:2004.13621 [cs.CV].

4. [4] M. Shimada, K. Yamamoto, T. Kurahashi, Y. Murakami, F. Ikeda and I. Ihara, Identification of nondimensional density distribution of concrete structures based on self-attention using hammering response data, Eng. Optim., 55 (2023), 1–17.

5. [5] D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, arXiv:1412.6980 [cs.LG].