Analysis of Accuracy in Predicting Stability of Piers Evaluated by Impact Load Test충격하중실험으로 평가한 교각 기초의 안정성 예측에 대한 정확도 분석
- Other Titles
- 충격하중실험으로 평가한 교각 기초의 안정성 예측에 대한 정확도 분석
- Authors
- 윤동후; 유민택; 박정준; 김기현; 이명재; 이일화
- Issue Date
- Jul-2021
- Publisher
- 한국철도학회
- Keywords
- Machine learning; Pier safety; Permutation importance; Safety prediction; Support vector machine; 머신러닝; 교각안전성; 순열중요도; 안전성 예측; 서포트 벡터 머신
- Citation
- 한국철도학회논문집, v.24, no.7, pp.581 - 589
- Journal Title
- 한국철도학회논문집
- Volume
- 24
- Number
- 7
- Start Page
- 581
- End Page
- 589
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/87604
- DOI
- 10.7782/JKSR.2021.24.7.581
- ISSN
- 1738-6225
- Abstract
- The safety of piers is predicted through machine learning based on a database built from impact load tests on piers. However, since the amount of data is insufficient to learn the algorithm using only field experiment data, the accuracy of the algorithm is analyzed by constructing 1,159 data sets of a model experiment and numerical analysis data. Among machine learning algorithms, the accuracy of safety diagnosis prediction is studied using three algorithms: Support Vector Machine (SVM), Decision Tree (DT), and Logistic Regression. The algorithm is evaluated using an evaluation index according to a confusion matrix and, as a result, the highest accuracy is shown at 95.9% when the support vector machine, a binary classification model that predicts the boundary line between the two classes of safety and poor, is used. © 2021 The Korean Society for Railway. All rights reserved.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 공과대학 > 토목환경공학과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/87604)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.