다중겹 교차검증 기법을 이용한 증기세관 결함크기 예측을 위한 신경회로망 성능 향상Improvement of Neural Network Performance for Estimating Defect Size of Steam Generator Tube using Multifold Cross-Validation
- Other Titles
- Improvement of Neural Network Performance for Estimating Defect Size of Steam Generator Tube using Multifold Cross-Validation
- Authors
- 김남진; 지수정; 조남훈
- Issue Date
- Sep-2012
- Publisher
- 한국조명.전기설비학회
- Keywords
- Steam Generator Tube; Eddy Current Testing; Neural Network; Multifold Cross-Validation; Steam Generator Tube; Eddy Current Testing; Neural Network; Multifold Cross-Validation
- Citation
- 조명.전기설비학회논문지, v.26, no.9, pp.73 - 79
- Journal Title
- 조명.전기설비학회논문지
- Volume
- 26
- Number
- 9
- Start Page
- 73
- End Page
- 79
- URI
- http://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/12901
- ISSN
- 1229-4691
- Abstract
- In this paper, we study on how to determine the number of hidden layer neurons in neural network for predicting defect size of steam generator tube. It was reported in the literature that the number of hidden layer neurons can be efficiently determined with the help of cross-validation. Although the cross-validation provides decent estimation performance in most cases, the performance depends on the selection of validation set and rather poor performance may be led to in some cases. In order to avoid such a problem, we propose to use multifold cross-validation. Through the simulation study, it is shown that the estimation performance of defect width (defect depth, respectively) attains 94% (99.4%, respectively) of the best performance achievable among the considered neuron numbers.
- Files in This Item
-
Go to Link
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.