All Issue

2021 Vol.31, Issue 1 Preview Page

Research Article

The Study for Improvement of Data-Quality of Cut-Slope Management System Using Machine Learning

기계학습을 활용한 도로비탈면관리시스템 데이터 품질강화에 관한 연구

Se-Hyeok Lee1
,
Seung-Hyun Kim3
,
Yonghoon Woo1
,
Jae-Pil Moon2
,
Inchul Yang3*
이 세혁1
,
김 승현3
,
우 용훈1
,
문 재필2
,
양 인철3*
1Research Specialist, Korea Institute of Civil Engineering and Building Technology
2Senior Researcher, Korea Institute of Civil Engineering and Building Technology
3Research Fellow, Korea Institute of Civil Engineering and Building Technology
1한국건설기술연구원 전임연구원
2한국건설기술연구원 수석연구원
3한국건설기술연구원 연구위원
*Corresponding Author
31 March 2021. pp. 31-42
PDF XML Citation
Abstract

Database of Cut-slope management system (CSMS) has been constructed based on investigations of all slopes on the roads of the whole country. The investigation data is documented by human, so it is inevitable to avoid human-error such as missing-data and incorrect entering data into computer. The goal of this paper is constructing a prediction model based on several machine-learning algorithms to solve those imperfection problems of the CSMS data. First of all, the character-type data in CSMS data must be transformed to numeric data. After then, two algorithms, i.g., multinomial logistic regression and deep-neural-network (DNN), are performed, and those prediction models from two algorithms are compared. Finally, it is identified that the accuracy of DNN-model is better than logistic model, and the DNN-model will be utilized to improve data-quality.

Keywords
cut-slope management system (CSMS)
missing-data
incorrect input
machine-learning
multinomial logistic regression
deep-neural-network

도로비탈면관리시스템(Cut-Slope Management System, CSMS)은 전국 일반국도 비탈면에 대해 기초 ‧ 정밀 조사를 바탕으로 데이터베이스를 구축해왔다. 그런데 이러한 데이터는 사람에 의해 기록되기 때문에 데이터 누락 및 오기입 문제가 발생할 수밖에 없다. 본 연구에서는 데이터의 불완전성 문제를 극복하기 위해 여러 머신러닝 기반의 예측모델들을 개발하고 이를 이용한 데이터 품질 강화 가능성을 검토하고자 하였다. 우선 다 범주 문자형 데이터를 수치화하는 과정을 수행하였고, 선정된 데이터 항목들에 대해 다항 로지스틱 회귀분석(Multinomial Logistic Regression)과 심층신경망(Deep-Neural-Network) 기반의 예측모델들을 개발하였다. 그 결과, 심층신경망 모델들의 정확도가 월등히 높은 것으로 나타났다. 향후 개발된 모델들을 활용하여 누락 및 오기입 데이터의 보완이 가능할 것으로 기대된다.

키워드
도로비탈면관리시스템
데이터 누락
데이터 오기입
머신러닝
다항 로지스틱 회귀분석
심층신경망
References
1
Baek, S.A., Cho, K.H., Hwang, J.S., Jung, D.H., Park, J.W., Choi, B., Cha, D.S., 2016, Assessment of slope failures potential in forest roads using a logistic regression model, Journal of Korean Society of Forest Science, 105(4), 429-434 (in Korean with English abstract). 10.14578/jkfs.2016.105.4.429
2
Cho, K., Lee, B.Y., Kwon, M., Kim, S., 2019, Air quality prediction using a deep neural network model, Journal of Korean Society for Atmospheric Environment, 35(2), 214-225 (in Korean with English abstract). 10.5572/KOSAE.2019.35.2.214
3
Jung, M., Kim, J.G., Uranchimeg, Sumiya., Kwon, H.H., 2020, The probabilistic estimation of inundation region using a multiple logistic regression analysis, Journal of Korea Water Resources Association, 53(2), 121-129 (in Korean with English abstract).
4
Kim, J.H., Shin, J.M., Park, J.J., Ha, T.J., 2010, Development of hazard-level forecasting model using combined method of genetic algorithm and artificial neural network at signalized intersections, Journal of The Korean Society of Civil Engineers, 30(4D), 351-360 (in Korean with English abstract).
5
Kim, M.J., 2012, Performance comparison of internal accounting control assessment models applying logistic regression and neural networks, Korea International Accounting Review, 46, 1-30 (in Korean with English abstract). 10.21073/kiar.2012..46.001
6
Kim, T., Song, J., Kwon, O.S., 2020a, Pre- and post-earthquake regional loss assessment using deep learning, Earthquake Engineering and Structural Dynamics, 49(7), 657-678. 10.1002/eqe.3258
7
Kim, T., Song, J., Kwon, O.S., 2020b, Probabilistic evaluation of seismic responses using deep learning method, Structural Safety, 84, 101913. 10.1016/j.strusafe.2019.101913
8
Kim, T.H., Shin, Y.S., Lee, U.K., Kang, K.I., 2007, Decision support model using a decision tree for formwork selection in tall building construction, Journal of the Architectural Institute of Korea Structure & Construction, 23(11), 177-184 (in Korean with English abstract).
9
KICT (Korea Institute of Civil Engineering and Building Technology), 2019, Operation of road cut slope management system in 2018, Republic of Korea Ministry of Land, Infrastructure and Transport, 355p.
10
Sim, S., Kang, H., 2014, A polychotomous regression model with tensor product splines and direct sums, Journal of the Korean Data & Information Science Society, 25(1), 19-26 (in Korean with English abstract). 10.7465/jkdi.2014.25.1.19
11
Woo, Y., Kim, S.H., Yang, I., Lee, S.H., 2020, The Study for Utilizing Data of Cut-Slope Management system by Using Logistic Regression, The Journal of Engineering Geology, 30(4), 649-661 (in Korean with English abstract).
Information
  • Publisher :Korean Society of Engineering Geology
  • Publisher(Ko) :대한지질공학회
  • Journal Title :The Journal of Engineering Geology
  • Journal Title(Ko) :지질공학
  • Volume : 31
  • No :1
  • Pages :31-42
  • Received Date : 2021-01-05
  • Revised Date : 2021-01-22
  • Accepted Date : 2021-01-25
  • DOI :https://doi.org/10.9720/kseg.2021.1.031
Journal Informaiton The Journal of Engineering Geology The Journal of Engineering Geology
Online Submission
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close