한국지반신소재학회논문집 (Journal of the Korean Geosynthetics Society)

  • 제22권1호
  • /
  • Pages.67-74
  • /
  • 2023
  • /
  • 2508-2876(pISSN)
  • /
  • 2287-9528(eISSN)
한국지반신소재학회 (Korean Geosynthetics Society)
권호 표지
DOI QR코드

DOI QR Code

경사면의 안정성 모니터링 데이터의 품질관리를 위한 2 단계 접근방안

Two-Phase Approach for Data Quality Management for Slope Stability Monitoring

  • Junhyuk Choi (Department of Industrial Management Engineering, Pohang University of Science and Technology) ;
  • Yongjin Kim (Smart Geotech) ;
  • Junhwi Cho (Department of Regional Infrastructure Engineering, Kangwon National University) ;
  • Woocheol Jeong (Department of Regional Infrastructure Engineering, Kangwon National University) ;
  • Songhee Suk (Department of Regional Infrastructure Engineering, Kangwon National University) ;
  • Song Choi (Department of Regional Infrastructure Engineering, Kangwon National University) ;
  • Yongseong Kim (Department of Regional Infrastructure Engineering, Kangwon National University) ;
  • Bongjun Ji (Department of Regional Infrastructure Engineering, Kangwon National University)
  • 투고 : 2023.02.23
  • 심사 : 2023.03.24
  • 발행 : 2023.03.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

경사면의 안정성을 모니터링 하기 위해 데이터 기반으로 사면의 붕괴를 예측, 경보를 하려는 연구가 증가하고 있다. 하지만 대부분의 논문에서는 데이터의 품질에 대해 간과하고 있다. 이는 오경보와 같은 문제를 발생시킬 수 있다. 이에 본 논문에서는 사면에서 수집된 데이터의 품질관리를 위한 규칙과 기계학습 모델로 구성된 2 단계의 접근 방안을 제안하였다. 규칙 기반은 높은 정확도와 직관적인 해석이 가능하다는 장점이 있으며 기계학습 모델은 명시적으로 표현할 수 없는 패턴을 도출할 수 있다는 장점이 있으며 2단계의 접근 방안은 이 두 장점을 모두 취할 수 있었다. 사례연구를 통해 두 방법을 단독으로 사용하였을 경우와 2단계의 접근 방안을 사용하였을 때의 성능을 비교하였고 2단계 접근 방안이 높은 성능을 보이는 것으로 판단되었다. 따라서 데이터의 품질관리를 위해 단독으로 두 방법을 사용하는 것보다 2단계 접근 방안 방법을 사용하는 것이 적절할것으로 판단된다.

In order to monitor the stability of slopes, research on data-based slope failure prediction and early warning is increasing. However, most papers overlook the quality of data. Poor data quality can cause problems such as false alarms. Therefore, this paper proposes a two-step hybrid approach consisting of rules and machine learning models for quality control of data collected from slopes. The rule-based has the advantage of high accuracy and intuitive interpretation, and the machine learning model has the advantage of being able to derive patterns that cannot be explicitly expressed. The hybrid approach was able to take both of these advantages. Through a case study, the performance of using the two methods alone and the case of using the hybrid approach was compared, and the hybrid method was judged to have high performance. Therefore, it is judged that using a hybrid method is more appropriate than using the two methods alone for data quality control.

키워드

과제정보

This research was supported by "Ministry of the Interior and Safety" R&D program(RS-2022-00155667).

참고문헌

  1. Bosman, H. H., Iacca, G., Tejada, A., Wortche, H. J. and Liotta, A. (2017), "Spatial anomaly detection in sensor networks using neighborhood information", Information Fusion, Vol.33, pp.41-56. https://doi.org/10.1016/j.inffus.2016.04.007
  2. Chen, Z., Yeo, C. K., Lee, B. S. and Lau, C. T. (2018), "Autoencoder-based network anomaly detection", In 2018 Wireless telecommunications symposium (WTS), Arizona, pp.1-5.
  3. Dereszynski, E. W. and Dietterich, T. G. (2011), "Spatiotemporal models for data-anomaly detection in dynamic environmental monitoring campaigns", ACM Transactions on Sensor Networks, Vol.9, No.1, pp.1-36. https://doi.org/10.1145/1993042.1993045
  4. Duffield, N., Haffner, P., Krishnamurthy, B. and Ringberg, H. (2009), "Rule-based anomaly detection on IP flows", In IEEE INFOCOM 2009, Rio de Janeiro, pp.424-432.
  5. Hochreiter, S. and Schmidhuber, J. (1997), "Long short-term memory", Neural computation, Vol.9, No.8, pp.1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  6. Ilgun, K. (1992), A real-time intrusion detection system for unix, Master Thesis, University of California Santa Barbara.
  7. Jesus, G., Casimiro, A. and Oliveira, A. (2017), "A survey on data quality for dependable monitoring in wireless sensor networks", Sensors, Vol.17, No.9, pp.2010.
  8. Lane, T. and Brodley, C. E. (1997), "An application of machine learning to anomaly detection", In Proc. of the 20th national information systems security conference, Baltimore, Vol.377, pp.366-380.
  9. Li, Y. and Parker, L. E. (2014), "Nearest neighbor imputation using spatial-temporal correlations in wireless sensor networks", Information Fusion, Vol.15, pp.64-79. https://doi.org/10.1016/j.inffus.2012.08.007
  10. Liu, H., Shah, S. and Jiang, W. (2004), "On-line outlier detection and data cleaning", Computers & Chemical Engineering, Vol.28, No.9, pp.1635-1647. https://doi.org/10.1016/j.compchemeng.2004.01.009
  11. Liu, P., Sun, X., Han, Y., He, Z., Zhang, W. and Wu, C. (2022), "Arrhythmia classification of LSTM autoencoder based on time series anomaly detection", Biomedical Signal Processing and Control, Vol.71, Part B, 103228.
  12. Mahalanobis, P. C. (1936), "On the generalised distance in statistics", In Proc. of the National Institute of Science of India, Kolkata, Vol.12, pp.49-55.
  13. Mori, A., Subramanian, S. S., Ishikawa, T. and Komatsu, M. (2017), "A case study of a cut slope failure influenced by snowmelt and rainfall", Procedia engineering, Vol.189, pp.533-538. https://doi.org/10.1016/j.proeng.2017.05.085
  14. Nassif, A. B., Talib, M. A., Nasir, Q. and Dakalbab, F. M. (2021), "Machine learning for anomaly detection: A systematic review", Ieee Access, Vol.9, pp.78658-78700. https://doi.org/10.1109/ACCESS.2021.3083060
  15. Omar, S., Ngadi, A. and Jebur, H. H. (2013), "Machine learning techniques for anomaly detection: an overview", International Journal of Computer Applications, Vol.79, No.2.
  16. Rabatel, J., Bringay, S. and Poncelet, P. (2011), "Anomaly detection in monitoring sensor data for preventive maintenance", Expert Systems with Applications, Vol.38, No.6, pp.7003-7015. https://doi.org/10.1016/j.eswa.2010.12.014
  17. Rassam, M. A., Maarof, M. A. and Zainal, A. (2014), "Adaptive and online data anomaly detection for wireless sensor systems", Knowledge-Based Systems, Vol.60, pp.44-57. https://doi.org/10.1016/j.knosys.2014.01.003
  18. Rumelhart, D. E., Hinton, G. E. and Williams, R. J. (1986), "Learning representations by back-propagating errors", Nature, Vol.323, No.6088, pp.533-536. https://doi.org/10.1038/323533a0
  19. Teh, H. Y., Kempa-Liehr, A. W. and Wang, K. I. K. (2020), "Sensor data quality: A systematic review", Journal of Big Data, Vol.7, No.1, pp.1-49.
  20. Zhang, H., Liu, J. and Pang, A. C. (2018), "A Bayesian network model for data losses and faults in medical body sensor networks", Computer Networks, Vol.143, pp.166-175. https://doi.org/10.1016/j.comnet.2018.07.009
  21. Zhang, L. L., Zhang, J., Zhang, L. M. and Tang, W. H. (2011), "Stability analysis of rainfall-induced slope failure: a review", Proc. of the Institution of Civil Engineers-Geotechnical Engineering, Vol.164, No.5, pp.299-316. https://doi.org/10.1680/geng.2011.164.5.299
  22. Zhang, Y., Meratnia, N. and Havinga, P. J. (2010), "Ensuring high sensor data quality through use of online outlier detection techniques", International Journal of Sensor Networks, Vol.7, No.3, pp.141-151. https://doi.org/10.1504/IJSNET.2010.033116