Smart Structures and Systems

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Investigation of characteristic values in TDR waveform using SHapley Additive exPlanations (SHAP) for dielectric constant estimation during curing time

  • Won-Taek Hong (Department of Civil & Environmental Engineering, Gachon University) ;
  • WooJin Han (School of Civil, Environmental and Architectural Engineering, Korea University) ;
  • Yong-Hoon Byun (Department of Agricultural Civil Engineering, Kyungpook National University) ;
  • Hyung-Koo Yoon (Department of Construction and Disaster Prevention Engineering, Daejeon University)
  • Received : 2024.05.07
  • Accepted : 2024.08.20
  • Published : 2024.07.25
⟨ Previous Next ⟩

Abstract

As materials cure, the internal electrical flow changes, leading to variations in the dielectric constant over time. This study aims to assess the impact of voltage values extracted from time domain reflectometry (TDR) waveforms, measured during the curing of materials, on predicting the dielectric constant. The experiments are conducted over a curing period ranging from 60 to 8640 minutes, with 30 TDR trials. From the measured waveforms, values of V0, V1, V2, Vf, and Δt are deduced. Additionally, curing time is included as an input variable. Groups A and B are distinguished based on the presence or absence of Δt, indicating a physical relationship between Δt and the dielectric constant. The dielectric constant is set as the output variable. The SHapley Additive exPlanations (SHAP) algorithm is applied to the compiled data. The results indicate that Δt and V1 are the most influential input variables in both Group-A and Group-B. The study also presents the distribution of SHAP values and interacts SHAP values to infer the interrelationships among the input variables. To validate the reliability of these findings, the partial dependence (PD) algorithm is applied to estimate the marginal effects of each input variable, with outcomes closely aligning with those of the SHAP algorithm. This research suggests that understanding the contributions and proportional relationships of each input variable can aid in interpreting the relationships among various material properties.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (NRF-2020R1A2C2012113), (2022R1A4A3029737).

References

  1. Alabi, R.O., Elmusrati, M., Leivo, I., Almangush, A. and Makitie, A.A. (2023), "Machine learning explainability in nasopharyngeal cancer survival using LIME and SHAP", Scientif. Reports, 13(1), 8984. https://doi.org/10.1038/s41598-023-35795-0
  2. Al-Swaidani, A.M., Meziab, A., Khwies, W. T., Al-Bali, M. and Lala, T. (2024), "Building MLR, ANN and FL models to predict the strength of problematic clayey soil stabilized with a combination of nano lime and nano pozzolan of natural sources for pavement construction", Int. J. Geo-Eng., 15(1), 2. https://doi.org/10.1186/s40703-023-00201-1
  3. Bang, H., Yu, B. and Jeon, H. (2023), "Assembly performance evaluation method for prefabricated steel structures using deep learning and k-nearest neighbors", Smart Struct. Syst., Int. J., 32(2), 111-121. https://doi.org/10.12989/sss.2023.32.2.111
  4. Byun, N., Lee, J., Lee, K. and Kang, Y.J. (2023), "Extended artificial neural network for estimating the global response of a cable-stayed bridge based on limited multi-response data", Smart Struct. Syst., Int. J., 32(4), 235-251. https://doi.org/10.12989/sss.2023.32.4.235
  5. Cakiroglu, C., Demir, S., Ozdemir, M.H., Aylak, B.L., Sariisik, G. and Abualigah, L. (2024), "Data-driven interpretable ensemble learning methods for the prediction of wind turbine power incorporating SHAP analysis", Expert Syst. Applicat., 237, 121464. https://doi.org/10.1016/j.eswa.2023.121464
  6. Doan, N.S. (2023), "Reliability analysis and uncertainty quantification of clay and sand slopes stability evaluated by Fellenius and Bishop's simplified methods", Int. J. Geo-Eng., 14(1), 22. https://doi.org/10.1186/s40703-023-00200-2
  7. Hong, W.T., Jung, Y.S., Kang, S. and Lee, J.S. (2016), "Estimation of soil-water characteristic curves in multiple-cycles using membrane and TDR system", Materials, 9(12), 1019. https://doi.org/10.3390/ma9121019
  8. Hong, W.T., Lee, J.S., Lee, D. and Yoon, H.K. (2022), "Estimation of bulk electrical conductivity in saline medium with contaminated lead solution through TDR coupled with machine learning", Process Safe. Environ. Protect., 161, 58-66. https://doi.org/10.1016/j.psep.2022.03.018
  9. Jabeur, S.B., Mefteh-Wali, S. and Viviani, J.L. (2024), "Forecasting gold price with the XGBoost algorithm and SHAP interaction values", Annals Operat. Res., 334(1), 679-699. https://doi.org/10.1007/s10479-021-04187-w
  10. Kim, S. and Yoon, H.K. (2023), "Application of classification coupled with PCA and SMOTE, for obtaining safety factor of landslide based on HRA", Bull. Eng. Geol. Environ., 82(10), 381. https://doi.org/10.1007/s10064-023-03403-0
  11. Lee, J.S., Hong, W.T., Park, K., Hong, S.S., Lee, S.H. and Byun, Y.H. (2018), "Evaluation of water content in an active layer using penetration-type time domain reflectometry", Appl. Sci., 8(6), 935. https://doi.org/10.3390/app8060935
  12. Lim, Y.Y., Smith, S.T., Padilla, R.V. and Soh, C.K. (2021), "Monitoring of concrete curing using the electromechanical impedance technique: Review and path forward", Struct. Health Monitor., 20(2), 604-636. https://doi.org/10.1177/1475921719893069
  13. Lin, G., Zhang, Y., Cai, E., Zhao, T. and Li, Z. (2023), "An ensemble learning based Bayesian model updating approach for structural damage identification", Smart Struct. Syst., Int. J., 32(1), 61-81. https://doi.org/10.12989/sss.2023.32.1.061
  14. Min, D.H. and Yoon, H.K. (2021), "Suggestion for a new deterministic model coupled with machine learning techniques for landslide susceptibility mapping", Scientif. Reports, 11(1), 1-24. https://doi.org/10.1038/s41598-021-86137-x
  15. Min, D.H., Kim, Y., Kim, S. and Yoon, H.K. (2023), "Strategy of oversampling geotechnical parameters through geostatistical, SMOTE, and CTGAN methods for assessing susceptibility of landslide", Landslides, 1-17. https://doi.org/10.1007/s10346-023-02166-9
  16. Molnar, C., Konig, G., Bischl, B. and Casalicchio, G. (2023), "Model-agnostic feature importance and effects with dependent features: a conditional subgroup approach", Data Min. Knowled. Discov., 1-39. https://doi.org/10.1007/s10618-022-00901-9
  17. Mondal, T.G., Chou, J.Y., Fu, Y. and Mao, J. (2023), "A hybrid deep neural network compression approach enabling edge intelligence for data anomaly detection in smart structural health monitoring systems", Smart Struct. Syst., Int. J., 32(3), 179-193. https://doi.org/10.12989/sss.2023.32.3.179
  18. Noborio, K., McInnes, K.J. and Heilman, J.L. (1996), "Measurements of soil water content, heat capacity, and thermal conductivity with a single TDR probe1", Soil Sci., 161(1), 22-28. https://doi.org/10.1097/00010694-199601000-00004
  19. Panda, C., Mishra, A.K., Dash, A.K. and Nawab, H. (2023), "Predicting and explaining severity of road accident using artificial intelligence techniques, SHAP and feature analysis", Int. J. Crashworth., 28(2), 186-201. https://doi.org/10.1080/13588265.2022.2074643
  20. Park, J., Lee, J.S. and Yoon, H.K. (2023), "Geoacoustic and geophysical data-driven seafloor sediment classification through machine learning algorithms with property-centered oversampling techniques", Comput.-Aided Civil Infrastr. Eng., 39(14), 2105-2121. https://doi.org/10.1111/mice.13126
  21. Pei, J., Cai, J., Zou, D., Zhang, J., Li, R., Chen, X. and Jin, L. (2016), "Design and performance validation of high-performance cement paste as a grouting material for semiflexible pavement", Constr. Build. Mater., 126, 206-217. https://doi.org/10.1016/j.conbuildmat.2016.09.036
  22. Piladaeng, N., Angkawisittpan, N. and Homwuttiwong, S. (2016), "Determination of relationship between dielectric properties, compressive strength, and age of concrete with rice husk ash using planar coaxial probe", Measur. Sci. Rev., 16(1), 14. https://doi.org/10.1515/msr-2016-0003
  23. Raihan, M.J., Khan, M.A.M., Kee, S.H. and Nahid, A.A. (2023), "Detection of the chronic kidney disease using XGBoost classifier and explaining the influence of the attributes on the model using SHAP", Scientif. Reports, 13(1), 6263. https://doi.org/10.1038/s41598-023-33525-0
  24. Samadi, H., Hassanpour, J. and Rostami, J. (2023), "Prediction of earth pressure balance for EPB-TBM using machine learning algorithms", Int. J. Geo-Eng., 14(1), 21. https://doi.org/10.1186/s40703-023-00198-7
  25. Siqueira, R.G., Moquedace, C.M., Fernandes-Filho, E.I., Schaefer, C.E., Francelino, M.R., Sacramento, I.F. and Michel, R.F. (2024), "Modelling and prediction of major soil chemical properties with Random Forest: Machine learning as tool to understand soil-environment relationships in Antarctica", Catena, 235, 107677. https://doi.org/10.1016/j.catena.2023.107677
  26. Topp, G.C., Davis, J.L. and Annan, A.P. (1980), "Electromagnetic determination of soil water content: Measurements in coaxial transmission lines", Water Resour. Res., 16(3), 574-582. https://doi.org/10.1029/WR016i003p00574
  27. Vimbi, V., Shaffi, N. and Mahmud, M. (2024), "Interpreting artificial intelligence models: a systematic review on the application of LIME and SHAP in Alzheimer's disease detection", Brain Inform., 11(1), 10. https://doi.org/10.1186/s40708-024-00222-1
  28. Wang, G., Wang, K.C., Zhang, A.A. and Yang, G. (2023), "A deep and multiscale network for pavement crack detection based on function-specific modules", Smart Struct. Syst., Int. J., 32(3), 135-151. https://doi.org/10.12989/sss.2023.32.3.135
  29. Yanuka, M., Topp, G.C., Zegelin, S. and Zebchuk, W.D. (1988), "Multiple reflection and attenuation of time domain reflectometry pulses: Theoretical considerations for applications to soil and water", Water Resour. Res., 24(7), 939-944. https://doi.org/10.1029/WR024i007p00939
  30. Zamani, S., Lajevardi, S.H., Yarivand, A. and Zeighami, E. (2023), "Experimental study of the behavior of square footing on reinforced sand with treated geotextile", Int. J. Geo-Eng., 14(1), 19. https://doi.org/10.1186/s40703-023-00195-w
  31. Zegelin, S.J., White, I. and Jenkins, D.R. (1989), "Improved field probes for soil water content and electrical conductivity measurement using time domain reflectometry", Water Resour. Res., 25(11), 2367-2376. https://doi.org/10.1029/WR025i011p02367
  32. Zhang, J., Ma, X., Zhang, J., Sun, D., Zhou, X., Mi, C. and Wen, H. (2023), "Insights into geospatial heterogeneity of landslide susceptibility based on the SHAP-XGBoost model", J. Environ. Manag., 332, 117357. https://doi.org/10.1016/j.jenvman.2023.117357
  33. Zivari, A., Siavoshnia, M. and Rezaei, H. (2023), "Effect of lime-rice husk ash on geotechnical properties of loess soil in Golestan province, Iran", Int. J. Geo-Eng., 14(1), 20. https://doi.org/10.1186/s40703-023-00199-6