Geomechanics and Engineering

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Machine learning application to seismic site classification prediction model using Horizontal-to-Vertical Spectral Ratio (HVSR) of strong-ground motions

  • Francis G. Phi (Department of Civil and Environmental Engineering, Kongju National University) ;
  • Bumsu Cho (Department of Computer Science and Engineering, Kongju National University) ;
  • Jungeun Kim (Department of Computer Science and Engineering, Kongju National University) ;
  • Hyungik Cho (Department of Civil Systems Engineering, Andong National University) ;
  • Yun Wook Choo (Department of Civil and Environmental Engineering, Kongju National University) ;
  • Dookie Kim (Department of Civil and Environmental Engineering, Kongju National University) ;
  • Inhi Kim (Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology)
  • Received : 2024.01.24
  • Accepted : 2024.05.02
  • Published : 2024.06.25
⟨ Previous Next ⟩

Abstract

This study explores development of prediction model for seismic site classification through the integration of machine learning techniques with horizontal-to-vertical spectral ratio (HVSR) methodologies. To improve model accuracy, the research employs outlier detection methods and, synthetic minority over-sampling technique (SMOTE) for data balance, and evaluates using seven machine learning models using seismic data from KiK-net. Notably, light gradient boosting method (LGBM), gradient boosting, and decision tree models exhibit improved performance when coupled with SMOTE, while Multiple linear regression (MLR) and Support vector machine (SVM) models show reduced efficacy. Outlier detection techniques significantly enhance accuracy, particularly for LGBM, gradient boosting, and voting boosting. The ensemble of LGBM with the isolation forest and SMOTE achieves the highest accuracy of 0.91, with LGBM and local outlier factor yielding the highest F1-score of 0.79. Consistently outperforming other models, LGBM proves most efficient for seismic site classification when supported by appropriate preprocessing procedures. These findings show the significance of outlier detection and data balancing for precise seismic soil classification prediction, offering insights and highlighting the potential of machine learning in optimizing site classification accuracy.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government and Ministry of Science and ICT (MSIT) (No.2021R1A4A1031509 and No.2021R1A2C2009985).

References

  1. A Design Spectrum Model Featuring Resonant-Like Soil-Amplification (2013).
  2. Abbas, M., Elbaz, K., Shen, S.L. and Chen, J. (2021), "Earthquake effects on civil engineering structures and perspective mitigation solution a review", Arabian J. Geosci., 14(14), 1350. https://doi.org/10.1007/s12517-021-07664-5.
  3. Adams, R.D. (1990), "Earthquake occurrence and effects: Injury", 21(1), 17-20. https://doi.org/10.1016/0020-1383(90)90146-L.
  4. Ahn, J.K., Kwak, D.Y. and Kim, H.S. (2021), "Estimating VS30 at Korean Peninsular seismic observatory stations using HVSR of event records", Soil Dyn. Earthq. Eng., 146(106650). https://doi.org/10.1016/j.soildyn.2021.106650.
  5. Aljanabi, K.R. and AL-Azzawi, O.M. (2021), "Neural network application in forecasting maximum wall deflection in homogenous clay", Int. J. Geo-Eng., 12(1), 29. https://doi.org/10.1186/s40703-021-00158-z.
  6. Aoi, S., Asano, Y., Kunugi, T., Kimura, T., Uehira, K., Takahashi, N., Ueda, H., Shiomi, K., Matsumoto, T. and Fujiwara, H. (2020), "MOWLAS: NIED observation network for earthquake, tsunami and volcano", Earth. Planet. Sp., 72(1), 126. https://doi.org/10.1186/s40623-020-01250-x.
  7. Aoi, S., Kunugi, T. and Fujiwara, H. (2004), "Strong-motion seismograph network operated by NIED: K-NET and KiK-net", J. JAEE, 4(3), 65-74. https://doi.org/10.5610/jaee.4.3_65.
  8. 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.
  9. Archer, K.J. and Kimes, R.V. (2008), "Empirical characterization of random forest variable importance measures", Comput. Stat. Data Anal., 52(4), 2249-2260. https://doi.org/10.1016/j.csda.2007.08.015.
  10. Aydin, Y., Isikdag, u., Bekdas, G., Nigdeli, S.M. and Geem, Z.W. (2023), "Use of machine learning techniques in soil classification", Sustainability, 15(3), 2374. https://doi.org/10.3390/su15032374.
  11. Baise, L.G., Kaklamanos, J., Berry, B.M. and Thompson, E.M. (2016), "Soil amplification with a strong impedance contrast", Boston, Massachusetts Engineering Geology, 202, 1-13, https://doi.org/10.1016/j.enggeo.2015.12.016.
  12. Bangdiwala, S.I. (2018), "Regression: simple linear", Int. J. Injury Control Saf. Promotion, 25(1), 113-115. https://doi.org/10.1080/17457300.2018.1426702.
  13. Bard, P.Y., Cadet, H., Endrun, B., Hobiger, M., Renalier, F., Theodulidis, N., Ohrnberger, M., Fah, D., Sabetta, F., Teves-Costa, P., Duval, A.M., Cornou, C., Guillier, B., Wathelet, M., Savvaidis, A., Kohler, A., Burjanek, J., Poggi, V., Gassner-Stamm, G., Havenith, H.B., Hailemikael, S., Almeida, J., Rodrigues, I. Veludo, I. and Kristekova, M. (2010), "From noninvasive site characterization to site amplification: Recent advances in the use of ambient vibration measurements", Earthquake Engineering in Europe, (Eds., Garevski, M. and Ansal, A.), Geotechnical, Geological, and Earthquake Engineering, Springer Netherlands, Dordrecht, 105-123.
  14. Benemaran, R.S. and Esmaeili-Falak, M. (2023), "Predicting the Young's modulus of frozen sand using machine learning approaches: State-of-the-art review", Geomech. Eng., 34(5), 507-527. https://doi.org/10.12989/gae.2023.34.5.507.
  15. Biau, G. and Scornet, E. (2016). "A random forest guided tour: TEST, 25(2), 197-227. https://doi.org/10.1007/s11749-016-0481-7.
  16. Bisong, E. (2019a), "Matplotlib and Seaborn", Building Machine Learning and Deep Learning Models on Google Cloud Platform: A Comprehensive Guide for Beginners, (Ed., Bisong, E.), Apress, Berkeley, CA.
  17. Bisong, E. (2019b), "NumPy." Building machine learning and deep learning models on Google cloud platform: A comprehensive guide for beginners, (Ed., Bisong, E.), Apress, Berkeley, CA.
  18. Breiman, L. (2001), "Random forests: Machine learning", 45(1), 5-32. https://doi.org/10.1023/A:1010933404324.
  19. Brownlee, J. (2020a), Data preparation for machine learning: data cleaning, feature selection, and data transforms in Python.
  20. Brownlee, J. (2020b), Imbalanced classification with Python: better metrics, balance skewed classes, cost-sensitive learning.
  21. BSSC (2003), Nehrp Recommended Provisions for Seismic Regulations for New Buildings and Other Structures (Fema 450), 2003rd Ed., NEHRP.
  22. Chawla, N.V., Bowyer, K.W., Hall, L.O. and Kegelmeyer, W.P. (2002), "SMOTE: Synthetic minority over-sampling technique", J. Artif. Intel. Res., 16, 321-357. https://doi.org/10.1613/jair.953.
  23. Cheng, Z., Zou, C. and Dong, J. (2019), "Outlier detection using isolation forest and local outlier factor", Proceedings of the conference on research in adaptive and convergent systems, RACS '19, Association for computing machinery, New York, NY, USA.
  24. Dobry, R., Borcherdt, R.D., Crouse, C.B., Idriss, I.M., Joyner, W.B., Martin, G.R., Power, M.S., Rinne, E.E. and Seed, R.B. (2000), "New site coefficients and site classification system used in recent building seismic code provisions", Earthq. Spectra, 16(1), 41-67. https://doi.org/10.1193/1.1586082.
  25. Fatahi, B., Tabatabaiefar, S.H.R. and Samali, B. (2014), "Soil-structure interaction vs Site effect for seismic design of tall buildings on soft soil", Geomech. Eng., 6(3), 293-320. https://doi.org/10.12989/gae.2014.6.3.293.
  26. Fernandez, A., Garcia, S., Galar, M., Prati, R.C., Krawczyk, B., and Herrera, F. (2018), Leaning from Learning from imbalanced data sets, Springer International Publishing, Cham.
  27. Fukushima, Y., Bonilla, L.F., Scotti, O. and Douglas, J. (2007), "Site classification using horizontal-to-vertical response spectral ratios and its impact when deriving empirical ground-motion prediction equations", J. Earthq. Eng., 11(5), 712-724. https://doi.org/10.1080/13632460701457116.
  28. Gallipoli, M.R. and Mucciarelli, M. (2009), "Comparison of site classification from vs30, vs10, and hvsr in Italy", Bull. Seismol. Soc. Am., 99(1), 340-351. https://doi.org/10.1785/0120080083.
  29. Ghasemi, H., Zare, M., Fukushima, Y. and Sinaeian, F. (2009a), "Applying empirical methods in site classification, using response spectral ratio (H/V): A case study on Iranian strong motion network (ISMN)", Soil Dyn. Earthq. Eng., 29(1), 121-132. https://doi.org/10.1016/j.soildyn.2008.01.007.
  30. Ghasemi, H., Zare, M., Fukushima, Y. and Sinaeian, F. (2009b). "Applying empirical methods in site classification, using response spectral ratio (H/V): A case study on Iranian strong motion network (ISMN)", Soil Dyn.Earthquake Eng., 29(1), 121-132. https://doi.org/10.1016/j.soildyn.2008.01.007.
  31. Grandini, M., Bagli, E. and Visani, G. (2020), "Metrics for multiclass classification: an overview", https://doi.org/10.48550/arXiv.2008.05756.
  32. Ghofrani, H. and Atkinson, G.M. (2014), "Site condition evaluation using horizontal-to-vertical response spectral ratios of earthquakes in the NGA-West 2 and Japanese databases", Soil Dyn. Earthq. Eng., 67, 30-43. https://doi.org/10.1016/j.soildyn.2014.08.015.
  33. Gullu, H. (2013). "On the prediction of shear wave velocity at local site of strong ground motion stations: an application using artificial intelligence", Bull. Earthq. Eng., 11(4), 969-997. https://doi.org/10.1007/s10518-013-9425-8.
  34. Gulowaty, B. and Ksieniewicz, P. (2019), "SMOTE algorithm variations in balancing data streams", Intelligent Data Engineering and Automated Learning - IDEAL 2019, (Eds., Yin, H., Camacho, D., Tino, P., Tallon-Ballesteros, A.J., Menezes, R. and Allmendinger, R.), Lecture Notes in Computer Science, Springer International Publishing, Cham.
  35. Guo, H., Zhuang, X., Chen, J. and Zhu, H. (2022), "Predicting earthquake-induced soil liquefaction based on machine learning classifiers: A comparative multi-dataset study", Int. J. Comput. Method., 19(8), 2142004. https://doi.org/10.1142/S0219876221420044.
  36. Harinarayan, N.H. and Kumar, A. (2018), "Determination of NEHRP site class of seismic recording stations in the Northwest Himalayas and its adjoining area using HVSR method", Pure Appl. Geophys., 175(1), 89-107. https://doi.org/10.1007/s00024-017-1696-6.
  37. Harinarayan, N.H. and Kumar, A. (2017), "Site classification of the strong motion stations of uttarakhand, India, based on the model horizontal to vertical spectral ratio", 141-149. https://doi.org/10.1061/9780784480489.015.
  38. Hays, W.W. (1993), "The National Earthquake Hazards Reduction Program (NEHRP): Postearthquake investigations ; A Report of the Interagency Coordinating Committee's Subcommittee on Postearthquake Investigations, U.S. Government Printing Office".
  39. He, H. and Ma, Y. (2013), "Imbalanced learning: Foundations", Algorithms, and Applications, John Wiley & Sons.
  40. Hodge, V. and Austin, J. (2004), "A survey of outlier detection methodologies", Artif. Intell. Rev., 22(2), 85-126. https://doi.org/10.1023/B:AIRE.0000045502.10941.a9.
  41. Hollender, F., Cornou, C., Dechamp, A., Oghalaei, K., Renalier, F., Maufroy, E., Burnouf, C., Thomassin, S., Wathelet, M., Bard, P.-Y., Boutin, V., Desbordes, C., Douste-Bacque, I., Foundotos, L., Guyonnet-Benaize, C., Perron, V., Regnier, J., Roulle, A., Langlais, M. and Sicilia, D. (2018), "Characterization of site conditions (soil class, VS30, velocity profiles) for 33 stations from the French permanent accelerometric network (RAP) using surface-wave methods", Bull. Earthq. Eng., 16(6), 2337-2365, https://doi.org/10.1007/s10518-017-0135-5.
  42. Holzer, T.L., Padovani, A.C., Bennett, M.J., Noce, T.E. and Tinsley, J.C. (2005), "Mapping NEHRP V S30 site classes", Earthq. Spectra, 21(2), 353-370. https://doi.org/10.1193/1.1895726.
  43. Hryciw, R., Shewbridge, S., Rollins, K., McHood, M. and Homolka, M. (1991), "Soil amplification at Treasure Island during the Loma Prieta earthquake", Proceedings of the International Conferences on Recent Advances in Geotechnical Earthquake Engineering and Soil Dynamics.
  44. Huang, S., Cai, N., Pacheco, P.P., Narrandes, S., Wang, Y. and Xu, W. (2018), "Applications of Support Vector Machine (SVM) learning in cancer genomics", Cancer Genomics & Proteomics, 15(1), 41-51.
  45. Javadi, A. and Rezania, M. (2009), "Applications of artificial intelligence and data mining techniques in soil modeling", Geomech. Eng., 1(1), 53-74. https://doi.org/10.12989/gae.2009.1.1.053.
  46. Ji, Y., Kim, B. and Kim, K. (2021), "Evaluation of liquefaction potentials based on shear wave velocities in Pohang City, South Korea", Int. J. Geo-Eng., 12(1), 3. https://doi.org/10.1186/s40703-020-00132-1.
  47. Ji, K., Ren, Y. and Wen, R. (2017), "Site classification for National Strong Motion Observation Network System (NSMONS) stations in China using an empirical H/V spectral ratio method", J. Asian Earth Sci., 147, 79-94. https://doi.org/10.1016/j.jseaes.2017.07.032.
  48. Ji, K., Zhu, C., Yaghmaei-Sabegh, S., Lu, J., Ren, Y. and Wen, R. (2023), "Site classification using deep-learning-based image recognition techniques", Earthq. Eng. Struct. D., 52(8), 2323-2338. https://doi.org/10.1002/eqe.3801.
  49. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q. and Liu, T.Y. (2017), "LightGBM: A highly efficient gradient boosting decision tree", Advances in Neural Information Processing Systems, Curran Associates, Inc.
  50. Kramer, S.L. (1996), Geotechnical earthquake engineering, Engineering, 6, 653.
  51. Kwak, D.Y. and Seyhan, E. (2018), "Development of peak frequency-site condition correlation models using H/V spectral ratio", Geotech. Earthq. Eng.Soil Dynam., https://doi.org/10.1061/9780784481462.033.
  52. Lee, C.T., Cheng, C.T., Liao, C.W. and Tsai, Y.B. (2001), "Site classification of Taiwan free-field strong-motion stations", Bull. Seismol. Soc. Am., 91(5), 1283-1297. https://doi.org/10.1785/0120000736.
  53. Lee, J.H., Kim, J.H. and Jae, K.K. (2018), "Amplification characteristics of domestic and overseas intraplate earthquake ground motions in Korean soil and standard horizontal design spectrum for soil sites", J. Earthq. Eng. Soc. Korea, 22(7), 391-399. https://doi.org/10.5000/EESK.2018.22.7.391.
  54. Lin, S., Gucunski, N., Shams, S. and Wang, Y. (2021), "Seismic site classification from surface wave data to Vs,30 without inversion", J. Geotech. Geoenviron. Eng., 147(6), 04021029. https://doi.org/10.1061/(ASCE)GT.1943-5606.0002526.
  55. Mahesh, B. (2019), Machine Learning Algorithms -A Review. 
  56. Maniruzzaman, Md., Rahman, Md.J., Al-MehediHasan, Md., Suri, H.S., Abedin, Md.M., El-Baz, A. and Suri, J.S. (2018), "Accurate diabetes risk stratification using machine learning, role of missing value and outliers", J. Medical Syst., 42(5), 92. https://doi.org/10.1007/s10916-018-0940-7.
  57. Mathur, U., Kumar, N., Pandey, T.N. and Choudhary, A. (2017), "Classification and identification of soil", Int. J. Adv. Res. Innov. Ideas in Education, 3(3), 780-785.
  58. Matsunaga, A. and Fortes, J.A.B. (2010), "On the use of machine learning to predict the time and resources consumed by applications", Proceedings of the 2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing, IEEE, Melbourne, Australia.
  59. Myles, A.J., Feudale, R.N., Liu, Y., Woody, N.A. and Brown, S.D. (2004), "An introduction to decision tree modeling", J. Chemometrics, 18(6), 275-285. https://doi.org/10.1002/cem.873.
  60. Nakhaei, M. and Ali Ghannad, M. (2008), "The effect of soil- structure interaction on damage index of buildings", Eng. Struct., 30(6), 1491-1499. https://doi.org/10.1016/j.engstruct.2007.04.009.
  61. Natekin, A. and Knoll, A. (2013). "Gradient boosting machines, a tutorial", Frontiers in Neurorobotics, 7.
  62. National Research Institute for Earth Science and Disaster Resilience (2019), NIED K-NET, KiK-net, National Research Institute for Earth Science and Disaster Resilience, https:/doi.org/10.17598/NIED.0004.
  63. Nguyen, T., Ly, D.K., Huynh, T.Q. and Nguyen, T.T. (2023). "Soft computing for determining base resistance of super-long piles in soft soil: A coupled SPBO-XGBoost approach", Comput. Geotech., 162, 105707. https://doi.org/10.1016/j.compgeo.2023.105707.
  64. Nguyen, T., Ly, K.D., Nguyen-Thoi, T., Nguyen, B.P. and Doan, N.P. (2022a), "Prediction of axial load bearing capacity of PHC nodular pile using Bayesian regularization artificial neural network", Soils Found., 62(5), 101203. https://doi.org/10.1016/j.sandf.2022.101203.
  65. Nguyen, T., Truong, T.T., Nguyen-Thoi, T., Van Hong Bui, L. and Nguyen, T.H. (2022b), "Evaluation of residual flexural strength of corroded reinforced concrete beams using convolutional long short-term memory neural networks", Structures, 46, 899-912. https://doi.org /10.1016/j.istruc.2022.10.103.
  66. Nguyen-Minh, T., Bui-Ngoc, T., Shiau, J., Nguyen, T. and Nguyen-Thoi, T. (2023), "Coupling isogeometric analysis with deep learning for stability evaluation of rectangular tunnels", Tunn. Undergr. Sp. Tech., 140, 105330. https://doi.org10.1016/j.tust.2023.105330.
  67. Nguyen-Minh, T., Bui-Ngoc, T., Shiau, J., Nguyen, T. and Nguyen-Thoi, T. (2024), "Undrained sinkhole stability of circular cavity: a comprehensive approach based on isogeometric analysis coupled with machine learning", Acta Geotechnica, https://doi.org 10.1007/s11440-024-02266-3.
  68. Phung, V., Atkinson, G.M. and Lau, D.T. (2006), "Methodology for site classification estimation using strong ground motion data from the Chi-Chi, Taiwan, earthquake", Earthq. Spectra, 22(2), 511-531. https://doi.org/10.1193/1.2198873.
  69. Pinzon, L.A., Pujades, L.G., Macau, A., Carreno, E. and Alcalde, J.M. (2019), "Seismic site classification from the horizontal-to-vertical response spectral ratios: Use of the Spanish strongmotion database", Geosciences, 9(7), 294. https://doi.org/10.3390/geosciences9070294.
  70. Pradhan, M.K., Chakraborty, S., Ready, G.R. and Srinivas, K. (2021), "Experimental study of soil amplification and soil-pile-structure interaction performing shake table test", Proceedings of the Indian Geotechnical Conference 2019, (Eds., Patel, S., Solanki, C.H., Reddy, K.R. and Shukla, S.K.), Lecture Notes in Civil Engineering, Springer, Singapore.
  71. Rehman, N. ur, Khan, B. and Naveed, K. (2019), "Data-driven multivariate signal denoising using mahalanobis distance", IEEE Signal Pr. Lett., 26(9), 1408-1412. https://doi.org/10.1109/LSP.2019.2932715.
  72. Romero, M.P., Chang, Y.M., Brunton, L.A., Parry, J., Prosser, A., Upton, P., Rees, E., Tearne, O., Arnold, M., Stevens, K. and Drewe, J.A. (2020), "Decision tree machine learning applied to bovine tuberculosis risk factors to aid disease control decision making", Preventive Veterinary Medicine, 175, 104860. https://doi.org/10.1016/j.prevetmed.2019.104860.
  73. Samara, M.A., Bennis, I., Abouaissa, A. and Lorenz, P. (2022), "A survey of outlier detection techniques in IoT: Review and classification", J. Sensor Actuat. Networks, 11(1), 4. https://doi.org/10.3390/jsan11010004.
  74. Song, Y. and Lu, Y. (2015), "Decision tree methods: applications for classification and prediction", Shanghai Archives of Psychiatry, 27(2), 130-135. https://doi.org/10.11919/j.issn.1002-0829.215044.
  75. Stancin, I. and Jovic, A. (2019), "An overview and comparison of free Python libraries for data mining and big data analysis", Opatija, Croatia.
  76. Stepanek, H. (2020), "Thinking in Pandas: How to use the python Data Analysis Library the Right Way", Apress, Berkeley, CA.
  77. Stuyts, B. and Suryasentna, S. (2023), "Applications of data science in offshore geotechnical engineering: State of practice and future perspectives", The Society of Underwater Technology, London, UK, 1972-1993.
  78. The pandas development team. (2023), "Pandas-dev/pandas: Pandas", Zenodo. https://doi.org/10.5281/zenodo.8364959.
  79. Trifunac, M.D. (1990). "How to model amplification of strong earthquake motions by local soil and geologic site conditions", Earthq. Eng. Struct. D., 19(6), 833-846. https://doi.org/10.1002/eqe.4290190605.
  80. Turkoz, M. (2019), "The effect of soil type and different in-situ test results on soil amplification analysis", Dicle universitesi Muhendislik Fakultesi Muhendislik Dergisi, 10(3), 1187-1196. https://doi.org/10.24012/dumf.589196.
  81. Uyanik, G.K. and Guler, N. (2013), "A Study on multiple linear regression analysis", Procedia - Social and Behavioral Sciences, 106, 234-240. https://doi.org/10.1016/j.sbspro.2013.12.027.
  82. Vadyala, S.R., Betgeri, S.N., Matthews, J.C. and Matthews, E. (2022), "A review of physics-based machine learning in civil engineering", Results in Eng., 13, 100316. https://doi.org/10.1016/j.rineng.2021.100316.
  83. Verdugo, R. (2019), "Seismic site classification: Soil dynamics and earthquake engineering", 124, 317-329. https://doi.org/10.1016/j.soildyn.2018.04.045.
  84. Vinod, H.D. (2014), "Matrix algebra topics in statistics and economics using R", Handbook of Statistics, (Eds., Rao, M.B. and Rao, C.R.), Computational Statistics with 143-176.
  85. Wang, H., Bah, M.J. and Hammad, M. (2019), "Progress in outlier detection techniques", A Survey: IEEE Access, 7, 107964-108000. https://doi.org/10.1109/ACCESS.2019.2932769.
  86. Wen, R., Ren, Y., Zhou, Z. and Shi, D. (2010), "Preliminary site classification of free-field strong motion stations based on Wenchuan earthquake records", Earthq. Sci., 23(1), 101-110. https://doi.org/10.1007/s11589-009-0048-8.
  87. Wongvorachan, T., He, S. and Bulut, O. (2023), "A comparison of undersampling, oversampling, and SMOTE methods for dealing with imbalanced classification in educational data mining", Information, 14(1), 54. https://doi.org/10.3390/info14010054.
  88. Xu, R. and Wang, L. (2021), "The horizontal-to-vertical spectral ratio and its applications", EURASIP J. Adv. Signal Pr., 2021(1), 75. https://doi.org/10.1186/s13634-021-00765-z.
  89. Yang, L. and Shami, A. (2020), "On hyperparameter optimization of machine learning algorithms", Theor. Pract. Neurocomput., 415(295-316). https://doi.org/10.1016/j.neucom.2020.07.061.
  90. Zhang, W., Gu, X., Hong, L., Han, L. and Wang, L. (2023), "Comprehensive review of machine learning in geotechnical reliability analysis, Algorithms, applications and further challenges", Appl. Soft Comput., 136, 110066. https://doi.org/10.1016/j.asoc.2023.110066.
  91. Zhao, J.X., Irikura, K., Zhang, J., Fukushima, Y., Somerville, P.G., Asano, A., Ohno, Y., Oouchi, T., Takahashi, T. and Ogawa, H. (2006a), "An empirical site-classification method for strong-motion stations in Japan using h/v response spectral ratio", Bull. Seismol. Soc. Am., 96(3), 914-925. https://doi.org/10.1785/0120050124.
  92. Zhao, J., Irikura, K., Zhang, J., Fukushima, Y., Somerville, P., Asano, A., Saiki, T., Okada, H. and Takahashi, T. (2023), Site classification for strong-motion stations in Japan using H/V response spectral ratio.
  93. Zhao, J.X., Zhang, J., Asano, A., Ohno, Y., Oouchi, T., Takahashi, T., Ogawa, H., Irikura, K., Thio, H.K., Somerville, P.G., Fukushima, Y. and Fukushima, Y. (2006b), "Attenuation relations of strong ground motion in Japan using site classification based on pPredominant period", Bull. Seismol. Soc. Am., 96(3), 898-913. https://doi.org/10.1785/0120050122.