Study of oversampling algorithms for soil classifications by field velocity resistivity probe

Jong Sub Lee, Junghee Park, Jongchan Kim, Hyung Koo Yoon

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)


A field velocity resistivity probe (FVRP) can measure compressional waves, shear waves and electrical resistivity in boreholes. The objective of this study is to perform the soil classification through a machine learning technique through elastic wave velocity and electrical resistivity measured by FVRP. Field and laboratory tests are performed, and the measured values are used as input variables to classify silt sand, sand, silty clay, and clay-sand mixture layers. The accuracy of k-nearest neighbors (KNN), naive Bayes (NB), random forest (RF), and support vector machine (SVM), selected to perform classification and optimize the hyperparameters, is evaluated. The accuracies are calculated as 0.76, 0.91, 0.94, and 0.88 for KNN, NB, RF, and SVM algorithms, respectively. To increase the amount of data at each soil layer, the synthetic minority oversampling technique (SMOTE) and conditional tabular generative adversarial network (CTGAN) are applied to overcome imbalance in the dataset. The CTGAN provides improved accuracy in the KNN, NB, RF and SVM algorithms. The results demonstrate that the measured values by FVRP can classify soil layers through three kinds of data with machine learning algorithms.

Original languageEnglish
Pages (from-to)247-258
Number of pages12
JournalGeomechanics and Engineering
Issue number3
Publication statusPublished - 2022 Aug 10

Bibliographical note

Publisher Copyright:
© 2022 Techno-Press, Ltd.


  • classification
  • conditional tabular generative adversarial network (CTGAN)
  • field velocity resistivity probe (FVRP)
  • machine learning
  • synthetic minority oversampling technique (SMOTE)

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Geotechnical Engineering and Engineering Geology


Dive into the research topics of 'Study of oversampling algorithms for soil classifications by field velocity resistivity probe'. Together they form a unique fingerprint.

Cite this