The demand for a precise evaluation of shear wave velocity Vs, is gaining interest in the field of geotechnical engineering due to its importance as a key parameter required to properly evaluate typical characteristics of soils. Nowadays, Vs measurements are performed on the field using different methods, such as SCPT tests and various geophysical methods. However, the effectiveness of these field measurements is not guaranteed and rather depends on how they are analyzed. Furthermore, a proper analysis is critical since the collected data may be used in liquefaction evaluation or earthquake ground response analyses. In these situations, it is recommended to verify the coherence between the obtained geophysical (Vs) and geotechnical (N-SPT, qc-CPT) measurements using alternative methods (e.g., Vs-correlations, H/V method, etc...). In some situations, the correlation between the different measurements makes it easier to unambiguously define seismic wave profiles. In other cases, geophysical and geotechnical tests would provide different resolutions for Vs measurements, an issue that complicates the decision of the practitioner. In this paper, we first demonstrate the importance of the shear-wave velocity in liquefaction potential analysis. A case study performed in eastern Canada is also presented where we show the importance of the method used to calculate Vs profiles (MASW, MMASW).

Abstract. Determination of pile bearing capacity from the in-situ tests has developed considerably due to the significant development of their technology. The project presented in this paper is a combination of two approaches, artificial neural networks and main component analyses that allow the development of a neural network model that provides a more accurate prediction of axial load bearing capacity based on the SPT test data. The retropropagation multi-layer perceptron with Bayesian regularization (RB) was used in this model. This was established by the incorporation of about 260 data, obtained from the published literature, of experimental programs for large displacement driven piles. The PCA method is proposed for compression and suppression of the correlation between these data. This will improve the performance of generalization of the model.

Abstract. Determination of pile bearing capacity from the in-situ tests has developed considerably due to the significant development of their technology. The project presented in this paper is a combination of two approaches, artificial neural networks and main component analyses that allow the development of a neural network model that provides a more accurate prediction of axial load bearing capacity based on the SPT test data. The retropropagation multi-layer perceptron with Bayesian regularization (RB) was used in this model. This was established by the incorporation of about 260 data, obtained from the published literature, of experimental programs for large displacement driven piles. The PCA method is proposed for compression and suppression of the correlation between these data. This will improve the performance of generalization of the model.