[CS12-10] Trial study on the sparse modeling for the physical logging data
Keywords:sparse modeling, fused lasso, regularization parameter, geotechnical model, physical logging
A technique called sparse modeling has been used in the fields such as machine learning and image processing. This study aimed to apply such the sparse modeling method to geotechnical logging data and to examine its practicality. As a result of examination, it was found that the surface ground amplification characteristic changes depending on the value of regularization parameter. Therefore, when applying the sparse modeling to geotechnical survey results, it is important to set appropriate regularization parameter values.
Abstract password authentication.
Password is required to view the abstract. Please enter a password to authenticate.