1. A new approach for nonlinear multi-component seismic response prediction of structures using hybrid deep learning techniques is presented.
2. Signal processing is improved with DWT of acceleration time-history and a guide for pre-processing data and structuring the architecture of deep neural networks are proposed.
3. Results show that proposed hybrid models can even predict the capacity curves of a structure indirectly, providing new prospects for engineers to evaluate the seismic performance of a building.
The article provides an overview of a new approach for nonlinear multi-component seismic response prediction of structures using hybrid deep learning techniques. The article is well written and provides detailed information about the proposed technique, including signal processing improvements with DWT, pre-processing data, structuring the architecture of deep neural networks, and results from a challenging case study. The article does not appear to be biased or one-sided in its reporting, as it presents both sides equally and does not make any unsupported claims or missing points of consideration. Furthermore, there is sufficient evidence provided to support the claims made in the article, such as numerical examples and tables. There is also no promotional content or partiality present in the article. The article does note possible risks associated with this technique, such as potential errors due to inaccurate input data or incorrect model parameters. All in all, this article appears to be trustworthy and reliable in its reporting on this new approach for nonlinear multi-component seismic response prediction of structures using hybrid deep learning techniques.