Data-Driven Detection of Nonlinear Mode Interactions Using Post-Hoc Interpretable Deep Learning

Bayan Abusalameh, Gianmarco Mengaldo

Submission Type: I want my submission to be considered for both oral and poster presentation.

Keywords: Nonlinear mode interactions, Explainable AI (XAI), Computational mechanics, Structural dynamics, Deep learning, Time-series classification.

TL;DR: A methodology combining deep learning and post-hoc interpretability to categorize structural interaction regimes from multi-modal time-series histories without manual feature extraction.

Confirmation Of Submission Requirements: I submit an abstract. It uses the template provided on the submission page and is no longer than 2 pages.

Submission Number: 276