Fig. 3: Data generation and ML model development procedure.
From: Designing bioinspired brick-and-mortar composites using machine learning and statistical learning
The data set was generated by MATLAB53 and ABAQUS52. Mechanical strengths obtained from FEA were considered as the ground truth and held the correct class. The classification to good and bad classes was done through the decision tree with its leaves representing different features conditions. A support vector regression was used for strength prediction.
