Comparison of out-of-plane displacement prediction of infill masonries using artificial intelligence techniques

In the current paper, the aim is to compare the out-of-plane response prediction of an infill wall using artificial intelligence techniques. The out-of-plane response is considered displacement. To predict out-of-plane responses, artificial neural networks and extreme learning machines were used. To generate the database, two shake table experiment results were considered. R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>, mean square error, and mean absolute percentage error were used as quality metrics. The results showed that, despite the artificial neural network’s predicted score being nearly the same as the extreme learning machine’s R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>, the extreme learning machine outperformed artificial neural networks in output prediction based on the remaining quality metrics.