Asst. Prof. Ma. Doreen Candelaria recently published her research paper titled “Evaluation of thermal damages of concrete subjected to high temperatures using recurrent neural networks for ultrasonic pulse waves” in the Construction and Building Materials Journal of Elsevier.
The paper proposes the use of deep learning methods to classify the thermal damage of concrete cylinder specimens based on ultrasonic pulse wave data. Some highlights of the study:
– Advanced classification models were developed for the evaluation of thermally damaged concrete.
– The use of a gated recurrent unit resulted in the best performance of the classification models.
– The performance of the deep learning-based models was especially superior to conventional ultrasonic models.
Asst. Prof. Candelaria is currently the head of UP ICE Construction Engineering and Management Group (CEMG).
Access the full paper on this link: https://doi.org/10.1016/j.conbuildmat.2023.133416
