Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Freeze-thaw durability estimation for concrete through the Gaussian process regression with kernel convolution
https://orcid.org/0000-0001-6958-7880
Highlights The experiment results showed the theoretical trend according to each parameter. The covariance by each kernel showed own characteristics well in the heatmap. Although the properties in each kernel appeared strongly, the drawbacks from kernels were improved by the kernel convolution.
Abstract This study aimed to improve the performance of Gaussian process regression (GPR) estimation through kernel convolution for relative dynamic modulus (RDM) of the freeze–thaw (FT) test. The FT test includes various parameters that affect its outcome. However, FT test results must be measured by humans directly, and due to the characteristics of the experiment, output data is very small. This makes it difficult to apply AI to predict the FT durability process. This study focused on the Bayesian approach of the GPR method with small data. The results showed that kernel convolution improved the estimation performance, as demonstrated by the validation of the fitted GPR with a convoluted kernel. The convolution work could be simplified as the 5/2 Matèrn kernel and periodic kernel showed perfect independence from each other. The independence checking results showed that the chi-square was 0.8579, the Fisher test was 0.98, and the Pearson correlation was 0.00129 respectively in the posterior state. The drawbacks of each kernel were reinforced by the strong points of the other when the kernels performed the convolution, resulting in a reasonable range of RDM estimation. Therefore, it was proved that Bayesian regression performance could be improved through kernel convolution.
Freeze-thaw durability estimation for concrete through the Gaussian process regression with kernel convolution
https://orcid.org/0000-0001-6958-7880
Highlights The experiment results showed the theoretical trend according to each parameter. The covariance by each kernel showed own characteristics well in the heatmap. Although the properties in each kernel appeared strongly, the drawbacks from kernels were improved by the kernel convolution.
Abstract This study aimed to improve the performance of Gaussian process regression (GPR) estimation through kernel convolution for relative dynamic modulus (RDM) of the freeze–thaw (FT) test. The FT test includes various parameters that affect its outcome. However, FT test results must be measured by humans directly, and due to the characteristics of the experiment, output data is very small. This makes it difficult to apply AI to predict the FT durability process. This study focused on the Bayesian approach of the GPR method with small data. The results showed that kernel convolution improved the estimation performance, as demonstrated by the validation of the fitted GPR with a convoluted kernel. The convolution work could be simplified as the 5/2 Matèrn kernel and periodic kernel showed perfect independence from each other. The independence checking results showed that the chi-square was 0.8579, the Fisher test was 0.98, and the Pearson correlation was 0.00129 respectively in the posterior state. The drawbacks of each kernel were reinforced by the strong points of the other when the kernels performed the convolution, resulting in a reasonable range of RDM estimation. Therefore, it was proved that Bayesian regression performance could be improved through kernel convolution.
Freeze-thaw durability estimation for concrete through the Gaussian process regression with kernel convolution
https://orcid.org/0000-0001-6958-7880
Highlights The experiment results showed the theoretical trend according to each parameter. The covariance by each kernel showed own characteristics well in the heatmap. Although the properties in each kernel appeared strongly, the drawbacks from kernels were improved by the kernel convolution.
Abstract This study aimed to improve the performance of Gaussian process regression (GPR) estimation through kernel convolution for relative dynamic modulus (RDM) of the freeze–thaw (FT) test. The FT test includes various parameters that affect its outcome. However, FT test results must be measured by humans directly, and due to the characteristics of the experiment, output data is very small. This makes it difficult to apply AI to predict the FT durability process. This study focused on the Bayesian approach of the GPR method with small data. The results showed that kernel convolution improved the estimation performance, as demonstrated by the validation of the fitted GPR with a convoluted kernel. The convolution work could be simplified as the 5/2 Matèrn kernel and periodic kernel showed perfect independence from each other. The independence checking results showed that the chi-square was 0.8579, the Fisher test was 0.98, and the Pearson correlation was 0.00129 respectively in the posterior state. The drawbacks of each kernel were reinforced by the strong points of the other when the kernels performed the convolution, resulting in a reasonable range of RDM estimation. Therefore, it was proved that Bayesian regression performance could be improved through kernel convolution.
Freeze-thaw durability estimation for concrete through the Gaussian process regression with kernel convolution
Woo, Byeong-Hun (Autor:in) / Ryou, Jae-Suk (Autor:in) / Kim, Joo Young (Autor:in) / Lee, Binna (Autor:in) / Gi Kim, Hong (Autor:in) / Kim, Jee-Sang (Autor:in)
01.08.2023
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Freeze-thaw durability of aggregate in concrete
Engineering Index Backfile | 1956
Freeze-Thaw Durability of High-Strength Concrete
| NTIS | 1998
Freeze/thaw durability in concrete with fibre additions
| British Library Online Contents | 2003
Freeze/thaw durability in concrete with fibre additions
| Emerald Group Publishing | 2003