A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Evaluation of Compactive Parameters of Soil Using Machine Learning
https://orcid.org/http://orcid.org/0000-0001-9939-4844
https://orcid.org/http://orcid.org/0000-0003-1154-9608
The artificial intelligence is a revolutionary technology applied in many fields, and these fields are medical science, space science, and engineering. Artificial intelligence has two subsets; one is machine learning, and the second is deep learning. In this technical article, the regression analysis, multilayer perceptron class-based neural network models are employed to predict the compactive parameters (optimum moisture content and maximum dry density) of soil in MATLAB R2020a. Various neural network models are developed using different hyperparameters, i.e. hidden layers (one to five), neurons (two to eleven). The performance of the proposed ANN models is compared to determine the best architectural ANN models. The ANN_OMC_3H8 and ANN_MDD_5H1 NN models are determined as the best architectural ANN models and compared to regression model to obtain the optimum performance model. From the comparison, it is observed that the artificial neural network outperformed the regression model. Hence, the proposed artificial neural network models, namely ANN_OMC_3H8 and ANN_MDD_5H1, have the potential to predict the OMC and MDD of soil, respectively.
Evaluation of Compactive Parameters of Soil Using Machine Learning
https://orcid.org/http://orcid.org/0000-0001-9939-4844
https://orcid.org/http://orcid.org/0000-0003-1154-9608
The artificial intelligence is a revolutionary technology applied in many fields, and these fields are medical science, space science, and engineering. Artificial intelligence has two subsets; one is machine learning, and the second is deep learning. In this technical article, the regression analysis, multilayer perceptron class-based neural network models are employed to predict the compactive parameters (optimum moisture content and maximum dry density) of soil in MATLAB R2020a. Various neural network models are developed using different hyperparameters, i.e. hidden layers (one to five), neurons (two to eleven). The performance of the proposed ANN models is compared to determine the best architectural ANN models. The ANN_OMC_3H8 and ANN_MDD_5H1 NN models are determined as the best architectural ANN models and compared to regression model to obtain the optimum performance model. From the comparison, it is observed that the artificial neural network outperformed the regression model. Hence, the proposed artificial neural network models, namely ANN_OMC_3H8 and ANN_MDD_5H1, have the potential to predict the OMC and MDD of soil, respectively.
Evaluation of Compactive Parameters of Soil Using Machine Learning
https://orcid.org/http://orcid.org/0000-0001-9939-4844
https://orcid.org/http://orcid.org/0000-0003-1154-9608
The artificial intelligence is a revolutionary technology applied in many fields, and these fields are medical science, space science, and engineering. Artificial intelligence has two subsets; one is machine learning, and the second is deep learning. In this technical article, the regression analysis, multilayer perceptron class-based neural network models are employed to predict the compactive parameters (optimum moisture content and maximum dry density) of soil in MATLAB R2020a. Various neural network models are developed using different hyperparameters, i.e. hidden layers (one to five), neurons (two to eleven). The performance of the proposed ANN models is compared to determine the best architectural ANN models. The ANN_OMC_3H8 and ANN_MDD_5H1 NN models are determined as the best architectural ANN models and compared to regression model to obtain the optimum performance model. From the comparison, it is observed that the artificial neural network outperformed the regression model. Hence, the proposed artificial neural network models, namely ANN_OMC_3H8 and ANN_MDD_5H1, have the potential to predict the OMC and MDD of soil, respectively.
Evaluation of Compactive Parameters of Soil Using Machine Learning
Lecture Notes in Civil Engineering
Muthukkumaran, Kasinathan (editor) / Ayothiraman, R. (editor) / Kolathayar, Sreevalsa (editor) / Khatti, Jitendra (author) / Grover, Kamaldeep Singh (author)
Indian Geotechnical Conference ; 2021 ; Trichy, India
Soil Dynamics, Earthquake and Computational Geotechnical Engineering ; Chapter: 1 ; 1-14
2023-01-01
14 pages
Article/Chapter (Book)
Electronic Resource
English
The effect of compactive energy level on some soil properties
| Online Contents | 1997
Compactive measure of cohesionless soils
| British Library Conference Proceedings | 1993
Compactive Effort Applied by Hand-Operated Compactors
| British Library Conference Proceedings | 2000
Influence of Compactive Efforts and Compaction Delays on Lime-Treated Soil
| Online Contents | 1998