12th Annual International Conference on Industrial Engineering and Operations Management

Estimation of Compaction Characteristics Using Machine Learning Techniques

0 Paper Citations
1 Views
1 Downloads
Track: Modeling and Simulation

bstract
Application of Machine learning which is the main driver of Artificial Intelligence is gradually gaining ground in the field of geotechnical engineering for prediction and forecasting.  In the present research, efforts are made to explore some machine learning techniques such as:  Support Vector Machine, Random Forest, Artificial Neural Networks, M5 Tree and Multiple Linear Regression models to correlate maximum dry density and optimum moisture content with some soil index properties where the best predicting model was determined. Four hundred and eighty (480) soil samples were obtained and divided into data set using training and validation of the developed models from the basic soil parameters. The Goodness of fit between the Actual and the Predicted Values showed that the values of Root Mean Square Error 253.84, 295.44, 218.08, 101.63, 211.12 and 3.91, 4.55, 3.54, 1.67, 20.13. are from Support Vector Machine; Random Forest, Artificial Neural Networks, M5 Tree and Multiple Linear Regression models for Maximum Dry Density and Optimum Moisture Content values respectively. The least values 101.63 and 1.67 was observed from Random Forest for Maximum Dry Density and Optimum Moisture Content. Similarly, the correlation coefficient values range between 0.15 – 0.96 and 0.2 ─0.96. From the foregoing, the correlation coefficient value proved the Random Forest model as the best for estimating Maximum Dry Density and Optimum Moisture Content while the model having the least correlation coefficient is the Multiple Linear Regression model for Maximum Dry Density and Support Vector Machine for Optimum Moisture Content respectively. It’s concluded that this research work will be an excellent guide to Constructors, Future planners and Civil engineers for estimation of unavailable data, and for cross checking the observed values particularly at the project preliminary stages within the study area.

Key words: Compaction characteristics, Correlation coefficient , Machine Learning, Optimum Moisture Content and Maximum Dry Density.

Published in: 12th Annual International Conference on Industrial Engineering and Operations Management, Istanbul, Turkey

Publisher: IEOM Society International
Date of Conference: March 7-10, 2022

ISBN: 978-1-7923-6131-9
ISSN/E-ISSN: 2169-8767