Advertisement
Published in:
2021 | OriginalPaper | Chapter
Prediction of Strength Characteristics of Soil Using Neural Network Techniques
Authors : Amit Kumar, D. K. Soni
Published in: Smart Technologies for Sustainable Development
Publisher: Springer Singapore
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
New era of machine learning technique has many prediction techniques like linear/nonlinear regression, genetic expression programming, artificial neural networks (ANN), etc. In the present study, among all artificial intelligence techniques, ANN was used to predict the maximum dry density, optimum moisture content, and unconfined compressive strength of 7-, 14-, and 21-day-aged soil samples those contained stone waste at different percentages. The prediction model consists of input parameters, i.e., mix constituents, one hidden layer with two neurons, and results as output parameters. The training and testing results of prediction models were validated with the laboratory findings. The results showed that ANN prediction model produced very precise results with respect to high correlation coefficient and least root mean square error. Therefore, ANN predictive model can be used to predict various parameters of soil efficiently.