Model with artificial neural network to predict the relationship between the soil resistivity and dry density of compacted soil

S. M Taohidul Islam, Zamri Chik, Mohd. Marzuki Mustafa, Hilmi Sanusi

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This paper presents a technique to obtain the outcomes of soil dry density and optimum moisture contents with artificial neural network (ANN) for compacted soil monitoring through soil resistivity measurement in geotechnical engineering. The compacted soil monitoring through soil electrical resistivity shows the important role in the construction of highway embankments, earth dams and many other engineering structure. Generally, soil compaction is estimated through the determination of maximum dry density at optimum moisture contents in laboratory test. To estimate the soil compaction in conventional soil monitoring technique is time consuming and costly for the laboratory testing with a lot of samples of compacted soil. In this work, an ANN model is developed for predicting the relationship between dry density of compacted soil and soil electrical resistivity based on experimental data in soil profile. The regression analysis between the output and target values shows that the R 2 values are 0.99 and 0.93 for the training and testing sets respectively for the implementation of ANN in soil profile. The significance of our research is to obtain an intelligent model for getting faster, cost-effective and consistent outcomes in soil compaction monitoring through electrical resistivity for a wide range of applications in geotechnical investigation.

Original languageEnglish
Pages (from-to)351-357
Number of pages7
JournalJournal of Intelligent and Fuzzy Systems
Volume25
Issue number2
DOIs
Publication statusPublished - 2013

Fingerprint

Resistivity
Artificial Neural Network
Soil
Neural networks
Soils
Predict
Electrical Resistivity
Compaction
Model
Monitoring
Moisture Content
Relationships
Moisture
Engineering
Embankment dams
Geotechnical engineering
Testing
Embankments
Regression Analysis
Neural Network Model

Keywords

  • ANN modeling
  • dry density
  • electrical resistivity
  • Soil compaction

ASJC Scopus subject areas

  • Artificial Intelligence
  • Engineering(all)
  • Statistics and Probability

Cite this

@article{82338a875bde469584e8466173314d92,
title = "Model with artificial neural network to predict the relationship between the soil resistivity and dry density of compacted soil",
abstract = "This paper presents a technique to obtain the outcomes of soil dry density and optimum moisture contents with artificial neural network (ANN) for compacted soil monitoring through soil resistivity measurement in geotechnical engineering. The compacted soil monitoring through soil electrical resistivity shows the important role in the construction of highway embankments, earth dams and many other engineering structure. Generally, soil compaction is estimated through the determination of maximum dry density at optimum moisture contents in laboratory test. To estimate the soil compaction in conventional soil monitoring technique is time consuming and costly for the laboratory testing with a lot of samples of compacted soil. In this work, an ANN model is developed for predicting the relationship between dry density of compacted soil and soil electrical resistivity based on experimental data in soil profile. The regression analysis between the output and target values shows that the R 2 values are 0.99 and 0.93 for the training and testing sets respectively for the implementation of ANN in soil profile. The significance of our research is to obtain an intelligent model for getting faster, cost-effective and consistent outcomes in soil compaction monitoring through electrical resistivity for a wide range of applications in geotechnical investigation.",
keywords = "ANN modeling, dry density, electrical resistivity, Soil compaction",
author = "Islam, {S. M Taohidul} and Zamri Chik and Mustafa, {Mohd. Marzuki} and Hilmi Sanusi",
year = "2013",
doi = "10.3233/IFS-2012-0641",
language = "English",
volume = "25",
pages = "351--357",
journal = "Journal of Intelligent and Fuzzy Systems",
issn = "1064-1246",
publisher = "IOS Press",
number = "2",

}

TY - JOUR

T1 - Model with artificial neural network to predict the relationship between the soil resistivity and dry density of compacted soil

AU - Islam, S. M Taohidul

AU - Chik, Zamri

AU - Mustafa, Mohd. Marzuki

AU - Sanusi, Hilmi

PY - 2013

Y1 - 2013

N2 - This paper presents a technique to obtain the outcomes of soil dry density and optimum moisture contents with artificial neural network (ANN) for compacted soil monitoring through soil resistivity measurement in geotechnical engineering. The compacted soil monitoring through soil electrical resistivity shows the important role in the construction of highway embankments, earth dams and many other engineering structure. Generally, soil compaction is estimated through the determination of maximum dry density at optimum moisture contents in laboratory test. To estimate the soil compaction in conventional soil monitoring technique is time consuming and costly for the laboratory testing with a lot of samples of compacted soil. In this work, an ANN model is developed for predicting the relationship between dry density of compacted soil and soil electrical resistivity based on experimental data in soil profile. The regression analysis between the output and target values shows that the R 2 values are 0.99 and 0.93 for the training and testing sets respectively for the implementation of ANN in soil profile. The significance of our research is to obtain an intelligent model for getting faster, cost-effective and consistent outcomes in soil compaction monitoring through electrical resistivity for a wide range of applications in geotechnical investigation.

AB - This paper presents a technique to obtain the outcomes of soil dry density and optimum moisture contents with artificial neural network (ANN) for compacted soil monitoring through soil resistivity measurement in geotechnical engineering. The compacted soil monitoring through soil electrical resistivity shows the important role in the construction of highway embankments, earth dams and many other engineering structure. Generally, soil compaction is estimated through the determination of maximum dry density at optimum moisture contents in laboratory test. To estimate the soil compaction in conventional soil monitoring technique is time consuming and costly for the laboratory testing with a lot of samples of compacted soil. In this work, an ANN model is developed for predicting the relationship between dry density of compacted soil and soil electrical resistivity based on experimental data in soil profile. The regression analysis between the output and target values shows that the R 2 values are 0.99 and 0.93 for the training and testing sets respectively for the implementation of ANN in soil profile. The significance of our research is to obtain an intelligent model for getting faster, cost-effective and consistent outcomes in soil compaction monitoring through electrical resistivity for a wide range of applications in geotechnical investigation.

KW - ANN modeling

KW - dry density

KW - electrical resistivity

KW - Soil compaction

UR - http://www.scopus.com/inward/record.url?scp=84878861915&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878861915&partnerID=8YFLogxK

U2 - 10.3233/IFS-2012-0641

DO - 10.3233/IFS-2012-0641

M3 - Article

AN - SCOPUS:84878861915

VL - 25

SP - 351

EP - 357

JO - Journal of Intelligent and Fuzzy Systems

JF - Journal of Intelligent and Fuzzy Systems

SN - 1064-1246

IS - 2

ER -