Bio-inspired Predictive Models Development for Strength Characterization of Cement Deep-Mixed Plastic Soils

This paper utilizes various artificial intelligence models to predict the experimental results of the deep-mixing technology for ground improvement and stabilization. A total of 192 unconfined compression strength laboratory experiments were conducted on specimens taken from Khuzestan, Iran, to comp...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of geosynthetics and ground engineering 2024-02, Vol.10 (1), Article 9
Hauptverfasser: Mojtahedi, Farid Fazel, Ahmadihosseini, Adel, Eidgahee, Danial Rezazadeh, Rezaee, Milad, Spagnoli, Giovanni
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 1
container_start_page
container_title International journal of geosynthetics and ground engineering
container_volume 10
creator Mojtahedi, Farid Fazel
Ahmadihosseini, Adel
Eidgahee, Danial Rezazadeh
Rezaee, Milad
Spagnoli, Giovanni
description This paper utilizes various artificial intelligence models to predict the experimental results of the deep-mixing technology for ground improvement and stabilization. A total of 192 unconfined compression strength laboratory experiments were conducted on specimens taken from Khuzestan, Iran, to compare the strength of the soil before and after the treatment with cement. In this research, 144 sets of experimental data, constituting 75% of the total, were used for training, while 48 sets, equivalent to 25% of the experimental data, were utilized for both testing. Different artificial intelligence methods including artificial neural networks, hybrid artificial bee colony-artificial neural networks, combinational group modeling of data handling, and gene expression programming were used. To evaluate the performance of each method, mean squared error, root mean squared error, mean absolute percentage error, mean absolute error, linear correlation coefficient, and coefficient of determination was calculated for each method. Based on the performance analysis, the hybrid artificial bee colony-artificial neural network algorithm outperformed other methods with an R 2 calculated as 0.9969 and 0.9952, respectively in training and testing. The R 2 values during training for ANN, GMDH, and GEP are 0.993, 0.983, and 0.96, respectively. Likewise, during testing, the R 2 values for ANN, GMDH, and GEP are 0.992, 0.978, and 0.953, respectively. The results demonstrated significant agreement between artificial intelligence predictive models and experimental data. Furthermore, this paper provides robust and cost-effective models with a “closed-form solution” for predicting the strength of stabilized soils by the deep mixing technique. The closed-form equation presented in this study, which is derived from the group method of data handling combinatorial algorithm and gene expression programming models, is more intuitive for engineers to apply.
doi_str_mv 10.1007/s40891-023-00508-0
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2916429842</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2916429842</sourcerecordid><originalsourceid>FETCH-LOGICAL-c319t-e39b339c7039b71f26fec6145910c949ca0efe2b08040704aa172a7f65b3252f3</originalsourceid><addsrcrecordid>eNp9kE1PAjEQhjdGEwnyBzw18VyddpddetTFrwSiCXpuSplCcdmubSHqr3dhjd68zMzhed9JniQ5Z3DJAIqrkMFIMAo8pQBDGFE4SnqcCUEFL8Tx753DaTIIYQ0AnGUF8LyXvN1YR20dGutxQZ7bYXW0OyRTt8AqkDHusHLNButIjPNkFj3Wy7gi5Up5pSN6-6WidTVxhpR44MaIDZ3aj31hpUK0msycrcJZcmJUFXDws_vJ693tS_lAJ0_3j-X1hOqUiUgxFfM0FbqA9iiY4blBnbNsKBhokQmtAA3yOYwggwIypVjBVWHy4TzlQ27SfnLR9TbevW8xRLl2W1-3LyUXLM-4GGW8pXhHae9C8Ghk4-1G-U_JQO69ys6rbL3Kg1cJbSjtQqGF6yX6v-p_Ut9lOHra</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2916429842</pqid></control><display><type>article</type><title>Bio-inspired Predictive Models Development for Strength Characterization of Cement Deep-Mixed Plastic Soils</title><source>SpringerLink Journals - AutoHoldings</source><creator>Mojtahedi, Farid Fazel ; Ahmadihosseini, Adel ; Eidgahee, Danial Rezazadeh ; Rezaee, Milad ; Spagnoli, Giovanni</creator><creatorcontrib>Mojtahedi, Farid Fazel ; Ahmadihosseini, Adel ; Eidgahee, Danial Rezazadeh ; Rezaee, Milad ; Spagnoli, Giovanni</creatorcontrib><description>This paper utilizes various artificial intelligence models to predict the experimental results of the deep-mixing technology for ground improvement and stabilization. A total of 192 unconfined compression strength laboratory experiments were conducted on specimens taken from Khuzestan, Iran, to compare the strength of the soil before and after the treatment with cement. In this research, 144 sets of experimental data, constituting 75% of the total, were used for training, while 48 sets, equivalent to 25% of the experimental data, were utilized for both testing. Different artificial intelligence methods including artificial neural networks, hybrid artificial bee colony-artificial neural networks, combinational group modeling of data handling, and gene expression programming were used. To evaluate the performance of each method, mean squared error, root mean squared error, mean absolute percentage error, mean absolute error, linear correlation coefficient, and coefficient of determination was calculated for each method. Based on the performance analysis, the hybrid artificial bee colony-artificial neural network algorithm outperformed other methods with an R 2 calculated as 0.9969 and 0.9952, respectively in training and testing. The R 2 values during training for ANN, GMDH, and GEP are 0.993, 0.983, and 0.96, respectively. Likewise, during testing, the R 2 values for ANN, GMDH, and GEP are 0.992, 0.978, and 0.953, respectively. The results demonstrated significant agreement between artificial intelligence predictive models and experimental data. Furthermore, this paper provides robust and cost-effective models with a “closed-form solution” for predicting the strength of stabilized soils by the deep mixing technique. The closed-form equation presented in this study, which is derived from the group method of data handling combinatorial algorithm and gene expression programming models, is more intuitive for engineers to apply.</description><identifier>ISSN: 2199-9260</identifier><identifier>EISSN: 2199-9279</identifier><identifier>DOI: 10.1007/s40891-023-00508-0</identifier><language>eng</language><publisher>Cham: Springer International Publishing</publisher><subject>Algorithms ; Artificial intelligence ; Artificial neural networks ; Bees ; Biomimetics ; Building Materials ; Cement constituents ; Closed form solutions ; Combinatorial analysis ; Compressive strength ; Correlation coefficients ; Engineering ; Environmental Science and Engineering ; Errors ; Exact solutions ; Foundations ; Gene expression ; Geoengineering ; Group method of data handling ; Hydraulics ; Mathematical analysis ; Neural networks ; Original Paper ; Performance evaluation ; Prediction models ; Soil strength ; Soils ; Swarm intelligence ; Training</subject><ispartof>International journal of geosynthetics and ground engineering, 2024-02, Vol.10 (1), Article 9</ispartof><rights>The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c319t-e39b339c7039b71f26fec6145910c949ca0efe2b08040704aa172a7f65b3252f3</citedby><cites>FETCH-LOGICAL-c319t-e39b339c7039b71f26fec6145910c949ca0efe2b08040704aa172a7f65b3252f3</cites><orcidid>0000-0002-1866-4345</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s40891-023-00508-0$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s40891-023-00508-0$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Mojtahedi, Farid Fazel</creatorcontrib><creatorcontrib>Ahmadihosseini, Adel</creatorcontrib><creatorcontrib>Eidgahee, Danial Rezazadeh</creatorcontrib><creatorcontrib>Rezaee, Milad</creatorcontrib><creatorcontrib>Spagnoli, Giovanni</creatorcontrib><title>Bio-inspired Predictive Models Development for Strength Characterization of Cement Deep-Mixed Plastic Soils</title><title>International journal of geosynthetics and ground engineering</title><addtitle>Int. J. of Geosynth. and Ground Eng</addtitle><description>This paper utilizes various artificial intelligence models to predict the experimental results of the deep-mixing technology for ground improvement and stabilization. A total of 192 unconfined compression strength laboratory experiments were conducted on specimens taken from Khuzestan, Iran, to compare the strength of the soil before and after the treatment with cement. In this research, 144 sets of experimental data, constituting 75% of the total, were used for training, while 48 sets, equivalent to 25% of the experimental data, were utilized for both testing. Different artificial intelligence methods including artificial neural networks, hybrid artificial bee colony-artificial neural networks, combinational group modeling of data handling, and gene expression programming were used. To evaluate the performance of each method, mean squared error, root mean squared error, mean absolute percentage error, mean absolute error, linear correlation coefficient, and coefficient of determination was calculated for each method. Based on the performance analysis, the hybrid artificial bee colony-artificial neural network algorithm outperformed other methods with an R 2 calculated as 0.9969 and 0.9952, respectively in training and testing. The R 2 values during training for ANN, GMDH, and GEP are 0.993, 0.983, and 0.96, respectively. Likewise, during testing, the R 2 values for ANN, GMDH, and GEP are 0.992, 0.978, and 0.953, respectively. The results demonstrated significant agreement between artificial intelligence predictive models and experimental data. Furthermore, this paper provides robust and cost-effective models with a “closed-form solution” for predicting the strength of stabilized soils by the deep mixing technique. The closed-form equation presented in this study, which is derived from the group method of data handling combinatorial algorithm and gene expression programming models, is more intuitive for engineers to apply.</description><subject>Algorithms</subject><subject>Artificial intelligence</subject><subject>Artificial neural networks</subject><subject>Bees</subject><subject>Biomimetics</subject><subject>Building Materials</subject><subject>Cement constituents</subject><subject>Closed form solutions</subject><subject>Combinatorial analysis</subject><subject>Compressive strength</subject><subject>Correlation coefficients</subject><subject>Engineering</subject><subject>Environmental Science and Engineering</subject><subject>Errors</subject><subject>Exact solutions</subject><subject>Foundations</subject><subject>Gene expression</subject><subject>Geoengineering</subject><subject>Group method of data handling</subject><subject>Hydraulics</subject><subject>Mathematical analysis</subject><subject>Neural networks</subject><subject>Original Paper</subject><subject>Performance evaluation</subject><subject>Prediction models</subject><subject>Soil strength</subject><subject>Soils</subject><subject>Swarm intelligence</subject><subject>Training</subject><issn>2199-9260</issn><issn>2199-9279</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kE1PAjEQhjdGEwnyBzw18VyddpddetTFrwSiCXpuSplCcdmubSHqr3dhjd68zMzhed9JniQ5Z3DJAIqrkMFIMAo8pQBDGFE4SnqcCUEFL8Tx753DaTIIYQ0AnGUF8LyXvN1YR20dGutxQZ7bYXW0OyRTt8AqkDHusHLNButIjPNkFj3Wy7gi5Up5pSN6-6WidTVxhpR44MaIDZ3aj31hpUK0msycrcJZcmJUFXDws_vJ693tS_lAJ0_3j-X1hOqUiUgxFfM0FbqA9iiY4blBnbNsKBhokQmtAA3yOYwggwIypVjBVWHy4TzlQ27SfnLR9TbevW8xRLl2W1-3LyUXLM-4GGW8pXhHae9C8Ghk4-1G-U_JQO69ys6rbL3Kg1cJbSjtQqGF6yX6v-p_Ut9lOHra</recordid><startdate>20240201</startdate><enddate>20240201</enddate><creator>Mojtahedi, Farid Fazel</creator><creator>Ahmadihosseini, Adel</creator><creator>Eidgahee, Danial Rezazadeh</creator><creator>Rezaee, Milad</creator><creator>Spagnoli, Giovanni</creator><general>Springer International Publishing</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0002-1866-4345</orcidid></search><sort><creationdate>20240201</creationdate><title>Bio-inspired Predictive Models Development for Strength Characterization of Cement Deep-Mixed Plastic Soils</title><author>Mojtahedi, Farid Fazel ; Ahmadihosseini, Adel ; Eidgahee, Danial Rezazadeh ; Rezaee, Milad ; Spagnoli, Giovanni</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c319t-e39b339c7039b71f26fec6145910c949ca0efe2b08040704aa172a7f65b3252f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Artificial intelligence</topic><topic>Artificial neural networks</topic><topic>Bees</topic><topic>Biomimetics</topic><topic>Building Materials</topic><topic>Cement constituents</topic><topic>Closed form solutions</topic><topic>Combinatorial analysis</topic><topic>Compressive strength</topic><topic>Correlation coefficients</topic><topic>Engineering</topic><topic>Environmental Science and Engineering</topic><topic>Errors</topic><topic>Exact solutions</topic><topic>Foundations</topic><topic>Gene expression</topic><topic>Geoengineering</topic><topic>Group method of data handling</topic><topic>Hydraulics</topic><topic>Mathematical analysis</topic><topic>Neural networks</topic><topic>Original Paper</topic><topic>Performance evaluation</topic><topic>Prediction models</topic><topic>Soil strength</topic><topic>Soils</topic><topic>Swarm intelligence</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Mojtahedi, Farid Fazel</creatorcontrib><creatorcontrib>Ahmadihosseini, Adel</creatorcontrib><creatorcontrib>Eidgahee, Danial Rezazadeh</creatorcontrib><creatorcontrib>Rezaee, Milad</creatorcontrib><creatorcontrib>Spagnoli, Giovanni</creatorcontrib><collection>CrossRef</collection><jtitle>International journal of geosynthetics and ground engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Mojtahedi, Farid Fazel</au><au>Ahmadihosseini, Adel</au><au>Eidgahee, Danial Rezazadeh</au><au>Rezaee, Milad</au><au>Spagnoli, Giovanni</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Bio-inspired Predictive Models Development for Strength Characterization of Cement Deep-Mixed Plastic Soils</atitle><jtitle>International journal of geosynthetics and ground engineering</jtitle><stitle>Int. J. of Geosynth. and Ground Eng</stitle><date>2024-02-01</date><risdate>2024</risdate><volume>10</volume><issue>1</issue><artnum>9</artnum><issn>2199-9260</issn><eissn>2199-9279</eissn><abstract>This paper utilizes various artificial intelligence models to predict the experimental results of the deep-mixing technology for ground improvement and stabilization. A total of 192 unconfined compression strength laboratory experiments were conducted on specimens taken from Khuzestan, Iran, to compare the strength of the soil before and after the treatment with cement. In this research, 144 sets of experimental data, constituting 75% of the total, were used for training, while 48 sets, equivalent to 25% of the experimental data, were utilized for both testing. Different artificial intelligence methods including artificial neural networks, hybrid artificial bee colony-artificial neural networks, combinational group modeling of data handling, and gene expression programming were used. To evaluate the performance of each method, mean squared error, root mean squared error, mean absolute percentage error, mean absolute error, linear correlation coefficient, and coefficient of determination was calculated for each method. Based on the performance analysis, the hybrid artificial bee colony-artificial neural network algorithm outperformed other methods with an R 2 calculated as 0.9969 and 0.9952, respectively in training and testing. The R 2 values during training for ANN, GMDH, and GEP are 0.993, 0.983, and 0.96, respectively. Likewise, during testing, the R 2 values for ANN, GMDH, and GEP are 0.992, 0.978, and 0.953, respectively. The results demonstrated significant agreement between artificial intelligence predictive models and experimental data. Furthermore, this paper provides robust and cost-effective models with a “closed-form solution” for predicting the strength of stabilized soils by the deep mixing technique. The closed-form equation presented in this study, which is derived from the group method of data handling combinatorial algorithm and gene expression programming models, is more intuitive for engineers to apply.</abstract><cop>Cham</cop><pub>Springer International Publishing</pub><doi>10.1007/s40891-023-00508-0</doi><orcidid>https://orcid.org/0000-0002-1866-4345</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 2199-9260
ispartof International journal of geosynthetics and ground engineering, 2024-02, Vol.10 (1), Article 9
issn 2199-9260
2199-9279
language eng
recordid cdi_proquest_journals_2916429842
source SpringerLink Journals - AutoHoldings
subjects Algorithms
Artificial intelligence
Artificial neural networks
Bees
Biomimetics
Building Materials
Cement constituents
Closed form solutions
Combinatorial analysis
Compressive strength
Correlation coefficients
Engineering
Environmental Science and Engineering
Errors
Exact solutions
Foundations
Gene expression
Geoengineering
Group method of data handling
Hydraulics
Mathematical analysis
Neural networks
Original Paper
Performance evaluation
Prediction models
Soil strength
Soils
Swarm intelligence
Training
title Bio-inspired Predictive Models Development for Strength Characterization of Cement Deep-Mixed Plastic Soils
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T01%3A33%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Bio-inspired%20Predictive%20Models%20Development%20for%20Strength%20Characterization%20of%20Cement%20Deep-Mixed%20Plastic%20Soils&rft.jtitle=International%20journal%20of%20geosynthetics%20and%20ground%20engineering&rft.au=Mojtahedi,%20Farid%20Fazel&rft.date=2024-02-01&rft.volume=10&rft.issue=1&rft.artnum=9&rft.issn=2199-9260&rft.eissn=2199-9279&rft_id=info:doi/10.1007/s40891-023-00508-0&rft_dat=%3Cproquest_cross%3E2916429842%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2916429842&rft_id=info:pmid/&rfr_iscdi=true