Intelligent prediction of settlement ratio for soft clay with stone columns using embankment improvement techniques

Zamri Chik, Qasim A. Aljanabi

    Research output: Contribution to journalArticle

    6 Citations (Scopus)

    Abstract

    Construction of highway roads, railways and other engineering structures on soft clay soils normally encounters problems related to excessive settlement issues. The conventional methods are inadequate to analyze and to predict the settlement behavior. Artificial neural network systems are included to predict settlement under embankment load using soft soil properties together with various geometric parameters as inputs for each stone column arrangement and embankment conditions. A case study site investigated field data are taken from a highway project Lebuhraya Pantai Timur2 in Terengganu, Malaysia. Actual angle of internal friction (φ{symbol}), spacing ratio (s/D), cylindrical ratio (L/D) and height of the embankment (H) were used as the input parameters, while the settlement ratio was the main output. The properties of materials on a stone column (φ{symbol}) have high relative importance (40.15 %) compared with the other parameters. Two techniques namely non-cross-validation (β NCV) and ten-fold cross-validation (β FCV) were used to build the ANN model. The β FCV model gives higher efficiency of 0.985 for training and 0.939 for testing, while β NCV model gives 0.937 and 0.905. The β FCV model provides results of greater accuracy as compared to the β NCV models.

    Original languageEnglish
    Pages (from-to)73-82
    Number of pages10
    JournalNeural Computing and Applications
    Volume25
    Issue number1
    DOIs
    Publication statusPublished - 2014

    Fingerprint

    Embankments
    Clay
    Soils
    Internal friction
    Neural networks
    Testing

    Keywords

    • Artificial neural network
    • Settlement ratio
    • Soil improvement
    • Stone column technique

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Software

    Cite this

    Intelligent prediction of settlement ratio for soft clay with stone columns using embankment improvement techniques. / Chik, Zamri; Aljanabi, Qasim A.

    In: Neural Computing and Applications, Vol. 25, No. 1, 2014, p. 73-82.

    Research output: Contribution to journalArticle

    @article{09918a3af2ab450fad4ae21d3d2c79d5,
    title = "Intelligent prediction of settlement ratio for soft clay with stone columns using embankment improvement techniques",
    abstract = "Construction of highway roads, railways and other engineering structures on soft clay soils normally encounters problems related to excessive settlement issues. The conventional methods are inadequate to analyze and to predict the settlement behavior. Artificial neural network systems are included to predict settlement under embankment load using soft soil properties together with various geometric parameters as inputs for each stone column arrangement and embankment conditions. A case study site investigated field data are taken from a highway project Lebuhraya Pantai Timur2 in Terengganu, Malaysia. Actual angle of internal friction (φ{symbol}), spacing ratio (s/D), cylindrical ratio (L/D) and height of the embankment (H) were used as the input parameters, while the settlement ratio was the main output. The properties of materials on a stone column (φ{symbol}) have high relative importance (40.15 {\%}) compared with the other parameters. Two techniques namely non-cross-validation (β NCV) and ten-fold cross-validation (β FCV) were used to build the ANN model. The β FCV model gives higher efficiency of 0.985 for training and 0.939 for testing, while β NCV model gives 0.937 and 0.905. The β FCV model provides results of greater accuracy as compared to the β NCV models.",
    keywords = "Artificial neural network, Settlement ratio, Soil improvement, Stone column technique",
    author = "Zamri Chik and Aljanabi, {Qasim A.}",
    year = "2014",
    doi = "10.1007/s00521-013-1449-0",
    language = "English",
    volume = "25",
    pages = "73--82",
    journal = "Neural Computing and Applications",
    issn = "0941-0643",
    publisher = "Springer London",
    number = "1",

    }

    TY - JOUR

    T1 - Intelligent prediction of settlement ratio for soft clay with stone columns using embankment improvement techniques

    AU - Chik, Zamri

    AU - Aljanabi, Qasim A.

    PY - 2014

    Y1 - 2014

    N2 - Construction of highway roads, railways and other engineering structures on soft clay soils normally encounters problems related to excessive settlement issues. The conventional methods are inadequate to analyze and to predict the settlement behavior. Artificial neural network systems are included to predict settlement under embankment load using soft soil properties together with various geometric parameters as inputs for each stone column arrangement and embankment conditions. A case study site investigated field data are taken from a highway project Lebuhraya Pantai Timur2 in Terengganu, Malaysia. Actual angle of internal friction (φ{symbol}), spacing ratio (s/D), cylindrical ratio (L/D) and height of the embankment (H) were used as the input parameters, while the settlement ratio was the main output. The properties of materials on a stone column (φ{symbol}) have high relative importance (40.15 %) compared with the other parameters. Two techniques namely non-cross-validation (β NCV) and ten-fold cross-validation (β FCV) were used to build the ANN model. The β FCV model gives higher efficiency of 0.985 for training and 0.939 for testing, while β NCV model gives 0.937 and 0.905. The β FCV model provides results of greater accuracy as compared to the β NCV models.

    AB - Construction of highway roads, railways and other engineering structures on soft clay soils normally encounters problems related to excessive settlement issues. The conventional methods are inadequate to analyze and to predict the settlement behavior. Artificial neural network systems are included to predict settlement under embankment load using soft soil properties together with various geometric parameters as inputs for each stone column arrangement and embankment conditions. A case study site investigated field data are taken from a highway project Lebuhraya Pantai Timur2 in Terengganu, Malaysia. Actual angle of internal friction (φ{symbol}), spacing ratio (s/D), cylindrical ratio (L/D) and height of the embankment (H) were used as the input parameters, while the settlement ratio was the main output. The properties of materials on a stone column (φ{symbol}) have high relative importance (40.15 %) compared with the other parameters. Two techniques namely non-cross-validation (β NCV) and ten-fold cross-validation (β FCV) were used to build the ANN model. The β FCV model gives higher efficiency of 0.985 for training and 0.939 for testing, while β NCV model gives 0.937 and 0.905. The β FCV model provides results of greater accuracy as compared to the β NCV models.

    KW - Artificial neural network

    KW - Settlement ratio

    KW - Soil improvement

    KW - Stone column technique

    UR - http://www.scopus.com/inward/record.url?scp=84902519929&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84902519929&partnerID=8YFLogxK

    U2 - 10.1007/s00521-013-1449-0

    DO - 10.1007/s00521-013-1449-0

    M3 - Article

    AN - SCOPUS:84902519929

    VL - 25

    SP - 73

    EP - 82

    JO - Neural Computing and Applications

    JF - Neural Computing and Applications

    SN - 0941-0643

    IS - 1

    ER -