Investigation of the Case-based Reasoning Retrieval Process to Estimate Resources in Construction Projects

Borja Garcia de Soto, Bryan T. Adey

    Research output: Contribution to journalConference article

    Abstract

    Case-based reasoning (CBR) is a methodology that is seeing increasing use to make predictions during the early phases of a project. It allows estimators to exploit existing knowledge to make predictions that are considerably better than without its use. All CBR, however, is not identical, and variations in how CBR is done can affect the accuracy of the predictions. One particular area of sensitivity is the retrieval phase, i.e. the way in which the CBR determines the closeness between the new and the existing cases. In this paper, CBR is used to make estimates of resources for construction projects, and the use of the nearest neighbor technique to identify the similarity for the retrieval phase to predict the construction material quantities (CMQs) in concrete structures is investigated. Two types of distances, i.e. 1) the City-block distance and 2) the Euclidean distance, and four different types of weights, based on regression analysis and feature counting, to account for the relative importance of the different parameters, are investigated. The four different types of weights used were 1) the adjusted unstandardized coefficients from the regression models, 2) the unadjusted unstandardized coefficients from the regression models, 3) the standardized coefficients from the regression models, and 4) equal weights (i.e.; feature counting), in which the weights applied are 1/k, and k is the number of parameter being compared to determine the distance. The mean absolute percentage error (MAPE) was used to evaluate each combination investigated. It was found that for a similarity threshold of 90%, the CBR methodology using the City-block distance with the adjusted unstandardized coefficients from the regression analysis models using the transformed (LN) dataset as weights, gave the best results, with a MAPE of 8.16%. The worst results were obtained from the CBR methodology using the Euclidean distance with feature counting weights, with a MAPE of 28.40%.

    Original languageEnglish (US)
    Pages (from-to)169-181
    Number of pages13
    JournalProcedia Engineering
    Volume123
    DOIs
    StatePublished - Jan 1 2015
    Event4th Creative Construction Conference, CCC 2015 - Krakow, Poland
    Duration: Jun 21 2015Jun 24 2015

    Fingerprint

    Case based reasoning
    Regression analysis
    Concrete construction

    Keywords

    • artificial intelligence
    • case-based reasoning
    • preliminary estimates
    • resource estimates
    • retrieval process

    ASJC Scopus subject areas

    • Engineering(all)

    Cite this

    Investigation of the Case-based Reasoning Retrieval Process to Estimate Resources in Construction Projects. / Garcia de Soto, Borja; Adey, Bryan T.

    In: Procedia Engineering, Vol. 123, 01.01.2015, p. 169-181.

    Research output: Contribution to journalConference article

    @article{a2e3b205823b43f393ff0d1808614b02,
    title = "Investigation of the Case-based Reasoning Retrieval Process to Estimate Resources in Construction Projects",
    abstract = "Case-based reasoning (CBR) is a methodology that is seeing increasing use to make predictions during the early phases of a project. It allows estimators to exploit existing knowledge to make predictions that are considerably better than without its use. All CBR, however, is not identical, and variations in how CBR is done can affect the accuracy of the predictions. One particular area of sensitivity is the retrieval phase, i.e. the way in which the CBR determines the closeness between the new and the existing cases. In this paper, CBR is used to make estimates of resources for construction projects, and the use of the nearest neighbor technique to identify the similarity for the retrieval phase to predict the construction material quantities (CMQs) in concrete structures is investigated. Two types of distances, i.e. 1) the City-block distance and 2) the Euclidean distance, and four different types of weights, based on regression analysis and feature counting, to account for the relative importance of the different parameters, are investigated. The four different types of weights used were 1) the adjusted unstandardized coefficients from the regression models, 2) the unadjusted unstandardized coefficients from the regression models, 3) the standardized coefficients from the regression models, and 4) equal weights (i.e.; feature counting), in which the weights applied are 1/k, and k is the number of parameter being compared to determine the distance. The mean absolute percentage error (MAPE) was used to evaluate each combination investigated. It was found that for a similarity threshold of 90{\%}, the CBR methodology using the City-block distance with the adjusted unstandardized coefficients from the regression analysis models using the transformed (LN) dataset as weights, gave the best results, with a MAPE of 8.16{\%}. The worst results were obtained from the CBR methodology using the Euclidean distance with feature counting weights, with a MAPE of 28.40{\%}.",
    keywords = "artificial intelligence, case-based reasoning, preliminary estimates, resource estimates, retrieval process",
    author = "{Garcia de Soto}, Borja and Adey, {Bryan T.}",
    year = "2015",
    month = "1",
    day = "1",
    doi = "10.1016/j.proeng.2015.10.074",
    language = "English (US)",
    volume = "123",
    pages = "169--181",
    journal = "Procedia Engineering",
    issn = "1877-7058",
    publisher = "Elsevier BV",

    }

    TY - JOUR

    T1 - Investigation of the Case-based Reasoning Retrieval Process to Estimate Resources in Construction Projects

    AU - Garcia de Soto, Borja

    AU - Adey, Bryan T.

    PY - 2015/1/1

    Y1 - 2015/1/1

    N2 - Case-based reasoning (CBR) is a methodology that is seeing increasing use to make predictions during the early phases of a project. It allows estimators to exploit existing knowledge to make predictions that are considerably better than without its use. All CBR, however, is not identical, and variations in how CBR is done can affect the accuracy of the predictions. One particular area of sensitivity is the retrieval phase, i.e. the way in which the CBR determines the closeness between the new and the existing cases. In this paper, CBR is used to make estimates of resources for construction projects, and the use of the nearest neighbor technique to identify the similarity for the retrieval phase to predict the construction material quantities (CMQs) in concrete structures is investigated. Two types of distances, i.e. 1) the City-block distance and 2) the Euclidean distance, and four different types of weights, based on regression analysis and feature counting, to account for the relative importance of the different parameters, are investigated. The four different types of weights used were 1) the adjusted unstandardized coefficients from the regression models, 2) the unadjusted unstandardized coefficients from the regression models, 3) the standardized coefficients from the regression models, and 4) equal weights (i.e.; feature counting), in which the weights applied are 1/k, and k is the number of parameter being compared to determine the distance. The mean absolute percentage error (MAPE) was used to evaluate each combination investigated. It was found that for a similarity threshold of 90%, the CBR methodology using the City-block distance with the adjusted unstandardized coefficients from the regression analysis models using the transformed (LN) dataset as weights, gave the best results, with a MAPE of 8.16%. The worst results were obtained from the CBR methodology using the Euclidean distance with feature counting weights, with a MAPE of 28.40%.

    AB - Case-based reasoning (CBR) is a methodology that is seeing increasing use to make predictions during the early phases of a project. It allows estimators to exploit existing knowledge to make predictions that are considerably better than without its use. All CBR, however, is not identical, and variations in how CBR is done can affect the accuracy of the predictions. One particular area of sensitivity is the retrieval phase, i.e. the way in which the CBR determines the closeness between the new and the existing cases. In this paper, CBR is used to make estimates of resources for construction projects, and the use of the nearest neighbor technique to identify the similarity for the retrieval phase to predict the construction material quantities (CMQs) in concrete structures is investigated. Two types of distances, i.e. 1) the City-block distance and 2) the Euclidean distance, and four different types of weights, based on regression analysis and feature counting, to account for the relative importance of the different parameters, are investigated. The four different types of weights used were 1) the adjusted unstandardized coefficients from the regression models, 2) the unadjusted unstandardized coefficients from the regression models, 3) the standardized coefficients from the regression models, and 4) equal weights (i.e.; feature counting), in which the weights applied are 1/k, and k is the number of parameter being compared to determine the distance. The mean absolute percentage error (MAPE) was used to evaluate each combination investigated. It was found that for a similarity threshold of 90%, the CBR methodology using the City-block distance with the adjusted unstandardized coefficients from the regression analysis models using the transformed (LN) dataset as weights, gave the best results, with a MAPE of 8.16%. The worst results were obtained from the CBR methodology using the Euclidean distance with feature counting weights, with a MAPE of 28.40%.

    KW - artificial intelligence

    KW - case-based reasoning

    KW - preliminary estimates

    KW - resource estimates

    KW - retrieval process

    UR - http://www.scopus.com/inward/record.url?scp=84953282518&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84953282518&partnerID=8YFLogxK

    U2 - 10.1016/j.proeng.2015.10.074

    DO - 10.1016/j.proeng.2015.10.074

    M3 - Conference article

    VL - 123

    SP - 169

    EP - 181

    JO - Procedia Engineering

    JF - Procedia Engineering

    SN - 1877-7058

    ER -