Comparative Study of Hybrid Artificial Intelligence Approaches for Predicting Hangingwall Stability

    Research output: Contribution to journalArticle

    23 Citations (Scopus)

    Abstract

    Five hybrid artificial intelligence (AI) approaches based on machine learning (ML) and metaheuristic algorithms were proposed to predict open stope hangingwall (HW) stability. The ML algorithms consisted of logistic regression (LR), multilayer perceptron neural networks (MLPNN), decision tree (DT), gradient boosting machine (GBM), and support vector machine (SVM), and the firefly algorithm (FA) was used to tune their hyperparameters. The objectives are to compare different hybrid AI approaches for HW stability prediction and investigate the relative importance of its influencing variables. Performance measures were chosen to be the confusion matrix, the receiver operating characteristic (ROC) curve, and the area under the ROC curve (AUC). The results showed that the proposed hybrid AI approaches had great potential to predict HW stability and the FA was efficient in ML hyperparameters tuning. The AUC values of the optimum GBM, SVM, and LR models on the testing set were 0.855, 0.816, and 0.801, respectively, denoting that their performance was excellent. The optimum GBM model with the top left cutoff or the Youden's cutoff was recommended for HW prediction in terms of the accuracy, the true positive rate and the AUC value. The relative importance of influencing variables on HW stability was obtained, in which stope design method was found to be the most significant variable.

    Original languageEnglish
    Article number04017086
    JournalJournal of Computing in Civil Engineering
    Volume32
    Issue number2
    DOIs
    Publication statusPublished - 1 Mar 2018

    Fingerprint

    Artificial intelligence
    Learning systems
    Support vector machines
    Logistics
    Multilayer neural networks
    Decision trees
    Learning algorithms
    Tuning
    Neural networks
    Testing

    Cite this

    @article{6828b30777ef44e7b413e0dd9701d3e9,
    title = "Comparative Study of Hybrid Artificial Intelligence Approaches for Predicting Hangingwall Stability",
    abstract = "Five hybrid artificial intelligence (AI) approaches based on machine learning (ML) and metaheuristic algorithms were proposed to predict open stope hangingwall (HW) stability. The ML algorithms consisted of logistic regression (LR), multilayer perceptron neural networks (MLPNN), decision tree (DT), gradient boosting machine (GBM), and support vector machine (SVM), and the firefly algorithm (FA) was used to tune their hyperparameters. The objectives are to compare different hybrid AI approaches for HW stability prediction and investigate the relative importance of its influencing variables. Performance measures were chosen to be the confusion matrix, the receiver operating characteristic (ROC) curve, and the area under the ROC curve (AUC). The results showed that the proposed hybrid AI approaches had great potential to predict HW stability and the FA was efficient in ML hyperparameters tuning. The AUC values of the optimum GBM, SVM, and LR models on the testing set were 0.855, 0.816, and 0.801, respectively, denoting that their performance was excellent. The optimum GBM model with the top left cutoff or the Youden's cutoff was recommended for HW prediction in terms of the accuracy, the true positive rate and the AUC value. The relative importance of influencing variables on HW stability was obtained, in which stope design method was found to be the most significant variable.",
    keywords = "Firefly algorithm, Hangingwall stability prediction, Hybrid artificial intelligence (AI) approaches, Machine learning, Performance comparison, Variable importance",
    author = "Chongchong Qi and Andy Fourie and Guowei Ma and Xiaolin Tang and Xuhao Du",
    year = "2018",
    month = "3",
    day = "1",
    doi = "10.1061/(ASCE)CP.1943-5487.0000737",
    language = "English",
    volume = "32",
    journal = "Journal of Computing in Civil Engineering",
    issn = "0887-3801",
    publisher = "American Society of Civil Engineers",
    number = "2",

    }

    TY - JOUR

    T1 - Comparative Study of Hybrid Artificial Intelligence Approaches for Predicting Hangingwall Stability

    AU - Qi, Chongchong

    AU - Fourie, Andy

    AU - Ma, Guowei

    AU - Tang, Xiaolin

    AU - Du, Xuhao

    PY - 2018/3/1

    Y1 - 2018/3/1

    N2 - Five hybrid artificial intelligence (AI) approaches based on machine learning (ML) and metaheuristic algorithms were proposed to predict open stope hangingwall (HW) stability. The ML algorithms consisted of logistic regression (LR), multilayer perceptron neural networks (MLPNN), decision tree (DT), gradient boosting machine (GBM), and support vector machine (SVM), and the firefly algorithm (FA) was used to tune their hyperparameters. The objectives are to compare different hybrid AI approaches for HW stability prediction and investigate the relative importance of its influencing variables. Performance measures were chosen to be the confusion matrix, the receiver operating characteristic (ROC) curve, and the area under the ROC curve (AUC). The results showed that the proposed hybrid AI approaches had great potential to predict HW stability and the FA was efficient in ML hyperparameters tuning. The AUC values of the optimum GBM, SVM, and LR models on the testing set were 0.855, 0.816, and 0.801, respectively, denoting that their performance was excellent. The optimum GBM model with the top left cutoff or the Youden's cutoff was recommended for HW prediction in terms of the accuracy, the true positive rate and the AUC value. The relative importance of influencing variables on HW stability was obtained, in which stope design method was found to be the most significant variable.

    AB - Five hybrid artificial intelligence (AI) approaches based on machine learning (ML) and metaheuristic algorithms were proposed to predict open stope hangingwall (HW) stability. The ML algorithms consisted of logistic regression (LR), multilayer perceptron neural networks (MLPNN), decision tree (DT), gradient boosting machine (GBM), and support vector machine (SVM), and the firefly algorithm (FA) was used to tune their hyperparameters. The objectives are to compare different hybrid AI approaches for HW stability prediction and investigate the relative importance of its influencing variables. Performance measures were chosen to be the confusion matrix, the receiver operating characteristic (ROC) curve, and the area under the ROC curve (AUC). The results showed that the proposed hybrid AI approaches had great potential to predict HW stability and the FA was efficient in ML hyperparameters tuning. The AUC values of the optimum GBM, SVM, and LR models on the testing set were 0.855, 0.816, and 0.801, respectively, denoting that their performance was excellent. The optimum GBM model with the top left cutoff or the Youden's cutoff was recommended for HW prediction in terms of the accuracy, the true positive rate and the AUC value. The relative importance of influencing variables on HW stability was obtained, in which stope design method was found to be the most significant variable.

    KW - Firefly algorithm

    KW - Hangingwall stability prediction

    KW - Hybrid artificial intelligence (AI) approaches

    KW - Machine learning

    KW - Performance comparison

    KW - Variable importance

    UR - http://www.scopus.com/inward/record.url?scp=85038935133&partnerID=8YFLogxK

    U2 - 10.1061/(ASCE)CP.1943-5487.0000737

    DO - 10.1061/(ASCE)CP.1943-5487.0000737

    M3 - Article

    VL - 32

    JO - Journal of Computing in Civil Engineering

    JF - Journal of Computing in Civil Engineering

    SN - 0887-3801

    IS - 2

    M1 - 04017086

    ER -