New paper published on Journal of Computing in Civil Engineering
Paper Title: Comparative study of hybrid artificial intelligence approaches for predicting hangingwall stability
Authors: Chong-chong Qi*, Andy Fourie, Guo-wei Ma, Xiao-lin Tang, Xu-hao Du.
Abstract: Five hybrid artificial intelligence (AI) approaches based on machine learning (ML) and metaheuristic algorithms were proposed to predict open stope hangingwall (HW) stability. 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 hyper-parameters. 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 hyper-parameters 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: Hybrid AI approaches; Hangingwall stability prediction; Machine learning; Firefly algorithm; Performance comparison; Variable importance
Comments from reviews:
Reviewer 1: In this study, the authors have proposed five hybrid artificial intelligence (AI) approaches to predict open stope hanging wall (HW) stability. After reviewing this article, there are some comments and suggestions listed below for possibly improving the quality of manuscript.
Reviewer 2: This paper proposes a comparative study of hybrid artificial intelligence approaches for predicting hanging wall stability. Five hybrid artificial intelligence (AI) approaches, which combine machine learning (ML) and metaheuristic algorithms, are developed in this research. The accuracy rate is high, and the findings are very interesting. This reviewer has slight comments for improvement.
Representative figure fron this paper:
ROC curves and AUC values of optimum classification models for HW stability prediction.
Full paper can be obtained through Email.