Please use this identifier to cite or link to this item:
https://rda.sliit.lk/handle/123456789/2608
Title: | A novel approach to explain the black-box nature of machine learning in compressive strength predictions of concrete using Shapley additive explanations (SHAP) |
Authors: | Ekanayake, I.U Meddage, D. P. P Rathnayake, U |
Keywords: | Explainable machine learning Compressive strength Tree-based regression SHAP explanation Laplacian kernel Ridge Regression |
Issue Date: | Apr-2022 |
Publisher: | Elsevier |
Citation: | Ekanayake, Imesh & Meddage, D. P. P. & Rathnayake, Upaka. (2022). A novel approach to explain the black-box nature of machine learning in compressive strength predictions of concrete using Shapley additive explanations (SHAP). Case Studies in Construction Materials. 16. 1-20. 10.1016/j.cscm.2022.e01059. |
Series/Report no.: | Case Studies in Construction Materials;16(5):1-20 |
Abstract: | Machine learning (ML) techniques are often employed for the accurate prediction of the compressive strength of concrete. Despite higher accuracy, previous ML models failed to interpret the rationale behind predictions. Model interpretability is essential to appeal to the interest of domain experts. Therefore, overcoming research gaps identified, this research study proposes a way to predict the compressive strength of concrete using supervised ML algorithms (Decision tree, Extra tree, Adaptive boost (AdaBoost), Extreme gradient boost (XGBoost), Light gradient boosting method (LGBM), and Laplacian Kernel Ridge Regression (LKRR). Alternatively, SHapley Additive exPlainations (SHAP) – a novel black-box interpretation approach - was employed to elucidate the predictions. The comparison revealed that tree-based algorithms and LKRR provide acceptable accuracy for compressive strength predictions. Moreover, XGBoost and LKRR algorithms evinced superior performance (R ¼ 0.98). According to SHAP interpretation, XGBoost predictions capture complex relationships among the constituents. On the other hand, SHAP provides unified measures on feature importance and the impact of a variable for a prediction. Interestingly, SHAP interpretations were in accordance with what is generally observed in the compressive behavior of concrete, thus validating the causality of ML predictions. |
URI: | http://rda.sliit.lk/handle/123456789/2608 |
ISSN: | 2214-5095 |
Appears in Collections: | Department of Civil Engineering Research Papers - Department of Civil Engineering Research Papers - Open Access Research Research Papers - SLIIT Staff Publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
1-s2.0-S2214509522001917-main.pdf | 6.75 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.