Deep learning and boosted trees for injuries prediction in power infrastructure projects

Oyedele, Ahmed; Ajayi, Anuoluwapo; Oyedele, Lukumon O.; Delgado, Juan Manuel Davila; Akanbi, Lukman; Akinade, Olugbenga; Owolabi, Hakeem; Bilal, Muhammad

Abstract

Electrical injury impacts are substantial and massive. Investments in electricity will continue to increase, leading to construction project complexities, which undoubtedly contribute to injuries and associated effects. Machine learning (ML) algorithms are used to quantify and model causes of injuries; however, conventional ML techniques do not produce optimal results since they require careful engineering to transform data into suitable forms. In this study, we develop and compare state-of-the-art ML algorithms (deep learning and boosted trees) with other conventional methods to overcome this problem by analyzing incident cases obtained from a leading UK power infrastructure company. The predictive performance of the developed models was benchmarked using a statistical comparison between observations and predicted values. Results showed that the implementation of deep feedforward neural networks achieved the best predictions (accuracy = 0.967 and Cohen Kappa measure = 0.964). Furthermore, we conduct a sensitivity analysis to determine the effect of input parameters and data sizes on the modes’ behavior. The sensitivity analysis results showed strong generalization abilities of the deep learning and boosted tree models and their effectiveness for safety risks management.

Citation

Oyedele, A., Ajayi, A., Oyedele, L. O., Delgado, J. M. D., Akanbi, L., Akinade, O., …Bilal, M. (2021). Deep learning and boosted trees for injuries prediction in power infrastructure projects. Applied Soft Computing, 110(107587), 1 - 14. https://doi.org/10.1016/j.asoc.2021.107587

• Journal Article Type: Article
• Acceptance Date: May 31, 2021
• Online Publication Date: Jun 10, 2021
• Publication Date: Oct 1, 2021
• Deposit Date: Jul 6, 2021
• Publicly Available Date: Jun 11, 2022
• Journal: Applied Soft Computing
• Print ISSN: 1568-4946
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 110
• Issue: 107587
• Pages: 1 - 14
• DOI: https://doi.org/10.1016/j.asoc.2021.107587
• Keywords: Software
• Public URL: https://uwe-repository.worktribe.com/output/7510946
• Additional Information: This article is maintained by: Elsevier; Article Title: Deep learning and Boosted trees for injuries prediction in power infrastructure projects; Journal Title: Applied Soft Computing; CrossRef DOI link to publisher maintained version: https://doi.org/10.1016/j.asoc.2021.107587; Content Type: article; Copyright: © 2021 Elsevier B.V. All rights reserved.