Human-Centred Neuro-Safety in Industry 5.0 Construction: An Explainable Causal-Predictive Study of Neuroimaging and Bio-Signal Wearables
Loading...
Citations
Altmetric:
Altmetric::
Download
Associated Records
Authors
File Licence
Editors
Date
2026-04-19
Source Title
2026 IEEE International Conference on Smart Sustainable Systems for Computer and Engineering Applications (3SCEA)
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE
Affiliation
Infrastructure Engineering
Document Type
Conference Paper
Subject Code
Citation
Elmousalami, H., Hui, F. & Aye, L. (2026). Human-Centred Neuro-Safety in Industry 5.0 Construction: An Explainable Causal-Predictive Study of Neuroimaging and Bio-Signal Wearables. 2026 IEEE International Conference on Smart Sustainable Systems for Computer and Engineering Applications (3SCEA), 00, pp.18-22. IEEE. https://doi.org/10.1109/3scea68071.2026.11603214.
Access Status
Access this item via the Open Access location
Access URL
Open Access URL
Open Access at PMC
Linked Resource URL
NHMRC Grant Code
ARC Grant Code
Description
Abstract
This study develops a human-centred analytics framework for assessing how neuroimaging and bio-signal wearable systems can support safer and more sustainable construction under Industry 5.0. The framework combines Partial Least Squares Structural Equation Modelling (PLSSEM) with ensemble-based machine learning to examine the links among adoption drivers, perceived benefits, organisational readiness, and sustainability outcomes. Survey responses were prepared through screening, treatment of missing entries, and feature scaling before several predictive models, including Gradient Boosting, LightGBM, AdaBoost, Ridge Regression, Support Vector Regression, and K-Nearest Neighbours, were evaluated through cross-validation. Explainable artificial intelligence was then applied using SHAP values to identify the variables that contributed most strongly to prediction. The results indicate that wearable neuro-safety systems can support earlier hazard recognition, fatigue and workload management, adaptive training, improved coordination, and more resilient site operations. The combined PLS-SEM and machine learning approach offers both causal interpretation and predictive insight, connecting worker-level cognitive and physiological information with broader safety, productivity, and sustainability performance. The paper therefore presents neurosafety as a practical pathway for responsible, transparent, and human-centred construction transformation within Industry 5.0.