Leveraging Machine Learning and Wearable Sensor for Cognitive Risk Assessments in Human-Wearable Robot Interactions
Mariam Tomori1, Sriram Gnanaprakasam1, Omobolanle Ogunseiju1
- Georgia Institute of Technology
Published in Proceedings of the International Conference on Smart and Sustainable Built Environment (SASBE 2024), edited by Ali GhaffarianHoseini, Amirhosein GhaffarianHoseini, Farzad Rahimian and Mahesh Babu Purushothaman. Springer Nature, Lecture Notes in Civil Engineering, volume 591, 2025, pages 1137 to 1146. DOI 10.1007/978-981-96-4051-5_109.
Abstract
Significant safety challenges continue to persist in the construction industry despite several efforts to mitigate them. To address this, the industry has started exploring the potential of wearable robots owing to their ability to augment human capabilities, often resulting in increased safety, productivity, and efficiency. However, studies have revealed that while wearable robots offer significant safety and productivity benefits, potential safety challenges can occur in tasks involving human-wearable robot interactions. Hence, to ensure the effective integration of wearable robots in the construction industry, the potential safety challenges, such as impacts on workers’ cognitive load, must be seamlessly explored. While studies have focused on the potential benefits of wearable robots for the construction industry, scarce information exists as to how safety challenges posed by wearable robots can be effectively mitigated. This study presents machine learning models using data from wearable sensors to predict the cognitive risks faced by workers during physically intensive tasks like masonry. Thirteen participants performed masonry tasks with the use of a wearable robot and physiological sensors to assess cognitive risk levels. The study then employed machine learning algorithms for predicting cognitive risks during these tasks. The findings suggest that the ensemble classifier achieved the highest accuracy in predicting cognitive risk levels, with an accuracy of 78.1%. By developing models that can provide predictive insights into the impacts of wearable robots on construction workers, the study seeks to facilitate the strategic deployment of wearable robots, thereby enhancing construction workers’ safety. This study further sets precedence for intelligent human-wearable robot integration in the construction industry.
Keywords
Session
Presented in Recorded Presentations, Session III, Saturday 9 November 2024, 11:00 to 13:30, room WG 201, Auckland University of Technology. Session chair Dr Antonio Lara Hernandez.
How to Cite
Tomori, M., Gnanaprakasam, S., & Ogunseiju, O. (2025). Leveraging Machine Learning and Wearable Sensor for Cognitive Risk Assessments in Human-Wearable Robot Interactions. In A. GhaffarianHoseini, A. GhaffarianHoseini, F. Rahimian, & M. B. Purushothaman (Eds.), Proceedings of the International Conference on Smart and Sustainable Built Environment (SASBE 2024) (Lecture Notes in Civil Engineering, Vol. 591, pp. 1137–1146). Springer Nature Singapore. https://doi.org/10.1007/978-981-96-4051-5_109
About the Conference
Presented at SASBE 2024, the International Conference on Smart and Sustainable Built Environment, held in Auckland from 7 to 9 November 2024 and chaired by Professors Ali and Amirhosein GhaffarianHoseini, founders of GDI Academy. The version of record is published by Springer Nature; this page is the conference archive record kept by GDI Academy.