Work

Oxygen Uptake Prediction for Timely Construction Worker Fatigue Monitoring Through Wearable Sensing Data Fusion

Year: 2025

Type: article

Abstract: The physical workload evaluation of construction activities will help to prevent excess physical fatigue or overexertion. The workload determination involves measuring physiological responses such as oxygen uptake (VO2) while performing the work. The objective of this study is to develop a procedure for automatic oxygen uptake prediction using the worker’s forearm muscle activity and motion data. The fused IMU and EMG data were analyzed to build a bidirectional long-short-term memory (BiLSTM) model to predict VO2. The results show a strong correlation between the IMU and EMG features and oxygen uptake (R = 0.90, RMSE = 1.257 mL/kg/min). Moreover, measured (9.18 ± 1.97 mL/kg/min) and predicted (9.22 ± 0.09 mL/kg/min) average oxygen consumption to build one scaffold unit are significantly the same. This study concludes that the fusion of IMU and EMG features resulted in high model performance compared to IMU and EMG alone. The results can facilitate the continuous monitoring of the physiological status of construction workers and early detection of any potential occupational risks.

Source: Sensors

DOI: 10.3390/s25103204

Authors: Srikanth Sagar Bangaru, Chao Wang, Fereydoun Aghazadeh, Shashank Muley, Sueed Willoughby

Institution: Louisiana State University

Language: English

Topic: Context-Aware Activity Recognition Systems

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: gold

Estimated APC paid: $3,137