Feasibility Analysis of Integrating Wearable Cortisol Sensor Data with Machine Learning for Physical Fatigue Identification in Construction Workers

Details

• Personal Author:
  Pali, Madhavi ; Hossain, Md Adil ; Tian, Chi ; Bao, Jieyi ; Sangmen, Elvis D. ; Tabassum, Shawana
• Description:
  Workplace fatigue caused by stress is a significant concern in physically demanding environments such as construction sites, where long hours and strenuous labor increase the risk of injuries and health issues. To address this challenge, we developed a wearable, user-friendly stress sensor capable of monitoring cortisol levels in human sweat-a key biomarker of physiological stress. The sensor incorporates a functionalized aptamer-based assay to enable real-time, on-site tracking of fatigue symptoms. Impedance-based measurements, specifically changes in charge transfer resistance, were recorded from 10 healthy individuals during a physical stress-inducing hammering task. The sensor showed an increase in charge transfer resistance following the onset of the hammering activity, indicating the physical stress experienced by the participants. Furthermore, cortisol sensor data, combined with other physiological metrics like heart rate variability, were incorporated into a machine learning framework to classify participants' fatigue levels. Of the various models evaluated, the support vector machine achieved the highest classification accuracy of 0.764, effectively distinguishing between low, medium, and high fatigue levels based on quantile-based distributions of signal changes. Hence, this work advances the development of a wearable platform for continuous stress and fatigue monitoring, supporting occupational health management in high-risk labor environments. Description provided by NIOSH
• Subjects:
  • Construction Industry
  • Fatigue
  • Hydrocortisone
  • Occupational Health
  • Safety
  • Wearable Electronic Devices
• Keywords:
  • Fatigue; Physiological stress; Construction workers; Wearable technologies; Machine learning; Long work hours; Biomarkers; Sensors;
  • Author Keywords: wearable sensor; cortisol; fatigue; machine learning; support vector machine; construction work
• Source:
  2025 21st International Conference on Body Sensor Networks (BSN), November 3-5, 2025, Los Angeles, California. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2025 Nov; :1-4
• ISBN:
  9798331554545
• ISSN:
  2376-8894
• Document Type:
  Text
• Funding:
  Cooperative Agreement
• Genre:
  Proceedings
• Place as Subject:
  Atlanta Region OSHA ; Birmingham Region OSHA ; Dallas Region OSHA ; Florida ; Texas
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Pages in Document:
  6 pdf pages
• NIOSHTIC Number:
  nn:20071628
• Contact Point Address:
  Madhavi Pali, The University of Texas at Tyler, Department of Electrical and Computer Engineering, Tyler, TX, United States
• Email:
  mpali@uttyler.edu
• Federal Fiscal Year:
  2026
• NORA Priority Area:
  Agriculture, Forestry and Fishing
• Performing Organization:
  University of Texas Health Center at Tyler
• Peer Reviewed:
  False
• Start Date:
  20010930
• End Date:
  20270929
• Download URL:
  https://stacks.cdc.gov/view/cdc/259403/cdc_259403_DS1.pdf
• File Type:
  [PDF - 4.24 MB]
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:74c8bfafa3b46f6ecf985f51ddd6d179a0f18c15324f20a5c7130781c58399fe1c6499b134e5d717e17535cabebb4d0d251459d358fb07fd3d37ec54f72b2518