Intelligent Hearing Protection for Construction Workers Exposed to Hazardous Noise

Details

• Personal Author:
  Le, Tuyen ; Elelu, Kehinde ; Le, Tuyen ; Elelu, Kehinde
• Corporate Authors:
  Clemson University. ; CPWR--The Center for Construction Research and Training. ; National Institute for Occupational Safety and Health. ; Clemson University. ; CPWR--The Center for Construction Research and Training. ; National Institute for Occupational Safety and Health.
• Description:
  "The ability to hear safety cues while wearing hearing protection equipment (HPE) is critical to preventing injuries and deaths on construction job sites. The goal of this project is to improve auditory situational awareness of construction workers exposed to loud noise by investigating a new hearing protection technology that uses artificial intelligence (AI) to amplify safety-critical sounds of collision hazards while greatly attenuating ambient noise. This Small Study focused on developing a signal processing model to help workers wearing HPE improve their audible sense of mobile equipment. This study included three phases: (a) collecting audio data of construction equipment, (b) developing a novel audio-based machine learning model for automated detection of collision hazards to be integrated into intelligent hearing protection devices, and (c) conducting field experiments to investigate the system's efficiency and latency. The outcomes showed that the proposed model detects equipment correctly gave workers timely notifications of hazardous situations. Key Findings. The key results of this study include: 1. The machine learning models trained with a Convolutional Neural Network (CNN) yield reliable collision hazard predictions, with an accuracy of 88% in detecting sounds related to collision hazards when the signals are not buried in background noises. Accuracy remained at that level in loud-noise situations when the signal-to-noise ratio remains above 10db. 2. The study developed a mobile application implementing the CNN model and conducted two sets of experiments, in a controlled environment and on a construction site. The results showed that the mobile application yields a high detection accuracy, particularly for equipment with unique sound patterns." - NIOSHTIC-2
  
  NIOSHTIC no. 20065024
  
  Report #20-3-PS
  
  SS2022-intelligent-hearing-protection.pdf
  
  
• Subjects:
  Construction Industry Ear Protective Devices Hearing Loss, Noise-Induced/prevention & Control Safety Management
• Document Type:
  Pamphlet (or booklet)
• Funding:
  production of this document was supported by cooperative agreement OH 009762 from the National Institute for Occupational Safety and Health (NIOSH)
• Pages in Document:
  I, 14 numbered pages
• NIOSHTIC Number:
  nn:20065024
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:3cefbf8b5e0e63a33c41dc3a59ff60d828c3c8cde6710611cac286a873af501f78e245babc5fe07d093f52dc9bee87fa6462c764954ea6cef98faec0d2bc7eb4
• Download URL:
  https://stacks.cdc.gov/view/cdc/138362/cdc_138362_DS1.pdf
• File Type:
  [PDF - 1.09 MB ]