skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • NSF Public Access
  • Search Results
  • Autoencoder-Based Motion Artifact Reduction in Photoplethysmography (PPG) Signals Acquired from Wearable Sensors during Construction Tasks
Title: Autoencoder-Based Motion Artifact Reduction in Photoplethysmography (PPG) Signals Acquired from Wearable Sensors during Construction Tasks
Construction workers often experience high levels of physical and mental stress due to the demanding nature of their work on construction sites. Real-time health monitoring can provide an effective means of detecting these stressors. Previous research in this field has demonstrated the potential of photoplethysmography (PPG), which represents cardiac activities, as a biomarker for assessing various stressors, including physical fatigue, mental stress, and heat stress. However, PPG acquisition during construction tasks is subject to several external noises, of which motion artifact is a major one. To address this, the study develops and examines an autoencoder network—a special type of artificial neural network—to remove PPG signals’ motion artifacts during construction tasks, thereby enhancing the accuracy of health assessments.Artifact-free PPG signals are acquired through subjects in a stationary position, which is used as the reference for training the autoencoder network. The network’s performance is examined with PPG signals acquired from the same subjects performing multiple construction tasks. The developed autoencoder network can increase the signal-to-noise ratio (SNR) by up to 33% for the corrupted signals acquired in a construction setting. This research contributes to the extensive and resilient use of PPG signals in health monitoring for construction workers.  more » « less
Award ID(s):
2401745
PAR ID:
10516382
Author(s) / Creator(s):
;
Publisher / Repository:
American Society of Civil Engineers
Date Published:
Journal Name:
Construction Research Congress 2024
ISBN:
9780784485293
Page Range / eLocation ID:
719 to 728
Format(s):
Medium: X
Location:
Des Moines, Iowa
Sponsoring Org:
National Science Foundation
More Like this
  1. ; (, Automation in Construction)
    Prior research has validated Photoplethysmography (PPG) as a promising biomarker for assessing stress factors in construction workers, including physical fatigue, mental stress, and heat stress. However, the reliability of PPG as a stress biomarker in construction workers is hindered by motion artifacts (MA) - distortions in blood volume pulse measurements caused by sensor movement. This paper develops a deep convolutional autoencoder-based framework, trained to detect and reduce MA in MA-contaminated PPG signals. The framework's performance is evaluated using PPG signals acquired from individuals engaged in specific construction tasks. The results demonstrate the framework has effectiveness in both detecting and reducing MA in PPG signals with a detection accuracy of 93% and improvement in signal-to-noise ratio by over 88%. This research contributes to a more reliable and error-reduced usage of PPG signals for health monitoring in the construction industry. 
    more » « less
  2. ; ; (, CIB Conferences)
    While drones have exhibited considerable potential to revolutionize the construction industry, previous studies across domains have proposed that human-drone interaction could cause adverse impacts on humans (e.g., collision and discomfort). Given that construction has been recognized as a hazardous and high-stress workplace, it deserves deep exploration regarding how newly introduced drones will influence worker well-being during the interaction. However, there is a paucity of research on worker stress when communicating with drones in construction. Successful human-drone interaction must necessitate seamless and comfortable communication between workers and drones. Therefore, this study investigates the impact of physically demanding response levels on construction workers’ mental and physical well-being throughout the communication cycle. Three levels of physical responses (low, medium, and high) required for drone communication were simulated in an extended reality roofing experiment. During the communication process, real-time stress levels were assessed through participants’ electrodermal activity. The results indicated that a higher physical level of communication significantly increased workers’ higher stress levels in both the response and decoding phases. Additionally, providing drones’ feedback in verbal human-drone communication is especially important to reduce workers’ confusion and mental stress. This study highlights the critical need for worker-centric design and communication strategies in drone integration within construction. 
    more » « less
  3. ; ; ; (, Construction Research Congress 2022)
    Recent research suggests construction workers fall prey to the cognitive biases of risk compensation, wherein workers offset safety improvements by taking more risks. Parallel previous literature indicates that time pressure and mental load may increase workers’ arousal and stress. However, it is unclear whether time, productivity, and/or cognitive demands can worsen risk compensation behaviors by stimulating workers to make riskier decisions to complete tasks faster. Combining a multi-modal mixed-reality environment with wearable neuro-psychophysiological sensors, this study examines changes in safety and task performance for high-risk electrical-line tasks simulated under time/performance pressure and cognitive demand. The results show risk-compensation is in play as subjects over-rely on safety technologies and maintain their risk perception even while undertaking more risks to adapt to increased time pressure and/or cognitive demand. This paper contributes to body of knowledge by affecting safety-training approaches and the controls needed when providing workers with safety protection and new technological advances. 
    more » « less
  4. ; ; ; ; ; ; ; ; ; ; et al (, BMC Public Health)
    Abstract BackgroundAs an illustrative example of COVID-19 pandemic community-based participatory research (CBPR), we describe a community-academic partnership to prioritize future research most important to people experiencing high occupational exposure to COVID-19 – food service workers. Food service workers face key challenges surrounding (1) health and safety precautions, (2) stress and mental health, and (3) the long-term pandemic impact. MethodUsing CBPR methodologies, academic scientists partnered with community stakeholders to develop the research aims, methods, and measures, and interpret and disseminate results. We conducted a survey, three focus groups, and a rapid qualitative assessment to understand the three areas of concern and prioritize future research. ResultsThe survey showed that food service employers mainly supported basic droplet protections (soap, hand sanitizer, gloves), rather than comprehensive airborne protections (high-quality masks, air quality monitoring, air cleaning). Food service workers faced challenging decisions surrounding isolation, quarantine, testing, masking, vaccines, and in-home transmission, described anxiety, depression, and substance use as top mental health concerns, and described long-term physical and financial concerns. Focus groups provided qualitative examples of concerns experienced by food service workers and narrowed topic prioritization. The rapid qualitative assessment identified key needs and opportunities, with help reducing in-home COVID-19 transmission identified as a top priority. COVID-19 mitigation scientists offered recommendations for reducing in-home transmission. ConclusionsThe COVID-19 pandemic has forced food service workers to experience complex decisions about health and safety, stress and mental health concerns, and longer-term concerns. Challenging health decisions included attempting to avoid an airborne infectious illness when employers were mainly only concerned with droplet precautions and trying to decide protocols for testing and isolation without clear guidance, free tests, or paid sick leave. Key mental health concerns were anxiety, depression, and substance use. Longer-term challenges included Long COVID, lack of mental healthcare access, and financial instability. Food service workers suggest the need for more research aimed at reducing in-home COVID-19 transmission and supporting long-term mental health, physical health, and financial concerns. This research provides an illustrative example of how to cultivate community-based partnerships to respond to immediate and critical issues affecting populations most burdened by public health crises. 
    more » « less
  5. ; ; ; ; (, Construction Research Congress 2024)
    Exoskeletons, also known as wearable robots, are being studied as a potential solution to reduce the risk of work-related musculoskeletal disorders (WMSDs) in construction. The exoskeletons can help enhance workers’ postures and provide lift support, reducing the muscular demands on workers while executing construction tasks. Despite the potential of exoskeletons inreducing the risk of WMSDs, there is a lack of understanding about the potential effects ofexoskeletons on workers’ psychological states. This lack of knowledge raises concerns thatexoskeletons may lead to psychological risks, such as cognitive overload, among workers. Tobridge this gap, this study aims to assess the impact of back-support exoskeletons (BSE) onworkers’ cognitive load during material lifting tasks. To accomplish this, a physiologically basedcognitive load assessment framework was developed. This framework used wearable biosensorsto capture the physiological signals of workers and applied Autoencoder and Ensemble Learningtechniques to train a machine learning classifier based on the signals to estimate cognitive loadlevels of workers while wearing the exoskeleton. Results showed that using BSE increasedworkers’ cognitive load by 33% compared to not using it during material handling tasks. Thefindings can aid in the design and implementation of exoskeletons in the construction industry. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email