Search for: All records

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. 

Active back-support exoskeleton has gained recognition as a potential solution to mitigate work- related musculoskeletal disorders. However, their utilization in the construction industry can introduce unintended consequences, such as increased fall hazards. This study examines the implications of using active back-support exoskeleton on fall risk during construction framing tasks, incorporating wearable pressure insoles for data collection. Two experimental conditions were established, one involving the simulation of construction framing tasks with exoskeleton and the other without exoskeleton. These tasks encompassed six subtasks: measuring, assembly, nailing, lifting, moving, and installation. Foot plantar pressure distribution was recorded across various spatial foot regions, including the arch, toe, metatarsal, and heel. Statistical analysis, employing a paired t-test on peak plantar pressure data, revealed that the use of active back-support exoskeleton significantly increased fall risks in at least one of the foot regions for all subtasks, except for the assembly subtask. These findings provide valuable insights for construction stakeholders when making decisions regarding the adoption of active back-support exoskeleton in the industry. Moreover, they inform exoskeleton manufacturers of the need to develop adaptive and customized exoskeleton solutions tailored to the unique demands of construction sites.

 

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. 

Recent advancements in wearable physiological sensing and artificial intelligence have made some remarkable progress in workers’ health monitoring in construction sites. However, the scalable application is still challenging. One of the major complications for deployment has been the distribution shift observed in the physiological data obtained through sensors. This study develops a deep adversarial domain adaptation framework to adapt to out-of-distribution data(ODD) in the wearable physiological device based on photoplethysmography (PPG). The domain adaptation framework is developed and validated with reference to the heart rate predictor based on PPG. A heart rate predictor module comprising feature generating encoder and predictor isinitially trained with data from a given training domain. An unsupervised adversarial domain adaptation method is then implemented for the test domain. In the domain adaptation process, the encoder network is adapted to generate domain invariant features for the test domain using discriminator-based adversarial optimization. The results demonstrate that this approach can effectively accomplish domain adaptation, as evidenced by a 27.68% reduction in heart rate prediction error for the test domain. The proposed framework offers potential for scaled adaptation in the jobsite by addressing the ODD problem.