Lee, Gaang (2022) Wearable biosensor-based stress detection to understand and improve the quality of interactions between humans and construction and built environments. PhD thesis, University of Michigan, USA.
Abstract
Ensuring human health, safety, comfort, and productivity is a key factor in the management of both construction and built environments (CBEs); human workers are the most important resource at construction sites and the operation of most built environments places the highest priority on serving people optimally. However, the "one-size-fits-all" approach, widely applied in current CBE operation practices, is not effective for ensuring quality of the human-CBE interaction because every individual has unique characteristics and thus differently interacts with CBEs even under an identical setup. Wearable biosensors have great potential to continuously and less-invasively monitor stress as the indicator of individuals' quality of experience during their daily work and lives, thereby enabling more individual response-aware CBE operations. However, still there is a lack of field-applicable means (1) to detect stress from biosignals in an artifact-robust and scalable manner; and (2) to provide information useful in understanding stress-related circumstances (e.g., stressor and impact) and further designing circumstance-specific effective interventions, despite these means' necessity in realizing the wearable biosensors' potential in CBEs. To fill these gaps, five interrelated studies were conducted (1) to denoise both stationary and non-stationary artifacts in biosignals collected during people's daily work and lives in CBEs; (2) to reliably assess generalizability of machine learning models for tasks monitoring human responses from biosignals; (3) to advance model generalizability across different subjects and contexts in detecting stress using a wearable biosensor; (4) to distinguish and locate stress responses related to environmental features; and (5) to differentiate stress types into positive (i.e., eustress) and negative types (i.e., distress). The individual response-aware CBE operations enabled by these studies can significantly contribute to improving human safety, health, and comfort in CBEs and ultimately promoting not only the performance of the construction industry, but only people's quality of life in built environments.
| Item Type: | Thesis (Doctoral) |
|---|---|
| Thesis advisor: | Lee, SangHyun; D'Souza, Clive Rahul; Kamat, Vineet Rajendra; Masoud, Neda and Menassa, Carol C |
| Uncontrolled Keywords: | wearable biosensing to understand human stress in construction and built environments |
| Index terms: | biosensing, productivity, distress, interaction, construction industry, monitoring, human response, comfort, built environment, quality of life, construction site, artifact, human health, machine learning |
| Subjects: | control systems, work location, artificial intelligence, management, public and environmental health, occupational health and safety management, sociology, industry analysis, infrastructure and transport systems, environmental science, structural engineering, behavioral psychology |
| Topics: | Sustainability, Engineering Principles, Health and Safety, Research Practice, Business Strategy, Site Management, Digital Applications, Urban Studies |
| Descriptive scope: | 3 PCT |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here