Lee, Yong-Cheol; Shariatfar, Moeid; Rashidi, Abbas; Lee, Hyun Woo. (2020). Evidence-Driven Sound Detection for Prenotification and Identification Of Construction Safety Hazards and Accidents. Automation In Construction, 113.
View Publication
Abstract
As the construction industry experiences a high rate of casualties and significant economic loss associated with accidents, safety has always been a primary concern. In response, several studies have attempted to develop new approaches and state-of-the-art technology for conducting autonomous safety surveillance of construction work zones such as vision-based monitoring. The current and proposed methods including human inspection, however, are limited to consistent and real-time monitoring and rapid event recognition of construction safety issues. In addition, the health and safety risks inherent in construction projects make it challenging for construction workers to be aware of possible safety risks and hazards according to daily planned work activities. To address the urgent demand of the industry to improve worker safety, this study involves the development of an audio-based event detection system to provide daily safety issues to laborers and through the rapid identification of construction accidents. As an evidence-driven approach, the proposed framework incorporates the occupational injury and illness manual data, consisting of historical construction accident data classified by types of sources and events, into an audio-based safety event detection framework. This evidence-driven framework integrated with a daily project schedule can automatically provide construction workers with prenotifications regarding safety hazards at a pertinent work zone as well as consistently contribute to enhanced construction safety monitoring by audio-based event detection. By using a machine learning algorithm, the framework can clearly categorize the narrowed-down sound training data according to a daily project schedule and dynamically restrict sound classification types in advance. The proposed framework is expected to contribute to an emerging knowledge base for integrating an automated safety surveillance system into occupational accident data, significantly improving the accuracy of audio-based event detection.
Keywords
Construction Projects; Occupational Hazards; Construction Workers; Construction; System Safety; Video Surveillance; Work-related Injuries; Audio-based Accident Recognition; Autonomous Safety Surveillance; Construction Safety; Evidence-driven Sound Event Detection; Accident Prevention; Accidents; Audio Acoustics; Classification (of Information); Construction Industry; Health Hazards; Health Risks; Knowledge Based Systems; Learning Algorithms; Losses; Machine Learning; Monitoring; Motion Compensation; Occupational Diseases; Steel Beams And Girders; Audio-based; Construction Accidents; Construction Work Zones; Historical Construction; Sound Event Detection; State-of-the-art Technology; Vision Based Monitoring; Algorithm; System
Shang, Luming; Lee, Hyun Woo; Dermisi, Sofia; Choe, Youngjun. (2020). Impact of Energy Benchmarking and Disclosure Policy on Office Buildings. Journal Of Cleaner Production, 250.
View Publication
Abstract
Building energy benchmarking policies require owners to publicly disclose their building's energy performance. In the US, the adoption of such policies is contributing to an increased awareness among tenants and buyers and is expected to motivate the owners of less efficient buildings to invest in energy efficiency improvements. However, there is a lack of studies specifically aimed at investigating the impact of such policies on office buildings among major cities through quantitative analyses. In response, this study evaluated the effectiveness of the benchmarking policy on energy efficiency improvements decision-making and on real estate performances, by applying two interrupted time series analyses to office buildings in downtown Chicago. The initial results indicate a lack of statistically strong evidence that the policy affected the annual vacancy trend of the energy efficient buildings (represented by ENERGY STAR labeled buildings). However, the use of interrupted time series in a more in-depth analysis shows that the policy is associated with a 6.7% decrease in vacancy among energy efficient buildings. The study proposed a method to quantitatively evaluate the impact of energy policies on the real estate performance of office buildings, and the result confirms the positive impact of energy-efficient retrofits on the real estate performance. The study findings support the reasoning behind the owners' decision in implementing energy efficiency improvements in their office buildings to remain competitive in the market. (C) 2019 Elsevier Ltd. All rights reserved.
Keywords
Office Buildings; Building Failures; Time Series Analysis; Real Property; Energy Consumption; Metropolis; Building Performance; Chicago (ill.); Building Energy Benchmarking And Disclosure Policies; Building Energy Efficiency; Time Series Modeling; Energy Star (program); Building Management Systems; Buildings (structures); Decision Making; Energy Conservation; Maintenance Engineering; Time Series; Disclosure Policy; Energy Benchmarking Policies; Building; Benchmarking Policy; Energy Efficiency Improvements Decision-making; Estate Performance; Energy Efficient Buildings; Energy Star; Energy Policies; Energy-efficient Retrofits; Interrupted Time-series; Regression; Behavior; Designs; Building Energy Benchmarking And; Disclosure Policies; Buildings; Cities; Energy Efficiency; Energy Policy; Markets; Quantitative Analysis; United States
Chen, Chen; Lindell, Michael K.; Wang, Haizhong. (2021). Tsunami Preparedness and Resilience in the Cascadia Subduction Zone: A Multistage Model of Expected Evacuation Decisions and Mode Choice. International Journal Of Disaster Risk Reduction, 59.
View Publication
Abstract
Physical scientists have estimated that the Cascadia Subduction Zone (CSZ) has as much as a 25% chance to produce a M9.0 earthquake and tsunami in the next 50 years, but few studies have used survey data to assess household risk perceptions, emergency preparedness, and evacuation intentions. To understand these phenomena, this study conducted a mail-based household questionnaire using the Protective Action Decision Model (PADM) as a guide to collect 483 responses from two coastal communities in the CSZ: Crescent City, CA and Coos Bay, OR. We applied multistage regression models to assess the effects of critical PADM variables. The results showed that three psychological variables (risk perception, perceived hazard knowledge, and evacuation mode efficacy) were associated with some demographic variables and experience variables. Evacuation intention and evacuation mode choice are associated with those psychological variables but not with demographic variables. Contrary to previous studies, location and experience had no direct impact on evacuation intention or mode choice. We also analyzed expected evacuation mode compliance and the potential of using micro-mobility during tsunami response. This study provides empirical evidence of tsunami preparedness and intentions to support interdisciplinary evacuation modeling, tsunami hazard education, community disaster preparedness, and resilience plans.
Keywords
False Discovery Rate; American-samoa; Earthquake; Washington; Behavior; Oregon; Wellington; Responses; Disaster; Tsunami Evacuation; Cascadia Subduction Zone; Risk Perception
Lin, Lin; Chen, Xueming (Jimmy); Moudon, Anne Vernez. (2021). Measuring the Urban Forms of Shanghai’s City Center and Its New Districts: A Neighborhood-Level Comparative Analysis. Sustainability, 13(15).
View Publication
Abstract
Rapid urban expansion has radically transformed the city centers and the new districts of Chinese cities. Both areas have undergone unique redevelopment and development over the past decades, generating unique urban forms worthy of study. To date, few studies have investigated development patterns and land use intensities at the neighborhood level. The present study aims to fill the gap and compare the densities of different types of developments and the spatial compositions of different commercial uses at the neighborhood level. We captured the attributes of their built environment that support instrumental activities of daily living of 710 neighborhoods centered on the public elementary schools of the entire Shanghai municipality using application programming interfaces provided in Baidu Map services. The 200 m neighborhood provided the best fit to capture the variations of the built environment. Overall, city center neighborhoods had significantly higher residential densities and housed more daily routine destinations than their counterparts in the new districts. Unexpectedly, however, the total length of streets was considerably smaller in city-center neighborhoods, likely reflecting the prominence of the wide multilane vehicular roads surrounding large center city redevelopment projects. The findings point to convergence between the city center's urban forms and that of the new districts.
Keywords
Quantifying Spatiotemporal Patterns; Fast-food Restaurants; Instrumental Activities; Physical-activity; Chinese Cities; Land; Schools; Redevelopment; Expansion; Transformation; Built Environment; Planning; Neighborhood; Urban Form; Shanghai
Zou, Tianqi; Aemmer, Zack; Mackenzie, Don; Laberteaux, Ken. (2022). A Framework for Estimating Commute Accessibility and Adoption of Ridehailing Services Under Functional Improvements from Vehicle Automation. Journal Of Transport Geography, 102.
View Publication
Abstract
This paper develops an analytical framework to estimate commute accessibility and adoption of various ridehailing service concepts across the US by synthesizing individual commute trips using national Longitudinal Employer-Household Dynamics Origin-Destination Employment Statistics (LODES) data. Focusing on potential improvements in cost and time that could be enabled by vehicle automation, we use this modeling framework to simulate a lower-price autonomous service (e.g., 50% or 75% lower) with variable wait times and implementation levels (solo, pooled, and first/last mile transit connections services, alone or in combination) to determine how they might affect adoption rates. These results are compared across metrics of accessibility and trip density, as well as socioeconomic factors such as household income. We find - unsurprisingly - that major cities (e.g. New York, Los Angeles, and Chicago) support the highest adoption rates for ridehailing services. Decreases in price tend to increase market share and accessibility. The effect of a decrease in price is more drastic for lower income groups. The proposed method for synthesizing trips using the LODES contributes to current travel demand forecasting methods and the proposed analytic framework can be flexibly implemented with any other mode choice model, extended to non-commute trips, or applied to different levels of geographic aggregation.
Keywords
Choice Of Transportation; Demand Forecasting; Poor People; Adoption; Price Cutting; Metropolis; Employment Statistics; Los Angeles (calif.); New York (state); Chicago (ill.); Accessibility; Autonomous Vehicles; New Mobility Services; Ridehailing; Travel Demand; Preferences
Launching the Inspire Fund: An early step for CBE’s Office of Research “For a small college, CBE has a broad range of research paradigms, from history and arts, to social science and engineering.” — Carrie Sturts Dossick, Associate Dean of Research Upon taking on the role of Associate Dean of Research, Carrie Sturts Dossick, professor in the Department of Construction Management, undertook listening sessions to learn about the research needs of faculty, staff and students across the College of Built…
ARPA-E announced $5 million in funding to two universities—the University of Washington and University of California, Davis—working to develop life cycle assessment tools and frameworks associated with transforming buildings into net carbon storage structures. The funding is part of the Harnessing Emissions into Structures Taking Inputs from the Atmosphere (HESTIA) Exploratory Topic. Parametric Open Data for Life Cycle Assessment (POD | LCA) – $3,744,303 The University of Washington’s Carbon Leadership Forum will develop a rigorous and flexible parametric Life Cycle Assessment (LCA)…
In 2021 the College of Built Environments launched the CBE Inspire Fund, designed to support CBE research activities for which a relatively small amount of support can be transformative. The second year of awards have just been announced, supporting five projects across 4 departments within the college as they address topics such as food sovereignty, anti-displacement, affordable housing, and health & wellbeing. This year’s awardees include: Defining the New Diaspora: Where Seattle’s Black Church Congregants Are Moving and Why Rachel…
Assistant Professor of Landscape Architecture Catherine De Almeida remembers picking up trash on the playground, seeing people throw trash out their car window, and noticing trash flying around while she played outside as a child. The presence of litter in landscapes upset her so much that she would spend her elementary school recesses picking up trash. When she got into the field of architecture, De Almeida found herself drawn to how things could be flexible and take on multiple identities…
I am interested in researching equitable revitalization methods in marginalized communities so those communities can be revitalized without creating mass displacement and erasure of the existing culture. I have been using environmental psychology as a lens to analyze the neighborhood and explain the existing value there to people who do not inherently see it. I am interested in delving into how design can be used as a tool to empower communities to strive for spatial justice. I have additional interests in culture, place, identity, collectivism, belonging, community, equitable community development, human well-being, affordable housing, economic empowerment, and interdependence.