A5100419591- Evacuation and Crowd Dynamics
- Fire effects on ecosystems
- Urban Transport and Accessibility
- Human Mobility and Location-Based Analysis
- Remote Sensing in Agriculture
- Health disparities and outcomes
- Air Quality and Health Impacts
- Flood Risk Assessment and Management
- Urban Green Space and Health
- Microbial Applications in Construction Materials
- Transportation Planning and Optimization
- Infrastructure Maintenance and Monitoring
- Air Quality Monitoring and Forecasting
- Geophysical Methods and Applications
- Land Use and Ecosystem Services
- Smoking Behavior and Cessation
- Infections and bacterial resistance
- Soil Geostatistics and Mapping
- Obesity, Physical Activity, Diet
- Data Visualization and Analytics
- Geographic Information Systems Studies
- Homelessness and Social Issues
- Traffic and Road Safety
- Plant Pathogenic Bacteria Studies
- Food Security and Health in Diverse Populations
University of Alabama
2024
Wenzhou Medical University
2024
Lanzhou Institute of Husbandry and Pharmaceutical Sciences
2023
South Dakota State University
2017-2023
China Electric Power Research Institute
2023
North China Electric Power University
2023
Hebei Agricultural University
2023
East China Normal University
2020-2022
Neusoft (China)
2022
Beihang University
2013-2020
Studies suggest that where people live, play, and work can influence health well-being. However, the dearth of neighborhood data, especially data is timely consistent across geographies, hinders understanding effects neighborhoods on health. Social media represents a possible new resource for research.The aim this study was to build, from geotagged Twitter national database with area-level indicators well-being behaviors.We utilized Twitter's streaming application programming interface...
Monoculture and simplified two-crop rotation systems compromise the ecosystem services essential to crop production, diminish agricultural productivity, cause detrimental effects on environment. In contrast rotation, diversified (DCR) refers that contain three or more crops. Despite multiple benefits generated by DCR, its usage has dwindled over past several decades. This paper examined determinants of farmers' adoption decisions perceived DCR in west margins U.S. Corn Belt where diversity...
Crop yield prediction before the harvest is crucial for food security, grain trade, and policy making. Previously, several machine learning methods have been applied to predict crop using different types of variables. In this study, we propose Geographically Weighted Random Forest Regression (GWRFR) approach improve at county level in US Corn Belt. We trained GWRFR five other popular algorithms (Multiple Linear (MLR), Partial Least Square (PLSR), Support Vector (SVR), Decision Tree (DTR),...
Climate variability and trends have significant environmental socioeconomic impacts. Global challenges such as food security, biodiversity loss, water scarcity human health are affected by reference evapotranspiration, temperature, solar radiation, precipitation together, but nonlinear dynamics of these four climatic factors not been assessed simultaneously at the national scale. This leads to unclear limited applications. To address this knowledge gap, we analyzed daily (reference...
Determining the most effective public warnings to issue during a hazardous environmental event is complex problem. Three primary questions need be answered: Who should take protective action? What best and When this action initiated? Warning triggers provide proactive means for emergency managers simultaneously answer these by recommending that target group specified if preset trigger condition occurs (e.g., warn community evacuate wildfire crosses proximal ridgeline). Triggers are used...
This paper presents a time- and cost-efficient method for the management of construction demolition (C&D) debris at sites, jobsites, illegal C&D waste dumping sites. The developed integrates various drone, deep learning, geographic information system (GIS) technologies, including drone scanning, 3D reconstruction with structure from motion (SfM), image segmentation fully convolutional network (FCN), georeferenced 2D as-built. Experiments parameter analysis led us to conclude that (1)...
To leverage geotagged Twitter data to create national indicators of the social environment, with small-area prevalent sentiment and modeling health behaviors, test associations county-level outcomes, while controlling for demographic characteristics.
Built environment neighborhood characteristics are difficult to measure and assess on a large scale. Consequently, there is lack of sufficient data that can help us investigate as structural determinants health national level. The objective this study utilize publicly available Google Street View images source for characterizing built environments examine the influence chronic diseases behaviors in United States. Data were collected by processing 164 million from November 2019 across...
Collecting neighborhood data can both be time- and resource-intensive, especially across broad geographies. In this study, we leveraged 1.4 million publicly available Google Street View (GSV) images from Utah to construct indicators of the built environment evaluate their associations with 2017-2019 health outcomes approximately one-third population living in Utah. The use electronic medical records allows for assessment between characteristics individual-level while controlling predisposing...
This study utilizes innovative computer vision methods alongside Google Street View images to characterize neighborhood built environments across Utah. Convolutional Neural Networks were used create indicators of street greenness, crosswalks, and building type on 1.4 million images. The demographic medical profiles Utah residents came from the Population Database (UPDB). We implemented hierarchical linear models with individuals nested within zip codes estimate associations between...
Food insecurity (FI) is a pressing concern among university students in the United States, and COVID-19 pandemic has exacerbated this issue. Providing food assistance for become more challenging due to pandemic-related consequences interventions. This study aims (1) analyze social inequalities FI large public during pandemic, (2) investigate association of their utilization campus, community, federal programs (FAPs) FI, (3) understand barriers face accessing FAPs. Survey questionnaires were...
Fuel consumption and air pollution caused by transportation is becoming more serious. Developing an effective meso model to analyze dynamically the temporal spatial distribution of fuel in urban road network has become a research focus. However, parameters used most models traffic field are not detailed enough, generalization ability accuracy these still be improved. For discovering typical driving features relationship with consumption, this paper collected 150 million records within two...
Vertical displacement is a common concrete slab sidewalk deficiency, which may cause trip hazards and reduce wheelchair accessibility. This paper presents an automatic approach for hazard detection mapping based on deep learning. A low-cost mobile LiDAR scanner was used to obtain full-width as-is conditions of sidewalks, after method developed convert the scanned 3D point clouds into 2D RGB orthoimages elevation images. Then, learning-based model pixelwise segmentation joints. Algorithms...
The aim of this paper is to advance understanding the value national address point databases in improving wildfire public safety U.S. begins with a review database evacuations. An introduction data presented by examining two datasets—the National Address Database and OpenAddresses project. We examine existing potential uses evacuation research practice. Specifically, we cover four primary applications: wildland-urban interface mapping, warnings/zoning, traffic simulation, house loss...
Legal judgment prediction (LJP) is a crucial task in legal intelligence to predict charges, law articles and terms of penalties based on case fact description texts. Although existing methods perform well, they still have many shortcomings. First, the significant limitations understanding long documents, especially those RNNs BERT. Secondly, are not good at solving problem similar charges do fully effectively integrate information articles. To address above problems, we propose novel LJP...