A5043453718- Human Mobility and Location-Based Analysis
- Urban Transport and Accessibility
- Flood Risk Assessment and Management
- Data-Driven Disease Surveillance
- Disaster Management and Resilience
- Transportation Planning and Optimization
- Geographic Information Systems Studies
- Environmental Justice and Health Disparities
- Hydrological Forecasting Using AI
- Misinformation and Its Impacts
- Smart Cities and Technologies
- Evacuation and Crowd Dynamics
- Land Use and Ecosystem Services
- Remote-Sensing Image Classification
- Indoor and Outdoor Localization Technologies
- Privacy-Preserving Technologies in Data
- COVID-19 epidemiological studies
- Anomaly Detection Techniques and Applications
- Traffic and Road Safety
- Remote Sensing and Land Use
- Human Pose and Action Recognition
- Traffic Prediction and Management Techniques
- Complex Network Analysis Techniques
- Geochemistry and Geologic Mapping
- Tropical and Extratropical Cyclones Research
Texas A&M University
2023-2025
Mitchell Institute
2023-2025
Hong Kong Polytechnic University
2018-2024
State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing
2022-2024
Wuhan University
2022-2024
Nankai University
2022-2024
Peking University
2024
Coherent (United States)
2024
Guangdong-Hongkong-Macau Joint Laboratory of Collaborative Innovation for Environmental Quality
2023
Minzu University of China
2022
The coronavirus disease 2019 (COVID-19) has exposed and, to some degree, exacerbated social inequity in the United States. This study reveals correlation between demographic and socioeconomic variables home-dwelling time records derived from large-scale mobile phone location tracking data at U.S. census block group (CBG) level twelve most populated Metropolitan Statistical Areas (MSAs) further investigates contribution of these disparity that reflects compliance with stay-at-home orders via...
Social media platforms allow users worldwide to create and share information, forging vast sensing networks that information on certain topics be collected, stored, mined, analyzed in a rapid manner. During the COVID-19 pandemic, extensive social mining efforts have been undertaken tackle challenges from various perspectives. This review summarizes progress of data studies contexts categorizes them into six major domains, including early warning detection, human mobility monitoring,...
Abstract As COVID-19 spread around the world, epidemic prevention and control policies have been adopted by many countries. This process has prompted online social platforms to become important channels enable people socialize exchange information. The massive use of media data mining techniques, analyze development public opinion during epidemic, is great significance in relation management opinion. paper presents a study that aims developmental course terms fine-grained emotions presented...
Abstract Background The urban built environment (BE) has been globally acknowledged as one of the main factors that affects spread infectious disease. However, effect street network on coronavirus disease 2019 (COVID-19) incidence insufficiently studied. Severe acute respiratory syndrome 2, which causes COVID-19, is far more transmissible than previous viruses, such severe coronavirus, highlights role spatial configuration in COVID-19 spread, it where humans have contact with each other,...
Abstract Landscape ecological risk assessment (LERA) serves as a crucial tool for guiding effective environmental management. However, the conventional approach of LERA suffers from two notable drawbacks: utilization low‐resolution land‐use data (e.g., 30 × m) and application arbitrary evaluation units uniformly‐sized grids), both which introduce uncertainty inaccuracies into outcomes. Moreover, extent to traditional accurately reflects true level remains unexplored. To address these...
Climate hazards are escalating in frequency and severity, with flooding as a major threat. The limitations of the existing analytical necessitate computational tools for flood risk management necessitates shift towards more data-driven strategies informed by AI-driven methods. This paper explores forefront focusing on integrating artificial intelligence (AI), specifically machine learning (ML) deep (DL) technologies. By reviewing hundreds relevant studies, we present comprehensive analysis...
Motivated by the need for precise epidemic control and epidemic-resilient urban design, this study aims to reveal joint interactive associations between socioeconomic, density, connectivity, functionality characteristics COVID-19 spread within a high-density city. Many studies have been made on spread, but there is scarcity of such in intra-city scale as regards complex using advanced machine learning approaches.
Individuals' indoor trajectories can be reconstructed with sensing data for navigation. However, the movement uncertainty of such has seldom been modelled before, which seriously affects reliability trajectory analytics. Previous methods modelling mainly focus on outdoor trajectories, and are based various user-specified assumptions, may not hold effective environments hence introduce inaccuracy in determining sizes uncertain regions trajectories. To address above challenge, this research...
Modelling the movement uncertainty of crowdsourced human trajectories in complex urban areas is useful for various mobility analytics and applications. However, existing modelling approaches only consider largest distance or speed, fixed sampling measurement errors, resulting limited accuracy prediction. To fill this gap, paper presents a Bi-directional Long Short-Term Memory (Bi-LSTM) assisted framework under environments. The proposed adaptively integrates pedestrian motion detection...
Modelling pedestrian movement uncertainty in complex urban environments is regarded as a meaningful and challenging task regarding the promotion of geospatial data mining analysis. However, traditional prediction model only takes distance or speed into consideration not able to adapt well time-varying measurement errors. In this paper, deep-learning framework proposed for modelling large-scale indoor areas, which hybrid combines one-dimensional Convolutional Neural Network (1D-CNN) with long...
Standard environmental hazard exposure assessment methods have been primarily based on residential places, neglecting individuals' exposures due to activities outside home neighborhood and underestimating peoples' overall exposures. To address this limitation, study proposes a novel mobility-based index for the evaluation. Using large-scale human mobility data, we quantify extent of population dwell time in high places 239 US counties three hazards. We explore how extends reach hazards leads...
Various methods have been proposed to detect the base locations of individuals, with their geo-tagged social media data. However, a common challenge relating base-location detection (BDMs) is that, rare availability ground-truth data impedes method assessment accuracy and robustness, thus undermining research validity reliability. To address this challenge, we collect users' information from unstructured online content, evaluate both performance robustness BDMs. The evaluation consists two...
High-resolution remote sensing images usually contain multiscale information, which can be used to enhance the change detection (CD) performance. How make effective use of information needs intensive study. This letter presents a novel decision fusion (MDF) method for unsupervised CD based on Dempster–Shafer (DS) theory and modified conditional random field (CRF). The consists three main steps: 1) different scales are created automatically by image segmentation, then three-scale difference...
Volunteered geographic information can be used to predict regional desirability. A common challenge regarding previous works is that intuitive empirical models, which are inaccurate and bring in perceptual bias, traditionally This results from the fact hidden interactions between user online check-ins desirability have not been revealed clearly modelled yet. To solve problem, a novel neural network model 'RegNet' proposed. The check-in history input into encoder structure firstly for...
Remote sensing change detection (CD) plays an important role in Earth observation. In this paper, we propose a novel fusion approach for unsupervised CD of multispectral remote images, by introducing majority voting (MV) into fuzzy topological space (FTMV). The proposed FTMV consists three principal stages: (1) the results different difference images produced C-means algorithm are combined using modified MV, and initial map is obtained; (2) topology theory, automatically partitioned two...
Attractive regions can be detected and recommended by investigating users' online footprints. However, social media data suffers from short noisy text lack of a-priori knowledge, impeding the usefulness traditional semantic modelling methods. Another challenge is need for an effective strategy selection/recommendation candidate regions. To address these challenges, we propose a comprehensive workflow which combines location information to recommend thematic urban users with specific...
Change detection (CD) is one of the most important topics in remote sensing. In this paper, we propose a novel higher-order clique conditional random field model to unsupervised CD for sensing images (termed HOC2RF), by defining potential. The potential, constructed based on well-designed image objects, takes interaction between neighboring objects both feature and location spaces into account. HOC2RF consists five principle steps: (1) Two difference with complementary change information are...