A5059822985- Disaster Management and Resilience
- Public Relations and Crisis Communication
- Tropical and Extratropical Cyclones Research
- Evacuation and Crowd Dynamics
- Misinformation and Its Impacts
- Social Media and Politics
- Multimodal Machine Learning Applications
- Data-Driven Disease Surveillance
- Security and Verification in Computing
- Advanced Graph Neural Networks
- Petri Nets in System Modeling
- Topic Modeling
- Sentiment Analysis and Opinion Mining
- Smart Grid Security and Resilience
Emisphere Technologies (United States)
2024
Louisiana State University
2020-2024
Southwest Jiaotong University
2022
Louisiana State University Agricultural Center
2019
Despite the increasingly prominent role of social media in disaster events, studies analyzing its use rescue operations remain scanty. Hurricane Harvey hit Texas with unprecedented rainfall and flooding 2017 was marked by widespread for requests. We conducted a survey 195 Twitter users Houston surrounding communities who had requested during Harvey. The objective to investigate our targeted group's socioeconomic flood exposure characteristics, report effectiveness Twitter, highlight lessons...
This paper develops a social media-disaster resilience analysis framework by categorizing types of media use and their challenges to better understand assess its role in disaster research management. The is derived primarily from several case studies Twitter three hurricane events the United States – Hurricanes Isaac, Sandy, Harvey. first outlines four major contributions data for management, which include serving as an effective communication platform, providing ground truth information...
Disaster resilience is the capacity of a community to “bounce back” from disastrous events. Most studies rely on traditional data such as census study resilience. With increasing use social media, new sources Twitter could be utilized monitor human response during different phases disasters better understand An important research question is: Does correlate with disaster resilience? Specifically, will communities more disaster-related uses resilient disasters, presumably because they have...
Abstract Twitter can supply useful information on infrastructure impacts to the emergency managers during major disasters, but it is time consuming filter through many irrelevant tweets. Previous studies have identified types of messages that be found social media few solutions been proposed efficiently extract ones. We present a framework applied in timely manner provide disaster impact sourced from media. The tested well-studied and data-rich case Hurricane Harvey. procedures consist...
Disaster resilience describes the ability of a community to bounce back from disaster impacts by building activities. Social media provides an innovative way observe human attitudes and responses, especially during disasters. However, most previous social disasters studies were conducted at coarse spatial scale such as county. This study analyzes Twitter activities Hurricane Sandy in 2012, county zip code area levels five affected states. The examines two questions: (1) will relationships...
Abstract AI fairness is tasked with evaluating and mitigating bias in algorithms that may discriminate towards protected groups. This paper examines if exists used disaster management what manner. We consider the 2017 Hurricane Harvey when flood victims Houston resorted to social media request for rescue. evaluate a Random Forest regression model trained predict Twitter rescue rates from social-environmental data using three criteria (independence, separation, sufficiency). The Social...
The abundance of available information on social networks can provide invaluable insights into people's responses to health and public guidance concerning COVID-19. This study examines tweeting patterns engagement Twitter, as forms networks, related messaging in two U.S. states (Washington Louisiana) during the early stage pandemic. We analyze more than 7M tweets 571K COVID-19-related posted by users over first 25 days pandemic (Feb. 23, 2020, Mar. 18, 2020). also qualitatively code examine...
ABSTRACT The growing global interest in Geographic Information System/Science (GIS) programs has led to an increased demand for higher education this field. However, students often struggle identify suitable and faculty due the overwhelming options lack of personalized guidance. This paper presents GISphere‐KG, AI‐powered platform based on GISphere project. It combines knowledge graph (KG) large language models (LLMs) enhance search recommendation GIS‐related graduate programs. GISphere‐KG...
Lam, N.S.N.; Wang, K., and Mihunov, V., 2024. The Resilience Inference Measurement (RIM) approach to measuring predicting community resilience coastal hazards. In: Phillips, M.R.; Al-Naemi, S., Duarte, C.M. (eds.), Coastlines under Global Change: Proceedings from the International Coastal Symposium (ICS) 2024 (Doha, Qatar). Journal of Research, Special Issue No. 113, pp. 33-37. Charlotte (North Carolina), ISSN 0749-0208. Improving hazards has been a key societal issue studied widely by...
The development of networked communication not only brings convenience to communication, but also makes feed-back controlled systems exposed cyber-attack. In this work, we address the problem attack identification under various attacks in discrete event systems. A sensor attacker can modify output system while an actuator falsify control decisions sent from supervisor plant. Both them may be capable mislead into unsafe states. Our goal is determine whether based on observation produced by...