Predicting the transmission trend of respiratory viruses in new regions via geospatial similarity learning

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2023, Volume and Issue: 125, P. 103559 - 103559

Published: Nov. 16, 2023

The outbreak and spread of COVID-19 remind us again the devastating attack that human-to-human transmitted respiratory infectious diseases (H-HRIDs) bring to global economics public health. Predicting trend H-HRIDs yields important suggestions for making response strategies. Existing methods predict future based on prophase epidemiological data. However, it is also crucial potential in regions without data those with available. This prediction can provide constructive pharmaceutical strategies non-pharmaceutical interventions such as pre-allocating limited preventions different trends, especially at early stage an H-HRID. In this paper, transform problem predicting early-stage H-HRID new into learning regions' geospatial features via a Contrastive learning-based Hierarchical Graph Convolutional Neural Network (CHGCN). Specifically, CHGCN first generates training from available Relaxed Edit Distance (RGED) algorithm. then uses schema learn region embeddings, where similar trends exhibit embeddings. Once trained, searches has highest embedding similarity given query data, so achieve region. Experimental results demonstrate proposed achieves state-of-the-art performance H-HRIDs, compared baselines.

Language: Английский

---

Assessing the impact of urban amenities on people with disabilities in London: A multiscale geographically weighted regression analysis

Habitat International, Journal Year: 2025, Volume and Issue: 161, P. 103426 - 103426

Published: May 1, 2025

Language: Английский

---

The Networked Community of Urban Mobility during the Pandemic

Annals of the American Association of Geographers, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 14

Published: Jan. 19, 2024

The COVID-19 pandemic has altered urban mobility patterns as various travel restrictions were imposed at different stages of the pandemic. Such dynamics inevitably affect structure spatial interactions underlying disease spreading. Understanding interaction and its is crucial for control. Through detecting networked communities, we identified latent movement boundaries emerged from actual human flows. We analyzed intra- intercommunity flows that not only capture regional cross-region structures but also facilitate expansion relocation diffusion processes. Networks representing four snapshots (prepandemic, lockdown, transition, normal) analyzed. intracommunity flow intensities indicated similar across snapshots, suggesting relative stability local throughout study period. analysis showed changes within city, signifying dynamic cross-regions Analyzing network provided a more holistic understanding during pandemic, highlighting potential This framework can be used management strategies simulation future mobility-related planning.

Language: Английский

---

Using spatial big data to analyse neighbourhood effects on immigrant inclusion and well-being

International Journal of Intercultural Relations, Journal Year: 2024, Volume and Issue: 102, P. 102020 - 102020

Published: July 26, 2024

Language: Английский

---