EpiVECS: exploring spatiotemporal epidemiological data using cluster embedding and interactive visualization DOI Creative Commons
Lee Mason, Blánaid Hicks, Jonas S. Almeida

et al.

Scientific Reports, Journal Year: 2023, Volume and Issue: 13(1)

Published: Dec. 1, 2023

The analysis of data over space and time is a core part descriptive epidemiology, but the complexity spatiotemporal makes this challenging. There need for methods that simplify exploration such tasks as surveillance hypothesis generation. In paper, we use combined clustering dimensionality reduction (hereafter referred to 'cluster embedding' methods) spatially visualize patterns in epidemiological time-series data. We compare several cluster embedding techniques see which performs best along variety internal validation metrics. find based on k-means generally perform better than self-organizing maps real world data, with some minor exceptions. also introduce EpiVECS, tool allows user explore results using interactive visualization. EpiVECS available privacy preserving, in-browser open source web application at https://episphere.github.io/epivecs .

Language: Английский

Exploring criminal patterns in Pampanga: A spatiotemporal and classification study DOI

Julieta M. Umali,

John Paul P. Miranda

AIP conference proceedings, Journal Year: 2025, Volume and Issue: 3287, P. 030004 - 030004

Published: Jan. 1, 2025

Language: Английский

Citations

0
Future workspace needs flexibility and diversity: A machine learning-driven behavioural analysis of co-working space DOI Creative Commons
Jiayu Pan, Tze Yeung Cho, Maoran Sun

et al.

PLoS ONE, Journal Year: 2023, Volume and Issue: 18(10), P. e0292370 - e0292370

Published: Oct. 18, 2023

The future of workspace is significantly shaped by the advancements in technologies, changes work patterns and workers' desire for an improved well-being. Co-working space alternative solution, cost-effectiveness, opportunity diverse flexible design multi-use. This study examined human-centric choices using spatial temporal variation occupancy levels user behaviour a co-working London. Through machine-learning-driven analysis, we investigated time-dependent patterns, decompose usage, calculate seat utilisation identify hotspots. analysis incorporated large dataset sensor-detected data spanning 477 days, comprising more than 140 million (145×106) points. Additionally, on-site observations activities were recorded 13 days over year, with 110 time instances including 1000 snapshots occupants' activities, indoor environment, working preferences. Results showed that shared areas positioned near windows or open, connected visible locations are preferred utilised communication working, semi-enclosed on side less visibility higher privacy focused working. flexibility multi-use was most feature hybrid findings offer data-driven insights planning office spaces future, particularly context setups, hot-desking systems.

Language: Английский

Citations

9
A probabilistic spatio-temporal neural network to forecast COVID-19 counts DOI Creative Commons
Federico Ravenda, Mirko Cesarini, Stefano Peluso

et al.

International Journal of Data Science and Analytics, Journal Year: 2024, Volume and Issue: unknown

Published: March 21, 2024

Abstract Geo-referenced and temporal data are becoming more ubiquitous in a wide range of fields such as medicine economics. Particularly the realm medical research, spatio-temporal play pivotal role tracking understanding spread dynamics diseases, enabling researchers to predict outbreaks, identify hot spots, formulate effective intervention strategies. To forecast these types we propose Probabilistic Spatio-Temporal Neural Network that (1) estimates, with computational efficiency, models spatial components; (2) combines flexibility Network—which is free from distributional assumptions—with uncertainty quantification probabilistic models. Our architecture compared established INLA method, well other baseline models, on COVID-19 Italian regions. empirical analysis demonstrates superior predictive effectiveness our method across multiple ranges offers insights for shaping targeted health interventions

Language: Английский

Citations

2
Spatiotemporal hierarchical Bayesian analysis to identify factors associated with COVID-19 in suburban areas in Colombia DOI Creative Commons
Javier Cortés-Ramírez, Juan D. Wilches-Vega, Beatriz Caicedo-Velásquez

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(9), P. e30182 - e30182

Published: April 24, 2024

The pandemic had a profound impact on the provision of health services in Cúcuta, Colombia where neighbourhood-level risk Covid-19 has not been investigated. Identifying sociodemographic and environmental factors large cities is key to better estimate its morbidity support strategies targeting specific suburban areas. This study aims identify associated with Cúcuta considering inter -spatial temporal variations disease city's neighbourhoods between 2020 2022.

Language: Английский

Citations

2
A spatio-temporal model for binary data and its application in analyzing the direction of COVID-19 spread DOI

Anagh Chattopadhyay,

Soudeep Deb

AStA Advances in Statistical Analysis, Journal Year: 2024, Volume and Issue: 108(4), P. 823 - 851

Published: July 8, 2024

Language: Английский

Citations

2
Adaptive Gaussian Markov random field spatiotemporal models for infectious disease mapping and forecasting DOI Open Access
Ying C. MacNab

Spatial Statistics, Journal Year: 2023, Volume and Issue: 53, P. 100726 - 100726

Published: Jan. 21, 2023

Language: Английский

Citations

6
Socioeconomic disparities and concentration of the spread of the COVID-19 pandemic in the province of Quebec, Canada DOI Creative Commons
Gabrielle Lefebvre, Slim Haddad,

Dominique Moncion-Groulx

et al.

BMC Public Health, Journal Year: 2023, Volume and Issue: 23(1)

Published: June 6, 2023

Abstract Background Recent studies suggest that the risk of SARS-CoV-2 infection may be greater in more densely populated areas and cities with a higher proportion persons who are poor, immigrant, or essential workers. This study examines spatial inequalities exposure health region province Quebec Canada. Methods The was conducted on 1206 Canadian census dissemination Capitale-Nationale Quebec. observation period 21 months (March 2020 to November 2021). number cases reported daily each area identified from available administrative databases. magnitude estimated using Gini Foster-Greer-Thorbecke (FGT) indices. association between transmission socioeconomic deprivation based concentration socially disadvantaged nonparametric regressions relating cumulative incidence rate by ecological indicators disadvantage. Quantification median family income degree supplemented an ordered probit multiple regression model. Results Spatial disparities were elevated (Gini = 0.265; 95% CI [0.251, 0.279]). spread limited less City agglomeration outlying municipalities. mean subsample made up most exposed pandemic 0.093. epidemic concentrated areas, especially areas. Socioeconomic inequality appeared early increased successive wave. models showed economically populations three times likely among at highest for COVID-19 (RR 3.55; [2.02, 5.08]). In contrast, population (fifth quintile) two 0.52; [0.32, 0.72]). Conclusion As H1N1 pandemics 1918 2009, revealed social vulnerabilities. Further research is needed explore various manifestations relation pandemic.

Language: Английский

Citations

5
Waves in time, but not in space – an analysis of pandemic severity of COVID-19 in Germany DOI Creative Commons
Andreas Kuebart, Martin Stabler

Spatial and Spatio-temporal Epidemiology, Journal Year: 2023, Volume and Issue: 47, P. 100605 - 100605

Published: July 17, 2023

While pandemic waves are often studied on the national scale, they typically not distributed evenly within countries. This study presents a novel approach to analyzing spatial-temporal dynamics of COVID-19 in Germany. By using composite indicator severity and subdividing into fifteen phases, we were able identify similar trajectories among all German counties through hierarchical clustering. Our results show that hotspots cold spots first four relatively stationary space. highlights importance examining regional scale gain more comprehensive understanding their dynamics. combining spatial autocorrelation clustering time series, important patterns anomalies, which can help target effective public health interventions scale.

Language: Английский

Citations

4
Exploration of spatiotemporal heterogeneity and socio-demographic determinants on COVID-19 incidence rates in Sarawak, Malaysia DOI Creative Commons
Piau Phang, Jane Labadin, Jamaludin Suhaila

et al.

BMC Public Health, Journal Year: 2023, Volume and Issue: 23(1)

Published: July 20, 2023

Abstract Background In Sarawak, 252 300 coronavirus disease 2019 (COVID-19) cases have been recorded with 1 619 fatalities in 2021, compared to only 117 2020. Since Sarawak is geographically separated from Peninsular Malaysia and half of its population resides rural districts where medical resources are limited, the analysis spatiotemporal heterogeneity incidence rates their relationship socio-demographic factors crucial understanding spread Sarawak. Methods The spatial dependence district-wise investigated using autocorrelation two orders contiguity weights for various pandemic waves. Nine determinants chosen 14 covariates via elastic net regression recursive partitioning. relationships between examined ordinary least squares, lag error models, weighted regression. Results first 8 months COVID-19 severely affected Sarawak’s central region, which was followed by southern region next 2 months. third wave, based on second-order weights, rate a district most strongly influenced neighboring districts’ rate, although variance best explained local coefficient estimates wave. It discovered that percentage households garbage collection facilities, density proportion male positively associated increase rates. Conclusion This research provides useful insights State Government public health authorities critically incorporate characteristics communities into evidence-based decision-making altering monitoring response plans. Policymakers can make well-informed judgments implement targeted interventions having an in-depth patterns characteristics. will effectively help mitigating disease.

Language: Английский

Citations

4
Sensitivity Analysis on Hyperprior Distribution of the Variance Components of Hierarchical Bayesian Spatiotemporal Disease Mapping DOI Creative Commons
I Gede Nyoman Mindra Jaya, Farah Kristiani, Yudhie Andriyana

et al.

Mathematics, Journal Year: 2024, Volume and Issue: 12(3), P. 451 - 451

Published: Jan. 31, 2024

Spatiotemporal disease mapping modeling with count data is gaining increasing prominence. This approach serves as a benchmark in developing early warning systems for diverse types. modeling, characterized by its inherent complexity, integrates spatial and temporal dependency structures, well interactions between space time. A Bayesian employing hierarchical structure solution model inference, addressing the identifiability problem often encountered when utilizing classical approaches like maximum likelihood method. However, faces significant challenge determining hyperprior distribution variance components of spatiotemporal models. Commonly used distributions include logGamma log inverse variance, Half-Cauchy, Penalized Complexity, Uniform hyperparameter standard deviation. While relatively straightforward faster computing times, it highly sensitive to changes values, specifically scale shape. research aims identify most optimal parameters under various conditions autocorrelation, observation units, through Monte Carlo study. Real on dengue cases West Java are utilized alongside simulation results. The findings indicate that, across different conditions, proves be choice.

Language: Английский

Citations

1