Analysis of Spatial Spread Relationships of Coronavirus (COVID-19) Pandemic in the World using Self Organizing Maps

Melín, Patricia; Monica, Julio Cesar; Sánchez, Daniela; Castillo, Oscar

doi:10.1016/j.chaos.2020.109917

Cited by 144 publications

(113 citation statements)

References 24 publications

Supporting

Mentioning

108

Contrasting

Unclassified

Order By: Relevance

“…As future work, regarding the proposed hybrid modular ensemble neural network we envision that the integrator and aggregator need special attention and we plan to consider using type-2 fuzzy systems and the Sugeno integral to improve the results, as in the works Melin et al ( 2007 ),( 2012a , b ), Melin and Sánchez ( 2018 ), Sánchez et al ( 2017 ). We also plan to combine our method with recent proposed prediction approaches using fuzzy logic and the fractal dimension, like in Melin et al ( 2020a , b ).…”

Section: Discussionmentioning

confidence: 99%

RETRACTED ARTICLE: A new prediction approach of the COVID-19 virus pandemic behavior with a hybrid ensemble modular nonlinear autoregressive neural network

et al. 2020

Self Cite

View full text Add to dashboard Cite

We describe in this paper an approach for predicting the COVID-19 time series in the world using a hybrid ensemble modular neural network, which combines nonlinear autoregressive neural networks. At the level of the modular neural network, which is formed with several modules (ensembles in this case), the modules are designed to be efficient predictors for each country. In this case, an integrator is used to combine the outputs of the modules, in this way achieving the goal of predicting a set of countries. At the level of the ensembles, forming a part of the modular network, these are constituted by a set of modules, which are nonlinear autoregressive neural networks that are designed to be efficient predictors under particular conditions for each country. In each ensemble, the results of the modules are combined with an aggregator to achieve a better and improved result for the ensemble. Publicly available datasets of coronavirus cases around the globe from the last months have been used in the analysis. Interesting conclusions have been obtained that could be helpful in deciding the best strategies in dealing with this virus for countries in their fight against the coronavirus pandemic. In addition, the proposed approach could be helpful in proposing strategies for similar countries.

show abstract

Section: Discussionmentioning

confidence: 99%

RETRACTED ARTICLE: A new prediction approach of the COVID-19 virus pandemic behavior with a hybrid ensemble modular nonlinear autoregressive neural network

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Melin et al. [6] conducted a study to analyze the spatial evolution of coronavirus pandemic around the world using unsupervised neural network namely self-organizing maps. The researchers concluded that the clustering abilities of self-organizing maps enable to group countries based on COVID-19 confirmed cases.…”

Section: Introductionmentioning

confidence: 99%

Association between weather data and COVID-19 pandemic predicting mortality rate: Machine learning approaches

Malki

Atlam

Hassanien

et al. 2020

Chaos, Solitons & Fractals

195

129

View full text Add to dashboard Cite

Nowadays, a significant number of infectious diseases such as human coronavirus disease (COVID-19) are threatening the world by spreading at an alarming rate. Some of the literatures pointed out that the pandemic is exhibiting seasonal patterns in its spread, incidence and nature of the distribution. In connection to the spread and distribution of the infection, scientific analysis that answers the questions whether the next summer can save people from COVID-19 is required. Many researchers have been exclusively asked whether high temperature during summer can slow down the spread of the COVID-19 as it has with other seasonal flues. Since there are a lot of questions that are unanswered right now, and many mysteries aspects about the COVID-19 that is still unknown to us, in-depth study and analysis of associated weather features are required. Moreover, understanding the nature of COVID-19 and forecasting the spread of COVID-19 request more investigation of the real effect of weather variables on the transmission of the COVID-19 among people. In this work, various regressor machine learning models are proposed to extract the relationship between different factors and the spreading rate of COVID-19. The machine learning algorithms employed in this work estimate the impact of weather variables such as temperature and humidity on the transmission of COVID-19 by extracting the relationship between the number of confirmed cases and the weather variables on certain regions. To validate the proposed method, we have collected the required datasets related to weather and census features and necessary prepossessing is carried out. From the experimental results, it is shown that the weather variables are more relevant in predicting the mortality rate when compared to the other census variables such as population, age, and urbanization. Thus, from this result, we can conclude that temperature and humidity are important features for predicting COVID-19 mortality rate. Moreover, it is indicated that the higher the value of temperature the lower number of infection cases.

show abstract

“…Literature supports that some certain studies were carried out over different parts of the world regarding the analysis of COVID-19 spatially (Zhou et al 2020 ; Fan et al 2020 , Gatto et al 2020 , Murugesan et al 2020 ; Kamel-Boulos and Geraghty 2020 ; Meyer et al 2017 ; Mo et al 2020 ; Roy et al 2020 ). Particularly, a comprehensive study on the nature of spatial spreading, geospatial pattern of transmission, vulnerability, and risk level along with hot spots analysis of COVID-19 were not widely analyzed (Ramírez-Aldana et al 2020 ; Huang et al 2020 ; Jia et al 2020 ; Kang et al 2020 ; Melin et al 2020 ; Ghosh et al 2020 ; Mishra et al 2020 ; Acharya and Porwal 2020 ). Conversely, in case of Bangladesh, in-depth study of COVID-19 using geospatial approach was very rare (Sakamoto et al 2020 ; Masrur et al 2020 ) and which were available mostly epidemiological, temporal, and modelling based and some of those mainly highlighted the impacts of COVID-19 on the economy, society, health, and environment (Anwar et al 2020 ; Bodrud-Doza 2020 ; Hossain et al 2020 ; Jahan et al 2020 ; Khan et al 2020a , b ; Khan et al 2020a ; Zabir et al 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Geospatial modelling on the spread and dynamics of 154 day outbreak of the novel coronavirus (COVID-19) pandemic in Bangladesh towards vulnerability zoning and management approaches

Rahman

Islam

2020

Model. Earth Syst. Environ.

View full text Add to dashboard Cite

The novel COVID-19 is a worldwide transmitted pandemic and has received global attention. Since there is no effective medication yet, to minimize and control the transmission of the COVID-19, non-pharmaceutical interventions (NPIs) are followed globally. However, for the implementation of needful NPIs through effective management strategies and planning, space-time-based information on the nature, magnitude, pattern of transmission, hotspots, the potential risk factors, vulnerability, and risk level of the pandemic are important. Hence, this study was an attempt to in-depth assess and analyze the COVID-19 outbreak and transmission dynamics through space and time in Bangladesh using 154 day real-time epidemiological data series. District-level data were analyzed for the geospatial analysis and modelling using GIS. Getis-Ord Gi* statistics was applied for the hotspot analysis, and on the other hand, the analytical hierarchy process-based weighted sum method (AHP-WSM) was used for the modelling of vulnerability zoning of COVID-19. In Bangladesh, the status of the pandemic COVID-19 still is in exposure level. Disease transmitted at a high rate (20.37%), and doubling time of the cases were 11 days (latest week of the study period). The fatality rate was comparatively low (1.3%), and the recovery rate was about 57.50%. Geospatial analysis exhibits the disease propagates from the central parts, and Dhaka was the most exposed district followed by Chattogram, Narayanganj, Cumilla, and Bogra. A single strong clustering pattern in the central part, which spread out mainly to the southeastern part, was identified as a prime hotspot in both the cases and deaths distributions. Additionally, potential linkages between the transmission of disease and the selected factors that gear up the spreading of the disease were identified. The central, eastern, and southeastern parts were recognized as high vulnerable zone, and conversely, the western, southwestern , northwestern , and northeastern parts as medium vulnerable zone. The vulnerable zoning exercise made it possible to identify vulnerable areas with the different magnitude that require urgent intervention through proper management and action plan, and accordingly, comprehensive management strategies were anticipated. Thus, this study will be a useful guide towards understanding the space-time-based investigations and vulnerable area delineation of the COVID-19 and assist to formulate an effective management action plan to reduce and control the disease propagation and impacts. By appropriate adjustment of some factors with local relevance, COVID-19 vulnerability zoning derived here can be applied to other regions, and generally can be used for any other infectious disease. This method was applied at a regional scale, but the availability of larger scale data of the determining factors could be applied in small areas too, and accordingly, management strategies can be formulated.

show abstract

Analysis of Spatial Spread Relationships of Coronavirus (COVID-19) Pandemic in the World using Self Organizing Maps

Cited by 144 publications

References 24 publications

RETRACTED ARTICLE: A new prediction approach of the COVID-19 virus pandemic behavior with a hybrid ensemble modular nonlinear autoregressive neural network

RETRACTED ARTICLE: A new prediction approach of the COVID-19 virus pandemic behavior with a hybrid ensemble modular nonlinear autoregressive neural network

Association between weather data and COVID-19 pandemic predicting mortality rate: Machine learning approaches

Geospatial modelling on the spread and dynamics of 154 day outbreak of the novel coronavirus (COVID-19) pandemic in Bangladesh towards vulnerability zoning and management approaches

Contact Info

Product

Resources

About