DSpace Repository


Show simple item record

dc.contributor.author Bayat, Mohammad Nawid
dc.date.accessioned 2023-05-25T10:23:57Z
dc.date.available 2023-05-25T10:23:57Z
dc.date.issued 2023
dc.identifier.citation Bayat, M. N. (2023). Respond of Smart Cities to pandemic COVID-19. School of Engineering and Digital Sciences en_US
dc.identifier.uri http://nur.nu.edu.kz/handle/123456789/7080
dc.description.abstract Over the past several years, smart cities have gained widespread recognition worldwide because they facilitate a better life for people and bring substantial changes in society; more specifically, smart cities impact the lives of citizens amid the pandemic COVID-19. The COVID-19 epidemic has affected many elements of life, including economics, education, healthcare, politics, and financial planning. However, case studies of 120 cities have been examined concerning their responses to pandemics, the pillars of smart cities, and the number of COVID cases. The study investigates how pandemic preparedness in smart cities could be improved by stopping the spread of the virus, finding treatment (vaccine), and remotely providing education and business continuity. Smart city solutions are desperately needed to deal with the multiple challenges of controlling the COVID-19 epidemic. One of the approaches is to forecast the spread of the virus and its effects on various areas of urban life using machine-learning models. We can test the effectiveness of different regression models in both scenarios using a dataset that contains relevant variables for the COVID-19 and smart city pillars. The prognostic accuracy of the Elastic Regression, Ridge Regression, Lasso Regression, Random Forest Regression, and MLP Regression models for the prediction of COVID-19 infection rates based on smart city characteristics will be assessed in this way. The Random Forest Model outperformed Ridge Regression after adjusting model parameters and hidden layers (R-squared score 0.88 and 0.85, respectively). The MAE and MSE scores obtained using the Random Forest Regression technique are 0.009692 and 0.000261, respectively. On the other hand, the unsupervised ML Elbow technique separates the COVID data into five groups. The Elbow technique results in different records for each cluster, with the first cluster [0] including the most countries (171), the second and third clusters each comprising one country, the fourth cluster containing six countries, and the last cluster containing three countries. It explains why the majority of nations have comparable COVID-affected data and comparable pandemic prevention strategies and measures. The World Health Organization found that when cities and people had easier access to smart city features, the number of cases and deaths in each city reduced, while the rate of recovery and immunization climbed dramatically. Due to the limited data available, the acquired results do not confirm that each smart city responds to pandemics in the same way. en_US
dc.language.iso en en_US
dc.publisher School of Engineering and Digital Sciences en_US
dc.rights Attribution-NonCommercial-ShareAlike 3.0 United States *
dc.rights.uri http://creativecommons.org/licenses/by-nc-sa/3.0/us/ *
dc.subject Type of access: Embargo en_US
dc.subject IoT en_US
dc.subject Smart Sustainable Cities en_US
dc.subject Smart Technologies en_US
dc.subject Social Distancing en_US
dc.subject Facial Mask en_US
dc.subject Machine Learning en_US
dc.subject Remotely employment and learning en_US
dc.subject COVID-19 en_US
dc.subject Blockchain en_US
dc.type Master's thesis en_US
workflow.import.source science

Files in this item

The following license files are associated with this item:

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-ShareAlike 3.0 United States Except where otherwise noted, this item's license is described as Attribution-NonCommercial-ShareAlike 3.0 United States

Video Guide

Submission guideSubmission guide

Submit your materials for publication to

NU Repository Drive


My Account