Related references
Note: Only part of the references are listed.
Editorial Material
Medicine, General & Internal
Wafaa M. M. El-Sadr et al.
NEW ENGLAND JOURNAL OF MEDICINE
(2023)
Article
Automation & Control Systems
Luyu Zhou et al.
Summary: Whenever an epidemic of infectious illnesses breaks out, individuals in any country are badly impacted both economically and physically. In 2019, a novel coronavirus strain caused the outbreak of COVID-19, which was officially named by the WHO on February 11, 2020. The use of machine learning-informed models is currently a major focus in forecasting studies.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Biology
Katharine Sherratt et al.
Summary: This study reports on the performance of ensembles in predicting COVID-19 cases and deaths in Europe. The results show that combining multiple models into an ensemble can improve predictive performance, and the ensemble performs well in forecasting both cases and deaths. The findings suggest that using the median average as the ensemble method is more effective than using the mean. Overall, the study is rated 9 out of 10 in terms of importance.
Article
Computer Science, Artificial Intelligence
Hatice Vildan Dudukcu et al.
Summary: A hybrid deep neural network architecture is proposed for chaotic time series prediction, achieving the best prediction performance.
APPLIED SOFT COMPUTING
(2023)
Article
Medicine, General & Internal
Abdul Aziz K. Abdul Hamid et al.
Summary: Improving the accuracy and efficiency of time-series forecasts is crucial for authorities to predict and prevent the spread of the Coronavirus disease. The dataset contains both linear and non-linear patterns, which makes it inefficient to use linear models for prediction. A hybrid approach is proposed to achieve a more accurate and efficient predictive value of COVID-19.
Article
Haviluddin Haviluddin et al.
International Journal of Advances in Intelligent Informatics
(2023)
Article
Automation & Control Systems
A. Hasan et al.
Summary: This paper presents a data-driven approach for COVID-19 modeling and forecasting, which can be used by policymakers to control the outbreak through non-pharmaceutical interventions. The paper applies an extended Kalman filter to estimate the time-varying effective reproduction number and forecasts the effect of relaxing and tightening public measures. Case studies are provided to demonstrate the practicality of the approach.
Article
Chemistry, Analytical
Mario Munoz-Organero et al.
Summary: This paper proposes a new machine learning model that combines time pattern extraction and spatial analysis to optimize predictions of COVID-19 transmission. The model, which utilizes deep learning algorithms for data processing, achieves better results compared to previous models.
Article
Economics
Chiou-Jye Huang et al.
Summary: This paper introduces a novel deep neural network framework that accurately predicts the COVID-19 outbreak. The framework demonstrates higher accuracy compared to other models when applied to three severely affected European countries, and serves as an important reference for devising public health strategies. The study also reveals the high spatiotemporal relations of COVID-19, highlighting the need to maintain social distance and avoid unnecessary travel.
SOCIO-ECONOMIC PLANNING SCIENCES
(2022)
Article
Construction & Building Technology
Mohammad Shareef Ghanim et al.
Summary: This study developed an artificial neural network model to analyze the impact of implemented response measures on urban traffic flows. The results showed that the model accurately predicted traffic flows with good performance and could be generalized to predict demand levels in the post-pandemic era.
SUSTAINABLE CITIES AND SOCIETY
(2022)
Article
Engineering, Civil
Cunqi Shao et al.
Summary: Effectively predicting the evolution of COVID-19 is crucial for containing the pandemic. By utilizing digital trajectory data, we developed a method to estimate the impact of human mobility on the transmission of the disease and evaluate the effectiveness of non-pharmacological interventions through predicting epidemic situations. The results demonstrated that this approach can provide effective guidance for epidemic control.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Chemistry, Analytical
Ana Belen Rodriguez Gonzalez et al.
Summary: COVID-19 pandemic has significantly impacted public and private mobility in a mid-size city in Spain, resulting in a drastic decrease in travel volume. Analysis based on real data showed a clear change in user behavior during the pandemic, with public transport demand showing slower recovery compared to private transportation.
Article
Computer Science, Interdisciplinary Applications
Aoyong Li et al.
Summary: The study analyzed the changes in micro-mobility trip patterns during the pandemic, finding that the number of trips significantly decreased during the lockdown period, with changes in trip times. The origin-destination pairs remained consistent, but the number of trips between each pair decreased due to the pandemic. Additionally, there was an increase in proportions of Home, Park, and Grocery activities, while Leisure and Shopping activities decreased during the lockdown period.
COMPUTERS ENVIRONMENT AND URBAN SYSTEMS
(2021)
Article
Computer Science, Interdisciplinary Applications
Abdelkader Dairi et al.
Summary: This study compared the performances of machine learning methods for COVID-19 transmission forecasting, revealing that hybrid deep learning models can efficiently predict COVID-19 cases. The research confirmed the superiority of deep learning models over baseline machine learning models, with LSTM-CNN showing the best performance with an averaged mean absolute percentage error of 3.718%.
JOURNAL OF BIOMEDICAL INFORMATICS
(2021)
Proceedings Paper
Computer Science, Hardware & Architecture
Necati Ayan et al.
Summary: This study aims to model and forecast the number of COVID-19 infections in the future using cellular network traffic data. By partnering with a major cellular network provider in Brazil, TIM Brazil, and analyzing network connections in Rio de Janeiro, a Markovian model was developed to capture individual mobility across municipalities. This model combined mobility characteristics and reported COVID-19 cases to predict future cases, outperforming a baseline linear regression model in terms of accuracy metrics such as RMSE and MAE.
2021 IFIP NETWORKING CONFERENCE AND WORKSHOPS (IFIP NETWORKING)
(2021)
Article
Mathematical & Computational Biology
Yifan Zhu et al.
Summary: Since December 2019, a novel strain of coronavirus (COVID-19) has caused a disease outbreak in China, infecting a large number of people and spreading globally. A statistical disease transmission model was used to estimate the transmissibility of the early-phase outbreak, with sensitivity analyses and evaluation of lockdown intervention efficacy.
STATISTICS IN BIOSCIENCES
(2021)
Article
Computer Science, Information Systems
Daniel Fryer et al.
Summary: The Shapley value has gained popularity in the XAI literature due to its solid theoretical foundation and its recent uses as a feature selection tool. However, its application in feature selection may face limitations as the axioms of the Shapley value might not align with the goals of feature selection.
Article
Immunology
Hien Lau et al.
JOURNAL OF MICROBIOLOGY IMMUNOLOGY AND INFECTION
(2020)
Article
Medicine, General & Internal
Dan Assaf et al.
INTERNAL AND EMERGENCY MEDICINE
(2020)
Article
Multidisciplinary Sciences
Fenglin Liu et al.
Article
Mathematics, Interdisciplinary Applications
Farah Shahid et al.
CHAOS SOLITONS & FRACTALS
(2020)
Article
Mathematics, Interdisciplinary Applications
Talha Burak Alakus et al.
CHAOS SOLITONS & FRACTALS
(2020)
Article
Mathematics, Applied
Abdelilah Kaddar et al.
NONLINEAR ANALYSIS-MODELLING AND CONTROL
(2011)