A model based on cellular automata for investigating the impact of lockdown, migration and vaccination on COVID-19 dynamics

Neural-SEIR: A flexible data-driven framework for precise prediction of epidemic disease

Accurately modeling and predicting epidemic diseases is crucial to prevent disease transmission and reduce mortality. Due to various unpredictable factors, including population migration, vaccination, control efforts, and seasonal fluctuations, traditional epidemic models that rely on prior knowledge of virus transmission mechanisms may not be sufficient to forecast complex epidemics like coronavirus disease 2019(COVID-19). The application of traditional epidemiological models such as susceptible-exposed-infectious-recovered (SEIR) may face difficulties in accurately predicting such complex epidemics. Data-driven prediction approaches lack the ability to generalize and exhibit low accuracy on small datasets due to their reliance on large amounts of data without incorporating prior knowledge. To overcome this limitation, we introduce a flexible ensemble data-driven framework (Neural-SEIR) that "neuralizes" the SEIR model by approximating the core parameters through neural networks while preserving the propagation structure of SEIR. Neural-SEIR employs long short-term memory (LSTM) neural network to capture complex correlation features, exponential smoothing (ES) to model seasonal information, and prior knowledge from SEIR. By incorporating SEIR parameters into the neural network structure, Neural-SEIR leverages prior knowledge while updating parameters with real-world data. Our experimental results demonstrate that Neural-SEIR outperforms traditional machine learning and epidemiological models, achieving high prediction accuracy and efficiency in forecasting epidemic diseases.

Simulation and forecasting models of COVID-19 taking into account spatio-temporal dynamic characteristics: A review

The COVID-19 epidemic has caused more than 6.4 million deaths to date and has become a hot topic of interest in different disciplines. According to bibliometric analysis, more than 340,000 articles have been published on the COVID-19 epidemic from the beginning of the epidemic until recently. Modeling infectious diseases can provide critical planning and analytical tools for outbreak control and public health research, especially from a spatio-temporal perspective. However, there has not been a comprehensive review of the developing process of spatio-temporal dynamic models. Therefore, the aim of this study is to provide a comprehensive review of these spatio-temporal dynamic models for dealing with COVID-19, focusing on the different model scales. We first summarized several data used in the spatio-temporal modeling of the COVID-19, and then, through literature review and summary, we found that the existing COVID-19 spatio-temporal models can be divided into two categories: macro-dynamic models and micro-dynamic models. Typical representatives of these two types of models are compartmental and metapopulation models, cellular automata (CA), and agent-based models (ABM). Our results show that the modeling results are not accurate enough due to the unavailability of the fine-grained dataset of COVID-19. Furthermore, although many models have been developed, many of them focus on short-term prediction of disease outbreaks and lack medium- and long-term predictions. Therefore, future research needs to integrate macroscopic and microscopic models to build adaptive spatio-temporal dynamic simulation models for the medium and long term (from months to years) and to make sound inferences and recommendations about epidemic development in the context of medical discoveries, which will be the next phase of new challenges and trends to be addressed. In addition, there is still a gap in research on collecting fine-grained spatial-temporal big data based on cloud platforms and crowdsourcing technologies to establishing world model to battle the epidemic.

Cellular automata in the light of COVID-19

Currently, the world has been facing the brunt of a pandemic due to a disease called COVID-19 for the last 2 years. To study the spread of such infectious diseases it is important to not only understand their temporal evolution but also the spatial evolution. In this work, the spread of this disease has been studied with a cellular automata (CA) model to find the temporal and the spatial behavior of it. Here, we have proposed a neighborhood criteria which will help us to measure the social confinement at the time of the disease spread. The two main parameters of our model are (i) disease transmission probability (q) which helps us to measure the infectivity of a disease and (ii) exponent (n) which helps us to measure the degree of the social confinement. Here, we have studied various spatial growths of the disease by simulating this CA model. Finally we have tried to fit our model with the COVID-19 data of India for various waves and have attempted to match our model predictions with regards to each wave to see how the different parameters vary with respect to infectivity and restrictions in social interaction.

A GIS-aided cellular automata system for monitoring and estimating graph-based spread of epidemics

In this study, we introduce an application of a Cellular Automata (CA)-based system for monitoring and estimating the spread of epidemics in real world, considering the example of a Greek city. The proposed system combines cellular structure and graph representation to approach the connections among the area's parts more realistically. The original design of the model is attributed to a classical SIR (Susceptible-Infected-Recovered) mathematical model. Aiming to upgrade the application's effectiveness, we have enriched the model with parameters that advances its functionality to become self-adjusting and more efficient of approaching real situations. Thus, disease-related parameters have been introduced, while human interventions such as vaccination have been represented in algorithmic manner. The model incorporates actual geographical data (GIS, geographic information system) to upgrade its response. A methodology that allows the representation of any area with given population distribution and geographical data in a graph associated with the corresponding CA model for epidemic simulation has been developed. To validate the efficient operation of the proposed model and methodology of data display, the city of Eleftheroupoli, in Eastern Macedonia-Thrace, Greece, was selected as a testing platform (Eleftheroupoli, Kavala). Tests have been performed at both macroscopic and microscopic levels, and the results confirmed the successful operation of the system and verified the correctness of the proposed methodology.

There exists the "smartest" movement rate to control the epidemic rather than "city lockdown"

The emergency outbreak and spread of coronavirus disease 2019 (COVID-19) has left great damage to individuals over most of the world. Population mobility is the primary reason for the spread of the epidemic. A delayed stochastic epidemic susceptible-infected-recovered (SIR) model with Gaussian white noise is introduced. Compared with traditional models,this model is characterized by time delay, environmental noise and population mobility among municipalities with the convenient transportation network. The stochastic dynamic behavior of the SIR model is analyzed and the existence of the stochastic bifurcation of the system is proved. The effect of time delay and movement rate are investigated. Numerical simulations are performed to support the theoretical results. It is worth mentioning that the movement rate is not as low as possible and appropriate population mobility is conducive to alleviating the epidemic. Through simulation, we demonstrate the existence of the best movement rate named the "smartest" κ , which is helpful to control the epidemic. This model is also useful to prevent other infectious diseases.

The Assessment of COVID-19 Vulnerability Risk for Crisis Management

The subject of this article is to determine COVID-19 vulnerability risk and its change over time in association with the state health care system, turnover, and transport to support the crisis management decision-making process. The aim was to determine the COVID-19 Vulnerability Index (CVI) based on the selected criteria. The risk assessment was carried out with methodology that includes the application of multicriteria analysis and spatiotemporal aspect of available data. Particularly the Spatial Multicriteria Analysis (SMCA) compliant with the Analytical Hierarchy Process (AHP), which incorporated selected population and environmental criteria were used to analyse the ongoing pandemic situation. The influence of combining several factors in the pandemic situation analysis was illustrated. Furthermore, the static and dynamic factors to COVID-19 vulnerability risk were determined to prevent and control the spread of COVID-19 at the early stage of the pandemic situation. As a result, areas with a certain level of risk in different periods of time were determined. Furthermore, the number of people exposed to COVID-19 vulnerability risk in time was presented. These results can support the decision-making process by showing the area where preventive actions should be considered.

Computational and Mathematical Methods in Medicine Prediction of COVID-19 in BRICS Countries: An Integrated Deep Learning Model of CEEMDAN-R-ILSTM-Elman

Since the outbreak of COVID-19, BRICS countries have experienced different epidemic spread due to different health conditions, social isolation measures, vaccination rates, and other factors. A descriptive analysis is conducted for the spread of the epidemic in the BRICS countries. Considering the nonlinear and nonstationary characteristics of COVID-19 data, a principle of decomposition-reconstruction(R)-prediction-integration is proposed. Correspondingly, this paper constructs an integrated deep learning prediction model of CEEMDAN-R-ILSTM-Elman. Specifically, the prediction model is integrated by complete ensemble empirical mode decomposition (CEEMDAN), improved long-term and short-term memory network (ILSTM), and Elman neural network. First, the data is decomposed by adopting CEEMDAN. Then, by calculating the permutation entropy and average period, the decomposed eigenmode component IMFs are reconstructed into four sequences of high, medium, low level, and trend term. Thus, ILSTM and Elman algorithms are used for component sequence prediction, whose results are integrated as the final results. The ILSTM is established based on the LSTM model and the improved beetle antennae search algorithm (IBAS). The ILSTM mainly considers that the prediction accuracy of LSTM model is vulnerable to the influence of parameter selection. The IBAS with adaptive step size is used to automatically optimize the super parameters of LSTM model and to improve the modeling efficiency and prediction accuracy. Experimental results indicate that compared with other benchmark models, CEEMDAN-R-ILSTM-Elman integrated model predicts the number of newly confirmed cases of COVID-19 in BRICS countries with higher accuracy and lower error. Strict social policies have a greater impact on the infection rate and mortality rate of the epidemic. During July-August 2021, epidemic spread in BRICS countries will slow down, and the overall situation is still quite severe.

A symbiosis between cellular automata and dynamic weighted multigraph with application on virus spread modeling

The pattern of coronavirus spread at different geographical scales verifies that travel or shipment by air, sea or road are potential to transmit viruses from one location to somewhere far away in a very short time. Simulation and analysis of such a situation requires the development of models that support long distance transmission of viruses. Cellular Automata (CA) are a family of spatiotemporal computational models frequently employed in analysis of biomedical systems. A CA consists of a topological combination of units called cells as well as a transition function that propagates the configuration of cells locally and step by step. In this paper, we first present some patterns that show the local interaction between CA cells is not sufficient for virus spread modeling, especially at large spatial scales. Then, we generalize the concept of CA by providing a symbiosis between the neighborhood relationship of cells and the transmission channels represented by a dynamic weighted multigraph. Furthermore, we characterize the capabilities of the proposed modeling tool in simulation of the virus spread, and estimating the risk control during the movement restrictions and related health protocols. Finally, we simulate the coronavirus outbreak in the five study areas including three states and two countries. Our experiments using the proposed model verify that the proposed model is capable of formulating different ways of virus transmission, including long-distance transmission, and supports high-precision simulation of the pandemic.