Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA self-supervised neural-analytic method to predict the evolution of COVID-19 in Romania
66
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Analysing and understanding the transmission and evolution of the COVID-19 pandemic is mandatory to be able to design the best social and medical policies, foresee their outcomes and deal with all the subsequent socio-economic effects. We address this important problem from a computational and machine learning perspective. More specifically, we want to statistically estimate all the relevant parameters for the new coronavirus COVID-19, such as the reproduction number, fatality rate or length of infectiousness period, based on Romanian patients, as well as be able to predict future outcomes. This endeavor is important, since it is well known that these factors vary across the globe, and might be dependent on many causes, including social, medical, age and genetic factors. We use a recently published improved version of SEIR, which is the classic, established model for infectious diseases. We want to infer all the parameters of the model, which govern the evolution of the pandemic in Romania, based on the only reliable, true measurement, which is the number of deaths. Once the model parameters are estimated, we are able to predict all the other relevant measures, such as the number of exposed and infectious people. To this end, we propose a self-supervised approach to train a deep convolutional network to guess the correct set of Modified-SEIR model parameters, given the observed number of daily fatalities. Then, we refine the solution with a stochastic coordinate descent approach. We compare our deep learning optimization scheme with the classic grid search approach and show great improvement in both computational time and prediction accuracy. We find an optimistic result in the case fatality rate for Romania which may be around 0.3% and we also demonstrate that our model is able to correctly predict the number of daily fatalities for up to three weeks in the future.
rate research
Read More
We studied the COVID-19 pandemic evolution in selected African countries. For each country considered, we modeled simultaneously the data of the active, recovered and death cases. In this study, we used a year of data since the first cases were reported. We estimated the time-dependent basic reproduction numbers, $R_0$, and the fractions of infected but unaffected populations, to offer insights into containment and vaccine strategies in African countries. We found that $R_0leq 4$ at the start of the pandemic but has since fallen to $R_0 sim 1$. The unaffected fractions of the populations studied vary between $1-10$% of the recovered cases.
The novel Coronavirus (COVID-19) incidence in India is currently experiencing exponential rise but with apparent spatial variation in growth rate and doubling time rate. We classify the states into five clusters with low to the high-risk category and study how the different states moved from one cluster to the other since the onset of the first case on $30^{th}$ January 2020 till the end of unlock 1 that is $30^{th}$ June 2020. We have implemented a new clustering technique called the incrementalKMN (Prasad, R. K., Sarmah, R., Chakraborty, S.(2019))
A pandemic caused by a new coronavirus (COVID-19) has spread worldwide, inducing an epidemic still active in Argentina. In this chapter, we present a case study using an SEIR (Susceptible-Exposed-Infected-Recovered) diffusion model of fractional order in time to analyze the evolution of the epidemic in Buenos Aires and neighboring areas (Region Metropolitana de Buenos Aires, (RMBA)) comprising about 15 million inhabitants. In the SEIR model, individuals are divided into four classes, namely, susceptible (S), exposed (E), infected (I) and recovered (R). The SEIR model of fractional order allows for the incorporation of memory, with hereditary properties of the system, being a generalization of the classic SEIR first-order system, where such effects are ignored. Furthermore, the fractional model provides one additional parameter to obtain a better fit of the data. The parameters of the model are calibrated by using as data the number of casualties officially reported. Since infinite solutions honour the data, we show a set of cases with different values of the lockdown parameters, fatality rate, and incubation and infectious periods. The different reproduction ratios R0 and infection fatality rates (IFR) so obtained indicate the results may differ from recent reported values, constituting possible alternative solutions. A comparison with results obtained with the classic SEIR model is also included. The analysis allows us to study how isolation and social distancing measures affect the time evolution of the epidemic.
The CoVid-19 is spreading pandemically all over the world. A rapid defeat of the pandemic requires carrying out on the population a mass screening, able to separate positive from negative cases. Such a cleaning will free a flow of productive population. The current rate and cost of testing, performed with the common PCR (polymerase chain reaction) method and with the available resources, is forcing a selection of the subjects to be tested. Indeed, each one must be examined individually at the cost of precious time. Moreover, the exclusion of potentially positive individuals from screening induces health risks, a broad slowdown in the effort to curb the viral spread, and the consequent mortality rates. We present a new procedure, the Purified by Unified Resampling of Infected Multitudes, in short Purim, able to untangle any massive candidate sample with inexpensive screening, through the cross-correlated analysis of the joint speciments. This procedure can reveal and detect most negative patients and in most cases discover the identity of the few positives already in the first or few secondary tests. We investigate the the two-dimensional correlation case in function of the infection probability. The multi-dimensional topology, the scaled Purim procedure are also considered. Extensive Purim tests may measure and weight the degree of epidemic: their outcome may identify focal regions in the early stages. Assuming hundreds or thousand subjects, the saving both in time and in cost will be remarkable. Purim may be able to filter scheduled flights, scholar acceptance, popular international event participants. The optimal extension of Purim outcome is growing as the inverse of the epidemia expansion. Therefore, the earlier, the better.
Population-wide vaccination is critical for containing the SARS-CoV-2 (Covid-19) pandemic when combined with restrictive and prevention measures. In this study, we introduce SAIVR, a mathematical model able to forecast the Covid-19 epidemic evolution during the vaccination campaign. SAIVR extends the widely used Susceptible-Infectious-Removed (SIR) model by considering the Asymptomatic (A) and Vaccinated (V) compartments. The model contains several parameters and initial conditions that are estimated by employing a semi-supervised machine learning procedure. After training an unsupervised neural network to solve the SAIVR differential equations, a supervised framework then estimates the optimal conditions and parameters that best fit recent infectious curves of 27 countries. Instructed by these results, we performed an extensive study on the temporal evolution of the pandemic under varying values of roll-out daily rates, vaccine efficacy, and a broad range of societal vaccine hesitancy/denial levels. The concept of herd immunity is questioned by studying future scenarios which involve different vaccination efforts and more infectious Covid-19 variants.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
