scholarly journals Forecasting Covid-19 Outbreak Progression in Italian Regions: A model based on neural network training from Chinese data

2020 ◽  
Author(s):  
Cosimo Distante ◽  
Igor Gadelha Pereira ◽  
Luiz M. Garcia Gonçalves ◽  
Prisco Piscitelli ◽  
Alessandro Miani
Keyword(s):  
Neural Network ◽  
Reproduction Number ◽  
National Level ◽  
Compartment Model ◽  
Epidemic Curve ◽  
Network Training ◽  
Italian Regions ◽  
Northern Regions ◽  
The Mean ◽  
Day By Day

AbstractBackgroundEpidemiological figures of Covid-19 epidemic in Italy are worse than those observed in China.MethodsWe modeled the Covid-19 outbreak in Italian Regions vs. Lombardy to assess the epidemics progression and predict peaks of new daily infections and total cases by learning from the entire Chinese epidemiological dynamics. We trained an artificial neural network model, a modified auto-encoder with Covid-19 Chinese data, to forecast epidemic curve of the different Italian regions, and use the susceptible–exposed–infected–removed (SEIR) compartment model to predict the spreading and peaks. We have estimated the basic reproduction number (R0) - which represents the average number of people that can be infected by a person who has already acquired the infection - both by fitting the exponential growth rate of the infection across a 1-month period, and also by using a day by day assessment, based on single observations.ResultsThe expected peak of SEIR model for new daily cases was at the end of March at national level. The peak of overall positive cases is expected by April 11th in Southern Italian Regions, a couple of days after that of Lombardy and Northern regions. According to our model, total confirmed cases in all Italy regions could reach 160,000 cases by April 30th and stabilize at a plateau.ConclusionsTraining neural networks on Chinese data and use the knowledge to forecast Italian spreading of Covid-19 has resulted in a good fit, measured with the mean average precision between official Italian data and the forecast.

scholarly journals Covid-19 Outbreak Progression in Italian Regions: Approaching the Peak by the End of March in Northern Italy and First Week of April in Southern Italy

2020 ◽  
Vol 17 (9) ◽  
pp. 3025 ◽  
Author(s):  
Cosimo Distante ◽  
Prisco Piscitelli ◽  
Alessandro Miani
Keyword(s):  
Growth Rate ◽  
National Level ◽  
Compartment Model ◽  
Campania Region ◽  
Chinese City ◽  
A Value ◽  
Italian Regions ◽  
Northern Regions ◽  
Heavy Burden ◽  
Day By Day

Epidemiological figures of the SARS-CoV-2 epidemic in Italy are higher than those observed in China. Our objective was to model the SARS-CoV-2 outbreak progression in Italian regions vs. Lombardy to assess the epidemic’s progression. Our setting was Italy, and especially Lombardy, which is experiencing a heavy burden of SARS-CoV-2 infections. The peak of new daily cases of the epidemic has been reached on the 29th, while was delayed in Central and Southern Italian regions compared to Northern ones. In our models, we estimated the basic reproduction number (R0), which represents the average number of people that can be infected by a person who has already acquired the infection, both by fitting the exponential growth rate of the infection across a 1-month period and also by using day-by-day assessments based on single observations. We used the susceptible–exposed–infected–removed (SEIR) compartment model to predict the spreading of the pandemic in Italy. The two methods provide an agreement of values, although the first method based on exponential fit should provide a better estimation, being computed on the entire time series. Taking into account the growth rate of the infection across a 1-month period, each infected person in Lombardy has involved 4 other people (3.6 based on data of April 23rd) compared to a value of R 0 = 2.68 , as reported in the Chinese city of Wuhan. According to our model, Piedmont, Veneto, Emilia Romagna, Tuscany and Marche will reach an R0 value of up to 3.5. The R0 was 3.11 for Lazio and 3.14 for the Campania region, where the latter showed the highest value among the Southern Italian regions, followed by Apulia (3.11), Sicily (2.99), Abruzzo (3.0), Calabria (2.84), Basilicata (2.66), and Molise (2.6). The R0 value is decreased in Lombardy and the Northern regions, while it is increased in Central and Southern regions. The expected peak of the SEIR model is set at the end of March, at a national level, with Southern Italian regions reaching the peak in the first days of April. Regarding the strengths and limitations of this study, our model is based on assumptions that might not exactly correspond to the evolution of the epidemic. What we know about the SARS-CoV-2 epidemic is based on Chinese data that seems to be different than those from Italy; Lombardy is experiencing an evolution of the epidemic that seems unique inside Italy and Europe, probably due to demographic and environmental factors.

scholarly journals Covid-19 Outbreak Progression in Italian Regions: Approaching the Peak by March 29th

2020 ◽  
Author(s):  
Cosimo Distante ◽  
Prisco Piscitelli ◽  
Alessandro Miani
Keyword(s):  
Growth Rate ◽  
National Level ◽  
Compartment Model ◽  
Campania Region ◽  
Lombardy Region ◽  
A Value ◽  
Italian Regions ◽  
Northern Regions ◽  
Heavy Burden ◽  
Day By Day

AbstractBackgroundItaly and especially the Lombardy region is experiencing a heavy burden of Covid-19 infection. The peak of the epidemics has not yet been reached and it is expected to be delayed in Central and Southern Italian regions compared to Northern ones. We have modeled the Covid-19 outbreak progression in Italian Regions vs. Lombardy.MethodsIn our models, we have estimated the basic reproduction number (R0) -which represents the average number of people that can be infected by a person who has already acquired the infection - both by fitting the exponential growth rate of the infection across a 1-month period and also by using day by day assessment, based on single observations. We used the susceptible–exposed–infected–removed (SEIR) compartment model to predict the spreading of the pandemic in Italy.ResultsThe two methods provide agreements of values, although the first method based on exponential fit should provide a better estimation, being computed on the entire time series. Taking into account the growth rate of the infection across a 1-month period, in Lombardy each infected person has involved other 5 people (4.94 base on data of March 22nd vs. 5.07 based on data of March 19th) compared to a value of R0 = 2.68 reported in the Chinese city of Whuan. According to our model and Piedmont, Veneto, Emilia Romagna, Tuscany and Marche reach an R0 value up to 4. The R0 is 3.7 for Lazio and 3.6 for Campania region, where this latter shows the highest value among the Southern Italian regions, followed by Apulia (3.5), Sicily (3.4), Abruzzo (3.4), Calabria (3.1), Basilicata (2.5) and Molise (2.4). The value of R0 is decreasing in Lombardy and Northern Regions, while it is increasing in Central and Southern Regions.ConclusionThe expected peak of SEIR model can be forecast by the last week of March at national level, and by the first weeks of April in Southern Italian Regions. These kind of models can be useful for adoption of all the possible preventive measures, and to assess the epidemics progression across Southern regions as opposed to the Northern ones.

scholarly journals Epidemic Big Bang: development and quarantine measures for Covid-19

2020 ◽  
Author(s):  
Sergey Trigger ◽  
Eugeny Czerniawski
Keyword(s):  
Statistical Data ◽  
Reproduction Number ◽  
Big Bang ◽  
Infected Person ◽  
Good Correspondence ◽  
Closed Population ◽  
Infinite Population ◽  
Duration Of Disease ◽  
The Mean ◽  
Day By Day

Abstract New discrete approximation for the infection spread is constructed based on COVID-19 epidemic data. We consider the epidemic as dependent upon four key parameters: the size of population involved, the mean number of dangerous contacts of one infected person per day, the probability to transmit infection due to such contact and the mean duration of disease. In the simplest case of free epidemic in an infinite population, the number of infected rises exponentially day by day. Here we show the model for epidemic process in a closed population, constrained by isolation, treatment and so on. The four parameters introduced here have the clear sense and are in association with the well-known concept of reproduction number in the continuous susceptible-infected-susceptible model. We derive these parameters from the adequate statistical data. On this basis, we also found the corresponding basic reproduction number mentioned above. Our approach allows evaluating the influence of quarantine measures on free pandemic process. We found a good correspondence of the theory and reliable statistical data. The model is quite flexible and it can be expanded for situations that are more complex.

scholarly journals Epidemiological characteristics of COVID-19 cases in Italy and estimates of the reproductive numbers one month into the epidemic

2020 ◽  
Author(s):  
Flavia Riccardo ◽  
Marco Ajelli ◽  
Xanthi D Andrianou ◽  
Antonino Bella ◽  
Martina Del Manso ◽  
...  
Keyword(s):  
National Level ◽  
Control Measures ◽  
Care Workers ◽  
Italian Regions ◽  
Northern Regions ◽  
Independent Risk Factors ◽  
The One ◽  
Net Reproduction ◽  
Epidemiological Characteristics ◽  
Older Males

SUMMARYBackgroundIn February 2020, a locally-acquired COVID-19 case was detected in Lombardia, Italy. This was the first signal of ongoing transmission of SARS-CoV-2 in the country. The outbreak rapidly escalated to a national level epidemic, amid the WHO declaration of a pandemic.MethodsWe analysed data from the national case-based integrated surveillance system of all RT-PCR confirmed COVID-19 infections as of March 24th 2020, collected from all Italian regions and autonomous provinces. Here we provide a descriptive epidemiological summary on the first 62,843 COVID-19 cases in Italy as well as estimates of the basic and net reproductive numbers by region.FindingsOf the 62,843 cases of COVID-19 analysed, 71.6% were reported from three Regions (Lombardia, Veneto and Emilia-Romagna). All cases reported after February 20th were locally acquired. Estimates of R0 varied between 2.5 (95%CI: 2.18-2.83) in Toscana and 3 (95%CI: 2.68-3.33) in Lazio, with epidemic doubling time of 3.2 days (95%CI: 2.3-5.2) and 2.9 days (95%CI: 2.2-4.3), respectively. The net reproduction number showed a decreasing trend starting around February 20-25, 2020 in Northern regions. Notably, 5,760 cases were reported among health care workers. Of the 5,541 reported COVID-19 associated deaths, 49% occurred in people aged 80 years or above with an overall crude CFR of 8.8%. Male sex and age were independent risk factors for COVID-19 death.InterpretationThe COVID-19 infection in Italy emerged with a clustering onset similar to the one described in Wuhan, China and likewise showed worse outcomes in older males with comorbidities. Initial R0 at 2.96 in Lombardia, explains the high case-load and rapid geographical spread observed. Overall Rt in Italian regions is currently decreasing albeit with large diversities across the country, supporting the importance of combined non-pharmacological control measures.Fundingroutine institutional funding was used to perform this work.

scholarly journals Epidemic transmission with quarantine measures: application to COVID-19

2021 ◽  
Author(s):  
S.A. Trigger ◽  
E.B. Czerniawski ◽  
A.M. Ignatov
Keyword(s):  
Differential Equations ◽  
Delay Differential Equations ◽  
Statistical Data ◽  
Reproduction Number ◽  
Good Correspondence ◽  
Closed Population ◽  
The Mean ◽  
Delay Differential ◽  
Day By Day ◽  
Infection Spread

Equations for infection spread in a closed population are found in discrete approximation, corresponding to the published statistical data, and in continuous time in the form of delay differential equations. We consider the epidemic as dependent upon four key parameters: the size of population involved, the mean number of dangerous contacts of one infected person per day, the probability to transmit infection due to such contact and the mean duration of disease. In the simplest case of free-running epidemic in an infinite population, the number of infected rises exponentially day by day. Here we show the model for epidemic process in a closed population, constrained by isolation, treatment and so on. The four parameters introduced here have the clear sense and are in association with the well-known concept of reproduction number in the continuous susceptible– infectious–removed, susceptible–exposed–infectious–removed (SIR, SEIR) models. We derive the initial rate of infection spread from the published statistical data for the initial stage of epidemic, when the quarantine measures were absent. On this basis, we can found the corresponding basic reproduction number mentioned above. Our approach allows evaluating the influence of quarantine measures on free pandemic process that leads to the time-dependent rate of infection and suppression of infection. We found a good correspondence of the theory and reliable statistical data. The initially formulated discrete model, describing epidemic course day by day is transferred to differential form. The conditions for saturation of epidemic are found by solving the delay differential equations. They differ essentially from ones in SIR model due to finite delay, typical for COVID-19 The proposed model opens up the possibility to predict the optimal level of social quarantine measures. The model is quite flexible and it can be extended to more complex cases.

scholarly journals Undocumented infectives in the Covid-19 pandemic

2020 ◽  
Author(s):  
Maurizio Melis ◽  
Roberto Littera
Keyword(s):  
Basic Reproduction Number ◽  
Preventive Measures ◽  
Reproduction Number ◽  
Sir Model ◽  
Mean Value ◽  
Careful Monitoring ◽  
Italian Regions ◽  
The Mean ◽  
Rapid Diffusion ◽  
The Basic Reproduction Number

Background. A crucial role in epidemics is played by the number of undetected infective individuals who continue to circulate and spread the disease. Epidemiological investigations and mathematical models have revealed that the rapid diffusion of Covid-19 can mostly be attributed to the large percentage of undocumented infective individuals who escape testing. Methods. The dynamics of an infection can be described by the SIR model, which divides the population into susceptible (S), infective (I) and removed (R) subjects. In particular, we exploited the Kermack and McKendrick epidemic model which can be applied when the population is much larger than the fraction of infected subjects. Results. We proved that the fraction of undocumented infectives, in comparison to the total number of infected subjects, is given by 1-1/R0 , where R0 is the basic reproduction number. The mean value R0=2.10 (2.09-2.11) in three Italian regions for the Covid-19 epidemic yielded a percentage of undetected infectives of 52.4% (52.2% - 52.6%) compared to the total number of infectives. Conclusions. Our results, straightforwardly obtained from the SIR model, highlight the role played by undetected carriers in the transmission and spread of the SARS-CoV-2 infection. Such evidence strongly recommends careful monitoring of the infective population and ongoing adjustment of preventive measures for disease control until a vaccine becomes available.

Pencarian Question-Answer Menggunakan Convolutional Neural Network Pada Topik Agama Berbahasa Indonesia

2018 ◽  
Vol 10 (1) ◽  
pp. 57-64 ◽  
Author(s):  
Rizqa Raaiqa Bintana ◽  
Chastine Fatichah ◽  
Diana Purwitasari
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Question Answering ◽  
Mean Average Precision ◽  
Average Precision ◽  
Community Based ◽  
Network Methods ◽  
The Mean ◽  
Index Terms ◽  
Search Information

Community-based question answering (CQA) is formed to help people who search information that they need through a community. One condition that may occurs in CQA is when people cannot obtain the information that they need, thus they will post a new question. This condition can cause CQA archive increased because of duplicated questions. Therefore, it becomes important problems to find semantically similar questions from CQA archive towards a new question. In this study, we use convolutional neural network methods for semantic modeling of sentence to obtain words that they represent the content of documents and new question. The result for the process of finding the same question semantically to a new question (query) from the question-answer documents archive using the convolutional neural network method, obtained the mean average precision value is 0,422. Whereas by using vector space model, as a comparison, obtained mean average precision value is 0,282. Index Terms—community-based question answering, convolutional neural network, question retrieval

Comparison of an Artificial Neural Network and a Multiple Linear Regression in Predicting the Heat of Combustion of Diesel Fuel Based on Hydrocarbon Groups

2020 ◽  
Vol 71 (6) ◽  
pp. 66-74
Author(s):  
Younis M. Younis ◽  
Salman H. Abbas ◽  
Farqad T. Najim ◽  
Firas Hashim Kamar ◽  
Gheorghe Nechifor
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Diesel Fuel ◽  
Back Propagation ◽  
Second Step ◽  
Heating Value ◽  
Network Training ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt ◽  
Propagation Network

A comparison between artificial neural network (ANN) and multiple linear regression (MLR) models was employed to predict the heat of combustion, and the gross and net heat values, of a diesel fuel engine, based on the chemical composition of the diesel fuel. One hundred and fifty samples of Iraqi diesel provided data from chromatographic analysis. Eight parameters were applied as inputs in order to predict the gross and net heat combustion of the diesel fuel. A trial-and-error method was used to determine the shape of the individual ANN. The results showed that the prediction accuracy of the ANN model was greater than that of the MLR model in predicting the gross heat value. The best neural network for predicting the gross heating value was a back-propagation network (8-8-1), using the Levenberg�Marquardt algorithm for the second step of network training. R = 0.98502 for the test data. In the same way, the best neural network for predicting the net heating value was a back-propagation network (8-5-1), using the Levenberg�Marquardt algorithm for the second step of network training. R = 0.95112 for the test data.

scholarly journals Birth prevalence of tetrahydrobiopterin deficiency in China: data from the national newborn screening program, 2013–2019

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Xuelian Yuan ◽  
Jun Zhu ◽  
Hanmin Liu ◽  
Liangcheng Xiang ◽  
Yongna Yao ◽  
...  
Keyword(s):  
Screening Program ◽  
National Level ◽  
Recall Rate ◽  
Birth Prevalence ◽  
Live Births ◽  
Provincial Level ◽  
Tetrahydrobiopterin Deficiency ◽  
Total Prevalence ◽  
Entire Country ◽  
Northern Regions

Abstract Background Tetrahydrobiopterin deficiency (BH4D), a less common form of hyperphenylalaninemia (HPA), can lead to severe developmental retardation if untreated. Little has been reported on the prevalence of BH4D among live births worldwide. This study examined its prevalence across China and between geographical areas within the country. Methods We analyzed data from the Chinese national screening program for HPA in newborns between 2013 and 2019. BH4D prevalence was examined by province, region and the entire country. Provincial-level prevalence was estimated from the number of confirmed BH4D cases and screened newborns, after adjusting for HPA-positive recall rate. Regional- and national-level prevalences were estimated by summing provincial-level prevalences after weighting them by the number of live births. A Poisson distribution was assumed in order to calculate 95% confidence intervals (CIs) for prevalence. Results Among 107,078,115 newborns screened for HPA in China, 380 with BH4D were identified, corresponding to a total prevalence of 3.8 per 1,000,000 live births. Prevalence was higher in eastern regions (5.9 per 1,000,000) and northern regions (4.1 per 1,000,000) of China than in southern regions (1.6 per 1,000,000) or northwestern regions (1.7 per 1,000,000). Across the entire country, 3.9% cases of HPA were diagnosed as BH4D, and this proportion reached as high as 15.1% in the southern part of the country. Conclusions These first insights into BH4D prevalence across China suggest slightly higher prevalence than in other countries, and it varies substantially by region. More attention should be paid to early diagnosis and timely treatment of BH4D.

Sign in / Sign up

Export Citation Format

Share Document