Analysis of COVID-19 cases in India through Machine Learning: A Study of Intervention

• URL: http://arxiv.org/abs/2008.10450v1
• Date: Mon, 17 Aug 2020 05:45:50 GMT
• Title: Analysis of COVID-19 cases in India through Machine Learning: A Study of Intervention
• Authors: Hanuman Verma, Akshansh Gupta and Utkarsh Niranjan
• Abstract summary: To combat the coronavirus disease 2019 (COVID-19) pandemic, the world has vaccination, plasma therapy, herd immunity, and epidemiological interventions as few possible options. In this work, we have suggested the SIR model with intervention, which incorporates the epidemiological interventions in the classical SIR model. We present predicted numbers of active and recovered COVID-19 cases till Sept 30, 2020, for entire India and some states of India and also estimate the 95% and 99% confidence interval for the predicted cases.
• Score: 3.4483987421251516
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To combat the coronavirus disease 2019 (COVID-19) pandemic, the world has vaccination, plasma therapy, herd immunity, and epidemiological interventions as few possible options. The COVID-19 vaccine development is underway and it may take a significant amount of time to develop the vaccine and after development, it will take time to vaccinate the entire population, and plasma therapy has some limitations. Herd immunity can be a plausible option to fight COVID-19 for small countries. But for a country with huge population like India, herd immunity is not a plausible option, because to acquire herd immunity approximately 67% of the population has to be recovered from COVID-19 infection, which will put an extra burden on medical system of the country and will result in a huge loss of human life. Thus epidemiological interventions (complete lockdown, partial lockdown, quarantine, isolation, social distancing, etc.) are some suitable strategies in India to slow down the COVID-19 spread until the vaccine development. In this work, we have suggested the SIR model with intervention, which incorporates the epidemiological interventions in the classical SIR model. To model the effect of the interventions, we have introduced \r{ho} as the intervention parameter. \r{ho} is a cumulative quantity which covers all type of intervention. We have also discussed the supervised machine learning approach to estimate the transmission rate (\b{eta}) for the SIR model with intervention from the prevalence of COVID-19 data in India and some states of India. To validate our model, we present a comparison between the actual and model-predicted number of COVID-19 cases. Using our model, we also present predicted numbers of active and recovered COVID-19 cases till Sept 30, 2020, for entire India and some states of India and also estimate the 95% and 99% confidence interval for the predicted cases.

Related papers

• Dense Feature Memory Augmented Transformers for COVID-19 Vaccination Search Classification [60.49594822215981]
  This paper presents a classification model for detecting COVID-19 vaccination related search queries. We propose a novel approach of considering dense features as memory tokens that the model can attend to. We show that this new modeling approach enables a significant improvement to the Vaccine Search Insights (VSI) task.
  arXiv  Detail & Related papers  (2022-12-16T13:57:41Z)
• Modeling the effect of the vaccination campaign on the Covid-19 pandemic [0.0]
  We introduce SAIVR, a mathematical model able to forecast the Covid-19 epidemic evolution during the vaccination campaign. The model contains several parameters and initial conditions that are estimated by employing a semi-supervised machine learning procedure. 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.
  arXiv  Detail & Related papers  (2021-08-27T19:12:13Z)
• Understanding the Spread of COVID-19 Epidemic: A Spatio-Temporal Point Process View [44.67854875502783]
  Since first coronavirus case was identified in the U.S. on Jan. 21, more than 1 million people in the U.S. have confirmed cases of COVID-19. This infectious respiratory disease has spread rapidly across more than 3000 counties and 50 states in the U.S. It is essential to understand the complex spacetime intertwined propagation of this disease so that accurate prediction or smart external intervention can be carried out.
  arXiv  Detail & Related papers  (2021-06-24T15:26:46Z)
• STELAR: Spatio-temporal Tensor Factorization with Latent Epidemiological Regularization [76.57716281104938]
  We develop a tensor method to predict the evolution of epidemic trends for many regions simultaneously. STELAR enables long-term prediction by incorporating latent temporal regularization through a system of discrete-time difference equations. We conduct experiments using both county- and state-level COVID-19 data and show that our model can identify interesting latent patterns of the epidemic.
  arXiv  Detail & Related papers  (2020-12-08T21:21:47Z)
• Steering a Historical Disease Forecasting Model Under a Pandemic: Case of Flu and COVID-19 [75.99038202534628]
  We propose CALI-Net, a neural transfer learning architecture which allows us to'steer' a historical disease forecasting model to new scenarios where flu and COVID co-exist. Our experiments demonstrate that our approach is successful in adapting a historical forecasting model to the current pandemic.
  arXiv  Detail & Related papers  (2020-09-23T22:35:43Z)
• VacSIM: Learning Effective Strategies for COVID-19 Vaccine Distribution using Reinforcement Learning [6.167847933188907]
  VacSIM is a novel pipeline that dovetails Deep Reinforcement Learning models into a Contextual Bandits approach for optimizing the distribution of COVID-19 vaccine. We evaluate this framework against a naive allocation approach of distributing vaccine proportional to the incidence of COVID-19 cases in five different States across India.
  arXiv  Detail & Related papers  (2020-09-14T17:37:13Z)
• Projections for COVID-19 spread in India and its worst affected five states using the Modified SEIRD and LSTM models [3.0507203596180488]
  This paper proposes a Modified SEIRD (Susceptible-Exposed-Infected-Recovered-Deceased) model for projecting COVID-19 infections in India. The projections obtained from the proposed Modified SEIRD model have also been compared with the projections made by LSTM for next 30 days. The results presented in this paper will act as a beacon for future policy-making to control the COVID-19 spread in India.
  arXiv  Detail & Related papers  (2020-09-07T07:38:10Z)
• COVID-19 Pandemic Outbreak in the Subcontinent: A data-driven analysis [0.8057708414390126]
  COVID-19 virus emerged in late December 2019 in Wuhan city, Hubei, China. Numerous studies claim that the subcontinent could remain in the worst affected region by the COVID-19. This paper uses publicly available epidemiological data of Bangladesh, India, and Pakistan to estimate the reproduction numbers.
  arXiv  Detail & Related papers  (2020-08-22T10:40:17Z)
• Understanding the temporal evolution of COVID-19 research through machine learning and natural language processing [66.63200823918429]
  The outbreak of the novel coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been continuously affecting human lives and communities around the world. We used multiple data sources, i.e., PubMed and ArXiv, and built several machine learning models to characterize the landscape of current COVID-19 research. Our findings confirm the types of research available in PubMed and ArXiv differ significantly, with the former exhibiting greater diversity in terms of COVID-19 related issues.
  arXiv  Detail & Related papers  (2020-07-22T18:02:39Z)
• Cross-lingual Transfer Learning for COVID-19 Outbreak Alignment [90.12602012910465]
  We train on Italy's early COVID-19 outbreak through Twitter and transfer to several other countries. Our experiments show strong results with up to 0.85 Spearman correlation in cross-country predictions.
  arXiv  Detail & Related papers  (2020-06-05T02:04:25Z)
• A kinetic model for qualitative understanding and analysis of the effect of complete lockdown imposed by India for controlling the COVID-19 disease spread by the SARS-CoV-2 virus [0.0]
  The present ongoing global pandemic caused by SARS-CoV-2 virus is creating havoc across the world. The Union Government of India made an announcement of unprecedented complete lockdown of the entire country effective from the next day. This study aims to scientifically analyze the implications of this decision using a kinetic model covering more than 96% of Indian territory.
  arXiv  Detail & Related papers  (2020-04-12T19:34:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.