Machine Learning, Deep Learning, and Mathematical Models to Analyze Forecasting and Epidemiology of COVID-19: A Systematic Literature Review

Saleem, Farrukh; AL-Ghamdi, Abdullah S. AL-Malaise; Alassafi, Madini O.; AlGhamdi, Saad Abdulla

doi:10.3390/ijerph19095099

Cited by 30 publications

(23 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comparison between ML algorithms was also considered for the task of news topic classification [24] to study the different ML models. Many researchers have also carried out the works like detecting the disease, predicting the end of pandemic [25] and creating a decision support system [26] for Covid-19. Many authors have carried out the research on the features extraction from text and tried to establish how this will help in attaining the better accuracy [27][28][29].…”

Section: Literature Surveymentioning

confidence: 99%

BERT-Based Hybrid RNN Model for Multi-class Text Classification to Study the Effect of Pre-trained Word Embeddings

Shreyashree¹,

Sunagar²,

Rajarajeswari³

et al. 2022

IJACSA

View full text Add to dashboard Cite

Due to the Covid-19 pandemic which started in the year 2020, many nations had imposed lockdown to curb the spread of this virus. People have been sharing their experiences and perspectives on social media on the lockdown situation. This has given rise to increased number of tweets or posts on social media. Multi-class text classification, a method of classifying a text into one of the pre-defined categories, is one of the effective ways to analyze such data that is implemented in this paper. A Covid-19 dataset is used in this work consisting of fifteen predefined categories. This paper presents a multi-layered hybrid model, LSTM followed by GRU, to integrate the benefits of both the techniques. The advantages of word embeddings techniques like GloVe and BERT have been implemented and found that, for three epochs, the transfer learning based pre-trained BERThybrid model performs one percent better than GloVe-hybrid model but the state-of-the-art, fine-tuned BERT-base model outperforms the BERT-hybrid model by three percent, in terms of validation loss. It is expected that, over a larger number of epochs, the hybrid model might outperform the fine-tuned model.

show abstract

Section: Literature Surveymentioning

confidence: 99%

BERT-Based Hybrid RNN Model for Multi-class Text Classification to Study the Effect of Pre-trained Word Embeddings

Shreyashree¹,

Sunagar²,

Rajarajeswari³

et al. 2022

IJACSA

View full text Add to dashboard Cite

show abstract

“…These questions were framed by considering the demands of research questions. The quality assessment questions framework has already been used in several earlier SLRs (Hassan et al, 2022, Haafza et al, 2021, Saleem et al, 2022. In this SLR, we have considered six questions that demand objectivity: the topic's context, data sources, limitations or gaps, discussion of future directions, and performance evaluation criteria used in the selected studies.…”

Section: Quality Assessmentmentioning

confidence: 99%

“…An optimized Fuzzy time series (FTS) using the Partial Swarm Optimisation (PSO) algorithm(Kennedy & Eberhart, 1997) was proposed in [P29] to improve the accuracy of the model signi cantly. The time series models given in the selected articles are mentioned in (Table6).Numerous research has presented various COVID-19 prediction models; however, deep learning models are now the ones that the international scienti c community nds most intriguing(Saleem et al, 2022). Different DL methods have been adopted for the prediction of the COVID-19 outbreak, which showed high accuracy.…”

mentioning

confidence: 99%

A sytematic study of covid-19 prediction models of India

Yadav

Rana

2022

Preprint

View full text Add to dashboard Cite

Infecting billions of people and death of over 6.5 millions people and loss of economy across the world, this COVID-19 outbreak caused by SARS-COV-2 has uncover the poor health management in the large populated country like India. Therefore, there is a requirement of detailed study i.e. Systematic Literature Review(SLR) of existing models by analysing the predicting behaviour of epidemic which plays a vital role in controlling the spread in future. Our study considered prediction models of COVID-19 which includes case study of India using machine learning and deep learning. This study includes only scholarly peer-review research articles of two renowned databases, Web of Science and Scopus from 2020–2022. PRISMA(Preferred Reporting Items for Systematic Reviews and Meta Analysis) guidelines have used for results and discussion. Before screening 317 articles were reported and after screening, eligibility of inclusion/exclusion criteria, 51 research articles were included for the final study. This SLR examined articles thoroughly, identified different machine learning, deep learning prediction models, identified research gaps/limitations, future scopes, and examined different performance metrics used in these studies. An additional objective of this research is to identify limitations and future directions provided by each research article which were not covered in any SLR on COVID-19.

show abstract

“…[12] During the COVID-19 epidemics, more complex deep learning (DL) methods, including recurrent neural networks have been successfully applied for epidemiological trend forecasting. [13] ML/DL methods depend on the extraction of useful information from historical data sets. From within the univariate case-number time series, additional useful information can usefully be recovered.…”

Section: Introductionmentioning

confidence: 99%

“…[12] During the COVID-19 epidemics, more complex deep learning (DL) methods, including recurrent neural networks have been successfully applied for epidemiological trend forecasting. [13]…”

Section: Introductionmentioning

confidence: 99%

Weeks-Ahead Epidemiological Predictions of Varicella Cases From Univariate Time Series Data Applying Artificial Intelligence

Wood¹

2023

Infect Dis Immun

View full text Add to dashboard Cite

Background “Chickenpox” is a highly infectious disease caused by the varicella-zoster virus, influenced by seasonal and spatial factors. Dealing with varicella-zoster epidemics can be a substantial drain on health-authority resources. Methods that improve the ability to locally predict case numbers from time-series data sets every week are therefore worth developing. Methods Simple-to-extract trend attributes from published univariate weekly case-number univariate data sets were used to generate multivariate data for Hungary covering 10 years. That attribute-enhanced data set was assessed by machine learning (ML) and deep learning (DL) models to generate weekly case forecasts from next week (t0) to 12 weeks forward (t+12). The ML and DL predictions were compared with those generated by multilinear regression and univariate prediction methods. Results Support vector regression generates the best predictions for weeks t0 and t+1, whereas extreme gradient boosting generates the best predictions for weeks t+3 to t+12. Long-short-term memory only provides comparable prediction accuracy to the ML models for week t+12. Multi–K-fold cross validation reveals that overall the lowest prediction uncertainty is associated with the tree-ensemble ML models. Conclusion The novel trend-attribute method offers the potential to reduce prediction errors and improve transparency for chickenpox time series.

show abstract

Machine Learning, Deep Learning, and Mathematical Models to Analyze Forecasting and Epidemiology of COVID-19: A Systematic Literature Review

Cited by 30 publications

References 82 publications

BERT-Based Hybrid RNN Model for Multi-class Text Classification to Study the Effect of Pre-trained Word Embeddings

BERT-Based Hybrid RNN Model for Multi-class Text Classification to Study the Effect of Pre-trained Word Embeddings

A sytematic study of covid-19 prediction models of India

Weeks-Ahead Epidemiological Predictions of Varicella Cases From Univariate Time Series Data Applying Artificial Intelligence

Contact Info

Product

Resources

About