Temporal deep learning architecture for prediction of COVID-19 cases in India

Verma, Hanuman; Mandal, Suvra; Gupta, Akanksha

doi:10.1016/j.eswa.2022.116611

Cited by 46 publications

(27 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the proposed architecture, the Relu activation function used after each convolution operation is given in Eq. (14) [34] .

…”

Section: Methodsmentioning

confidence: 99%

“…In literature, it can be seen that many deep learning-based studies have been carried out for the diagnosis of Covid-19 with the help of radiological images [32] , [33] , [34] , [35] , [36] , [37] , [38] , [39] , [40] , [41] , [42] .…”

Section: Introductionmentioning

confidence: 99%

“…Verma et al. [34] proposed different models such as vanilla (vanilla) LSTM, stacked LSTM, ED_LSTM, BiLSTM, CNN, and hybrid CNN+LSTM model to capture the complex trend of the COVID-19 outbreak and perform the Covid-19 prediction. In another study by Khan et al.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detection of Covid-19 and other pneumonia cases from CT and X-ray chest images using deep learning based on feature reuse residual block and depthwise dilated convolutions neural network

Çelik

2023

Applied Soft Computing

View full text Add to dashboard Cite

“…In the proposed architecture, the Relu activation function used after each convolution operation is given in Eq. (14) [34] .

…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection of Covid-19 and other pneumonia cases from CT and X-ray chest images using deep learning based on feature reuse residual block and depthwise dilated convolutions neural network

Çelik

2023

Applied Soft Computing

View full text Add to dashboard Cite

“…The researchers use deep learning methods to model the temporal dependencies in timeseries data related to COVID-19. Recurrent neural networks (RNN) and their variants, such as Long short term memory (LSTM), Gated Recurrent Unit (GRU), and bidirectional LSTM networks are explored for modelling COVID-19 timeseries data [ 14 , 15 , 16 , 17 , 18 ]. In particular, Arko Barman in his study [ 19 ], proposed an LSTM model and comparatively analyzed its performance, using traditional ARIMA methods, for forecasting the number of confirmed COVID-19 cases.…”

Section: Related Workmentioning

confidence: 99%

COVID-19 Spatio-Temporal Evolution Using Deep Learning at a European Level

Kavouras

Kaselimi

Protopapadakis

et al. 2022

Sensors

View full text Add to dashboard Cite

COVID-19 evolution imposes significant challenges for the European healthcare system. The heterogeneous spread of the pandemic within EU regions elicited a wide range of policies, such as school closure, transport restrictions, etc. However, the implementation of these interventions is not accompanied by the implementation of quantitative methods, which would indicate their effectiveness. As a result, the efficacy of such policies on reducing the spread of the virus varies significantly. This paper investigates the effectiveness of using deep learning paradigms to accurately model the spread of COVID-19. The deep learning approaches proposed in this paper are able to effectively map the temporal evolution of a COVID-19 outbreak, while simultaneously taking into account policy interventions directly into the modelling process. Thus, our approach facilitates data-driven decision making by utilizing previous knowledge to train models that predict not only the spread of COVID-19, but also the effect of specific policy measures on minimizing this spread. Global models at the EU level are proposed, which can be successfully applied at the national level. These models use various inputs in order to successfully model the spatio-temporal variability of the phenomenon and obtain generalization abilities. The proposed models are compared against the traditional epidemiological and Autoregressive Integrated Moving Average (ARIMA) models.

show abstract

“…Following a similar methodology, in Ribeiro, da Silva, Mariani, and dos Santos Coelho (2020) , the predictive capacity of different machine learning regression models is measured using data from 10 Brazilian states. More complex models are used in Verma, Mandal, and Gupta (2022) for forecasting purposes, where long short-term memory (LSTM) recurrent neural networks are designed for predicting the contagion rate in 4 Indian states. Multiple regressors were applied in An et al (2020) to predict the risk of mortality using different characteristics of an infected person, concluding that variables such as advanced age or taking metformin are important predictors that influence the output probability.…”

Section: Introductionmentioning

confidence: 99%