Using discrete wavelet transform for optimizing COVID-19 new cases and deaths prediction worldwide with deep neural networks
This work aims to compare deep learning models designed to predict daily number of cases and deaths caused by COVID-19 for 183 countries, using a daily basis time series, in addition to a feature augmentation strategy based on Discrete Wavelet Transform (DWT). The following deep learning architectur...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2023-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10079093/?tool=EBI |
| _version_ | 1797850300383494144 |
|---|---|
| author | Erick Giovani Sperandio Nascimento Júnia Ortiz Adhvan Novais Furtado Diego Frias |
| author_facet | Erick Giovani Sperandio Nascimento Júnia Ortiz Adhvan Novais Furtado Diego Frias |
| author_sort | Erick Giovani Sperandio Nascimento |
| collection | DOAJ |
| description | This work aims to compare deep learning models designed to predict daily number of cases and deaths caused by COVID-19 for 183 countries, using a daily basis time series, in addition to a feature augmentation strategy based on Discrete Wavelet Transform (DWT). The following deep learning architectures were compared using two different feature sets with and without DWT: (1) a homogeneous architecture containing multiple LSTM (Long-Short Term Memory) layers and (2) a hybrid architecture combining multiple CNN (Convolutional Neural Network) layers and multiple LSTM layers. Therefore, four deep learning models were evaluated: (1) LSTM, (2) CNN + LSTM, (3) DWT + LSTM and (4) DWT + CNN + LSTM. Their performances were quantitatively assessed using the metrics: Mean Absolute Error (MAE), Normalized Mean Squared Error (NMSE), Pearson R, and Factor of 2. The models were designed to predict the daily evolution of the two main epidemic variables up to 30 days ahead. After a fine-tuning procedure for hyperparameters optimization of each model, the results show a statistically significant difference between the models’ performances both for the prediction of deaths and confirmed cases (p-value<0.001). Based on NMSE values, significant differences were observed between LSTM and CNN+LSTM, indicating that convolutional layers added to LSTM networks made the model more accurate. The use of wavelet coefficients as additional features (DWT+CNN+LSTM) achieved equivalent results to CNN+LSTM model, which demonstrates the potential of wavelets application for optimizing models, since this allows training with a smaller time series data. |
| first_indexed | 2024-04-09T18:58:51Z |
| format | Article |
| id | doaj.art-68638e5c6eb64bbc89d39e5c448b990d |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-09T18:58:51Z |
| publishDate | 2023-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-68638e5c6eb64bbc89d39e5c448b990d2023-04-09T05:32:15ZengPublic Library of Science (PLoS)PLoS ONE1932-62032023-01-01184Using discrete wavelet transform for optimizing COVID-19 new cases and deaths prediction worldwide with deep neural networksErick Giovani Sperandio NascimentoJúnia OrtizAdhvan Novais FurtadoDiego FriasThis work aims to compare deep learning models designed to predict daily number of cases and deaths caused by COVID-19 for 183 countries, using a daily basis time series, in addition to a feature augmentation strategy based on Discrete Wavelet Transform (DWT). The following deep learning architectures were compared using two different feature sets with and without DWT: (1) a homogeneous architecture containing multiple LSTM (Long-Short Term Memory) layers and (2) a hybrid architecture combining multiple CNN (Convolutional Neural Network) layers and multiple LSTM layers. Therefore, four deep learning models were evaluated: (1) LSTM, (2) CNN + LSTM, (3) DWT + LSTM and (4) DWT + CNN + LSTM. Their performances were quantitatively assessed using the metrics: Mean Absolute Error (MAE), Normalized Mean Squared Error (NMSE), Pearson R, and Factor of 2. The models were designed to predict the daily evolution of the two main epidemic variables up to 30 days ahead. After a fine-tuning procedure for hyperparameters optimization of each model, the results show a statistically significant difference between the models’ performances both for the prediction of deaths and confirmed cases (p-value<0.001). Based on NMSE values, significant differences were observed between LSTM and CNN+LSTM, indicating that convolutional layers added to LSTM networks made the model more accurate. The use of wavelet coefficients as additional features (DWT+CNN+LSTM) achieved equivalent results to CNN+LSTM model, which demonstrates the potential of wavelets application for optimizing models, since this allows training with a smaller time series data.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10079093/?tool=EBI |
| spellingShingle | Erick Giovani Sperandio Nascimento Júnia Ortiz Adhvan Novais Furtado Diego Frias Using discrete wavelet transform for optimizing COVID-19 new cases and deaths prediction worldwide with deep neural networks PLoS ONE |
| title | Using discrete wavelet transform for optimizing COVID-19 new cases and deaths prediction worldwide with deep neural networks |
| title_full | Using discrete wavelet transform for optimizing COVID-19 new cases and deaths prediction worldwide with deep neural networks |
| title_fullStr | Using discrete wavelet transform for optimizing COVID-19 new cases and deaths prediction worldwide with deep neural networks |
| title_full_unstemmed | Using discrete wavelet transform for optimizing COVID-19 new cases and deaths prediction worldwide with deep neural networks |
| title_short | Using discrete wavelet transform for optimizing COVID-19 new cases and deaths prediction worldwide with deep neural networks |
| title_sort | using discrete wavelet transform for optimizing covid 19 new cases and deaths prediction worldwide with deep neural networks |
| url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10079093/?tool=EBI |
| work_keys_str_mv | AT erickgiovanisperandionascimento usingdiscretewavelettransformforoptimizingcovid19newcasesanddeathspredictionworldwidewithdeepneuralnetworks AT juniaortiz usingdiscretewavelettransformforoptimizingcovid19newcasesanddeathspredictionworldwidewithdeepneuralnetworks AT adhvannovaisfurtado usingdiscretewavelettransformforoptimizingcovid19newcasesanddeathspredictionworldwidewithdeepneuralnetworks AT diegofrias usingdiscretewavelettransformforoptimizingcovid19newcasesanddeathspredictionworldwidewithdeepneuralnetworks |