Prediction of COVID-19 epidemic situation via fine-tuned IndRNN

The COVID-19 pandemic is the most serious catastrophe since the Second World War. To predict the epidemic more accurately under the influence of policies, a framework based on Independently Recurrent Neural Network (IndRNN) with fine-tuning are proposed for predict the epidemic development trend of...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Zhonghua Hong, Ziyang Fan, Xiaohua Tong, Ruyan Zhou, Haiyan Pan, Yun Zhang, Yanling Han, Jing Wang, Shuhu Yang, Hong Wu, Jiahao Li
Formato: article
Lenguaje:EN
Publicado: PeerJ Inc. 2021
Materias:
Acceso en línea:https://doaj.org/article/29562d9c71404cce9b11fd09ac22caaf
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:29562d9c71404cce9b11fd09ac22caaf
record_format dspace
spelling oai:doaj.org-article:29562d9c71404cce9b11fd09ac22caaf2021-11-14T15:05:12ZPrediction of COVID-19 epidemic situation via fine-tuned IndRNN10.7717/peerj-cs.7702376-5992https://doaj.org/article/29562d9c71404cce9b11fd09ac22caaf2021-11-01T00:00:00Zhttps://peerj.com/articles/cs-770.pdfhttps://peerj.com/articles/cs-770/https://doaj.org/toc/2376-5992The COVID-19 pandemic is the most serious catastrophe since the Second World War. To predict the epidemic more accurately under the influence of policies, a framework based on Independently Recurrent Neural Network (IndRNN) with fine-tuning are proposed for predict the epidemic development trend of confirmed cases and deaths in the United Stated, India, Brazil, France, Russia, China, and the world to late May, 2021. The proposed framework consists of four main steps: data pre-processing, model pre-training and weight saving, the weight fine-tuning, trend predicting and validating. It is concluded that the proposed framework based on IndRNN and fine-tuning with high speed and low complexity, has great fitting and prediction performance. The applied fine-tuning strategy can effectively reduce the error by up to 20.94% and time cost. For most of the countries, the MAPEs of fine-tuned IndRNN model were less than 1.2%, the minimum MAPE and RMSE were 0.05%, and 1.17, respectively, by using Chinese deaths, during the testing phase. According to the prediction and validation results, the MAPEs of the proposed framework were less than 6.2% in most cases, and it generated lowest MAPE and RMSE values of 0.05% and 2.14, respectively, for deaths in China. Moreover, Policies that play an important role in the development of COVID-19 have been summarized. Timely and appropriate measures can greatly reduce the spread of COVID-19; untimely and inappropriate government policies, lax regulations, and insufficient public cooperation are the reasons for the aggravation of the epidemic situations. The code is available at https://github.com/zhhongsh/COVID19-Precdiction. And the prediction by IndRNN model with fine-tuning are now available online (http://47.117.160.245:8088/IndRNNPredict).Zhonghua HongZiyang FanXiaohua TongRuyan ZhouHaiyan PanYun ZhangYanling HanJing WangShuhu YangHong WuJiahao LiPeerJ Inc.articleCOVID-19Deep LearningPrediction ModelFine-tuningIndependently Recurrent Neural NetworkLong-Short-Term-MemoryElectronic computers. Computer scienceQA75.5-76.95ENPeerJ Computer Science, Vol 7, p e770 (2021)
institution DOAJ
collection DOAJ
language EN
topic COVID-19
Deep Learning
Prediction Model
Fine-tuning
Independently Recurrent Neural Network
Long-Short-Term-Memory
Electronic computers. Computer science
QA75.5-76.95
spellingShingle COVID-19
Deep Learning
Prediction Model
Fine-tuning
Independently Recurrent Neural Network
Long-Short-Term-Memory
Electronic computers. Computer science
QA75.5-76.95
Zhonghua Hong
Ziyang Fan
Xiaohua Tong
Ruyan Zhou
Haiyan Pan
Yun Zhang
Yanling Han
Jing Wang
Shuhu Yang
Hong Wu
Jiahao Li
Prediction of COVID-19 epidemic situation via fine-tuned IndRNN
description The COVID-19 pandemic is the most serious catastrophe since the Second World War. To predict the epidemic more accurately under the influence of policies, a framework based on Independently Recurrent Neural Network (IndRNN) with fine-tuning are proposed for predict the epidemic development trend of confirmed cases and deaths in the United Stated, India, Brazil, France, Russia, China, and the world to late May, 2021. The proposed framework consists of four main steps: data pre-processing, model pre-training and weight saving, the weight fine-tuning, trend predicting and validating. It is concluded that the proposed framework based on IndRNN and fine-tuning with high speed and low complexity, has great fitting and prediction performance. The applied fine-tuning strategy can effectively reduce the error by up to 20.94% and time cost. For most of the countries, the MAPEs of fine-tuned IndRNN model were less than 1.2%, the minimum MAPE and RMSE were 0.05%, and 1.17, respectively, by using Chinese deaths, during the testing phase. According to the prediction and validation results, the MAPEs of the proposed framework were less than 6.2% in most cases, and it generated lowest MAPE and RMSE values of 0.05% and 2.14, respectively, for deaths in China. Moreover, Policies that play an important role in the development of COVID-19 have been summarized. Timely and appropriate measures can greatly reduce the spread of COVID-19; untimely and inappropriate government policies, lax regulations, and insufficient public cooperation are the reasons for the aggravation of the epidemic situations. The code is available at https://github.com/zhhongsh/COVID19-Precdiction. And the prediction by IndRNN model with fine-tuning are now available online (http://47.117.160.245:8088/IndRNNPredict).
format article
author Zhonghua Hong
Ziyang Fan
Xiaohua Tong
Ruyan Zhou
Haiyan Pan
Yun Zhang
Yanling Han
Jing Wang
Shuhu Yang
Hong Wu
Jiahao Li
author_facet Zhonghua Hong
Ziyang Fan
Xiaohua Tong
Ruyan Zhou
Haiyan Pan
Yun Zhang
Yanling Han
Jing Wang
Shuhu Yang
Hong Wu
Jiahao Li
author_sort Zhonghua Hong
title Prediction of COVID-19 epidemic situation via fine-tuned IndRNN
title_short Prediction of COVID-19 epidemic situation via fine-tuned IndRNN
title_full Prediction of COVID-19 epidemic situation via fine-tuned IndRNN
title_fullStr Prediction of COVID-19 epidemic situation via fine-tuned IndRNN
title_full_unstemmed Prediction of COVID-19 epidemic situation via fine-tuned IndRNN
title_sort prediction of covid-19 epidemic situation via fine-tuned indrnn
publisher PeerJ Inc.
publishDate 2021
url https://doaj.org/article/29562d9c71404cce9b11fd09ac22caaf
work_keys_str_mv AT zhonghuahong predictionofcovid19epidemicsituationviafinetunedindrnn
AT ziyangfan predictionofcovid19epidemicsituationviafinetunedindrnn
AT xiaohuatong predictionofcovid19epidemicsituationviafinetunedindrnn
AT ruyanzhou predictionofcovid19epidemicsituationviafinetunedindrnn
AT haiyanpan predictionofcovid19epidemicsituationviafinetunedindrnn
AT yunzhang predictionofcovid19epidemicsituationviafinetunedindrnn
AT yanlinghan predictionofcovid19epidemicsituationviafinetunedindrnn
AT jingwang predictionofcovid19epidemicsituationviafinetunedindrnn
AT shuhuyang predictionofcovid19epidemicsituationviafinetunedindrnn
AT hongwu predictionofcovid19epidemicsituationviafinetunedindrnn
AT jiahaoli predictionofcovid19epidemicsituationviafinetunedindrnn
_version_ 1718429036813746176