WITHDRAWN: Recurrent neural network based prediction of number of COVID-19 cases in India
| Autor: | Ch. Mallikarjuna Rao, Y. C. A. Padmanabha Reddy, K. Shyam Sunder Reddy |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
010302 applied physics
2019-20 coronavirus outbreak Two parameter Artificial neural network Coronavirus disease 2019 (COVID-19) business.industry Computer science Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) 02 engineering and technology 021001 nanoscience & nanotechnology Machine learning computer.software_genre 01 natural sciences Recurrent neural network 0103 physical sciences Artificial intelligence 0210 nano-technology business computer |
| Zdroj: | Materials Today: Proceedings. |
| ISSN: | 2214-7853 |
| DOI: | 10.1016/j.matpr.2020.11.117 |
| Popis: | COVID-19 has become the most devastating disease of the current century and is pandemic. As per WHO report, there are globally 31,174,627 confirmed cases including 962,613 deaths as of 22nd September,2020. The disease is spreading through outbreaks despite the availability of latest technologies for treatment of patients. In this paper, we proposed a neural network-based prediction of number of cases in India due to COVID-19. Recurrent neural network (RNN) based LSTM is applied on India dataset for prediction. LSTM networks are a type of RNN capable of learning order dependence in sequence forecasting problems. We analyze the performance of the network and then compare it with two parameter reduced variants of LSTM, obtained by elimination of hidden unit signals, bias and input signal. For performance evaluation, we used the MSE measure. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect