Title
LSTM perfomance analysis for predictive models based on Covid-19 dataset
Date Issued
12 October 2020
Access level
open access
Resource Type
other
Author(s)
Cruz-Mendoza, Isac
Quevedo-Pulido, Jonathan
Adanaque-Infante, Luz
Publisher(s)
IEEE
Abstract
Within the large amount of data that can be processed with Neural Networks (NN), COVID-19 is leaving us a lot of information that is susceptible to be treated and set trends regarding the development of the disease in the country. The present work shows the implementation and the optimization of a Long Short-Term Memory (LSTM) Neural Network in two different simulation environments, with a dataset related to the number of infected people by COVID-19 in Peru, in order to optimize the prediction level on the number of infected people on following days.
Subjects
Publication version
Version of Record
Handle or URL
Resource of which it is part
2020 IEEE XXVII International Conference on Electronics, Electrical Engineering and Computing (INTERCON)
Sources of information:
Instituto Nacional de Investigación y Capacitación de Telecomunicaciones
Directorio de Producción CientÃfica