Download PDFOpen PDF in browser

COVID-19 Prediction through CNN and LSTM Deep Learning Models

EasyChair Preprint no. 8007

7 pagesDate: May 22, 2022

Abstract

The advances in the medical field have been
crucial for the purpose of attaining the improvement in the
the health of the masses. A healthy populous for a nation has
the ability to achieve the goals of productivity while
reducing the efforts to combat the spread of diseases and
other communicable ailments. If the majority of the
individuals are healthy and have a healthy lifestyle, it
would be far easier to recover from a pandemic and also
achieve effective realizations that can be useful in
achieving the growth and advancements far more
efficiently. The recent pandemic is a testament to this fact,
the Covid-19 virus has led to the largescale deaths and
destruction across the world. This pandemic could have
been better handled if the healthcare sector had an idea
about the scale and the severity of the pandemic which
would let them be effectively-prepared in response to the
increasing infections. The progression of a pandemic is
extremely complicated which can only be predicted using
machine-learning implementations. For this purpose, this
research article deploys Pearson correlation and K Nearest
Neighbor clustering along with the Convolutional Neural
Networks and Decision Tree for precise Covid-19
predictions. The experimental outcomes have proved the
improvement offered by the presented approach over
conventional implementations.

Keyphrases: Convolution Neural Network, COVID-19 prediction, K- Nearest neighbor Classifications, LSTM, Pearson correlation

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@Booklet{EasyChair:8007,
  author = {Vishal Shinde and Nagaraju Bogiri},
  title = {COVID-19 Prediction through CNN and LSTM Deep Learning Models},
  howpublished = {EasyChair Preprint no. 8007},

  year = {EasyChair, 2022}}
Download PDFOpen PDF in browser