Connect with us

Machine Learning

A new long short-term memory method to predict the spread of covid19

Published

on

A new long short-term memory method to predict the spread of covid19

As covid19 has posed a major threat to human health and the economy, it is necessary to take appropriate measures to control the pandemic. A long short-term memory (LSTM) network method has been proposed to forecast the spread of covid19 [1].

This method is proposed based on data obtained from New Zealand country, as it is the first country that has been able to completely contain the spread of covid19 and bring the daily cases to zero. This model is capable of predicting the estimated dates within which the spread of covid19 can be contained. The model was able to correctly predict the dates within which the spread of covid19 was contained in New Zealand.

It is based on a deep-learning approach that is a recurrent neural network with an LSTM layer. This network uses the information from the past using its memory cell that contains a memory gate, input gate, and a forget gate. In this network, there is a sequence input layer that is used to provide time-series input to the network. After that, there is an LSTM layer consisting of 150 hidden units that are determined experimentally. This layer predicts the future value at the next time step. This layer is followed by a fully connected layer and a regression layer at the output [1].

This model was tested on New Zealand data and predicted the containment of the spread of covid19 between 25th April and 15th May. As compared with the facts, New Zealand recorded its first zero cases on 13th May.

For more details, read here.


References

  1. Kumar, S., Sharma, R., Tsunoda, T. et al. (2021). Forecasting the spread of COVID-19 using LSTM network. BMC Bioinformatics 22, 316.

Dr. Muniba is a Bioinformatician based in New Delhi, India. She has completed her PhD in Bioinformatics from South China University of Technology, Guangzhou, China. She has cutting edge knowledge of bioinformatics tools, algorithms, and drug designing. When she is not reading she is found enjoying with the family. Know more about Muniba

Advertisement
Click to comment

You must be logged in to post a comment Login

Leave a Reply

Drug Discovery

CNN-DDI: A drug-drug interaction prediction method using convolutional neural networks

Published

on

cnnddi-drug drug interaction prediction

Drug-drug interaction (DDI) prediction is gaining much more interest in the drug development process and disease diagnosis. Recently, a novel algorithm is proposed based on convolutional neural networks (CNN). (more…)

Continue Reading

Algorithms

Prediction of biochemical reactions catalyzed by enzymes in humans

Published

on

There are many biological important enzymes which exist in the human body, one of them is Cytochrome P450 (CyP450) enzymes which are mostly considered in drug discovery due to their involvement in the majority (75%) of drug metabolism [1]. Therefore, various in-silico methods have been applied to predict the possible substrates of CyP 450 enzymes [2-4]. Recently, an in-silico model has been developed to predict the potential chemical reactions mediated by the enzymes present in humans including CyP450 enzymes [5]. (more…)

Continue Reading

Algorithms

Machine learning in prediction of ageing-related genes/proteins

Published

on

Ageing has a great impact on human health, when people’s age advance towards 80 years, approximately half of the proteins in the body get damaged through oxidation. The chemical degradations occurring in our body produce energy by the consumed food via oxidation in the presence of oxygen. (more…)

Continue Reading

LATEST ISSUE

ADVERT