Classification of COVID-19 Symptoms Using Multilayer Perceptron

Nurulain Nusrah Mohd Azam; Mohd Arfian Ismail; Mohd Saberi Mohamad; Ashraf Osman Ibrahim; Shermina Jeba

doi:10.52866/ijcsm.2023.04.04.009

Authors

Nurulain Nusrah Mohd Azam Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah, 26600, Pekan, Malaysia. https://orcid.org/0000-0002-6374-3560
Mohd Arfian Ismail Faculty of Computing, Universiti Malaysia Pahang
Mohd Saberi Mohamad Health Data Science Lab, Department of Genetics and Genomics, College of Medicine and Health Sciences, United Arab Emirates University, P.O. Box 17666, Al Ain, Abu Dhabi, United Arab Emirates https://orcid.org/0000-0001-9557-8195
Ashraf Osman Ibrahim Creative Advanced Machine Intelligence Research Centre, Faculty of Computing and Informatics, Universiti Malaysia Sabah, Jalan UMS, 88400 Kota Kinabalu, Sabah, Malaysia. https://orcid.org/0000-0002-4977-0538
Shermina Jeba Department of Computing Muscat College Muscat,Oman. https://orcid.org/0000-0003-0489-5529

DOI:

https://doi.org/10.52866/ijcsm.2023.04.04.009

Keywords:

Multilayer Perceptron; Covid19; Artificial Neural Network; Machine Learning

Abstract

The COVID-19 virus had easily affected people worldwide through direct contact. Individuals
diagnosed with positive COVID-19 virus may be affected with many symptoms, such as fever, tiredness, dry cough,
difficulty in breathing, sore throat, chest pain, nasal congestion, runny nose, and diarrhea. An individual can also
be diagnosed with COVID-19 even when he does not have any symptoms or be in contact with an infected person.
Data classification was required due to the size of COVID-19 data that will be analyzed for future countermeasures
determination. Some problems in data classification occurred due to unorganized data, such as time consumption,
human error in complexity of symptom features and the diagnosis process data needed expert knowledge. This study
aimed to use the artificial neural network (ANN) approach, which was multilayer perceptron (MLP) to classify the
COVID-19 data by using patient symptom data. The MLP process involved data collection, data normalization, MLP
design, MLP training, testing, and MLP verification. From the experiments, the MLP method was able to obtain
an accuracy rate of 77.10%. In conclusion, the MLP method could classify the COVID-19 data and achieve a high
accuracy rate