Page 147 - IJEEE-2022-Vol18-ISSUE-1
P. 147
Atiyah & Thalij | 143
present accurate information to health care institutions and [8] Du, L., et al., "The spike protein of SARS-CoV—a
hospitals to accommodate as many COVID-19 patients as target for vaccine and therapeutic development", Nature
possible. This work aims to help professionals understand Reviews Microbiology, vol. 7, no. 3, pp.226-236, 2009.
the spread of COVID-19 around the world. The dataset was
obtained from the dataset website at Google. We performed [9] Bayat, V., et al., "A severe acute respiratory syndrome
a preprocessing to compensate for the missing values and coronavirus 2 (sars-cov-2) prediction model from standard
encoded the categorical data to convert it to numeric, as well laboratory tests", Clinical Infectious Diseases, vol. 73, no.
as analyzed the data to provide a visualization of it and a 9, pp.e2901-e2907, 2021.
feature scaling was made to match the dimensions of the
values in the data set to obtain an effective model to speed [10] Zhou, Y., et al., "A new predictor of disease severity in
up the computation process in the modules. The dataset was patients with COVID-19 in Wuhan", China. MedRxiv,
segmented into a set of trains of 80% and 20% for a set of 2020.
tests and eight algorithms (LR, GNB, RF, SGD, KNN, SVM,
XGBoost, and DT) were used, in the form of two models. [11] Atiyah, O.S. and S.H. Thalij, "Evaluation of COVID-
The algorithm's performance was evaluated, and the 19 Cases based on Classification Algorithms in Machine
outcome appeared that SGD is the best algorithm for Learning", Webology, vol. 19, no. 1, 2022.
classification with 99% of accuracy, and the execution time
was 0.01 sec. SGD was the least. [12] O. S. Atiyah, S.H.T., "Using Classification Algorithms
in Machine Learning for COVID-19 Cases Diagnosis",
ACKNOWLEDGMENT International Journal of Mechanical Engineering, vol. 7,
no. 1, pp.6472-6478, 2022.
I would like to extend my sincere appreciation and gratitude
to team that giving us a dataset of COVID-19 with quality as [13] https://www.kaggle.com / S % C3 % ADrio-Libanes/
well as my family and teachers for encouraging and covid19.
supporting every stage of life.
[14] Mahboob, T., S. Irfan, and A. Karamat, "A machine
CONFLICT OF INTEREST learning approach for student assessment in E-learning
using Quinlan's C4. 5", Naive Bayes and Random Forest
The authors have no conflict of relevant interest to this algorithms. in 2016 19th International Multi-Topic
article. Conference (INMIC). 2016.
REFERENCES [15] Bhandari, S., et al., "Logistic regression analysis to
predict mortality risk in COVID-19 patients from routine
[1] Abdulkareem, N.M., et al., "COVID-19 world hematologic parameters", Ibnosina Journal of Medicine
vaccination progress using machine learning classification and Biomedical Sciences, vol. 12, no. 2, 2020.
algorithms", Qubahan Academic Journal, vol. 1, no. 2,
pp.100-105, 2021. [16] LeCun, Y.A., et al., Efficient backprop, in Neural
networks: Tricks of the trade. 2012, Springer. p. 9-48.
[2] Abdulqader, D.M., A.M. Abdulazeez, and D.Q.
Zeebaree, "Machine learning supervised algorithms of [17] Samuel, J., et al., "Covid-19 public sentiment insights
gene selection: A review", Machine Learning, vol. 62, no. and machine learning for tweets classification",
3, 2020. Information, vol. 11, no. 6, 2020.
[3] Alsharif, M., et al., "Artificial intelligence technology [18] Wang, Y., et al., "A Comparative Assessment of Credit
for diagnosing COVID-19 cases: A review of substantial Risk Model Based on Machine Learning a case study of
issues", Eur. Rev. Med. Pharmacol. Sci, vol. 24, pp.9226- bank loan data", Procedia Computer Science, vol. 174,
9233, 2021. pp.141-149, 2020.
[4] Siddique, S. and J.C. Chow, "Machine learning in [19] Noori, N.A. and A.A. Yassin, "Towards for Designing
healthcare communication. Encyclopedia", vol. 1, no. 1, Intelligent Health Care System Based on Machine
pp.220-239, 2021. Learning", Iraqi Journal for Electrical & Electronic
Engineering, vol. 17, no. 2, 2021.
[5] Kumar, A., P.K. Gupta, and A. Srivastava, "A review of
modern technologies for tackling COVID-19 pandemic", [20] Lodhi, H., et al., "Text classification using string
Diabetes & Metabolic Syndrome: Clinical Research & kernels", in NIPS. 2000.
Reviews, vol. 14, no. 4, pp.569-573, 2020.
[21] Xu, Y., et al., "Research on a mixed gas classification
[6] Bao, Y., et al., "2019-nCoV epidemic: address mental algorithm based on extreme random tree", Applied
health care to empower society", The Lancet, vol. 395, no. Sciences, vol. 9, no. 9, 2019.
10224, pp.e37-e38, 2020.
[22] Piryonesi, S.M. and T.E. El-Diraby, "Role of data
[7] Sarwar, A., et al., "Diagnosis of diabetes type-II using analytics in infrastructure asset management: Overcoming
hybrid machine learning based ensemble model", data size and quality problems", Journal of Transportation
International Journal of Information Technology, vol. 12, Engineering, Part B: Pavements, vol. 146, no. 2, 2020.
no. 2, pp.419-428, 2020.
[23] Rokach, L. and O. Maimon, "Top-down induction of
decision trees classifiers-a survey", IEEE Transactions on
Systems, Man, and Cybernetics, Part C (Applications and
Reviews), vol. 35, no. 4, pp.476-487, 2005.
