Covid-19 Aşılama Sürecinin Tahminine Yönelik Derin Öğrenme Tabanlı Bir Model

Abstract

Covid-19 pandemisi, insanlığın son zamanlarda karşılaştığı en büyük zorluklardan biridir. Henüz tedavi edici bir ilaç geliştirilemediği için tüm dünyayı sosyal ve ekonomik anlamda olumsuz etkilemektedir. Covid-19’un etkilerini ve vücutta bıraktığı hasarı en aza indirmek için farklı aşı çalışmaları yapılmıştır. Dünya genelinde insanlar aşılanarak salgının seyri kontrol altına alınmaya çalışılmaktadır. Bu noktada kullanılacak günlük aşı miktarının belirlenmesi, ihtiyaç duyulacak aşı ve enjektör gibi malzemelerin miktarına ve bunlarla beraber sağlık hizmetlerinin planlanmasına kadar önemli birçok alanda belirleyici olacaktır. Bununla birlikte birçok araştırmacı, virüs yayılım modeli oluşturmak ve Covid-19'un gidişatını tahmin etmek için farklı tahmin yöntemleri önermiştir. Bunlar arasında yapay zekâya dayalı yöntemler en ilgi çekici ve yaygın olarak kullanılan yöntemlerdir. Bu çalışmada, dünyada en yüksek aşılama oranına sahip ilk 20 ülke için günlük yapılan aşı sayılarının tahmin edilmesi amaçlanmıştır. Bu amaçla DT, kNN, LR, RF, SVM, MLP, CNN, RNN ve geliştirilen LSTM tabanlı derin öğrenme modelinin karşılaştırmalı bir analizi sunulmuştur. Uygulanan modeller için RMSE, MAE ve R2 metriklerine göre elde edilen deneysel sonuçlar karşılaştırmalı olarak analiz edilmiştir. Deneysel sonuçlar, geliştirilen LSTM tabanlı modelin uygulanan ülkelerin tamamına yakınında 0.90’ın üzerinde R2 değerine sahip olduğunu göstermiştir

Keywords

• Aşı
• covid-19
• derin öğrenme
• LSTM
• makine öğrenmesi

A Deep Learning Based Prediction Model for Predicting the Covid-19 Vaccination Process

Abstract

The COVID-19 pandemic is one of the biggest challenges humanity has faced lately. As a therapeutic drug has not yet been developed, it negatively affects the entire world in social and economic terms. Various vaccine studies have been conducted to minimize the impact of COVID-19 and its harm to the body. People around the world are trying to control the course of the epidemic by vaccinating them. Determining the daily amount of vaccines to be used at this point will be decisive in important points such as the number of materials such as vaccines and injectors that will be needed, as well as the planning of health services. However, many researchers have proposed different predictive methods to build a model for the spread of the virus and predict the course of COVID-19. Of these, artificial intelligence methods are the most attractive and widely used. This study, it has been aimed to predict the number of daily vaccinations for the top 20 countries with the highest vaccination rate in the world. In this regard, a comparative analysis of DT, kNN, LR, RF, SVM, MLP, CNN, RNN, and the LSTM-based deep learning model was presented. The experimental results obtained according to the RMSE, MAE, and R2 metrics for the applied models have been analyzed comparatively. Experimental results showed that the developed LSTM-based model has an R2 value of over 0.90 in almost all of the applied countries.

Keywords

• Vaccine
• covid-19
• deep learning
• LSTM
• machine learning

References

1. Abbasimehr, H. ve Paki, R. (2021). Prediction of COVID-19 confirmed cases combining deep learning methods and Bayesian optimization. Chaos, Solitons & Fractals, 142, 110511.
2. Alassafi, M. O. Jarrah, M. ve Alotaibi, R. (2022). Time series predicting of COVID-19 based on deep learning. Neurocomputing, 468, 335-344.
3. Alazab, M. Awajan, A. Mesleh, A. Abraham, A. Jatana, V. ve Alhyari, S. (2020). COVID-19 prediction and detection using deep learning. International Journal of Computer Information Systems and Industrial Management Applications, 12 (June), 168-181.
4. Arora, P. Kumar, H. ve Panigrahi, B. K. (2020). Prediction and analysis of COVID-19 positive cases using deep learning models: A descriptive case study of India. Chaos, Solitons & Fractals, 139, 110017.
5. Bisgin, A. Sanlioglu, A. D. Eksi, Y. E. Griffith, T. S. ve Sanlioglu, S. (2021). Current update on severe acute respiratory syndrome coronavirus 2 vaccine development with a special emphasis on gene therapy viral vector design and construction for vaccination. Human Gene Therapy, 32(11-12), 541-562.
6. Bodapati, J. D. ve Veeranjaneyulu, N. (2019). Feature extraction and classification using deep convolutional neural networks. Journal of Cyber Security and Mobility, 261-276.
7. Che Azemin, M. Z. Hassan, R. Mohd Tamrin M. I. ve Md Ali, M. A. (2020). COVID-19 deep learning prediction model using publicly available radiologist-adjudicated chest X-ray images as training data: preliminary findings. International Journal of Biomedical Imaging, 2020.
8. Cucinotta, D. ve Vanelli, M., (2020). “WHO declares COVID-19 a pandemic.” Acta bio-medica: Atenei Parmensis, vol. 91, no. 1, pp. 157–160.

9. Daily and Total Vaccination for COVID-19 in the World from Our World in Data, https://www.kaggle.com/datasets/gpreda/covid-world-vaccination-progress (Erişim Tarihi: 20 Mart 2021)
10. Franco-Lopez, H. Ek, A. R. ve Bauer, M. E. (2001). Estimation and mapping of forest stand density, volume, and cover type using the k-nearest neighbors method. Remote sensing of Environment, 77(3), 251-274.
11. Ghritlahre, H. K. ve Prasad, R. K. (2018). Exergetic performance prediction of solar air heater using MLP, GRNN and RBF models of artificial neural network technique. Journal of environmental management, 223, 566-575.
12. Gupta, A. Sardar, P. Cash, M. E. Milani, R. V. ve Lavie, C. J. (2021). Covid-19 vaccine-induced thrombosis and thrombocytopenia-a commentary on an important and practical clinical dilemma. Progress in cardiovascular diseases.
13. Hazra, A. ve Gogtay, N. (2016). Biostatistics series module 6: correlation and linear regression. Indian journal of dermatology, 61(6), 593.
14. Hou, R. Huang, C. R. Zhou, M. ve Jiang, M. (2019). Distance between Chinese registers based on the Menzerath-Altmann law and regression analysis. Glottometrics, 45, 24-57.
15. Ibrahim, I. ve Abdulazeez, A. (2021). The role of machine learning algorithms for diagnosing diseases. Journal of Applied Science and Technology Trends, 2(01), 10-19.
16. Jamal, M. Shah, M. Almarzooqi, S. H. Aber, H. Khawaja, S. El Abed, R. ... ve Samaranayake, L. P. (2021). Overview of transnational recommendations for COVID‐19 transmission control in dental care settings. Oral diseases, 27, 655-664.
17. Kızıloluk, S. ve Can, U. (2021). Kalite Test Fonksiyonları Kullanılarak Güncel Metasezgisel Optimizasyon Algoritmalarının Karşılaştırılması. International Journal of Pure and Applied Sciences, 7(1), 100-112.
18. Lalmuanawma, S. Hussain, J. ve Chhakchhuak, L. (2020). Applications of machine learning and artificial intelligence for Covid-19 (SARS-CoV-2) pandemic: A review. Chaos, Solitons & Fractals, 139, 110059.
19. Laroui, S. Omara, H. LAZAAR, M. ve MAHBOUB, O. (2019). Comparative study of performing features applied in CNN architectures. In ICCWCS 2019: Third International Conference on Computing and Wireless Communication Systems, April 24-25, Faculty of Sciences, Ibn Tofaïl University-Kénitra-Morocco (p. 313).
20. Liu, G. ve Guo, J. (2019). Bidirectional LSTM with attention mechanism and convolutional layer for text classification. Neurocomputing, 337, 325-338.
21. Liu, Y. Gong, C. Yang, L. ve Chen, Y. (2020). DSTP-RNN: A dual-stage two-phase attention-based recurrent neural network for long-term and multivariate time series prediction. Expert Systems with Applications, 143, 113082.
22. Liu, Y. Liu, S. Wang, Y. Lombardi, F. ve Han, J. (2018). A stochastic computational multi-layer perceptron with backward propagation. IEEE Transactions on Computers, 67(9), 1273-1286.
23. Nurcahyanto, H. Prihatno, A. T. Alam, M. M. Rahman, M. H. Jahan, I. Shahjalal, M. ve Jang, Y. M. (2022). Multilevel RNN-Based PM10 Air Quality Prediction for Industrial Internet of Things Applications in Cleanroom Environment. Wireless Communications and Mobile Computing, 2022.
24. Pinter, G. Felde, I. Mosavi, A. Ghamisi, P. ve Gloaguen, R. (2020). COVID-19 pandemic prediction for Hungary; a hybrid machine learning approach. Mathematics, 8(6), 890.
25. Prasad, A. M. Iverson, L. R. ve Liaw, A. (2006). Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems, 9(2), 181-199.
26. Rahman, A. S. Shamrat, F. J. M. Tasnim, Z. Roy, J. ve Hossain, S. A. (2019). A comparative study on liver disease prediction using supervised machine learning algorithms. International Journal of Scientific & Technology Research, 8(11), 419-422.
27. Royer, H. D. ve Reinherz, E. L. (1987). T lymphocytes: ontogeny, function, and relevance to clinical disorders. New England Journal of Medicine, 317(18), 1136-1142.
28. Rubin, R. (2021). COVID-19 vaccines vs variants—determining how much immunity is enough. Jama, 325(13), 1241-1243.
29. Samaranayake, L. P. Seneviratne, C. J. ve Fakhruddin, K. S. (2021). Coronavirus disease 2019 (COVID‐19) vaccines: A concise review. Oral diseases.
30. Sen, P. C. Hajra, M. ve Ghosh, M. (2020). Supervised classification algorithms in machine learning: A survey and review. In Emerging technology in modelling and graphics (pp. 99-111). Springer, Singapore.
31. Shivanna, A. ve Agrawal, D. P. (2020). Prediction of defaulters using machine learning on Azure ML. In 2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) (pp. 0320-0325).
32. Song, Y. Y. ve Ying, L. U. (2015). Decision tree methods: applications for classification and prediction. Shanghai archives of psychiatry, 27(2), 130.
33. Staudemeyer, R. C. ve Morris, E. R. (2019). Understanding LSTM--a tutorial into long short-term memory recurrent neural networks. arXiv preprint arXiv:1909.09586.
34. Şengür, D. (2021). KOVİD-19 Salgını Sırasında Öğrencilerin Öğrenme Alışkanlıklarının Schur Ayrıştırma Tabanlı Dalgacık Aşırı Öğrenme Makineleri ile Tahmini. International Journal of Pure and Applied Sciences, 7(1), 13-18.
35. Tomppo, E. ve Halme, M. (2004). Using coarse scale forest variables as ancillary information and weighting of variables in k-NN estimation: a genetic algorithm approach. Remote Sensing of Environment, 92(1), 1-20.
36. Wang, N. Shang, J. Jiang, S. ve Du, L. (2020). Subunit vaccines against emerging pathogenic human coronaviruses. Frontiers in microbiology, 11, 298.
37. Wang, P. Zheng, X. Ai, G. Liu, D. ve Zhu, B. (2020). Time series prediction for the epidemic trends of COVID-19 using the improved LSTM deep learning method: Case studies in Russia, Peru and Iran. Chaos, Solitons & Fractals, 140, 110214.
38. Younis, M. C. (2021). Evaluation of deep learning approaches for identification of different corona-virus species and time series prediction. Computerized Medical Imaging and Graphics, 90, 101921.
39. Zhang, L. ve Yan, W. Q. (2020). Deep learning methods for virus identification from digital images. In 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ) (pp. 1-6). IEEE 39.
40. Zhang, N. Cai, Y. X. Wang, Y. Y. Tian, Y. T. Wang, X. L. ve Badami, B. (2020). Skin cancer diagnosis based on optimized convolutional neural network. Artificial intelligence in medicine, 102, 101756.