Feature Selection in the Diabetes Dataset with the Marine Predator Algorithm and Classification using Machine Learning Methods

Abstract

Diabetes, which is classified as one of the leading causes of mortality, is a chronic and intricate metabolic disorder defined by disruptions in the metabolism of carbohydrates, fats, and proteins. Type 1 diabetes is categorized alongside Type 2 diabetes, as well as other distinct kinds of diabetes, including gestational diabetes. Complications, both acute and chronic, manifest in individuals with diabetes due to diminished insulin secretion and disruptions in the metabolism of carbohydrates, fats, and proteins. Following the completion of the data preparation step, the diabetes dataset that was collected from Kaggle is then sent to the feature extraction module for analysis. After the optimization process has been completed, the feature selection block will determine which characteristics stand out the most. The selected traits discussed before are sorted into several categories using the categorization module. The findings are compared to those that would have been obtained if the marine predator optimization algorithm (MPOA) technique had not been carried out, specifically regarding metrics like the F1 score, Recall, Accuracy, and Precision. The findings indicate that the LR classification approach achieves an accuracy rate of 77.63% without property selection. However, when the characteristics are selected using the MPOA, the accuracy rate increases to 79.39%.

Keywords

• : Machine learning
• marine predator
• classification diabetes
• feature selection

Kaynakça

1. [1] İ. Kabalı and S. Özan, “Communication with Chronic Patients and Patient Relatives in the Example of Diabetes Disease,” Tıp Eğitimi Dünyası, vol. 19, no. 57, pp. 109–119, 2020, doi: 10.25282/ted.576901.
2. [2] B. Aydoğan, A. Aydın, M. B. İnci, and H. Ekerbiçer, “TİP 2 Di̇yabet Hastalarinin Hastaliklariyİlgi̇liBi̇lgi̇, Tutum Düzeyleri̇ İli̇şki̇li̇ Faktörleri Değerlendi̇ri̇lmesi̇,” Sak. Med. J., 2020, doi: 10.31832/smj.743455.
3. [3] T. Gülsün and S. Şahhn, “Diyabet ve Diyabete Bağlı Fizyolojik ve Farmakokinetik Değişiklikler,” Hacettepe Univ. J. Fac. Pharm., vol. 37, no. 2, pp. 105–123, 2017.
4. [4] A. Abac, “Tip 1 Diyabet türkçe,” no. 8, pp. 1–10, 2007.
5. [5] D. Sisodia and D. S. Sisodia, “Prediction of Diabetes using Classification Algorithms,” Procedia Comput. Sci., vol. 132, no. Iccids, pp. 1578–1585, 2018, doi: 10.1016/j.procs.2018.05.122.
6. [6] G. Kaur and A. Chhabra, “Improved J48 Classification Algorithm for the Prediction of Diabetes,” Int. J. Comput. Appl., vol. 98, no. 22, pp. 13–17, 2014, doi: 10.5120/17314-7433.
7. [7] M. E. Febrian, F. X. Ferdinan, G. P. Sendani, K. M. Suryanigrum, and R. Yunanda, “Diabetes prediction using supervised machine learning,” Procedia Comput. Sci., vol. 216, no. 2022, pp. 21–30, 2022, doi: 10.1016/j.procs.2022.12.107.
8. [8] H. Liu, L. Teng, L. Fan, Y. Sun, and H. Li, “A new ultra-wide-field fundus dataset to diabetic retinopathy grading using hybrid preprocessing methods,” Comput. Biol. Med., vol. 157, no. 2699, p. 106750, 2023, doi: 10.1016/j.compbiomed.2023.106750.

9. [9] F. Mercaldo, V. Nardone, and A. Santone, “Diabetes Mellitus Affected Patients Classification and Diagnosis through Machine Learning Techniques,” Procedia Comput. Sci., vol. 112, pp. 2519–2528, 2017, doi: 10.1016/j.procs.2017.08.193.
10. [10] L. Wu, “Classification of diabetic retinopathy and diabetic macular edema,” World J. Diabetes, vol. 4, no. 6, p. 290, 2013, doi: 10.4239/wjd.v4.i6.290.
11. [11] S. NAHZAT and M. YAĞANOĞLU, “Makine Öğrenimi Sınıflandırma Algoritmalarını Kullanarak Diyabet Tahmini,” Eur. J. Sci. Technol., no. 24, pp. 53–59, 2021, doi: 10.31590/ejosat.899716.
12. [12] Kaggle, Available: https://www.kaggle.com/datasets/mathchi/diabetes-data-set
13. [13] A. Faramarzi, M. Heidarinejad, S. Mirjalili, and A. H. Gandomi, “Marine Predators Algorithm: A nature-inspired metaheuristic,” Expert Syst. Appl., vol. 152, p. 113377, 2020, doi: 10.1016/j.eswa.2020.113377.
14. [14] Z. Garip, M. Çimen, and A. Boz, “Otomatik Gerilim Regülatör Sistemi için Deniz Yırtıcıları Algoritmasının Performans Analizi,” Acta Infologica, vol. 0, no. 0, pp. 0–0, 2022, doi: 10.26650/acin.1026494.
15. [15] S. Mugemanyi et al., “Marine predators algorithm: A comprehensive review,” Mach. Learn. with Appl., vol. 12, no. June, p. 100471, 2023, doi: 10.1016/j.mlwa.2023.100471.
16. [16] O. ULUDAĞ and A. GÜRSOY, “Financial Risk Estimation with KNN Classification Algorithm on Determined Financial Ratios,” Eur. J. Sci. Technol., no. 29, pp. 26–29, 2021, doi: 10.31590/ejosat.1001663.
17. [17] M. Lüy, N. A. Metin “Classification of heart disease dataset with k-NN optimized by pso and gwo algorithms,” 2023, doi: 10.51271/JCEEES-0009.
18. [18] E. Akkur, “Investigatıon of the effect of feature selection and hyperparameter optimizatıon method on machine learning,” no. July, 2023.
19. [19] A. G. Kakisim, Z. Turgut, and T. Atmaca, “XAI Empowered Dual Band Wi-Fi Based Indoor Localization via Ensemble Learning,” 2023 14th Int. Conf. Netw. Futur., pp. 150–158, 2023, doi: 10.1109/NoF58724.2023.10302788.
20. [20] E. Akkur, F. Turk, and O. Erogul, “Breast cancer diagnosis using feature selection approaches and bayesian optimization,” Comput. Syst. Sci. Eng., vol. 45, no. 2, pp. 1017–1031, 2023, doi: 10.32604/csse.2023.033003.
21. [21] K. Çoşkun and G. Çetin, “a Comparative Evaluation of the Boosting Algorithms for Network Attack Classification,” Int. J. 3D Print. Technol. Digit. Ind., vol. 6, no. 1, pp. 102–112, 2022, doi: 10.46519/ij3dptdi.1030539.
22. [22] V. A. Dev and M. R. Eden, “Formation lithology classification using scalable gradient boosted decision trees,” Comput. Chem. Eng., vol. 128, pp. 392–404, 2019, doi: 10.1016/j.compchemeng.2019.06.001.
23. [23] P. Li, C. J. C. Burges, and Q. Wu, “McRank: Learning to rank using multiple classification and gradient boosting,” Adv. Neural Inf. Process. Syst. 20 - Proc. 2007 Conf., no. 1, 2008.
24. [24] D. Altaş and V. Gürpınar, “Karar ağaçları ve yapay sinir ağlarının sınıflandırma performanslarının karışılaştırılması: avrupa birliği örneği,” Trak. Üniversitesi Sos. Bilim. Derg., vol. 14, no. 1, pp. 1–22, 2012.
25. [25] A. Çalış, S. Kayapınar, and T. Çetinyokuş, “Veri madenci̇li̇ği̇nde karar ağacialgori̇tmalari ı̇le bi̇lgi̇sayar ve ı̇nternet güvenli̇ği̇ üzeri̇ne bi̇r uygulama,” Endüstri Mühendisliği, vol. 25, no. 3,pp.2–19, 2014, Available: http://dergipark.org.tr/endustrimuhendisligi/issue/46771/586362
26. [26] M. Trafi, D. Sald, M. Shap, A. C. Kelle, M. Queuing, and T. Transport, “Araştırma Makalesi / Research Article,” vol. 3, no. 1, pp. 50–62, 2022.
27. [27] M. Tokmak, "XGBoost Algoritması ile ikili parçacık sürü optimizasyonu öznitelik seçme tabanlı jar kötü amaçlı yazılımlarının tespiti jar malware detection with xgboost algorithm based on binary particle swarm optimization feature selection," vol. 10, no. 1, pp. 140–152, 2023.
28. [28] C. D. Kumral, A. Topal, M. Ersoy, R. Çolak, and T. Yiğit, “Performing Performance Analysis by Implementing Random Forest Algorithm on FPGA,” El-Cezeri J. Sci. Eng., vol. 9, no. 4, pp. 1315–1327, 2022, doi: 10.31202/ecjse.1134799.
29. [29] Ö. Akar and O. Güngör, “Rastgele orman algoritması kullanılarak çok bantlı görüntülerin sınıflandırılması,” J. Geod. Geoinf., vol. 1, no. 2, pp. 139–146, 2012, doi: 10.9733/jgg.241212.1t.
30. [30] X. Zou, Y. Hu, Z. Tian, and K. Shen, “Logistic Regression Model Optimization and Case Analysis,” Proc. IEEE 7th Int. Conf. Comput. Sci. Netw. Technol. ICCSNT 2019, pp. 135–139, 2019, doi: 10.1109/ICCSNT47585.2019.8962457.
31. [31] E. Sivari and S. Sürücü, “Prediction of heart attack risk using linear discriminant analysis methods,” J. Comput. Electr. Electron. Eng. Sci., vol. 1, no. 1, pp. 5–9, 2023, doi: 10.51271/jceees-0002.
32. [32] Ö. Vupa Çilengiroğlu and A. Yavuz, “Lojistik regresyon ve cart yöntemlerinin tahmin edici performanslarının yaşam memnuniyeti verileri için karşılaştırılması,” Eur. J. Sci. Technol., no. 18, pp. 719–727, 2020, doi: 10.31590/ejosat.691215.
33. [33] A. Göde and A. Kalkan, “Performance comparison machine learning algorithms in diabetes disease prediction,” Eur. Mech. Sci., vol. 7, no. 3, pp. 178–183, 2023, doi: 10.26701/ems.1335503.
34. [34] M. İ. Gürsoy and A. Alkan, “Investigation Of Diabetes Data with Permutation Feature Importance Based Deep Learning Methods,” Karadeniz Fen Bilim. Derg., vol. 12, no. 2, pp. 916–930, 2022, doi: 10.31466/kfbd.1174591.
35. [35] Z. PAMUK and C. KAYA, “Classification of Type 2 Diabetes Using Machine Learning Techniques,” Eur. J. Sci. Technol., no. 28, pp. 1265–1268, 2021, doi: 10.31590/ejosat.1014878.
36. [36] Ö. N. ERGÜN and H. O.İLHAN, “Early Stage Diabetes Prediction Using Machine Learning Methods,” Eur. J. Sci. Technol., no. 29, pp. 52–57, 2021, doi: 10.31590/ejosat.1015816.
37. [37] Y. GÜLTEPE, “Makine Öğrenmesi Algoritmaları ile Hava Kirliliği Tahmini Üzerine Karşılaştırmalı Bir Değerlendirme,” Eur. J. Sci. Technol., no. 16, pp. 8–15, 2019, doi: 10.31590/ejosat.530347.
38. [38] F. M. sakran Alamery, “Cryptocurrency analysis using machine learning and deep learning approaches,” J. Comput. Electr. Electron. Eng. Sci., vol. 1, no. 2, pp. 29–33, 2023, doi: 10.51271/jceees-0007.
39. [39] U. Tanyeri, T. Dindar, Y. Kökver, and N. F. Koçak, “Machine learning methods on quantized vectors,” J. Comput. Electr. Electron. Eng. Sci., vol. 1, no. 2, pp. 46–49, 2023, doi: 10.51271/jceees-0010.