Optimalisasi Algortima Klasifikasi Ensemble Menggunakan Algortima Genetika Untuk Prediksi Resiko Diabetes

Aldi Kristiawan Febianto(1*), Castaka Agus Sugianto(2),

(1) Politeknik TEDC Bandung, Jawa Barat, Indonesia
(2) Politeknik TEDC Bandung, Jawa Barat, Indonesia
(*) Corresponding Author

Abstract


Diabetes mellitus (DM) is a global health problem that affects the quality of life and life expectancy of patients. Diabetes risk prediction can help in disease prevention and management. This study aims to optimize ensemble classification for diabetes risk prediction using a Genetic Algorithm (Optimize Selection). The Ensemble methods used are Bagging, Random Forest, and AdaBoost. The genetic algorithm is applied for Ensemble model hyperparameter optimization. The data used is the Pima Indians Diabetes dataset which consists of 768 samples with 8 features. Experimental results show that Ensemble Classification optimized with the Genetic Algorithm (Optimize Selection) produces quite good performance. The accuracy of the Genetic Algorithm (Optimize Selection) + Ensemble Bagging Classification Algorithm got a result of 97.14%, the Genetic Algorithm (Optimize Selection) + Random Forest Ensemble Classification Algorithm got a result of 98.57%, and the Genetic Algorithm (Optimize Selection) + AdaBoost Ensemble Classification Algorithm got a result of 99.87%. %, These results indicate that this approach can be an effective solution in diabetes risk prediction.

Full Text:

PDF

References


O. Daanouni, B. Cherradi, and A. Tmiri, “Predicting diabetes diseases using mixed data and supervised machine learning algorithms,” ACM Int. Conf. Proceeding Ser., no. October, 2019, doi: 10.1145/3368756.3369072.

W. Apriliah, I. Kurniawan, M. Baydhowi, and T. Haryati, “Prediksi Kemungkinan Diabetes pada Tahap Awal Menggunakan Algoritma Klasifikasi Random Forest,” J. Sist. Inf., vol. 10, no. 1, pp. 163–171, 2021, [Online]. Available: http://sistemasi.ftik.unisi.ac.id

L. M. Cendani and A. Wibowo, “Perbandingan Metode Ensemble Learning pada Klasifikasi Penyakit Diabetes,” J. Masy. Inform., vol. 13, no. 1, pp. 33–44, 2022, doi: 10.14710/jmasif.13.1.42912.

Amelia, “Self-Monitoring of Blood Glucose dalam Mencegah Neropati pada Ektremitas Bawah Pasien Diabetes Melitus Tipe II,” Indones. J. Nurs. Sci. Pract., pp. 58–72, 2020.

S. K. Kermani, A. Khatony, R. Jalali, M. Rezaei, and A. Abdi, “Accuracy and precision of measured blood sugar values by three glucometers compared to the standard technique,” J. Clin. Diagnostic Res., vol. 11, no. 4, pp. OC05–OC08, 2017, doi: 10.7860/JCDR/2017/23926.9613.

V. Agustin, M. M. P. Putra, and A. Husni, “Impact of Enzymatic Hydrolysis on Antioxidant Activity of Snakehead Fish (Channa striata) Head Protein Hydrolysate,” J. Ilm. Perikan. dan Kelaut., vol. 15, no. 1, pp. 44–56, 2023, doi: 10.20473/jipk.v15i1.38391.

M. Aryuni, “Penerapan Ensemble Feature Selection dan Klasterisasi Fitur pada Klasifikasi Dokumen Teks,” ComTech Comput. Math. Eng. Appl., vol. 4, no. 1, p. 333, 2013, doi: 10.21512/comtech.v4i1.2745.

M. Mirqotussa’adah, M. A. Muslim, E. Sugiharti, B. Prasetiyo, and S. Alimah, “Penerapan Dizcretization dan Teknik Bagging Untuk Meningkatkan Akurasi Klasifikasi Berbasis Ensemble pada Algoritma C4.5 dalam Mendiagnosa Diabetes,” Lontar Komput. J. Ilm. Teknol. Inf., vol. 8, no. 2, p. 135, 2017, doi: 10.24843/lkjiti.2017.v08.i02.p07.

Muflih Ihza Rifatama, Mohammad Reza Faisal, Rudy Herteno, Irwan Budiman, and Muhammad Itqan Mazdadi, “Optimasi Algoritma K-Nearest Neighbor Dengan Seleksi Fitur Menggunakan Xgboost,” J. Inform. dan Rekayasa Elektron., vol. 6, no. 1, pp. 64–72, 2023, doi: 10.36595/jire.v6i1.723.

H. Marlina, A. Zulius, and O. L. W. H. Wijaya, “Penerapan Algoritma Random Forest Dalam Klasifikasi Penjurusan Di SMA Negeri Tugumulyo,” BRAHMANA J. Penerapan Kecerdasan Buatan Terakreditasi, vol. 4, no. 2, pp. 138–143, 2023, [Online]. Available: https://tunasbangsa.ac.id/pkm/index.php/brahmana/article/view/188.




DOI: https://doi.org/10.30645/brahmana.v5i2.391

DOI (PDF): https://doi.org/10.30645/brahmana.v5i2.391.g387

Refbacks

  • There are currently no refbacks.


Published Papers Indexed/Abstracted By: