Implementasi Metode Support Vector Machine pada Klasifikasi Diagnosis Penyakit Hipertensi

Hilda Zaqya Elnaz Putri, Hisyam Fahmi

Abstract


Hypertension is one of the leading causes of death worldwide. This disease is often referred to as the silent killer because it can lead to death without noticeable symptoms, leaving those affected unaware of their condition. Therefore, early detection and management of hypertension are crucial. This research aims to obtain the classification of hypertension using the Support Vector Machine (SVM) method by utilizing various attributes such as age, smoking habits, lifestyle, blood pressure, and hypertension diagnosis, as well as determining the accuracy level of hypertension classification results using the SVM method. The SVM method is trained with various kernel parameters and hyperparameters to find the best model. The research findings indicate that the best model for classifying hypertension using the SVM method employs the RBF kernel with parameters = 100 and  (gamma) = 0,1, achieving an accuracy of 97.15%. This demonstrates that the SVM method is capable of classifying hypertension very well and significantly contributes to the early detection and management of hypertension.


Keywords


Hypertension; Support Vector Machine; SVM; Data Mining; Classification;

Full Text:

PDF

References


Andriansyah, Mochamad Rafli, Edy Santoso, and Sutrisno. (2018). “Klasifikasi Risiko Hipertensi Menggunakan Fuzzy Decision Tree Iterative Dichotomiser 3 (ID3).” Jurnal Pengembangan Teknologi Informasi Dan Ilmu Komputer 2(Vol 2 No 12 (2018)):7088–96.

BPS Kota Malang. (2019). Jumlah Kasus Penyakit Terbanyak di Kota Malang (Jiwa), 2019. https://malangkota.bps.go.id/indicator/30/371/1/jumlah-kasus-penyakit-terbanyak-di-kota-malang.html. Diakses pada tanggal 5 Oktober 2023.

Don, D. P. W. R. (2018). Multiclass Classification Using Support Vector Machines [Tesis, Georgia Southern University]. https://digitalcommons.georgiasouthern.edu/etd/1845/. Diakses pada tanggal 5 Januari 2024.

Khalim, K. A., Hayati, U., & Bahtiar, A. (2023). Perbandingan Prediksi Penyakit Hipertensi Menggunakan Metode Random Forest Dan Naïve Bayes. JATI (Jurnal Mahasiswa Teknik Informatika), 7(1), 498-504. doi:10.36040/jati.v7i1.6376

Maiyanti, S. I., Zayanti, D. A., Andriani, Y., Suprihatin, B., Desiani, A., Salsabila, A., & Marselina, N. C. (2023). Perbandingan Klasifikasi Penyakit Kanker Paru-Paru Menggunakan Support Vector Machine Dan K-Nearest Neighbor. Jurnal Ilmiah Teknologi Kesehatan, 18(1), 54-62. doi: 10.33998/processor.2023.18.1.700

P2TPM Kemenkes Kesehatan RI. (2016). Tekanan darah tinggi (hipertensi). Diakses pada 25 Oktober 2023, dari https://p2ptm.kemkes.go.id/uploads/2016/10/Tekanan-Darah-Tinggi-Hipertensi.pdf

P2TPM Kemenkes Kesehatan RI. (2019). Hari Hipertensi Dunia 2019 : “Know Your Number, Kendalikan Tekanan Darahmu dengan CERDIK.” https://p2ptm.kemkes.go.id/tag/hari-hipertensi-dunia-2019-know-your-number-kendalikan-tekanan-darahmu-dengan-cerdik. Diakses pada tanggal 15 Oktober 2023.

Septiani, W. D. (2017). Komparasi Metode Klasifikasi Data Mining Algoritma C4.5 Dan Naive Bayes Untuk Prediksi Penyakit Hepatitis. Journal of Computing and Information System, 13(1), 76-84.

Setiawati, I., Wibowo, A. P., & Hermawan, A. (2019). Pendahuluan tinjauan pustaka penelitian sebelumnya klasifikasi. Jurnal of Information System Management, 1(1), 13-17.

Tan, P.-N., Steinbach, M., & Kumar, V. (2016). Introduction to data mining (3rd ed.). Harlow, England: Pearson Education Limited.

Tino, M. D. F., Hasanah, H., & Santosa, T. D. (2023). Perbandingan Algoritma Support Vector Machines (Svm) Dan Neural Network Untuk Klasifikasi Penyakit Jantung. INFOTECH journal, 9(1), 232-235. doi: 10.31949/infotech.v9i1.5432




DOI: https://doi.org/10.18860/jrmm.v3i5.27312

Refbacks

  • There are currently no refbacks.