Data Classification of Prospective Blood Donors with the K-Nearest Neighbor Algorithm and Support Vector Machine

  • RACHMAT RAMADHAN UNIVERSITAS NASIONAL
Keywords: Keywords— Donors; Blood; SVM; KNN; Accuracy

Abstract

 Blood plays an important role in the human body. Meeting the need for blood is very important to improve the quality of health services and save a person's life. According to World Health Organization guidelines, blood from a donor cannot be used after 42 days. The national blood reserve that meets the standards of the International Health Organization (WHO) is 2% of the population. To know and understand the behavior of blood donors, it is very important to increase blood supply in the future, one of which is by using an algorithm to predict the behavior of blood donors. To classify prospective blood donors using the K-Nearest Neighbors Algorithm and Support Vector Machine. The data used comes from the PMI UTD, South Jakarta City, the primary data collection for blood donors. The test is done by comparing the training data and testing data. The results of the test show that the Support Vector Machine produces an accuracy of 90% greater than the K-Nearest Neighbors Algorithm which only has an accuracy of 76% with a data comparison of 60:40 with a dataset of 200 data. .

References

[1] Infodatin Kemenkes RI, “Kementerian Kesehatan Republik Indonesia. Pusat Data dan Informasi (Profil Kesehatan Indonesia).” pp. 1–6, 2014, Accessed: Dec. 22, 2021. [Online]. Available: https://pusdatin.kemkes.go.id/article/view/18091000001/pelayanan-darah-di-indonesia-2018.html.
[2] I. C. Yeh, K. J. Yang, and T. M. Ting, “Knowledge discovery on RFM model using Bernoulli sequence,” Expert Syst. Appl., vol. 36, no. 3 PART 2, pp. 5866–5871, Apr. 2009, doi: 10.1016/j.eswa.2008.07.018.
[3] H. Wahono and D. Riana, “Prediksi Calon Pendonor Darah Potensial Dengan Algoritma Naïve Bayes, K-Nearest Neighbors dan Decision Tree C4.5Wahono, H., & Riana, D. (2020). Prediksi Calon Pendonor Darah Potensial Dengan Algoritma Naïve Bayes, K-Nearest Neighbors dan Decision Tree C4.,” JURIKOM (Jurnal Ris. Komputer), vol. 7, no. 1, p. 7, 2020, doi: 10.30865/jurikom.v7i1.1953.
[4] W. E. Susanto and D. Riana, “Komparasi Algoritma Neural Network, K-Nearest Network dan Naive Bayes Untuk Memprediksi Pendonor Darah Potensial,” J. Speed, vol. 8, no. 3, pp. 18–27, 2016.
[5] B. Yulianto, “Penentuan Calon Pendonor Darah Menggunakan Algoritma Naive Bayes Classification (Studi Kasus Pmi Semarang),” Provider, vol. 12, no. 1, pp. 4982–4987, 2010, Accessed: Jan. 17, 2022. [Online]. Available: http://os.ibds.kit.edu/downloads/sa_2010_braehler-stefan_android-architecture.pdf%5Cnhttp://www.ijarcce.com/upload/2014/january/IJARCCE3B__A_unmesh_Location.pdf%5Cnhttp://sedici.unlp.edu.ar/handle/10915/22055.
[6] W. E. Susanto and C. Agustina, “Komparasi Akurasi Algoritma C4.5 dan Naïve Bayes untuk Prediksi Pendonor Darah Potensial dengan Dataset RFMTC,” Semin. Nas. Ilmu Komput., 2016.
[7] Y. Nurdiansyah, P. Pandunata, N. D. Prasetyo, A. Trihartono, F. G. Putrianti, and F. Wijayanto, “Application of blood donor routine detector using K-Nearest neighbors,” in IOP Conference Series: Earth and Environmental Science, Jun. 2019, vol. 293, no. 1, doi: 10.1088/1755-1315/293/1/012042.
[8] I. T. Utami, F. Fadjryani, and D. Daniaty, “View of Perbandingan Klasifikasi Status Pendonor Darah dengan Menggunakan Regresi Logistik dan K-Nearest Neighbor,” J. Apl. Stat. Komputasi Stat., vol. 12, no. 1, p. 1, Jun. 2020, doi: 10.34123/jurnalasks.v12i1.217.
[9] E. B. Nugroho, M. T. Furqon, and N. Hidayat, “Klasifikasi Pendonor Darah Menggunakan Metode Support Vector Machine,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 2, no. 10, pp. 3860–3864, 2018.
[10] “Give Blood Save Life.” http://ayodonor.pmi.or.id/about.php (accessed Jan. 17, 2022).
[11] L. Y. Hu, M. W. Huang, S. W. Ke, and C. F. Tsai, “The distance function effect on k-nearest neighbor classification for medical datasets,” Springerplus, vol. 5, no. 1, pp. 1–9, Dec. 2016, doi: 10.1186/s40064-016-2941-7.
[12] A. T. Umum, “Pendahuluan Latar belakang Deskripsi Pelatihan Materi ini berisi penjelasan mengenai persiapan pemodelan dan proses pemodelan klasifikasi Kompetensi Dasar.”
[13] Jung, Data mining konsep dan aplikasi menggunakan satscan. 2017.
[14] S. Vijayakumar and S. Wu, “Sequential Support Vector Classifiers and Regression,” in Proceedings of International Conference on Soft Computing (SOCO ‘99), 1999, vol. 619, pp. 610–619.
[15] S. A. Naufal, A. Adiwijaya, and W. Astuti, “Analisis Perbandingan Klasifikasi Support Vector Machine (SVM) dan K-Nearest Neighbors (KNN) untuk Deteksi Kanker dengan Data Microarray,” JURIKOM (Jurnal Ris. Komputer), vol. 7, no. 1, p. 162, 2020, doi: 10.30865/jurikom.v7i1.2014.
[16] “sklearn.neighbors.KNeighborsClassifier — scikit-learn 1.0.2 documentation.” https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html (accessed Jan. 17, 2022).
[17] “sklearn.svm.SVC — scikit-learn 1.0.2 documentation.” https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html?highlight=svc#sklearn.svm.SVC (accessed Jan. 17, 2022).
Published
2022-06-14