Pemanfaatan metode SMOTE untuk prediksi periode donor darah dengan metode Backpropagation

Authors

  • Ach Afrian Auliansyah Program Studi Teknik Informatika, Universitas Islam Negeri Maulana Malik Ibrahim Malang
  • Willia Dwi Puspitasari Program Studi Teknik Informatika, Universitas Islam Negeri Maulana Malik Ibrahim Malang
  • Ni’matul Wafiroh Program Studi Teknik Informatika, Universitas Islam Negeri Maulana Malik Ibrahim Malang

Keywords:

prediction, blood donation, SMOTE method, backpropagation, knowledge engineering

Abstract

Prediction of blood donor periods is an important part of blood storage to ensure an adequate blood supply. The aim of this research is to compare the performance of the SMOTE method with an approach that does not use oversampling on the blood donor period dataset. The dataset used in this research includes information about blood donors, which consists of 4 attributes and 1 label. The experimental results show that the use of the SMOTE method significantly improves the predictability of blood donor periods. SMOTE successfully improves the accuracy, precision, recall, and F1 score of the classification model used. This indicates that the use of oversampling can address the class imbalance issue in the blood donor period dataset and improve the predictive ability of the model. This research makes an important contribution to the field of knowledge engineering by applying the SMOTE method to predict blood donor periods combined with Backpropagation. The results of this research can serve as a guide for the development of more efficient and effective blood donor prediction systems.

Downloads

Download data is not yet available.

Downloads

Published

2024-05-31

How to Cite

Auliansyah, A. A., Puspitasari, W. D., & Wafiroh, N. (2024). Pemanfaatan metode SMOTE untuk prediksi periode donor darah dengan metode Backpropagation. Maliki Interdisciplinary Journal, 2(5), 676–685. Retrieved from https://urj.uin-malang.ac.id/index.php/mij/article/view/5327

Issue

Vol. 2 No. 5 (2024): MAY

Section

Articles

License

Authors who publish with this journal agree to the following terms:

  • Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work’s authorship and initial publication in this journal.
  • Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  • Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.