Please use this identifier to cite or link to this item:
https://repositori.uma.ac.id/handle/123456789/24433
Title: | Klasifikasi Data Transfusi Darah melalui Pendekatan Algoritma Random Forest dan Support Vector Machine |
Other Titles: | Classification of Blood Transfusion Data using the Random Forest Algorithm and Support Vector Machine Approach |
Authors: | Putra, Dwi Kurnia |
metadata.dc.contributor.advisor: | Rahmadsyah |
Keywords: | Random Forest;Klasifikasi Data;Blood Transfusion Service Center;Transfusi Darah;Support Vector Machine |
Issue Date: | Apr-2024 |
Publisher: | Universitas Medan Area |
Series/Report no.: | NPM;198160073 |
Abstract: | Penelitian ini bertujuan untuk mengevaluasi dan membandingkan efektivitas algoritma Random Forest dan Support Vector Machine (SVM) dalam mengklasifikasikan data transfusi darah. Tujuan utama adalah untuk meningkatkan pemahaman tentang kebutuhan transfusi darah serta mengoptimalkan alokasi sumber daya dan identifikasi pasien berisiko tinggi. Studi ini menggunakan dataset Blood Transfusion Service Center, yang terdiri dari sampel yang diklasifikasikan sebagai pendonor reguler dan pendonor tidak reguler. Data dibagi menjadi 80% untuk pelatihan dan 20% untuk pengujian. Random Forest menunjukkan akurasi sebesar 72%, dan SVM mencapai akurasi 76%. Algoritma Random Forest menunjukkan kinerja yang lebih seimbang antara kedua kelas, dan SVM menunjukkan presisi yang tinggi untuk pendonor reguler tetapi kekurangan dalam mengenali pendonor tidak reguler. This study aims to evaluate and compare the effectiveness of the Random Forest and Support Vector Machine (SVM) algorithms in classifying blood transfusion data. The primary goal is to improve understanding of blood transfusion requirements as well as optimize resource allocation and identification of high-risk patients. This study uses the Blood Transfusion Service Center dataset, which consists of samples classified as regular donors and irregular donors. The data is divided into 80% for training and 20% for testing. Random Forest showed an accuracy of 72%, and SVM achieved an accuracy of 76%. The Random Forest algorithm shows more balanced performance between the two classes, and the SVM shows high precision for regular donors but is deficient in recognizing irregular donors. |
Description: | 71 Halaman |
URI: | https://repositori.uma.ac.id/handle/123456789/24433 |
Appears in Collections: | SP - Informatic Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
198160073 - Dwi Kurnia Putra - Chapter IV.pdf Restricted Access | Chapter IV | 674.24 kB | Adobe PDF | View/Open Request a copy |
198160073 - Dwi Kurnia Putra - Fulltext.pdf | Cover, Abstract, Chapter I, II, III, V, Bibliography | 1.51 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.