Claim Missing Document
Check
Articles

Found 1 Documents
Search

Support Vector Regression Untuk Peramalan Permintaan Darah: Studi Kasus Unit Transfusi Darah Cabang - PMI Kota Malang M. Raabith Rifqi; Budi Darma Setiawan; Fitra Abdurrachman Bachtiar
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 10 (2018): Oktober 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1285.495 KB)

Abstract

PMI is responsible for meeting blood demand from hospitals. The management of the blood storage center has a very important task, to predict the requirement of blood components to minimize the ex less and the lack of blood supply. Blood has only a life span of 35 days since donated. If it is past the time then it can not be used anymore. Excess or lack of blood supply at the site should not occur, because it can affect the number of patients death. In order to reduce the losses that if it occurs, it is necessary to do research that uses the prediction method of blood predict that is implemented in a system. One of them with Support Vector Regression method that is suitable for blood demand forecasting. Implement SVR using normalized min - max data and use RBF kernel function. Based on the test results for the SVR method that has been done, the result of the minimum MAPE value is 3.899% with the parameter value lambda = 10, sigma = 0.5, cLR = 0.01, C = 0.1, epsilon = 0.01, number of data features = 4 and number of iterations of 5000, of the 12 test data used. The resulting MAPE value is <10% and can be categorized as good for predicting the amount of blood demand.