Klasifikasi Penyakit Anemia Menggunakan Metode K-nearest Neighbor (k-nn)

Azzahra, Annisa (2024) Klasifikasi Penyakit Anemia Menggunakan Metode K-nearest Neighbor (k-nn). Other thesis, Universitas Islam Riau.

Text 203510444.pdf - Submitted Version Restricted to Registered users only Download (9MB) | Request a copy

Abstract

Anemia is a serious health problem and can affect populations throughout the world. Early detection and correct diagnosis are very important for prevention, effective management and treatment can be done using data mining. Data mining has various classification methods that can be used to detect anemia early. In this research, the classification method used is the K-Nearest Neighbor (K-NN) algorithm by carrying out k-fold cross validation testing. The objective of this research is to develop a classification system to identify anemia using data on gender, hemoglobin, Mean Corpuscular Hemoglobin (MCH), Mean Corpuscular Hemoglobin Concentration (MCHC), and Mean Corpuscular Volume (MCV). The results of this research, in measuring accuracy using k-fold cross validation with 10 times, obtained the optimal k value of 1 with an average accuracy of 99% and system accuracy of 99.30%. Because of that, the application of the k-nearest neighbor method can work very well and be an effective solution for determining anemia or not.

Actions (login required)

View Item