Comparison of the K-Means Method with the K-Medoids Method for Recipient Infant Clustering Measles Immunization

Abstract

Measles or meales is a disease that can be transmitted, if someone who is affected by measles is in the same room with other people who have never been exposed to or received the measles vaccine, it is estimated that they will be infected with measles. The measles vaccine is a very effective vaccine for preventing measles. This type of vaccine is included in the routine immunization program recommended by the Ministry of Health of the Republic of Indonesia. So far, there are two types of measles vaccine, namely the MR vaccine and the MMR vaccine. The MR vaccine is used to prevent measles and rubella, while the MMR vaccine prevents measles, rubella and mumps. The target of vaccine administration can be observed by applying the data mining method, while the data mining method that can be used in this study is by using K-Means and K-Medoids. The purpose of this study was to compare the K-Means and K-Medoids methods in analyzing the achievement of vaccine administration to infants aged 9 months to 18 months. The results of the study obtained optimal k values of 21 provinces with the highest cluster of 3 using the K-Means algorithm, while the optimal K values of 10 provinces with the highest cluster of 3 were obtained using the K-Medoids algorithm.