<![CDATA[In order to obtain the target of Complete Basic Immunization (IDL), puskesmas (public health centers) in the sub-district of Duren Palm need to improve immunization services and data collection for infants and baduta (two-year-old babies). However, in the process of collecting data and grouping immunization data on infants and under-fives there are obstacles, because the data is too much to process so it takes a long time in grouping which puskesmas have reached the IDL target and which have not reached the IDL target, this makes the process ineffective and efficient. Seven Puskesmas in Duren Sawit sub-district will be divided into three groups, consisting of Puskesmas with high, medium, and low immunization targets. K-means clustering is the method used in this research, k-means clustering is a distance-based clustering algorithm, exclusively works on numeric attributes and divides data into several groups. The final results obtained using this method are in the final results of Clustering immunization targets in infants, there are three puskesmas that get a high predicate and four puskesmas that get a medium predicate. In the final results of Clustering immunization targets in under-fives, there are six health centers with high predicates and only one health center with moderate predicates. With the information system classification of infant and under-five immunization target data at Web-based health centers, it can simplify and speed up data processing and data grouping so that it becomes effective and efficient.]]>
Copyrights © 2024
