<![CDATA[Heart failure disease is a serious condition that is significant in affecting both a person's quality of life and health. Therefore, it is important to develop classification methods that can help detect this disease. In this research, a data preprocessing stage is performed before being used to classify heart failure diseases using machine learning models, such as K-NN. Data preprocessing is an effort to simplify data analysis and ensure accurate results, and it is a very essential step in analyzing data to improve the quality of the data used. The dataset used in this research is raw data that has not gone through the preprocessing stage. The dataset consists of 918 data with target attributes of 0 and 1, where a value of 0 indicates a normal condition and a value of 1 indicates a potential heart failure condition. Data preprocessing includes data cleaning, data transformation, and data normalization. The main objective of this research is to carry out the preprocessing stage on data derived from heart failure disease datasets. Based on the comparison between two normalization methods, namely Min-Max and Simple Feature Scale, it is found that the Simple Feature Scale normalization method has the best performance, with an accuracy rate of 85%, while the Min-Max normalization method only reaches 84%.]]>
Copyrights © 2023
