Implementation of Machine Learning Based on the K-Nearest Neighbor (KNN) Algorithm in Elderly Activities in Nursing Homes

Abstract

 This study aims to implement the K-Nearest Neighbor (KNN) algorithm to classify elderly activities in nursing homes based on their daily activity data. The method assists administrators in better understanding the preferences and conditions of the elderly so that activities provided can be more targeted. The dataset includes various attributes such as age, gender, health condition, and types of activities attended. After preprocessing, the KNN algorithm is applied with different values of k to determine optimal performance. The evaluation results show that k=3 yields the highest accuracy of 92%. Therefore, the model can be used as a decision support system for planning elderly activities in nursing homes.