Research Article
Determination of Nutritional Status Using Classification Method Datamining Using K- Nearst Neighbord (KNN) Algorithm
@INPROCEEDINGS{10.4108/eai.17-7-2020.2302994, author={Muhamad Fatchan and Muhamad Taufik Akbar and Wahyu Hadikristanto and Andri Firmansyah}, title={Determination of Nutritional Status Using Classification Method Datamining Using K- Nearst Neighbord (KNN) Algorithm}, proceedings={Proceedings of the 1st International Conference on Economics Engineering and Social Science, InCEESS 2020, 17-18 July, Bekasi, Indonesia}, publisher={EAI}, proceedings_a={INCEESS}, year={2021}, month={1}, keywords={nutritional status classification k-neart neigbord euclidean distance}, doi={10.4108/eai.17-7-2020.2302994} }- Muhamad Fatchan
Muhamad Taufik Akbar
Wahyu Hadikristanto
Andri Firmansyah
Year: 2021
Determination of Nutritional Status Using Classification Method Datamining Using K- Nearst Neighbord (KNN) Algorithm
INCEESS
EAI
DOI: 10.4108/eai.17-7-2020.2302994
Abstract
The Determination of nutritional status aims to determine the nutritional status of children, in health centers in the district of Bojonggambir, the parameters commonly used in determining the nutritional status of children based on body weight according to age (WA/ A), IIn determining the nutritional status of children often miscalculates due to several factors including, the psychological factors of nutritionists due to the large number of cases handled and the limited number of human resources in addition to the number of posyandu managed by the health center in Bojongambir quite a number of thousands of children each year, the purpose of this study is to determine patterns in the process of determining nutritional status and overcome the risk of errors in calculations performed by nutritionists, the method used in this study is the classification of data mining with the k nearst neighbord algorithm, the results of the k nearst neighbord algorithm calculation with the euncledean distance formula against 1001 children's data with value k is determined k = 3, k = 5, k = 7, k = 9, resulting in an average accuracy value of 96.88%, precision 98.59%, recall 95.25% and AUC 0.989 based on these results, it can be concluded the process of determining the nutritional status using an algorithm k nearst neighbord can be applied with very good accuracy results.
