Silvia Dini Widianti
STMIK IKMI Cirebon

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Menentukan Nilai Gizi pada Balita Menggunakan Algoritma Support Vektor Machine (SVM) di Posyandu Kelurahan Ciherang Silvia Dini Widianti; Rini Astuti; Fadhil Muhamad Basysyar
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol 6, No 1 (2024): Maret
Publisher : Universitas Wahid Hasyim

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36499/jinrpl.v6i1.10274

Abstract

Determining nutritional status in toddlers is based on age, weight and height. The process is still done manually, resulting in the resulting data being less relevant. This research serves to provide information about determining the nutritional status of toddlers so that the community and officers at Posyandu Ciherang Village. The problem of this study is to determine the growth and development of nutritional status in toddlers at Posyandu Ciherang Village. Data obtained from Posyandu at the village level whose activities are carried out once a month by cadres under the technical guidance of the puskesmas. Based on the existing problems, a system for determining the nutritional status of toddlers is needed to make it easier to get the right results. The method to be used is Support Vector Marchine (SVM) which is a method of classifying data and providing a basis for early preventive action in overcoming nutritional problems in toddlers. The purpose of this study is to determine the nutritional status of toddlers there are 3 criteria needed, namely the age of toddlers, weight and height. The Support Vector Marchine (SVM) algorithm is considered more optimal because it is able to analyze the best results. The results of this study are expected to provide better insight into determining nutritional values in toddlers. Based on the results show True Less (TK) on pred.NORMAL is 31 records classified as malnutrition and True Normal (TN) on pred.NORMAL is 267 records classified as normal nutrition with the smallest result of class recall 76.52% and the smallest result of class precision 76.52%. From these results it can be concluded that the accuracy rate with the Support Vector Marchine (SVM) algorithm is 85.58%.