Implementasi Algoritma Support Vector Machine Untuk Klasifikasi Status Stunting Pada Balita

A Jalil, A Homaidi, Z Fatah - G-Tech: Jurnal …, 2024 - ejournal.uniramalang.ac.id
G-Tech: Jurnal Teknologi Terapan, 2024ejournal.uniramalang.ac.id
In Indonesia, the main health problem is stunting or dwarfism in toddlers due to chronic
malnutrition. This study uses the Support Vector Machine (SVM) algorithm to classify the
stunting status of toddlers with high accuracy. The dataset for stunting cases in Indonesia,
which includes 6500 data, consists of eight attributes:" Gender"," age"," birth weight"," body
weight"," height"," exclusive action"," stunting". This data was obtained from the public data
Kaggle website. Preprocessing, such as data noise cleaning and data variable refinement …
Abstract
In Indonesia, the main health problem is stunting or dwarfism in toddlers due to chronic malnutrition. This study uses the Support Vector Machine (SVM) algorithm to classify the stunting status of toddlers with high accuracy. The dataset for stunting cases in Indonesia, which includes 6500 data, consists of eight attributes:" Gender"," age"," birth weight"," body weight"," height"," exclusive action"," stunting". This data was obtained from the public data Kaggle website. Preprocessing, such as data noise cleaning and data variable refinement, is a process stage. Next, the ready dataset is divided into twenty percent test data and eighty percent training data. The SVM algorithm that uses a" linear" kernel has an accuracy of 82%, precision of 80%, and recall of 86% when used to classify cases of stunting in toddlers. These results show that the SVM algorithm is very good at classifying stunting cases in toddlers. Next, the stunting classification model created was applied to a web application using the Streamlit framework.
ejournal.uniramalang.ac.id
以上显示的是最相近的搜索结果。 查看全部搜索结果

Google学术搜索按钮

example.edu/paper.pdf
搜索
获取 PDF 文件
引用
References