Classification of Toddler Nutritional Status Based on Antrophometric Index and Feature Discrimination using Support Vector Machine Hyperparameter Tuning

Mughni, Much. Afif Masykur and Kamisutara, Made and Fahrudin, Tresna Maulana (2021) Classification of Toddler Nutritional Status Based on Antrophometric Index and Feature Discrimination using Support Vector Machine Hyperparameter Tuning. International Journal Of Computer, Network Security and Information System, 2 (2). pp. 60-65. ISSN 2686-3480

[img] Text
6. Jurnal 6.pdf

Download (537kB)
[img] Text (Peer Review)
6. PeerReview Jurnal 6.pdf

Download (411kB)
[img] Text (Plagiarism)
6. Plagiasi Jurnal 6.pdf

Download (1MB)

Abstract

The study of food and its relationship to health is known as nutritional status. Nutritional status is a criterion for determining a toddler's overall health. Body weight to age (BW / A), body height to age (BH / A), and body weight to body height (BW / BH) are three indexes used to determine a toddler's nutritional condition. Nutrition is still a crucial component in the development and growth of toddlers in Indonesia. In Indonesia, public health services like as the Public Health Center (Puskesmas) and the Integrated Healthcare Center (Posyandu) collaborate to manage toddler growth and development. We proposed a research to classify the nutritional status of toddler based on anthropometric index, to help control the growth and development of toddler. SVM Hyperparameter Tuning was used to turn the nutritional status of toddlers into a classification model. SVM is a machine learning algorithm that uses a hypothesis space in the form of linear functions in a high-dimensional feature space to classify data. To get a model that can solve machine learning issues optimally, the hyperparameter has to be adjusted. As a preprocessing stage, we used Fisher's Discriminant Ratio to choose important features, such as body weight (BB) and body height (BH). The classification model using SVM on training and testing data with a 70:30 ratio achieved 84% accuracy, while SVM Hyperparameter Tuning with parameters of Cost = 100 parameters, Gamma = 0.01, Kernel = RBF achieved 97% accuracy.They represented a significant accuracy difference of 13%. Keywords—Toddler; Nutritional Status; Fisher's Discriminant Ratio; Hyperparameter Tuning; Support Vector Machine

Item Type: Article
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Fakultas Ilmu Komputer > Teknik Informatika
Depositing User: Repository Administrator
Date Deposited: 21 Mar 2022 07:32
Last Modified: 31 Mar 2022 09:45
URI: http://repository.narotama.ac.id/id/eprint/1131

Actions (login required)

View Item View Item
["lib/irstats2:embedded:summary_page:eprint:downloads" not defined]