Klasifikasi Gizi Balita Berdasarkan Indikator Antropometri Berat Badan Menggunakan Algoritma Support Vector Machine

Eva, Rahma Indriyani (2022) Klasifikasi Gizi Balita Berdasarkan Indikator Antropometri Berat Badan Menggunakan Algoritma Support Vector Machine. Project Report. Institut Telkom Telkom Purwokerto. (Unpublished)

	Text Cover.pdf Download (381kB)
	Text Abstract.pdf Download (20kB)
	Text Abstrak.pdf Download (20kB)
	Text BAB I.pdf Download (263kB)
	Text BAB II.pdf Download (397kB)
	Text BAB III.pdf Restricted to Registered users only Download (594kB) | Request a copy
	Text BAB IV.pdf Download (22kB)
	Text Daftar Pustaka.pdf Download (138kB)

Abstract

Malnutrition or commonly referred to as malnutrition is one of the health problems that quite often afflicts toddlers in Indonesia. According to data from Riskesdas in 2018, 3 out of 10 toddlers were stunted and a total of 17.7% of all toddlers in Indonesia experienced severe malnutrition and malnutrition. Growth in toddlers is not only used as an illustration of increasing body size, but is also used as an illustration of the continuity between intake and nutritional needs. One indicator that can determine the health level of toddlers themselves is to look at their nutritional status using an anthropometric scale. In anthropometric calculations, the determination of the nutritional status of children under five is only based on 4 internal factors, namely gender, age, weight and height. The classification of nutritional status of children under five, which includes poor nutrition, undernutrition, good nutrition and overweight and obesity, is measured based on the anthropometric index of weight and height according to age. In this study, the author tries to design a nutritional classification model for toddlers based on the anthropometric index of weight and height according to age by applying the Support Vector Machine algorithm. The variables used were gender, age, weight, and height. The results of the research and discussion conducted, the Support Vector Machine algorithm obtained an accuracy percentage of 86% with a total data of 336 record.

Actions (login required)

View Item