Comparative Analysis of Child Nutrition Using Extreme Learning Machine and Gradient Boosting Machine Methods at Al-Islam Krian Hospital

Ramadhan, Firman Rizky (2026) Comparative Analysis of Child Nutrition Using Extreme Learning Machine and Gradient Boosting Machine Methods at Al-Islam Krian Hospital. Undergraduate thesis, Universitas Pembangunan Nasional Jawa Timur.

	Text (Cover) 21081010238_Cover.pdf Download (834kB)
	Text (Bab 1) 21081010238_Bab_1.pdf Download (314kB)
	Text (Bab 2) 21081010238_Bab_2.pdf Restricted to Repository staff only until 30 July 2029. Download (600kB)
	Text (Bab 3) 21081010238_Bab_3.pdf Restricted to Repository staff only until 30 July 2029. Download (873kB)
	Text (Bab 4) 21081010238_Bab_4.pdf Restricted to Repository staff only until 30 July 2029. Download (1MB)
	Text (Bab 5) 21081010238_Bab_5.pdf Download (234kB)
	Text (Daftar Pustaka) 21081010238_Daftar_Pustaka.pdf Download (175kB)
	Text (lampiran) 21081010238_Lampiran.pdf Restricted to Repository staff only until 30 July 2029. Download (234kB)

Abstract

The nutritional status of school-age children (6–12 years) is a crucial indicator for physical growth and cognitive development. Nutritional issues, including both undernutrition and overnutrition (obesity), require fast and accurate early detection to minimize the risk of degenerative diseases in adulthood. This study aims to design and compare the performance of Extreme Learning Machine (ELM) and Gradient Boosting Machine (GBM) classification models in classifying the nutritional status of children at RS Al-Islam H.M. Mawardi, Krian. The research dataset consists of 257 medical records with feature variables including age, weight, height, gender, and body mass index (BMI). Data preprocessing was performed through numerical transformation, normalization, standardization, and class balancing using the Synthetic Minority Over-sampling Technique (SMOTE) to address data imbalance. The test results demonstrate that the Gradient Boosting Machine (GBM) model provides superior performance with an accuracy of 92%, precision of 80%, recall of 57%, and F1-score of 0.67. Meanwhile, the Extreme Learning Machine (ELM) model produced an accuracy of 90%, precision of 75%, recall of 43%, and F1-score of 0.55. Based on these results, it is concluded that the GBM method is more effective and stable in classifying children's nutritional status compared to the ELM method in this case, thus having the potential to be developed as a medical decision support system.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Wahananni, Henni Endah	NIDN0012049005	henniendah.if@upnjatim.ac.id
Thesis advisor	Mulyo, Budi Mukhamad	NIDN0718118904	budi.m.mulyo.fasilkom@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76.6 Computer Programming
Q Science > QA Mathematics > QA76.87 Neural computers
T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Firman Rizky ramadhan

Date Deposited:

31 Jul 2026 02:08

Last Modified:

31 Jul 2026 02:13

URI:

https://repository.upnjatim.ac.id/id/eprint/58321