Sistem Rekomendasi Diet Rendah Natrium Bagi Penderita Hipertensi Dengan Content-Based Filtering Dan K-Nearest Neighbor

Nur Haliza, Hanim Rachma (2026) Sistem Rekomendasi Diet Rendah Natrium Bagi Penderita Hipertensi Dengan Content-Based Filtering Dan K-Nearest Neighbor. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 22082010010-cover.pdf Download (422kB)
	Text (Bab 1) 22082010010-bab 1.pdf Download (154kB)
	Text (Bab 2) 22082010010-bab 2.pdf Restricted to Repository staff only until 19 July 2029. Download (380kB)
	Text (Bab 3) 22082010010-bab 3.pdf Restricted to Repository staff only until 19 July 2029. Download (814kB)
	Text (Bab 4) 22082010010-bab 4.pdf Restricted to Repository staff only until 19 July 2029. Download (1MB)
	Text (Bab 5) 22082010010-bab 5.pdf Download (11kB)
	Text (Daftar Pustaka) 22082010010-daftarpustaka.pdf Download (162kB)
	Text (Lampiran) 22082010010-lampiran.pdf Restricted to Repository staff only until 29 July 2029. Download (1MB)

Abstract

Hypertension is a chronic disease with high prevalence in Indonesia that requires strict dietary management, particularly sodium restriction. This study develops a low-sodium diet recommendation system for hypertension patients using a Content-Based Filtering approach that integrates Rule-Based Filtering, K-Nearest Neighbor (KNN) with Weighted Euclidean Distance, and K-Means Clustering within the CRISP-DM framework. The dataset consists of 1,142 Indonesian food records obtained via web scraping from Fatsecret. Nutritional feature weights were derived through a hybrid approach combining clinical dietitian knowledge and Logistic Regression, with sodium receiving the highest weight. Sodium intake thresholds were established in accordance with the DASH (Dietary Approaches to Stop Hypertension) diet principles as recommended by the Indonesian Ministry of Health. Evaluation demonstrates strong performance, with an Average Weighted Euclidean Distance of 0.4509, a Nutritional Compliance Rate of 100%, and a Diversity Score of 100%. Clinical validation by a registered dietitian, Khusnun Adibah S.Gz, across 9 hypertension subjects yielded an average compliance rate of 79.36%. A clinical consultation with Dr. Hendra Saputra Sp.PD, a specialist in internal medicine, further confirmed that the overall dietary pattern applied by the system, emphasizing vegetables, fruits, and lean protein with sodium restriction in accordance with DASH diet principles, aligns with clinical recommendations for hypertension patients. These findings confirm that the system is capable of generating 7-day meal plans that consistently adhere to hypertension dietary limits and are clinically applicable.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Wahyuni, Eka Dyar	NIDN198412012021212005	ekawahyuni.si@upnjatim.ac.id
Thesis advisor	Arifiyanti, Amalia Anjani	NIDN199208122018032001	amalia_anjani.fik@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Information Systems

Depositing User:

hanim rachma nur haliza

Date Deposited:

20 Jul 2026 01:47

Last Modified:

20 Jul 2026 03:35

URI:

https://repository.upnjatim.ac.id/id/eprint/56038