IMPLEMENTASI ALGORITMA K-NEAREST NEIGHBORS PADA MODEL REKOMENDASI MAKANAN BERDASARKAN NUTRISI INDIVIDU

Muhamad Thoriq Ambia, - (2025) IMPLEMENTASI ALGORITMA K-NEAREST NEIGHBORS PADA MODEL REKOMENDASI MAKANAN BERDASARKAN NUTRISI INDIVIDU. S1 thesis, Universitas Pendidikan Indonesia.

Abstract

Nutrisi yang tepat dan seimbang merupakan aspek yang krusial untuk menjaga kesehatan, mencegah malnutrisi dan menurunkan risiko penyakit kronis seperti obesitas, hipertensi, gangguan ginjal, dan diabetes. Meskipun akses informasi mengenai nutrisi dan gizi semakin mudah diakses, rekomendasi makanan yang saat ini ada cenderung bersifat umum, konvensional dan hanya berbasis kecocokan kalori, tanpa mempertimbangkan personalisasi nutrisi dan kebutuhan makronutrien termasuk karbohidrat, protein, dan lemak secara personal. Penelitian ini bertujuan untuk mengimplementasikan algoritma K-Nearest Neighbors (KNN) karena kemampuaanya dalam menangani data numerik dan kategorikal serta adaptif terhadap variasi individu. Dataset yang digunakan terdiri dari data profil individu dan data resep makanan. KNN diterapkan dalam dua tahap utama yaitu prediksi kebutuhan nutrisi harian individu yang diperoleh berdasarkan data usia, jenis kelamin, tinggi badan, berat badan, dan tingkat aktivitas harian dan rekomendasi makanan berdasarkan kebutuhan nutrisi tersebut. Dengan menggunakan nilai K = 5 dan metrik Euclidean Distance. Hasil penelitian menunjukkan bahwa model prediksi nutrisi menghasilkan nilai Mean Absolute Error (MAE) sebesar 0,262252 dan Root Mean Squared Error (RMSE) sebesar 0,387986. Sementara, model rekomendasi makanan menghasilkan MAE sebesar 0,281922 dan RMSE sebesar 0,403113. Hasil ini menunjukkan bahwa model mampu memprediksi kebutuhan nutrisi secara akurat dan merekomendasikan makanan secara sesuai. --------- Appropriate and balanced nutrition is a crucial aspect of maintaining health, preventing malnutrition, and reducing the risk of chronic diseases such as obesity, hypertension, kidney disorders, and diabetes. Although access to information about nutrition and dietary intake is increasingly easy, current food recommendations tend to be general, conventional, and based solely on caloric matching, without considering personalized nutrition and personal macronutrient needs, including carbohydrates, protein, and fats. This study aims to implement the K-Nearest Neighbors (KNN) algorithm because of its ability to handle both numerical and categorical data and its adaptability to individual variation. The dataset used consists of individual profile data and meal recipe data. KNN is applied in two main stages, predicting an individual’s daily nutritional requirements based on age, gender, height, weight, and daily activity level and recommending foods according to those nutritional requirements. A value of K = 5 and the Euclidean Distance metric are used. The results show that the nutritional prediction model achieves a Mean Absolute Error (MAE) of 0.262252 and a Root Mean Squared Error (RMSE) of 0.387986. Meanwhile, the food recommendation model yields an MAE of 0.281922 and an RMSE of 0.403113. These findings indicate that the model is capable of accurately predicting nutritional needs and recommending foods accordingly.

	Text S_RPL_2109869_Title.pdf Download (1MB)
	Text S_RPL_2109869_Chapter1.pdf Download (279kB)
	Text S_RPL_2109869_Chapter2.pdf Restricted to Staf Perpustakaan Download (625kB) | Request a copy
	Text S_RPL_2109869_Chapter3.pdf Download (588kB)
	Text S_RPL_2109869_Chapter4.pdf Restricted to Staf Perpustakaan Download (872kB) | Request a copy
	Text S_RPL_2109869_Chapter5.pdf Download (226kB)
	Text S_RPL_2109869_Appendix.pdf Restricted to Staf Perpustakaan Download (1MB) | Request a copy

Item Type:	Thesis (S1)
Additional Information:	https://scholar.google.com/citations?hl=en&user=AuQgpeMAAAAJ ID SINTA Dosen Pembimbing: Mochamad Iqbal Ardimansyah: 6658552 Yulia Retnowati: 6852573
Uncontrolled Keywords:	K-Nearest Neighbors, Model rekomendasi, Kebutuhan Nutrisi Harian, Personalisasi Nutrisi, Makronutrien; K-Nearest Neighbors, Recommendation Model, Daily Nutritional Requirements, Personalized Nutrition, Macronutrient.
Subjects:	L Education > L Education (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine T Technology > T Technology (General)
Divisions:	UPI Kampus cibiru > S1 Rekayasa Perangkaat Lunak
Depositing User:	Muhamad Thoriq Ambia
Date Deposited:	07 Aug 2025 03:16
Last Modified:	07 Aug 2025 03:16
URI:	http://repository.upi.edu/id/eprint/135074

Actions (login required)

View Item