Implementasi Binary Particle Swarm Optimization Untuk Penentuan Nutrisi Diet Ideal Bagi Penderita Diabetes Melitus Tipe 2

Sholekah, Nadila Nur (2025) Implementasi Binary Particle Swarm Optimization Untuk Penentuan Nutrisi Diet Ideal Bagi Penderita Diabetes Melitus Tipe 2. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5026211041-Undergraduate_Thesis.pdf Restricted to Repository staff only Download (6MB) | Request a copy

Abstract

Diabetes Melitus Tipe 2 merupakan kondisi kronis yang memerlukan pengelolaan pola makan secara cermat untuk menjaga kestabilan kadar gula darah dan mencegah komplikasi. Penelitian ini membahas permasalahan dalam merancang pola makan ideal yang sesuai dengan kebutuhan nutrisi penderita. Kompleksitasnya terletak pada keseimbangan zat gizi makro kalori, karbohidrat, protein, dan lemak dengan tetap mempertimbangkan parameter kesehatan masing-masing individu. Untuk mengatasi tantangan tersebut, penelitian ini menerapkan model Linear Goal Programming (LGP) yang dioptimalkan menggunakan algoritma Binary Particle Swarm Optimization (BPSO), sebuah teknik metaheuristik yang efektif dalam menyelesaikan permasalahan optimasi kompleks. Kebutuhan nutrisi dihitung berdasarkan pedoman dari Perhimpunan Endokrinologi Indonesia (PERKENI), sementara data komposisi pangan diperoleh dari Tabel Komposisi Pangan Indonesia (TKPI) menggunakan Daftar Bahan Makanan Penukar (DBMP). Sistem ini menghasilkan rekomendasi menu mingguan dengan lima kali waktu makan per hari dan ditujukan bagi penderita DM tipe 2 berusia di atas 40 tahun tanpa komplikasi. Hasil penelitian menunjukkan bahwa algoritma BPSO dengan parameter optimal jumlah partikel sebanyak 80, inertia weight sebesar 0,4, serta koefisien akselerasi c1 = 2 dan c2 = 1,25 yang mencapai konvergensi pada iterasi ke-10 dan menghasilkan rata-rata deviasi sebesar 0% untuk kalori, 2,5% untuk karbohidrat, 4,8% untuk protein, dan 4,65% untuk lemak. Seluruh deviasi tersebut berada dalam batas toleransi ±5% menurut ahli gizi. Dengan demikian, sistem ini mendukung perencanaan diet personal bagi penderita DM Tipe 2 sekaligus berkontribusi pada pencapaian Good Health and Well-Being (SDG 3).

====================================================================================================================================
Type 2 Diabetes Mellitus is a chronic condition that requires careful dietary management to maintain optimal blood glucose levels and prevent complications. This study addresses the challenge of formulating an ideal diet that meets the nutritional needs of individuals with this condition. The complexity lies in balancing macronutrients like calories, carbohydrates, proteins, and fats while accounting for individual health parameters. To overcome these challenges, this study implements a Linear Goal Programming (LGP) model optimized using the Binary Particle Swarm Optimization (BPSO) algorithm, a metaheuristic technique effective in solving complex optimization problems. Nutritional requirements are calculated based on the guidelines of the Indonesian Endocrinology Association (PERKENI), and food composition data is obtained from the Indonesian Food Composition Table (TKPI) using the Food Exchange List (DBMP). The system generates weekly dietary recommendations based on five mealtimes per day and is targeted at patients over 40 years of age without complications. The results show that the BPSO algorithm, with optimal parameters 80 particles, inertia weight of 0.4, and acceleration coefficients c1 = 2 and c2 = 1.25 achieves convergence at the 10th iteration and produces average deviations of 0% for calories, 2.5% for carbohydrates, 4.8% for protein, and 4.65% for fat. These values fall within the acceptable ±5% tolerance range according to nutritionists, indicating that the proposed model effectively meets patients’ nutritional needs. This study contributes system supports personalized diet planning for Type 2 Diabetes patients while contributing to the achievement of Good Health and Well-Being (SDG 3).

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Diabetes Melitus Tipe 2, linear goal programming, metaheuristic, BPSO, Good health and well-being, Type 2 Diabetes Mellitus, linear goal programming, metaheuristic, BPSO, Good health and well-being
Subjects:	T Technology > T Technology (General) T Technology > T Technology (General) > T57.6 Operations research--Mathematics. Goal programming T Technology > T Technology (General) > T57.84 Heuristic algorithms.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 57201-(S1) Undergraduate Thesis
Depositing User:	Nadila Nur Sholekah
Date Deposited:	28 Jul 2025 01:56
Last Modified:	28 Jul 2025 01:56
URI:	http://repository.its.ac.id/id/eprint/121726

Actions (login required)

View Item