ULFA, ANIS FITRIA (2025) KLASIFIKASI STATUS GIZI BALITA DI PUSKESMAS TAJUR DENGAN ALGORITMA NAIVE BAYES DAN RANDOM FOREST. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (512kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 BAB 1.pdf Restricted to Registered users only Download (103kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (226kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (105kB) |
|
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (398kB) |
|
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (24kB) |
|
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (163kB) |
|
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (737kB) |
Abstract
The nutritional status of toddlers is a crucial indicator for assessing children's health conditions and identifying potential nutritional problems at an early stage. This study aims to classify the nutritional status of toddlers using the Naive Bayes and Random Forest algorithms based on data obtained from Puskesmas Tajur. The dataset consists of 3,414 records of children aged 0–5 years, with attributes including gender, age, weight, and height. The data underwent a preprocessing stage, which included converting age into months, labeling nutritional status based on the BB/U Z-score values, and transforming variables into numerical form. Two data-splitting scenarios were applied, namely 70:30 and 80:20, for training and testing purposes. The model performance evaluation showed that the Naive Bayes algorithm achieved an accuracy of 77.23% with a 70:30 split, and 76.18% with an 80:20 split. Meanwhile, the Random Forest algorithm achieved an accuracy of 92.84% with a 70:30 split and 93.24% with an 80:20 split. Based on these results, it can be concluded that the Random Forest algorithm demonstrates superior classification performance compared to Naive Bayes, as it consistently produces higher and more stable accuracy across both data-splitting scenarios. Keywords: Toddler Nutritional Status, Naive Bayes, Random Forest, Z-score, Classification. Status gizi balita merupakan indikator yang sangat penting dalam menilai kondisi kesehatan anak dan mendeteksi potensi masalah gizi sejak dini. Penelitian ini bertujuan untuk mengklasifikasikan status gizi balita dengan menggunakan Algoritma Naive Bayes dan Random Forest berdasarkan data dari Puskesmas Tajur. Dataset yang digunakan terdiri dari 3.414 data balita berusia 0–5 tahun dengan atribut seperti jenis kelamin, usia, berat badan, dan tinggi badan. Data tersebut diproses melalui tahap preprocessing, konversi usia ke dalam bulan, pelebelan status gizi yang berdasarkan nilai Z-score BB/U, serta transformasi variabel menjadi numerik. Dua skenario pembagian data dilakukan, yaitu 70:30 dan 80:20 untuk keperluan pelatihan dan pengujian model. Hasil evaluasi performa model menunjukkan bahwa algoritma Naive Bayes menghasilkan akurasi sebesar 77,23% dengan pembagian data 70:30 dan pada pembagian data 80:20 menghasilkan akurasi sebesar 76,18%. Sementara itu, Algoritma Random Forest menghasilkan akurasi sebesar 92.84% dengan pembagian data 70:30 dan pada pembagian data 80:20 menghasilkan akurasi sebesar 93,24%.Berdasarkan hasil tersebut, dapat disimpulkan bahwa algoritma Random Forest memiliki kinerja klasifikasi yang lebih unggul dibandingkan Naive Bayes, karena mampu menghasilkan akurasi yang lebih tinggi dan stabil pada kedua skenario pembagian data. Kata kunci: Status Gizi Balita, Naive Bayes, Random Forest, Z-score, Klasifikasi.
Actions (login required)
 |
View Item |
