Yusuf, Farsya Farahdita (2025) KLASIFIKASI STATUS GIZI BALITA DI PUSKESMAS PONDOK RANJI MENGGUNAKAN ALGORITMA NAIVE BAYES DAN KNN. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (381kB) | 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 (41kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (313kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (60kB) |
|
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (363kB) |
|
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (30kB) |
|
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (158kB) |
|
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (789kB) |
Abstract
The toddler stage is a critical period for a child’s growth and development, where balanced nutrition plays a key role in supporting optimal health. Monitoring nutritional status is essential to ensure healthy development. The Indonesian Nutrition Status Survey (SSGI) reported that the prevalence of underweight toddlers in Indonesia reached 17.1% in 2022, while overweight cases slightly decreased from 3.8% to 3.5% in the same year. In Ciputat Timur District, the prevalence of malnutrition among toddlers was recorded at 2.97% in the same year, highlighting the need for further intervention. This study aims to classify toddler nutritional status using Naive Bayes and K-Nearest Neighbors (KNN) algorithms, with a case study at Pondok Ranji Health Center. The secondary data used includes parameters such as weight, height, and age. Naive Bayes utilizes a probabilistic approach, while KNN classifies based on the distance between data points. Testing results show that KNN outperforms Naive Bayes, achieving an accuracy of 98.00%, precision of 94.48%, recall of 90.85%, and F1-score of 92.60%. In comparison, Naive Bayes obtained an accuracy of 80.64%, precision of 78.29%, recall of 45.83%, and F1-score of 50.83%. These findings suggest that KNN is more effective for classifying toddler nutritional status on the dataset used. The results can serve as a reference for developing data-based systems to support nutritional monitoring, such as simple dashboards or applications at health centers, enabling healthcare workers to input data and obtain nutritional predictions quickly and efficiently. Keywords: Nutritional Status, Naive Bayes, Toddlers, K-Nearest Neighbors, Classification Masa balita merupakan periode krusial dalam pertumbuhan dan perkembangan anak, di mana pemenuhan gizi seimbang menjadi kunci untuk mendukung kesehatan secara optimal. Pemantauan status gizi balita menjadi penting untuk memastikan tumbuh kembang yang sesuai. Survei Status Gizi Indonesia (SSGI) mencatat bahwa prevalensi balita underweight di Indonesia mencapai 17,1% pada 2022, dan overweight sedikit menurun dari 3,8% pada menjadi 3,5% di tahun 2022. Di Kecamatan Ciputat Timur, prevalensi gizi buruk pada balita sebesar 2,97% di tahun yang sama menunjukkan perlunya upaya lebih lanjut. Penelitian ini bertujuan untuk mengklasifikasikan status gizi balita menggunakan algoritma Naive Bayes dan K-Nearest Neighbors (KNN) dengan studi kasus di Puskesmas Pondok Ranji. Data sekunder yang digunakan mencakup parameter seperti berat badan, tinggi badan, dan usia. Naive Bayes memanfaatkan pendekatan probabilistik untuk memprediksi status gizi, sedangkan KNN menggunakan jarak terdekat antar data. Hasil pengujian menunjukkan bahwa algoritma KNN memberikan performa lebih baik dengan akurasi 98,00%, precision 94,48%, recall 90,85%, dan F1-score 92,60%. Sementara itu, algoritma Naive Bayes mencatat akurasi 80,64%, precision 78,29%, recall 45,83%, dan F1-score 50,83. Menunjukkan bahwa algoritma KNN lebih unggul dalam mengklasifikasikan status gizi balita pada dataset yang digunakan. Hasil penelitian ini dapat menjadi acuan dalam pengembangan sistem berbasis data untuk mendukung pemantauan gizi balita, seperti dashboard atau aplikasi sederhana di puskesmas, agar tenaga kesehatan dapat memperoleh prediksi status gizi secara cepat dan praktis. Kata kunci: Status Gizi, Naive Bayes, Balita, K-Nearest Neighbors, Klasifikasi
Actions (login required)
 |
View Item |
