Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal RABIT: Jurnal Teknologi dan Sistem Informasi Univrab
Ahmad Junaidi
UNIVERSITAS MALIKUSSALEH
Computer Science & IT Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
KLASIFIKASI STATUS ANAK STUNTING MENGGUNAKAN METODE K-NEAREST NEIGHBOR : CLASSIFICATION OF CHILD STUNTING STATUS USING THE K-NEAREST NEIGHBOR METHOD Ahmad Junaidi; Nurdin Nurdin; Rini Meiyanti
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 10 No 2 (2025): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v10i2.6536

Abstract

Stunting is a public health problem that has a serious impact on children's growth and development, particularly during the first 1,000 days of life. This study aims to implement the K-Nearest Neighbor (KNN) algorithm to classify stunting status in toddlers and to develop a web-based system to support early detection at the Muara Satu Public Health Center. The dataset consists of 558 entries, including age at measurement, birth weight, birth height, current weight, current height, and upper arm circumference. Data normalization was performed using the Min-Max method to standardize feature scales. The classification process applied the Euclidean distance metric and determined the class based on the majority of the three nearest neighbors (k=3). The choice of k was based on preliminary testing, but further optimization is suggested for future research. The developed system allows healthcare workers to input toddler data and automatically obtain classification results as either “Normal” or “Indicated Stunting.” Experimental results show an accuracy of 89.42%, although potential false positives and false negatives remain to be further analyzed. This study is limited to data from a single health center, thus model generalization requires validation with multi-center datasets and larger sample sizes. The integration of machine learning into health information systems has proven to improve the efficiency and accuracy of community nutrition services, and future work is recommended to explore other algorithms such as ensemble learning to further enhance performance.
Co-Authors Nurdin Nurdin Rini Meiyanti