Thohir, Sasqia Salsabila At (2026) Sistem Pemetaan Risiko Stunting Pada Balita Di Desa Gempol Menggunakan Algoritma K-Nearest Neighbors (KNN). Undergraduate thesis, Politeknik Negeri Jember.
![[img]](https://sipora.polije.ac.id/style/images/fileicons/text.png) |
Text (Abstract)
ABSTRACT.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (280kB) |
|
Text (Bab 1 Pendahuluan)
BAB I PENDAHULUAN.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (288kB) |
|
Text (Daftar Pustaka)
DAFTAR PUSTAKA.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (262kB) |
|
Text (Laporan Lengkap)
LAPORAN LENGKAP.pdf - Submitted Version Restricted to Registered users only Download (3MB) | Request a copy |
Abstract
This study develops a web-based stunting risk mapping system for toddlers by integrating the K-Nearest Neighbors (KNN) algorithm and Geographic Information System (GIS). The development of this system is motivated by the manual data recording process and the lack of region-based visualization, which makes monitoring stunting conditions difficult. The system utilizes several variables, including sex, age, height, weight, mid-upper arm circumference, head circumference, as well as height-for-age and weight-for-age z-scores, to automatically classify the nutritional status of toddlers. Classification testing was conducted using a confusion matrix by comparing K = 3, 5, 7, and 9 with 500 training data and 261 testing data, where K = 5 achieved the best performance with an accuracy of 88.1%, precision of 37.0%, recall of 89.5%, specificity of 88.0%, and an F1-score of 52.3%. Although the precision value is relatively low, the high recall indicates that the system has a strong ability to detect toddlers at risk of stunting as an early detection tool. Therefore, this system can be utilized as a decision-support tool for monitoring stunting risk based on geographic areas. However, further improvements are needed to enhance precision and achieve better alignment between classification results and actual conditions in the field.
Actions (login required)
 |
View Item |
