Development of an IoT-Based Anthropometric System Employing K-Means Clustering for Stunting Detection and Spatial Mapping in Toddlers

Stunting remains a major public health challenge in Indonesia, affecting children’s physical growth and cognitive development due to inaccurate and delayed monitoring in community health centers. This study aims to develop an Internet of Things (IoT)-based anthropometric measurement and regional stunting mapping system that provides real-time, automated, and spatially contextualized data analysis. The novelty of this research lies in integrating IoT sensor networks with machine learning–based K-Means clustering and statistical validation through the Sum of Squared Error (SSE) method, supported by an automated email alert for high-risk areas. Unlike previous studies that focus solely on anthropometric measurement or standalone IoT monitoring, this study integrates real-time IoT-based data acquisition with K-Means clustering for regional stunting mapping and automated alert generation. The system employs an HC-SR04 ultrasonic sensor, an MPU-6050 gyroscope, and an ESP32 microcontroller for data acquisition and transmission, followed by clustering analysis to categorize stunting prevalence into five levels. Experimental results show high measurement accuracy (mean error of 1.24%) and optimal clustering compactness (SSE = 1.72 × 10³ at k = 5), effectively identifying regions with very high prevalence and visualizing them through a web-based dashboard. Although the study is limited by the use of secondary datasets and pilot- scale validation, the findings demonstrate that the proposed IoT-based framework can enhance data-driven public health decision-making. This innovation aligns with Indonesia’s national stunting reduction strategy and supports Sustainable Development Goal (SDG) 3 Good Health and Well-being, contributing to the digital transformation of early childhood health monitoring.