<![CDATA[Stunting is a condition in which toddlers have a shorter height compared to the normal growth standard for their age. Preventing stunting is crucial, as children with stunting are more vulnerable to illnesses, experience growth failure before the age of 12 months, and tend to have lower intellectual abilities. Stunting can be diagnosed even before birth by assessing the nutritional status of pregnant women. Pregnant women with poor nutritional status are at a higher risk of delivering babies with low birth weight (LBW), which in turn increases the risk of stunting. Diagnosing the nutritional status of pregnant women and the risk of giving birth to stunted children typically requires expert knowledge, such as that of midwives or obstetricians. Expert systems make it possible for pregnant women to receive real-time diagnoses without the need for direct consultations with healthcare professionals. Expert knowledge in identifying the nutritional status of pregnant women and indicators of stunting risk is stored in a knowledge base, which is translated into a computer-readable rule base in the form of IF-THEN statements. This process is known as knowledge acquisition. The accuracy of the rule base plays a crucial role in ensuring reliable diagnostic results. Decision Tree is one of the data mining algorithms used to generate rule bases. In this study, the Decision Tree algorithm is optimized using Grid Search as a knowledge acquisition technique to determine the rule base applied in the Stunting Prevention Expert System (SIPENTING). The system is Android-based and aims to help pregnant women better understand their nutritional needs. Testing and validation results show that the Decision Tree model achieved an accuracy of 86.3%.]]>
Copyrights © 2025
