Electronic Theses and Dissertation

Stunting merupakan kondisi di mana pertumbuhan anak balita terhambat akibat kekurangan gizi kronis. stunting menjadi salah satu tantangan serius di berbagai daerah, termasuk di desa meunasah papeun provinsi aceh. penelitian ini bertujuan untuk mengimplementasikan dan membandingkan tiga algoritma machine learning, yaitu k-nearest neighbor (knn), random forest (rf), dan support vector machine (svm), dalam mengklasifikasikan status stunting pada balita di desa meunasah papeun provinsi aceh. evaluasi dilakukan berdasarkan akurasi dan efisiensi waktu eksekusi. hasil menunjukkan bahwa algoritma svm memberikan akurasi tertinggi sebesar 90%, selanjutnya diikuti oleh rf sebesar 86,67% dan knn sebesar 73,33%. berdasarkan efisiensi waktu, knn memiliki waktu eksekusi sebesar 44,13 detik, diikuti rf sebesar 45,88 detik, dan svm sebesar 48,94 detik. seluruh pengujian dilakukan pada komputer dengan spesifikasi yang sama untuk memastikan perbandingan objektif. penelitian ini dapat memberikan kontribusi pemanfaatan machine learning di bidang kesehatan sebagai alat bantu dalam mendeteksi risiko balita stunting secara lebih efisien. kata kunci: stunting, machine learning, k-nearest neighbor (knn), random forest (rf), support vector machine (svm), klasifikasi.

Stunting is a condition in which the growth of toddlers is hampered due to chronic malnutrition. Stunting is a serious challenge in various regions, including Meunasah Papeun Village, Aceh. This study aims to implement and compare three machine learning algorithms, namely K-Nearest Neighbor (KNN), Random Forest (RF), and Support Vector Machine (SVM), in classifying stunting status in toddlers in Meunasah Papeun Village, Aceh. Evaluation was carried out based on accuracy and execution time efficiency. The results showed that the SVM algorithm provided the highest accuracy of 90%, followed by RF at 86.67% and KNN at 73.33%. Based on time efficiency, KNN had an execution time of 44.13 seconds, followed by RF at 45.88 seconds, and SVM at 48.94 seconds. All tests were conducted on computers with the same specifications to ensure objective comparisons. This research can contribute to the use of machine learning in the health sector as a tool to assist in detecting the risk of stunting in toddlers more efficiently. Keywords: Stunting, Machine Learning, K-Nearest Neighbor (KNN), Random Forest (RF), Support Vector Machine (SVM), Classification.