Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Progresif: Jurnal Ilmiah Komputer
Majid, Annisa Maulana
Universitas Pelita Bangsa
Computer Science & IT Control & Systems Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Implementasi Machine Learning Menggunakan Adaboost dalam Prediksi Status Gizi Anak di Posyandu Tanjung XXIV Majid, Annisa Maulana; Nawangsih, Ismasari
Progresif: Jurnal Ilmiah Komputer Vol 20, No 2: Agustus 2024
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v20i2.2143

Abstract

Nutritional status is important for children's growth and development, as well as for measuring nutritional adequacy. Posyandu Tanjung XXIV is a facility for routinely recording children's growth and development, but it still uses manual processes to determine nutritional status so it is not yet effective. Data processing is needed to help predict children's nutritional status. Machine Learning is used for data processing and predicting data based on algorithmic patterns. Previous research related to nutritional status using Machine Learning has been carried out but resulted in a small level of accuracy in the Naïve Bayes algorithm, so accuracy needs to be increased. This research aims to implement Machine Learning using Naïve Bayes combined with the Adaboost method to increase the accuracy of the Posyandu Tanjung XXIV toddler dataset. The research uses variable dataWeight by Age, Height by Age, Weight by Height. The results of the research show that the implementation of Naïve Bayes using Adaboost increases accuracy with results of 100% accuracy, an increase of 6.67% from the implementation of Naïve Bayes independently with results of 93.33%.Keywords: Nutritional status; Machine Learning; Naive Bayes; Adaboost AbstrakStatus Gizi hal yang penting bagi pertumbuhan dan perkembangan anak, serta untuk mengukur kecukupan zat gizi.  Posyandu Tanjung XXIV merupakan fasilitas untuk mendata pertumbuhan dan perkembangan anak secara rutin, namun masih menggunakan proses manual untuk menentukan status gizi sehingga belum efektif. Perlu pengolahan data untuk membantu memprediksi status gizi anak. Machine Learning digunakan untuk pengolahan data serta memprediksi data berdasarkan pola algoritma. Penelitian sebelumnya terkait status gizi menggunakan Machine Learning sudah dilakukan namun menghasilkan tingkat akurasi kecil pada algoritma Naïve Bayes, sehingga perlu peningkatan akurasi. Penelitian ini bertujuan untuk implementasi Machine Learning menggunakan Naïve Bayes dikombinasikan dengan metode Adaboost untuk meningkatkan akurasi dataset balita Posyandu Tanjung XXIV. Penelitian menggunakan data variable Berat Badan menurut Umur, Tinggi Badan menurut Umur, Berat Badan menurut Tinggi Badan. Hasil dari penelitian menunjukkan implementasi Naïve Bayes menggunakan Adaboost meningkatkan akurasi dengan hasil akurasi 100%, meningkat sebesar 6,67% dari penerapan Naïve bayes mandiri dengan hasil 93,33%Kata kunci: Status Gizi; Machine Learning; Naive Bayes; Adaboost 
Penerapan Explainable AI dan Model Stacking Untuk Mengindentifikasi Faktor Risiko Stunting Balita Majid, Annisa Maulana; Nawangsih, Ismasari
Progresif: Jurnal Ilmiah Komputer Vol 22, No 1 (2026): Januari
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i1.3549

Abstract

Stunting remains a nutritional problem in children that is difficult to detect early due to its multifactorial causes and the limitations of conventional analytical approaches. This study aims to develop a stacking-based Machine Learning model for stunting prediction and to implement Explainable Artificial Intelligence (XAI) to interpret the risk factors influencing the prediction outcomes. The methods employed include Decision Tree, Random Forest, and Support Vector Machine (SVM) as base learners, and Logistic Regression as the meta-learner in an ensemble stacking framework, with performance evaluated using accuracy, precision, recall, and F1-score. The results indicate that the Decision Tree algorithm and the Stacking method achieved the best performance with 100% accuracy, while the XAI analysis identified current body weight, birth weight, and age as the primary factors influencing stunting prediction.Keywords: Stunting; Stacking; Machine Learning; Explainable Artificial Intelligence AbstrakStunting masih menjadi permasalahan gizi pada anak yang sulit dideteksi secara dini karena dipengaruhi oleh berbagai faktor dan keterbatasan analisis konvensional. Penelitian ini bertujuan mengembangkan model stacking berbasis Machine Learning untuk prediksi stunting serta menerapkan Explainable Artificial Intelligence (XAI) dalam menginterpretasikan faktor-faktor risiko yang berpengaruh terhadap hasil prediksi. Metode yang digunakan meliputi algoritma Decision Tree, Random Forest, Support Vector Machine (SVM) sebagai base learner dan Logistic Regression sebagai meta learner pada ensemble stacking, dengan evaluasi menggunakan accuracy, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa algoritma Decision Tree dan penerapan metode Stacking menghasilkan kinerja terbaik dengan tingkat akurasi 100%, sementara analisis XAI mengidentifikasi bahwa berat badan, BB lahir, dan usia merupakan faktor utama yang memengaruhi prediksi stunting.Kata kunci: Stunting; Stacking; Machine Learning; Explainable Artificial Intelligence
Co-Authors Nawangsih, Ismasari