Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal JITK (Jurnal Ilmu Pengetahuan dan Komputer) REMIK : Riset dan E-Jurnal Manajemen Informatika Komputer
Khairul Hawani Rambe
Politeknik Negeri Bali
Computer Science & IT Decision Sciences, Operations Research & Management Education

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

Found 2 Documents
Search

 1 
Model Ensemble Stacking untuk Klasifikasi Big Data Stunting Berbasis XGBoost dan MLP Khairul Hawani Rambe; Frans Mikael Sinaga; Leni Anggraini Susanti; Moh. Erkamim
REMIK: Riset dan E-Jurnal Manajemen Informatika Komputer Vol. 10 No. 1 (2026): Volume 10 Nomor 1 Januari 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/remik.v10i1.15903

Abstract

Klasifikasi status gizi balita berbasis data besar memerlukan pendekatan machine learning yang mampu menangani kompleksitas dan heterogenitas data secara akurat dan stabil. Populasi penelitian mencakup seluruh data rekam medis balita periode 2023–2024 yang diperoleh dari RS Mitra Medika Tanjung Mulia, dengan teknik pengambilan sampel menggunakan total sampling terhadap dataset yang tersedia. Sampel berupa data antropometri balita yang meliputi jenis kelamin, usia, berat badan, tinggi atau panjang badan, nilai Z-score, serta label status gizi. Metode yang digunakan adalah pendekatan kuantitatif berbasis machine learning dengan tahapan pra-pemrosesan, pembangunan model, dan evaluasi performa. Pra-pemrosesan mencakup pembersihan data, transformasi variabel kategorikal, normalisasi fitur numerik, serta pembagian data latih dan data uji dengan rasio 80:20. Model yang dikembangkan menggunakan pendekatan ensemble stacking dengan XGBoost sebagai base learner dan Multi-Layer Perceptron (MLP) sebagai meta learner. Evaluasi kinerja model dilakukan menggunakan confusion matrix, precision, recall, F1-score, dan akurasi. Hasil pengujian menunjukkan bahwa model stacking mencapai akurasi sebesar 99,64% dengan jumlah kesalahan prediksi yang sangat rendah serta nilai precision, recall, dan F1-score yang seimbang pada setiap kelas. Temuan ini menunjukkan bahwa integrasi algoritma boosting dan neural network mampu meningkatkan stabilitas dan kemampuan generalisasi model. Dengan demikian, pendekatan stacking XGBoost–MLP efektif dalam klasifikasi status gizi balita dan berpotensi diterapkan sebagai sistem pendukung keputusan deteksi dini masalah gizi berbasis big data.
ENHANCING SENTIMENT ANALYSIS ACCURACY WITH BERT AND SILHOUETTE METHOD OPTIMIZATION Kelvin Kelvin; Frans Mikael Sinaga; Wulan Sri Lestari; Sunaryo Winardi; Khairul Hawani Rambe; Ronsen Purba
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 1 (2025): JITK Issue August2025
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i1.6392

Abstract

This research is based on the emergence of ChatGPT technology, which has significant implications in various fields. This research aims to design a model that improves sentiment analysis classification accuracy. The methods applied include the use of the Silhouette Coefficient to determine the best cluster parameters before performing data grouping with the Self-Organizing Map (SOM) method. Additionally, the Bidirectional Encoder Representations from Transformers (BERT) model is utilized to perform precise and convergent sentiment classification. The research methodology encompasses several phases, including data preprocessing through natural language processing techniques. Textual data is converted into vector representations, which are then processed using the Silhouette Coefficient to identify the optimal cluster parameters. These parameters are subsequently applied in the Self-Organizing Map method to cluster data, while the Bidirectional Encoder Representations from Transformers model determines public sentiment, categorized as positive, negative, or neutral. The findings of this study indicate that the best cluster parameter is 9, using a batch size of 64 and a maximum sequence length of 128. The highest accuracy achieved using the confusion matrix is 92.06%. Further tests with varying parameters confirm that the Silhouette Coefficient method significantly enhances the convergence and accuracy of classification outcomes. The conclusion of this research is that integrating the Silhouette Coefficient and Bidirectional Encoder Representations from Transformers is effective in optimizing sentiment analysis on large datasets, achieving both accurate and reliable results.
Co-Authors Frans Mikael Sinaga Kelvin Kelvin Leni Anggraini Susanti Moh. Erkamim Ronsen Purba Winardi, Sunaryo Wulan Sri Lestari