Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Jurnal Masyarakat Informatika Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer
Darnell Ignasius
Universitas Dian Nuswantoro
Aerospace Engineering Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

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

Found 2 Documents
Search

 1 
Comparative Evaluation of Machine Learning Algorithms with Data Balancing Approach and Hyperparameter Tuning in Predicting Thyroid Disorder Recurrence Darnell Ignasius; Rhyan David Levandra; Ramadhan Rakhmat Sani; Ika Novita Dewi
Jurnal Masyarakat Informatika Vol 16, No 2 (2025): November 2025
Publisher : Department of Informatics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jmasif.16.2.75073

Abstract

This research evaluates and compares the performance of five machine learning algorithms (Logistic Regression, K-Nearest Neighbors, Decision Tree, Random Forest, and Gradient Boosting) in predicting thyroid disease recurrence using patient data. The analysis was conducted on the Thyroid Disease Dataset from the UCI Machine Learning Repository. The methodology includes data preprocessing, normalization, and class balancing with the Synthetic Minority Over-sampling Technique (SMOTE). Additionally, hyperparameter tuning was conducted using GridSearchCV to optimize model performance. The results demonstrate that ensemble-based models, specifically Random Forest and Gradient Boosting, consistently outperform the other algorithms in terms of accuracy and robustness. These models achieve 95–96% accuracy across various scenarios.A key finding is that SMOTE significantly improves recall for minority classes, highlighting its value in imbalanced medical datasets.
Domain Adaptation of Bert Models for Biomedical Entity Extraction from Indonesian Health News Maria Bernadette Chayeenee Norman; Ika Novita Dewi; Darnell Ignasius
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 10 No. 1 (2026)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v10i1.2116

Abstract

Health-related news articles play an increasingly important role in public health monitoring. However, their unstructured linguistic style complicates the automatic extraction of biomedical information. Indonesian health news shows high lexical variation by combining medical terms, colloquial expressions, borrowed Eng-lish words, and culturally specific symptom descriptions. This condition creates challenges for Named Entity Recognition (NER). To address the limited availability of domain-specific resources, this study compares four Transformer-based models, namely BERT, IndoBERT, RoBERTa, and BioBERT, for biomedical NER in Indone-sian health news. A new BIO-annotated dataset consisting of 272 manually labeled articles was constructed and validated, achieving strong inter-annotator agreement (Cohen’s Kappa = 0.88). To reduce data limita-tions, an additional 103 articles were automatically annotated using the best-performing model, RoBERTa, through a semi-supervised approach. All models were fine-tuned under identical settings and evaluated at both BIO and entity levels. The results show that RoBERTa achieves the highest weighted F1-score (0.9543). Howev-er, its macro F1-score (0.3873) indicates uneven performance across entity classes because of severe label im-balance, with non-entity tokens dominating the dataset. This finding highlights the importance of emphasizing macro-level evaluation to better reflect entity recognition performance. RoBERTa consistently outperforms the other models, which may be explained by its robust architecture and adaptability to diverse linguistic patterns. In contrast, BioBERT underperforms because of cross-lingual and domain mismatch, as it is pretrained on Eng-lish biomedical corpora and optimized for scientific text rather than journalistic language. The error analysis further identifies boundary inconsistencies and under-detection of low-frequency entities, especially in the drug and symptom categories.
Co-Authors Ika Novita Dewi Maria Bernadette Chayeenee Norman Ramadhan Rakhmat Sani Rhyan David Levandra