Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Journal of Information Systems and Informatics
Hamidah
Institut Sains dan Bisnis Atma Luhur
Computer Science & IT

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

Found 2 Documents
Search

 1 
Two-Stage Tuning of Machine Learning Models for Heart Disease Classification on Synthetic Data Marini; Tri Sugihartono; Chandra Kirana; Benny Wijaya; Hamidah
Journal of Information System and Informatics Vol 8 No 3 (2026): June
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i3.1599

Abstract

Heart disease remains a leading global cause of mortality, highlighting the need for accurate early risk classification. This study benchmarks Random Forest, XGBoost, and Logistic Regression for heart disease risk classification using a synthetic, perfectly balanced dataset, while addressing performance limitations caused by inadequate hyperparameter configuration. The dataset comprised 70,000 samples with a 50/50 class distribution and 18 clinical and demographic features. Although useful for controlled benchmarking, synthetic balanced data may yield optimistic estimates and may not fully represent real-world clinical variability. Each model was implemented in a scikit-learn Pipeline with median imputation and, where applicable, standard scaling. A two-stage tuning strategy was applied by combining RandomizedSearchCV with GridSearchCV refinement to optimize model configurations systematically. Under these benchmarking conditions, XGBoost achieved the best test performance, with an F1-score of 99.34%, AUC-ROC of 99.97%, and accuracy of 99.34%. Random Forest obtained an F1-score of 99.20% and AUC-ROC of 99.95%, while Logistic Regression achieved an F1-score of 99.12% and AUC-ROC of 99.95%. Age, pain in the arms/jaw/back, and cold sweats/nausea were the most influential predictors. The proposed framework is reproducible, computationally efficient, and suitable for validation on heterogeneous clinical datasets.
A Hybrid SEM-PLS and ANN Approach for Predicting Student Loyalty in Higher Education Learning Management Systems Hamidah; Sarwindah; Hengki; Tri Sugihartono
Journal of Information System and Informatics Vol 8 No 3 (2026): June
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i3.1625

Abstract

This study aims to develop a hybrid Structural Equation Modeling–Partial Least Squares (SEM-PLS) and Artificial Neural Network (ANN) approach to analyze student loyalty in Learning Management Systems (LMS) at ISB Atma Luhur. Data were collected from 200 students at ISB Atma Luhur, representing a single-institution sample, and analyzed using SEM-PLS to examine causal relationships and ANN (Multilayer Perceptron) implemented in SPSS to support predictive analysis. The model includes e-service quality, user experience, information quality, and system quality as predictors of satisfaction and loyalty. The SEM-PLS results show that E-Service Quality (β = 0.350), System Quality (β = 0.170), and User Experience (β = 0.292) significantly affect Satisfaction, whereas Information Quality is not statistically significant (p = 0.054). Satisfaction positively influences Loyalty (β = 0.360), and User Experience has the strongest direct effect on Loyalty (β = 0.484). The model explains a substantial proportion of variance (R² = 0.717 and 0.631) with positive Q² values (0.460 and 0.379). Across ten independent runs, the ANN model achieved an average accuracy of 84.88% (SD = 2.82) and an average AUC of 0.949 (SD = 0.003), indicating stable predictive performance, indicating promising predictive performance under the current testing configuration. The findings provide context-specific explanatory and predictive insights into student loyalty in LMS, however, they should be interpreted with caution due to discriminant-validity limitations and the single-institution setting of the study.
Co-Authors Benny Wijaya Chandra Kirana Hengki Marini Sarwindah Tri Sugihartono