Aswan Supriyadi Sunge

@sibara.pelitabangsa.ac.id

Department of Informatics Engineering
Pelita Bangsa University

Aswan Supriyadi Sunge


                     Download Compact PDF  
https://researchid.co/aswan26

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Science, Computer Engineering, Artificial Intelligence, Software
13

Scopus Publications

343

Scholar Citations

9

Scholar h-index

9

Scholar i10-index

Scopus Publications

  • An explainable data-driven framework for short-term residential energy forecasting
    Julien Nkunduwera Mupenzi, Deden Witarsyah, Adhi Kusnadi, Aswan Supriyadi Sunge
    Energy and Buildings, 2026
  • The Effect of Feature Selection Based on CatBoost, LIME, SHAP, and Random Forest in Identifying the Risk of Violence Against Women
    Harco Leslie Hendric Spits Warnars, Aswan Supriyadi Sunge, Suzanna, Beni Bevlyadi, Maybin Muyeba
    Studies in Computational Intelligence, 2026
  • Interpretable Machine Learning for Miscarriage Risk Prediction Using Anchor Rules and Counterfactual Explanations on Large Scale Data
    Aswan Supriyadi Sunge
    Hunan Daxue Xuebao Journal of Hunan University Natural Sciences, 2025
    Miscarriage remains a critical concern in maternal health, particularly during early pregnancy when medical intervention options are limited. Although machine learning models have shown promise in identifying high-risk cases, their predictive opacity often undermines clinical trust and adoption. This study proposes an interpretable framework for analyzing miscarriage predictions by combining anchor rules and counterfactual explanations. A Random Forest classification model is applied to a dataset of maternal medical records, and its predictions are interpreted using explainable AI techniques that generate logical rule patterns (anchors) and simulate “what-if” scenarios (counterfactuals). Anchor rules provide human-understandable conditions that strongly influence the model’s decisions, while counterfactual explanations highlight the minimal changes required to alter prediction outcomes. The primary objective of this research is to develop a clinical decision support system that is not only accurate but also transparent and trustworthy for healthcare professionals, particularly for early miscarriage risk detection. The novelty of this approach lies in the integration of two explainability methods rarely combined in maternal health contexts, alongside an evaluation strategy that moves beyond conventional performance metrics such as Accuracy, Precision, Recall, F1-Score, or AUC, focusing instead on interpretability and practical relevance. This work holds significant value for clinicians by delivering actionable insights through clear and consistent risk patterns, thereby facilitating faster, more informed decision-making. Additionally, it contributes to the computer science community by demonstrating how robust machine learning models can be aligned with transparency, ethics, and accountability principles via explainable AI techniques especially in sensitive and high-stakes domains such as maternal and child healthcare. Keywords: Explainable AI; Miscarriage Prediction; Anchor Rule; Counterfactual Explanation; Pregnancy Health.
  • Prediction of Violence Against Women Using Ensemble Learning Models: A Comparative Study of LightGBM, XGBoost, and Others
    Harco Leslie Hendric Spits Warnars, Aswan Supriyadi Sunge, Suzanna, Beni Bevlyadi, Maybin K. Muyeba
    International Journal of Safety and Security Engineering, 2025
    Violence against women and the possibility of its occurrence among children is a very serious issue that negatively impacts the physical, psychological, and emotional aspects of the victims and those around them.Various efforts have been made to reduce violence against women and children; however, in reality, such violence still occurs significantly in many countries due to emotions and turmoil within human relationships.It is necessary to propose prediction methods so that violence can be reduced through early observation and intervention against violence experienced by women.machine learning, as one of the Artificial Intelligence algorithms, offers a solution to identify and predict the risk of violence.This study aims to explore the use of several Ensemble Learning models, such as LightGBM, XGBoost, CatBoost, and AutoEnsemble, which are expected to improve prediction accuracy and stability.This study uses a dataset consisting of 348 samples with 5 selected features that represent indicators relevant to the risk of violence against women.The test results show that XGBoost and CatBoost achieved the highest accuracy, approximately 73%, with a precision of 76%, recall of 65%, and F1-Score of 70%.TabNet demonstrated similar performance with an accuracy of 73%, but with a higher recall of 70%.Meanwhile, LightGBM showed slightly lower performance with 68% accuracy and an F1-Score of 64%.AutoEnsemble produced stable results with 73% accuracy, 76% precision, 65% recall, and 70% F1-Score.However, the practical limitation of this study lies in the relatively small dataset size, which may affect the model's generalization ability when applied to larger or more diverse features.The findings of this study indicate that Ensemble Learning models can provide accurate and effective results in predicting violence against women.It is hoped that this research can contribute to more proactive and accurate efforts to prevent violence against women in the future.
  • Benchmarking Automated Machine Learning Frameworks for Miscarriage Classification with Shap-Based Feature Interpretation
    Aswan Supriyadi Sunge, Harco Leslie Hendric Spits Warnars, Maybin K. Muyeba, Sri Rahayu, Arief Teguh Nugraha
    2025 IEEE International Biomedical Instrumentation and Technology Conference Ibitec 2025, 2025
    Miscarriage is a common pregnancy complication with significant physical and psychological effects. Early risk detection is essential to prevent severe outcomes. This study compares three AutoML frameworks—TPOT, H2O, and AutoGluon—for classifying miscarriage risk using physiological and behavioral data from an open-access GitHub dataset. Data preprocessing included cleaning and class balance checks to ensure data integrity and reliability. Evaluation metrics comprised Accuracy, Precision, Recall, F1-Score, AUC, and Confusion Matrix analysis to provide a comprehensive performance assessment. AutoGluon outperformed the others with an F1-score of 73.87% and accuracy of 69.82%, demonstrating its robustness in handling tabular clinical data. TPOT's model was further analyzed using SHAP values to interpret feature contributions, revealing heart rate (bpm) and stress as critical predictors. The integration of interpretability enhances model transparency, promoting trust and practical adoption in clinical settings. This study contributes valuable insights into AutoML capabilities for miscarriage prediction and highlights the importance of explainable AI in healthcare.
  • The model interpretability on SHAP and comparison classification selection feature for heart disease prediction
    Aswan Supriyadi Sunge, Amali, Ahmad Turmudi ZY, Dendy K. Pramudito, Aceng Badruzzaman, Purwanto
    Procedia Computer Science, 2024
    How to predict coronary heart disease is a very important factor in determining human safety, because it can cause various complications, the most fatal of which is death. Although predictions based on medical record data are very helpful, this can be an obstacle because the influential features are not yet known. After all, Machine Learning (ML) helps in learning patterns from medical record data. After getting the influential features, they will be tested with the Classifier model to see which one is the best for accurate and efficient coronary heart prediction. The dataset obtained was obtained from 4240 secondary data consisting of 16 features and 2 classes, namely Yes and No with the class name TenYearCHD or patients who suffered from coronary heart disease within 10 years after the examination. Dataset testing looks for the highest or most influential features with the SHapley Additive exPlanations (SHAP) model so that interpretability is easy to understand for each feature displayed. Finally, the test uses selected data from the highest feature test results with the classifier model. From the test results, the most disturbing and influencing features are age, sysBP, and cigsPerday, then the test results with the classifier model with the highest features are an accuracy of 85% with the Logistic Regression and Gradient Boosting models. The research aims to look for highly influential features that have never been conducted in other studies related to heart disease and compare other classification models using highly influential features, which so far other studies have only tested the entire data set. It is hoped that this will lead to prototype design or model development as a handy tool for other research and the medical world, especially in detecting heart disease.
  • PERFORMANCE COMPARISON OF DECISION TREE, RANDOM FOREST, AND XGBOOST MODELS; AND ITS INTERPRETABILITY USING SHAP FOR RECOGNIZING THE NECESSITY OF CAESAREANS SECTION OF CHILDBIRTH
    Journal of Theoretical and Applied Information Technology, 2023
  • Interpretable Using Feature Importance, SHAP and LIME for Caesar's Prediction
    International Journal of Applied Engineering and Technology London, 2023
  • Machine Learning Methods for Predicting the Necessity of Caesareans Section of Childbirth
    Aswan Supriyadi Sunge, Yaya Heryadi, Edi Abdurachman, Iman H. Kartowisatro
    Proceedings 2021 IEEE 5th International Conference on Information Technology Information Systems and Electrical Engineering Applying Data Science and Artificial Intelligence Technologies for Global Challenges During Pandemic Era Icitisee 2021, 2021
    In the process of delivery usually the baby comes out of the vagina but under some circumstances a cesarean section is performed. Caesarean section, on the one hand can have short-term and long-term effects for the mother but on the other hand it is a life-saving procedure for both mother and child. The purpose of this study is to predict whether or not a caesarean section is necessary for a pregnant mother using a machine learning classifier model and some features from medical records as input data. In this study, some machine models were explored including Logistic Regression, K-Nearest Neighbor, Random Forest, Decision Tree, Gradient Boosting and Support Vector Machine. The experiment found that Logistic Regression model achieved the highest performance as measured by average accuracy 95%, average precision 86%, average recall 95%, and average F1 86%.
  • Comparison of Distance Function to Performance of K-Medoids Algorithm for Clustering
    Aswan Supriyadi Sunge, Yaya Heryadi, Yoga Religia, Lukas
    Proceeding Icosta 2020 2020 International Conference on Smart Technology and Applications Empowering Industrial Iot by Implementing Green Technology for Sustainable Development, 2020
    The clustering task aims to assign a cluster for each observation data in such a way that observations data within each cluster are more homogeneous to one another than with those in the other groups. Its wide applications in many research fields have motivated many researchers to propose a plethora of clustering algorithms. K-medoids are a prominent clustering algorithm as an improvement of the predecessor, K-Means algorithm. Despite its widely used and less sensitive to noises and outliers, the performance of K-medoids clustering algorithm is affected by the distance function. This paper presents experimentation findings to compare the performance of K-medoids clustering algorithm using Euclidean, Manhattan and Chebyshev distance functions. In this study the K-medoids algorithm was tested using the village status dataset from Gorontalo Province, Indonesia. Execution time and Davies Bouldin Index were used as performance metrics of the clustering algorithm. Experiment results showed that methods of Manhattan distance and Euclidean distance with the Index Davies value of 0.050.
  • Prediction Diabetes Mellitus Using Decision Tree Models
    Aswan Supriyadi Sunge, Harco Leslie Hendric S. Warnar, Yaya Heryadi, Edi Abdurachman, Benfano Soewito, Ford Lumban Gaol
    2019 International Congress on Applied Information Technology Ait 2019, 2019
  • The E-Commerce Implementation to Improve the Agricultural Product by using User Centered Design Method
    Popon Handayani, Sri Utami, Wisti Dwi Septiani, Ida Darwati, Wati Erawati, Panji Madya Ramdani, Endang Suparni, Octa Pratama Putra, Aswan Supriyadi Sunge
    Journal of Physics Conference Series, 2019
  • Comparison of Distance Methods in K-Means Algorithm for Determining Village Status in Bekasi District
    Yoga Religia, Aswan Supriyadi Sunge
    Proceeding 2019 International Conference of Artificial Intelligence and Information Technology Icaiit 2019, 2019

RECENT SCHOLAR PUBLICATIONS

  • An Explainable Hybrid Machine Learning Framework for Financial and Tax Fraud Analytics in Emerging Economies
    JN Mupenzi, A Kusnadi, D Witarsyah, AS Sunge
    Jurnal Teknik Informatika 2 (2026), 194 , 2026
    2026
  • SOSIALISASI DAN PENDAMPINGAN PEMANFAATAN AI UNTUK EFISIENSI PEMBUATAN BAGAN TANDING TURNAMEN PENCAK SILAT DI IPSI CIKARANG SELATAN
    AH Anshor, AS Sunge, TN Wiyatno, E Erdi, R Rismawati
    Jurnal Dinamika Pengabdian 11 (2), 111-119 , 2026
    2026
  • Designing Prototypes in Making Automatic Predictions Drying Clothes
    AS Sunge, C Naya, AZ Kamalia, NT Kurniadi, I Afrianto, A Suwarno
    International Conference on Industrial Electronics, Robotics and Informatics … , 2025
    2025
  • Komparasi Algoritma Linear Regression & Machine learning untuk Memprediksi Pengaruh Tingkat Pendidikan Terhadap Jumlah Pengangguran Terbuka di Jawa Barat
    A Surahman, TY Agustian, AS Sunge
    Jurnal RESTIKOM: Riset Teknik Informatika dan Komputer 7 (3), 344-358 , 2025
    2025
  • Interpretable Machine Learning for Miscarriage Risk Prediction Using Anchor Rules and Counterfactual Explanations on Large Scale Data
    AS Sunge, HLHS Warnars, MK Muyeba, S Rahayu, AT Nugraha
    Journal of Hunan University Natural Sciences 52 (2025), 18-30 , 2025
    2025
  • Benchmarking Automated Machine Learning Frameworks for Miscarriage Classification with Shap-Based Feature Interpretation
    AS Sunge, HLHS Warnars, MK Muyeba, S Rahayu, AT Nugraha
    2025 IEEE International Biomedical Instrumentation and Technology Conference … , 2025
    2025
  • Pelatihan Pembuatan Toko Online E-Commerce Terintegrasi Database MySQL Untuk Meningkatkan Kompetensi Digital Siswa
    AS Sunge, D Pramudito, N Susanto, AT Nugraha
    Jurnal Pengabdian Pelitabangsa 6 (2025), 31-41 , 2025
    2025
  • The Effect of Feature Selection Based on CatBoost, LIME, SHAP, and Random Forest in Identifying the Risk of Violence Against Women
    HLHS Warnars, AS Sunge, Suzanna, B Bevlyadi, M Muyeba
    Advances in Smart Knowledge Computing, 331–347 , 2025
    2025
  • Analysis of Predicting the Number of Rejected Chips Using Random Forest at PT. Wahyu Kartumasindo Internasional
    A Supriyadi, AS Sunge, N Tedi
    Journal of Computer Networks, Architecture and High Performance Computing 7 … , 2025
    2025
  • Interpretable Machine Learning for Employee Recruitment Prediction Using Boruta, CatBoost, Lasso, Logistic Regression, NLP, and RFE Feature Selection
    AS Sunge, Suzanna, HMM Putra
    Jurnal Teknik Informatika (JUTIF) 6 (4), 2153-2170 , 2025
    2025
    Citations: 3
  • Penerapan Model MobileNetV2 Untuk Prediksi Tingkat Roasting Biji Kopi Berbasis Gambar Pada Bot Telegram
    N Pratama, AS Sunge, E Budiarto
    RIGGS: Journal of Artificial Intelligence and Digital Business 4 (2), 4571-4576 , 2025
    2025
  • Dampak Pelatihan Pembuatan Toko Online Berbasis E-Commerce Dengan Metode Rapid Prototyping Bagi Siswa Sekolah Menengah Kejuruan
    AS Sunge, DK Pramudito, SA Prasetyo
    JPM: Jurnal Pengabdian Masyarakat 5 (2025), 396-404 , 2025
    2025
  • Prediction of Violence Against Women Using Ensemble Learning Models: A Comparative Study of LightGBM, XGBoost, and Others.
    HLHS Warnars, AS Sunge, B Bevlyadi, MK Muyeba
    International Journal of Safety & Security Engineering 15 (4) , 2025
    2025
    Citations: 1
  • Optimasi Prediksi Diabetes Mellitus Menggunakan Komparasi Random Forest dan SVM dengan Analisis Pemilihan Fitur Berbasis SHAP
    AS Sunge, DK Pramudito, AH Anshor, E Widodo
    Prosiding Sains dan Teknologi (SAINTEK) 4, 664 - 670 , 2025
    2025
  • Kepuasan Siswa dalam Pembelajaran Interaktif Animasi 2 Dimensi Matahari Terbit Melalui Pendekatan ADDIE
    AS Sunge, DK Pramudito, SA Prasetyo
    Jurnal Pengabdian kepada Masyarakat Nusantara 6 (1), 327-333 , 2025
    2025
    Citations: 3
  • Comparative Analysis of Earthquake Prediction with SVM, Naïve Bayes, and K-Means Models
    AF Muttaqin, AS Sunge, AT Zy
    Journal of Computer Networks, Architecture and High Performance Computing 7 … , 2025
    2025
    Citations: 2
  • Prediksi Sentiment Analysis Dalam Membahas Produk Di E-Commerce Dengan Algoritma Naive Bayes
    N Kurniasih, AS Sunge, A Amali, BE Priyo, TI Trialfhianty
    Jurnal SIGMA 15 (3), 52-60 , 2024
    2024
  • Sistem Informasi Buku Tamu Berbasis Web pada MA Nihayatul Amal Menggunakan Metode Waterfall
    MF Pasaribu, AS Sunge, FE Putra
    Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi 13 (3), 2211-2222 , 2024
    2024
    Citations: 4
  • Using Graph Neural Networks and CatBoost for Internet Security Prediction with SMOTE
    AS Sunge, SWHL Hendric, DK Pramudito
    Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) 10 (4), 747-762 , 2024
    2024
    Citations: 4
  • Association Relationship Analysis in Finding Sales of Goods With Apriori Algorithm
    H Fathurrahman, AS Sunge, S Butsianto
    Journal of Computer Networks, Architecture and High Performance Computing 6 … , 2024
    2024
    Citations: 4

MOST CITED SCHOLAR PUBLICATIONS

  • Perbandingan Algoritma Linear Regression, LSTM, dan GRU Dalam Memprediksi Harga Saham Dengan Model Time Series Stock Price Prediction Using Time Series Model By Comparing …
    K Sofi, AS Sunge, SR Riady, AZ Kamalia
    2021
    Citations: 57
  • Prediksi Penjualan Obat Dan Alat Kesehatan Terlaris Menggunakan Algoritma K-Nearest Neighbor
    A Azis, AT Zy, AS Sunge
    Jurnal Teknologi Dan Sistem Informasi Bisnis 6 (1), 117-124 , 2024
    2024
    Citations: 27
  • Prediksi Kompetensi Karyawan Menggunakan Algoritma C4.5 (Studi Kasus : PT Hankook Tire Indonesia)
    AS Sunge
    Seminar Nasional Teknologi Informasi dan Komunikasi (SENTIKA) 1 (Universitas … , 2018
    2018
    Citations: 25
  • Analisis Sentimen Tentang Mobil Listrik Dengan Metode Support Vector Machine Dan Feature Selection Particle Swarm Optimization
    A Santoso, A Nugroho, AS Sunge
    Journal of Practical Computer Science 2 (1), 24-31 , 2022
    2022
    Citations: 20
  • Klasifikasi Penetapan Status Karyawan Dengan Menggunakan Metode Naïve Bayes
    F Ariani, NA Amir, K Rizal, C Sitasi, AS Sunge
    ILKOM Jurnal Komputer Dan Informatika 20 (2) , 2018
    2018
    Citations: 18
  • Sistem smart door lock menggunakan voice recognition berbasis Arduino
    RF Rizky, AT Zy, AS Sunge
    Bulletin of Information Technology (BIT) 4 (2), 239-244 , 2023
    2023
    Citations: 17
  • Comparison of distance function to performance of K-medoids algorithm for clustering
    AS Sunge, Y Heryadi, Y Religia
    2020 International Conference on Smart Technology and Applications (ICoSTA), 1-6 , 2020
    2020
    Citations: 17
  • Optimasi Algoritma C4. 5 Dalam Prediksi Web Phishing Menggunakan Seleksi Fitur Genetic Algoritma
    AS Sunge
    Paradigma , 2018
    2018
    Citations: 17
  • Analisis Sentimen Masyarakat Dengan Metode Naïve Bayes dan Particle Swarm Optimization
    SD Pramukti, A Nugroho, AS Sunge
    publikasi.dinus.ac.id, 62-75 , 2022
    2022
    Citations: 12
  • Analisis Prediksi Penjualan Dengan Metode Regresi Linear Di Pt. Eagle Industry Indonesia
    AS Sunge, AT Zy
    Jurnal Informatika Teknologi dan Sains (Jinteks) 5 (3), 398-403 , 2023
    2023
    Citations: 9
  • The model interpretability on shap and comparison classification selection feature for heart disease prediction
    AS Sunge, AT ZY, DK Pramudito, A Badruzzaman
    Procedia Computer Science 245, 210-219 , 2024
    2024
    Citations: 8
  • Prediction diabetes mellitus using decision tree models
    AS Sunge, HLHS Warnar, Y Heryadi, E Abdurachman, B Soewito, ...
    2019 International Congress on Applied Information Technology (AIT), 1-6 , 2019
    2019
    Citations: 7
  • Comparison of Distance Methods in K-Means Algorithm for Determining Village Status in Bekasi District
    Y Religia, AS Sunge
    International Conference of Artificial Intelligence and Information … , 2019
    2019
    Citations: 7
  • Machine Learning Methods for Predicting the Necessity of Caesareans Section of ChildBirth
    AS Sunge, E Abdurachman, Y Heryadi, IH Kartiwisastro
    Information System and Electrical Engineering (ICITISEE) 2021 , 2021
    2021
    Citations: 6
  • Comparison Data Mining Techniques To Prediction Diabetes Mellitus
    AS Sunge
    Journal of Sustainable Engineering: Proceedings Series 1(2) 2019 2 (23 … , 2019
    2019
    Citations: 6
  • Perbandingan algoritma linear regression, LSTM, dan GRU dalam memprediksi harga saham dengan model time series. PROSIDING SEMINASTIKA, 3 (1), 39-46
    K Sofi, AS Sunge, SR Riady, AZ Kamalia
    2021
    Citations: 5
  • Implementasi Cost Control System Berbasis Website pada Departemen PPIC PT XYZ Menggunakan Analisis SWOT
    K Sofi, AS Sunge, RRW Ken Widodasih, SR Riady
    Jurnal Sains Indonesia 1 (http://jurnal.pusatsains.com/) , 2020
    2020
    Citations: 5
  • Sistem Informasi Buku Tamu Berbasis Web pada MA Nihayatul Amal Menggunakan Metode Waterfall
    MF Pasaribu, AS Sunge, FE Putra
    Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi 13 (3), 2211-2222 , 2024
    2024
    Citations: 4
  • Using Graph Neural Networks and CatBoost for Internet Security Prediction with SMOTE
    AS Sunge, SWHL Hendric, DK Pramudito
    Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) 10 (4), 747-762 , 2024
    2024
    Citations: 4
  • Association Relationship Analysis in Finding Sales of Goods With Apriori Algorithm
    H Fathurrahman, AS Sunge, S Butsianto
    Journal of Computer Networks, Architecture and High Performance Computing 6 … , 2024
    2024
    Citations: 4