Article Per Year (5 Year)
p-Index From 2021 - 2026
3.321
P-Index
This Author published in this journals
All Journal CommIT (Communication & Information Technology) Jurnal TIMES Sinkron : Jurnal dan Penelitian Teknik Informatika JIKO (Jurnal Informatika dan Komputer) JOURNAL OF APPLIED INFORMATICS AND COMPUTING METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Jiko (Jurnal Informatika dan komputer) JURIKOM (Jurnal Riset Komputer) JURTEKSI Building of Informatics, Technology and Science Jurnal Ilmiah Smart Journal of Applied Computer Science and Technology (JACOST) Majalah Ilmiah METHODA Journal of Computing Theories and Applications Jurnal Ilmiah Smart
Robet Robet
STMIK TIME
Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Languange, Linguistic, Communication & Media Medicine & Pharmacology Public Health

Published : 32 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 32 Documents
Search

 1   2   3   4 
A Comparative Study of Machine Learning and Deep Learning Models for Heart Disease Classification Simanjuntak, Martina Sances; Robet, Robet; Hoki, Leony
Journal of Applied Informatics and Computing Vol. 9 No. 6 (2025): December 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i6.11546

Abstract

Heart disease remains one of the leading causes of mortality worldwide, necessitating accurate early detection. This study aims to compare the performance of several Machine Learning (ML) and Deep Learning (DL) algorithms in heart disease classification using the Heart Disease dataset with 918 samples. The methods tested included Naïve Bayes, Decision Tree, Random Forest, Support Vector Machine (SVM), Logistic Regression, K-Nearest Neighbor (KNN), and Deep Neural Network (DNN). Preprocessing included feature normalization, data splitting (80:20), and simple hyperparameter tuning for parameter-sensitive models. Evaluations were conducted using accuracy, precision, recall, F1-score, AUC, and confusion matrix analysis to identify error patterns. The results showed that SVM and DNN achieved the highest accuracies of 91.3% and 92.1%, respectively. However, DNN has higher computational costs and risks of overfitting on small datasets. These findings confirm that traditional ML models such as SVM remain highly competitive on tabular medical data.
SECURE DOCUMENT NOTARIZATION: A BLOCKCHAIN-BASED DIGITAL SIGNATURE VERIFICATION SYSTEM Tio, Nicholas; Pribadi, Octara; Robet, Robet
JIKO (Jurnal Informatika dan Komputer) Vol 8, No 3 (2025)
Publisher : Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v8i3.10811

Abstract

The increasing need for trustworthy digital document verification presents challenges in ensuring authenticity, transparency, and tamper resistance without relying on centralized authorities. This study aims to develop and evaluate a decentralized document notarization system using Ethereum and IPFS that offers secure, transparent, and cost-efficient verification. The system employs modular smart contracts deployed through a factory pattern to create user-specific verifier instances, enabling document submission, revocation, and verification using keccak-256 hashes, ECDSA signatures, and IPFS content identifiers. Methods include contract development, deployment on a local Hardhat network, performance benchmarking, and front-end integration for user interaction. Results show that verifier deployment consumes approximately 1.19 million gas (≈$85 at 20 gwei), document submission around 85 thousand gas (≈$6), and revocation about 50 thousand gas (≈$3.50). Client-side operations such as hashing and IPFS pinning occur in under 50 milliseconds, while real-world blockchain confirmations take 10–30 seconds. The findings demonstrate that decentralized notarization using Ethereum and IPFS is both technically feasible and economically viable. Future enhancements, including Layer 2 rollups, batch notarization, and privacy-preserving features such as encrypted IPFS pinning or zero-knowledge proofs, are proposed to further improve scalability, cost-efficiency, and data confidentiality
Performance Analysis of Machine Learning Model Combination for Spaceship Titanic Classification using Voting Classifier Wirawan, Haria; Robet, Robet; Hendrik, Jackri
JIKO (Jurnal Informatika dan Komputer) Vol 8, No 3 (2025)
Publisher : Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v8i3.10866

Abstract

The Spaceship Titanic dataset is fictional yet complex and challenging, featuring a mix of numerical and categorical features and missing values. This study aims to evaluate the performance of three machine learning model scenarios for classifying passenger status as “Transported” or “not”. The three scenarios implemented include linear-like models, a combination of the Top 5 Diverse models, and tree-based/ensemble models, each using a voting classifier approach. The voting model is employed because it can combine the strengths of multiple algorithms to reduce bias and variance, thus improving overall prediction accuracy and stability. The voting mechanism aggregates predictions from several base classifiers using two strategies: hard voting, which selects the majority class, and soft voting, which averages the predicted probabilities across models. The dataset was obtained from Kaggle and processed through several stages: data preprocessing, data splitting, model training, and evaluation. The evaluation results show that the tree-based/ensemble scenario achieved the highest accuracy of 90.38%, followed by the Top 5 Diverse model combination at 87.31% and the Linear-like model at 76.51%. Visualization using the confusion matrix, ROC Curve, and Feature importance analysis further supports the claim that ensemble models are superior at detecting complex classification patterns. These findings suggest that tree-based ensemble models provide the most optimal approach for classification tasks on a dataset like Spaceship Titanic.
Comparative Analysis of Loss Functions for Predicting Autoimmunity from Molecular Descriptors Using Deep Learning Gunawan, Candra; Robet, Robet; Hendri, Hendri
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8581

Abstract

Drug-induced autoimmunity (DIA) presents a complex obstacle in pharmacological safety due to its rare occurrence and unpredictable manifestation, often compounded by class imbalance in clinical datasets. This study investigates the influence of three loss functions, Binary Cross-Entropy (BCE), Focal Loss, and Dice Loss, on the performance of deep learning architectures comprising Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), and 2-Layer Neural Network (SimpleNN). Models were trained using numerical molecular descriptors from the publicly available DIA dataset. The architectures were chosen based on their complementary properties: MLP is suitable for high-dimensional tabular descriptor data, CNN was examined to explore whether 1D convolutions can capture localized feature interactions among correlated descriptors, and 2-Layer Neural Network served as a lightweight baseline for comparison. A stratified 5-fold cross-validation strategy was employed to ensure statistical robustness. The results demonstrate that the MLP model, optimized with Focal Loss, consistently delivered the highest classification performance, achieving average scores of 94% accuracy, 93% precision, 95% recall, 94% F1-score, and an AUC of 0.97. In contrast, CNN and SimpleNN architectures yielded less favorable outcomes under the same loss configurations. These findings highlight the importance of aligning loss function choice with model complexity in the context of imbalanced biomedical data. The insights from this work contribute to the development of more reliable computational frameworks for early-phase immunogenicity screening and support the advancement of precision pharmacovigilance strategies.
COMPARISON OF DECISION TREE AND RANDOM FOREST ALGORITHMS FOR ASTHMA Lase, Wisriani; Robet, Robet; Hendri, Hendri
JURTEKSI (jurnal Teknologi dan Sistem Informasi) Vol. 12 No. 1 (2025): Desember 2025
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Royal Kisaran

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurteksi.v12i1.4192

Abstract

Abstract: Asthma is a chronic respiratory disease that affects millions of people worldwide, making early detection crucial to prevent complications. This study aims to compare the performance of the Decision Tree and Random Forest algorithms in classifying asthma based on clinical symptom data. The data were processed through feature selection and model training stages, then evaluated using accuracy, precision, recall, and F1-score.The experimental analysis revealed that the Random Forest algorithm surpassed the Decision Tree in all metrics, achieving 95.19% accuracy, 90.43% precision, 95.00% recall, and 93.00% F1-score. In contrast, the Decision Tree obtained 89.14% accuracy, 90.60% precision, 88.70% recall, and 89.70% F1-score. These results suggest that Random Forest is more robust and dependable, especially in managing complex and imbalanced medical datasets. Keywords: asthma detection; decision tree; random forest; machine learning. Abstrak: Asma merupakan penyakit pernapasan kronis yang memengaruhi jutaan orang di seluruh dunia sehingga deteksi dini sangat penting untuk mencegah komplikasi. Penelitian ini bertujuan membandingkan kinerja algoritma Decision Tree dan Random Forest dalam mengklasifikasikan asma berdasarkan data gejala klinis. Data diproses melalui tahapan seleksi fitur dan pelatihan model, kemudian dievaluasi menggunakan akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa Random Forest memberikan performa terbaik dengan akurasi 90.43%, presisi 95.00%, recall 95.00%, dan F1-score 93.00%. Sebaliknya, Decision Tree memperoleh akurasi 89.14%, presisi 90.60%, recall 88.70%, dan F1-score 89.70%. Hasil ini menunjukkan bahwa Random Forest lebih kuat dan dapat diandalkan, terutama dalam mengelola kumpulan data medis yang kompleks dan tidak seimbang. Kata kunci: deteksi asma; decision tree; random forest; pembelajaran mesin.
Comparative Analysis of XGBoost, KNN, and SVM Algorithms for Heart Disease Prediction Using SMOTE-Tomek Balancing Yuliana, Yuliana; Robet, Robet; Hoki, Leony
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 1 (2026): Article Research January 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i1.15469

Abstract

Heart disease remains one of the leading causes of death worldwide, making early detection crucial for improving patient outcomes. This study aims to evaluate and compare the performance of several machine learning algorithms in detecting heart disease using the 2015 BRFSS dataset, which includes responses from 253,680 individuals. The three algorithms examined are Extreme Gradient Boosting (XGBoost), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). The data preprocessing steps involved feature encoding, class imbalance handling using the Synthetic Minority Over-sampling Technique combined with Tomek Links (SMOTE-Tomek), and hyperparameter tuning through RandomizedSearchCV. The models were assessed on a hold-out validation set using several metrics, including accuracy, Receiver Operating Characteristic-Area Under the Curve (ROC-AUC), F1-score, precision, and recall. The results demonstrated that XGBoost achieved the highest performance, with an accuracy of 94%, a ROC-AUC score of 0.98, and an F1-score of 0.94. In comparison, KNN achieved an accuracy of 87% (ROC-AUC 0.95), while SVM attained an accuracy of 79% (ROC-AUC 0.86). These findings suggest that XGBoost is a robust model for large-scale heart disease classification and holds potential for implementation in clinical decision support systems.
IoT Sensor Data Analysis for Early Fire Detection Using Dynamic Threshold Br Tarigan, Widia; Robet, Robet; Tarigan, Feriani Astuti
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 1 (2026): Article Research January 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i1.15478

Abstract

Early fire detection using Internet of Things (IoT) technology plays a vital role in minimizing potential material losses and casualties. Conventional systems generally still rely on static thresholds that are less adaptive to environmental dynamics, leading to high false alarm rates and delayed detection. This study proposes a dynamic threshold approach based on a hybrid method of Fuzzy Logic–Random Forest–Adaptive Z-Score and compares it with the static threshold method. Testing was conducted using publicly available secondary datasets, and the algorithms were implemented and tested in Jupyter Notebook. Evaluation was performed using accuracy, false alarm rate (FAR), detection time, F1-score, precision, and recall metrics. The test results show that the dynamic threshold method provides better performance with an increase in accuracy from 59.5% to 74.8%, a decrease in FAR from 31.1% to 14.3%, and a reduction in detection time from 21 seconds to 0 seconds. In addition, the F1-score increased from 0.459 to 0.638, precision from 0.473 to 0.716, and recall from 0.446 to 0.575. These results show that the dynamic threshold approach is more adaptive and reliable in IoT-based fire detection systems than conventional static threshold methods.
Comparative Analysis of Four Machine Learning Algorithms for Smoke Detection Using SMOTE-Rebalanced Sensor Data Liecero, Marcus; Robet, Robet; Hendrik, Jackri
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 1 (2026): Article Research January 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i1.15546

Abstract

Smoke detection plays a critical role in preventing fire-related hazards, particularly in intelligent monitoring and early warning systems. Conventional smoke sensors often exhibit limited responsiveness in dynamic environmental conditions, prompting the adoption of IoT-based sensor data combined with machine learning techniques. This study presents a comparative evaluation of four supervised classification algorithms, K-Nearest Neighbors (KNN), Decision Tree, Random Forest, and Gradient Boosting, using the Smoke Detection Dataset from Kaggle. The methodology integrates SMOTE to address class imbalance and Z-score normalization for feature standardization. Hyperparameter tuning was performed using GridSearchCV with 5-fold cross-validation, and model performance was assessed based on accuracy and execution time. Experimental results show that KNN achieved the highest accuracy (98.33%) with the lowest execution time (0.0327 s), whereas Decision Tree recorded the lowest accuracy (84.17%) but remained computationally fast (0.0406 s). Random Forest and Gradient Boosting demonstrated strong predictive capability (97.22% and 96.94%, respectively), but at higher computational costs (1.4338 s and 8.3819 s, respectively). Almost all models achieved perfect scores (1.00) for precision, recall, and F1-score following SMOTE-based balancing, except KNN which obtained slightly lower values (0.99). The findings indicate a trade-off between predictive performance and computational efficiency, suggesting that lightweight models such as KNN are better suited for real-time IoT-based smoke detection. In contrast, ensemble models may be more appropriate for backend analysis. This research contributes an integrated evaluation framework that combines data rebalancing, multi-model benchmarking, and time-based performance analysis, providing practical insights for the development of responsive and scalable early smoke detection systems.
Comparative Study of Baseline and CBAM-Enhanced ResNet50 and MobileNetV2 for Indonesian Rupiah Banknote Classification Alvin, Alvin; Robet, Robet; Feriani, Feriani Astuti Tarigan
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 1 (2026): Article Research January 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i1.15558

Abstract

This study investigates the performance of Convolutional Neural Network (CNN) architectures enhanced with Convolutional Block Attention Module (CBAM) for Indonesian banknote classification. Although attention mechanisms have shown strong potential in improving fine-grained visual recognition, their effectiveness for the classification of banknotes with fine textures and similar color patterns remains underexplored, forming a key research gap addressed in this work. Four architectures, ResNet50, ResNet50+CBAM, MobileNetV2, and MobileNetV2+CBAM, were evaluated using K-Fold cross-validation on a dataset of 1,281 images representing seven banknote denominations. Experimental results show that ResNet50 achieves strong baseline performance with a weighted Train accuracy of 99.14% and a Val accuracy of 96.72%, while the integration of CBAM further improves feature discrimination, with ResNet50+CBAM obtaining the highest average accuracy across all folds with a weighted Train accuracy of 100% and a Val accuracy of 99.45%. MobileNetV2 showed lower performance due to its lightweight capacity with a Train accuracy of 91.88% and a decrease in Val accuracy of 85.71%. However, the addition of CBAM provided measurable improvements and greater stability with a Train accuracy of 99.61% and Val accuracy of 92.82%. Overall, CBAM improved CNN’s ability to focus on spatial information and salient channels, resulting in more reliable classification. ResNet50+CBAM emerged as the best-performing model, offering the best balance between accuracy and consistency. These findings support the development of reliable computer vision systems for financial technology applications, including automatic banknote recognition, counterfeit detection, and secure transaction verification.
Predicting AI Job Salary Classes Through a Comparative Study of Machine Learning Algorithms Vincent, Vincent; Robet, Robet; Edi Wijaya
JURNAL RISET KOMPUTER (JURIKOM) Vol. 12 No. 6 (2025): Desember 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i6.8979

Abstract

The rapid growth of Artificial Intelligence (AI) has brought significant transformation to the global job market, particularly in salary structures across various AI-related professions. This study aims to classify AI job salaries into three categories—Low, Medium, and High—using supervised machine learning algorithms. The dataset, sourced from Kaggle, combines two real-world datasets featuring key attributes such as experience level, job type, education level, technical skills, remote work ratio, and salary in USD. Preprocessing techniques include One-Hot Encoding for categorical data, StandardScaler for normalization, and MultiLabelBinarizer to handle multi-skill entries. Four machine learning models—Logistic Regression, Random Forest, Gradient Boosting, and XGBoost—were trained and evaluated using consistent pipelines, with evaluation metrics including accuracy, precision, recall, and F1-score, applying macro-averaging to address class imbalance. Logistic Regression achieved the highest performance with 85.4% accuracy and 77.6% F1-score, followed by Gradient Boosting with 84.8% accuracy and 76.3% F1-score. High-salary classes were predicted with higher precision and recall than low-salary classes, indicating skewness in class distribution. Feature importance analysis shows that experience, remote work ratio, and key skills such as Python and SQL significantly affect prediction accuracy. This study demonstrates that traditional machine learning methods, when applied with appropriate preprocessing, can effectively support salary classification and labor market analysis in the AI domain.
Co-Authors Aghaunor, Tabitha Chukwudi Agus Maringan Siahaan Alvin Alvin, Alvin Andi Andi Andy Andy Br Tarigan, Widia CANDRA GUNAWAN Carles Juliandy De Rosal Ignatius Moses Setiadi Didik Aryanto edi edi Edi Wijaya Edi Wijaya Edi Wijaya Feriani Astuti Tarigan Feriani, Feriani Astuti Tarigan Hendri Hendri Hoki, Leony Hose, Fernando Jackri Hendrik Johanes Terang Kita Perangin Angin Kartikadarma , Etika Lase, Wisriani Liecero, Marcus Nurhayati Harahap Octara Pribadi Ojugo, Arnold Adimabua Parapak, Yehezkiel E.A Rizkita, Ari Robin Robin Robin Robin, Robin Robin Zheng Sarker, Md Kamruzzaman Satriya Miharja Setyoko, Bimo Haryo Simanjuntak, Martina Sances Siregar, Tarq Hilmar Suyud Widiono Tio, Nicholas Ugbotu, Eferhire Valentine Vincent Vincent, Vincent Wirawan, Haria Yuliana Yuliana