Garuda - Garba Rujukan Digital

Evaluating Deep Learning Models for HIV/AIDS Classification: A Comparative Study Using Clinical and Laboratory Data Airlangga, Gregorius
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6783

The accurate classification of HIV/AIDS status is critical for effective diagnosis, treatment planning, and disease management. This study evaluates the performance of four deep learning models: Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) on a comprehensive clinical and laboratory dataset derived from the AIDS Clinical Trials Group Study 175. The dataset includes features such as demographic information, treatment history, and immune markers like CD4 and CD8 counts. To address class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) was applied, followed by stratified 10-fold cross-validation to ensure robust evaluation. Each model's performance was assessed using metrics including accuracy, precision, recall, F1-score, and ROC-AUC. GRU emerged as the most effective model, achieving the highest accuracy (71.04%) and ROC-AUC (57.72%), demonstrating its robustness in handling sequential data. CNN and LSTM showed competitive performance, particularly in balancing precision and recall. However, all models faced challenges in recall, highlighting difficulties in identifying minority-class samples. The findings underscore the potential of GRU for HIV/AIDS classification while identifying limitations in current approaches to handling class imbalance. Future work will explore advanced architectures, such as attention mechanisms and hybrid models, to further improve sensitivity and robustness. This study contributes to the growing body of research on applying deep learning to healthcare, with implications for improving diagnostic accuracy and patient outcomes.

Performance Evaluation of Machine Learning Models for HIV/AIDS Classification Airlangga, Gregorius
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6790

Accurate and early diagnosis of HIV/AIDS is critical for effective treatment and reducing disease transmission. This study evaluates the performance of several machine learning models, including Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naive Bayes, for classifying HIV/AIDS infection status. A dataset comprising 50,000 samples was used, and models were assessed based on accuracy, precision, recall, and F1 score using stratified ten-fold cross-validation to ensure robust evaluation. The results reveal significant trade-offs between sensitivity and specificity across the models. Gradient Boosting achieved the highest accuracy (70.85%) and precision (57.81%), making it suitable for confirmatory testing where minimizing false positives is critical. Conversely, Naive Bayes demonstrated the highest recall (57.99%) and F1 score (51.04%), emphasizing its effectiveness in early-stage diagnostics where sensitivity is paramount. SVM exhibited the highest precision (59.87%) but struggled with recall (11.28%), reflecting its conservative nature in classifying positive cases. These findings underscore the importance of selecting models tailored to specific diagnostic objectives. While Naive Bayes is ideal for comprehensive screening programs, Gradient Boosting and SVM are better suited for confirmatory testing. This research provides valuable insights into the strengths and limitations of machine learning models for medical diagnostics, paving the way for developing more robust, hybrid approaches to optimize sensitivity and specificity in HIV/AIDS classification.

Machine Learning for Tsunami Prediction: A Comparative Analysis of Ensemble and Deep Learning Models Airlangga, Gregorius
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 6, No 1 (2025): Edisi Januari
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v6i1.572

Tsunamis, triggered by seismic activities, pose significant threats to coastal regions, necessitating accurate prediction models to mitigate their impact. This study explores the application of machine learning models, including ensemble methods (Random Forest, Gradient Boosting, XGBoost, LightGBM, and CatBoost) and deep learning (Neural Networks), for tsunami prediction based on seismic data. The dataset spans seismic events from 1995 to 2023, characterized by features such as magnitude, depth, and geographic location. A 10-fold cross-validation approach was employed to evaluate model performance using precision, recall, F1-score, accuracy, and ROC-AUC metrics. The results highlight that Gradient Boosting achieved the best balance between precision and recall, with an F1-score of 0.6544 and the highest ROC-AUC of 0.8606, demonstrating its strong discriminatory power. Random Forest excelled in precision (0.6920) and F1-score (0.6287), making it suitable for reducing false positives. Ensemble boosting models, such as CatBoost and LightGBM, offered consistent performance with low variability across folds. In contrast, Neural Networks underperformed, achieving an F1-score of 0.5497 and an ROC-AUC of 0.7936, indicating the need for further optimization. Despite promising results, challenges in recall scores underscore the need for enhanced detection of tsunami-triggering events. The findings establish ensemble methods, particularly Gradient Boosting and Random Forest, as robust tools for tsunami prediction, providing a foundation for early warning systems. Future work will focus on improving recall and exploring hybrid modeling techniques to optimize predictive accuracy and reliability.

Comparative Evaluation of CNN, LSTM, and GRU Architectures for Tsunami Prediction Using Seismic Data Airlangga, Gregorius
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 6, No 1 (2025): Edisi Januari
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v6i1.573

Tsunamis are among the most catastrophic natural disasters, often triggered by seismic events such as earthquakes. Accurately predicting tsunami occurrences based on seismic parameters is critical for mitigating their devastating impacts. This study investigates the application of three advanced deep learning architectures such as Convolutional Neural Networks (CNNs), Long Short-Term Memory Networks (LSTMs), and Gated Recurrent Units (GRUs) for binary classification of tsunami events using seismic data. The dataset comprises earthquake records from 1995 to 2023, including features such as magnitude, depth, latitude, longitude, Modified Mercalli Intensity (MMI), and Community Internet Intensity (CDI). The models were evaluated using stratified 10-fold cross-validation and assessed across precision, recall, F1-score, accuracy, and ROC-AUC metrics. Results indicate that CNN outperformed the other architectures, achieving the highest accuracy (72.5%), precision (0.5987), and ROC-AUC (0.7838). GRU demonstrated moderate performance, balancing computational efficiency and predictive accuracy with an accuracy of 71.7% and ROC-AUC of 0.7709. LSTM, while theoretically adept at modeling temporal dependencies, showed the lowest performance due to challenges in capturing the dataset’s characteristics. The findings emphasize the importance of selecting architecture suited to the dataset’s features and task requirements. CNN’s superior performance highlights its effectiveness in spatial pattern extraction, while GRU offers a computationally efficient alternative. Future work will explore hybrid models and the integration of additional features to enhance prediction robustness. This study contributes to advancing tsunami prediction methodologies, supporting early warning systems for disaster preparedness.

A Comparative Analysis of Machine Learning Models for Obesity Prediction Airlangga, Gregorius
Jurnal Informatika Ekonomi Bisnis Vol. 7, No. 1 (March 2025)
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/infeb.v7i1.1089

Obesity is a global health challenge with significant implications for public health systems and individual well-being. Predictive modeling using machine learning (ML) offers a powerful approach to identify individuals at risk of obesity and inform early intervention strategies. This study evaluates the performance of ten ML models, including Logistic Regression, Support Vector Machines, Decision Trees, K-Nearest Neighbors, Naive Bayes, Random Forest, Gradient Boosting, AdaBoost, XGBoost, and LightGBM, in predicting obesity using a publicly available dataset. A rigorous preprocessing pipeline, incorporating missing value handling, categorical encoding, normalization, and outlier detection, was applied to ensure data quality and compatibility with ML algorithms. Performance metrics such as accuracy, precision, recall, and F1-score were evaluated using 10-fold stratified cross-validation. Among the models, LightGBM demonstrated the highest test accuracy (99.19%) and F1-score (99.20%), outperforming Gradient Boosting and Random Forest, which also showed competitive results. The study highlights the superior predictive capabilities of ensemble methods while underscoring the trade-offs between model complexity and interpretability. Logistic Regression provided a strong baseline, demonstrating the importance of preprocessing, but was outperformed by advanced ensemble techniques. This research contributes to the growing field of ML-driven healthcare solutions, offering valuable insights into the strengths and limitations of various predictive models. The findings support the integration of advanced ML techniques in public health systems and pave the way for future research on hybrid and explainable models for obesity prediction and management.

A Comparative Analysis of Deep Learning Architectures for Obesity Classification Using Structured Data Airlangga, Gregorius
Jurnal Informatika Ekonomi Bisnis Vol. 7, No. 1 (March 2025)
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/infeb.v7i1.1090

Obesity is a significant global health concern, necessitating accurate and efficient diagnostic tools to classify individuals based on obesity levels. This study investigates the performance of five deep learning architectures: Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Bidirectional LSTM (BiLSTM) in classifying obesity levels using structured data. The dataset comprises clinical, demographic, and lifestyle features, and is preprocessed through normalization, label encoding, and Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance. Each model was evaluated using accuracy, precision, recall, and F1-score metrics under stratified 10-fold cross-validation. The results indicate that MLP achieved the highest performance across all metrics, with an accuracy of 99.05%, followed closely by CNN at 98.77%. Sequential models, including LSTM, GRU, and BiLSTM, exhibited comparatively lower performance, achieving accuracies of 83.80%, 86.59%, and 86.78%, respectively. The superior performance of MLP and CNN underscores their suitability for structured datasets with static features, while the sequential models struggled due to the lack of temporal dependencies in the data. This study highlights the importance of aligning model architecture with dataset characteristics for optimal performance. The findings suggest that MLP and CNN are effective choices for obesity classification tasks, providing robust and computationally efficient solutions. Future work could explore hybrid models and incorporate temporal features to enhance the performance of sequential architecture.

A Comparative Analysis of Machine Learning Models for Obesity Prediction Airlangga, Gregorius
Jurnal Informatika Ekonomi Bisnis Vol. 7, No. 1 (March 2025)
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/infeb.v7i1.1089

Obesity is a global health challenge with significant implications for public health systems and individual well-being. Predictive modeling using machine learning (ML) offers a powerful approach to identify individuals at risk of obesity and inform early intervention strategies. This study evaluates the performance of ten ML models, including Logistic Regression, Support Vector Machines, Decision Trees, K-Nearest Neighbors, Naive Bayes, Random Forest, Gradient Boosting, AdaBoost, XGBoost, and LightGBM, in predicting obesity using a publicly available dataset. A rigorous preprocessing pipeline, incorporating missing value handling, categorical encoding, normalization, and outlier detection, was applied to ensure data quality and compatibility with ML algorithms. Performance metrics such as accuracy, precision, recall, and F1-score were evaluated using 10-fold stratified cross-validation. Among the models, LightGBM demonstrated the highest test accuracy (99.19%) and F1-score (99.20%), outperforming Gradient Boosting and Random Forest, which also showed competitive results. The study highlights the superior predictive capabilities of ensemble methods while underscoring the trade-offs between model complexity and interpretability. Logistic Regression provided a strong baseline, demonstrating the importance of preprocessing, but was outperformed by advanced ensemble techniques. This research contributes to the growing field of ML-driven healthcare solutions, offering valuable insights into the strengths and limitations of various predictive models. The findings support the integration of advanced ML techniques in public health systems and pave the way for future research on hybrid and explainable models for obesity prediction and management.

A Comparative Analysis of Deep Learning Architectures for Obesity Classification Using Structured Data Airlangga, Gregorius
Jurnal Informatika Ekonomi Bisnis Vol. 7, No. 1 (March 2025)
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/infeb.v7i1.1090

Obesity is a significant global health concern, necessitating accurate and efficient diagnostic tools to classify individuals based on obesity levels. This study investigates the performance of five deep learning architectures: Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Bidirectional LSTM (BiLSTM) in classifying obesity levels using structured data. The dataset comprises clinical, demographic, and lifestyle features, and is preprocessed through normalization, label encoding, and Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance. Each model was evaluated using accuracy, precision, recall, and F1-score metrics under stratified 10-fold cross-validation. The results indicate that MLP achieved the highest performance across all metrics, with an accuracy of 99.05%, followed closely by CNN at 98.77%. Sequential models, including LSTM, GRU, and BiLSTM, exhibited comparatively lower performance, achieving accuracies of 83.80%, 86.59%, and 86.78%, respectively. The superior performance of MLP and CNN underscores their suitability for structured datasets with static features, while the sequential models struggled due to the lack of temporal dependencies in the data. This study highlights the importance of aligning model architecture with dataset characteristics for optimal performance. The findings suggest that MLP and CNN are effective choices for obesity classification tasks, providing robust and computationally efficient solutions. Future work could explore hybrid models and incorporate temporal features to enhance the performance of sequential architecture.

Detection of DDoS Attacks in UAV Communication Networks Using Machine Learning Models Airlangga, Gregorius
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 10, No 1 (2025): Edisi Februari
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v10i1.882

The increasing adoption of unmanned aerial vehicle (UAV) communication networks has introduced new cybersecurity challenges, particularly in detecting and mitigating distributed denial-of-service (DDoS) attacks. This study evaluates the effectiveness of multiple machine learning models, including Random Forest, Gradient Boosting, XGBoost, Logistic Regression, and Support Vector Machine (SVM), for DDoS attack detection in UAV networks. The dataset, derived from a simulated UAV communication network, incorporates key network parameters such as signal strength, packet loss rate, round-trip time, and base station load. Data preprocessing steps, including feature selection, normalization, and synthetic minority over-sampling (SMOTE), were applied to enhance model performance. Among the evaluated models, Random Forest demonstrated the highest classification accuracy with an F1-score of 0.839 and an AUC score of 0.912, outperforming other models in precision-recall trade-offs. Gradient Boosting and XGBoost exhibited moderate classification ability, whereas Logistic Regression and SVM struggled with capturing complex network patterns. The results highlight the effectiveness of ensemble learning in intrusion detection for UAV networks. This study provides valuable insights into optimizing machine learning-based intrusion detection systems and paves the way for further advancements in UAV cybersecurity. Future work will focus on integrating additional feature engineering techniques and validating models on real-time network traffic datasets.

Enhancing UAV Communication Security: Multi-Label Anomaly Detection Using Machine Learning in Imbalanced Data Environments Airlangga, Gregorius; Sihombing, Denny Jean Cross; Nugroho, Oskar Ika Adi
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 10, No 1 (2025): Edisi Februari
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v10i1.883

Unmanned Aerial Vehicle (UAV) communication networks are increasingly vulnerable to cyber threats, including spoofing, jamming, malware, and distributed denial-of-service (DDoS) attacks. Effective anomaly detection is crucial to maintaining network integrity and operational security. This study evaluates multiple machines learning models, including Support Vector Machines, Logistic Regression, XGBoost, Gradient Boosting, and Random Forest, to detect anomalies in UAV communication networks. A real-world dataset containing 44,016 instances of network telemetry and security indicators was utilized, with each instance labeled for multiple potential anomalies. Experimental results reveal a significant class imbalance, where models achieve high accuracy (92%) but fail to detect minority class anomalies, yielding near-zero recall scores for critical cyber threats. The study highlights the limitations of traditional classifiers in imbalanced multi-label classification tasks and emphasizes the need for advanced techniques such as Synthetic Minority Over-sampling (SMOTE), cost-sensitive learning, and deep learning-based anomaly detection. The findings suggest that conventional machine learning approaches alone are insufficient for reliable anomaly detection in UAV networks, necessitating hybrid solutions that integrate multiple detection paradigms. Future work should explore adaptive ensemble learning methods and deep anomaly detection frameworks to improve recall and precision for rare cybersecurity threats.

Title

Found 117 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 117 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 117 Documents
Search