Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal BAREKENG: Jurnal Ilmu Matematika dan Terapan Community Service Journal of Indonesia Jurnal Teknik Informatika (JUTIF)
Maulana, Avin
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Energy Engineering Health Professions Mathematics Mechanical Engineering Medicine & Pharmacology Nursing Physics Public Health Transportation

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
An Enhanced Particle Swarm Optimization with Mutation for Mean-Value-at-Risk Portfolio Optimization in the Indonesian Banking Sector Anam, Syaiful; Bukhori, Hilmi Aziz; Maulana, Avin; Maulana, M. Idam; Rasikhun, Hady
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 4 (2025): JUTIF Volume 6, Number 4, Agustus 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.4.5191

Abstract

Portfolio optimization in emerging markets is challenging because high volatility and non-normal return distributions reduce the effectiveness of traditional mean–variance models, which tend to underestimate downside risk. This study aims to develop and evaluate an Enhanced Particle Swarm Optimization with Mutation (PSO with Mutation) for portfolio optimization under the Mean-Value-at-Risk (Mean-VaR) framework in the Indonesian banking sector. The novelty of this approach lies in integrating a mutation operator into standard PSO to maintain population diversity, prevent premature convergence, and improve exploration of the solution space. To evaluate the method, daily adjusted closing prices of 31 Indonesian bank stocks from January 2020 to July 2025 were collected. Preprocessing included removing tickers with incomplete data and computing daily returns. The optimization problem was formulated using Mean-VaR as the risk measure, with portfolio weight constraints. The proposed PSO with Mutation was benchmarked against standard PSO, Genetic Algorithm (GA), Bat Algorithm (BA), BA with Mutation, and classical models (Markowitz and Monte Carlo–based VaR). Performance was assessed using expected return, Mean-VaR, risk-adjusted return, Sharpe ratio, execution time, and stability across 25 independent runs. The results show that PSO with Mutation achieved a competitive expected return (0.0020), the lowest Mean-VaR (0.0311), the highest risk-adjusted return (0.0650), and the lowest variability across runs, while maintaining acceptable execution time. These findings confirm that mutation-enhanced PSO provides a robust, balanced, and efficient solution for portfolio optimization, making it highly relevant for investors in volatile emerging markets and advancing research on hybrid metaheuristics in financial optimization.
Improving Lateral-Movement Intrusion Detection in Virtualized Networks using SHAP Feature Selection, SMOTE, and a Voting Ensemble Classifier Maulana, Avin; Anam, Syaiful; Aziz Bukhori, Hilmi
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 4 (2025): JUTIF Volume 6, Number 4, Agustus 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.4.5233

Abstract

Modern virtualized networks, such as those using VXLAN (Virtual eXtensible LAN), generate heavy east–west traffic, which can conceal the lateral movement of attackers. Detecting such infiltration attacks is challenging due to overlay encapsulation (e.g., VXLAN) and flat subnet architectures create blind spots for traditional IDS.  This study aims to evaluate a robust methodology for addressing class imbalance in intrusion detection by integrating SHAP-driven feature selection with SMOTE in a voting ensemble. We conducted an ablation study on the CICIDS2017 Thursday-WorkingHours-Afternoon-Infiltration subset, which is highly imbalanced (36 infiltration flows vs. 288,566 benign flows), varying SHAP feature sets (Top-5 vs. Top-30), classification thresholds , and SMOTE (Synthetic Minority Over-sampling Technique) balancing. The ensemble combined XGBoost, Random Forest, and Logistic Regression, and was evaluated with ROC-AUC, precision, recall, and F1-score. Results indicate that using more SHAP‑important features improves ROC‑AUC and recall, while SMOTE substantially enhances minority‑class detection. The best configuration is Top‑30 SHAP features with SMOTE at , achieved ROC‑AUC = 0.976 and F1‑score = 0.78, whereas using fewer features or omitting SMOTE significantly reduced recall and F1‑score. This synergy of interpretable feature selection and synthetic oversampling establishes a practical methodology for intrusion detection in highly imbalanced, modern virtualized environments. The novelty lies in demonstrating that SHAP + SMOTE integration yields both transparency and resilience, directly addressing encapsulation challenges in detecting stealthy lateral movement.
HETEROGENEOUS GRAPH NEURAL NETWORKS FOR STOCK PRICE PREDICTION: MODELING TEMPORAL AND CROSS-STOCK DEPENDENCIES Bukhori, Hilmi Aziz; Aruchunan, Elayaraja; Anam, Syaiful; Bukhori, Saiful; Maulana, Avin
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 20 No 2 (2026): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol20iss2pp0981-1000

Abstract

Stock price prediction remains a challenging task due to the complex interplay of temporal trends and relational dependencies within financial markets. This study proposes the GNN-LSTM Hybrid model, a novel framework that integrates Graph Neural Networks (GNNs) with Long Short-Term Memory (LSTM) units to simultaneously capture heterogeneous graph structures and temporal dynamics in stock data, leveraging GNNs to model relational dependencies and LSTMs to address long-term temporal patterns, with graph construction based on stock correlation and temporal edge features. Using a dataset covering 1,270 trading days from March 2015 to April 2020, we evaluate the model against traditional methods (ARIMA, LSTM) and modern graph-based approaches (T-GCN, GAT, Transformer-TS, Base GraphSAGE, SAGE-IS). The GNN-LSTM Hybrid achieves superior performance, with a Mean Absolute Error (MAE) of 0.740 (±0.13), Root Mean Squared Error (RMSE) of 1.100 (±0.21), Mean Absolute Percentage Error (MAPE) of 4.92% (±1.16), and Directional Accuracy (DA) of 67.0% (±2.7), and significantly outperforms all baselines, as confirmed by paired t-tests (p < 0.05). Hyperparameter analysis reveals that a configuration of 6 GNN layers and a hidden dimension size of 128 optimizes predictive accuracy, balancing computational efficiency (training time: 16.0 ± 0.7 s) and performance. Validation across 100 training epochs further confirms the model’s robust convergence across all metrics. With an inference time of 20.0 ± 1.0 ms, which is competitive compared to baselines like ARIMA (23.5 ± 1.1 ms) and GAT (20.5 ± 1.0 ms), the GNN-LSTM Hybrid demonstrates strong potential for practical financial forecasting, offering a scalable and accurate solution for capturing the multifaceted dynamics of stock markets, with implications for real-time applications and broader economic modeling.
IMPROVING MADRASAH TEACHERS' COMPETENCIES IN ARTIFICIAL INTELLIGENCE-BASED LEARNING DATA PROCESSING IN BATU CITY Anam, Syaiful; Aziz Bukhori, Hilmi; Maulana, Avin; Yanti, Indah; Gustiningsih Hapsani, Anggi
Community Service Journal of Indonesia Vol. 7 No. 2 (2025): Community Service Journal of Indonesia
Publisher : Institute for Research and Community Service, Health Polytechnic of Kerta Cendekia, Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36720/csji.v7i2.813

Abstract

Teacher competence is a crucial factor in improving the quality of education..This community service program aimed to enhance the professional competence of madrasah teachers in processing learning data using artificial intelligence (AI)-based tools. Conducted through a one-day intensive workshop in Batu City, the program involved 18 teachers from five madrasahs at the Madrasah Aliyah and Madrasah Tsanawiyah levels. The training adopted the ADDIE instructional design model, covering needs analysis, AI-assisted data processing with Google Sheets and ChatGPT/OpenAI, reinforcement of AI ethics, and infographic creation. Quantitative evaluation showed a significant improvement in participants’ competencies, with average scores increasing from 60.3 (pre-test) to 86.3 (post-test). The most notable progress was observed in logical operations (IF function mastery) and ethical awareness in AI use, while 88% of participants reported high satisfaction with the training content and delivery. The program effectively integrated digital literacy, ethical reflection, and practical application to foster teacher professionalism. Beyond individual competence, this initiative contributed to building a sustainable collaborative network through the Subject Teachers’ Working Group (MGMP) and provided a replicable model for technology-based professional development in Islamic education.
Co-Authors Aruchunan, Elayaraja Aziz Bukhori, Hilmi Bukhori, Hilmi Aziz Gustiningsih Hapsani, Anggi Hady Rasikhun Indah Yanti Maulana, M. Idam Saiful Bukhori Syaiful Anam