Article Per Year (5 Year)
p-Index From 2021 - 2026
1.944
P-Index
This Author published in this journals
All Journal Jurnal Pilar Nusa Mandiri AJAD : Jurnal Pengabdian kepada Masyarakat Paradigma Nuansa Informatika Journal of Computing Innovations and Emerging Technologies Bulletin of Intelligent Machines and Algorithms Jurnal Informatika
Nur Alamsyah
Universitas Informatika Dan Bisnis Indonesia
Humanities Computer Science & IT

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : bulletin of intelligent machines and algorithms

 1 
A Progressive Training Framework for Robust YOLOv11-Based Vehicle Detection Across Domain Shifts in Real-World CCTV Environments Aditya Gunaldhi; Budiman; Chairul Habibi; Nur Alamsyah
Bulletin of Intelligent Machines and Algorithms Vol. 1 No. 5 (2026): BIMA July 2026 Issue
Publisher : Maheswari Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65780/bima.v1i5.27

Abstract

The performance of deep learning-based vehicle detection models often deteriorates when applied to real-world CCTV environments due to domain shift caused by variations in lighting, occlusion, glare, and changes in camera viewpoint. This study aims to develop a YOLOv11-based progressive training framework to improve the model’s generalization ability under heterogeneous operational conditions. The proposed method consists of four stages: base training, fine-tuning, and a supervised progressive domain adaptation strategy implemented through sequential fine-tuning on labeled target-domain CCTV images before OpenVINO-based inference optimization. The model is trained using a source dataset and adapted to a target dataset representing real-world CCTV conditions. Evaluation was conducted using Precision, Recall, mAP@50, mAP@50–95, loss curve analysis, per-vehicle-class evaluation, visual testing on CCTV video, as well as latency and throughput measurements. The results show that base training achieved an mAP@50 of 0.919 and built a robust feature representation, while fine-tuning maintained performance stability with an mAP@50 of 0.915. Although domain adaptation reduced mAP@50 to 0.811 due to domain shift, the model demonstrated improved generalization capabilities and maintained more consistent detection under low-light conditions, glare, occlusion, and heavy traffic. OpenVINO INT8 optimization increased inference speed from 4.86 FPS to 9.08 FPS with minimal accuracy loss. These findings demonstrate that the progressive training framework effectively bridges differences in data distribution while producing a vehicle detection model that is more robust, efficient, and suitable for deployment in real-time CCTV-based traffic monitoring systems.
A Trigger Aware, Event Centric, and Uncertainty Calibrated Neuro-Symbolic Framework for Actionable Cyber Threat Intelligence from Indonesian Online News Elia Setiana; Muhamad Achya Arifudin; Nur Alamsyah
Bulletin of Intelligent Machines and Algorithms Vol. 1 No. 5 (2026): BIMA July 2026 Issue
Publisher : Maheswari Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65780/bima.v1i5.31

Abstract

Online news can provide timely cyberthreat signals, but duplicative reporting, fragmented event descriptions, resource-constrained Indonesian language text, and uncalibrated model confidence limit its operational use. This study presents A Trigger-Aware, Event-Centric, and Uncertainty-Calibrated Neuro-Symbolic Framework for Actionable Cyber ​​Threat Intelligence from Indonesian Online News (TRACE-CTI-ID), a proof-of-concept framework that integrates exact deduplication, event-centric clustering, trigger-aware semantic representation, neuro-symbolic fusion, ordinal risk estimation, conformal uncertainty, mitigation mapping, and an event-centric knowledge graph. The experiment used 711 Liputan6 records collected on March 14, 2025. Exact deduplication reduced the corpus to 79 unique headlines, which were automatically consolidated into 26 events. Splitting the separate events resulted in 30 training articles, 5 calibration articles, and 44 test articles with zero event leakage. The calibrated neuro-symbolic model achieved a micro-F1 of 0.283 and a macro-F1 of 0.441, outperforming the baseline TF-IDF of 0.074 and 0.013, respectively. However, ordinal severity prediction remained weak with an accuracy of 0.136, a macro-F1 of 0.138, and a mean absolute error of 2.023. Conformal coverage was also unstable, and the abstention mechanism did not direct uncertain articles to human review. These findings demonstrate the technical feasibility of the integrated pipeline while also demonstrating that silver labeled, title only, and single source data are insufficient for final operational validation. Therefore, the key contribution is a transparent, leak aware evaluation architecture and protocol that can be strengthened through full text collection from multiple sources and independent expert annotation.
Classification of Pension Program Service Workload Levels Across Payment Cities at PT ASABRI (Persero) Bandung Branch Office Using Machine Learning Models Angela Nisrina Zhafir; Nur Alamsyah
Bulletin of Intelligent Machines and Algorithms Vol. 1 No. 6 (2026): BIMA issue September 2026
Publisher : Maheswari Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65780/bima.v1i6.44

Abstract

This study classifies service workload levels across 13 cities served by the PT ASABRI (Persero) Bandung Branch Office to mitigate evaluation bias by implementing the CRISP-DM methodology on transaction data from 2023 to 2024. The target variable was constructed by combining multiple operational variables into a composite score index, using percentile cutoffs to define High, Medium, and Low workload categories. Under an Out-of-Time Validation (OOTV) framework, data from 2023 served as training data and data from 2024 as testing data, followed by the application of the Synthetic Minority Oversampling Technique (SMOTE) exclusively to the training data to neutralize class imbalance. Comparative evaluation identified a Random Forest model optimized via RandomizedSearchCV as the top-performing model, achieving an accuracy of 83.33%, a macro F1-score of 81.17%, and minimal performance discrepancy between training and test sets. Architecture stability was demonstrated through 5-fold cross-validation, yielding an average accuracy of 72.42% with a minimal standard deviation of 5.69%. Global Feature Importance analysis identified the total number of family dependents (TOTAL_JIWA_DILAYANI) as the dominant operational factor, with an importance score of 0.4145. This comprehensive modeling provides a measurable Early Warning System that enables management to prioritize evaluation areas more systematically while minimizing subjective assumptions.
Optimization of Cross-Selling Strategies and Retail Product Layouts of Building Materials Based on Market Basket Analysis Using the Apriori Algorithm Yolanda Joice Maria Lumbantobing; Nur Alamsyah; Titan Parama Yoga
Bulletin of Intelligent Machines and Algorithms Vol. 1 No. 6 (2026): BIMA issue September 2026
Publisher : Maheswari Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65780/bima.v1i6.46

Abstract

In an era of increasingly fierce retail competition, optimizing product layout and sales strategies is a matter of urgency for businesses seeking to maintain and increase revenue. CV. Tolong Kita Jaya, a building materials store, is currently facing challenges in determining an effective product placement strategy and has not yet maximized its cross-selling potential. This is due to a lack of analysis of past consumer purchasing patterns, resulting in frequent missed opportunities to sell related products. Therefore, this study aims to address this issue by implementing a data mining approach. This study employs the comprehensive Cross-Industry Standard Process for Data Mining (CRISP-DM) framework, ranging from business understanding to the evaluation stage. For modeling, this study implements Market Basket Analysis (MBA) using the Apriori algorithm. This model was specifically chosen to extract association rules from a set of historical transaction data to identify relationships among building materials that are frequently purchased together. The test results from this modeling revealed several product combinations with high and valid support, confidence, and lift ratio metrics. The key findings of this study provide a strategic foundation for redesigning retail layouts, in which items with strong associations are positioned in close proximity. Furthermore, these findings facilitate the formulation of actionable cross-selling strategies by management, such as the creation of promotional sales bundles, which are ultimately projected to increase the overall sales volume of building materials.
Co-Authors Acep Hendra Aditya Gunaldhi Akbar, Imannudin Alif Januantara Prima Angela Nisrina Zhafir Angela Nisrina Zhafirama Arafat Febriandirza Artika Arista Budiman Chairul Habibi Esa Prakasa Fahreja Ramadhan Gunthur Bayu Wibisono Hani Fitria Rahmani Henki Bayu Seta Ihsan AlFauzi Ilham Ramadhan Muhamad Achya Arifudin Niqotaini, Zatin Nursyanti, Reni Rezza Novian Noor Rochmat Setiana, Elia Tiara Permata Hati Titan Parama Yoga Titan Parama Yoga Valencia Claudia Jennifer Kaunang Venia R Danestiara Wala Erpurini Yolanda Joice Maria Lumbantobing