cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Muhammad Khoiruddin Harahap
Contact Email
choir.harahap@yahoo.com
Phone
+6282251583783
Journal Mail Official
publikasi@itscience.org
Editorial Address
Medan
Location
Unknown,
Unknown
INDONESIA
Brilliance: Research of Artificial Intelligence
Published by Information Technology and Science
ISSN : -     EISSN : 28079035     DOI : https://doi.org/10.47709
Core Subject : Science, Education,
Decision Sciences, Operations Research & Management Mathematics Other
Brilliance: Research of Artificial Intelligence is The Scientific Journal. Brilliance is published twice in one year, namely in February, May and November. Brilliance aims to promote research in the field of Informatics Engineering which focuses on publishing quality papers about the latest information about Artificial Intelligence. Submitted papers will be reviewed by the Journal and Association technical committee. All articles submitted must be original reports, previously published research results, experimental or theoretical, and colleagues will review. Articles sent to the Brilliance may not be published elsewhere. The manuscript must follow the author guidelines provided by Brilliance and must be reviewed and edited. Brilliance is published by Information Technology and Science (ITScience), a Research Institute in Medan, North Sumatra, Indonesia.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 594 Documents
 55   56   57   58   59 
An Explainable Ai Framework For Transparent Poverty Classification And Citizen Engagement In Nigeria Emmanuel John Anagu; Umar Mairo; Victoria Sabo
Brilliance: Research of Artificial Intelligence Vol. 6 No. 2 (2026): Brilliance: Research of Artificial Intelligence, Article Research May 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i2.8205

Abstract

Poverty targeting in Nigeria remains quite astonishingly inefficient with exclusion error rates above 40 per cent which puts millions of eligible households out of reach of welfare assistance. The existing models of the Proxy Means Test (PMT) are binary classification based, non-transparent and cannot work in dynamic and high noise settings and this leads to an ongoing accuracy-transparency-robustness trilemma. The aim is to design and test an explainable artificial intelligence system that will increase the accuracy of poverty classification, transparency, and decrease errors of exclusion in the welfare targeting system of Nigeria. The Design Science Research (DSR) methodology was applied to develop the Fuzzy-Adaptive Stacking Ensemble for Explainable AI (FAS-XAI) that incorporates Type-2 Fuzzy Logic, stacking ensembles of XGBoost, CatBoost, and LightGBM, and a Cognitive Transparency Module. This model was evaluated using the GHs Wave 5 (20232024; N = 5,067) of Nigeria with cross-validation and performance values of R 2 and AUC. FAS-XAI showed an impressive predictive performance (R 2 = 0.967; AUC = 0.996), reducing the exclusion errors by 100-34.3 per cent. High-ranked predictors were found to be the dependency ratio, asset wealth and gaps in energy transition, whereas integrated interventions had more significant poverty reduction impacts. This paper introduces a novel groundbreaking fuzzy-stacking explainable AI framework that combines interpretability and robustness, providing a policy-relevant, scalable solution to transparent and equitable poverty targeting in Nigeria.
Optimizing Chronic Kidney Disease Prediction Via Ensemble Learning On Imbalanced Multi-Feature Clinical Data Emmanuel John Anagu; Gani Timothy Abe; Victoria Zevini Sabo; Sunday Jatau Lamiri
Brilliance: Research of Artificial Intelligence Vol. 6 No. 2 (2026): Brilliance: Research of Artificial Intelligence, Article Research May 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i2.8210

Abstract

Chronic Kidney Disease (CKD) remains a critical global health burden, characterized by its asymptomatic progression in early stages and high risk of culminating in end-stage renal disease, yet timely detection remains elusive within conventional diagnostic frameworks. This study addresses this gap by comparatively evaluating four machine learning classifiers Random Forest, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Logistic Regression for early CKD prediction using a multi-feature, class-imbalanced clinical dataset. A dataset comprising 1,659 patient records and 54 clinical, demographic, and laboratory features was sourced from the Kaggle repository, preprocessed through feature elimination (reducing features to 40), standardization, and Random Oversampling to correct class imbalance. An 80-20 train-test split was applied prior to model training and hyperparameter tuning. Classification performance was assessed using accuracy, precision, recall, F1-score, and Area Under the Receiver Operating Characteristic Curve (AUC-ROC). Random Forest achieved the highest accuracy of 99.67%, an AUC of 1.00, and near-perfect precision and recall, substantially outperforming KNN (95.26%), SVM (80.00%), and Logistic Regression (78.53%). These findings confirm the superiority of ensemble bagging methods over distance-based and linear classifiers in managing high-dimensional, imbalanced medical datasets. The study contributes to the growing body of evidence supporting machine learning integration into CKD screening pathways, while underscoring the critical role of class-balancing strategies in preventing diagnostic bias. The deployed Streamlit application further demonstrates a viable pathway toward accessible clinical decision-support tools for CKD early detection.
Comparative Analysis of K-Means, PSO-KMeans and Butterfly Optimization Algorithm for Road Damage Clustering Herfia Rhomadhona; Widiya Astuti Alam Sur; Norminawati Dewi; Winda Aprianti; Jaka Permadi
Brilliance: Research of Artificial Intelligence Vol. 6 No. 2 (2026): Brilliance: Research of Artificial Intelligence, Article Research May 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i2.8389

Abstract

Road damage on access routes to coastal tourism areas in Tanah Laut Regency, South Borneo has become a critical issue affecting travel safety and tourist visits. Various types of pavement distress such as cracking, depression, bump and sags, patching and potholes, polished aggregat, rutting, and swelling create complex data patterns that require robust analytical methods. This study adopts a data-driven approach to compare the performance of three clustering algorithms K-Means, Hybrid PSO–KMeans, and the Butterfly Optimization Algorithm (BOA) to determine the optimal grouping structure of road damage data. The dataset consists of seven types of road distress obtained from field surveys across three coastal locations. Data preprocessing was carried out through normalization and standardization to ensure consistency in scale, followed by clustering analysis with varying numbers of clusters (k = 2 to 7). The Silhouette Coefficient was used to evaluate clustering performance and determine the optimal number of clusters. The results show that the optimal clustering structure is achieved at k = 3, representing three levels of road damage severity: minor, moderate, and severe. Among the evaluated methods BOA produced the highest Silhouette Score of 0.7559, outperforming Hybrid PSO–KMeans (0.6583) and K-Means (0.442) indicating more compact and well-separated clusters. These findings suggest that BOA is more effective in handling complex and heterogeneous road damage data. Practically, this approach can support data-driven decision-making in prioritizing road maintenance.
Information System Stock And Chain Supply Smart Platform Web Rule-Based On Store Break Split Ade Wm Nofita Elfina; Rizaldi Rizaldi; Parini Parini
Brilliance: Research of Artificial Intelligence Vol. 6 No. 3 (2026): Brilliance: Research of Artificial Intelligence, Article Research August 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i3.8452

Abstract

Inventory management is an important aspect in supporting business operations, especially in the trading sector with a high level of product turnover. At Ade WM Glassware Store, inventory management is still carried out manually, resulting in inaccurate data, delayed information, and difficulties in monitoring stock availability in real-time. In addition, coordination with suppliers is not yet well integrated, which often leads to delays in restocking and imbalanced inventory levels. This study aims to design and develop a web-based intelligent inventory and supply chain information system using a rule-based approach. The research stages include data collection through observation, interviews, and literature study, system requirement analysis, system design using UML, and implementation using PHP and MySQL. The results show that the developed system improves inventory data accuracy, accelerates the recording process, and facilitates real-time monitoring of stock and suppliers. Therefore, the system enhances operational efficiency and supports the optimization of the store’s supply chain.
Real-time Detection of Magnetic Resonance Imaging (MRI) Safe Label using Deep Learning for Standardization Aisyah Widayani; Adrian Dwi Nugroho; Alifatus Wahyu Nur Ma’rifah
Brilliance: Research of Artificial Intelligence Vol. 6 No. 2 (2026): Brilliance: Research of Artificial Intelligence, Article Research May 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i2.8453

Abstract

Magnetic Resonance Imaging (MRI) is an imaging modality that uses a non-ionising magnetic field, so it does not cause radiation exposure. However, a high magnetic field strength still poses a significant safety risk due to projectile effects, so screening is necessary to verify that standard MRI objects are present. This study aims to develop an MRI-safe Label Detection using You Only Look Once version 11 (YOLOv11) Framework. The YOLOv11 is one of the Deep Learning algorithms that is used for Real-time Object Detection with Medical Imaging Standardization. The dataset used consists of a standard MRI bed image and a normal patient bed obtained from several MRI facilities, with an image size of 640 pixels, and divided into four classes. The results show that the model achieves an accuracy of 97,5%, a precision of 99,1%, a recall of 98,8%, an F1-Score of 98,9%, and an mAP50 of 98,9%, which indicates excellent detection performance. The Loss curve analysis shows a stable training process without any indication of significant overfitting. In addition, the confusion matrix shows high classification ability in each class. This research aims to develop an automated safety screening system for zone three MRI to reduce the risk of accidents. However, limitations include the small number of datasets and the limited variety of objects. Therefore, further development is recommended by increasing the variety of object data and integrating real-time systems and supporting hardware.
Application of Decision Trees for Predicting High-Risk Pregnancies at the Sukarame Community Health Center Nicken Saskia Maharani; Mardalius Mardalius; Ari Dermawan
Brilliance: Research of Artificial Intelligence Vol. 6 No. 3 (2026): Brilliance: Research of Artificial Intelligence, Article Research August 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i3.8498

Abstract

High-risk pregnancy remains one of the major causes of maternal and infant morbidity and mortality, particularly in developing countries. Early identification of pregnancy risks at the primary healthcare level is essential to improve maternal healthcare services and reduce pregnancy complications. However, at the Sukarame Community Health Center, the identification of high-risk pregnancies is still conducted manually and relies heavily on subjective assessment by healthcare workers. Although medical record data of pregnant women are available, the data have not been optimally utilized for systematic risk prediction and classification. This study aims to implement the Decision Tree algorithm to predict high-risk pregnancies using medical record data from pregnant women at the Sukarame Community Health Center. The study applies a quantitative approach using secondary data consisting of maternal age, blood pressure, hemoglobin levels, pregnancy history, and clinical symptoms. The research process includes data collection, preprocessing, classification modeling using the Decision Tree algorithm, and evaluation of model performance using accuracy, precision, and recall metrics. The results indicate that the Decision Tree algorithm is capable of classifying pregnancy risks into low, moderate, and high-risk categories in a structured and objective manner. The resulting model generates interpretable decision rules that can assist healthcare workers in conducting early detection and intervention for high-risk pregnancies. Furthermore, the implementation of the web-based prediction system improves efficiency in processing patient data and reduces subjectivity in pregnancy risk assessment. Therefore, the proposed system can support data-driven decision-making and contribute to improving the quality of maternal healthcare services at the primary healthcare level.
Analysis Of Best-Selling Accessories In The Wiwid Collection Using The Moora Method Susana Susana; Fauriatun Helmiah; Maulana Dwi Sena
Brilliance: Research of Artificial Intelligence Vol. 6 No. 3 (2026): Brilliance: Research of Artificial Intelligence, Article Research August 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i3.8538

Abstract

Medication logistics management is a critical aspect of supporting healthcare Wiwid Collection is a business selling various types of accessories located in Perk Sei Balai (Lolotan), Dusun 3 Sukajadi, Batu Bara Regency, North Sumatra. Wiwid Collection faces various challenges in determining best-selling accessories that are most in demand by consumers. Difficulties in identifying superior products persist because product selection is based on guesswork and not based on structured sales data analysis. This often leads to inaccurate decisions regarding stock management and marketing strategies. To address these issues, a Decision Support System (DSS) using the MOORA (Multi-Objective Optimization on the Basis of Ratio Analysis) method is needed, capable of processing accessory sales data in a structured and systematic manner based on assessment criteria including stock, sales quantity, price, and purchase time. The purpose of this research is to design and build a computerized system capable of assisting decision-making in determining best-selling accessories at Wiwid Collection. The Multi-Objective Optimization by Ratio Analysis (MOORA) method is one of the methods used in Decision Support Systems (DSS). The research method used is quantitative, a research method that prioritizes the collection and analysis of quantitative data in the form of numbers, statistics, and mathematical formulas. Based on the research results, the alternative preferences for best-selling accessories are ranked 1 (Long Socks), 2 (Bead Bracelets), 3 (Chinese Rubber), 4 (Star Clips), and 5 (Rings)
Zerotier-Based Remote Access and Control for MiktoTik System Rial Fauza
Brilliance: Research of Artificial Intelligence Vol. 6 No. 2 (2026): Brilliance: Research of Artificial Intelligence, Article Research May 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i2.8581

Abstract

The ZeroTier features and menu on MikroTik have been available since RouterOS version 7, specifically introduced in version 7.1rc2 for the arm and arm64 architectures. ZeroTier offers a relatively simpler configuration process compared with traditional VPNs such as PPTP, L2TP, or IPsec. Administrators only need to install the ZeroTier service on the MikroTik device and the client, then enter the Network ID so the devices can connect to each other. This convenience provides time efficiency in the implementation of remote access networks. The research method was carried out through system design, MikroTik and ZeroTier configuration, and connection testing using client devices such as a computer and a smartphone. The results show that ZeroTier is able to build a virtual network that allows communication between the client and the MikroTik device as if they were on the same local network. In addition, this technology provides security through data encryption and easier configuration compared with traditional VPNs. Thus, ZeroTier can be an effective solution to support remote management and monitoring of MikroTik devices.
YOLOv8-Based Multi-Class Detection of Coffee Bean Defects and Contaminants for Automated Quality Grading Sayid Muhammad Jundullah; Hafizh Al Kautsar Aidilof; Fadlisyah
Brilliance: Research of Artificial Intelligence Vol. 6 No. 2 (2026): Brilliance: Research of Artificial Intelligence, Article Research May 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i2.8612

Abstract

The quality of coffee beans is a crucial factor in determining export value and compliance with international standards set by the International Coffee Organization (ICO) and Standar Nasional Indonesia (SNI). Traditional manual sorting methods are time-consuming, labor-intensive, and prone to human subjectivity and inconsistency. This study aims to develop an automated coffee bean quality grading system using the YOLOv8s object detection model to accurately identify 20 classes of physical defects and contaminants from static images and automatically calculate the quality grade. A dataset consisting of 2,000 annotated images of Arabica and Robusta coffee beans was collected and divided into training (70%), validation (20%), and testing (10%) sets. The YOLOv8s model was trained using transfer learning with pre-trained weights and data augmentation techniques, then integrated into a web-based application using FastAPI for defect detection and automated defect scoring based on ICO and SNI 01-2907-2008 standards. Experimental results showed that the proposed model achieved a mean Average Precision (mAP@0.5) of 0.75, precision of 0.76, and recall of 0.75. The model performed excellently on distinct classes such as normal beans, large husk fragments, stones, and twigs, while facing challenges in differentiating visually similar defects like variants of black beans and sour beans. This study demonstrates the effectiveness of YOLOv8s for multi-class coffee bean defect detection and provides a practical, scalable, and objective solution for coffee quality assessment, significantly reducing reliance on manual inspection while improving consistency and efficiency in the grading process.
Video-Based Disease Detection in Vannamei Shrimp Using YOLOv8 Architecture Fathurrahman Siregar; Fadlisyah Fadlisyah; Hafizh Al Kautsar Aidilof
Brilliance: Research of Artificial Intelligence Vol. 6 No. 2 (2026): Brilliance: Research of Artificial Intelligence, Article Research May 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i2.8613

Abstract

Vannamei shrimp (Litopenaeus vannamei) is a high-value aquaculture commodity that significantly contributes to the fisheries sector. However, shrimp farming faces a high risk of disease outbreak to mass mortality and substantial economic losses. Conventional health detection methods rely on manual observation, which is subjective, inefficient, and requires expert knowledge. Therefore, this study proposes an automated shrimp health detection system based on video imagery using Convolutional Neural Networks (CNN) implemented through the YOLOv8 algorithm.The dataset consists of 2,000 images extracted from video frames of vannamei shrimp and categorized into healthy and diseased classes. The research methodology includes data preprocessing, augmentation, model training, and evaluation using performance metrics such as precision, recall, and mean Average Precision (mAP). The trained model is deployed in a web-based system using FastAPI and OpenCV to enable real-time detection. Experimental results show that the proposed CNN-based model achieves an mAP@0.5 of approximately 0.92 (92%), with precision and recall values of approximately 0.85 and 0.90, respectively. These results indicate strong detection performance under real-world conditions. The system is capable of automatically identifying shrimp health conditions and provides higher efficiency compared to manual inspection. This study demonstrates that deep learning-based computer vision has strong potential for early disease detection and can support sustainable aquaculture management

Page 57 of 60 | Total Record : 594

 55   56   57   58   59 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol. 6 No. 3 (2026): Brilliance: Research of Artificial Intelligence, Article Research August 2026 Vol. 6 No. 2 (2026): Brilliance: Research of Artificial Intelligence, Article Research May 2026 Vol. 6 No. 1 (2026): Brilliance: Research of Artificial Intelligence, Article Research May 2026 Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025 Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025 Vol. 4 No. 2 (2024): Brilliance: Research of Artificial Intelligence, Article Research November 2024 Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024 Vol. 3 No. 2 (2023): Brilliance: Research of Artificial Intelligence, Article Research November 2023 Vol. 3 No. 1 (2023): Brilliance: Research of Artificial Intelligence, Article Research May 2023 Vol. 2 No. 3 (2022): Brilliance: Research of Artificial Intelligence, Article Research November 2022 Vol. 2 No. 2 (2022): Brilliance: Research of Artificial Intelligence, Article Research May 2022 Vol. 2 No. 1 (2022): Brilliance: Research of Artificial Intelligence, Article Research February 2022 Vol. 1 No. 2 (2021): Brilliance: Research of Artificial Intelligence, Article Research November 2021 Vol. 1 No. 1 (2021): Brilliance: Research of Artificial Intelligence, Article Research May 2021 More Issue