Garuda - Garba Rujukan Digital

Article Per Year (5 Year)

All

Brilliance: Research of Artificial Intelligence

brilliance
Website

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 Articles sent to the Brilliance may not be published elsewhere.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 544 Documents

51 52 53 54 55

Effectiveness of the E-Katalog System in Supporting the Procurement Process of Goods and Services Tires, Thalia Devega; Qona'ah, Insanita; Rustam, Arief Hertadi; Irawan, Debi; Ismail, Ismail
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.7443

This research investigates the effectiveness of the E-Catalog system in supporting goods and services procurement at Sesko TNI Bandung. As a digital procurement platform introduced by the government, the E-Catalog aims to increase transparency, accuracy, and process efficiency. Despite these intended advantages, its adoption remains constrained by users’ limited familiarity with digital procurement practices and their long-standing reliance on manual procedures. To address this issue, the study applies the Technology Acceptance Model (TAM) as the analytical framework, focusing on perceived usefulness, perceived ease of use, user attitudes, and behavioral intentions toward system utilization. A mixed-methods approach with a sequential explanatory design was employed. The quantitative phase involved distributing structured questionnaires to procurement personnel to measure key variables related to system acceptance. Subsequently, qualitative data were obtained through in-depth interviews with procurement operators to clarify and deepen the interpretation of statistical results. The study finds that perceived usefulness and perceived ease of use significantly shape user attitudes and intention to utilize the E-Catalog. These variables collectively contribute to improving the overall effectiveness of the procurement process. The results highlight that the more users perceive the system as beneficial and easy to operate, the more likely they are to adopt it consistently, thereby enhancing operational efficiency at Sesko TNI Bandung. This research underscores the importance of increasing digital literacy, strengthening system socialization, and providing continuous training to optimize the performance of the E-Catalog platform.

Predictive Maintenance on Fortinet Firewall Devices Using Artificial Intelligence Rustianto, April; Murobbie, Faqih; Rusmanto, Rusmanto
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.7448

The growing complexity of enterprise network infrastructures has increased the importance of predictive maintenance for network security devices, particularly firewall systems. In operational environments using Fortinet firewalls, large volumes of firewall logs are continuously generated, while existing monitoring tools such as FortiAnalyzer remain limited to descriptive analysis and lack predictive capabilities. This study aims to evaluate the effectiveness of artificial intelligence, specifically Large Language Models (LLMs), for predictive maintenance through automated analysis of firewall logs. Four open-source LLMs-Gemma 2B, Mistral 7B, DeepSeek-R1 7B, and Qwen 2.5-Coder 7B-were benchmarked using a standardized Indonesian-language prompt designed to extract high-severity events, including emergency, alert, and critical conditions, from multi-severity Fortinet log data. The evaluation focused on AI benchmarking metrics such as severity filtering compliance, reasoning accuracy, linguistic consistency, structural clarity, and processing efficiency. The results indicate that Qwen 2.5-Coder 7B provides the most reliable overall performance, demonstrating strong adherence to severity constraints, consistent Indonesian-language output, and well-structured analytical results suitable for operational predictive maintenance. Mistral shows superior contextual reasoning but exhibits language inconsistency, while Gemma offers the fastest processing time with moderate severity accuracy. DeepSeek performs least effectively due to instruction non-compliance. This study addresses an existing research gap by demonstrating how large language models can support predictive maintenance for firewall-based network security systems and provides a comparative framework for future AI-driven firewall and log-analysis research.

Evaluating BISMA Application Success at Jambi University Using the D&M Information Success Model Nuraini, Rts; Utomo, Pradita Eko Prasetyo; Lestari, Dewi
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.7455

The BISMA application is a web-based information system adopted by Jambi University to manage the submission, review, and reporting processes for research and community service activities. As a mandatory system implemented since 2024, it is essential to evaluate its level of success and user acceptance to ensure that the system effectively supports academic and administrative needs. This study aims to assess the success of BISMA using the DeLone and McLean IS Success Model, which comprises six key constructs: System Quality, Information Quality, Service Quality, Use, User Satisfaction, and Net Benefit. This model was selected because it provides a comprehensive framework for examining system performance, information effectiveness, and the resulting impact on user satisfaction and organizational benefits. A quantitative approach was employed by distributing questionnaires to 100 respondents consisting of lecturers and internal BISMA users. The collected data were analyzed using Structural Equation Modeling–Partial Least Squares (SEM-PLS) to test the relationships among the model’s constructs. The findings indicate that Information Quality and User Satisfaction significantly influence system use and perceived net benefits, suggesting that accurate, relevant, and timely information plays a crucial role in enhancing the value of the system. Conversely, System Quality and Service Quality were found to have no significant effect on user satisfaction, indicating the need for improvements in system reliability, responsiveness, and technical support. Overall, BISMA is considered to provide satisfactory benefits in supporting research and community service management; however, enhancements in service quality and system stability are still required to optimize user experience and strengthen system effectiveness in the future.

Performance Comparison of EfficientNetB0 in Potato Leaf Disease Classification with Adam and SGD Rivaldo, Mario; Udjulawa, Daniel
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.7482

Potatoes (Solanum tuberosum L.) are an important food commodity for global food security, but they are highly susceptible to leaf diseases that reduce yield and tuber quality. This study aims to classify potato leaf diseases using the EfficientNetB0 architecture with two optimizers, Adam and SGD, and applying data augmentation techniques such as rotation, flipping, and cropping. The dataset consists of 3076 images divided into seven categories: Bacteria, Fungi, Healthy, Nematodes, Pests, Phytophthora, and Viruses. The results show that the Adam optimizer with a learning rate of 0.001, a batch size of 16, and 100 epochs provides the best performance. The training accuracy reached 92.10%, validation 81.49%, and testing 78.14%. The model precision was 0.7982, recall was 0.7536, and the F1 score was 0.7671. Meanwhile, the SGD optimizer produced a test accuracy of 79.55%, with precision of 0.7752, recall of 0.7781, and an F1 score of 0.7715. Although Adam's accuracy is higher, SGD shows better stability in preventing overfitting. This study confirms that data augmentation plays an important role in improving model performance, although the challenge of overfitting still needs to be addressed. Further studies are expected to optimize hyperparameters and explore other model architectures to improve the accuracy and efficiency of potato leaf disease classification.

Comparison of XGBoost and LightGBM Algorithms in Predicting Heart Disease Caroline, Fionna; Rachmat, Nur
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.7505

Heart disease remains a leading cause of mortality worldwide, underscoring the need for early and accurate diagnosis to reduce complications and improve patient outcomes. Recent advances in machine learning have enabled the development of predictive models that assist healthcare professionals in disease detection using patient medical records. This study aims to develop and compare the performance of Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) for heart disease prediction. The dataset used in this research was obtained from the UCI Machine Learning Repository and consists of 303 patient records with binary class labels indicating the presence or absence of heart disease. Data preprocessing involved feature standardization using StandardScaler and handling class imbalance through the Synthetic Minority Over-sampling Technique (SMOTE). Model evaluation was conducted using Stratified K-Fold Cross Validation with K values of 3, 5, and 7 to ensure robust and unbiased performance assessment. Hyperparameter optimization was carried out using RandomizedSearchCV to efficiently identify optimal model configurations. Experimental results indicate that both XGBoost and LightGBM achieved strong classification performance, with accuracy exceeding 80% and AUC values above 0.89. LightGBM demonstrated slightly superior performance in terms of average accuracy, F1-score, and stability across folds, while XGBoost achieved higher precision, reflecting better control of false positives. Overall, both algorithms are effective for heart disease prediction, supporting the potential of machine learning in early disease detection and clinical decision-support systems.

Analysis of the Effect of Digital Color Grading Techniques on Aesthetic Perception and Emotional Response in a Short Rice Farming Video Yuda, Yoga Prisma; Kurniawati, Inung Diah; Azis, Muh.Nur Luthfi
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.7525

Digital color grading is a post-production technique used to adjust hue, saturation, luminance, and color temperature to enhance visual mood, aesthetic appeal, and emotional expression. In agricultural-themed videos, color adjustments significantly influence how audiences perceive naturalness, warmth, authenticity, and emotional closeness to rural environments. This study aims to examine the influence of three digital color grading techniques—warm tone, cool tone, and neutral tone—on viewers’ aesthetic perception, emotional response, visual comfort, and thematic suitability when watching a two-minute video of rice-field activities. An experimental design was employed, involving 30 respondents who evaluated three graded versions using a 5-point Likert questionnaire. The analysis relied solely on descriptive statistics, including mean, standard deviation, and frequency distribution, to identify perceptual tendencies across tone variations. The findings indicate that warm tone tends to improve aesthetic judgment and emotional positivity, while neutral tone contributes to higher visual comfort due to its natural appearance. Cool tone, although perceived as calm and professional, shows lower emotional engagement in this context. These results align with previous Indonesian multimedia studies emphasizing the role of color tone in shaping viewer interpretation of documentary and thematic video content. This research contributes practical insights for multimedia practitioners, educators, and content creators working with agricultural visual materials. The outcomes may guide color grading decisions for rural documentaries, educational videos, or promotional media by highlighting how tone selection influences viewer perception.

The Utilization of Mobile-Based GeoGebra Applications for Elementary School Educators Nita, Sekreningsih; Untari, Erny; Astuti, Indra Puji; Sari, Eka Resty Novieta; Sussolaikah, Kelik
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.7542

In the current Generation-Z Era, the use of digital technology in learning, especially mathematics in elementary schools, is increasingly important to increase student effectiveness and engagement. GeoGebra Mobile, as a dynamic mathematics application, offers interactive visualizations that can help students understand abstract concepts more concretely. This study discusses the use of mobile-based GeoGebra in mathematics learning at the Bancong Elementary School level, Madiun Regency, which includes materials on plane figures, fractions, number lines, and simple Cartesian coordinates. Meanwhile, the method used in this study is a literature review by examining various sources such as journals, books, and relevant research reports related to the use of the GeoGebra Mobile application in elementary mathematics learning. Furthermore, the researcher conducted analysis and scoring by grouping several findings based on benefits, implementation, as well as challenges and solutions. The final results of the study show that the GeoGebra Mobile application can help in visualizing abstract concepts, making it easier to understand concepts and being skilled in solving basic mathematical problems with a score of 90.00 (very good), GeoGebra as an interactive and innovative mathematics learning score of 85.15 (very good), with GeoGebra can motivate students to learn score of 88.50. In addition, GeoGebra also supports students in independent learning score of 80.50 (good) and can facilitate authentic assessment with a score of 80.10 (good). Although there are several technical challenges, practical solutions can be implemented so that the use of the GeoGebra Mobile application remains optimal. The conclusion is that the use of the GeoGebra Mobile application is in line with the characteristics of today's students (gen-z) who are familiar with digital devices.

Soil Health Data Acquisition System with Augmented Reality (AR) Features: Innovation in Sustainable Plantation Management Abadi, Sarosa Castrena; Aminah, Siti; Ramdani, Cepi
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.7548

Plantations in West Java are vital to Indonesia’s agricultural economy, yet they face significant challenges in efficient and real-time soil monitoring due to reliance on conventional, labor-intensive methods. This study aims to develop a distributed soil health data acquisition system integrated with Augmented Reality (AR) visualization to enable intuitive, real-time access to key soil parameters specifically moisture, pH, and NPK (Nitrogen, Phosphorus, Potassium) levels without manual sampling. The system employs a multi-hop LoRa-based wireless sensor network comprising two sensor nodes and a master gateway. Node 2 collects soil nutrient data and relays it to Node 1, which aggregates it with environmental data before forwarding the payload to the gateway. The gateway publishes the consolidated data to an MQTT broker, which feeds both a Firebase database and a Unity-based AR application. System performance was evaluated through field tests measuring latency, packet loss, and AR rendering accuracy across ten data batches. The system achieved stable communication with an average end-to-end latency of 3.00–3.40 ms and successfully visualized soil metrics in real time through the AR interface. Although minor packet loss (up to 20%) occurred in later test batches, data integrity remained sufficient for monitoring non-rapidly changing soil conditions. The integration of LoRa multi-hop communication and AR provides a robust, scalable framework for real-time soil monitoring, offering a practical foundation for future smart agriculture systems in plantation environments.

Indonesian-Language Spam Email Classification Using Support Vector Machine Rizi, Muhammad Alfa; Rachmat, Nur
Brilliance: Research of Artificial Intelligence Vol. 6 No. 1 (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.v6i1.7578

Spam email remains a significant problem in digital communication, particularly for Indonesian-language emails, due to linguistic complexity, informal writing styles, and similarities between spam and legitimate (ham) messages. These factors often reduce the effectiveness of traditional spam filtering techniques. This study evaluates the performance of the Support Vector Machine (SVM) algorithm for classifying Indonesian spam emails using a combination of Term Frequency–Inverse Document Frequency (TF-IDF) and N-gram features. The proposed approach applies a text preprocessing pipeline, including case folding, text cleaning, tokenization, stopword removal, and stemming, to reduce noise and improve feature representation. Text data are transformed into numerical vectors using TF-IDF with unigram and bigram configurations to capture individual terms and contextual phrase patterns commonly found in spam emails. A linear kernel SVM is used as the classification model, and its performance is evaluated using K-Fold Cross-Validation to ensure robustness and reduce evaluation bias. The model is assessed using accuracy, precision, recall, and F1-score metrics. Experiments are conducted on the Indonesian Email Spam Dataset, consisting of 2,636 emails, with 1,368 spam messages and 1,268 non-spam (ham) messages. Experimental results show that the proposed model achieved an average accuracy of 98.71%, precision of 98.34%, recall of 99.20%, and F1-score of 98.76 across 10-fold cross-validation. This study contributes to the development of an efficient and lightweight spam detection model for Indonesian-language emails and provides empirical evidence that SVM combined with TF-IDF and N-gram features remains a reliable alternative to more complex deep learning approaches for medium-sized text datasets.

Rice Leaf Disease Classification Using ResNet-50: A Comparative Study of Adam, SGD, and RMSProp Paula, Bebin; Pribadi, Muhammad Rizky
Brilliance: Research of Artificial Intelligence Vol. 6 No. 1 (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.v6i1.7582

Rice plant diseases significantly affect crop productivity and require accurate and timely identification to support effective management. This study proposes a rice leaf disease classification approach using the ResNet-50 convolutional neural network and compares the performance of three optimization algorithms, namely ADAM, Stochastic Gradient Descent (SGD), and RMSProp. The model was trained and evaluated on a rice leaf image dataset consisting of four classes BrownSpot, Healthy, Hispa, and LeafBlast. The dataset contains visual variations in color, texture, and disease patterns that influence classification performance. Performance was assessed using training accuracy, loss, precision, recall, F1-score, and confusion matrix analysis. These evaluation metrics provide a comprehensive measurement of model effectiveness and class-wise prediction behavior. Experimental results show that the ADAM optimizer achieved the best performance with a training accuracy of 75.84%, followed by RMSProp at 74.60%, while SGD obtained the lowest accuracy of 71.34%. The differences in performance highlight the impact of optimization strategies on deep neural network training stability. Class-wise evaluation indicates that the model performed well in detecting BrownSpot and Healthy classes, but showed lower performance on the Hispa class across all optimizers. This limitation is influenced by the visual similarity of Hispa symptoms to other classes. These findings demonstrate that adaptive learning rate–based optimizers provide faster convergence and better classification performance for deep learning–based rice disease detection. The results support the use of optimized convolutional neural networks for image-based agricultural applications.

Page 54 of 55 | Total Record : 544

51 52 53 54 55

Filter by Year

2021 2026

Filter By Issues

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

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

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

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

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