cover
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
ISSN : -     EISSN : 28079035     DOI : https://doi.org/10.47709
Core Subject : Science, Education,
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 Articles sent to the Brilliance may not be published elsewhere.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.
Articles 637 Documents
Crowdsourced Facility Issues Reporting System: A Case Study in Higher Education Institution Athiyatul Ulya; Annisa Karima; Liza Afra; Annisya Febriana Lubis; M. Arsaly Athaaf Neutron
Brilliance: Research of Artificial Intelligence Vol. 6 No. 4 (2026): Brilliance: Research of Artificial Intelligence, Article Research November 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i4.9684

Abstract

Higher education institutions (HEIs) face persistent inefficiencies in facility management due to reliance on manual, paper-based reporting mechanisms, resulting in communication bottlenecks, delayed maintenance, and a lack of traceability. Although crowdsourcing has proven effective in urban civic management, its application within the micro-environment of a university campus remains underexplored. This study aims to design, develop, and evaluate a web-based Crowdsourced Facility Issues Reporting System tailored for HEIs, utilizing a case study at the Faculty of Engineering, Malikussaleh University. Employing a Research and Development (R&D) approach, the system was developed iteratively using the Prototyping method, with requirements derived from interviews and observations analyzed via thematic analysis. The system was implemented using PHP and MySQL, featuring a three-tier role-based access control architecture (Reporter, Faculty Admin, and Bureau Admin). Functional evaluation through Black Box Testing confirmed that all system modules operated according to specifications. A key finding from the implementation is the efficacy of a "Tiered Triage" workflow model, where the Faculty Admin acts as an intermediary verification node. This hierarchical filtration successfully filters invalid or hyper-local issues before they reach the central bureau, preventing administrative overload. Ultimately, the system transforms passive facility users into active stakeholders by providing real-time status tracking, thereby restoring transparency, reducing manual data entry errors, and offering a scalable digital model for facility management in complex institutional bureaucracies.
Controllable Stable Diffusion Using ControlNet for Stylized Javanese Script Typography Synthesis Zidan Amikul Afham; Muhammad Fachrie
Brilliance: Research of Artificial Intelligence Vol. 6 No. 4 (2026): Brilliance: Research of Artificial Intelligence, Article Research November 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i4.9729

Abstract

Preserving traditional indigenous scripts in digital environments requires robust computational frameworks that maintain strict orthographic fidelity alongside flexible artistic expression. Indigenous writing systems possess intricate non-linear structures, vertical character stacking, and delicate diacritics that frequently trigger severe structural distortion and character hallucinations in standard text-to-image generative architectures. This research aims to develop an automated hybrid pipeline that unites rule-based natural language processing with probabilistic generative artificial intelligence to synthesize high-fidelity stylized Javanese script calligraphy. The proposed method integrates linguistic normalization and deterministic transliteration to produce standardized visual guidance masks, followed by dual spatial conditioning that executes edge boundary extraction and depth estimation in parallel. Furthermore, low-rank adaptation modules are embedded into the latent diffusion process to extract complex visual material textures from curated paired synthetic datasets. Experimental evaluations demonstrate that the optimal parameter configuration successfully synthesizes five distinct aesthetic material styles with zero typographical errors and zero percent physical glyph deformation. The dual spatial constraints effectively lock vertical stacking components and microscopic diacritics while rendering realistic three-dimensional relief depth and specular surface lighting. In conclusion, the proposed hybrid architecture resolves structural disorientations in baseline diffusion models, providing a reliable technological infrastructure for digital cultural preservation, automated graphic typography production, and creative ethnic heritage dissemination.
Comparison of Support Vector Machine Optimization Methods for Chili Pepper Nutrient Deficiency Identification Ilham Sahputra; Usnawiyah Usnawiyah; Athiyatul Ulya; Sirril Muna; Ahmad Rizki
Brilliance: Research of Artificial Intelligence Vol. 6 No. 4 (2026): Brilliance: Research of Artificial Intelligence, Article Research November 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i4.9730

Abstract

Deficiencies of macronutrients such as nitrogen, phosphorus, and potassium in chili pepper plants can cause visible changes in leaf characteristics, which can be utilized as information for identifying plant conditions through digital images. The performance of the Support Vector Machine in classifying leaf conditions is highly influenced by its hyperparameter configuration; therefore, an appropriate optimization strategy is required. This study aims to compare the performance of four Support Vector Machine optimization methods, namely Grid Search, Particle Swarm Optimization, Principal Component Analysis, and Adaptive Boosting, combined with RGB color features and Gray Level Co-occurrence Matrix texture features to classify four conditions of chili pepper leaves: healthy, nitrogen-deficient, phosphorus-deficient, and potassium-deficient leaves. The classification was performed using two image resolutions, namely 120 × 120 and 244 × 244 pixels. This study employed a quantitative approach using 1,040 chili pepper leaf images obtained from primary data and secondary datasets from Kaggle and Roboflow. The research process consisted of data augmentation, feature extraction, Support Vector Machine modeling, and evaluation using accuracy, precision, recall, and F1-score. The experimental results showed that the Particle Swarm Optimization configuration achieved the highest accuracy, reaching 86.06% for 244 × 244 pixel images and increasing to 91.83% for 120 × 120 pixel images. It was followed by Grid Search, which achieved 84.13% and 90.38%, respectively, while Principal Component Analysis and Adaptive Boosting achieved lower accuracy at both image resolutions. This study concludes that the combination of RGB and Gray Level Co-occurrence Matrix features with Particle Swarm Optimization provides the best classification performance for identifying nutrient conditions in chili pepper plants based on leaf images. The findings also indicate that image resolution affects classification accuracy differently across optimization methods.
Deployment-Aware Evaluation of a Machine Learning-Based Web Application Firewall for Academic E-Voting Systems Muhammad Zainuddin; Achmad Zakki Falani; Hariadi Yutanto
Brilliance: Research of Artificial Intelligence Vol. 6 No. 4 (2026): Brilliance: Research of Artificial Intelligence, Article Research November 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i4.9731

Abstract

Web applications in higher education, including e-voting systems for student-organization elections, are frequent targets of SQL Injection (SQLi) and Cross-Site Scripting (XSS) attacks. Machine Learning (ML) based Web Application Firewall (WAF) studies usually select models by offline accuracy on curated datasets, which says little about how a model behaves once it filters live requests. This study aims to build an ML-based WAF embedded as middleware in an academic e-voting application and to test whether offline accuracy is a sufficient criterion for selecting a deployable model. HTTP request payloads were vectorized with character-level TF-IDF n-grams and Chi-Square feature selection, and Decision Tree (DT) and Random Forest classifiers were integrated into a Flask-based WAF that performs allow, block, and log actions. The models were assessed with a three-layer deployment-aware protocol: offline hold-out evaluation, black-box testing of the integrated middleware, and an independent stress test of 500 requests containing obfuscated attacks and look-alike benign inputs. Offline, the two models differed by less than 0.3 percentage points, with Random Forest reaching 99.54% accuracy for SQLi and 100% for XSS. Under the stress test, however, DT missed four obfuscated SQLi payloads, whereas Random Forest blocked all 400 attacks with 99.2% overall accuracy and a mean inference latency of 5.5 ms. Offline accuracy therefore hid a security-relevant difference that only deployment-aware testing revealed. The protocol and the security-first selection criterion offer a practical basis for evaluating ML-based WAFs in institutional web applications.
AI-Based Prediction of Water Vapor Changes from Kalimantan Forest Fires Using Terra MODIS Imagery Oktalia Triananda Lovita; Zharifah Muthi’ah; Mohd. Iqbal Muttaqin; Mulyati Mulyati; Khairunnisa Khairunnisa
Brilliance: Research of Artificial Intelligence Vol. 6 No. 4 (2026): Brilliance: Research of Artificial Intelligence, Article Research November 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i4.9749

Abstract

The weather changes from forest fires in Kalimantan resulted in the earth's changing very ekstrim. Water Vapor or Vapor is a manifestation of water in the form of gas. It is still a job has been difficult for researchers atmosphere. Global Positioning System (GPS) in the troposphere and are equipped with surface data, this study used 8 (eight) GPS stations Kalhutra GPS Array (SuGAR) and 2 (two) points which is the world IGS CORS station. This method is called inversion GPS, while the TERRA MODIS satellite imagery used methods transmittance. From the experiments conducted in this research process, obtained. From the results of plotting graphs of temporal variations, it is known that the average moisture content in the dry months ranged from 56.59 mm to 38.95 mm, while the wettest months in this case because the graph ranges from 58.71 mm to 47.72 mm. The obtained results from average Water Vapor during the fire that was in 2010 ranged from 70.26% in 2011 ranged between 84.49% and in 2026 ranged from 90.15%, but the correlation (r) between the Water Vapor from TERRA MODIS satellite imagery and GPS is quite high. Based on forest fires, MODIS estimate the humidity around 54-77%. But Water Vapor obtained TERRA MODIS satellite imagery ranges between ± 3-8 cm / day is ± 89.49%. Then it will affect human health, because it influences the weather cycle in Indonesia.
Machine Learning-Based Classification of Quranic Verses Based on Islamic Pillars Fauzan Azima; Safwandi Safwandi; Said Fadlan Anshari
Brilliance: Research of Artificial Intelligence Vol. 6 No. 4 (2026): Brilliance: Research of Artificial Intelligence, Article Research November 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i4.9760

Abstract

Background: Text classification is a machine learning process used to categorize data based on specific characteristics. This study focuses on classifying the content of Islamic Pillars in Quranic verses into six categories: Shahada, Salah, Zakat, Fasting, Hajj, and Non-Islamic Pillars. Objective: This study seeks to develop a classification application while evaluating Naive Bayes and Support Vector Machine (SVM) algorithms with TF-IDF and FastText as feature representation methods. Methods: The dataset consisted of 800 Quranic verses selected using purposive sampling and divided into 80% training data and 20% testing data. The research stages included data preparation, text preprocessing, feature representation, model training, testing, evaluation, and implementation of the best-performing model in an application. Model performance was evaluated using accuracy, macro precision, macro recall, and macro F1-score. Results: The results showed that the SVM model using TF-IDF achieved the best performance, with an accuracy of 81.88%, macro precision of 92.55%, macro recall of 75.63%, and macro F1-score of 81.98%. Based on these results, SVM with TF-IDF was selected as the final classification model and implemented in the application to classify Quranic verses according to the content of the Islamic Pillars. Conclusion: The results demonstrate that the combination of SVM and TF-IDF can be applied to classify Quranic verses into the defined Islamic Pillars categories.
Development of a Robotic Arm Using a Convolutional Neural Network for Areca Nut Sorting Herizon Herizon; Milda Yuliza; Fisla Wirda; Ranti Dina Fitri; Rahmat Rahmat
Brilliance: Research of Artificial Intelligence Vol. 6 No. 4 (2026): Brilliance: Research of Artificial Intelligence, Article Research November 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i4.9770

Abstract

Manual post-harvest sorting of areca nuts is time-consuming and may result in inconsistent classification. To address this limitation, this study developed an automated sorting system that integrates a Convolutional Neural Network (CNN) with a robotic arm to classify and transfer areca nuts into the juice and split categories. The system comprises webcam-based image acquisition, image processing and classification using Python and the MobileNetV3 architecture, and a microcontroller-based control system for a 4 degree of freedom (4 DOF) robotic arm. The CNN model was trained to classify three categories: juice areca nut, split areca nut, and surrounding objects. Based on the reported confusion matrix, the model correctly classified 188 of 189 validation images, achieving an accuracy of 99.47%. The image processing evaluation also reported accuracy values of 99.07% for color, 91.65% for shape, and 94.62% for dimensional measurement. Integrated system testing was conducted on 30 areca nuts, comprising 15 juice type and 15 split type nuts. All 30 objects were successfully transferred to their designated bins, resulting in a sorting success rate of 100% under the tested conditions. The reported CNN inference time was 0.032 s, while the average robotic arm movement time was 15 s per cycle, yielding an estimated total sorting time of 15.032 s per object. These findings demonstrate the feasibility of integrating CNN based image classification with robotic manipulation for automated areca nut sorting. Further testing involving more diverse samples and operating conditions is required to assess the system's generalizability and operational reliability.
A Multi-Algorithm AIoT Framework for Sustainable Performance Assessment in Rural Banks Muhammad Syaukani; Fitria Fitria; Yeffriansjah Salim; Muhammad Amin Paris; Surya Eka Priyatna
Brilliance: Research of Artificial Intelligence Vol. 6 No. 4 (2026): Brilliance: Research of Artificial Intelligence, Article Research November 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i4.9802

Abstract

Sustainability assessment in Rural Banks (RBs) remains challenging due to fragmented operational data, limited analytical capabilities, and inadequate integration of economic, social, and environmental indicators. This study aims to develop an Artificial Intelligence of Things (AIoT)-based decision support framework for comprehensive, data-driven sustainability assessment in rural banking. The proposed framework integrates Global Reporting Initiative (GRI) indicators, the Analytical Hierarchy Process (AHP), a Sustainability Index, and the Random Forest algorithm. Using a Design Science Research approach, the framework was evaluated using operational and organizational data from five Rural Banks in South Kalimantan, covering 2021–2025. The dataset comprised 100 quarterly observations and 31 sustainability indicators derived from sensor-based operational monitoring and non-sensor organizational disclosures. AHP assigned the highest weight to the environmental dimension (0.38), followed by the social (0.34) and governance (0.28) dimensions, with an acceptable consistency ratio of 0.073. The Random Forest model achieved an R² of 0.87, an RMSE of 0.18, and an MAE of 0.12, outperforming Linear Regression, Support Vector Machine, and XGBoost. Feature importance and SHAP analyses identified emissions and energy consumption as the dominant indicators, followed by workplace and customer safety. These findings demonstrate the potential of integrating AIoT monitoring, multi-criteria weighting, and machine learning to improve sustainability evaluation. Practically, the framework supports transparent performance monitoring, predictive analysis, and evidence-based strategic decision-making. Future research should expand the number of participating banks and improve automated monitoring of non-sensor indicators.
Information Systems Strategic Planning for Computer Science Faculty to Achieve LAM-INFOKOM Excellent Accreditation Dicky Pratama; Muhammad Rachmadi; Novan Wijaya; Balqis Muthmainnah
Brilliance: Research of Artificial Intelligence Vol. 6 No. 4 (2026): Brilliance: Research of Artificial Intelligence, Article Research November 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i4.9804

Abstract

Rapid technological shifts and stringent accreditation standards require higher education institutions to align their information technology infrastructure with organizational goals strategically. This study addresses operational inefficiencies, data silos, and manual quality management processes within a Faculty of Computer Science in South Sumatra seeking to achieve LAM-INFOKOM Excellent Accreditation. This research aims to develop a comprehensive Information Systems and Information Technology (IS/IT) strategic plan that automates the Planning, Implementation, Evaluation, Control, and Improvement (PPEPP) quality cycle and optimizes academic tridharma data. Utilizing the Ward and Peppard framework, the methodology incorporates internal and external environment assessments through Value Chain, PESTEL, SWOT, and Critical Success Factors (CSF) analyses. The findings yield a prioritized future application portfolio categorized via the McFarlan Strategic Grid, featuring a Strategic Automated Accreditation Portal, an Outcome Based Education (OBE) Management Platform, and an integrated Academic Information System linked via an API Gateway. Furthermore, the resulting IT infrastructure strategy advocates for cloud-based Virtual Private Servers and enhanced cybersecurity frameworks in compliance with data privacy regulations. Practically, this research delivers an actionable five-year roadmap (2026–2030) that bridges the gap between technical execution and institutional quality assurance. In conclusion, the formulated strategic blueprint successfully aligns digital transformation with accreditation benchmarks, providing a sustainable roadmap for academic excellence and serving as a scalable reference for higher education institutions undergoing digital transformation.
IndoBERTweet-Based Sentiment Analysis of AIESEC Indonesia's Instagram Comments for Brand Image Assessment An'nur Aisyah Ghaidah Senjaya Mangkunegara; Apriansyah Putra; Ken Ditha Tania; Mira Afrina
Brilliance: Research of Artificial Intelligence Vol. 6 No. 4 (2026): Brilliance: Research of Artificial Intelligence, Article Research November 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i4.9805

Abstract

Social media platforms such as Instagram have become strategic channels through which organizations shape their brand image, and public comments on official accounts often reflect collective perceptions that are difficult to interpret manually because of their volume and informal language style. AIESEC Indonesia, the national chapter of the world's largest youth-run international non-governmental organization, relies heavily on its official Instagram account to communicate its leadership-development programs and cross-cultural exchange opportunities to Indonesian youth, yet no prior study has systematically examined how comment sentiment reflects the organization's brand image at the national level. This study aims to identify the sentiment tendencies of public comments on AIESEC Indonesia's Instagram posts, to evaluate the performance of IndoBERTweet in classifying these Indonesian-language comments through sentiment analysis, and to interpret the resulting sentiment distribution as a brand image indicator. A descriptive quantitative approach was applied, in which comments were collected through crawling, cleaned and normalized, manually labeled into positive, neutral, and negative categories, and classified using a fine-tuned IndoBERTweet model evaluated with accuracy, precision, recall, and F1-score. Results from 755 comments show 60.7% positive, 32.6% neutral, and 6.8% negative sentiment. IndoBERTweet achieved 83.3% accuracy and a 0.813 macro F1-score, outperforming the baseline by improving negative sentiment detection. Conclusively, AIESEC maintains a highly favorable brand image, and IndoBERTweet can effectively automate feedback monitoring. These findings are expected to provide an evidence-based understanding of public perception toward AIESEC Indonesia on social media.

Filter by Year

2021 2026


Filter By Issues
All Issue Vol. 6 No. 4 (2026): Brilliance: Research of Artificial Intelligence, Article Research November 2026 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