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 Articles sent to the Brilliance may not be published elsewhere.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 544 Documents
Front-End Development of a Geographic Information System for Language and Literature Mapping in Jambi Putra, Aldi Sukma; Utomo, Pradita Eko Prasetyo; Khaira, Ulfa
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.v5i2.7388

Abstract

This study addresses the need for an interactive digital platform to support the preservation of linguistic and literary data in Jambi Province. Existing platforms developed by Balai Bahasa Provinsi Jambi provide textual information only and lack spatial visualization, limiting users’ ability to explore linguistic distributions. Geographic Information Systems (GIS) are suitable for linguistic documentation because dialect boundaries and speech communities are strongly related to geographic regions. This study aims to design and develop a front-end GIS interface for mapping linguistic and literary data using the Incremental Model and to evaluate its functional performance through Black-Box Testing. The system was built using HTML, CSS, JavaScript, the Laravel Blade templating engine, and the Leaflet library for interactive map visualization. The Incremental Model supported iterative development, allowing core features map visualization, search and filter functions, and detailed information pages to be refined based on continuous feedback. Data from Balai Bahasa Provinsi Jambi, including language names, literary descriptions, documentation files, and geographic coordinates, were used as input. The results show that the system meets all functional requirements, achieving a 100% success rate across 11 Black-Box test scenarios, and providing real-time response capabilities for search and filter functions. These technical outcomes demonstrate that incremental front-end development is effective for building modular and interactive GIS interfaces. This study contributes to digital cultural preservation efforts and provides a foundation for future GIS-based linguistic mapping initiatives, while further research is needed to enhance backend integration, expand datasets, and evaluate system performance at scale.
Application of Visual Data Mining for Visualization of UKBI Achievement Data Yolanda, Ketri genes; Utomo, Pradita Eko Prasetyo; Abidin, Zainil
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.v5i2.7409

Abstract

The current visualization of Adaptive Indonesian Language Proficiency Test (UKBI Adaptif) results in Jambi Province is suboptimal, often relying on static, basic charts, which hinders transparency and the effective formulation of evidence-based language policies. This research aims to address this critical gap by developing an interactive, data-driven system to analyze the language proficiency profile of UKBI participants in Jambi from 2021 to 2024. The research objective is to accurately map regional competence, identify hidden patterns, and provide actionable intelligence to the Jambi Language Center. The study adopts the Visual Data Mining (VDM) methodology, integrating interactive visualization with the K-Means clustering algorithm. This method allowed for the normalization and grouping of over 10,000 participant data points, with the optimal number of clusters determined by the Silhouette Score. The research results successfully established three distinct proficiency clusters, including a "Listening Struggler Group" dominated by non-education professions, exhibiting significantly low scores in the Listening section. Furthermore, geographical analysis revealed a disparity where Jambi City—the region with the highest participation—maintained an average proficiency at the lower boundary of the Intermediate category, while smaller regions like Muaro Jambi showed higher rates of Superior and Exceptional achievement. The conclusion is that the VDM-based interactive dashboard is a validated and effective tool that successfully provides micro-level insights, supporting the strategic allocation of resources and the design of targeted intervention programs to address specific skill weaknesses, such as listening comprehension.
Emotion Detection and Sentiment Analysis of Women’s E-Commerce Clothing Reviews Using DistilBERT Transformer Muflih, M; Karyadiputra, Erfan
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.v5i2.7411

Abstract

Customer reviews on e-commerce platforms have become an essential source of information for understanding user perceptions, satisfaction levels, and product quality. However, most existing studies still focus on sentiment polarity classifying opinions only as positive or negative without examining deeper emotional expressions that may reflect customer experiences more comprehensively. To address this gap, this study applies a Natural Language Processing (NLP) approach using the pre-trained DistilBERT transformer model to detect emotional patterns in women’s fashion product reviews. The dataset, obtained from Kaggle’s Women’s E-Commerce Clothing Reviews, contains approximately 23,000 entries and includes review texts along with demographic and product-related attributes. The research workflow consists of data cleaning, feature engineering, exploratory text analysis, and emotion detection using the DistilBERT-based emotion classifier. All analyses were performed using Python in the Google Colab environment. The results reveal that positive emotions, particularly joy and admiration, dominate customer feedback, indicating strong satisfaction with product fit and quality. Conversely, negative emotions such as anger and sadness appear more frequently in reviews mentioning sizing inconsistencies, fabric issues, or unmet expectations. The combination of sentiment context, emotional tone, and engineered features provides a more nuanced understanding of customer behavior compared to sentiment polarity alone. These findings highlight the potential of emotion-aware analytical approaches to support e-commerce businesses in improving product development, enhancing customer experience, and designing data-driven marketing strategies.
Operational Data Integration with Pureshare Dashboard for Unified Service Unit Rhamadani, Hana Silvanov; Utomo, Pradita Eko Prasetyo; Putri, Mutia Fadhila
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.v5i2.7412

Abstract

Public institutions in digital era increasingly require integrated data to support decision-making and performance monitoring. The development of the Electronic Unified Service Units (ULT-E) at the Jambi Language Office responds to this need by establishing a mechanism capable of consolidating operational data. The objective of this research is to design and develop a service dashboard using Pureshare as a guiding framework for identifying requirements, planning visual structures, and organizing information elements. The key performance indicators are presented as operational indicators across operational service data, including service requests, complaints, and public satisfaction. The development process includes requirement user, operational indicators, visual design, data integration through ETL procedures. The results show that the dashboards produced in this research present key performance indicators as operational indicators across three main areas, service requests, complaints, and public satisfaction surveys. The visual components consist of drill-down and time-range features for data exploration. The integration of these dashboards into the operational web interface indicates that the system is ready to support the institution’s digital service environment. The average System Usability Scale (SUS) score of 72.50 represents that users were able to follow the interaction flow and understand the visual components provided. The conclusion is that dashboard development can enhance service management efficiency, even when data conditions differ across modules, making operational information more accessible.
Dashboard-Based Tourism Data Visualization In Jambi Province Using The Seven Stages Of Visualizing Data Muhammad Nabil; Utomo, Pradita Eko Prasetyo; Bintana, Rizqa Raaiqa
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.v5i2.7420

Abstract

Tourism is a global and national priority sector that holds significant potential in Jambi Province, supported by its rich natural and cultural heritage. To support effective development strategies, the availability of accurate, accessible, and informative data is fundamental. Although the Jambi Open Data Website has presented a tourism dashboard, observations indicate that the visualizations are statistical in nature, lack comprehensiveness, and fail to present in-depth patterns or trends, thus limiting their utility as a decision-making tool. This study aims to address this gap by developing a more interactive, informative, and analytical tourism data visualization dashboard for Jambi Province using Tableau. The methodology used is The Seven Stages of Visualizing Data by Ben Fry (2008), which systematically combines data processing and visual design, including Acquire, Parse, Filter, Mine, Represent, Refine, and Interact. The result is the development of three functional dashboards: Tourist and Attraction, Hotel Accommodation, and Tourism Business, with functional validation using Black Box Testing. The main findings revealed by the dashboards are the presence of significant geographic regularities; Although Kerinci Regency recorded the highest number of attractions (135), Jambi City dominates in terms of tourist arrivals (4.258 million) and the concentration of hotel infrastructure (196 hotels) and tourism businesses (605 Creative Economy businesses). The Creative Economy sector is dominated by Culinary and Crafts. The conclusion of this study is that the application of the Seven Stages framework has proven effective in producing a valid and analytical system, providing clearer insights into the dynamics of Jambi tourism and supporting evidence-based policy formulation.
Implementation of Least Square Method to Predict Crime in Indonesia Based on the Web Cahyani, Nita; Irsyada, Rahmat; Anggi, Diva
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.v5i2.7424

Abstract

This study was initiated by the need to apply the Least Square method to project the number of crimes in Indonesia using historical data from 2018 to 2022. Crime is a crucial issue in maintaining public security and supporting law enforcement, so accurate prediction results can assist the government in formulating public policies and optimizing resource use. The main problem of this study is how to apply the Least Square method to predict various categories of crimes in Indonesia, such as crimes against life, physical violence, morality, individual freedom, property rights with or without violence, and narcotics crimes. The purpose of this study is to develop a prediction model that can provide an accurate picture of future crime trends. The Least Square method was chosen because it can minimize prediction errors and process data with diverse variations, resulting in more stable and reliable estimates. The data used covers various types of crimes within the study period, with accuracy checked through the Mean Absolute Percentage Error (MAPE) value. The results show that the Least Square method is able to produce highly precise predictions with a MAPE value of 1.21%, thus proving effective in predicting crime rates in Indonesia with a very low error rate.
Utilizing ResNet-50 for Deep Learning-Based Rice Leaf Disease Detection Sari, Risna; Asbudi, Hedy Leoni; Susilawati, Fitrah Eka
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.v5i2.7425

Abstract

Rice is a primary global food commodity, yet its productivity is frequently threatened by various diseases that significantly reduce both yield quality and quantity. Traditional manual diagnosis by farmers is often subjective, time-consuming, and prone to inaccuracies, necessitating more efficient automated solutions. This research evaluates the ResNet50 architecture for the automated classification of rice leaf diseases through digital image analysis. The study specifically investigates the model's performance on a specialized dataset and analyzes how different data splitting ratios influence accuracy and stability. A public dataset comprising four classes—Hispa, Healthy, Leaf Blast, and Brown Spot—was employed. The data underwent rigorous labeling, pre-processing, and augmentation to enhance sample diversity before being partitioned into training and testing sets using three ratios: 85:15, 80:20, and 90:10. The ResNet50 model was implemented using transfer learning with pre-trained ImageNet weights and fine-tuned on the classification layers. Experimental results reveal that the 85:15 split ratio achieved the highest accuracy of 81.48%, followed by 78.77% for the 80:20 ratio and 76.21% for the 90:10 ratio. These findings suggest that ResNet50 provides competitive performance for rice disease detection. Furthermore, achieving an optimal balance between training and testing data is critical for maximizing model generalization within modern smart farming applications.
Support Vector Regression-Based Prediction of Rice Production Across Provinces in Sumatra Island Sijabat, Elton Elyon; Khaira, Ulfa; Putri, Mutia Fadhila
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.v5i2.7429

Abstract

This study develops a Support Vector Regression (SVR)–based forecasting framework to model rice production across the ten provinces of Sumatra, a region whose agricultural output is highly sensitive to climate variability and land-use dynamics. Rising uncertainty in rainfall-dependent rice ecosystems underscores the need for more accurate predictive tools to support regional food-security planning. The objective of this research is to construct and evaluate a multivariate SVR model that integrates harvested area, rainfall, humidity, and temperature, while accounting for nonlinear temporal patterns and structural differences among provinces. The methodological approach includes extensive feature engineering, log-transformed SVR estimation with time-series cross-validation, a specialized year-over-year model for small and volatile provinces, and a stabilization procedure to ensure temporal consistency in the predictions. Results show that the blended–stabilized model performs strongly on the 2021–2024 test period, achieving SMAPE of 16.10%, MAE of 124,975.77, RMSE of 194,853.89, and R² of 0.9637, and generating three-year-ahead forecasts supported by bootstrap-based uncertainty intervals. These findings indicate that the proposed framework effectively captures heterogeneous production dynamics and provides reliable predictions for 2025–2027. The study concludes that SVR offers a robust and interpretable foundation for agricultural forecasting in data-limited environments, though future work should incorporate higher-frequency data, additional agronomic indicators, and hybrid machine-learning or deep-learning models to further improve long-term performance.
Design and Implementation of a Web-Based Personnel Information System (Sisfopers) At Kogartap II/Bandung Putri, Rahmi; Andika, Yusuf; Irawan, Debi; Hardiansyah, Hardiansyah; 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.v5i2.7436

Abstract

Personnel data management in the military is a crucial aspect in supporting the operational effectiveness of units. This study aims to design and implement a web-based Personnel Information System (Sisfopers) at Kogartap II/Bandung to make data management more efficient, secure, and integrated with the existing military IT infrastructure. The research method employed is developmental research (R&D) with a qualitative-descriptive approach, supplemented by data collection through literature review, observation, interviews, and documentation. The system is developed using the SDLC (Waterfall) model and UML to model functional requirements and process flows. The results indicate that the developed Sisfopers can accelerate administrative processes, maintain the security and integrity of personnel data, and support data-driven decision-making by the leadership. This study is expected to serve as a reference for the development of personnel information systems in other military environments
Development of an Intent-Classification Chatbot to Support Operational Services at Kadin Indonesia Aulia, Rahma; Purnama, Adi
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.v5i2.7438

Abstract

The digital transformation era demands business membership organizations such as the Indonesian Chamber of Commerce and Industry (Kadin) to provide responsive and scalable services. Operational inquiries related to the Certificate of Origin (COO), membership information (KTA), activity agendas, and administrative correspondence are still predominantly handled manually, resulting in service queues and limited operating hours. This study develops an intelligent text-based chatbot using Natural Language Processing (NLP) with an intent classification approach implemented through a Long Short-Term Memory (LSTM) model to automate initial responses to user queries. A labeled dataset consisting of more than 90 intents was constructed from Frequently Asked Questions (FAQ), Kadin service data, and data augmentation to increase text variation. The preprocessing pipeline includes normalization, tokenization, padding, and 300 dimensional FastText embeddings. The LSTM model, configured with 128 units, was trained using categorical cross-entropy with a label smoothing factor of 0.05, the Adam optimizer, a batch size of 20, and 80 epochs, and integrated into the backend for real-time inference. Evaluation on the test set achieved an accuracy of 92.08% and a Top-3 Accuracy of 96.23%. Visual analyses using the confusion matrix and accuracy–loss curves indicate strong generalization capability. These findings demonstrate that a properly configured LSTM model can effectively recognize service-related intents for Kadin.