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 Articles sent to the Brilliance may not be published elsewhere.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
Implementation of Monitoring and Cooling System to Improve Solar Power Plant Efficiency Based IoT Teuku Multazam; Andik Bintoro; Ilham Sahputra; Imam Syahputra Nasution; Dimas Ananda Putra
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.v6i4.9809

Abstract

Solar power plants are one of the renewable energy solutions with great potential for development in tropical regions. The efficiency of solar panels decreases as surface temperature of modules increases, resulting in suboptimal performance of the solar power plant and affecting amount of electricity generated. The study aims to design a real-time, automated Internet of Things based solar panel monitoring and cooling system to maintain a constant level of electrical energy. The system measures panel temperature, light intensity, voltage, current, input power, output power, efficiency, and the status of cooling pump; the data is then analyzed across five tests based on average value of each parameter. The data is used as a reference to control the cooling system’s operation if temperature parameter reaches maximum limit of 38°C. The results show that panel temperatures recorded by the system ranged from approximately 31°C to 38.64 °C, with a maximum light intensity of 24,040 lux. The first test recorded highest average temperature 38.64 °C an average light intensity of 7,363 lux and an average output power of 6.64 W. Under these conditions, cooling system operated optimally and achieved an average efficiency of 77.18%. In the second through fifth tests, panel temperature decreased, with an average value ranging from 34.59 °C to 31.97 °C, and light intensity was approximately 700–900 lux, indicating that the cooling system was operating normally. These conditions affected average efficiency, with the highest average value recorded in second test at 82.64% and lowest in the fourth test at 69.56%.
Analyzing Chatbot Interaction Patterns and Customer Satisfaction Classification Using Text Data Dhafin Rizky Trisandy; Rizka Dhini Kurnia; Purwita Sari; Ari Wedhasmara; Apriansyah Putra
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.v6i4.9810

Abstract

This study aims to identify recurring customer interaction patterns in the chatbot service of CV Mawar and independently evaluate text-based customer satisfaction classification using the Flipkart customer support dataset. The primary dataset consisted of 137 chatbot interaction sessions from CV Mawar. After removing 10 sessions with empty transcripts, 127 sessions were manually coded and analyzed descriptively. Because reliable customer satisfaction labels were limited, a separate Flipkart dataset containing customer remarks and Customer Satisfaction (CSAT) scores was used for machine learning. Text classification was performed using Term Frequency–Inverse Document Frequency (TF-IDF) and a linear Support Vector Machine (SVM). The model was evaluated using accuracy, balanced accuracy, precision, recall, F1-score, and a confusion matrix. Delivery estimates and product information or usage were the most frequent categories in CV Mawar, each representing 19.69% of the coded sessions. Only three usable sessions contained genuine service ratings, all rated “Good,” while no usable written feedback was available. The Flipkart classification model achieved 79.62% accuracy, 81.92% balanced accuracy, and a macro F1-score of 78.31%, outperforming the majority-class baseline accuracy of 68.74%. The findings highlight common customer information needs in chatbot interactions and demonstrate the potential of text classification for analyzing customer feedback. However, the limited satisfaction ratings at CV Mawar and the use of an independent Flipkart dataset restrict conclusions about satisfaction among CV Mawar customers.
Spatio-Temporal Pattern Analysis of White Root Rot Disease in Rubber Plantations Using ST-DBSCAN Ela Roza Batubara; Sumarno Sumarno; Fazli Nugraha Tambunan
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.v6i4.9851

Abstract

Plant diseases pose a severe threat to the economic sustainability of rubber plantations (Hevea brasiliensis), requiring advanced analytical models for effective management. Traditional monitoring often relies on uniform, reactive treatments that fail to capture spatial-temporal dynamics. This study aims to identify spatio-temporal distribution patterns and evaluate disease risk levels of White Root Rot (Rigidoporus microporus) at the PT. Bridgestone Sumatera plantation using longitudinal observation data from 2021 to 2025. To achieve this, the research implements the Spatio-Temporal DBSCAN (ST-DBSCAN) algorithm, integrating geographical coordinates, temporal duration, and attribute severity to cluster infection incidents. The experimental results successfully identified three distinct disease hotspots with an exceptional spatial validation performance, yielding a high Silhouette Score of 0.846. Based on calibrated temporal and severity thresholds, all identified clusters were classified as High-Risk Persistent zones, remaining active across the entire observation period with average severity scores exceeding 2.0. In conclusion, the proposed ST-DBSCAN framework successfully fulfills research expectations by providing a robust, data-driven decision-support tool. Practically, these findings enable estate managers to prioritize targeted, proactive interventions - such as intensive soil treatment and structural root isolation - rather than applying uniform fungicide treatments. Future research should integrate environmental variables and conduct parameter sensitivity analyses to capture smaller, emerging outbreak patterns.
Evaluating Informatics Engineering Learning Outcomes Using Weighted Rubrics to Compare Teacher and LLM Scores Nurhadi surojudin; Antika Zahrotul Kamalia; Sufajar Butsianto; Refania Meilani Firdos; Bagus Tri Ardiawan
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.v6i4.9858

Abstract

The increasing use of large language models (LLMs) in educational assessment highlights the need to examine scoring consistency between automated and teacher evaluations. This study analyzes assessment-score consistency and compares teacher and LLM evaluations using a weighted-rubric approach. A descriptive-analytical method was applied to the HARMOGEN-R dataset. First, 32,805 evaluation records were examined to assess consistency between recorded total scores and aggregated criterion scores. Second, 345 paired teacher–LLM responses were analyzed across five criteria using equal weights of 0.20. Evaluation metrics included mean absolute error (MAE), root mean squared error (RMSE), mean score difference, Pearson correlation, and Spearman rank correlation. The results showed that 32,618 evaluations (99.43%) had matching recorded totals and summed criterion scores. In the paired analysis, the mean teacher score was 52.583, compared with 49.996 for LLM scores. The MAE was 4.168, the RMSE was 9.328, and the mean difference (LLM minus teacher) was ?2.587. Pearson and Spearman correlations were 0.9781 and 0.9863, respectively (both p < 0.001). Despite these strong positive associations, score differences indicate that correlation does not necessarily establish agreement or interchangeability. The weighted-rubric approach provides a transparent method for score aggregation and identifying assessment discrepancies. However, equal weights were used as a baseline, and the criteria were not validated against official Course Learning Outcomes (CLOs) or Program Learning Outcomes (PLOs). Future research should investigate alternative weighting schemes, validate learning-outcome mapping, and assess score agreement across broader educational contexts.
Integrating Sentinel-2 NDVI and Web GIS for Rice Vegetation Monitoring Beny Riswanto; Kusnana Kusnana; Nursetianti Nursetianti; Agus Sudarmanto; Syaiful Akbar Rizy Mubarok
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.v6i4.9878

Abstract

Monitoring rice vegetation across agricultural plots requires accessible spatial information. Satellite-derived vegetation indices provide periodic observations, while Web Geographic Information Systems (Web GIS) present spatial data through interactive maps. This study develops a Web GIS integrating Sentinel-2-derived Normalized Difference Vegetation Index (NDVI) data to support rice vegetation monitoring in Negarajati Village, Cimanggu District, Cilacap Regency, Indonesia. The study used processed monthly NDVI values from ten sampling locations (P1–P10) covering May–September 2026. Descriptive statistics were calculated to summarise monthly NDVI values and their variation. The Web GIS was developed using Laravel, PostgreSQL with PostGIS for spatial data management, and LeafletJS for map visualisation. The application was deployed in a web-hosting environment to provide browser-based access. The monthly mean NDVI values were 0.159538 in May, 0.270014 in June, 0.491593 in July, 0.621865 in August, and 0.571092 in September. The mean increased from May to August before declining in September. The Web GIS presents monthly NDVI information and sampling-point attributes through an interactive map, enabling users to explore the processed spatial dataset. The developed Web GIS provides an integrated platform for presenting Sentinel-2-derived NDVI information for village-scale rice vegetation monitoring. The monthly values describe variation in the processed dataset but do not independently confirm crop growth stages or field health. Further work should document image-processing procedures and include field validation to strengthen interpretation.
Analysis and Prediction of MyTelkomsel Complaints Using IndoBERTweet and TimesFM-3 for Service Improvement Prioritization Muhammad Syaikh Azka; Apriansyah Putra; Rahmat Izwan Heroza; Ken Ditha Tania
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.v6i4.9879

Abstract

Application reviews contain useful feedback, but the growing volume of Indonesian-language reviews makes manual identification of complaints inefficient, and earlier MyTelkomsel studies stopped at sentiment classification. Objective: This study develops an integrated framework to identify the dominant technical complaints in MyTelkomsel reviews, forecast their trends, and prioritize service improvements. Methods: A total of 51,112 application-related Google Play reviews, published between November 2022 and September 2026, were kept after keyword-based relevance filtering. IndoBERTweet, fine-tuned on the SmSA dataset, performed sentiment analysis, and 44,937 negative reviews were grouped by BERTopic with K-Means into ten complaint categories. TimesFM-3 then produced zero-shot six-month complaint forecasting for each category, which was evaluated with a rolling-origin backtest and used to compute a priority score from forecast load and trend. Results: Login & Account Access, Loading/Performance Issues, and General Bugs/Errors accounted for 55.4% of the negative reviews. After two surge months were excluded, TimesFM-3 reached a weighted absolute percentage error of 54.65% and an 80% interval coverage of 84.42%. Loading/Performance Issues was the only high-priority category (score 74.5), and four categories were medium priority. Problems After Updates was the only medium-priority category with an increasing trend. Conclusion: The framework supports ranking and monitoring of complaint categories. Its moderate accuracy and wide intervals mean that the forecasts should guide priorities rather than predict exact monthly volumes.
Implementation of a NEWS 2-Based Early Warning System for Multiparameter Vital Sign Monitoring Yultrisna Yultrisna; Aditya Wardhani; Muhammad Al Ghazali
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.v6i4.9884

Abstract

Integrated vital-sign monitoring can support earlier recognition of physiological deterioration when measurements are converted into a consistent track-and-trigger score. This study designed and implemented an Internet of Things (IoT)-based multiparameter monitoring prototype that calculates the National Early Warning Score 2 (NEWS2). A MAX30102 measured peripheral oxygen saturation (SpO?), two MLX90614 sensors measured body temperature and respiratory rate, and an OMRON HEM-7156T supplied systolic/diastolic blood pressure and pulse rate to an ESP32 through Bluetooth Low Energy. The ESP32 transmitted data over Wi-Fi and MQTT to a Node.js backend, PostgreSQL/TimescaleDB storage, and a React dashboard; NEWS2 results were returned to a 20×4 LCD, LEDs, and a buzzer. Thirty paired measurements were used for sensor comparison, while the complete system was evaluated on 31 participants aged 20–81 years. The mean absolute differences were 0.26 percentage points for SpO?, 0.07 °C for temperature, and 0.40 breaths/min for respiratory rate. Corresponding MAPE values were 0.26%, 0.19%, and 2.58%. The 31-participant dataset produced mean values of 14.77 breaths/min, 97.99% SpO?, 84.77 bpm, 37.36 °C, and 121.65 mmHg systolic pressure. Total NEWS2 scores ranged from 0 to 4, and all participants were categorized as low risk without a single red score. Simulated scores of 6 and 9 verified medium-risk, high-risk, and single-red-score alert branches. The prototype demonstrated end-to-end technical feasibility, but the reported agreement and risk outputs are not a clinical validation and require calibrated references, repeated measurements, broader cohorts, and formal clinical evaluation

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