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 Articles sent to the Brilliance may not be published elsewhere.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
 56   57   58   59   60 
Oil Palm Price Prediction Using Holt-Winters Exponential Smoothing at PT Ivo Mas Tunggal Christoper Jodi Aman Sinaga; Ari Purno Wahyu Wibowo
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.v6i2.8704

Abstract

Fluctuations in oil palm Fresh Fruit Bunches (FFB) prices over time have created challenges in planning and decision-making processes within plantation companies, including at Nenggala Plantation of PT Ivo Mas Tunggal. Price instability affects production planning, marketing strategies, and risk management, making accurate forecasting essential for supporting managerial decisions-maing. Therefore, this study aims to predict oil palm Fresh Fruit Bunches (FFB) prices using the Holt-Winters Exponential Smoothing method and compare the performance of additive and multiplicative models. This study applies a time series forecasting using historical oil palm FFB price data from January 2020 to September 2024. The research process includes data preprocessing, splitting the dataset into training and testing sets, and forecasting using additive and multiplicative Holt-Winters models. Model performance was evaluated using Mean Absolute Percentage Error (MAPE). The results showed that the additive Holt-Winters model achieved better forecasting accuracy than the multiplicative model, with a MAPE value of 10.08% compared to 11.98%. The forecasting results also indicated that the additive model was able to follow the historical trend and seasonal patterns of oil palm FFB prices effectively. The Holt-Winters Exponential Smoothing method with an additive approach is effective for predicting palm oil prices and can support production planning and managerial decision-making at the plantation level. Future studies are recommended to incorporate external variables and compare the Holt-Winters method with other forecasting approach to improve prediction performance.
GIS-Based Spatial Temporal Analysis And Priority Scoring For Malaria Control In Nabire Regency Gunawan Prayitno; Anggreini Wibowo Puspita Sari
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.v6i2.8775

Abstract

Malaria remains a critical public health challenge in Nabire Regency, Central Papua, where escalating incidence rates necessitate targeted control strategies. Currently, routine surveillance data are predominantly presented in tabular formats, inherently limiting their utility for spatially informed decision-making. Addressing this gap, this study analyzes the spatial-temporal dynamics of malaria transmission and develops a novel Malaria Spatial Priority Index (MSPI) a GIS-based multi-criteria priority scoring model to identify high-risk intervention zones. A quantitative descriptive-analytical framework was applied to surveillance data spanning 2018- 2025, integrating epidemiological indicators Annual Parasite Incidence (API), Annual Blood Examination Rate (ABER), and Slide Positivity Rate (SPR) with localized village and Puskesmas spatial parameters. The results reveal a severe intensification of the malaria burden in 2025, characterized by a 76.85% surge in positive cases (from 3,274 to 5,790) alongside synchronized increases in API and SPR. Spatial risk stratification using the MSPI identified Samabusa and Legari as very high-priority service areas, while Kalibobo, Wami Jaya, and Sanoba emerged as the primary transmission hotspots at the village level. Crucially, the spatial distribution demonstrated that administrative boundaries do not uniformly dictate disease risk. This study concludes that synthesizing routine epidemiological metrics with GIS-based spatial prioritization successfully transforms descriptive tabular data into operational spatial intelligence. This novel MSPI framework provides local health authorities with a robust, evidence-based decision-support tool to optimize resource allocation and dismantle localized transmission chains in highly endemic regions.
Sentiment Analysis of TikTok Comments on Free Nutritious Meals Using Naïve Bayes Muhamad Adyaputra Yostira; Ari Purno Wahyu Wibowo
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.v6i2.8854

Abstract

Public opinions on various issues, including government programs, are increasingly expressed through social media platforms. TikTok, as one of the most active social media platforms, allows users to share comments, criticism, and support regarding the Free Nutritious Meals Program. This study examines TikTok remarks about the Free Nutritious Meals Initiative and classifies them into sentiment categories using the Naïve Bayes algorithm. A total of 2,094 comments were obtained through a crawling process and then manually grouped into positive, negative, and neutral classes. The labeling process was conducted manually based on predefined sentiment guidelines and was reviewed to improve label consistency. Before being used in the classification stage, the comments were cleaned and standardized through several preprocessing steps, such as cleaning, case folding, tokenization, stopword removal, and stemming. After preprocessing, the text data were transformed into numerical representations using the Term Frequency–Inverse Document Frequency method, and the classification process was carried out with the Naïve Bayes algorithm. The results showed that neutral sentiment had the highest proportion at 45.9%, followed by negative sentiment at 33.9% and positive sentiment at 20.2%. The model achieved an accuracy of 73.75%, with precision of 68%, recall of 69%, and F1-score of 69%. These findings indicate that Naïve Bayes is able to classify TikTok user sentiment toward the Free Nutritious Meals Program with reasonably good performance, although informal language, ambiguous expressions, and sarcasm remain challenges in the classification process.
Indonesian Online News Topic Classification Using Naive Bayes and Support Vector Machine Winando Parbo Kusuma; Pradita Eko Prasetyo Utomo; Mutia Fadhila Putri
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.v6i3.8905

Abstract

Indonesian online news portals publish large volumes of articles every day, making manual topic grouping time-consuming, inconsistent, and difficult to maintain when articles contain overlapping contexts. Objective: This study develops and compares Naive Bayes and support vector machine models for Indonesian online news topic classification and identifies the model that can be used as the basis for an automatic newsroom support tool. Methods: A dataset of 1,631 Kompas.com articles was collected through web scraping from six channels: economy, automotive, technology, lifestyle, politics, and sport. The article body was used as input, while the source channel became the class label. The text was prepared through duplicate checking, text normalization, case folding, tokenizing, filtering with Indonesian and custom stopwords, and stemming with Sastrawi. The processed texts were transformed with TF-IDF using a maximum of 10,000 unigram and bigram features, min_df=2, and max_df=0.9. The data were split into 80% training data and 20% testing data with stratification. GridSearchCV with five-fold cross validation was applied to tune Multinomial Naive Bayes and support vector machine parameters. Results: Naive Bayes achieved 97.25% testing accuracy, while support vector machine with a linear kernel, C=10, and gamma=scale achieved 98.17%. SVM also produced higher macro precision, recall, and F1-score. Remaining errors mainly appeared in technology articles because their vocabulary overlapped with lifestyle, automotive, and politics topics. Conclusion: TF-IDF with linear SVM effectively classifies Indonesian online news topics and supports automated content organization workflows.
Principal Component Optimization for Random Forest-Based Classification of Palm Oil Leaf Disease Images Oky Rahmanto; Veri Julianto; Ahmad Rusadi Arrahimi
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.v6i3.7552

Abstract

Principal Component Analysis (PCA) is a widely used dimensionality reduction technique for mitigating high-dimensional feature spaces, while Random Forest is a robust ensemble classifier that can naturally handle many input variables. However, the effect of the number of PCA components on the predictive performance and generalization ability of Random Forest models is still not well quantified, especially in terms of its trade-off between information preservation and noise reduction. This study investigates how varying the number of PCA components from 2 to 10 influences the performance of a Random Forest classifier on a multiclass dataset. The experimental design employs k-fold cross-validation and multiple values of the number of trees (n_estimators), and evaluates models using Accuracy, Precision, Recall, F1-score, and training time. The results exhibit an inverted U-shaped relationship, where 6–7 PCA components yield the highest and most stable performance, with average Accuracy around 0.96 and F1-score around 0.97, while very low (2–3) and high (?8) numbers of components lead to underfitting and structural overfitting, respectively. These findings suggest that PCA-based dimensionality reduction should be tuned with respect to discriminative performance rather than solely maximizing explained variance, and that a moderate number of components can best exploit the synergy between PCA and Random Forest.
Early Detection of Chili Leaf Diseases Using Convolutional Neural Network Based on Leaf Images Alam Bahari; Fadlisyah Fadlisyah; Hafizh Al Kautsar Aidilof
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.v6i3.8627

Abstract

Chili plants (Capsicum sp.) are one of the important horticultural commodities in Indonesia with high economic value. However, chili productivity is often reduced due to leaf diseases such as leaf curl, yellow leaf virus, and leaf spot disease. Manual disease identification conducted by farmers still has several limitations because it requires considerable time, experience, and is prone to observation errors. Therefore, an automatic system is needed to support early detection of chili leaf diseases quickly and accurately. This study aims to develop a chili leaf disease classification system using a Convolutional Neural Network (CNN) based on leaf images. The dataset used in this study consists of chili leaf images categorized into four classes, namely healthy leaves, leaf curl, yellow leaf, and leaf spot. The research stages include dataset collection, image preprocessing, data augmentation, CNN model training, and model evaluation using a confusion matrix with performance metrics including accuracy, precision, recall, and F1-score. The results show that the CNN model is capable of classifying chili leaf diseases with satisfactory performance. Based on the evaluation results, the model achieved a precision value of 0.75, a recall value of 0.53, and a mean Average Precision (mAP@0.5) value of 0.60. The developed system is also able to display classification results along with the confidence score of the prediction. Therefore, the CNN method has strong potential to be implemented as an image-based early detection system for chili leaf diseases to assist farmers in monitoring plant conditions more effectively.
Analysis Of Consumer Satisfaction Of Smartphone Repair Services At Samsung Service Center Using SAW Fahmi Fatdhlurrahman Manurung; Dewi Anggraeni; Rohminatin Rohminatin
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.v6i3.8760

Abstract

This study aims to develop a decision support system to evaluate customer satisfaction levels using the Simple Additive Weighting (SAW) method. The background of this research is based on the need for an objective and structured approach in assessing customer satisfaction in service environments, where manual evaluation is often subjective and inefficient. The problem addressed in this study is the difficulty in measuring customer satisfaction accurately and consistently based on multiple criteria. The objective of this research is to implement the SAW method in a computerized system to improve the accuracy and efficiency of customer satisfaction evaluation. The research method involves data collection through observation and documentation, followed by system development and implementation of the SAW method. Several criteria are used in the evaluation process, including service attitude, repair speed, communication, facilities, and service cost, each assigned with specific weights. The results show that the system is able to calculate customer satisfaction scores effectively and rank customers based on predefined criteria. The implementation of the SAW method provides more objective and consistent evaluation results compared to manual assessment. The conclusion indicates that the developed system can assist administrators in making better decisions related to service quality improvement and customer satisfaction management.
Design and Performance Analysis of GPON-Based FTTH Network in Sikucur Barat Padang Pariaman Regency Uzma Septima; Rikki Vitria; Ratna Dewi; Ramiati Ramiati; Yola Febrilla
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.v6i3.8877

Abstract

The increasing demand for internet services requires broadband infrastructure capable of providing high-capacity and reliable connectivity, including in rural areas. Nagari Sikucur Barat, Padang Pariaman Regency, requires an optical access network to support the growing communication needs of the community. This study aims to design and evaluate the performance of a Fiber To The Home (FTTH) network based on Gigabit Passive Optical Network (GPON) technology. The research applies the Prepare, Plan, Design, Implement, Operate, and Optimize (PPDIOO) methodology through geographical analysis, network planning using Google Earth Pro and AutoCAD, OptiSystem simulation, and performance evaluation based on Link Power Budget, Rise Time Budget, Q-Factor, and Bit Error Rate (BER). The proposed network serves 88 homepasses using 3 PON ports, 13 Optical Distribution Points (ODPs), 4 PLC 1:4 splitters, and 13 distribution splitters. The calculated attenuation ranges from 27.0523 dB to 27.2632 dB, with received power values between ?20.0523 dBm and ?20.2632 dBm and power margins ranging from 7.7368 dB to 7.9477 dB. Simulation results produce Q-Factor values of 12.1746 to 13.7883 and BER values of 1.49433 × 10??³ to 6.58298 × 10?³?, indicating compliance with GPON transmission quality requirements. The Rise Time Budget ranges from 0.3637 ns to 0.3712 ns, exceeding the theoretical limit of 0.29 ns. The results indicate that the proposed network is feasible for deployment because it satisfies the received power, power margin, Q-Factor, and BER requirements, while further optimization is needed to improve rise time performance.
Design and Implementation FTTH GPON Network Design Based on Attenuation Measurement and Optisystem Modeling Aprinal Adila Asril; Popy Maria; Ummul Khair; Silfia Rifka; Sri Nita
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.v6i3.8946

Abstract

This study aims to design and implement a Fiber to the Home (FTTH) network based on Gigabit Passive Optical Network (GPON) technology using attenuation measurement as an approach to detect physical disturbances in optical fiber through modeling with Optisystem software. The research activities were conducted in a laboratory through several stages, including network topology design, system simulation using Optisystem, implementation of an FTTH trainer module, and attenuation measurement using an Optical Power Meter (OPM). Testing was carried out under various cable conditions, namely normal conditions, bending, damaged core, and variations in dropcore cable length to analyze their effects on attenuation values. The results showed that the attenuation values under normal conditions ranged from 14.94 to 16.23 dB, while under physical disturbance conditions such as bending and core damage, there was a significant increase in attenuation. The addition of cable length also contributed to an increase in attenuation of approximately 0.9 dB for every 5 meters. The Optisystem simulation results were consistent with the link power budget calculations and actual measurements, with a difference of approximately 0.1 dB. Furthermore, cable conditions with severe damage such as a broken core showed attenuation values exceeding 50 dB, which can be used as an indicator of physical disturbances. Overall, this study successfully demonstrates that the attenuation measurement method combined with Optisystem modeling is effective in detecting physical disturbances in FTTH GPON networks. The developed trainer module can also be used as a learning medium to understand attenuation characteristics and the performance of optical fiber networks in a laboratory environment.
Public Sentiment Analysis on Ethanol-Blended Fuel News Using Support Vector Machine and Naïve Bayes Muhammad Khadafi; Riza Pahlevi; Eni Rohaini
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.v6i3.9007

Abstract

The increasing discourse surrounding ethanol-blended fuel policy in Indonesia has generated substantial public opinion across digital media platforms. Understanding this public sentiment is essential for policymakers and stakeholders in formulating effective communication strategies and evidence-based policy decisions. This study aims to (1) implement Support Vector Machine (SVM) and Naïve Bayes algorithms for classifying public sentiment toward ethanol-blended fuel news and (2) compare the performance of both algorithms using accuracy, precision, recall, and F1-score metrics. A total of 1,492 YouTube comments were collected through web scraping and preprocessed using case folding, tokenization, normalization, and stemming. Features were extracted using Term Frequency–Inverse Document Frequency (TF-IDF), and sentiments were classified into positive, negative, and neutral categories. Model performance was evaluated using a confusion matrix and the aforementioned metrics. Results show that SVM achieved a higher test accuracy of 73% and mean cross-validation accuracy of 72.05%, while Naïve Bayes obtained 61% and 64.94%, respectively. SVM also demonstrated superior weighted precision on the test set (0.72 vs. 0.65), whereas Naïve Bayes achieved higher macro recall (0.50 vs. 0.37) and macro F1-score (0.47 vs. 0.35). Cross-validation results showed a similar pattern. A Paired T-Test confirmed statistically significant differences between the models across all evaluation metrics (accuracy p=0.00016, precision p=0.039, recall p<0.001, F1-score p<0.001). This study contributes to Indonesian-language sentiment analysis in the renewable energy policy domain and provides insights into public perception of the national ethanol fuel blending program.

Page 58 of 60 | Total Record : 594

 56   57   58   59   60 

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