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 Articles sent to the Brilliance may not be published elsewhere.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 544 Documents
 19   20   21   22   23 
Effect of Connection Losses on Fiber To The Building (FTTB) Network Activation Nasrul, Nasrul; Maria, Popy; Zahra, Nurraudya Tuz; Gusmiati, Yosi
Brilliance: Research of Artificial Intelligence Vol. 4 No. 2 (2024): Brilliance: Research of Artificial Intelligence, Article Research November 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i2.4622

Abstract

The Fiber To The Building (FTTB) technology uses fiber optic cables for high-speed data transmission in high-rise office buildings. However, connection loss in fiber optic cables, especially during network activation, can significantly affect the overall performance and reliability of the FTTB network. This study investigates the effects of connection loss on total attenuation in FTTB networks before and after activation, using Passive Optical Network (PON) technology. Simulations were performed on three subscriber scenarios with different treatments of drop core cables (no connection, one connection, two connections) and patch cord cables of different lengths (3m, 5m, 10m), each with additional variations in the number of connections. Attenuation measurements were taken before and after network activation, showing that increasing cable length and splices leads to higher attenuation and reduced network performance. For example, customer 1 with no connections had the lowest attenuation before activation of 19.68 dB and after activation of 19.57 dB with signal quality (ping ONU 11 ms, ping OLT 9 ms, and ping Google 31 ms) while customer 3 with the most connections had attenuation values before activation of 20.92 dB and after activation of 20.87 dB with signal quality (ping ONU 29 ms, ping OLT 28 ms, and ping Google 70 ms). This research emphasises the importance of link management and the length of cable used to minimize attenuation and ensure optimal network performance.
A Comparative Analysis of Machine Learning Models for Predicting Student Performance: Evaluating the Impact of Stacking and Traditional Methods Airlangga, Gregorius
Brilliance: Research of Artificial Intelligence Vol. 4 No. 2 (2024): Brilliance: Research of Artificial Intelligence, Article Research November 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i2.4669

Abstract

This study investigates the application of machine learning models to predict student performance using socio-economic, demographic, and academic factors. Various models were developed and evaluated, including Linear Regression, Random Forest, Gradient Boosting, XGBoost, LightGBM, Support Vector Regressor, and a Stacking Regressor. The models were assessed using key evaluation metrics: Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), R-squared (????2), Mean Squared Log Error (MSLE), and Mean Absolute Percentage Error (MAPE). The Support Vector Regressor demonstrated the best overall performance, with an MAE of 4.3091, RMSE of 5.4110, and an ????2 of 0.8685, surpassing even the more complex ensemble models. Similarly, Linear Regression achieved strong results, with an MAE of 4.3154 and ????2 of 0.8685. In contrast, the Stacking Regressor, while effective, did not significantly outperform its base models, achieving an MAE of 4.5340 and ????2 of 0.8563, highlighting that greater model complexity does not necessarily lead to better predictive power. The analysis also revealed that MAPE was highly sensitive to outliers in the dataset, indicating the need for robust data preprocessing to handle extreme values. These results suggest that, in educational data mining, simpler models can often match or exceed the performance of more complex methods. Future research should investigate advanced ensembling strategies and feature engineering techniques to further enhance the accuracy and reliability of student performance predictions.
Spam Detection on YouTube Comments Using Advanced Machine Learning Models: A Comparative Study Airlangga, Gregorius
Brilliance: Research of Artificial Intelligence Vol. 4 No. 2 (2024): Brilliance: Research of Artificial Intelligence, Article Research November 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i2.4670

Abstract

The exponential growth of user-generated content on platforms like YouTube has led to an increase in spam comments, which negatively affect the user experience and content moderation efforts. This research presents a comprehensive comparative study of various machine learning models for detecting spam comments on YouTube. The study evaluates a range of traditional and ensemble models, including Linear Support Vector Classifier (LinearSVC), RandomForest, LightGBM, XGBoost, and a VotingClassifier, with the goal of identifying the most effective approach for automated spam detection. The dataset consists of labeled YouTube comments, and text preprocessing was performed using Term Frequency-Inverse Document Frequency (TF-IDF) vectorization. Each model was trained and evaluated using a stratified 10-fold cross-validation to ensure robustness and generalizability. LinearSVC outperformed all other models, achieving an accuracy of 95.33% and an F1-score of 95.32%. The model demonstrated superior precision (95.46%) and recall (95.33%), making it highly effective in distinguishing between spam and legitimate comments. The results highlight the potential of LinearSVC for real-time spam detection systems, offering a reliable balance between accuracy and computational efficiency. Furthermore, the study suggests that while ensemble models like RandomForest and VotingClassifier performed well, they did not surpass the simpler LinearSVC model in this context. Future work will explore the incorporation of deep learning techniques, such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), to capture more complex patterns and further enhance spam detection accuracy on social media platforms like YouTube.
Effect of Coiling and Macrobending on Fiber To The Building (FTTB) Network Activation Yustini, Yustini; Nasrul, Nasrul; Asril, Aprinal Adila; Nugraha, Bintang Aulia
Brilliance: Research of Artificial Intelligence Vol. 4 No. 2 (2024): Brilliance: Research of Artificial Intelligence, Article Research November 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i2.4674

Abstract

Fiber to the Building (FTTB) provides a fast and efficient service. However, the network quality may be affected by high attenuation at the termination (ONU) due to coiling, macrobending, and the length of patch cords, impacting network stability. This study aims to measure and analyze the effect of coiling and macrobending on patch cord cables of different lengths, as well as their influence on attenuation and FTTB network performance. The method includes simulating patch cord cables with lengths of 3m, 5m, and 10m. The tested treatments include conditions without coil, with coil, macrobending without coil, and macrobending with coil applied to the final termination before and after activating the FTTB network. Before activation, the lowest attenuation was 19.78 dB in the 3m cable without coil and macrobending, while the highest attenuation was 21.93 dB in the 10m cable with 5 coils (6cm curvature) and macrobending (0.8cm diameter). After activation, the lowest attenuation was 19.74 dB in the 3m cable without coil and macrobending, while the highest attenuation was 23.92 dB in the 10m cable with 5 coils (6cm curvature) and macrobending (0.8cm diameter). The test results show that the attenuation is affected by the number of coils, macrobending, and cable length.Damping increases with an increase in coils, cable length, and macrobending.
Course Learning Recommendation System Using Neural Collaborative Filtering Mulyana, Hadist Laroibafi; Rumaisa, Fitrah
Brilliance: Research of Artificial Intelligence Vol. 4 No. 2 (2024): Brilliance: Research of Artificial Intelligence, Article Research November 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i2.4699

Abstract

The proliferation of e-learning platforms has created a need for sophisticated course recommendation systems. This paper presents an innovative online course recommendation system using Neural Collaborative Filtering (NCF), a deep learning technique designed to surpass traditional methods in accuracy and personalization. Our system employs a hybrid NCF architecture, integrating matrix factorization with multi-layer perceptron to capture complex user-course interactions. The proposed NCF-based recommendation system aims to address key challenges in the e-learning domain, such as diverse user preferences, varying course content, and evolving learning patterns. By leveraging the power of neural networks, our approach seeks to provide more relevant and personalized course suggestions to learners. Our research contributes to the intersection of deep learning and educational technology, offering new insights into how advanced machine learning techniques can be applied to improve online learning experiences. The proposed system has the potential to enhance the quality of course recommendations, leading to more effective learning pathways for users. This work has important implications for e-learning platforms, educational institutions, and lifelong learners navigating the vast landscape of online courses. By improving the match between learners and courses, we aim to increase engagement, completion rates, and overall satisfaction in online education. Future work will explore the long-term impact of such personalized recommendations on learning outcomes and skill development.
Development Of A Web-Based E-Presence Application For Tracking Maps And Selfies Using Laravel Suherman, Asep; Ibrahim, Rohmat Nur; Seftiansyah, Rifan; Idzharulhaq, Zaidan
Brilliance: Research of Artificial Intelligence Vol. 4 No. 2 (2024): Brilliance: Research of Artificial Intelligence, Article Research November 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i2.4723

Abstract

Attendance is an activity aimed at assessing the level of employee presence and discipline within an organization or company. The E-Presence application is developed as a tool to enhance efficiency, accountability, and transparency in employee attendance, as well as to facilitate the processing of attendance data The E-Presence application aims to reduce errors and improve the accuracy of employee attendance records, which are crucial for the decision-making process. The development of the E-Presence application uses the Laravel framework, MySQL database, and UML (Unified Modeling Language) tools to design Use Case Diagrams, Activity Diagrams, and Class Diagrams. The system development method follows the waterfall model, and Black Box Testing is employed as the testing method. The urgency of this research lies in the system's ability to perform real-time attendance tracking that can be conducted outside the office within a maximum distance of 20 meters. With the implementation of tracking maps, employees do not need to queue, thereby increasing work efficiency. Attendance recording can be done in real time, is flexible, easily accessible, improves efficiency in attendance recording, reduces the potential for errors, enhances human resource management, and provides attendance reports in Excel format. The novelty of this research is the development of a web-based application that incorporates Tracking Maps and Selfie features, ensuring that employees must be in a designated area to check in. Thus, the company/organization can easily analyze and evaluate employee discipline. The testing results indicate that the application functions well and meets user needs.
Title Prototype of a Mobile-Based Interactive Application for Tourist Search in Nabire Prayitno, Gunawan; Bouk, Gatrida
Brilliance: Research of Artificial Intelligence Vol. 4 No. 2 (2024): Brilliance: Research of Artificial Intelligence, Article Research November 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i2.4734

Abstract

The Nabire area in Papua Indonesia has rich natural tourism potential, including attractive lakes and beaches. However, the low interest of tourists in visiting is caused by a lack of information and promotion about this tourist destination. The lack of efforts to disseminate information and promotions has resulted in low numbers of tourist visits, both domestic and international. This research aims to overcome this problem through the development of an interactive mobile application designed to facilitate access to comprehensive and up-to-date tourist information in Nabire. This research methodology uses a Design Thinking approach which consists of five stages: empathy, determination, ideation, prototype, and test. At the empathy stage, observations and interviews were carried out to understand user needs, which revealed that easily accessible and complete tourism information was still very much needed. The determination stage concluded that the main problem was the lack of accessibility of integrated and up-to-date tourism information. The ideation stage produced several potential solutions, including creating an application that provides complete information about tourist attractions, ticket prices, locations, images and videos. In the prototype stage, the application is designed using Figma to showcase important features and produce an initial model that can be tested. The prototype results include a main page, a short tourist description, a photo gallery, and a tourist video. The testing phase is carried out using the black box method to ensure the application functions operate as expected. Test results show that the application can display dashboard pages, short tourist descriptions, photo galleries and videos well.
Application of Ant Colony Optimization Algorithm in Determining PID Parameters in AC Motor Control Rahman, Farhan Wahyu Nur; Setiawan, Edy; Juniani, Anda Iviana; Nugraha, Anggara Trisna
Brilliance: Research of Artificial Intelligence Vol. 4 No. 2 (2024): Brilliance: Research of Artificial Intelligence, Article Research November 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i2.4741

Abstract

Application of Ant Colony Optimization (ACO) Algorithm in determining PID (Proportional-Integral-Derivative) parameters to optimize AC motor control through simulation using MATLAB. AC motors are a critical component in a wide range of industrial applications requiring efficient control to ensure optimal stability and response. This research focuses on optimizing the motor's RPM control by fine-tuning PID parameters using the ACO algorithm. Precise RPM control is crucial for maintaining performance in dynamic industrial environments. The ACO algorithm is used to optimize the PID parameter by referring to the objective function of Integral Time Absolute Error (ITAE). The optimization results show that this algorithm can achieve optimal convergence in the 33rd iteration with a fitness value of 6269. The optimal PID parameters obtained were Kp of 164.98, Ki of 23.47, and Kd of 10.51. The simulation of the AC motor control system shows a significant improvement in performance compared to the Trial-and-Error method. The simulation results demonstrate that ACO reduces steady-state errors by up to 9%, while Trial-and-Error reaches 25%. The settling time is also faster with ACO, which is 0.7 seconds, compared to the Trial-and-Error method which takes longer. The use of the ACO method in PID tuning has been proven to be more efficient and accurate than conventional approaches, thus improving the RPM stability and response of the AC motor control system. This study concludes that the integration between ACO and PID can be the optimal solution in automated control applications in industries that require responsive and stable motor RPM control.
Cyber Pandemic – The New Cybersecurity Risks Sukenda, Sukenda; Zulpratita, Ulil Surtia; Muttaqin, Helmy Faisal; Wahyu, Ari Purno; Yustim, Benny
Brilliance: Research of Artificial Intelligence Vol. 4 No. 2 (2024): Brilliance: Research of Artificial Intelligence, Article Research November 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i2.4759

Abstract

We are amidst a digital pandemic. In 2020, COVID-19 sped up a change towards remote working and the product being utilized for these assaults has become more straightforward to execute, ransom ware assaults have risen quickly and keep on speeding up in 2021. The COVID-19 pandemic has changed both the actual world and the computerized space, where organizations and associations are being gone up against with overwhelming online protection challenges for which not many were prepared or prepared to confront. Attributable to the extreme change in working conditions, cyber attacks and information extortion presently rank third among the best worries of business pioneers, as detailed in the World Economic Forum's COVID-19 Risks Outlook. The likelihood of malignant digital movement is considerably more upsetting thinking about that 53% of organizations have never pressure tried their systems. The key focus point from these and a large group of other alarming probabilities is that readiness for any kind of digital emergency whatsoever levels of an association is critical. Top administration, network protection trained professionals and each representative should know how to treat an emergency hit. Cyber security centers around securing information, yet it is presently not adequate; organizations need cyber resilience.
Evaluating Random Forest Algorithm: Detection of Palm Oil Leaf Disease Rahmanto, Oky; Julianto, Veri; Arrahimi, Ahmad Rusadi
Brilliance: Research of Artificial Intelligence Vol. 4 No. 2 (2024): Brilliance: Research of Artificial Intelligence, Article Research November 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i2.4798

Abstract

This research investigates the application of machine learning techniques for detecting diseases in oil palm leaves, utilizing a dataset of 1,119 images sourced from plantations in the Tanah Laut district. The dataset comprises 488 diseased and 631 healthy leaf samples, which were carefully cropped to isolate leaf areas and labeled with the assistance of domain experts. For feature extraction, both Lab and RGB color spaces were considered, alongside Haralick texture features, resulting in a total of eleven features per pixel. To reduce dimensionality and select relevant features, Principal Component Analysis (PCA) and Random Forest methods were applied. Support Vector Machine (SVM) was subsequently employed for the classification of leaf health status, and model performance was evaluated using accuracy, precision, recall, and F1 score metrics, all derived from a confusion matrix. The study finds that PCA and Random Forest significantly enhance model performance, improving the ability to distinguish between healthy and diseased leaves. These findings provide valuable insights for the development of automated disease detection systems in oil palm plantations, with potential applications in precision agriculture. Additionally, the results suggest pathways for further research into plant disease diagnostics, highlighting the role of advanced machine learning techniques in enhancing crop management and supporting sustainable agricultural practices.

Page 21 of 55 | Total Record : 544

 19   20   21   22   23 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue 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