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 Articles sent to the Brilliance may not be published elsewhere.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
Implementation of K-Means Clustering for Social Assistance Recipients with Silhouette Score Evaluation Rhomadhona, Herfia; Kusrini, Wiwik; Aprianti, Winda; Permadi, Jaka
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.5900

Abstract

The distribution of direct social assistance continues to face several challenges, particularly regarding inaccurate targeting and unequal allocation. One of the main causes of this issue is the lack of transparency in the distribution process, where assistance is often granted to individuals with familial ties to local committee members or even government officials. As a result, the groups most in need frequently do not receive the aid they deserve. This condition is also evident in Tanjung Village, Bajuin Subdistrict, Tanah Laut Regency. The manual process of grouping prospective aid recipients contributes to inaccuracies in targeting, which in turn leads to public dissatisfaction. To address this issue, this study applies the K-Means Clustering method to group potential social assistance recipients using data from 150 individuals and three main attributes: age, occupation, and income. The method clusters the data based on the similarity of characteristics, thus supporting a more equitable and efficient identification process. The evaluation is conducted using the Silhouette Coefficient to assess the quality of clustering. The results indicate that the highest Silhouette Score is achieved at k=2k = 2k=2, with a value of 0.8278, suggesting that dividing the data into two clusters provides the most optimal configuration. The Silhouette Score tends to decrease as the number of clusters increases, confirming that adding more clusters does not necessarily improve the quality of separation.
Analysis of the Impact of the Pre-Employment Card Program and Clustering of Unemployment Rates in West Java Using Spectral Clustering Khoirunnisa, Fathimah Fadhilah; Rumaisa, Fitrah
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.5917

Abstract

The Pre-Employment Card Program is an initiative launched by the Indonesian government to enhance workforce skills and reduce unemployment. In West Java Province, where population density and socio-economic diversity are high, assessing the effectiveness of this program is particularly relevant. This study aims to cluster regions in West Java based on participation in the Pre-Employment Card Program and unemployment rates using the spectral clustering method, as well as to analyze the program’s impact on regional unemployment levels.The dataset consists of variables such as unemployment rate, labor force size, education level, and program participation, obtained from the Central Bureau of Statistics (BPS) and the official Pre-Employment Program website (2020–2024). The clustering results identified two primary groups: regions with high unemployment and low participation, and those with low unemployment and high participation. The clustering structure achieved a Silhouette Score of 0.2808, indicating a reasonably good cluster separation. Correlation analysis revealed a weak positive relationship between program participation and unemployment reduction (r = 0.34), with the strongest correlation observed among senior high school and vocational school graduates. Regions with high participation experienced a decrease in the average unemployment rate from 10.39% to 8.36%, while those with low participation saw a decline from 9.16% to 7.21%. These findings suggest that the Pre-Employment Card Program holds potential in contributing to unemployment reduction in West Java. Nonetheless, further policy support is required, taking into account factors such as educational background, access to training, and local socio-economic dynamics to optimize the program’s impact.
Application of the Mean-Shift Method in Grouping the Influence of Labor Market Information on Labor Absorption in West Java Province Ulfah, Khaerani; Rumaisa, Fitrah
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.5920

Abstract

The imbalance between the number of job seekers and the availability of jobs is a challenge in the labor market in West Java Province. This study aims to group districts/cities based on the influence of labor market information on labor absorption using the Mean-Shift algorithm. Data were obtained from BPS for the 2019–2023 period, covering the number of job seekers, vacancies, and job placements. Data were processed through cleaning, transformation, normalization, and aggregation of a five-year average. Clustering was carried out using the Mean-Shift algorithm with an optimal bandwidth of 0.474611, resulting in two clusters with a Silhouette Score of 0.4943. The first cluster consists of areas with low labor absorption rates, characterized by the number of job seekers that are not comparable to vacancies and job placements. The second cluster includes areas with higher and more balanced labor absorption. The results of the study show that the Mean-Shift algorithm is able to group regions based on labor market characteristics. These findings suggest that labor market information can be used to map regions based on labor absorption rates in a more targeted manner, as well as support the formulation of data-based employment policies.
Ant Colony Optimization for Waste Collection Routing: A Case Study in Sekar Tunjung Residential Arimbawa K, Ida Bagus Kade Puja
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.5936

Abstract

Waste collection is a critical issue in the management of efficient urban systems, particularly in densely populated residential areas. Inefficient waste transportation routes can lead to excessive fuel consumption, prolonged collection times, and increased operational costs. This study proposes the application of the Ant Colony Optimization (ACO) algorithm as a metaheuristic approach to solve the Capacitated Vehicle Routing Problem (CVRP) in the context of waste collection. ACO mimics the foraging behavior of ant colonies, allowing it to explore and reinforce optimal routing paths based on pheromone intensity and distance-based desirability. The methodology involves modeling a spatial network of waste pick-up points, each with varying waste volumes, and incorporating truck capacity constraints into the routing algorithm. The case study is situated in the Sekar Tunjung residential in East Denpasar, where the simulation uses ten pick-up points and a waste truck starting and ending at TPS3R Kesiman. Parameters such as pheromone influence , visibility , and evaporation rate  are tuned to find the best route configuration. Simulation results show that ACO efficiently constructs a single-trip route covering all points while respecting capacity limits. The algorithm demonstrates adaptability to changes in volume distribution and capacity scenarios, resulting in minimal total travel distance. This research confirms the potential of ACO as a robust and flexible solution for optimizing waste transportation logistics in urban environments.
Internet Network QOS Analysis at Yala Kopitiam pamekasan Using Wireshak Putra, Fauzan Prasetyo Eka; Surur, Miftahus; Mahendra, Mahendra; Arifin, Goffal
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.5940

Abstract

This research aims to analyze the quality of internet network services at Yala Kopitiam Pamekasan in both indoor and outdoor areas using the Wireshark version 4.0.3 application. The main focus is on measuring several Quality of Service (QoS) parameters namely throughput, packet loss, delay, and jitter to evaluate the overall performance of the Wi-Fi network accessed by customers. The methodology used includes direct observation at the café, interviews with café management to understand user complaints and technical constraints, and literature review to strengthen theoretical foundations. The data collected was analyzed using the TIPHON (Telecommunications and Internet Protocol Harmonization Over Networks) standard, which classifies service quality based on quantified thresholds for each parameter. The results indicated that throughput was low in both outdoor (16 kbps) and indoor (32 kbps) areas, categorized as “Poor”. However, packet loss was minimal, at 0.049% for outdoor and 0.082% for indoor, both rated as “Excellent”. Delay varied between locations, with outdoor delay (1.883 ms) rated “Good” and indoor delay (152.88 ms) rated “Medium”. Jitter performance was also relatively stable, with values of 1.883 ms outdoors and 11.88 ms indoors, both classified as “Good”. Based on these measurements, the overall network service quality at Yala Kopitiam Pamekasan falls into the “Medium” category with an average QoS index of 2.5. The study concludes by recommending enhancements in bandwidth capacity and optimization of network device configurations to improve service reliability and customer satisfaction.
Machine Learning-Based Clustering for Program Learning Outcomes in Higher Education: A Systematic Review Wahyudin, W.; Riza, Lala Septem; Erlangga, E.; Al Husaeni, Dwi Novia
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.5953

Abstract

This study aims to systematically review the application of machine learning-based clustering algorithms in the evaluation of Graduate Learning Outcomes (CPL) in higher education. The review was conducted using the PRISMA approach on articles published in the Scopus database during the period 2020–2025. A total of 52 articles were analyzed to identify trends in the algorithms used, implementation challenges, and their contributions to curriculum development. The findings show that algorithms such as K-Means, Hierarchical Clustering, and Fuzzy C-Means are frequently used in mapping student competencies. However, their implementation in practice remains limited due to insufficient model validation, lack of justification for algorithm selection, and a disconnect between analytical results and academic decision-making. This situation reflects a broader issue in the integration of machine learning into educational contexts, where the technical potential of algorithms has not yet been fully translated into meaningful pedagogical impact. As a conceptual contribution, this study develops a machine learning-based computational model that includes the stages of CPL data collection, preprocessing, cluster modeling, result evaluation, and integration into curriculum policy. The proposed model is designed to enhance transparency, adaptability, and evidence-based decision-making in curriculum management systems. This study also highlights the need for the development of soft clustering techniques, integration with digital learning systems, and attention to the ethics and transparency of algorithms in data-based evaluation. Thus, this study emphasizes the importance of bridging the gap between algorithmic analysis and applicable educational strategies within higher education institutions.
Detection of DNS Spoofing Attacks on Campus Networks Using LightGBM with Hybrid Feature Selection (SelectKBest + SHAP) Budiansyah, Arie; Candra, Rudi Arif; Ilham, Dirja Nur; Misbullah, Alim
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.5962

Abstract

This study investigates the detection of Domain Name System over HTTPS (DoH) spoofing attacks utilizing the CIRA-CIC-DoHBrw-2020 dataset, which encompasses over 100,000 labeled DNS records categorized as either normal or malicious. Features such as packet timing, packet size, and TLS parameters are utilized for detection purposes. A systematic feature selection process is conducted utilizing the Elbow and Kneedle methods based on F-Score values derived from a built-in model evaluation. This method ensures that the top features are selected objectively and quantitatively, thereby enhancing the robustness of the model. The model is trained using the five most significant features, yielding exceptional performance metrics: a training time of just 0.5727 seconds, an inference time of 0.0157 seconds, and an inference latency of 0.0035 milliseconds per sample. Moreover, the model delivers an outstanding accuracy of 0.9995, an F1-Score of 0.9995, and an AUC-ROC of 1.0000, reflecting near-perfect detection capabilities. The classification report reveals a balanced distribution of precision, recall, and F1-Scores of 1.00 across both normal and malicious classes, based on a test sample of 14,974 entries. The Elbow plot visually confirms the optimal number of features utilized, while the SHAP beeswarm plot provides insights into how each selected feature contributes to the model’s predictions, facilitating interpretability. Additionally, the confusion matrix corroborates the model's reliability, showcasing that nearly all samples were accurately classified. The results demonstrate that the proposed methodology significantly enhances the effectiveness of DNS spoofing detection, offering a promising avenue for securing DNS over HTTPS communications.
Implementation And Evaluation Of Zerotier-Based Virtual Network For Device Connectivity Putra, Fauzan Prasetyo Eka; Ilhamsyah, Revi Mario; Efendy, Satrio Ananta; Rizki, Abdulloh
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.5966

Abstract

The demand for adaptable, secure, and easily deployable network connectivity is increasing rapidly, driven by continuous advancements in information and communication technology. This is particularly evident in the rising adoption of cloud computing, remote work models, and the growing need for scalable and flexible virtual network infrastructures. ZeroTier emerges as an innovative solution that combines the key concepts of Virtual Private Networks (VPN), Software Defined Networking (SDN), and peer-to-peer architectures into a unified platform. This study aims to explore the operational mechanism, implementation procedure, and real-world performance of ZeroTier in enabling seamless connections between devices located across different networks and physical locations. The research methodology includes a comprehensive literature review and practical testing by creating a virtual network using ZeroTier. The evaluation focuses on connection setup, security, ease of configuration, and performance under different network scenarios. The findings reveal that ZeroTier offers a reliable, secure, and efficient virtual networking environment, capable of delivering stable communication with minimal configuration effort. Additionally, it does not require complex infrastructure or technical expertise, making it suitable for academic research, remote work environments, and small to medium-sized businesses. The results suggest that ZeroTier can be considered a viable alternative to traditional VPN solutions and physical network setups, especially in contexts that demand agility, security, and simplicity.
Enhancing Early Childhood Green Awareness via Digital Platform: A Pangandaran Study Mayang, Ajeng; Barnadi, Yudi; Suryana, Ase; Ardiansyah, Neris Peri
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.5970

Abstract

Global environmental issues, particularly the energy crisis and climate change, require an active and sustainable educational response. Early Childhood Education (ECE) plays a crucial role in fostering environmental awareness and shaping values and understanding of renewable energy from an early age. In coastal areas like Pangandaran, Indonesia—which has abundant potential for environmentally friendly energy sources such as solar, wind, and biomass—it is essential for communities to begin utilizing these resources sustainably. However, the implementation of this concept in ECE settings remains limited, mainly due to inadequate facilities and a lack of suitable teaching methods. As a strategic measure, the Ministry of Education, Culture, Research, and Technology (Kemendikbudristek), through the Education Standards, Curriculum, and Assessment Agency (BSKAP), issued a regulation in 2023 mandating the integration of climate change issues into curricula at all educational levels, including ECE. This policy also supports teacher training programs to enable structured teaching of green energy topics. The main challenge lies in delivering complex material in a way that aligns with the developmental stage of early childhood, which is characterized by exploration and emotional learning. This study explores the effectiveness of a digital-based approach in supporting ECE teachers in Pangandaran by utilizing platforms such as Google Spaces and Learning Management Systems (LMS). This approach is designed to help teachers present renewable energy concepts in a fun, interactive, and age-appropriate manner, thereby enhancing both teachers' and students' understanding and active engagement with environmental issues.
Trends and Best Practices in API-Based Web Development Using Laravel and React Putra, Fauzan Prasetyo Eka; Efendi, Reynal Widya; Tamam, Alief Badrit; Pramadi, Walid Agel
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.5971

Abstract

Modern web development is undergoing a paradigm shift marked by the increasing adoption of API-based architectures that decouple frontend and backend responsibilities. This separation enables the development of modular, scalable, and maintainable applications, particularly through the combination of Laravel and React. This study aims to explore current trends and best practices in API-driven web application development by conducting a systematic literature review of academic publications and technical documentation published between 2022 and 2024. Laravel, a robust PHP backend framework, provides a powerful foundation for implementing RESTful APIs, while React, a declarative JavaScript library, enhances user interface responsiveness through efficient state management and component-based architecture. The review identifies several best practices: implementing RESTful principles, leveraging React's useContext and Redux for state handling, and maintaining well-structured and versioned API documentation using tools like Swagger. Integration between the two technologies offers high flexibility but presents technical challenges such as handling secure authentication (e.g., using Laravel Sanctum or Passport), managing asynchronous data flow, and configuring Cross-Origin Resource Sharing (CORS) policies correctly. Furthermore, emerging trends such as headless CMS, Single Page Applications (SPA), Server-Side Rendering (SSR), and microservices architecture have gained traction in enhancing performance, SEO, and development scalability. These trends reflect a broader movement toward decoupled and distributed systems. By synthesizing these findings, this study provides strategic insights for developers, educators, and researchers to better navigate the evolving landscape of web application development using Laravel and React in an API-centric ecosystem.