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 Articles sent to the Brilliance may not be published elsewhere.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
 42   43   44   45   46 
Application of the Support Vector Machine (SVM) Algorithm for the Diagnosis of Diabetic Retinopathy Yuliadi; Dzil Ikram, Fadhli; Julkarnain, M.; Hamdan, Fahri; Nuryadi, Halid
Brilliance: Research of Artificial Intelligence Vol. 3 No. 2 (2023): Brilliance: Research of Artificial Intelligence, Article Research November 2023
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v3i2.3436

Abstract

Diabetic Retinopathy (DR) is a disease whose main cause is complications of diabetes mellitus. High levels of sugar in the blood (glucose) are caused by the pancreas' inability to produce insulin. Prevention of diabetic retinopathy and blindness by carrying out examinations at an early stage and doing them regularly. Currently, doctors still carry out examinations manually so they are prone to errors in examinations. This research aims to build an application to diagnose Diabetic Retinopathy in order to facilitate the work of the medical team and doctors at the eye clinic. In the application creation process, MATLAB is used, while feature extraction uses GLCM and for classification, SVM is used. The results of the research are that doctors and medical teams are helped in carrying out manual patient diagnoses and reduce the occurrence of human error.
Evaluating the Efficacy of Traditional Machine Learning Models in Speaker Recognition: A Comparative Study Using the LibriSpeech Dataset Airlangga, Gregorius
Brilliance: Research of Artificial Intelligence Vol. 3 No. 2 (2023): Brilliance: Research of Artificial Intelligence, Article Research November 2023
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v3i2.3488

Abstract

The efficacy of machine learning models in speaker recognition tasks is critical for advancements in security systems, biometric authentication, and personalized user interfaces. This study provides a comparative analysis of three prominent machine learning models: Naive Bayes, Logistic Regression, and Gradient Boosting, using the LibriSpeech test-clean dataset—a corpus of read English speech from audiobooks designed for training and evaluating speech recognition systems. Mel-Frequency Cepstral Coefficients (MFCCs) were extracted as features from the audio samples to represent the power spectrum of the speakers’ voices. The models were evaluated based on precision, recall, F1-score, and accuracy to determine their performance in correctly identifying speakers. Results indicate that Logistic Regression outperformed the other models, achieving nearly perfect scores across all metrics, suggesting its superior capability for linear classification in high-dimensional spaces. Naive Bayes also demonstrated high efficiency and robustness, despite the inherent assumption of feature independence, while Gradient Boosting showed slightly lower performance, potentially due to model complexity and overfitting. The study underscores the potential of simpler machine learning models to achieve high accuracy in speaker recognition tasks, particularly where computational resources are limited. However, limitations such as the controlled nature of the dataset and the focus on a single feature type were noted, with recommendations for future research to include more diverse environmental conditions and feature sets.
Web-Based Application For Parenting Patterns In Vocational Schools In The Environment Of Politeknik Pelayaran Sorong Idris, Muh; Widarbowo, Dodik; Hafita, Yuniar Ayu; Herlambang P, Yudha; Sappewali, Sappewali
Brilliance: Research of Artificial Intelligence Vol. 3 No. 2 (2023): Brilliance: Research of Artificial Intelligence, Article Research November 2023
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v3i2.3489

Abstract

Digitalization of education is a logical consequence of developments over time, a response to educational services that are experiencing changes in both the learning system and learning culture. Developments in the field of education are closely related to the term innovation. Innovation in the realm of education is an obligation for all educational actors. Moreover, the development of science and technology is growing rapidly. The parenting pattern that has been implemented in most vocational schools within the Ministry of Transportation is still more of a manual system that cannot be connected directly to digitalization. The aim of the process of developing digitalization of parenting patterns is expected to increase efficiency and optimization in many ways, including efficiency and optimization of parenting activities, connectivity between institutions or units involved in parenting, access to data related to parenting patterns, personal data of cadets and caregivers, as well as ease of use. information in accessing rules relating to parenting patterns. The research method used is a mixed type of research. Mixed research is the use of two types of research, namely qualitative and quantitative in one study. The research location is planned to be carried out at a vocational school under the Ministry of Transportation (Poltekpel Sorong). This research then produced an online-based digitalization development desktop software and was then named the see cadet application website. This development and research uses the ADDIE Development Model, namely the analysis stage, design stage, development stage, implementation stage and evaluation stage.
Advanced Seismic Data Analysis: Comparative study of Machine Learning and Deep Learning for Data Prediction and Understanding Airlangga, Gregorius
Brilliance: Research of Artificial Intelligence Vol. 3 No. 2 (2023): Brilliance: Research of Artificial Intelligence, Article Research November 2023
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v3i2.3501

Abstract

This study delves into the application of machine learning (ML) and deep learning (DL) techniques for the analysis of seismic data, aiming to identify and categorize patterns and anomalies within seismic events. Using a robust dataset, we applied three distinct clustering approaches: K-Means, DBSCAN, and an Autoencoder-based method, each offering unique perspectives on the data. K-Means clustering provided a fundamental partitioning of the data into five predefined clusters, facilitating the identification of broad seismic patterns. DBSCAN, a density-based clustering algorithm, offered insights into the spatial distribution and density of seismic events, adeptly pinpointing anomalies and outliers that signify unusual seismic activity. The Autoencoder, leveraging deep learning, excelled in capturing complex and non-linear relationships within the data, revealing subtle patterns not immediately apparent through traditional methods. The effectiveness of these clustering techniques was quantitatively evaluated using the Silhouette Score and the Davies-Bouldin Score, alongside visual assessments through PCA and t-SNE for dimensionality reduction. The results indicated that while K-Means provided clear partitioning, DBSCAN excelled in outlier detection, and the Autoencoder offered a balanced approach with its nuanced analysis capabilities. Our comprehensive analysis underscores the significance of employing a multi-methodological approach in seismic data analysis, as each method contributes uniquely to the understanding of seismic events. The insights gained from this study are valuable for enhancing predictive models and improving disaster risk management strategies in seismology. Future research directions include the integration of additional seismic features, validation against larger datasets, and the development of hybrid models to further refine the predictive accuracy of seismic event analysis.
Augmented Reality Based Tajwid Reading Law Android Application Agyztia Premana
Brilliance: Research of Artificial Intelligence Vol. 3 No. 2 (2023): Brilliance: Research of Artificial Intelligence, Article Research November 2023
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v3i2.3502

Abstract

The learning method used in learning the subjects of the Qur'an and Hadith in Schools is a common teaching method, which uses books as a source of knowledge and teachers as teachers. In this problem, the author uses a learning method using Augmented Reality (AR) as the basic law of reading aloud so that students don't get bored. Augmented Reality (AR) is a combination of real and virtual objects displayed simultaneously on a screen. Augmented Reality is created with Unity 3D, Vuforia and Android software. The application of new learning methods should increase students' interest in serious and straightforward learning. This research aims to build a recitation science learning application for children 5-10 years old using an Android-based device "so that with this application it is hoped that it will have an attractive design, as well as complete features and have materials and examples of legal reading and pronunciation." easy for children to understand and can make children understand the science of recitation from a young age. The results of this research are applications for learning the science of Tajweed for children 5-10 years old which can display the hijaiyah letters accompanied by their pronunciation and how to pronounce them, the laws of the science of Tajweed which consist of the law of nun mati/tanwin, qalqalah and the law of mad, games as material for evaluating children. The Tajwid science learning application succeeded in increasing children's understanding of Tajweed science by 57.9%. Application feasibility testing uses white box and black box methods with several test requirements. Based on the test results, functionally the application is appropriate, feasible, and can be used as a learning medium for Tajwid science and is in the "Very Good" category.
The role of the number of transparent covers in enhancing the efficiency of flat plate collectors Khaled, Amer; Elzer, Rahma; Alkhazmi, Ali
Brilliance: Research of Artificial Intelligence Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i1.3514

Abstract

Solar energy has gained traction as an eco-friendly alternative to combat Carbon dioxid (CO2) emissions from fired-fossil fuel electrical power plants. One common application is converting solar energy into heat for water heating systems, often achieved through flat-plate solar heating collectors. The usefull thermal energy of these collectors depends on factors like climate, design, and operational parameters. This study examines the effect of number of transparent covers (TCs) and the inlet water temperature on the performance of a liquid-flat plate solar collector (LFPSC) in Beida city, Libya, on July 21, 2020, with data collected at hourly intervals. Different scenarios were considered, varying the number of covers (ranging from 0 to 3) and the inlet water temperatures (ranging from 25°C to 50°C). The findings reveal that the optimal number of covers is influenced by multiple factors, not solely the prevailing climatic conditions. Inlet water temperature and the collector's length were identified as the most influential parameters affecting the over all performance of LFPSC. Consequently, the decision to employ a specific number of covers depends on the system's operating conditions. When the inlet water temperature matches the ambient temperature, a single cover suffices for optimal collector performance. However, if the inlet water temperature surpasses the ambient temperature, multiple covers are necessary to achieve the collector's peak efficiency. This research underscores the importance of considering various factors, beyond just climate, when designing and operating solar collectors for efficient water heating systems.
Implementation of Forecasting with the Monte Carlo Simulation Method to Predict Supply and Demand for Psychotropic Drug Products Bima, Alim Citra Aria; Susanti, Pratiwi; Asyhari, Moch Yusuf
Brilliance: Research of Artificial Intelligence Vol. 3 No. 2 (2023): Brilliance: Research of Artificial Intelligence, Article Research November 2023
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v3i2.3515

Abstract

The availability of drugs is one of the needs that supports the presence of health in the community. Patient certainty regarding the availability of drugs becomes increasingly important for patients who use psychotropic drugs. This type is a dangerous drug and needs to be controlled. Control is carried out to avoid drug abuse outside of medical purposes. Two conflicting sides between the importance of ensuring the availability and controlling their use can be resolved, one of which is by measuring supply and demand. The availability of psychotropic drugs should be adjusted to demand. The problem is that we cannot know demand that has not yet occurred, drugs have an expiration date, and procuring drugs takes time. One way is to predict the demand when supplying drugs so that the order quantity is appropriate. The prediction method used is the Monte Carlo Simulation Method. One example of implementation is the Economic Order Quantity (EOQ) Method. As a result, the Monte Carlo method successfully made predictions based on existing data. In addition, it was found that the Monte Carlo Method tended to the distribution of the data used. The closer the distance between the data, the higher the prediction accuracy obtained. Uncertainty in actual demand is also a big challenge for producing accurate predictions based on patterns. Prediction results will be more accurate with more data patterns and variations. Implementation of prediction results with EOQ makes the number of drugs that should be ordered based on demand that is likely to occur.
Fault Detection and Condition Monitoring in Induction Motors Utilizing Machine Learning Algorithms Elgallai, Tareg
Brilliance: Research of Artificial Intelligence Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i1.3539

Abstract

Electric induction motors (IM) are considered to be a highly significant and extensively utilized category of machinery within contemporary industrial settings. Typically, powerful motors, which are frequently essential to industrial processes, are equipped with integrated condition-monitoring systems to support proactive maintenance and the identification of faults. Typically, the cost-effectiveness of such capabilities is limited for tiny motors with a power output of less than ten horsepower, given their relatively low replacement costs. Nevertheless, it is worth noting that several little motors are commonly employed by large industrial facilities, mostly to operate cooling fans or lubricating pumps that support the functionality of larger machinery. It is possible to allocate multiple small motors to a single electrical circuit, so creating a situation where a malfunction in one motor could potentially cause damage to other motors connected to the same circuit. Hence, there exists a necessity to implement condition monitoring techniques for collections of small motors. This paper presents a comprehensive overview of a continuous effort aimed at the development of a machine learning-driven solution for the identification of faults in a multitude of small electric motors.
Development Of Interactive Learning Applications For English Subjects Rangkuti, Melia Ivana Putri; Fakriza, M
Brilliance: Research of Artificial Intelligence Vol. 3 No. 2 (2023): Brilliance: Research of Artificial Intelligence, Article Research November 2023
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v3i2.3569

Abstract

The use of technology in learning is used as a means of learning. Learning media is anything that is used in the process of learning activities and can stimulate students' thoughts, feelings, interests and attention when learning, so that the process of interaction, communication and education between teachers and students can take place in accordance with the learning objectives. This research aims to produce a product in the form of a web-based interactive multimedia learning application, which is of good quality and highly suitable for use as a learning medium for students in English subjects. The research location was conducted at UPT SMP Negeri. 35 Medan. This multimedia learning product has gone through a strict review and revision process, based on suggestions from teachers and supervisors. This product was tested in a class with 31 students. The results show that learning management at UPT SMP Negeri 35 Medan using this interactive application has achieved learning management well, this can be seen from the acquisition section to the retrieval system of existing information/learning. Thus, this product can be used in the learning process to provide new, more meaningful experiences to students. In addition to this multimedia product, the teaching materials can be studied anywhere and at any time, which can increase students' learning motivation.
Bussiness Management System Of Catfish Cultivation Using Fuzzy Inference System Tsukamoto Methods Sugianti, Sugianti; Prasetyo, Angga; Triananda, Agnes
Brilliance: Research of Artificial Intelligence Vol. 3 No. 2 (2023): Brilliance: Research of Artificial Intelligence, Article Research November 2023
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v3i2.3619

Abstract

Catfish is a type of freshwater fish that is in great demand among people because it has high nutritional value. The high demand for catfish on the market is a promising business opportunity. The relatively fast maintenance period makes this cultivation much in demand. Management of a catfish farming business requires good strategy and planning so that the business process can provide optimal profits. Appropriate management practices, good planning can predict crop yields with minimal error rates. Based on past data from catfish farming businesses, catfish pond production results are influenced by several factors including pond area, number of seeds, and amount of feed. The catfish cultivation management system produces predictions of catfish harvest but ignores weather conditions, natural disasters and infectious diseases. The method used in crop yield prediction management is the Tsukamoto Fuzzy inference system. The Tsukamoto method applies monotonous reasoning and rules are built using expert knowledge, enabling the system to be able to conclude and manage predictions of catfish harvest based on data regarding pond size, number of seeds and amount of feed. System testing using 10 data shows prediction results obtained through manual calculations and system calculations, resulting in identical results. Further testing uses the white box method to ensure that the data implemented in the Tsukamoto fuzzy management system accurately produces logical decisions. Hence, it can be concluded that the management system using the Tsukamoto method is able to show effective performance in predicting harvest results based on data on pond area, number of seeds and amount of feed consumption. This management system is expected to be able to provide recommendations for catfish cultivation business planning for the community.

Page 44 of 55 | Total Record : 544

 42   43   44   45   46 

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