Brilliance: Research of Artificial Intelligence
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 Articles sent to the Brilliance may not be published elsewhere.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
<![CDATA[Enhancing the Accuracy of Diabetes Prediction Using Feedforward Neural Networks: Strategies for Improved Recall and Generalization ]]>
<![CDATA[Setiawan, Herry]]>;
<![CDATA[Firnanda, Ary]]>;
<![CDATA[Khair, Ummul]]>
<![CDATA[ Brilliance: Research of Artificial Intelligence Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024 ]]>
Publisher : <![CDATA[Yayasan Cita Cendekiawan Al Khwarizmi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47709/brilliance.v4i1.3888
<![CDATA[This study explores the development and evaluation of a neural network model for predicting diabetes based on clinical data. The model was built using the Keras API with TensorFlow backend. Key steps included data preprocessing, such as feature scaling with `StandardScaler` and splitting the data into training and testing sets. The neural network architecture consisted of an input layer, two hidden layers with ReLU activation functions, and an output layer with a sigmoid activation function, optimized using the Adam optimizer and binary crossentropy loss function. The model was trained over 50 epochs with a batch size of 10, incorporating a validation split of 20% to monitor performance on unseen data during training. The results demonstrated a high accuracy of approximately 97% on the test set, indicating the model's efficacy in predicting diabetes. Further analysis using a confusion matrix revealed a high count of true positives and true negatives, alongside minimal false positives and false negatives, confirming the model's robustness. These findings suggest that neural networks can be effectively employed for diabetes prediction, offering significant potential for integration into clinical decision support systems. However, further validation with larger and more diverse datasets, alongside considerations for data imbalance and model interpretability, is recommended to ensure generalizability and practical application in real-world healthcare settings.]]>
<![CDATA[Controlling System in Smart Agriculture for Automatic Monitoring of Plant Nutrition ]]>
<![CDATA[Agustina, Dian Resha]]>;
<![CDATA[Febrianti, Maria Shusanti]]>;
<![CDATA[Susanty, Wiwin]]>;
<![CDATA[Hindayanti, Kadek Setiani]]>
<![CDATA[ Brilliance: Research of Artificial Intelligence Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024 ]]>
Publisher : <![CDATA[Yayasan Cita Cendekiawan Al Khwarizmi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47709/brilliance.v4i1.4001
<![CDATA[Technological developments have had a major impact on the lifestyle of Indonesian people through sophisticated communication tools such as smartphones and gadgets. However, the use of this technology is still not optimal. In the Indonesian context, computer and information technology, especially Intelligent Systems, has changed the way people work, interact and live. One significant implementation of Smart Systems is Smart Agriculture, which uses information and communication technology to increase agricultural productivity. The application of Greenhouse technology and hydroponic methods in agriculture supports more efficient and productive plant growth. The use of TDS sensors to measure nutrient concentrations in water in the hydroponic method helps ensure optimal conditions. In this research, the automation of providing nutrition to lettuce plants has been carried out well according to predetermined conditions. The solution to solve the problem that occurs is to use an automatic nutrition system. This system can control the amount and frequency of nutrients provided accurately and efficiently, without depending on the skill and caution of the hydroponic farmer. In addition, this system also ensures that nutrients are provided consistently and safely for farmers and the environment. This technology utilizes sensors and automation systems to monitor nutritional conditions in the planting media in real-time and farmers can ensure that their plants receive the nutrients they need and have maximum yields. This system also helps farmers speed up the plant growth process and saves time and energy.]]>
<![CDATA[Semiotic Analysis of Twitter Logo Change to Logo X: User Interface (UI) Design and User Psychological Perspectives ]]>
<![CDATA[Yulianto, Arief]]>;
<![CDATA[Putri, I Gusti Ayu Agung Aristi]]>
<![CDATA[ Brilliance: Research of Artificial Intelligence Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024 ]]>
Publisher : <![CDATA[Yayasan Cita Cendekiawan Al Khwarizmi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47709/brilliance.v4i1.4037
<![CDATA[The development of a logo has become a visual identity for big brands. Some brands create logos to be the biggest promotional resource to attract the mindset of their customers. In the context of technology applications, a logo is not just a symbol, but also an integral part of the User Interface (UI) that influences user interaction and engagement. Twitter, as one of the largest social media platforms in the world, has undergone a significant change in its visual identity by replacing its iconic logo to a new logo known as X. This research uses a descriptive analysis research method with comparative analysis from the researcher himself and data approaches carried out with the 5W + 1H theory. Semiotic Theory using Roland Barthes theory which explains that the first stage of signification is the relationship of signifier (expression) and signified (content) in a sign to external reality. In addition, this analysis also looks at the UI Design side and the user psychology side with the Gestalt Psycholgy theory. The results and findings viewed in the context of UI design, these changes present new challenges and opportunities to create a consistent and engaging user experience. Users' psychological reactions were mixed, indicating that the logo change had a major impact on users' perception and engagement with the app. Through the 5W+1H concept and personal analysis, this research provides a comprehensive understanding of the meaning and impact of the logo change.]]>
<![CDATA[Application of the K-Nearest Neighbor Machine Learning Algorithm to Preduct Sales of Best-Selling Products ]]>
<![CDATA[Danny, Muhtajuddin]]>;
<![CDATA[Muhidin, Asep]]>;
<![CDATA[Jamal, Akhiratul]]>
<![CDATA[ Brilliance: Research of Artificial Intelligence Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024 ]]>
Publisher : <![CDATA[Yayasan Cita Cendekiawan Al Khwarizmi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47709/brilliance.v4i1.4063
<![CDATA[The development of increasingly intense competition in the business world, accompanied by advances in information technology, has brought retail companies into a situation of tighter and more open competition. PT LG Innotek Indonesia is the only company that produces tuners in Indonesia. Looking at consumer demand, PT LG Innotek must improve product quality, and add products that consumers like and frequently purchase. For this reason, PT LG Innotek Indonesia needs an analysis that can help the company identify products that tend to sell well. This analysis can be carried out through the application of machine learning algorithms, especially the K-Nearest Neighbor method. The aim of this research is to find out how the KNN algorithm performs in predicting products that are selling well and not selling well at PT LG Innotek Indonesia. Based on the analysis results, prediction results were obtained with an accuracy level of 94.74% and an error rate of 5.26%. With this high level of accuracy and low error rate, it can be concluded that the K-Nearest Neighbor method is effectively used to predict sales of PT LG Innotek Indonesia's best-selling products.]]>
<![CDATA[Sentiment Analysis Of Indosat's Mobile Operator Services On Twitter Using The Naïve Bayes Algorithm ]]>
<![CDATA[Butsianto, Sufajar]]>;
<![CDATA[Fauziah, Sifa]]>;
<![CDATA[Naya, Candra]]>;
<![CDATA[Maulana, Futuh]]>
<![CDATA[ Brilliance: Research of Artificial Intelligence Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024 ]]>
Publisher : <![CDATA[Yayasan Cita Cendekiawan Al Khwarizmi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47709/brilliance.v4i1.4084
<![CDATA[Twitter is a social media that allows users to share information with others in real time. Information that is shared on Twitter is usually referred to as a tweet. Sentiment analysis is a branch of research in the text mining domain where the process of identifying and extracting sentiment data will usually be categorized based on its polarity, whether it is positive, negative or neutral. We can process data from opinions on Twitter using data mining techniques, namely classification. The algorithm that will be used in this research is the Naïve Bayes Algorithm. This research will also use the RStudio application. It is a computer programming language that allows users to program algorithms and use tools that have been developed through R by other users. R is a high-level programming language and is also an environment for data and graph analysis. Based on the experimental results, using a comparison of training data and test data of 20%: 80%, 40%: 60%, 60%: 40%, 80%: 20% and 90%:10%, the results of sentiment classification using the Naïve Bayes method are obtained. and using 10-fold cross validation obtained an average value of 85.00% accuracy and The decrease in machine learning performance occurs in the ratio of 80:20 or 1440 training data: 360 data testing, while the ratio of 20%:80% and 90%:10% has the same accuracy value, namely 85.41%.]]>
<![CDATA[Linear Regression Algorithm Analysis for Predicting Electrical Panel Painting Quality ]]>
<![CDATA[Susilo, Arif]]>;
<![CDATA[Widodo , Edy]]>;
<![CDATA[Rilvani, Elkin]]>;
<![CDATA[Suryana, Syahro]]>
<![CDATA[ Brilliance: Research of Artificial Intelligence Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024 ]]>
Publisher : <![CDATA[Yayasan Cita Cendekiawan Al Khwarizmi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47709/brilliance.v4i1.4096
<![CDATA[Industry is increasingly developing rapidly and has an impact on the emergence of competition between companies, both private and state, both companies engaged in manufacturing and service companies. Linear Regression is used to find out how the dependent/criterion variable can be predicted through independent variables or predictor variables, individually. Based on the results of the tests that have been carried out, the variables or attributes used in this research (minute and thinkness results) have a significant effect on this research. It is proven that using the linear regression algorithm is able to provide good results with a Root Mean Squared Error value of 0.273 +/- 0.000. This is because there is a correlation or functional relationship (cause - effect) between one variable (dependent or criterion) and another variable (independent or predictor). This testing process is carried out to identify stock needs using a linear regression algorithm]]>
<![CDATA[Sentiment Analysis on Social Media X (Twitter) Against ChatGBT Using the K-Nearest Neighbors Algorithm ]]>
<![CDATA[Arwan Sulaeman, Asep]]>;
<![CDATA[Danny, Muhtajuddin]]>;
<![CDATA[Butsianto, Sufajar]]>;
<![CDATA[Pratama, Suria]]>
<![CDATA[ Brilliance: Research of Artificial Intelligence Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024 ]]>
Publisher : <![CDATA[Yayasan Cita Cendekiawan Al Khwarizmi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47709/brilliance.v4i1.4105
<![CDATA[This research aims to analyze the public's response to ChatGPT through data obtained from Twitter. Apart from that, it is also to understand whether people's responses tend to be positive or negative towards ChatGPT, as well as to test the performance of the K-Nearest Neighbors (KNN) method in classifying sentiment patterns in tweet data. The sentiment analysis method is carried out by dividing public responses into positive and negative categories. Next, the performance of the K-Nearest Neighbors (KNN) method was tested with varying k values ??to classify sentiment patterns in tweet data. This testing includes dataset division, vectorization of text data using TF-IDF, initialization and training of the KNN model, and evaluation of model performance using metrics such as precision, recall, and f1-score. The results of sentiment analysis show that the majority of people's responses to ChatGPT are positive (74.3%), while 25.7% of responses are negative. Performance testing of the KNN model shows that the highest accuracy of 88% is achieved when the k value is 5. Evaluation of model performance also shows satisfactory levels of precision, recall and f1-score. Based on the research results, it was concluded that sentiment analysis and classification using KNN were effective in understanding people's responses to ChatGPT]]>
<![CDATA[Implementation of the Naive Bayes Algorithm for Death Due to Heart Failure Using Rapid Miner ]]>
<![CDATA[Surojudin, Nurhadi]]>;
<![CDATA[Ermanto, Ermanto]]>;
<![CDATA[Danny, Muhtajuddin]]>;
<![CDATA[Pratama, Suria]]>
<![CDATA[ Brilliance: Research of Artificial Intelligence Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024 ]]>
Publisher : <![CDATA[Yayasan Cita Cendekiawan Al Khwarizmi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47709/brilliance.v4i1.4136
<![CDATA[Until now there is no treatment that can specifically treat heart failure problems. Heart failure treatment only functions to control symptoms, improve quality of life so that patients can carry out normal activities, and reduce the risk of complications due to heart failure such as heart rhythm disturbances, kidney and lung function disorders, stroke, and sudden death. Heart failure is a condition when the heart pump weakens so that it is unable to circulate sufficient blood throughout the body. This condition is also called congestive heart failure. Until now there is no treatment that can specifically treat heart failure problems. This research is a descriptive study which aims to describe the condition of heart failure. By using classification techniques in data mining on data from patients suffering from heart failure using the Naive Bayes algorithm. By using the Rapid Miner tool, data processing is based on the dataset, using classification techniques and data mining stages to classify data on patients suffering from heart failure. By using the Rapid Miner tool, the data processing that will be used as a data collection in this research is collected into 90% training data and 10% testing data. The research results showed an accuracy rate of 80.00%, precision of 66.67% and recall of 100.00%. Based on the research that has been conducted, it is concluded that classification techniques using the Naive Bayes algorithm can be used to determine the potential for life and death in heart failure sufferers.]]>
<![CDATA[Recruitment Classification of Security Unit PT. Satria Kencana Abadi Using Naïve Bayes Method ]]>
<![CDATA[Rilvani, Elkin]]>;
<![CDATA[Surojudin, Nurhadi]]>;
<![CDATA[Danny, Muhtajuddin]]>;
<![CDATA[Yoga Pratama, Evan]]>
<![CDATA[ Brilliance: Research of Artificial Intelligence Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024 ]]>
Publisher : <![CDATA[Yayasan Cita Cendekiawan Al Khwarizmi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47709/brilliance.v4i1.4138
<![CDATA[To get human resources according to company standards, the problem faced in the company is the difficulty of the selection process with a short time and the complexity of the decision making process resulting in subjective decision making. The purpose of this research is to assist the assessment process in making decisions for determining the selection of security units (SATPAM) to be more targeted so that it can help the company. In this study the data used were 697 data with 558 training data and 139 testing data. This test data was carried out using the Naïve Bayes algorithm method to classify so that it can determine accurate and efficient decision making, using Rapidminer tools which have 82 accuracy, 01%, 81.61% Precision, and 88.75% recall. This shows that the Naïve Bayes algorithm method has a good performance in determining decision making during the selection of security forces (SATPAM) at PT. Satria Kencana Abadi.]]>
<![CDATA[Prediction of Employee Assessments for Contract Extensions at PT Sagateknindo Sejati Using the Naïve Bayes Algorithm ]]>
<![CDATA[Naya, Candra]]>;
<![CDATA[Siswandi, Arif]]>;
<![CDATA[Butsianto, Sufajar]]>;
<![CDATA[Febriyanti, Febriyanti]]>
<![CDATA[ Brilliance: Research of Artificial Intelligence Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024 ]]>
Publisher : <![CDATA[Yayasan Cita Cendekiawan Al Khwarizmi ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47709/brilliance.v4i1.4170
<![CDATA[Companies must be selective in conducting employee assessments in order to retain employees with the best performance. When assessing employee performance, it is seen from their perseverance and discipline. However, in reality, good employee performance sometimes gets bad reviews and even gets reprimanded by their superiors. This is caused by the employee assessment monitoring system used, namely only personal assessment without using an assessment system and the data collected is less than optimal. This research uses the Naive Bayes method to process data using a data mining algorithm to obtain predictions that can be used as additional references in making employee performance assessment decisions. Aims to predict employee assessments of contract extensions at PT Sagateknindo Sejati. This research is important because it helps in making more accurate decisions regarding employee contract extensions based on existing historical data. Naive Bayes is a data processing algorithm that is classified as a calculation that is easy to understand but its accuracy results are reliable. It is used because it is efficient in managing data with various attributes and is able to produce predictions based on the probability of each existing attribute. The data used in this research includes various variables, using the Rapidminer supporting application to test the accuracy of the system created. Testing was carried out by preparing 320 data and testing 50 randomly selected data. Test data will be analyzed using the Rapidminer supporting application. The test results produced an accuracy of 83.96%.]]>
