Sinkron : jurnal dan penelitian teknik informatika
Not a member yet
1261 research outputs found
Sort by
Sentiment Analysis towards the 2024 Vice Presidential Candidate Debate Using the Support Vector Machine Algorithm
No full textIn today’s digital era, social media plays an important role in disseminating information and influencing public opinion. For instance, YouTube. At the 2024 Vice Presidential Debate, YouTube became a medium where people gave various comments. This study aimed to analyze public sentiment through comments on the 2024 Vice Presidential Debate on the Metro TV YouTube channel. This study used descriptive quantitative methods with the Support Vector Machine algorithm to identify various public comments. The results show that from the data experiment taken as many as 1012 data, 80% data training amounting to 809 data and 20% data testing amounting to 203 data is carried out. An accuracy of 82% was obtained with a precision value of 80%, a recall value of 87%, and an f1-score value of 83%. With a fairly high accuracy value, the support vector machine model can be said to be the right model to calculate the accuracy value in sentiment analysis
Tanjung, Tegar Haryahya Classification of Heart Disease Using Support Vector Machine
No full textHeart disease is a disease that has a high mortality rate, with more than 12 million deaths occurring throughout the world. Diagnosis of heart disease is very challenging due to the complex interdependence of several attribute factors. The problem that frequently encountered is the lack of accuracy in the classification process. Thus, a system is needed to carry out early diagnosis of heart disease. The structure of this research is to take a heart disease dataset from Kaggle. Then the data will be cleaned with preprocessing. The preprocessing process carried out is changing table names, checking missing values, and normalizing. 820 data will be trained using a Support Vector Machine and 205 data will be tested to find out how well the model can perform classification. The results of training and testing from a total of 1025 data will form a classification model. The model formed using the Support Vector Machine obtained confusion matrix results of 88 is True Positive data, 93 is True Negative data, 10 is False Positive data, and 14 is False Negative data. So the results of model training produce an accuracy of 88%
Summarizer Precision Value on Tribunnews Gorontalo in the Implementation of Online Discourse Sentiment Analysis
No full textThis research investigates the precision of a summarization-based sentiment analysis framework applied to online discourses, specifically from Tribunnews Gorontalo. This study aims to develop and evaluate a sentiment analysis framework that accurately parses complex meanings and nuances in online discourse. The research process begins with summarizing the content using Python, followed by tokenization and sentiment analysis using the BERT model. The precision of the sentiment analysis was meticulously measured. Results indicate that the precision analysis demonstrates that the Python-implemented model achieved a 86% precision rate when applied to ten online discourses from Tribunnews Gorontalo. This research contributes significantly to understanding public sentiments in online content, offering deeper and more accurate insights
Microcell Planning Analysis Using Cell Splitting Method In 4G LTE Network
No full textAs the growth of technology and telecommunication network, demands of mobile technology is also raised. The quality of the network will decrease by the insufficient number of network and cell to support the growth of user, and the scope of e-Node B is not optimal. The method of cell splitting can be used to solve the problem, this method splitting macro cell network become smaller size of cell with scoping area of each without interruption. The planning of new site as microcell implemented in area of Flamboyan Baru using XL operator. As the count gained, 1 site microcell and 2 cell with the antenna of 18,5 meters and power of 38 dBm, cell splitting method could increase network quality and improve the average number of parameter RSRP, SINR, and throughput, also proving that the implementation of cell splitting in microcell could escalate the quality of LTE network, the improvement of network quality in SINR parameter with average number of 24,23 dB with category of very good, RSRP parameter with average number of -94,28 dBm with category good, and the average number of throughput reach 63.094,91 kbps with category very good
Effect of Epoch Value on the Performance of the RNN-LSTM Algorithm in Classifying Lazada App Review Sentiments
No full textIn today's development, the process of buying and selling transactions between sellers and buyers is so developed. not only done directly but can also be done online or can be called e-commerce. Which is where the development of technology is so fast that it indirectly encourages entrepreneurs to develop through e-commerce. Lazada is one of the online stores in Indonesia that has many users and Lazada makes it easy to shop without the need to come to the place or directly. However, purchasing goods using e-commerce has problems regarding the quality of the goods you want to buy, therefore purchasing goods can be seen through reviews of each one you want to buy. Sentiment analysis is carried out using the Recurrent Neural Network (RNN) method with Long Short Term Memory (LSTM). And using the Epoch value as a parameter in processing validation data and test data to produce the best accuracy valu
Sentiment Analysis of Mobile Provider Application Reviews Using Naive Bayes Algorithm and Support Vector Machine
No full textTo choose a mobile provider to use, prospective users often rely on reviews left by previous users of the mobile provider application. One source of information for finding reviews of cellular provider applications is the Google Play Store. The purpose of this research is to analyze user reviews of cellular provider applications and find out the comparison of the accuracy levels of the two algorithms to be used, namely the Naïve Bayes Classification (NBC) and Support Vector Machine (SVM) algorithms. The object of this research is focused on the three most popular applications in Indonesia, according to the Goodstate website, namely Telkomsel, IM3, and XL Axiata. After testing using the Naïve Bayes Clasification method, the accuracy value obtained in the MyTelkomsel application is 75%, MyIM3 is 80%, and MyXL is 72%. While the Support Vector Machine method obtained an accuracy value of 77% for MyTelkomsel, 80% for MyIM3, and 76% for MyXL
Optimizing Facial Expression Recognition with Image Augmentation Techniques: VGG19 Approach on FERC Dataset
No full textIn the field of facial expression recognition (FER), the availability of balanced and representative datasets is key to success in training accurate models. However, Facial Expression Recognition Challenge (FERC) datasets often face the challenge of class imbalance, where some facial expressions have a much smaller number of samples compared to others. This issue can result in biased and unsatisfactory model performance, especially in recognizing less common facial expressions. Data augmentation techniques are becoming an important strategy as they can expand the dataset by creating new variations of existing samples, thus increasing the variety and diversity of the data. Data augmentation can be used to increase the number of samples for less common facial expression classes, thus improving the model's ability to recognize and understand diverse facial expressions. The augmentation results are then combined with balancing techniques such as SMOTE coupled with undersampling to improve model performance. In this study, VGG19 is used to support better model performance. This will provide valuable guidelines for optimizing more advanced CNN models in the future and may encourage further research in creating more innovative augmentation techniques
Exploring Regional Development Patterns using Machine Learning: A Python-based Clustering Analysis of Human Development Index in West Java
No full textMany local governments now prioritize human development when trying to raise the standard of living and welfare of their citizens. Developing effective development policies in West Java, one of Indonesia's most populous provinces, requires a thorough understanding of human development patterns in various districts and cities. Using the Human Development Index (HDI) as the primary indicator, we examine regional development patterns in this study using machine learning techniques, specifically clustering analysis. This study's scope includes an HDI analysis for each of West Java's 27 districts and cities from 2017 to 2022. Finding clusters of districts or cities with comparable human development traits and comparing and contrasting them are our primary goals. We provide a solution that allows for improved mapping and comprehension of human development patterns in West Java by utilizing the Python programming language as the primary tool and the K-Means clustering algorithm. The study's findings indicate that there are three major categories of districts and cities, each with a distinct human development pattern. By using clustering analysis, we can determine which districts or cities within each group have the highest and lowest levels of human development. This information helps policymakers plan more inclusive and sustainable development. In conclusion, a clustering analysis approach based on machine learning can be a helpful tool for understanding and creating more focused and efficient regional development policies in West Java and other areas
Leveraging Enterprise Architecture to Empower KOMINFO's Business Core Operations: A PMO Perspective
No full textThe Sky Bridge (Tol Langit) Program is an Indonesian government’s strategic project aimed at digital transformation in the 3T regions (Tertinggal, Terdepan, Terluar - Underdeveloped, Frontline, Outermost). It requires thorough planning and integrated management for its implementation. A specialized unit with a helicopter view perspective is needed to ensure and oversee the alignment of processes. This important role is managed by the Project Management Office (PMO). One of the challenges PMO faces in ensuring an end-to-end process alignment is identifying the appropriate digital resources to support the process. This is where the Enterprise Architecture (EA) framework plays a crucial role as a blueprint for the organization's digital landscape. This reference helps map out existing data, applications, and business processes. Having this blueprint allows PMO to have a holistic view and make targeted decisions. EA also helps identify existing applications that can be integrated with new programs, avoiding unnecessary duplication. The use of ArchiMate, a language for enterprise architecture modeling, assists PMOs in planning digital transformations considering all aspects - business needs, applications, and technology. In short, a well-defined EA framework empowers PMOs to navigate the complexities of digital transformation in the telecommunications sector to ensure the successful implementation of the Sky Bridge Program
A Comparative Analysis of Machine Learning Algorithms for Predicting Paddy Production
No full textFor countries with large populations, such as Indonesia, food security is a very important issue. The majority of Indonesia's population depends on rice as their main food, and paddy is one of the most widely cultivated food commodities. The very good and accurate national paddy production prediction results really support decisions regarding national paddy production targets for the coming period. Therefore, to ensure supply and price stability, paddy availability must be predicted. Many studies have used machine learning to predict crop yields. By learning important patterns and relationships from input data, machine learning can combine the advantages of other methods to make better predictions of paddy yields. The aim of this research is to conduct a comparative analysis between three machine learning algorithms, namely, random forest, decision tree, and k-nearest neighbors, in predicting paddy production. To determine which algorithm is the best, a model evaluation is carried out using the coefficient of determination (R2-score), mean absolute error (MAE), and mean squared error (MSE). This research goes through methodological stages, starting from collecting datasets, data preprocessing, training and testing split datasets, applying algorithms, and evaluating the model. From this research, results were obtained for the random forest algorithm with an R2-score of 82.38%, MAE of 261726.20, and MSE of 2.19495E+11. For the decision tree, the R2-score was 79.62%, MAE was 323257.99, and MSE was 2.49304E+11. Meanwhile, k-nearest neighbors obtained an R2-score of 76.25%, MAE of 318433.42, and MSE of 2.90577E+11. The results of this research show that the random forest algorithm is the best for predicting paddy production because it obtains a larger R2-score as well as smaller MAE and MSE results