Sinkron : jurnal dan penelitian teknik informatika
Not a member yet
1261 research outputs found
Sort by
Comparative Study of XGBoost, Random Forest, and Logistic Regression Models for Predicting Customer Interest in Vehicle Insurance
No full textIn today’s competitive insurance market, accurately predicting customer interest in additional products, such as vehicle insurance, is crucial for optimizing marketing strategies and maximizing sales. This study presents a comparative analysis of three machine learning models such as XGBoost, RandomForest, and Logistic Regression to predict customer interest in vehicle insurance based on a dataset that includes demographic, vehicle, and policy-related features. The dataset was analyzed using five-fold cross-validation, and the performance of the models was evaluated using AUC-ROC, precision, recall, and F1-score. XGBoost demonstrated the highest recall (0.9525) and AUC-ROC (0.7854), making it the most effective model for identifying customers interested in vehicle insurance, though at the expense of lower precision (0.2585). RandomForest showed a more balanced trade-off between precision (0.3064) and recall (0.5341) but performed lower overall. Logistic Regression, while the most interpretable model, exhibited high variability in performance across different folds, with a lower average precision (0.2372). The findings of this research highlight that XGBoost is ideal for maximizing recall in high-volume campaigns, while RandomForest may be better suited for applications requiring fewer false positives. These results offer valuable insights into model selection based on business objectives and resource allocation
Improving the Accuracy of Heart Failure Prediction Using the Particle Swarm Optimization Method
No full textMalfunction of the body's organs, heart failure, makes a person and those closest to them feel worried, which will result in the person's death. There are too many deaths caused by this deadly disease every year. The main problem throughout the world is heart disease, the death rate of which is getting higher and higher and is uncontrollable for various parties due to many factors, especially in terms of knowing it early or not being able to predict it accurately. Therefore, the aim of this research on heart failure problems is to improve heart failure predictions with optimal accuracy, namely the neural network method with the particle swarm optimization method. Previously, heart failure prediction research had been carried out using several methods, but here we will increase the accuracy of the methods that have been carried out. After the testing process on the neural network method and after being optimized and getting results from the particle swarm optimization method, the accuracy increased with an increase of 08.35%. As well as increasing AUC results with an increase of 0.067%. From the results of increasing the accuracy of the neural network method, testing the particle swarm optimization method on heart failure disease data can be used as a reference for stakeholders
Implementing Scrum in Executive Information System at University
No full textExecutive Information System is a type of system that provides information about reports generated by the system, assists executives in making necessary decisions, and provides easy access to information from both internal and external sources. This system aims to help specific organizations solve problems. The objective of this research is to design and develop a web-based executive information system that can provide access to student, faculty, and program data at the Faculty of Economics, Garut University, with data visualization in the form of graphs and numbers using the Scrum method. The Executive Information System can provide a real-time overview of data for executive-level individuals, namely the faculty leaders. Scrum is the development methodology used, with stages such as product backlog, sprint, daily scrum meeting, sprint review, and sprint retrospective. The results of this research have produced an Executive Information System that provides data on students, faculty, and programs. This system features functions such as filtering, drilldown, and importing. Testing results indicate the successful achievement of sprints on time or even ahead of schedule, and the team was able to meet targets in each sprint. In this research, the Scrum method has been effectively utilized in creating the executive information system. Therefore, this method can be employed to develop similar executive information systems in the future
Usability Evaluation of Tokopedia Application Version 3.242 Using System Usability Scale (SUS) Method
No full textIndonesia is currently experiencing rapid growth in the e-commerce sector. Its One of the existing e-commerce is the Tokopedia application, Users of this application reach more than 10 million users so that there are a lot of positive and negative reviews given by users. After manually analyzing there are still many negative reviews on the application, not only that, there are still other problems found such as expeditions that cannot be selected, then payment methods that cannot COD or pay on the spot, and sometimes force closes that come out by themselves suddenly. Therefore, researchers tried to conduct a study on Tokopedia application user satisfaction with the SUS method to measure the level of usability of the application. System Usability Scale (SUS) method to evaluate its usability aspect. The evaluation results showed that the app earned an SUS score of 55, with a percentile rank of about 30%, placing it at grade D. Although still above average, the slight difference with the standard SUS score (68) indicates a potential improvement. In interpretation based on nature (Adjective), the application is in the OK category, with the level of acceptance (Acceptable) is in the Marginal category. The Net Promoter Score (NPS) results show the Detractor category, indicating a tendency to lack user enthusiasm for the application. Further evaluation is needed to identify aspects of usability that affect user perception and cause unsatisfactory NPS categories. Future research can design improvement strategies based on these findings, with the aim of increasing SUS scores and changing the NPS category to be more positiv
Comparison of Hyperparameter Optimization Techniques in Hybrid CNN-LSTM Model for Heart Disease Classification
No full textHeart disease, which causes the highest number of deaths worldwide, recorded about 17.9 million cases in 2019, or about 32% of total global deaths, according to the World Health Organization (WHO). The significance of early detection of heart disease drives research to develop effective diagnosis systems utilizing machine learning. The advancement of machine learning in healthcare currently primarily serves as a supporting role in the ability of clinicians or analysts to fulfill their roles, identify healthcare trends, and develop disease prediction models. Meanwhile, deep learning has experienced rapid development and has become the most popular method in recent years, one of which is detecting diseases. The main objective of this research is to optimize the hybrid convolutional neural network (CNN) and long short-term memory (LSTM) model for classifying heart disease by comparing hyperparameter optimization using grid search and random search. Although random search requires less time in hyperparameter tuning, the classification performance results of grid search show higher accuracy. In the test, the hybrid CNN and LSTM model with grid search achieved 91.67% accuracy, 89.66% recall (sensitivity), 93.55% specificity, 92.86% precision, 91.23% f1-score, and 0.9310 AUC value. These results confirm that using a hybrid CNN and LSTM model with a grid search approach is better suited for classifying heart disease
LSB-2 Steganography with Brotli Compression and base64 Encoding for Improving Data Embedding Capacity
No full textSteganography functions as a technique for embedding messages or data in various forms of media, such as images, audio, video, or text, with the aim of avoiding detection by unauthorized parties. Steganography techniques can be used as a solution to hide and protect data. In this research, steganography will be carried out using images as the transmission object. This research was conducted to offer a modification of the Least Significant Bit (LSB) steganography technique using the LSB-2 method with Brotli compression and base64 encoding. Modification and use of Brotli compression and base64 coding aims to increase the message capacity that can be embedded in a transmission object while maintaining the quality of the transmission object. Experiments using small data and big data. The experimental results will be presented in tabular form by comparing the original image with the steganographically processed image using metrics such as Mean Square Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM) as a comparison. The experiments carried out resulted in an increase in image capacity by reducing capacity usage with an average of 47.13% for small data and an average of 71.34%. The big data experiment resulted in an increase in the PSNR value of around 3.49%, accompanied by a decrease in the average MSE value of 33.85%, and a constant SSIM value of 0.9999, thus proving that the proposed method was successful in increasing image capacity and improving stego-image quality. when embedding big data
Analyzing Public Sentiment Regarding the Qatar 2023 World Cup Debate Using TF-IDF and K-Nearest Neighbor Weighting
No full textThis research aims to uncover the sentiment of Twitter users regarding the polemics surrounding the 2023 Qatar World Cup using a text-based sentiment analysis approach. The research methodology involves collecting data from Twitter posts, encompassing discussions, opinions, and responses related to the Qatar World Cup 2023. The TF-IDF weighting is applied to identify significant keywords in each post, while the K-Nearest Neighbor algorithm is employed to classify sentiments as positive, negative, or neutral. The findings reveal a comprehensive picture of how the public perceives the Qatar World Cup 2023 on the Twitter platform. The results not only cover positive and negative aspects of online discussions but also identify trends and patterns of sentiment that emerge during specific periods.The application of these methods provides valuable insights into understanding the dynamics of public opinion related to international sports events through the lens of social media. The results of the analysis demonstrate that a majority of Twitter users express positive sentiments towards the Qatar World Cup 2023, highlighting excitement and anticipation. However, some negative sentiments also arise, primarily related to controversies and concerns about the event. The research further identifies temporal variations in sentiment, reflecting changing public perceptions over time.This research contributes to the development of sentiment analysis methods by using a combination of TF-IDF weighting and the K-Nearest Neighbor algorithm to delve into Twitter users' perspectives. Consequently, the findings have practical applicability for further research and implementation in managing the social impact and public perception of major sporting events like the World Cup.
Development of an Intelligent Imaging System for Determining Maturity of Copra Flesh in Coconuts Using Shape and Texture Extraction
No full textCopra is dried coconut meat that is used to produce coconut oil. According to the Central Statistics Agency (BPS), Indonesia's copra production in 2020 reached 2.3 million tonnes. This is one form of the process of improving the economy of people living on the coast. This research was conducted to educate farmers in determining the level of maturity of the copra meat produced. This research was conducted using an extraction method that involves colour extraction and texture extraction. the method is used to provide convenience in seeing the level of maturity of the two characteristics of copra obtained in the field, namely texture and colour. The process obtained in the training with one of the images used as a test image in colour extraction produces area, perimeter, metric and eccentricity values in label 3 with values of 651.00, 184.69, 0.24 and 0.89. while in the feature extraction method the results are obtained with an average intensity value of 243.31, standard deviation of intensity 39.76 and entropy value of the tested image 4.57. The method is able to perform a detection process so that it can determine the level of maturity of copra seen from the existing types of copra such as asalan copra, regular copra, black copra and wet copra, each of which provides different functions in the copra processing stage. The process will be carried out using KNN which is seen from all test data and training data stored after the detection process. The results of the process carried out using digital images involving the extraction method for detection and KNN for classification are able to provide the right value. This is evidenced by the better accuracy value of 98%
Laptop Recommender System Using the Hybrid of Ontology-Based and Collaborative Filtering
No full textIn the era of ever-evolving information technology, choosing the best laptop can be a complicated task for many users. The increasing complexity of technical specifications is often an obstacle, especially for users who need help understanding them. In addressing this challenge, we propose a solution: a laptop recommendation system that considers users' preferences and functional needs. We designed this system to help users choose a laptop that suits their daily functional needs. This system uses a form of Conversational Recommender System (CRS) by combining Ontology-Based Recommender System Filtering and Collaborative Filtering (CF). Ontology-Based Recommender System Filtering ensures a strong relationship between functional needs and technical specifications of laptops, making it easier for users to identify the right laptop. At the same time, Collaborative Filtering (CF) can provide diversity to the recommended products by using similar user preference data. We evaluate the accuracy of our system by calculating the success rate of recommendation accuracy with the accuracy metric, and the evaluation results show that the success rate of recommendation accuracy reaches 93.33%. Our system is highly effective in assisting users in choosing a laptop that suits their functional needs. With our laptop recommendation system, users can confidently select the correct laptop without being burdened by technical specifications, thus making their lives easier and more productive
Edge Detection Model Performance Using Canny, Prewitt and Sobel in Face Detection
No full textDetection of objects in the form of objects, humans and other objects at this time has been widely applied in many aspects of life. The help of this technology can facilitate human work, one of which is facial detection to get information about a person's identity. Face identification and detection is closely related to Data Mining science with Image Processing sub-science. This facial detection and recognition can use several technical approaches, one of which is to use edge detection. Edge detection is one of the basic operations of image processing. In the image classification process, edge detection is required before image segmentation processing. There are several methods that can be used to perform edge detection such as Canny, Prewitt and Sobel. These three methods are methods that have accurate and good detection results, with the advantages of each method having its own added value. From the results of previous studies that stated these three methods have good results, it became interesting to conduct a comparative study of these three methods in detecting edges in facial images. Edge detection applied to this study identifies facial images, and will get similarities with the original image from the result analysis process, and is reinforced by measurement results using the Mean Square Error error degree. The final result of this study states that this study the most optimal Mean Square Error measurement results obtained the final results in the Canny method of 10, the Prewitt method of 41 and Sobel of 29. These results show that the value of the Canny method has the smallest Mean Square Error value, which indicates that the Canny method on facial image edge detection has the most optimal results