Journal of Computer Networks, Architecture and High Performance Computing
Not a member yet
473 research outputs found
Sort by
Flood Prediction Using Support Vector Regression (Case Study of Floodgates in Jakarta)
Get PDFFlood can be interpreted as an event that occurs suddenly and quickly enough where the water discharge in the drainage channel cannot be accommodated, so that the blocked area causes the water discharge in the drainage channel in several surrounding areas to overflow and is one of the natural disasters that occurs at an unexpected time and cannot be prevented, because of this, a prediction must be made to detect floods for the next day. Flood prediction is a crucial aspect of disaster management and mitigation, particularly in flood-prone areas such as Jakarta, Indonesia. This study aims to leverage Support Vector Regression (SVR) to predict flood events by analyzing various environmental and hydrological factors that influence flooding. The primary data sources include historical wheater data, river water levels, floodgate positions in Jakarta. The data preprocessing involved cleaning, handling missing values, and normalizing the datasets to ensure compatibility with the SVR model. Feature selection was conducted to identify the most relevant predictors of flooding, such as wheater data, and river water levels. The dataset was then split into training and testing sets, maintaining an 80-20 ratio to ensure robust model validation. An SVR model with a radial basis function (RBF) kernel was trained on the standardized training data. The model's performance was evaluated using Root Mean Squared Error (RMSE) as the primary metric. The RMSE produced in this study was 0.112 with an R Square accuracy of 0.977. The results indicated that the SVR model could effectively predict flood events with a reasonable degree of accuracy, demonstrating its potential as a valuable tool in flood forecasting
Evaluation of Information Technology Service Devices At High Schools in Kendal Regency With ITIL 4.0
Get PDFSchools as educational institutions with information technology services in the form of New Student Admission Systems, e-report systems, and other information technology services require devices supported by good service. Information technology devices must be appropriately managed to conduct business processes according to business goals. With good service management, the business value offered to customers (students) will increase. ITIL V4 contains information technology service management guidelines that contain best practices for information technology service management, including attention to customer experience, value streams, and support for current digital transformation. This research measures information technology equipment services at high schools in Kendal Regency. This research uses indicators adapted to schools with ITIL V4: Key Performance Indicators (KPI) and Critical Success Factors (CSF). The results of this research show that the performance of the hardware needs to be improved, and the value of the maturity model for each service device is still not good
Development of SADS (Soil and Air Detector System) to Support Palm Oil Industries in Indonesia
Get PDFThe issue of environmental damage due to the expansion of palm oil plantations in Indonesia has become a global issue. It has often hampered the development of the downstream palm oil industries in Indonesia. The European market was once closed to palm oil and derivative products from Indonesia. In fact, this industry has become a source of income and employment for millions of Indonesians. Therefore, palm oil industry must be supported with sustainable efforts. One of them is developing SADS (Soil and Air Detector System) model. Which is a tool for detecting soil and air environmental conditions around palm oil plantations. The parameters are soil PH, CO2 levels, temperature and humidity, and sunlight. The measurement results from this tool can be accessed and displayed in real-time via the internet. This is research aims to build a smart system as a solution to environmental problems around palm oil plantations. This is useful for knowing and observing the condition of palm oil plantations and as a basis for taking mitigation actions if the condition is in a critical stat
Sentiment Analysis of Dune: Part Two Movie Reviews Using the Naive Bayes Method
Get PDFResearch on films is fascinating because of the profound changes that the development of information and communication technology has brought about in our interactions with and consumption of media content. This study performs sentiment analysis on "Dune: Part Two" movie reviews using the Naïve Bayes method. Review data was collected from IMDb and then processed through several stages such as preprocessing, feature selection with TF-IDF, data splitting, and data mining and evaluation. Naïve Bayes was chosen for its simplicity and ability to handle large datasets effectively. The test results showed a high accuracy rate of 95%, indicating that this model can identify positive, negative, and neutral sentiments well. The use of TF-IDF in feature selection allowed the model to focus on important words, enhancing its sentiment classification ability. This research can provide insights into audience perceptions of the film "Dune: Part Two," which is beneficial for the film industry
Network Coding Schemes and Cooperative Communication Systems Amplify and Forward in Outdoor Environments
Get PDFFading is a phenomenon of decreasing signal strength during transmission, caused by changes in environmental conditions or physical obstacles in the propagation path. Fading can cause interference in signal reception, such as distortion or loss of information, especially in Non-Line of Sight (NLoS) paths, where signals must pass through many paths or obstacles such as buildings, trees, or other objects. To eliminate fading interference, a cooperative communication system is created to reduce the effects of fading in wireless networks. The cooperative communication system works by utilizing other nodes in sending signals to the destination. The relay protocol used in this study is amplify and forward, where the signal to be sent will be amplified and forwarded to the destination by the relay node. A network coding scheme is added to the cooperative communication system to improve network performance. This scheme encodes each piece of information with the XOR technique. The parameters used in measuring the network coding scheme in the cooperative communication system are BER and throughput. Viewed from the BER value, the conventional cooperative communication system has better performance compared to the cooperative communication system with network coding. Cooperative communication system scheme without NC BER value is 0 when the transmit power value is -19 dBm or Gain 32. While for the cooperative communication system scheme with network coding BER value is 0 when transmit power of -9.25 dBm. Throughput system with network coding has increased by 17% compared to the conventional system
A Comparative Analysis of Deep Learning Models for SMS Spam Detection: CNN-LSTM, CNN-GRU, and ResNet Approaches
Get PDFSpam messages have become a growing challenge in mobile communication, threatening user security and data privacy. Traditional spam detection methods, including rule-based and machine learning techniques, are increasingly insufficient due to the evolving sophistication of spam tactics. This research evaluates the effectiveness of advanced deep learning models such as CNN-LSTM, CNN-GRU, and ResNet for SMS spam detection. The dataset used consists of diverse SMS messages labeled as either spam or legitimate (ham), ensuring broad coverage of real-world spam patterns. The study employs a robust ten-fold cross-validation approach to assess the generalization capabilities of the models, measuring performance based on accuracy, precision, recall, and F1 score. The results indicate that ResNet outperformed the other models, achieving an average accuracy of 99.08% and an F1 score of 0.9646, making it the most reliable model for spam detection. CNN-GRU demonstrated competitive performance with a balance between accuracy (98.97%) and computational efficiency, making it suitable for real-time applications. CNN-LSTM, while highly accurate (98.92%), showed a slightly lower recall compared to the other models, indicating a more cautious approach to detecting spam. These findings highlight the potential of hybrid deep learning models in addressing the complexities of SMS spam detection. Future research could focus on optimizing these models for deployment in resource-constrained environments, such as mobile devices, and further exploring the integration of residual connections for more effective spam filtering
Design And Build A Website-Based Accounting Information System With Extreme Programming Methods
Get PDFThe need to use information systems in the digital world is absolutely necessary for a company. With an information system, it will be easier for companies to process data, store data and make decisions. One of the information system implementations that companies need is an accounting information system that regulates cash receipts and disbursements. However, currently there are still many companies that still store their transaction data traditionally using Microsoft Excel and are not yet computerized. Based on data obtained from interviews conducted with a company accountant, it is known that errors occurred when processing data which had an impact on financial reports, namely when inputting data into Microsoft Excel there was still data that was missed, resulting in incorrect financial reports. balance due to errors in recording transactions. By implementing a website-based cash accounting information system, it makes it easier for accountants to collect data in the cash book. This information system was created using the PHP programming language with Laravel as the framework and Extreme Programming as the development method. Extreme Programming was chosen because it requires good and regular communication with the client to adjust system needs. This information system consists of 3 iterations which have a processing time of 32 days. System testing was carried out using User Acceptance Testing with an average percentage obtained of 86.8%. These results can be indicated that the system is running properly and can be understood well by the client or user
Web-based Ukp Public Health Center Services System Using the Waterfall Method
Get PDFBasic health services for the community are community health centers which have Health Service Units (UKP). UKP provides general health services to the community, which has many polyclinics and is interconnected with doctors, patients and administration. So far, in processing service data, there have been difficulties in general polyclinic units when receiving patient information, which is still done by recording it in a book, so there are often errors in information in patient registration services that should be received by the polyclinic that corresponds to the target polyclinic. The storage of patient data based on poly is not yet organized because the files that are stored and archived do not exist in each unit, so that when presenting data and searching you have to confirm who is archiving it, making it difficult for the data or information service department and services to be hampered. The method used in this research is the Waterfall method. This service system uses the waterfall method. The service system provides benefits in inputting and presenting data, searching for patient data such as registering online, then checking medical records to go to the clinic, online medical record results and viewing prescription information, then doctors can meet patients who carry out examinations. This system can provide good benefits and increase effectiveness and efficiency in health services for the surrounding community
Comparative Analysis of Machine Learning Models for Credit Card Fraud Detection in Imbalanced Datasets
Get PDFThis study presents a comprehensive evaluation of various machine learning models for detecting credit card fraud, emphasizing their performance in handling highly imbalanced datasets. We focused on three models: Logistic Regression, Random Forest, and Multilayer Perceptron (MLP), using a dataset comprising 555,719 transactions, each annotated with 22 attributes. Logistic Regression served as a baseline, Random Forest was evaluated for its high accuracy and low dependency on hyperparameter tuning, and MLP was tested for its capability to identify non-linear patterns. The models were assessed using ROC AUC, Matthews Correlation Coefficient (MCC), and precision-recall curves to determine their effectiveness in distinguishing fraudulent transactions. Results indicated that the Random Forest model outperformed others with a ROC AUC of 0.9868 and an MCC of 0.6638, showing substantial superiority in managing class imbalances and complex data interactions. Logistic Regression, although useful as a benchmark, exhibited limitations with a high number of false positives. MLP showed potential but was prone to a significant false positive rate, suggesting a need for further model refinement. The findings highlight the importance of choosing appropriate models and feature engineering techniques in fraud detection systems and suggest avenues for future research in real-time model deployment and advanced algorithmic strategie
Visual Basic.Net Based Library Information System
Get PDFLibraries are important institutions in the world of education as a place to develop knowledge through various book references. In a library, there is generally a very large stock of books. In addition, the number of book loan and return transactions continues to increase over time. Library data processing that still uses conventional methods, namely with notebooks and pens often causes problems, such as the use of a lot of time, data redundancy, and data loss. This research aims to develop a library data management system from a conventional system to a computerized one. The system that the author offers in this study is a visual basic net-based library information system equipped with a MySQL database as the right data storage and Crystal Report as a medium for attaching to print data processing reports that have been done. The system development method used in this research is the Waterfall method. The results of this research are in the form of a library information system that can be used on computer devices with the windows operating system