Journal of Computer Networks, Architecture and High Performance Computing
Not a member yet
473 research outputs found
Sort by
Prediction of DHF Disease Using Bagging Algorithm with Decision Tree C4.5
Get PDFDengue Fever (DHF) continues to represent a significant public health threat in Indonesia and other tropical regions, with an annual increase in the number of reported cases. The primary aim of this study is to develop a predictive model for DHF by integrating the Bagging technique and the Decision Tree C4.5 algorithm. The goal is to improve prediction accuracy by incorporating key environmental factors such as temperature, humidity, and rainfall. The research adopts a quantitative methodology with a descriptive approach, using publicly available datasets from data.mendeley.com and conducting the analysis using RapidMiner software. The findings of the study demonstrate that the proposed model is highly effective in accurately predicting and classifying DHF cases, achieving significant precision. In addition to this, the model is successful in identifying important patterns and trends linked to the disease's occurrence. These results underscore the efficacy of combining Bagging and Decision Tree C4.5 as a robust tool for detecting and forecasting DHF outbreaks. The research contributes substantially to the field of data-driven prediction models, offering valuable insights for health agencies to develop more effective and proactive strategies for disease prevention. For future research, it is recommended that additional factors such as genetic and medical data be considered, along with the application of triangulation methods to improve the analysis's validity, scope, and overall robustness. This approach would enable a more comprehensive understanding of DHF and its predictive modeling.Keywords: DHF Prediction; Bagging; Decision Tree C4.5; Machine Learning; Data Minin
Systematic Literature Review: Predicted Color Output in UI/UX Design Using Machine Learning
Get PDFAn attractive user interface (UI) design is greatly influenced by the selection of appropriate colors, but the selection process tends to be subjective. To address this challenge, this study was conducted to identify commonly used machine learning techniques and evaluate their effectiveness in recommending colors based on RGB and HSL features. The method used was a Systematic Literature Review (SLR) of 39 articles published between 2020 and 2025. The study was conducted through three main stages, namely planning, implementation, and reporting. The review results show that approaches such as K-Means are widely used in the dominant color extraction stage, while classification algorithms such as Support Vector Machine (SVM), Artificial Neural Network (ANN), and Random Forest are applied for color prediction and recommendation. Random Forest is one of the models that shows superior performance, especially in terms of prediction stability and the ability to handle large numbers of variables. The model development process usually begins with color quantization, followed by data labeling and model training. Based on these findings, it can be concluded that Random Forest is a reliable model in color recommendation systems, especially when supported by good data preprocessing stages and proper parameter tuning
Interactive Multimedia Website For Promoting Mumbul Sangeh Park As A Tourist Destination
Get PDFMumbul Sangeh Park in Bali has experienced low visitor turnout, primarily due to inadequate promotional strategies. To address this issue, a study was conducted to develop a modern, interactive promotional website aimed at increasing public awareness of the park’s historical significance and unique attractions. The website development followed a structured Software Development Life Cycle (SDLC) approach, specifically utilizing the waterfall model. The system was implemented using the PHP programming language, supported by the Laravel framework and a MySQL database. Functional verification was performed using black box testing to ensure all system features operated as intended. The resulting website is fully functional, responsive, and delivers comprehensive information. It also includes an intuitive administrative panel that enables park administrators to easily manage content updates, including photo galleries, news, and visitor information. The system represents a strategic digital initiative to enhance the visibility and reputation of Mumbul Sangeh Park in the era of digital tourism
Comparative Analysis of Yolov11 and Mask R-CNN Models for River Water Level Detection
Get PDFFlooding is one of the most frequent natural disasters in Indonesia, particularly in densely populated areas such as urban regions. The main cause is the delayed response in anticipating rising river water levels. One contributing factor is the continued use of manual river water monitoring systems. However, these systems often face challenges under various lighting and weather conditions. This study presents a comparison of two segmentation models, YOLOv11 and Mask R-CNN, for river water level detection. These models are evaluated for their application in real-time water level monitoring systems for dams and rivers under diverse lighting conditions. Data was gathered from publicly available sources, including river monitoring CCTV footage and social media content related to river activities, followed by annotation for model training. The YOLOv11 model, implemented using the Ultralytics framework and PyTorch library, achieved a mean Average Precision (mAP) at IoU (Intersection over Union) 50-95 of 99.657% and recall of 99.930%, demonstrating exceptional detection accuracy. The Mask R-CNN model, developed with Detectron2, attained an Average Precision (AP) at IoU 50-95 of 98.620% and a recall of 99.200%, also exhibiting high accuracy. Both models were tested in real-time scenarios, where they accurately detected water-level objects, although challenges arose under complex environmental conditions such as low light or water turbidity. To further enhance model performance, future work will focus on incorporating diverse environmental data and optimizing model parameters. In conclusion, YOLOv11 model offers higher accuracy and better resource efficiency, making it more suitable for real-time water level monitoring applications
Web-Based Attendance Information System At Diskominfosantik Bekasi District With Prototype Method
Get PDFThe rapid development of information technology has encouraged government agencies to utilize digital systems to improve operational efficiency and effectiveness, including in managing employee attendance data. This study aims to design and implement a Web-Based Attendance Information System at the Department of Communication, Informatics, Statistics, and Encryption (Diskominfosantik) of Bekasi Regency. The system was developed using the prototype method, allowing for a gradual design process involving users directly in evaluation and development. The main features of the system include login authentication for administrators and employees, barcode scanning for attendance validation, GPS data integration to verify attendance locations, digital leave requests, and real-time attendance data management and reporting. System testing was conducted using the black box testing method across various scenarios to ensure all functions operated as expected without errors. The system design is also supported by use case and class diagrams that illustrate the workflow and relationships between entities in the system. The results of the study indicate that the web-based attendance information system can improve recording accuracy, accelerate the attendance data recap process, and support transparency in personnel management. Thus, the system has the potential to serve as a model for other government agencies in digitizing employee attendance processes
Application of Google cloud computing for web-based library information systems at Bahayangkara University Surabaya
Get PDFLibraries are essential in academic work as they expose people to structured, easily procurable information. However, the majority of schools, including Bhayangkara University Surabaya, still face challenges in managing and storing library information because local or manual systems are substandard. The goal of this project is to deploy and test the effectiveness of Google Cloud Computing technologies, such as Google Cloud Storage, Google Cloud SQL, and Google Compute Engine, on a website-based library information system. We adopted a quantitative approach by performing experiments and system testing, i.e., black-box testing, access speed testing, and heavy load resistance testing. The result of the implementation is massive benefits, including a response time of 2 seconds on average, stability with 500 users at the same time, and storage efficiency at just 30% of the original size. Other colleges can have an example that they can use to make a change to a cloud-based digital library from this research. This also helps create digital library information systems that are technology-centered and dependable
Design and Implementation of a Waste Bank Application and Volunteer Platform for Marine Waste Reduction on the Southern Coast of Java
Get PDFMarine waste along the southern coast of Java, Indonesia, presents a critical environmental issue caused by ocean currents, tourism, and local industrial activities. This accumulation disrupts marine ecosystems and threatens the livelihoods of coastal communities. The lack of accessible and efficient waste management systems exacerbates the problem, highlighting the need for innovative solutions to foster community involvement and environmental awareness.To address this challenge, this study introduces a waste bank application prototype designed specifically for the region using a design thinking approach. This methodology involved five stages: Empathize, Define, Ideate, Prototype, and Test. Data collection included interviews and surveys with local stakeholders, which identified key needs such as waste accumulation tracking, incentive-based participation, volunteer coordination, and environmental education for children. These findings guided the development of features like a contribution-based incentive system, event coordination, and a game to teach waste separation to younger users.The prototype underwent independent testing to evaluate its usability and effectiveness. Results demonstrated that the application successfully enhanced community engagement, offering a user-friendly platform that combines waste management with education. The inclusion of real-time tracking and rewards motivated active participation, while the educational game increased awareness among children.This study underscores the importance of collaborative, user-centered technology in addressing environmental challenges and provides a scalable model for sustainable waste management in coastal regions
Combination of Regression and ARIMA Methods ( Reg – ARIMA ) Stock Price Prediction Model
Get PDFThis research is motivated by the limitations of the ARIMA method, which is only suitable for short-term forecasting and specific periods. Therefore, a combination of Regression and ARIMA methods (Reg- ARIMA) is introduced to predict stock prices over a longer period. The purpose of this study is to implement a combination of Regression and ARIMA methods to build a stock price prediction model. The research methodology involves using Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) to measure the accuracy of the generated prediction model. The study results indicate significant variations in MAPE and RMSE values among different stocks, reflecting the performance and liquidity of those stock markets. For example, stocks such as ITMG and UNTR show strong performance, while stocks with low closing values may carry higher risks or slower growth. In conclusion, the Reg-ARIMA combination method is effective in extending the range of stock price forecasting, providing a more accurate alternative compared to using only the ARIMA method. This suggests that this hybrid approach can be used to enhance investment decision-making strategies in the stock market
Rainfall Prediction in Jayapura City Area Using Long Short-Term Memory
Get PDFJayapura, one of Indonesia’s major fishing cities, relies heavily on accurate weather predictions to ensure the safety of its fishermen, particularly due to its significant tuna and skipjack production. This study aims to improve rainfall forecasting in Jayapura using a Long Short-Term Memory (LSTM) model, a type of artificial neural network designed for time series prediction. Accurate rainfall forecasts are crucial for reducing the risks fishermen face at sea due to sudden weather changes. Daily data from the Meteorological Station in Dok II Jayapura was collected and processed to train the LSTM model, incorporating variables such as TAVG (average temperature), RH_AVG (average relative humidity), FF_AVG (average wind speed), Pressure (air pressure), and Wind_Gust (wind gust). The model’s performance was evaluated using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE), yielding low values of 0.0542 and 0.0847, respectively, indicating high prediction accuracy. The MAE reflects the average magnitude of errors, while the RMSE highlights the model’s sensitivity to larger deviations, both supporting the reliability of the LSTM approach. The findings demonstrate that LSTM models can effectively forecast rainfall in Jayapura, providing valuable information that helps fishermen plan their activities more safely and efficiently. The study concludes that LSTM is a robust tool for rainfall prediction, and the inclusion of additional meteorological variables has proven to enhance accuracy. Further research is recommended to explore other factors to improve prediction reliability
Credit Risk Analysis on Motor Vehicle Financing Using the Kealhofer Merton Vasicek Model (KMV)
Get PDFThe development of the automotive sector in Indonesia continues to show significant growth, in line with the increasing demand for motor vehicles, both cars and motorcycles. Although it has great potential, the vehicle financing sector is not without challenges, particularly related to credit risk. The Kealhofer Merton Vasicek (KMV) model will be suitable for calculating vehicle credit risk because it can predict default (failure to pay) when the borrower reaches the end of the loan term. The objective of this research is to apply the KMV model to calculate the Expected Default Frequency (EDF) value and determine the minimum credit risk. From the analysis and estimation results, the time-to-maturity equity value for motor vehicles was obtained at Rp9.616.709.886 and the time-to-maturity liability value at Rp1.865.460.114, while for cars, the equity value was obtained at Rp2.057.843.305 and the time-to-maturity liability value at Rp468.544.695. Additionally, the Expected Default Frequency (EDF) value for motor vehicles was obtained at 4,26% and the EDF value for cars at 0,01%. The results indicate that the likelihood of default experienced by Adira Finance is low, especially for cars. Therefore, Adira Finance can be stated to have sufficient capital, so the likelihood of default is not high