Journal of Intelligent Decision Support System (IDSS)

Application of fuzzy logic method to determine the level of damage to buildings in elementary schools

2024-03-22T14:11:42+00:00

This study aims to provide information effectively and efficiently about the condition of damage to elementary school buildings to assist schools in determining decisions about buildings in schools that must be repaired immediately. In research, the application of fuzzy logic methods to assess the extent of damage to elementary school buildings will depend heavily on the research design, processes, and data used to develop and test fuzzy logic models. This approach involves reviewing, synthesizing, and evaluating a variety of literature sources, including scientific journals, books, conference papers, articles, and other written sources. It is important to consider that the value and novelty of a study can be assessed by the scientific community and practitioners in related fields, and the results will depend on the ability of that research to make a meaningful contribution. The value of applying fuzzy logic methods to determine the extent of damage to elementary school buildings will provide a more complete picture of the contribution of such research to science and practice in the field concerned.

Machine learning algorithm-based decision support system for prime bank stock trend prediction

2024-03-16T11:12:59+00:00

In the complex landscape of financial markets, predicting bank stock trends is a critical aspect that supports more accurate investment decision-making. This study aims to develop and evaluate machine learning algorithms—Random Forest, Support Vector Machine (SVM), and Artificial Neural Network (ANN)—for predicting the trends of major bank stocks in Indonesia using the IDX-PEFINDO dataset from January 1, 2020, to December 31, 2023. The adopted methodology includes collecting historical data, initial processing, feature selection, and training and validating models using evaluation metrics such as Accuracy, Precision, Recall, F1-Score, MAE, and RMSE. Results indicate that although no single algorithm is dominant, SVM and ANN perform better within the given data context. This research underscores the importance of a tailored approach to maximize the potential of machine learning algorithms in stock prediction, providing new insights into developing decision support systems for bank stock investments. This study implies that it recommends the integration of broader economic indicators and the exploration of advanced machine-learning techniques to enhance stock prediction accuracy in the future.

Application of computer vision for face recognition using viola jones algorithm method

2024-03-19T09:33:05+00:00

This research aims to develop a facial recognition system using computer vision technology by applying the Viola-Jones algorithm method. The main focus of this research is to improve accuracy and efficiency in face identification under various lighting conditions and face orientations. The Viola-Jones algorithm, known for its real-time object detection, was chosen for its efficiency in quickly identifying critical facial features. Through testing of various face datasets, the results showed that the system developed was able to recognize faces with a high level of accuracy, even in conditions of non-optimal lighting and various facial poses. The novelty of this research lies in the optimization of the parameters of the Viola-Jones algorithm to improve facial recognition performance, as well as its application in challenging dynamic environments. These findings make a significant contribution to the field of computer vision and facial recognition, offering more effective and efficient solutions for security and surveillance applications, as well as interactive applications that require fast and accurate facial identification.

Regional function-based land use balance

2024-03-16T05:27:37+00:00

The balance between the availability of land and the need for control, use and utilization of land based on regional functions is important as a reference for sustainable development directions and maintaining environmental sustainability. Imbalance in land use affects the direction of development and environmental sustainability. For this reason, it is necessary to conduct an analysis to determine the balance between land availability and land needs within a certain period of time through the preparation of a land use balance based on regional function directions. This research aims to analyze the balance between land availability and land use as well as the suitability of land use for the direction of regional functions. The method in this research uses a multi-temporal approach by utilizing remote sensing technology and geographic information systems. The overlay process was carried out to see the land change of Baubau city and see the level of conformity of existing land use with the direction of regional functions. The results show that the 2016 land use balance has the highest assets in forest land use of 21097.66 Ha and the 2020 land use balance has the highest liabilities in forest land use of 20959.56 Ha. The trend of land change in 2016-2020 is the change of forest, open land, mixed gardens, settlements and shrubs/shrubs. The level of conformity of existing land use with the direction of the function of the area is very high with a percentage level of suitability of 90.83% and a level of incompatibility of 9.17%.

Application of the viola-jones algorithm method to recognize faces of Stmik Tegal students

2024-03-21T14:19:33+00:00

This study examines the application of the modified Viola-Jones algorithm for student facial recognition at STMIK YMI Tegal, aiming to improve the efficiency and safety of the student attendance system. By adapting the algorithm to address the challenge of facial recognition accuracy from different angles and lighting conditions, a quasi-experimental quantitative design involved collecting data through photographic sessions with student subjects, followed by preprocessing to improve the quality of the analysis. The modification was evaluated for its ability to handle variations in facial and lighting conditions, showing significant improvements with 60% accuracy and precision, recall, and an F1-score of 71.43%. These findings demonstrate the effectiveness of the modification in improving facial recognition, potentially contributing significantly to attendance management and safety practices in educational settings. This research not only strengthens the existing literature.

Application of computer vision techniques to detect diseases and pests of chili plants

2024-03-14T07:11:58+00:00

This research aims to develop a disease and pest detection system in chili plants using computer vision techniques. In this study, deep learning methods, especially Convolutional Neural Networks (CNN), were applied to identify and classify various types of diseases and pests that often attack chili plants. The data used included images of chili leaves infected with various diseases and pests, which were then trained in CNN models to recognize certain patterns that indicate the presence of infection. The results showed that the developed system was able to detect and classify diseases and pests in chili plants with a very high degree of accuracy. The novelty of this research lies in the use of computer vision techniques combined with sophisticated deep learning algorithms to automatically detect diseases and pests, which were previously done manually by farmers or agricultural experts. These findings make an important contribution to improving efficiency and effectiveness in chili crop health management, offering innovative solutions to support agricultural sustainability through the use of advanced technology.

Transformation of land use change in Cilegon City 2017-2023 using passive sensor satellite imagery

2024-03-14T08:58:47+00:00

Transformation Land change that occurred in Cilegon City is a phenomenon that involves a significant transformation in urban land use over the last few years. Land is a natural resource that has an important function to meet various human needs. This change was caused by several factors, one of which was rapid population growth. This research involves analyzing satellite imagery from several different time periods to track the evolution of land use in Cilegon City. From the results of observations made, it is known that there is a reduction in green land in Cilegon City. Where in each period of the year there are changes in green land which is increasingly decreasing. This reduction was caused by several factors, namely the transfer of land function from greenland to housing and the occurrence of fires on the green land.

Application of nearest neighbor interpolation method and naïve bayes classifier for identification of bespectacled faces

2024-03-20T12:33:30+00:00

Facial identification has become necessary in the era of advanced technology, especially in security and human-computer interaction. However, accessories such as glasses often complicate the identification process. This research aims to develop a facial identification system that can recognize bespectacled individuals with high accuracy, overcoming the limitations of conventional facial recognition technology. The method combines nearest neighbor interpolation to improve image quality and Naïve Bayes classification to distinguish between bespectacled and non-spectacled faces. The results showed that the developed model effectively identified bespectacled subjects with a high recall rate, although accuracy and precision still needed improvement. The implications of this research are significant for the field of biometric security and facial recognition, offering new solutions for more inclusive and adaptive facial recognition systems and opening up opportunities for further research in method optimization and dataset quality improvement.

Application of fuzzy expert system method for early detection of dengue fever

2024-03-22T14:33:27+00:00

The application of the Fuzzy Expert System method in the early detection of dengue fever offers a promising approach to improve diagnostic accuracy. This study aims to develop a system that can overcome the diversity of dengue fever symptoms and uncertainty in the diagnosis process. Using medical record data of patients who have confirmed DHF, the study designed fuzzy rules for symptom evaluation, resulting in more precise diagnostic outputs. The results indicate the system's success in identifying dengue cases with high sensitivity and good positive predictive value. These findings confirm the importance of FES technology in clinical practice, especially for controlling and preventing dengue fever in endemic areas. Continued research will test this system in a broader clinical scenario to ensure its effectiveness and practicality in diverse medical environments.

Classification of fresh chicken meat and tainted chicken meat using naive bayes classifier algorithm

2024-03-20T05:07:37+00:00

This research discusses the classification of fresh and tainted chicken meat using the Naive Bayes Classifier (NBC) algorithm based on Gray Level Co-occurrence Matrix (GLCM) feature extraction, with the aim of developing an efficient and accurate classification method. This research aims to utilize image processing and machine learning technologies to distinguish fresh chicken meat from tainted ones, which is crucial for the food industry. The research methodology involved the use of GLCM for texture feature extraction from chicken meat images, with the implementation of the NBC model through RapidMiner, offering an intuitive and efficient approach. The results showed the success of the model in achieving 80% accuracy, with an average precision of 81.25%, recall of 80%, and F1-score of 80.62%, confirming its ability in chicken meat classification. The integration of GLCM and RapidMiner in the application of NBC not only improves accuracy and objectivity in chicken meat classification but also provides a foundation for the wider application of machine learning techniques in ensuring food safety and consumer satisfaction

Web & android based CCTV maintenance application at PT. CCTV Palace

2024-03-21T22:17:46+00:00

PT. Istana CCTV operates in the field of sales and services. Products sold include finger print, CCTV, access doors, hotel locks and so on. The services provided are product installation, maintenance and repairs. The problem that occurred was PT. Istana CCTV is unable to respond to customers' CCTV maintenance requests because the number of technicians is limited. On the other hand, PT. CCTV Palace often complains that CCTV maintenance requests are not immediately contacted and have to wait for the maintenance schedule. Therefore, an appropriate method is needed to increase sales turnover so that PT. CCTV Palace is making progress. The application of the FCFS method is very appropriate in Customer CCTV Maintenance services. Consumers who are the first to book CCTV Maintenance will be served first. The FCFS method is a scheduling algorithm with the characteristics of prioritizing processes that are submitted first, first come first served. So, the process that arrives first will be executed first.