Journal of Computer Networks, Architecture and High Performance Computing
Not a member yet
473 research outputs found
Sort by
Development of The Project-Based Learning Model In Making Teaching Modules for Courses Multimedia Technology and Animation
Get PDFThe discovery of errors in the delivery of Multimedia Technology and Animation course material is indirectly caused by the implementation of lectures for the course, which should be given for 2 semesters compressed into 1 semester only. The limited learning time prevents some course material from being delivered to students. This limitation was also triggered by the absence of teaching modules that support condensed learning due to the implementation of lectures for 1 semester. Seeing these problems makes the development of a teaching module in the Multimedia and Animation Technology course with Project-Based Learning to support the implementation of lectures a solution that can be done to overcome existing problems. The feasibility test results show that the teaching module is valid. In contrast, the results of the feasibility test by media experts show that 95.14% of the module is very valid, and seen from the results of the feasibility test by material experts show that 97.14% of the module is very valid for use in learning for 1 semester. In the trial involving students, it shows that through the results of individual trials, it can be seen that 94.17% of the teaching modules developed are very feasible to use in the learning process. In addition, through the results of the small group trial, it can be seen that the teaching module is 85.18% very feasible to use, as well as the results of the usage trial show that the teaching module is 87.45% very feasible to use in learning. Based on the data obtained, it can be concluded that the Multimedia and Animation Technology module with Project-Based Learning is very feasible to be used as a reference and in the learning process of Multimedia and Animation Technology courses
User Interface Design Prototype Application Special Onthel Bicycle Tourism in Towilfiets Yogyakarta
Get PDFForeign tourist visits to Yogyakarta, Indonesia have increased in 2022 and 2023 after Covid-19. Many tourists are seeking unique experiences, such as riding on bicycles to enjoy the beautiful scenery and interact with local residents. Towilfiets, a pioneer in onthel bicycle tourism, has been operating in Bantar Hamlet, Kulon Progo for around 10 years. With the growing demand for this activity, Towilfiets needed to innovate their promotion methods, specifically in the digital industry. The development of a user-interface design-based application became crucial to enhance and facilitate the onthel bicycle tourism experience at Towilfiets. The research conducted used a mixed method approach with a phenomenological qualitative method to gather interview data. The prototype method was chosen to allow for intensive and better communication between developers and users. The validation of the questionnaire data was calculated using the Scalable Usage System and received a good score 75 up to score 100 point, indicating acceptable usability. By focusing on user needs and the unique characteristics of tourist destinations, this application aims to increase user engagement and provide relevant and useful information about bicycle tourist attractions in the area. Ultimately, the research aims to develop an innovative and contextualized user interface design application that supports the growth of onthel bike tourism in Towilfiets, located in Dusun Bantar, Kulon Progo, Yogyakarta, Indonesia
Implementing Distribution Requirement Planning in Medan City Health Department's Medicine Distribution System
Get PDFOne of the pharmacy installations located in the Medan city area was tasked with overseeing the management of pharmaceutical inventory for public health facilities, ensuring adequate stock levels, and processing medication-related data, including receiving supplies and LPLPO forms from 41 Public Health Centers. Supervisors at the pharmacy installation were responsible for dispensing medications, while medication managers at the Public Health Centers handled medication requests by completing LPLPO forms and sending them to the installation. Issues arose regarding the accuracy of medication data within its operations, encompassing aspects such as initial stock, receipt of medications, inventory management, medication disbursement (including usage, damaged, or expired items), remaining stock, medication requests, and discrepancies between reported and actual medication quantities. The objective of this study was to establish a web-based data processing system utilizing the Distribution Requirement Planning (DRP) methodology. The DRP approach offered significant insights for forecasting medication stock demands and effectively guided the pharmacy installation in meeting the medication needs of the Public Health Centers. Furthermore, the DRP method shed light on the distribution process costs, thus serving as a valuable tool for enhancing cost efficiency and effectiveness. Results obtained through the DRP approach provided a more efficient distribution process, yielding a notable 93% reduction in expenditure. Additionally, the DRP method successfully anticipated future requirements by employing structured calculations that delineated demand levels experienced by each Public Health Center, accounting for the distinct needs of each facility
Implementation of the Naïve Bayes Algorithm in the SMS Spam Filtering System
Get PDFIn the context of the escalating global spam activity, supported by data from CNN Indonesia in 2021, this research aimed to investigate the root causes and characteristics of this phenomenon. The approach employed in this study involved a series of exploration and classification stages of text messages with the clear objective: to determine whether each message fell into the spam category or not, utilizing the Naïve Bayes method. Additionally, the research aimed to identify the factors influencing the status of text messages, whether they were considered as spam or not. The Naïve Bayes classification method was chosen to facilitate the process of identifying spam-related messages. The dataset used in this research had an 80:20 ratio and was obtained from the Department of Communication and Informatics of Asahan Regency. This data was used to train and test the developed classification model. Data labeling processes were conducted to uncover the factors influencing the status of text messages as spam or non-spam. The research findings indicated that issues related to spam and non-spam messages remained a serious concern. The high accuracy rate, reaching 92%, achieved by the Naïve Bayes method in classifying messages, demonstrated the effectiveness of the method in detecting spam messages
Performance Comparison of CART And KNN Algorithms for Analyzing Early Predictions of Mental Health
Get PDFCurrently, mental health is an unresolved mental health problem both at the national and international levels. Mental health disorders are conditions where a person has difficulty in adjusting to the conditions around them. Mental Health is an important aspect of overall health. Efforts to maintain and improve it can help a person achieve better well-being in everyday life. This research aims to conduct Early Prediction Analysis related to mental health problems experienced by students by measuring the accuracy level of the analysis. This research was conducted using the CART (Classification and Regression Trees) and KNN (K-Nearest Neighbor) algorithms with a set of Mental Health Datasets consisting of 11 attributes and 101 data. The data is processed using the Weka Application and the accuracy results of each algorithm are obtained, amounting to 94.0594% for the CART Algorithm and 91.0891% for the KNN Algorithm. From this achievement, it can be concluded that the performance of the CART and KNN algorithms falls into the Excellent Classification category. Judging from the accuracy obtained, the CART algorithm has a higher accuracy value than the KNN algorithm, so the CART algorithm has a high performance for analyzing early prediction of mental health of students who do not take steps in seeking mental health support
Mobile Platform for Building Applications at the Integrated Services Office Medan City
No full textThe advancement of computer technology has developed rapidly and has been applied in various aspects of life. At that time, computers were considered one of the most efficient tools in supporting technological development. At the Office of Investment and One-Stop Integrated Services (OI-OIS) in Medan City, the process of applying for Building Permits (BP) was still conducted manually and had not been computerized, resulting in slow and inefficient licensing processes. Applicants were required to fill out forms manually and deliver physical documents to the village and sub-district offices, which extended processing times. Furthermore, application reports were often piled up, hindering prompt and accurate handling. The lack of efficiency in managing applicant data further exacerbated the situation and slowed down the completion of applications. Therefore, an integrated digital system was needed to expedite and facilitate the submission and management of IMB applications. This research aimed to develop an Android-based Information System for Building Permit Applications at DPMPTSP in Medan City using the R&D (Research and Development) method. It was hoped that this application would make it easier for staff to manage IMB application data. The research results indicated that the development of the Android-based Information System for Building Permit Applications successfully addressed the issues encountered in the previously manual IMB application process. This application expedited and simplified the filling out and submission of applications, eliminating the need for applicants to deliver physical documents. Additionally, the management of applicant data became more efficient and computerized, reducing the backlog of reports and speeding up the verification process
Analysis of Basic Testing Using Smoke Testing in Asset Inventory Information Systems
Get PDFThe creation or development of a system must go through a testing phase with the aim that before the system is implemented by the user, bugs or errors can be detected at the start. The PGRI Madiun University Asset Inventory and Documentation Unit (UIAD) is currently building and developing an information system for managing inventory, asset and document data. So far, data management still uses manual recording on paper forms. This creates a problem of inconsistency between data in the field and data in the unit. To improve the quality of the UIAD information system so that it is more optimal, it is necessary to carry out basic testing with smoke testing to ensure that the basic features function properly. The aim of this research is to test the basic functionalities of the UIAD information system with smoke testing to provide recommendations for improvements in order to improve the quality of the UIAD information system. Testing is carried out manually with 3 types of test cases, namely login test case, master test case and asset test case. The test results show that the login test case passed 100%, the master test case passed 100%, and the asset test case passed 80%. Based on the test results, it is very important to carry out smoke testing on the basic functions of the system before the system is used so that bugs or errors can be found so that corrective action can be taken more quickly
Use of RESNET-50 Neural Network in Diagnosing Diseases Mango Leaves
Get PDFUsing a state-of-the-art convolutional neural network, specifically RESNET-50, for disease diagnosis on mango leaves is the focus of this research. The end goal is to develop a trustworthy method of mango plant disease detection using leaf image analysis. The approach used comprised gathering a sizable dataset encompassing a range of mango leaf diseases. Afterward, a classification system was developed by training the RESNET-50 model on image data. The system is able to learn extraordinarily intricate and profound visual patterns in pictures of mango leaves thanks to RESNET-50's deep and complicated architecture, which improves feature extraction. With a Test Accuracy of 99.16% and a Test Loss of only 0.4332, the results demonstrate a very reliable system. This impressive level of precision verifies that the system is capable of correctly distinguishing and categorizing mango leaf diseases. Consequently, this case demonstrates promising agricultural applications of the RESNET-50 model and offers a dependable and effective means of disease detection in mango plants. This study adds to the growing body of knowledge that can aid agricultural professionals and farmers in the early detection of disease symptoms on mango leaves, allowing for the prompt implementation of preventative measures. These findings also have broader implications, such as the potential for better agricultural productivity and management brought about by the use of comparable technologies for disease analysis in different crops
Comparative Analysis of Machine Learning Algorithms for Detecting Fake News: Efficacy and Accuracy in the Modern Information Ecosystem
Get PDFIn an era where the spread of fake news poses a significant threat to the integrity of the information landscape, the need for effective detection tools is paramount. This study evaluates the efficacy of three machine learning algorithms—Multinomial Naive Bayes, Passive Aggressive Classifier, and Logistic Regression—in distinguishing fake news from genuine articles. Leveraging a balanced dataset, meticulously processed and vectorized through Term Frequency-Inverse Document Frequency (TF-IDF), we subjected each algorithm to a rigorous classification process. The algorithms were evaluated on metrics such as precision, recall, and F1-score, with the Passive Aggressive Classifier outperforming others, achieving a remarkable 0.99 in both precision and recall. Logistic Regression followed with an accuracy of 0.98, while Multinomial Naive Bayes displayed robust recall at 1.00 but lower precision at 0.91, resulting in an accuracy of 0.95. These metrics underscored the nuanced capabilities of each algorithm in correctly identifying fake and real news, with the Passive Aggressive Classifier demonstrating superior balance in performance. The study's findings highlight the potential of employing machine learning techniques in the fight against fake news, with the Passive Aggressive Classifier showing promise due to its high accuracy and balanced precision-recall trade-off. These insights contribute to the ongoing efforts in digital media to develop advanced, ethical, and accurate tools for maintaining information veracity. Future research should continue to refine these models, ensuring their applicability in diverse and evolving news ecosystems
Decision Support System for the Presidential Election of the Student Executive Board Using the Multi-Factor Evaluation Process Method
Get PDFStudent Executive Board is a student organization or executive institution found in every tertiary institution and can represent the existence of a tertiary institution. The student Executive Board is headed by the Student Executive Board President, who is assisted by the Secretary-General, three Coordinating Ministers, and several ministries that represent student needs. In carrying out its function as a forum for student aspirations to make changes (agents of change) in paradigm, emotional, intellectual, and religious values, the Student Executive Board requires student candidates who are in synergy with their vision and mission. The Student Executive Board Presidential Election is usually held every year. A decision support system (DSS) was built by implementing the Multi-Factor Evaluation Process (MFEP) method to easily and efficiently elect the Student Executive Board President quickly and efficiently. The criteria used are communication skills (C1), leadership attitude (C2), vision and mission (C3), skills (C4), and organizational experience (C5). Each criterion is weighted where the total weight of all criteria equals 1. Next, calculate the evaluation weight value (EW), total evaluation weight (TEW), and ranking. The research results show that alternative 7 (A7), with the highest score of 4.35, is the student candidate with the top ranking, meaning A7 is the most recommended to be elected as President of the Student Executive Board. With this DSS, we can provide appropriate recommendations for Student Executive Board Presidential candidates and assist universities and students in carrying out the selection process quickly and efficiently