IJNMT (International Journal of New Media Technology) https://ejournals.umn.ac.id/index.php/IJNMT <div style="text-align: justify;"><strong>IJNMT (International Journal of New Media Technology)&nbsp;</strong>is scholarly open access, peer-reviewed&nbsp;and interdisciplinary journal focusing on theories, methods,&nbsp;and implementations of new media technology. Topics include, but not limited to digital technology for creative industry, infrastructure technology, computing communication and networking, signal and image processing, intelligent system, control and embedded system, mobile and web based system, and robotics. IJNMT is published annually by Information and Communication Technology Faculty of Universitas Multimedia Nusantara in cooperation with UMN Press.</div> <div style="text-align: justify;"><strong>Online ISSN :&nbsp;<a title="Online ISSN IJNMT" href="http://issn.pdii.lipi.go.id/issn.cgi?daftar&amp;1461222309&amp;1&amp;&amp;">2581-1851</a><br></strong><strong>Printed&nbsp;ISSN : <a title="Print ISSN IJNMT" href="http://issn.pdii.lipi.go.id/issn.cgi?daftar&amp;1388639043&amp;1&amp;&amp;">2355-0082</a>&nbsp;&nbsp;</strong></div> <div style="text-align: justify;">&nbsp;</div> Universitas Multimedia Nusantara en-US IJNMT (International Journal of New Media Technology) 2355-0082 <p>Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a <strong>Creative Commons Attribution-ShareAlike International License (CC-BY-SA 4.0)</strong> that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.</p> <p>Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.</p> <p><strong>Copyright without Restrictions</strong></p> <p>The journal allows the author(s) to hold the copyright without restrictions and will retain publishing rights without restrictions.</p> <p>The submitted papers are assumed to contain no proprietary material unprotected by patent or patent application; responsibility for technical content and for protection of proprietary material rests solely with the author(s) and their organizations and is not the responsibility of the IJNMT or its Editorial Staff. The main (first/corresponding) author is responsible for ensuring that the article has been seen and approved by all the other authors. It is the responsibility of the author to obtain all necessary copyright release permissions for the use of any copyrighted materials in the manuscript prior to the submission.</p> The Effect of Using the Al-Mumtaz Application on Student Learning Outcomes UIN Mahmud Yunus Batusangkar https://ejournals.umn.ac.id/index.php/IJNMT/article/view/3614 <p><em>Abstra</em><em>ct</em>— In today's digital era, the utilization of technology in the learning process is becoming increasingly important. Online learning applications such as Al-Mumtaz have the potential to overcome the limitations of conventional learning methods and increase student interest and motivation to learn. However, the effect of using the Al-Mumtaz application on student learning outcomes at Mahmud Yunus State Islamic University Batusangkar has not been widely studied. This study aims to identify and analyze the effect of using the Al-Mumtaz application on student learning outcomes at UIN Mahmud Yunus Batusangkar and provide evidence-based recommendations regarding the effectiveness of digital learning applications. This study used a quantitative pre-experiment design with a sample of Arabic language education students who used the Al-Mumtaz application. Data were collected through initial and final tests, and analyzed using validity, reliability, normality, homogeneity, and paired t tests. The analysis showed that 10 out of 15 questions were valid and reliable. The data were normally distributed and met the assumption of homogeneity of variance. &nbsp;The paired t-test revealed a significant mean difference between the pre-test (62.50) and post-test (89.00) scores after the use of Al-Mumtaz application, with an increase of 23.50.The use of Al-Mumtaz application in Arabic language learning at UIN Mahmud Yunus Batusangkar provides significant results.This study confirms the positive effect of Al-Mumtaz application on student learning outcomes and highlights the importance of technology in improving the effectiveness of learning in the academic environment.</p> Rahmat Hidayat Munirul Abidin Danial Hilmi ##submission.copyrightStatement## http://creativecommons.org/licenses/by-sa/4.0 2025-01-24 2025-01-24 11 2 43 48 10.31937/ijnmt.v11i2.3614 The Effect of Video Games Towards the Students' Academic Performance https://ejournals.umn.ac.id/index.php/IJNMT/article/view/3638 <p>Video games have remained popular ever since the video game industry boom in the 1980s. It has remained popular, especially for children, teenagers, and adults. However, video games have also sparked controversies among the population. Concerns have been raised regarding the harmful effects of video games, particularly regarding addictions. Video games have been accused by many of being the cause of lowering academic performance. Therefore, this study aims to explore the relationship between video games and the overall academic performance of university students in depth. We applied several statistical methods using a questionnaire, which 100 university students filled out. The insights uncovered from this study may help determine if and how much video games affect the academic performance of university students.</p> Yohanes Brian Caesaryano Lala Raymond Sunardi Oetama Kimberly Lvina ##submission.copyrightStatement## http://creativecommons.org/licenses/by-sa/4.0 2025-01-24 2025-01-24 11 2 49 55 10.31937/ijnmt.v11i2.3638 Approach Convolutional Neural Network LeNet-5 for Interactive Learning of Korean Syllables (Hangul) https://ejournals.umn.ac.id/index.php/IJNMT/article/view/3705 <p>The increasing popularity of South Korean culture among Indonesian society has led to a growing interest in gaining a deeper understanding of the country, including a desire to master the Korean language. However, learning the Korean alphabet (hangul) often presents challenges due to its characters being unfamiliar to the Indonesian people. Therefore, engaging and interactive learning media are needed to assist in the learning process. Within this endeavor, a learning website called Learn Hangul was developed, focusing on two main features: learning hangul characters and their arrangement, as well as practicing writing syllables using Korean letters. This website was developed using the Convolutional Neural Network (CNN) LeNet-5 to facilitate learning, with black box testing results indicating good functionality. Model performance evaluation yielded satisfactory values, with model accuracy at 89.2%, precision at 89.7%, recall at 88.8%, and an F1-score of 89.2%. Direct testing with users also showed a high success rate, with 80% of respondents experiencing an increase in their knowledge of Korean characters (Hangul) after trying to learn them on the Learn Hangul website. Thus, the Learn Hangul website serves as a useful learning tool for those interested in studying the Korean alphabet (hangul).</p> Vasyilla Kautsar Al Fitra Yudha Arvita Agus Kurniasari Aji Seto Arifianto Faisal Lutfi Afriansyah ##submission.copyrightStatement## http://creativecommons.org/licenses/by-sa/4.0 2025-01-24 2025-01-24 11 2 56 67 10.31937/ijnmt.v11i2.3705 Ensemble Learning - Random Forest Algorithm to Classify Obesity Level https://ejournals.umn.ac.id/index.php/IJNMT/article/view/3709 <p>Obesity is one of the serious global health problems caused by excessive accumulation of body fat. According to the World Health Organization (WHO), the prevalence of obesity has tripled in the last 40 years, with 650 million out of 1.9 billion overweight adults suffering from obesity. Obesity is a non-communicable disease that increases the risks of more dangerous diseases, such as heart disease and cancer. Therefore, early detection of obesity level is crucial. Currently, Body Mass Index (BMI) serves as a measurement indicator, but it tends to overestimate obesity for those with high muscle mass and vice versa, making it ineffective as it only relies on height and weight, without considering body composition and daily activities. To solve this, the best Random Forest model has been developed, selected based on the results of model selection after comparisons using feature selection and hyperparameter tuning. The selected model successfully improved accuracy by 1.4%, which then implemented into a web-based system to classify obesity levels. Evaluation of the model resulted in Precision, Recall, F1-Score, and Accuracy of 97%, 97%, 97%, and 96.8% respectively. Based on these evaluation results, it can be concluded that this system is highly effective in classifying obesity levels.</p> Tesalonika Abigail Marlinda Vasty Overbeek ##submission.copyrightStatement## http://creativecommons.org/licenses/by-sa/4.0 2025-01-24 2025-01-24 11 2 68 77 10.31937/ijnmt.v11i2.3709 IMPLEMENTATION OF HEURISTIC EVALUATION METHOD FOR EVALUATION AND RECOMMENDATIONS UI/UX DESIGN IMPROVEMENTS ON THE CINEPOLIS WEBSITE https://ejournals.umn.ac.id/index.php/IJNMT/article/view/3736 <p><em>UI/UX is one of the most important elements of a website. One of the tasks of UI/UX is to make it easier to achieve a goal that the user wants. Cinépolis is a cinema that has been established in Indonesia since 2014. Cinépolis then launched its own website to make it easier for users to view movie information and order tickets. Based on the questionnaires that have been distributed and calculated using the System Usability Scale or SUS method, the Cinépolis website gets a score of 54.03 and is below the SUS standard of 68. The predicate obtained from the Cinépolis website is grade D with the predicate Poor. Heuristics are methods for finding interface problems to improve usability and user experience. The joint evaluation of 2 evaluators showed that there were 20 problems on the Cinépolis website based on 10 heuristic principles, while the evaluation of the Cinépolis website improvement prototype with 1 other evaluator found 5 problem findings based on 10 heuristic principles on the Figma prototype. The prototype that has been implemented gets a final score of 88.01 using the SUS calculation based on the questionnaire data that has been distributed. The final predicate obtained from the Cinépolis repair website is grade A with the predicate of Excellent.</em></p> Cindy Aristawati Fenina Adline Twince Tobing Eunike Endariahna Surbakti Jimmy Peranginangin Anjar Pinem ##submission.copyrightStatement## http://creativecommons.org/licenses/by-sa/4.0 2025-01-24 2025-01-24 11 2 78 83 10.31937/ijnmt.v11i2.3736 Data Quality Issues : Case Study of Claim and Insured in Indonesia Insurance Company https://ejournals.umn.ac.id/index.php/IJNMT/article/view/3755 <p>Data has become an asset for insurance companies that have many benefits and management needs to realize the importance of data quality to avoid the impact of poor data quality. In this study, data quality measurement will be carried out by observation to see the total amount of invalid data from data dimensions, namely, accuracy, completeness and consistency of the relationship between claim data and insured, and findings from each data fields in this case study. In addition, researchers conducted interviews to find out the obstacles faced by IT, Customer Retention, Operational, and Actuary teams where they are directly related to data flow and data processing. From the results of the analysis, there is invalid data that will affect the analysis and cause obstacles faced by users according to the interview results. In the conclusion, management needs to form a data govenance team to avoid poor data quality that has responsibility for data flow and maintains data quality in order to provide a positive impact such as providing the right data accuracy in data analysis and user time to be more effective in data processing, assisting in making data warehouses, applying AI and digital transformation as a form of improvement in the services provided.</p> Chris Solontio Achmad Nizar Hidayanto ##submission.copyrightStatement## http://creativecommons.org/licenses/by-sa/4.0 2025-01-24 2025-01-24 11 2 84 89 10.31937/ijnmt.v11i2.3755 Evaluating the Impact of Particle Swarm Optimization Based Feature Selection on Support Vector Machine Performance in Coral Reef Health Classification https://ejournals.umn.ac.id/index.php/IJNMT/article/view/3761 <p>This research explores improving coral reef image classification accuracy by combining Histogram of Oriented Gradients (HOG) feature extraction, image classification with Support Vector Machine (SVM), and feature selection with Particle Swarm Optimization (PSO). Given the ecological importance of coral reefs and the threats they face, accurate classification of coral reef health is essential for conservation efforts. This study used healthy, whitish, and dead coral reef datasets divided into training, validation, and test data. The proposed approach successfully improved the classification accuracy significantly, reaching 85.44% with the SVM model optimized by PSO, compared to 79.11% in the original SVM model. PSO not only improves accuracy but also reduces running time, demonstrating its effectiveness and computational efficiency. The results of this study highlight the potential of PSO in optimizing machine learning models, especially in complex image classification tasks. While the results obtained are promising, the study acknowledges several limitations, including the need for further validation with larger and more diverse datasets to ensure model robustness and generalizability. This research contributes to the field of marine ecology by providing a more accurate and efficient coral reef classification method, which can be applied to other image classifications.</p> Jessica Carmelita Bastiaans James Hartojo Ricardus Anggi Pramunendar Pulung Nurtantio Andono ##submission.copyrightStatement## http://creativecommons.org/licenses/by-sa/4.0 2025-01-24 2025-01-24 11 2 90 99 10.31937/ijnmt.v11i2.3761 Enhancing Support Vector Machine Classification of Nutrient Deficiency in Rice Plants Through Particle Swarm Optimization-Based Feature Selection https://ejournals.umn.ac.id/index.php/IJNMT/article/view/3762 <p>The research focuses on the classification of nutrient deficiencies in rice plant leaves using a combination of Support Vector Machine (SVM) and Particle Swarm Optimization (PSO) methods for feature selection. Image features are extracted using Histogram of Oriented Gradients (HOG), which is then optimized with PSO to select the most relevant features in the classification process. Indonesia is one of the largest rice producers in the world, with food security as a major issue that requires sustainable solutions, especially in the agricultural sector. The growth and yield of rice plants are highly dependent on the availability of nutrients such as Nitrogen (N), Phosphorus (P), and Potassium (K). However, traditional observation methods to detect nutrient deficiencies in plants become inefficient as the scale of production increases. The dataset used includes images of rice leaves showing nitrogen (N), phosphorus (P), and potassium (K) deficiencies. Experiments show that the SVM model optimized with PSO provides a classification accuracy of 83.19% and a runtime of 129.63 seconds with 1150 best feature combinations out of 2303 extracted features, which is higher accuracy and faster runtime than the model that does not use PSO. These results show that the integration of PSO in the feature selection process not only improves the accuracy of the model, but also reduces the required computation time. This research makes an important contribution to the development of an automated system for the classification of nutrient deficiencies in crops, which can be implemented in large farms or other agricultural fields.</p> James Hartojo Jessica Carmelita Bastiaans Ricardus Anggi Pramunendar Pulung Nurtantio Andono ##submission.copyrightStatement## http://creativecommons.org/licenses/by-sa/4.0 2025-01-24 2025-01-24 11 2 100 110 10.31937/ijnmt.v11i2.3762 Cross-Platform Mobile Based Crowdsourcing Application for Sentiment Labeling Using Gamification Method https://ejournals.umn.ac.id/index.php/IJNMT/article/view/3935 <p>Sentiment analysis is the application of natural language processing which aims to identify the sentiment of texts. To carry out sentiment analysis, data which has been labeled sentiment is needed to be included in the training model. Crowdsourcing is considered as the most optimal method to label data because it has a high level of accuracy at a relatively low cost. However, the use of crowdsourcing platforms has its own challenge, which is to increase user interest and motivation. A solution which can be applied is to design and build a crowdsourcing platform or application using the gamification method. The definition of gamification is an effort to increase one's intrinsic motivation for an activity by applying game elements to it. Therefore, a cross-platform mobile based crowdsourcing application for sentiment labeling using gamification method was carried out. The gamification design process was done based on the 6D framework and the application was developed using the Ionic-React framework. Application was examined through black box testing and the result showed that the application was functioning properly and according to the design requirements. There was also an evaluation carried out by distributing Intrinsic Motivation Inventory questionnaires to users who had used the application for 2 weeks. From a total of 40 respondents, the result showed that the level of user motivation and interest in using the application was high with a percentage of 83.10%.</p> Elaine Elaine Farica Perdana Putri Alethea Suryadibrata ##submission.copyrightStatement## http://creativecommons.org/licenses/by-sa/4.0 2025-01-24 2025-01-24 11 2 111 118 10.31937/ijnmt.v11i2.3935 Cost Estimation for Software Development Using Function Point Analysis Method https://ejournals.umn.ac.id/index.php/IJNMT/article/view/4006 <p>Software development requires substantial financial resources. This study aims to examine the cost estimation for software development. The complexity of the software, its intangibility as a non-physical product, the technology utilized, and human resources can all influence the determination of software development costs. The method used for cost estimation is Function Point Analysis with a case study approach. The researchers conducted a case study on the software development for an employee savings and loan cooperative at XYZ Company. The result of this study is a cost recommendation that can serve as a reference for selecting software development vendors by the cooperative's management.</p> Ester Lumba Destriana Widyaningrum Alexander Waworuntu ##submission.copyrightStatement## http://creativecommons.org/licenses/by-sa/4.0 2025-01-24 2025-01-24 11 2 119 124 10.31937/ijnmt.v11i2.4006