JTIM : Jurnal Teknologi Informasi dan Multimedia
Not a member yet
290 research outputs found
Sort by
Analisis Pengalaman Pengguna Aplikasi ShopeePay: Implementasi Metode UEQ untuk Optimalisasi Layanan
No full textShopeePay is one of the e-wallet applications that is widely used in Indonesia thanks to its various benefits, convenience, and security in digital transactions. However, the quality of user experi-ence still requires in-depth analysis so that this application can meet the evolving needs of users. This study uses the User Experience Questionnaire (UEQ) method to assess six main dimensions, namely attractiveness, clarity, efficiency, accuracy, stimulation, and novelty. The analysis showed that attractiveness (1.15), clarity (1.27), and efficiency (1.14) were above average when compared to global standards. However, accuracy (0.98), stimulation (0.75), and novelty (0.67) were below average, highlighting the need for improvement in the aspects of innovation and emotional en-gagement of users. By understanding the strengths and weaknesses in each of these dimensions, this study provides recommendations for improvements to enhance the quality of the app. Up-dates in the dimensions of fidelity, stimulation, and sustainability are expected to increase user satisfaction while strengthening their loyalty to the app. These findings are not only useful for Shopee Pay developers but can also serve as a reference for the development of other e-wallet apps to remain competitive in the digital market. Overall, user experience optimization is an important element in maintaining app competitiveness and meeting user expectations in this era
Analisis Korelasi Faktor-Faktor Penentu Produktivitas dalam Skema Remote Work Menggunakan Pendekatan Visualisasi dan Statistik
No full textThe massive shift in work patterns caused by the global pandemic has significantly accelerated the adoption of remote work schemes across various industries and organizations. This condition has created a strong need for data-driven studies to understand the factors that influence employee productivity in flexible work environments. This study aims to analyze the relationships among several key variables, namely employment type (in-office or remote), weekly working hours, and well-being score, in relation to individual productivity scores. The research data were obtained from a publicly available dataset on the Kaggle platform, containing 1,000 entries from respondents with diverse professional backgrounds. The analysis process involved data preprocessing, Pearson correlation analysis, and exploratory data visualization using heatmaps and scatter plots to facilitate result interpretation. The results show that remote work is positively correlated with productivity (r = 0.40), while weekly working hours exhibit a negative correlation (r = -0.25). Meanwhile, the well-being score demonstrates a weak but positive correlation with productivity (r = 0.14). The data visualizations support these numerical findings by presenting consistent patterns among the analyzed variables. These findings offer preliminary insights that are valuable for future studies related to remote work productivity. This study can serve as an initial reference for decision-makers in designing data-driven policies to optimize flexible work arrangements
Perbandingan Metode Naïve Bayes dan Random Forest dalam Memprediksi Penyakit Diabetes Melitus pada Klinik Citra Sejati
No full textDiabetes mellitus is a chronic disease with a steadily increasing prevalence in Indonesia and is one of the leading causes of death, particularly in urban areas. Early detection of this disease is crucial to prevent serious complications such as heart disease, kidney failure, and vision impairment. In the era of digital transformation, machine learning techniques offer great potential to support early and automated diagnosis with higher accuracy. This study aims to develop a diabetes prediction system based on medical record data using two machine learning algorithms: Naïve Bayes and Random Forest. The dataset was obtained from Klinik Citra Sejati, consisting of 266 patient records with seven clinical features: age, gender, leukocytes, platelets, hematocrit, erythrocytes, and erythrocyte sedimentation rate (ESR). The models were implemented using Python programming language and the Scikit-learn library. Performance evaluation was carried out using the confusion matrix and classification metrics such as accuracy, precision, recall, and F1-score. Furthermore, ROC curve analysis and 95% confidence interval calculation were used to assess the stability and reliability of the predictions. The results showed that the Random Forest algorithm achieved an average accuracy of 89.97% with an AUC of 0.93, while Naïve Bayes achieved an accuracy of 85.97% with an AUC of 0.72. Based on these results, Random Forest is considered more effective for diabetes classification and is recommended as the primary algorithm for the development of clinical decision support systems based on local medical data
Analisis Pengaruh Recursive Feature Elimination Terhadap Kinerja Model Prediksi Dini Diabetes Mellitus di RS PKU Muhammadiyah Bima
No full textEarly detection of diabetes mellitus is a crucial step in preventing chronic complications and enabling more effective disease management. This study aims to analyze the impact of the Recursive Feature Elimination (RFE) method on the performance of machine learning-based diabetes prediction models at RS PKU Muhammadiyah Bima. A quantitative approach was employed by implementing the CRISP-DM framework, encompassing data selection, preprocessing, transformation, data mining, and model evaluation. Missing values in height and weight variables were imputed using linear regression based on age and gender features. The transformation process included calculating the Body Mass Index (BMI) as a new feature relevant to diabetes risk. Evaluation was carried out on three classification algorithms—Support Vector Machine (SVM), Logistic Regression (LR), and Random Forest (RF)—both before and after the application of RFE. The results showed that all models experienced significant performance improvements following feature selection with RFE, achieving 100% in all evaluation metrics. Insulin and BMI were consistently selected features, underscoring their contribution to diabetes detection. It can be concluded that RFE effectively reduces model complexity without sacrificing accuracy, thereby supporting the efficient implementation of predictive models in clinical settings
Media Pembelajaran Jenis Jamur Berbasis Augmented Reality Menggunakan Metode Marker Based Tracking
No full textMushrooms are a plant-based food source with considerable potential and are often found around us. However, some types of mushrooms have similar characteristics and morphology. Based on these problems, an application is made that aims as a medium for the introduction of mushroom types through the use of Augmented Reality (AR) technology. By utilizing Augmented Reality as an interactive educational media, it is expected to facilitate users in obtaining information about the type of fungus accompanied by visualization in the form of 3D objects. The research method used consists of three stages, namely data collection, multimedia product creation, and evaluation. This mushroom type learning application is made using AR marker based on tracking technology with the MDLC (Multimedia Development Life Cycle) method according to Luther Sutopo. Based on the results of Black Box testing, angle, distance and light intensity testing, the application can function properly. Evaluation using the System Usability Scale (SUS) was conducted on the general public with an age range of 17-45 years in RW 05 Panyingkiran Village, Indihiang District, Tasikmalaya City with a population of 356 people, determining the number of respondents using the slovin formula which is 32 people. The test results show that the application obtained an average score of 74.78, which indicates that the application is in the “Acceptable” category for Acceptability Range, Grade C in Grade Scale, and “Good” in Adjective Rating
Perancangan UI/UX pada Website Toko Kue Jager Bakery dengan Metode Design Thinking
No full textA patisserie website is a key channel for interacting with consumers and has great potential to increase market reach. Jäger Bakery comes as a new innovation in the world of online cake shops designed to provide a better user experience compared to other cake shop websites. The main problems found on cake shop websites are suboptimal design, such as unattractive appearance, confusing navigation, and mismatch between user needs and features provided. This has the potential to reduce user comfort and affect the level of customer satisfaction. Therefore, the purpose of this research is to identify and design a design solution that better suits user preferences and improves the quality of the online shopping experience at the cake shop. The Design Thinking method was chosen for its approach that focuses on deeply understanding user needs and wants, and generating innovative and effective design solutions. The research process begins with the Empathize stage to gather information from users, followed by Define to formulate the main problem, then continues to the Ideate, Prototype, and finally Test stages to test the design that has been made. Usability testing results showed an increase in Direct Success Rate (DSR) from 65% to 93.8% and a decrease in Missclick Rate from 54.2% to 8%. In addition,System Usability Scale (SUS) testing resulted in a Maze Usability Score (MAUS) of 79.23, which is categorized as “good”. These results prove that the application of the Design Thinking method has successfully improved the UI/UX of the Jäger Bakery website by producing a more user-friendly design, increasing user engagement, and simplifying the purchasing process
Perancangan dan Pengembangan Aplikasi Android Berbasis Augmented Reality pada Mahasvin Farm menggunakan Metode MDLC
No full textEducational tourism plays an important role in preserving nature and supporting the creative economy of local communities. Agritourism, as a subset of educational tourism, combines rec-reation with learning experiences about conservation and sustainability. Mahasvin Farm, an agro-tourism destination in Yogyakarta, incorporates this concept by showcasing rare animals such as ostriches, peacocks, ornamental chickens, and turtles. However, current methods of de-livering information, such as static boards and limited tour guides, are less effective in engaging younger audiences who prefer interactive digital media. This study aims to develop an An-droid-based application leveraging Augmented Reality (AR) technology to deliver educational content interactively. The Multimedia Development Life Cycle (MDLC) methodology was applied, consisting of six stages: Concept, Design, Material Collecting, Assembly, Testing, and Distribution. MDLC was selected for its structured framework and capability to integrate multimedia elements, including 3D visualization, audio, and text. Blackbox testing results indicated a 100% success rate across 13 test scenarios, including menu navigation, AR marker scanning, and audio description functionality. The application successfully enhances the educational experience by providing engaging and immersive features, while also having the potential to improve digital promotion efforts for Mahasvin Farm. In conclusion, the AR-based application offers an innovative solution to improve information dissemination at Mahasvin Farm. Furthermore, it demonstrates the poten-tial for broader adoption in the technology-based agritourism sector
Prediksi Beban Kerja Server Secara Real-Time pada Pusat Data Cloud dengan Pendekatan Gabungan Long Short-Term Memory (LSTM) dan Fuzzy Logic
No full textEfficient resource management in Cloud Data Centers is essential to reduce energy waste and maintain optimal system performance. This study aims to predict server workload in real time using a hybrid approach that combines Long Short-Term Memory (LSTM) and Fuzzy Logic. CPU and RAM usage data were collected every second from a Proxmox Cluster using its API, then normalized and processed using an LSTM model to forecast future workloads. The predicted results were then classified using Fuzzy Logic into three workload categories: light, medium, and heavy. The model was evaluated using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE), where the results showed an MAE of 2.48 on the training data and 3.09 on the testing data, as well as RMSE values of 5.15 and 5.57, respectively. Based on these evaluation results, the prediction system achieved an accuracy of 97.52% on the training data and 96.91% on the testing data, indicating that the model can generate accurate and stable predictions. This method enables automated decision-making such as workload-based power management, thereby improving energy efficiency and overall system performance
Sistem Pelaporan Data Capaian Standar Pelayanan Minimal Bidang Kesehatan Berbasis Website
No full textReporting the achievement of Minimum Service Standards in the health sector (SPM BK) plays a crucial role in evaluating and improving healthcare services. the reporting of Minimum Service Standards (SPM BK) achievement data at the Sumbawa District Health Office is not standardized, with inconsistent report formats and submissions via third-party messaging applications (WhatsApp). This leads to delays, data inconsistencies, and calculation errors, which affect the quality of monitoring. This study aims to design and develop a web-based information system to facilitate the reporting and monitoring of SPM BK achievements at the Sumbawa District Health Office. The web-based system enables easier reporting and monitoring, while the processing of SPM BK data can be automated to reduce the potential for human error. The system development followed the Waterfall model, starting from data collection through interview methods, system needs analysis, system design using Entity Relationship Diagram, Use Case Diagram, and Wireframe, followed by the system development process using Laravel 10 and MySQL database, and closed with the testing stages using the black box method, and User Acceptance Testing (UAT). The UAT results showed a success rate of 84.7% with a "Excellent" interpretation, indicating that the system meets user needs both functionally and in terms of interface. This system is expected to improve the speed, consistency, and accuracy of SPM achievement reporting
Implementasi Generatif Artificial Intelligence pada Tahap Pembuatan Animasi menggunakan Metode MDLC
No full textThe rapid advancement of artificial intelligence (AI) in recent years has unlocked new opportunities across various fields, including creative industries such as animation. This study focuses on the application and use of generative AI, particularly text-to-image, text-to-video, and image-to-video models, in the process of creating animated scenes. This technology enables the generation of complex and imaginative visual content based solely on narrative descriptions (prompts) provided by users. By automating the production of images or videos, generative AI not only accelerates the production process and significantly reduces costs but also opens doors to exploring more diverse and innovative visual styles. This research analyzes several cutting-edge generative AI technologies, while evaluating their advantages and challenges in producing animated content. The AI-based animation development process is examined using the Multimedia Development Life Cycle (MDLC) framework, which consists of six key stages: Concept, Design, Material Collection, Development, Testing, and Distribution. The findings suggest that generative AI holds great potential for enhancing animators\u27 efficiency, particularly in pre-production stages such as storyboarding, concept art creation, and rough animation. However, while AI can automate many technical aspects, human intervention remains essential to ensure visual consistency, artistic quality, and narrative coherence. Key challenges include dependence on dataset quality, risks of visual style plagiarism, and the need for manual refinement to align outputs with creative visions. Thus, the integration of generative AI in animation production should be viewed as an assistive tool rather than a complete replacement for human creativity. This study provides insights into how AI technology can be optimally utilized in the animation industry while preserving artistic value and originality