Jurnal Informatika: Jurnal Pengembangan IT
Not a member yet
437 research outputs found
Sort by
Optimization of Random Forest Algorithm Performance for Early Detection of Stroke Disease Using Medical Record Data
No full textStroke is a medical condition that occurs when blood flow to the brain is blocked, causing damage to brain tissue. Stroke is the second largest cause of death and disability in the world, this disease can affect all ages and is influenced by various risk aspects, such as unhealthy lifestyles, high blood pressure, high blood sugar levels, and other risks. It is very important to detect stroke in patients as soon as possible to prevent it. This study proposes the optimization of the performance of the Random Forest algorithm as an early detection model for stroke by utilizing a hybrid sampling method called SMOTETomek and also conducting several experiments on the parameter settings of the Random Forest algorithm. The results of this study show an increase compared to the previous one which had an accuracy was 94% with a standard deviation of 2%, In this study, it managed to reach accuracy of 96% with a standard deviation of 0% with a ROC curve (AUC) value of 0.96 or 96%. The algorithm that has 96% accuracy in the discussion is Random Forest Algorithm as estimator of AdaBoost
Enhancing E-Learning User Engagement Through Scrum-Based Development
No full textAbstract – Higher education faces challenges in meeting evolving needs while existing e-learning systems often fail to adapt to these changes. The current open-source e-learning system cannot accommodate the dynamic requirements of students, faculty, and administrators, hindering the effectiveness of the learning process. This research aims to design and develop an adaptive e-learning system using the Scrum methodology to bridge the gap between existing systems and the changing demands of higher education. The goal is to create a system that can quickly adapt to changes, accommodate user needs, and enhance learning effectiveness. The study applies the Scrum methodology, which supports iterative and incremental development, enabling continuous user feedback and risk management. The research involves a needs analysis, system design, and prototype development, followed by usability testing using the System Usability Scale (SUS) to evaluate the system's usability and effectiveness. The usability testing results show that the prototype system received neutral evaluations, indicating that while it provides a functional solution, further refinements, and additional iterations are necessary to fully meet user expectations. This study contributes to the understanding of how adaptive e-learning systems can be developed using Scrum and how they can be improved to better support the transformative goals of higher education in Indonesia. Keywords: E-learning, Ishikawa Diagram, Scrum, System Usability Scale (SUS), User Engagement Abstrak – Pendidikan tinggi menghadapi tantangan dalam memenuhi kebutuhan yang terus berkembang sementara sistem pembelajaran yang ada sering kali gagal beradaptasi dengan perubahan ini. Sistem pembelajaran sumber terbuka yang tersedia saat ini tidak dapat mengakomodasi kebutuhan dinamis mahasiswa, fakultas, dan administrator, sehingga menghambat efektivitas proses pembelajaran. Penelitian ini bertujuan untuk merancang dan mengembangkan sistem pembelajaran elektronik adaptif menggunakan metodologi Scrum untuk menjembatani kesenjangan antara sistem yang ada dan tuntutan pendidikan tinggi yang terus berubah. Tujuannya adalah untuk menciptakan sistem yang dapat dengan cepat beradaptasi dengan perubahan, mengakomodasi kebutuhan pengguna, dan meningkatkan efektivitas pembelajaran. Penelitian ini menerapkan metodologi Scrum, yang mendukung pengembangan iteratif dan inkremental, yang memungkinkan umpan balik pengguna dan manajemen risiko yang berkelanjutan. Penelitian ini melibatkan analisis kebutuhan, desain sistem, dan pengembangan prototipe, diikuti oleh pengujian kegunaan menggunakan Skala Kegunaan Sistem (SUS) untuk mengevaluasi kegunaan dan efektivitas sistem. Hasil pengujian kegunaan menunjukkan bahwa sistem prototipe menerima evaluasi netral, yang menunjukkan bahwa meskipun memberikan solusi fungsional, penyempurnaan lebih lanjut, dan iterasi tambahan diperlukan untuk sepenuhnya memenuhi harapan pengguna. Studi ini berkontribusi pada pemahaman tentang bagaimana sistem e-learning adaptif dapat dikembangkan menggunakan Scrum dan bagaimana sistem tersebut dapat ditingkatkan untuk lebih mendukung tujuan transformatif pendidikan tinggi di Indonesia. Kata Kunci: E-learning, Diagram Ishikawa, keterlibatan pengguna, Scrum, System Usability Scale (SUS)
Penerapan Metode SAW dalam Penentuan Mata Pelajaran Pilihan Siswa Kelas XI pada MAN 1 Brebes
No full textThe subject selection process for eleventh-grade students at Madrasah Aliyah Negeri 1 Brebes faces challenges including misalignment between student interests and academic abilities, and imbalanced teacher-to-subject ratios across Natural Sciences, Social Sciences, and Religious Studies. This study develops a decision support system using the Simple Additive Weighting (SAW) method to provide objective recommendations that consider both academic performance and student preferences. A quantitative descriptive analytical approach was applied with data from 30 tenth-grade students, incorporating four criteria: Natural Sciences scores, Social Sciences scores, Religious Studies scores, and student interests, weighted 0.25, 0.25, 0.10, and 0.40 respectively. The SAW implementation included decision matrix construction, normalization, weighted preference calculation, and recommendation determination. Results showed optimal distribution with 19 students recommended for Natural Sciences, 7 for Social Sciences, and 4 for Religious Studies, achieving 96.67% accuracy in aligning preferences while optimizing academic potential. The system preserved preferences for all students initially interested in Social Sciences and Religious Studies, while reassigning two Natural Sciences–interested students to Social Sciences based on superior performance. Top-performing students identified were Mohammad Abian for Natural Sciences (0.9802), Julia for Social Sciences (0.87243), and a student with 0.75995 for Religious Studies. The SAW method proves effective in addressing multi-criteria decision-making while ensuring transparency, objectivity, and balanced resource use in Islamic secondary education
Design and Implementation of IoT-Based Smart Election Using ESP32 and RFID
No full textThis research aims to design and implement a smart election system leveraging Internet of Things (IoT) technology through the integration of the RFID RC522 module, ESP32 microcontroller, and the MQTT communication protocol, with the goal of improving the efficiency, transparency, and security of the voting process. The research adopts a prototyping approach consisting of four main stages: requirement analysis, system design, performance evaluation, and refinement leading to final implementation. The system enables voter authentication through e-KTP verification using RFID sensors, which is cross-checked against a centralized database. Voting data are transmitted securely via the MQTT protocol and displayed in real-time through a Node-RED dashboard, allowing for continuous monitoring and rapid vote recapitulation. Experimental results indicate a 100% accuracy rate in UID verification, prevention of duplicate voting, and stable system responsiveness. The platform significantly reduces human intervention and the risk of vote manipulation, supporting the credibility and auditability of election results. In conclusion, the proposed IoT-based smart election prototype offers an efficient, scalable, and user-friendly technological solution suitable for local deployment. Future improvements may include the integration of cryptographic techniques, cloud-based data storage, and biometric authentication to enhance system robustness and security
Sistem Otomatisasi Pengendalian Perangkat Listrik Dan Penguncian Pintu Ruangan Menggunakan Komunikasi Bluetooth Rendah Energi
No full textThis research aims to design and implement an automation system for controlling electrical devices and door locking based on an ESP32 microcontroller with support for Bluetooth Low Energy (BLE) technology. The system was realized in prototype form using the iTag device as a communication medium between the user and the ESP32. The main aim of this system is to increase energy efficiency and room security through automatic control of electrical devices and a door locking mechanism when the room is not in use. Registered iTag devices will be connected to the ESP32 through the BLE pairing process, enabling detection of the user's presence within a 3 meter radius. When a user is detected, the system automatically activates the electrical device and unlocks the door; instead, the device will be disabled and the door locked when the user leaves the area. System testing was carried out to evaluate the BLE signal range and system response to various environmental conditions. Test results show that the system is able to detect iTag devices up to a maximum distance of 12 meters without physical obstacles and 9 meters with wall obstacles.
HARMONI: Home Automation Module Berbasis Internet of Things dan Deep Learning
No full textAlat listrik yang tidak dimatikan saat tidak digunakan seringkali menyebabkan terjadinya korsleting listrik yang berakibat bencana kebakaran. Selain itu, hal ini juga berpotensi dalam pemborosan penggunaan energi listrik. Orang-orang menyambungkan alat listrik langsung pada sumber listrik melalui stop kontak atau melalui jalur listrik kemudian dihubungkan dengan sakelar, dalam pengoperasiannya. Ini cukup efektif, namun, seringkali dialami kelalaian dalam mematikan atau mencabutnya, sehingga berpotensi membahayakan. Modul otomasi rumah berbasis IoT dan Deep Learning dibuat untuk melakukan digitalisasi dan otomasi sakelar. Terdiri dari mikrokontroler ESP32-S3 dan ESP32 sebagai pengendali sistem, modul relay sebagai sakelar otomatis, modul kamera untuk mendeteksi orang, integrasi Google Home dengan platform Sinric.Pro, website Mowny dengan integrasi protokol HTTPS. Mikrokontroler, modul, relay disusun pada papan-sirkuit-cetak. Website Mowny untuk mengontrol saklar dan monitoring ruangan. Pendeteksian keberadaan orang menggunakan YOLO sebagai pemicu otomasi sakelar. Model deteksi dimuat melalui API untuk diakses pada website. Pengujian sistem meliputi empat skenario untuk menyala-matikan sakelar secara digital dan otomatis, menghasilkan waktu respon sebagai berikut (dalam satuan detik): Google Home (±3,468), Google Assistant (±4,348), website Mowny (±1,042), dan otomasi deteksi objek (±19,375). Modul otomasi ini dapat mengontrol alat listrik dari secara digital dan otomatis, yang berdampak pada kemudahan pengoperasian sakelar ketika mengalami kelalaian mematikan alat listri
Rancang Bangun Webgame Edukasi Sebagai Media Pembelajaran Bahasa Inggris Maritim
No full textThe phenomenon of online game addiction is increasing among students, including students at the Indonesian State Maritime Polytechnic (Polimarin). They tend to spend time to playing game which decrease their academic performance. Apart from that, students also face challenges in learning through traditional learning methods which tend to be less interesting and boring, especially when learning English. English language skills are an important aspect that must be mastered by shipping students, because this language is widely used in the international maritime world. To improve students' English skills, an interactive and fun maritime English learning web game was built that can increase their interest in learning English in a more interesting way. The development method used the waterfall model, which consisted of the stages of analysis, design, implementation, testing and maintenance. At the analysis stage, user needs were identified to understand the most relevant and interesting content for students. Then, the interface and game mechanisms were designed to be attractive and easy to access. The implementation was carried out using responsive web technology so that it can be accessed via computer or mobile devices. The features in the web game were designed to enrich vocabulary, sentence understanding and English communication skills, which were relevant to the needs of the maritime studies field. Web game-based learning media provided a good learning experience in improving the quality and effectiveness of the teaching and learning process. Web games can be an innovative solution in increasing student learning motivation and helping students understand the material in a fun and interactive way.Keywords: learning media; maritime English; webgame
Evaluasi Performa Website Rumah Sakit CSH Mempergunakan User Acceptance Test
No full textUser Acceptance Testing (UAT) is a crucial step to ensure that the solutions implemented in a system align with user needs. Unlike system testing, UAT focuses on the functionality of the solution for end users. In this context, testing user acceptance becomes an essential element to assess the performance and user satisfaction of a website. The CSH Hospital website faces the challenge of lacking a scientific analysis to evaluate its performance and usability. Therefore, the UAT method is applied using the ISO 9126 dimensions and the Likert scale. The information system employed facilitates routine transactions, data processing, operational support, and provides relevant information to users. The evaluation results show that the CSH Hospital website achieved a score of 87%, reflecting a high level of user acceptance and comfort in using the website. However, identifying areas for improvement, such as simplifying and accelerating the online registration process, can enhance user experience and streamline services in the future.This aligns with the Sustainable Development Goal (SDG) 3, "Good Health and Well-Being." By improving digital services like the hospital's website, the community can gain easier access to healthcare services, increase registration efficiency, and improve the overall patient experience. Ultimately, this supports efforts to achieve universal access to quality healthcare services, as mandated by SDG 3
The Impact of Image Pre-processing for Tuberculosis Prediction System Based on Chest X-ray Images
No full textWith the rapid development of automated detection system using deep learning techniques on Chest X-ray (CXR) image datasets to the subjective assessment performed by healthcare professionals. Preprocessing is critical in medical image analysis as it helps highlight important anatomical features while suppressing irrelevant information, thus enabling the model to focus on meaningful patterns. In this paper, we investigate the impact of image preprocessing techniques on the performance of a tuberculosis prediction system based on CXR images using a deep learning approach. We used the “Tuberculosis Chest X-rays (Shenzhen)” dataset, which contains 1,344 CXR images (672 TB cases and 672 normal cases). We propose a five-step preprocessing pipeline consisting of resizing, heavy sharpen filtering, CLAHE (Contrast Limited Adaptive Histogram Equalization), horizontal flip augmentation, and data normalization. The findings indicate that the model utilising preprocessing markedly surpasses the one lacking it, attaining an accuracy, precision, recall, and F1-score of 71%, in contrast to 51%, 50%, 50%, and 36% without preprocessing, respectively. This study enhances the existing research on the application of deep learning in medical diagnostics and emphasises the significance of preprocessing for attaining dependable, high-performance systems
Segmentasi Citra Daun Tomat untuk Klasifikasi Penyakit Tanaman Menggunakan Support Vector Machine (SVM)
No full textTomatoes are one of the most widely grown crops worldwide. In Indonesia, particularly in West Sumatra, tomato production has declined. This is due to extreme weather conditions and plant disease outbreaks. One solution to help with early identification of tomato plant diseases is through digital image-based classification. This process involves several important stages, starting from image acquisition, preprocessing, segmentation, feature extraction, and classification. However, the quality of classification is highly dependent on the effectiveness of segmentation in separating leaf objects from the background. This study proposes a method for segmenting tomato leaf images based on a combination of color thresholding techniques, morphological operations, contour filtering, and bitwise masking to ensure that only the leaf parts are processed further. After undergoing the segmentation process, images are extracted based on color characteristics in HSV space and GLCM texture, then further processed using an SVM algorithm with an RBF kernel. The dataset used consists of 4000 tomato leaf images with an 80% training and 20% testing data division scheme, accompanied by 5-fold cross validation. The model achieved an accuracy of 96.97% on the training data and 93.75% on the testing data. The results show that segmentation methods using color thresholding, morphology, contours, and bitwise masking can help improve the consistency of extracted features, thereby potentially supporting more stable classification performance