Jurnal Informatika Progres

PERANCANGAN DAN IMPLEMENTASI AWAL APLIKASI FINEME BERBASIS FLUTTER UNTUK PENCATATAN KEUANGAN PRIBADI DIGITAL

2026-04-28T11:45:07+00:00

Personal financial record keeping is often delayed or messy, making it difficult to summarize data, unconnected to budget limits, and easily overlooked. This research designed and built FineMe, a Flutter-based application for recording transactions, managing categories, setting total and per-category budgets, displaying daily charts, exporting data to CSV, and managing recurring transactions. The development followed a layered architecture software engineering approach with SQLite in the data layer, a repository for logic and aggregation, Riverpod for state synchronization, and a Material interface. Requirements were derived from daily usage scenarios and implemented iteratively, while functional testing assessed the accuracy of calculations and interface responsiveness. Results showed that the income, expense, and balance summaries were updated instantly, two separate daily charts were easy to read, budget progress was calculated accurately, valid CSV files were opened in a spreadsheet, and recurring transaction rules reduced repetitive input. These findings confirm the effective combination of Flutter, SQLite, and reactive state management for building a precise, responsive, and scalable financial recorder.

RANCANG BANGUN MODEL KONTROL AKSES DINAMIS BERBASIS KONTEKS PADA ARSITEKTUR ZERO TRUST

2026-04-28T12:09:02+00:00

The rapid development of digital systems and interconnected environments has created new challenges in securing data. Traditional perimeter-based security models are no longer adequate to protect sensitive information from internal and external threats. This study proposes the design and implementation of a Context-Based Dynamic Access Control Model within the Zero Trust Architecture (ZTA) framework. The proposed system integrates contextual authentication, adaptive risk evaluation, and a dynamic policy engine to implement more granular access control in multi-user web applications. The prototype was developed using Node.js, Express.js, and MySQL, featuring multi-factor authentication, contextual verification via OTP, session management, and security notifications.The test results indicate that the system is capable of detecting changes in access context, enforcing re-authentication, and recording all user activities for auditing and anomaly detection purposes. The integration of contextual authentication, adaptive access control, and Zero Trust principles has been proven to enhance data protection and user accountability without reducing system usability..

IMPLEMENTASI SISTEM LOGIN WEB BERBASIS ZTA DENGAN INTEGRASI OTP BREVO DAN CAPTCHA

2026-04-28T12:51:42+00:00

Keamanan autentikasi pada sistem web merupakan komponen penting dalam menjaga kerahasiaan dan integritas data pengguna dari berbagai ancaman siber seperti brute force, phishing, dan serangan bot. Penelitian ini mengimplementasikan sistem login web berbasis Zero Trust Architecture (ZTA) yang diintegrasikan dengan One-Time Password (OTP) Brevo serta Google reCAPTCHA untuk memperkuat proses verifikasi identitas pengguna. Prinsip dasar “never trust, always verify” diterapkan agar setiap permintaan akses divalidasi secara menyeluruh tanpa adanya asumsi kepercayaan terhadap pengguna. Sistem dikembangkan menggunakan bahasa pemrograman web dengan dukungan basis data MySQL dan diuji melalui serangkaian uji fungsional, performa, serta keamanan. Hasil pengujian menunjukkan bahwa kombinasi ZTA, OTP Brevo, dan reCAPTCHA secara signifikan meningkatkan keamanan proses login dengan membatasi percobaan akses berulang, mencegah serangan otomatis dari bot, serta menekan potensi login ilegal. Selain itu, penerapan enkripsi kata sandi dan pembatasan waktu OTP terbukti meningkatkan keandalan autentikasi berlapis. Berdasarkan hasil percobaan, sistem yang dikembangkan dinilai lebih tangguh, adaptif, dan efisien dalam menghadapi ancaman siber modern tanpa mengurangi kenyamanan pengguna.

IDENTIFIKASI BIAS SOSIAL EKONOMI DALAM MODEL BAHASA AI INDONESIA MELALUI ETHICAL PROBING

2026-04-28T13:21:06+00:00

This study evaluates socioeconomic bias in three large language models (LLMs) that support Indonesian Nusantara, IndoGPT, and SEA-LION using an ethical probing approach. A total of 100 short narrative prompts (4–11 words) were compiled to represent issues of poverty, informal employment, access to education, and regional contexts. Each model output was analyzed using five key indicators: emotional valence, stereotypes, narrative themes, framing, and deontic indicators. The results show that all three models tend to produce neutral responses, especially SEA-LION, which has the highest proportion of neutral responses. However, stereotypes still appeared at almost the same level across all models, indicating that a neutral tone does not guarantee bias-free output. IndoGPT showed the highest use of normative language, while Nusantara more often displayed structural framing and empathetic nuances. In contrast, SEA-LION was the most stable in maintaining neutrality without eliminating implicit stereotypical tendencies. These findings confirm that socioeconomic bias in Indonesian-language LLMs still occurs subtly through deterministic narratives, generalizations, and framing that normalizes the vulnerability of low-income groups. This study provides an initial overview of the direction of generative bias in Indonesian LLMs and highlights the need for broader dataset development, stricter annotation methods, and continuous evaluation for the development of fairer models.

PERAN MEDIA SOSIAL DALAM MEMBANGUN JARINGAN PROFESIONAL UNTUK WIRAUSAHA GEN Z

2026-04-28T13:33:47+00:00

Social media has become an essential tool for Gen Z entrepreneurs in building professional networks. With more than 3.6 billion social media users worldwide in 2020, and that number expected to continue to grow, these platforms offer unlimited opportunities to interact, collaborate, and expand business networks. This study uses a literature review method to explore how social media functions as a bridge in building valuable professional connections. Through analysis of various relevant studies, it was found that social media not only facilitates communication, but also helps Gen Z entrepreneurs build reputation and credibility in their industries. By utilizing platforms such as LinkedIn, Instagram, and Twitter, these young entrepreneurs can access information, find mentors, and even discover investors. The results of this study indicate that effective use of social media can be the key to success in running a business, especially in an increasingly competitive digital era.

IMPLEMENTASI SISTEM DETEKSI PRODUK BOIKOT BERBASIS WEBSITE REAL-TIME MENGGUNAKAN METODE YOLOv10

2026-04-28T15:12:03+00:00

Manual identification ofboycott products remains a challenge for the public due to limited access to information and the complexity of brand affiliations. This study aims to develop a real-time, website-based boycott product detection system using the You Only Look Once version 10 (YOLOv10) algorithm. The dataset consists of images of food and beverage product packaging collected from various online sources, annotated using the bounding box method, and classified into five categories. The model was trained and tested using separate test data, while performance evaluation was conducted using a confusion matrix with precision, recall, and f1-score metrics. In addition, functional testing of the system was performed using the Black Box Testing method. The result indicate that the YOLOv10 model is capable of detecting boycott product with good performance and can be effectively integrated into a real-time web-based system. The proposed system is expected to assist users in identifying boycott products more quickly and accurately.

IMPLEMENTASI FINANCIAL TECHNOLOGY (FINTECH) PADA DEPOSITO DIGITAL BANK NEO COMMERCE (NEOBANK)

2026-04-28T22:06:08+00:00

Financial Technology (FinTech) transformation has driven a shift in public investment behavior toward digital banking services offering efficiency and transparency. This study aims to analyze the profitability of digital deposit services at Bank Neo Commerce (NeoBank) and map optimal investment strategies for customers. The research employs a quantitative descriptive approach with Time Value of Money (TVM) calculation simulations based on fixed returns across various time intervals. The results indicate that NeoBank's digital deposit system accumulates profits precisely from yearly to hourly intervals, providing more measurable yield certainty compared to conventional banking. Decision Tree analysis recommends this product for investors with conservative to moderate risk profiles who prioritize liquidity and LPS security guarantees. This study concludes that FinTech implementation in digital deposits offers a balance between accessibility, security, and profitability.

PENINGKATAN AKURASI DETEKSI DINI KEBAKARAN BERBASIS IOT MENGGUNAKAN ALGORITMA RANDOM FOREST

2026-04-29T05:33:12+00:00

Fire is one of the most frequent disasters and poses a significant risk to human safety, environmental sustainability, and property due to delayed early detection. This study aims to design and implement an early fire warning system based on the Internet of Things (IoT) enhanced with Machine Learning to improve detection accuracy and reliability. The system utilizes an ESP32 microcontroller as an edge node integrated with a DHT11 sensor for temperature and humidity, an MQ-2 sensor for gas and smoke concentration, and a flame sensor for fire detection. Multisensor data are transmitted in real time to a Flask-based server via the HTTP protocol and processed using a Random Forest classification model to determine environmental conditions as either safe or fire-hazardous. The classification results are displayed on a web-based dashboard and accompanied by automatic notifications delivered through a Telegram bot. Experimental results show that the proposed system achieves a detection accuracy of 94%, a low false positive rate, and a notification latency of less than 3 seconds, based on experiments conducted using a dataset of 3000 samples with an 80:20 split between training and testing data.The integration of IoT and Machine Learning demonstrates superior performance compared to conventional threshold-based methods, making the system a promising preventive solution for fire risk mitigation in residential and industrial environments.

OPTIMASI PROMPT ENGINEERING SEBAGAI STRATEGI PENINGKATAN KOGNITIF: STUDI EKSPERIMEN PADA PEMBELAJARAN ALGORITMA DAN PEMROGRAMAN

2026-04-29T07:06:40+00:00

Penetrasi ChatGPT di lingkungan akademik telah memicu kekhawatiran mengenai penurunan kemampuan berpikir kritis mahasiswa akibat ketergantungan pada jawaban instan. Penelitian ini bertujuan untuk menguji efektivitas optimasi prompt engineering (teknik pemberian instruksi terstruktur) sebagai strategi untuk meningkatkan kemampuan kognitif mahasiswa pada mata kuliah Algoritma dan Pemrograman. Dengan menggunakan metode eksperimen murni (True Experimental Design), penelitian ini melibatkan 60 mahasiswa Program Studi Teknologi Informasi yang dibagi ke dalam kelompok eksperimen dan kelompok kontrol. Kelompok eksperimen diberikan intervensi berupa panduan prompting menggunakan teknik Chain-of-Thought (CoT) dan Socratic Prompting, sementara kelompok kontrol menggunakan ChatGPT secara bebas. Hasil penelitian menunjukkan adanya perbedaan signifikan pada nilai post-test antara kedua kelompok ($p < 0,05$), dengan rata-rata kelompok eksperimen (82,5) jauh melampaui kelompok kontrol (64,2). Analisis N-Gain Score menunjukkan bahwa kelompok eksperimen mengalami peningkatan kognitif kategori "Tinggi" (0,71). Temuan ini membuktikan bahwa optimasi prompting mampu mengubah peran AI dari mesin penjawab otomatis menjadi mitra dialog kognitif yang merangsang logika berpikir. Penelitian ini memberikan implikasi bagi dosen muda untuk mengintegrasikan literasi prompting dalam kurikulum sebagai strategi mitigasi terhadap risiko adiksi teknologi tanpa mengorbankan efisiensi AI.

KLASIFIKASI TANAMAN OBAT TRADISIONAL BERBASIS CITRA BUAH DAN DAUN

2026-04-29T12:38:38+00:00

Indonesia is a megabiodiversity country with extensive use of traditional medicinal plants; however, plant identification in natural environments remains largely manual and error-prone. Recent advances in deep learning, particularly Vision Transformer (ViT), provide a promising solution by effectively capturing global spatial features for image classification. This study applies a ViT-Base/16 model to automatically classify fruit and leaf images of Indonesian medicinal plants. The dataset comprises 1,000 field-collected images from Galung Village, West Sulawesi, covering 20 classes (10 medicinal and 10 non-medicinal plants). The model was fine-tuned using the AdamW optimizer with a learning rate of 2×10⁻⁵ and trained for 30 epochs with cosine annealing. The proposed approach achieved high performance, with 99.33% accuracy, 99.41% precision, 99.33% recall, and a 99.33% F1-score, while binary classification between medicinal and non-medicinal plants reached 100% accuracy. The system was deployed as a Flask-based web application, demonstrating reliable functionality and practical response times. Overall, the results confirm the effectiveness of Vision Transformer for medicinal plant classification under natural conditions and highlight its potential to support digital documentation, education, and the preservation of local ethnobotanical knowledge.

PERBANDINGAN CNN DAN YOLO PADA SISTEM PENGENALAN WAJAH BERBASIS PRESENSI

2026-04-30T03:27:47+00:00

Face recognition based on image data has been widely applied in automated attendance systems; however, it still faces challenges related to accuracy and efficiency under varying lighting conditions and facial pose variations. This study aims to compare the performance of Convolutional Neural Network (CNN) and You Only Look Once (YOLO) methods for face detection and recognition in a deep learning–based attendance system. The dataset consists of facial images collected from students in a limited campus environment with several variations in viewpoint and illumination. The research stages include image preprocessing, training of CNN and YOLO models, and performance evaluation using accuracy, precision, recall, and computation time metrics. The experimental results indicate that YOLO outperforms CNN in terms of detection speed and performance stability, while CNN demonstrates competitive classification performance on limited datasets. This study provides empirical insights into the characteristics of both methods in attendance system scenarios and can serve as a reference for selecting appropriate models for real-world implementation. The main limitations of this study are the dataset size and the restricted data acquisition scope.

PENERAPAN ALGORITMA MOBILENETV2 UNTUK KLASIFIKASI HURUF HIJAIYAH BERBASIS GESTUR TANGAN

2026-04-30T03:59:37+00:00

The digitalization of religious education offers significant opportunities to enhance Hijaiyah letter learning, particularly for the hearing-impaired community through visual gesture recognition. This study aims to develop and evaluate a real-time web-based classification system for 28 Hijaiyah hand gestures using the MobileNetV2 architecture. The research methodology involves a quantitative approach utilizing transfer learning with a balanced dataset of augmented images. The model was trained using fine-tuning techniques and deployed on a web platform using TensorFlow.js and MediaPipe for efficient on-device inference. Experimental results demonstrate that the model achieved an overall accuracy of 84% on the independent test set, with specific classes reaching near-perfect detection in real-time scenarios, although misclassification persisted among visually similar gestures. The system effectively balances computational efficiency with classification performance, minimizing latency during user interaction. In conclusion, the implementation of MobileNetV2 facilitates a responsive and accessible educational tool, proving the viability of computer vision in creating inclusive religious learning environments without requiring complex server-side infrastructure.

PENERAPAN METODE PROTOTYPE DALAM PENGEMBANGAN WEBSITE KONVERSI GAMBAR VEKTOR KE MODEL 3D

2026-04-30T04:43:27+00:00

This research aims to design and build a static website capable of automatically converting SVG vector images into 3D objects. The main problem addressed is the lack of user-friendly and efficient web-based tools for converting SVG files into 3D models, which are important for 3D designers and 3D printing. The development applies the Prototype method, allowing initial prototypes to be tested and refined based on user feedback. The website is developed using JavaScript with the Three.js library for 3D object processing and visualization, and Vite as a modern development tool to ensure responsiveness. Users are able to upload SVG files, adjust object thickness, preview the conversion in real-time, and export the 3D model in STL format. The results show that this website provides a practical and interactive solution for users who require fast conversion from SVG images to 3D objects through a web platform, accessible at https://sv3dkonversi.xyz. User Acceptance Testing was conducted and achieved a score of 82.2%, indicating that users can operate the website effectively in terms of layout, interface, system, and ease of use. This demonstrates the potential of the website to support 3D designers in digital manufacturing and 3D printing workflows.

PENERAPAN MODEL ESRGAN UNTUK UPSCALING CITRA DAN VIDEO DIGITAL

2026-04-30T05:25:41+00:00

Low-resolution images and videos remain a common problem in various digital applications due to limited visual quality. Conventional interpolation-based upscaling methods often produce blurry results and lead to the loss of important texture details. This study aims to apply the Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) to improve the resolution of digital images and videos. The dataset used consists of low-resolution images and videos that are processed through preprocessing, model training, and testing stages using the Google Colab environment. The ESRGAN model is trained to generate high-resolution images while preserving visual details and structural information. Model performance is evaluated using the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and visual comparison between images before and after the upscaling process. The results show that ESRGAN significantly improves the quality of images and videos compared to conventional interpolation methods, both quantitatively and qualitatively. Therefore, the application of ESRGAN is considered effective for enhancing the resolution of digital images and videos and can be utilized in applications that require high visual quality.

MONITORING DAN NOTIFIKASI REAL-TIME PERUBAHAN FILE PADA WEB SERVER MENGGUNAKAN WATCHDOG DAN TELEGRAM BOT SEBAGAI SISTEM PERINGATAN DINI

2026-04-30T06:10:33+00:00

Web servers are critical infrastructures for delivering digital services and are highly vulnerable to unauthorized file changes that may threaten system security and service availability. However, many conventional monitoring systems still rely on periodic checking mechanisms, which often fail to provide timely detection of security incidents. This study aims to design and implement a real-time file change monitoring system on a web server using the Watchdog library and a Telegram Bot as an early warning mechanism. The research adopts an applied research method with an experimental approach. The system is developed using the Python programming language and evaluated in a local XAMPP-based web server environment, with the uploads directory selected as the monitoring target. Experimental results demonstrate that the proposed system is capable of detecting various file change events, including file creation, deletion, content modification, and file renaming, in real time without event loss. Notifications delivered via the Telegram Bot provide clear, timely, and actionable information to administrators. These findings indicate that the proposed event-driven monitoring system is effective and efficient in enhancing web server security and improving incident response capabilities.