Jurnal Responsive Teknik Informatika

Improving Traditional Mask Recognition with CNNs and Data Augmentation

Ashabul Kahpi — Fri, 19 Dec 2025 00:00:00 +0000

This study aims to develop a classification system for Indonesian traditional masks using the Convolutional Neural Network (CNN) method. Traditional masks exhibit rich visual diversity that reflects the cultural identities of various regions in Indonesia; however, manual identification is time-consuming and prone to errors. The system developed in this study is capable of classifying five types of masks—Cirebon, Balinese, Malangan, Dayak, and Betawi masks—based on digital images with a high level of accuracy. The proposed CNN model achieved an accuracy of 92.3% on the test dataset, with an average macro F1-score of 0.91. Data preprocessing and augmentation techniques, including rotation, flipping, and brightness adjustment, effectively enhanced the model’s performance by reducing the risk of overfitting. These results demonstrate the strong potential of deep learning technology in supporting cultural heritage preservation through the digitalization and automated classification of Indonesian traditional masks.

Sistem Informasi Administrasi Yayasan Daarul Qur’an Wal-Hadits Nw Batam Berbasis Web

Dewi Sartika Wati, Army Trilidia Devega — Sat, 20 Dec 2025 00:00:00 +0000

Yayasan Daarul Qur’an Wal-Hadits NW mempunyai website masih terbatas profile saja dan gambar yang mengakibatkan informasi belum begitu lengkap untuk dapat dibaca oleh santri, orang dan masyarakat umum dan pengolahan administrasi menggunakan aplikasi bantu Microsoft office excels dan word dalam membuat data guru dan santri, serta informasi kami tempelkan juga di mading atau di depan kelas untuk dapat dibaca oleh guru dan santri mengakibatkan informasi belum bisa menjadi informasi ke masyarakat umum. Maka penulis merumuskan masalah bagaimana merancang, menguji dan mengimplementasikan website dan administrasi di Yayasan Daarul Qur’an Wal-Hadits NW Batam. Metode menggunakan model waterfall dengan tahapan analisis kebutuhan, desain sistem menggunakan Unified Modeling Language, implementasi, pengujian dengan black box testing, dan deployment. Hasil Perancangan website dan administrasi dengan tahapan model waterfall menghasilkan analisis sistem, desain sistem dengan pemodelan UML dan empat diagram serta delapan belas tabel untuk mendukung pembuatan website. Pengujian dan penerapan website dan administrasi yang diuji secara localhost dan online di alamat https://darulqurannwbatam.com/ serta blackbox testing dinyatakan sistem berhasil digunakan. Website dan administrasi sebagai sarana informasi, promosi serta sebagai alat bantu administrasi Yayasan Daarul Qur’an Wal-Hadits NW Batam dalam mengolah data guru dan santri serta menjadi informasi yang dapat dilihat oleh masyarakat umum. Website dan administrasi memenuhi unsur pengguna sesuai perkembangan teknologi yang lebih kompleks dengan support berbagai smartphone dan dashboard perlu dikembang serta peningkatan sumber daya manusia, yaitu sumber daya dalam pengoperasian sistem dan mampu merawat, memelihara sistem tersebut dengan baik.

Data Quality Management dalam Data Warehouse: Tinjauan Literatur

Romiko Afriantoni, Naisya Nindy Pangestuti — Sun, 28 Dec 2025 00:00:00 +0000

This study presents a systematic literature review of Data Quality Management (DQM) in data warehouse environments, aiming to map key dimensions, processes, and architectural/technological enablers, and to identify research gaps. Searches were conducted across Scopus, ScienceDirect, IEEE Xplore, ACM Digital Library, SpringerLink, and Google Scholar (as a complement) for the period 2009–2025, following PRISMA 2020. Of 200 initial records, 133 were excluded during the first screening, 67 underwent further assessment, and 6 studies met the inclusion criteria for in-depth analysis. Thematic synthesis indicates that effective DQM rests on four integrated pillars: (1) standardized quality dimensions and metrics (accuracy, completeness, consistency, timeliness, and traceability), (2) prevention–detection–correction processes embedded along the ETL/ELT pipeline (including consistent SCD policies and handling of late-arriving data), (3) architectural/technological support (automated data tests within CI/CD, catalogs/metadata, data lineage, observability, and data contracts), and (4) governance that clarifies roles and accountability (data owners/stewards) with incident-response procedures. Practically, organizations should start from critical data elements and high-priority consumption paths, translating SLA/SLI into executable rules. Limitations include the small number of included studies and contextual heterogeneity, motivating further work on cross-domain metric standardization, open DQM benchmarks, cost–benefit evaluations of observability/contract enforcement, and the impact of data quality on analytic/AI performance in near real-time settings.

Improving Market Transparency via a Web-Based Food Price Monitoring System

Indra Indra — Tue, 30 Dec 2025 00:00:00 +0000

This study aims to design and develop a web-based food price monitoring system in Regency X to address delays and data inaccuracies found in conventional systems. A qualitative descriptive approach is employed using the Waterfall system development method, encompassing requirements analysis, system design, implementation, and testing. Primary data are collected through interviews and observations in traditional markets, while secondary data are obtained from official documents. The system is designed using Unified Modeling Language (UML) and developed with PHP and MySQL. White Box and Black Box testing results indicate that the system operates in accordance with user requirements, with a high level of user satisfaction based on survey results. The system enables real-time monitoring of food prices, accelerates information dissemination, and enhances transparency in the local market. In conclusion, the system effectively supports decision-making related to food price control; however, further development such as automatic data integration and price prediction features is still required.

Pengembangan Otomasi Inventaris Farmasi Rumah Sakit Gigi dan Mulut Berbasis YOLO

Siti Salmiah, Khairul Abdi — Tue, 30 Dec 2025 00:00:00 +0000

Abstrak—Penelitian ini mengembangkan sistem otomasi inventaris farmasi pada rumah sakit gigi dan mulut berbasis deteksi objek menggunakan YOLO. Dataset disusun dari 183 citra produk farmasi berformat JPEG yang mencakup 11 kelas, kemudian dibagi menjadi data latih dan validasi dengan rasio 80:20. Proses anotasi dilakukan menggunakan Label Studio dan disimpan dalam format label YOLO (.txt) berisi class_id serta koordinat bounding box ter-normalisasi. Model YOLO11s dilatih menggunakan bobot pralatih selama 60 epoch dengan ukuran input 640 piksel. Evaluasi dilakukan menggunakan precision, recall, F1-score, [email protected], dan [email protected]:0.95. Hasil terbaik diperoleh pada epoch ke-55 dengan precision 0.9641, recall 0.9218, F1-score 0.9425, [email protected] 0.9796, serta [email protected]:0.95 0.7565. Nilai [email protected] yang tinggi menunjukkan kemampuan deteksi yang sangat baik pada ambang IoU standar, sedangkan [email protected]:0.95 mengindikasikan masih adanya ruang peningkatan presisi lokalisasi bounding box pada ambang IoU yang lebih ketat. Sistem yang diusulkan berpotensi mempercepat inspeksi stok dan meningkatkan konsistensi pencatatan inventaris berbasis citra.

Kata kunci: inventaris farmasi, deteksi objek, YOLO

Abstract—This study develops an automated pharmacy inventory approach for a dental and oral hospital using YOLO-based object detection. A dataset of 183 product images covering 11 classes was collected and split into training and validation sets with an 80:20 ratio. Annotations were created using Label Studio and exported in YOLO format (.txt) with normalized bounding box coordinates. A YOLO11s model with pretrained weights was trained for 60 epochs using a 640-pixel input size. Performance was evaluated using precision, recall, F1-score, [email protected], and [email protected]:0.95. The best checkpoint (epoch 55) achieved 0.9641 precision, 0.9218 recall, 0.9425 F1-score, 0.9796 [email protected], and 0.7565 [email protected]:0.95. The high [email protected] indicates strong detection capability under standard IoU, while the lower [email protected]:0.95 suggests opportunities to improve bounding-box localization at stricter IoU thresholds. The proposed approach can accelerate stock inspection and improve consistency of image-based inventory recording.

Keywords: pharmacy inventory, object detection, YOLO