Jurnal Responsive Teknik Informatika
Vol. 9 No. 02 (2025): Jurnal Responsive Teknik Informatika

Pengembangan Otomasi Inventaris Farmasi Rumah Sakit Gigi dan Mulut Berbasis YOLO

Siti Salmiah (Unknown)
Abdi, Khairul (Unknown)



Article Info

Publish Date
30 Dec 2025

Abstract

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, mAP@0.5, dan mAP@0.5:0.95. Hasil terbaik diperoleh pada epoch ke-55 dengan precision 0.9641, recall 0.9218, F1-score 0.9425, mAP@0.5 0.9796, serta mAP@0.5:0.95 0.7565. Nilai mAP@0.5 yang tinggi menunjukkan kemampuan deteksi yang sangat baik pada ambang IoU standar, sedangkan mAP@0.5:0.95 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, YOLOAbstract—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, mAP@0.5, and mAP@0.5:0.95. The best checkpoint (epoch 55) achieved 0.9641 precision, 0.9218 recall, 0.9425 F1-score, 0.9796 mAP@0.5, and 0.7565 mAP@0.5:0.95. The high mAP@0.5 indicates strong detection capability under standard IoU, while the lower mAP@0.5:0.95 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

Copyrights © 2025






Journal Info

Abbrev

JR

Publisher

Subject

Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

Description

JR: Jurnal Responsive Teknik Informatika is a scientific journal aimed at providing a platform for researchers, academics, and professionals to publish their latest research and thoughts in the field of responsive informatics engineering. This journal was established with the goal of being one of ...