Deteksi Area Penyakit Jambu Biji menggunakan YOLOv8 dan K-Means Clustering
DOI:
https://doi.org/10.26623/transformatika.v23i2.13234Abstract
Produktivitas tanaman jambu biji (Psidium guajava L.) menghadapi ancaman serius dari penyakit Phytophthora, Scab, dan Stylar End Rot, namun metode deteksi konvensional seringkali memiliki keterbatasan dalam melokalisasi area infeksi secara akurat. Penelitian ini mengusulkan sistem deteksi terintegrasi menggunakan algoritma YOLOv8s untuk deteksi objek real-time dan K-Means Clustering untuk segmentasi area penyakit. Model dilatih menggunakan 600 citra dengan pembagian data latih, validasi, dan uji sebesar 50:40:10. Hasil pengujian menunjukkan performa tinggi dengan nilai Mean Average Precision (mAP50-95) mencapai 0.891 pada data uji, konsisten dengan hasil validasi (0.894), serta waktu inferensi rata-rata 26.1 ms. Sistem ini berkontribusi dalam menyediakan solusi pemantauan penyakit yang layak untuk aplikasi real-time, di mana integrasi K-Means terbukti efektif memvisualisasikan area terinfeksi secara presisi untuk analisis tingkat keparahan penyakit.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Naufal Hesti
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
Transformatika is licensed under a Creative Commons Attribution 4.0 International License.
