Klasifikasi Tingkat Kematangan Nanas Berdasarkan Citra Warna dengan Metode SVM 292 331
DOI:
https://doi.org/10.26623/transformatika.v23i2.13235Abstrak
Penentuan kematangan nanas manual bersifat subjektif dan tidak konsisten. Penelitian ini bertujuan membangun sistem klasifikasi nanas (Matang, SetengahMatang, Mentah) yang objektif menggunakan Support Vector Machine (SVM) berbasis citra warna. Metode ini menggunakan 2044 citra augmentasi. Fitur warna mentah (30.000 fitur) diekstraksi dan direduksi menggunakan Principal Component Analysis (PCA) menjadi 51 komponen untuk mengatasi overfitting. Model SVM (RBF) dioptimalkan dengan GridSearchCV. Hasilnya, model SVM (RBF Tuned) terpilih mencapai akurasi 81.78% pada data uji, secara signifikan mengungguli KNN (75.79%). Model ini mencapai "Good Fit" dengan selisih overfit rendah (11.04%). Kesimpulannya, kombinasi SVM dan PCA valid dan efektif.
Unduhan
Referensi
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 Zulkhan Arbi Toyibun Abdillah, Adi Prihandono
Artikel ini berlisensi 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.
