Klasifikasi Tanaman Liar sebagai Tanaman Obat menggunakan Metode Convolutional Neural Network dengan Arsitektur Resnet-50

Fiekri, Moch. Iqbal Maulana (2025) Klasifikasi Tanaman Liar sebagai Tanaman Obat menggunakan Metode Convolutional Neural Network dengan Arsitektur Resnet-50. Undergraduate thesis, Politeknik Negeri Jember.

	Text (Abstract) Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (350kB)
	Text (Bab 1 Pendahuluan) Bab 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (416kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (292kB)
	Text (Laporan Lengkap) E41210746 - Laporan Lengkap.pdf - Submitted Version Restricted to Registered users only Download (6MB) | Request a copy

Abstract

Wild plants are often an underutilized natural resource in the health sector. Many wild plants have potential as medicinal plants, but the identification and classification of these wild plant species can be a complicated and time-consuming task. The use of technology in wild plant identification, especially in the context of their use as medicinal plants, can provide an efficient and effective solution. The results of this experiment using CNN method with Resnet-50 architecture show consistency and superiority over others. A total of 1,200 leaf images from six types of medicinal plants, namely gotu kola, brotowali, minjangan grass, sembung rambat, rambusa, and tumpang air, were used as datasets. The training results showed that the model achieved an accuracy of 97.91% and a continuously decreasing error rate, indicating a stable and accurate model performance.

Actions (login required)

View Item