Please use this identifier to cite or link to this item:
https://repositori.uma.ac.id/handle/123456789/26186
Title: | Klasifikasi Penyakit Daun pada Tanaman Tomat Menggunakan Resnet-152 |
Other Titles: | Classification of Leaf Diseases in Tomato Plants Using Resnet-152 |
Authors: | Napitupulu, Simon Palti |
metadata.dc.contributor.advisor: | Muhathir |
Keywords: | Klasifikasi;Deep Learning;ResNet-152;Penyakit Daun Tomat;Classification;Tomato Leaf Disease |
Issue Date: | Aug-2024 |
Publisher: | Universitas Medan Area |
Series/Report no.: | NPM;208160028 |
Abstract: | Penyakit daun pada tanaman tomat dapat menurunkan hasil panen secara signifikan, sehingga diperlukan identifikasi yang cepat dan akurat. Penelitian ini bertujuan untuk mengklasifikasikan penyakit daun pada tanaman tomat menggunakan model deep learning dengan arsitektur ResNet-152. Data yang digunakan dalam penelitian ini terdiri dari 10.000 gambar daun tomat, dengan sembilan jenis penyakit dan satu kategori tanaman sehat, yang diperoleh dari Kaggle. Data dibagi menjadi tiga bagian: train, val dan test. Model ini dievaluasi menggunakan confusion matrix untuk menghitung accuracy, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa ResNet-152 mampu mengklasifikasikan penyakit daun tomat dengan akurasi rata-rata 99,10%. Penelitian ini membuktikan bahwa ResNet-152 mampu dalam mendeteksi penyakit daun tomat dan dapat membantu petani mengidentifikasi penyakit secara cepat dan akurat. Penelitian selanjutnya disarankan menggunakan dataset yang lebih besar dan beragam. Leaf diseases in tomato plants can significantly reduce crop yields, making rapid and accurate identification essential. This research aimed to classify leaf diseases in tomato plants using a deep learning model with a ResNet-152 architecture. The dataset used in this research consisted of 10,000 tomato leaf images, including nine types of diseases and one healthy category, sourced from Kaggle. The data was divided into three parts: train, validation, and test. The model was evaluated using a confusion matrix to calculate accuracy, precision, recall, and F1-score. The results showed that ResNet-152 can classify tomato leaf diseases with an average accuracy of 99.10%. This research demonstrated that ResNet-152 is capable of detecting tomato leaf diseases and can assist farmers in identifying diseases quickly and accurately. Future studies are recommended to use larger and more diverse datasets. |
Description: | 60 Halaman |
URI: | https://repositori.uma.ac.id/handle/123456789/26186 |
Appears in Collections: | SP - Informatic Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
208160028 - Simon Palti Napitupulu Fulltext.pdf | Cover, Abstract, Chapter I, II, III, V, Bibliography | 1.25 MB | Adobe PDF | View/Open |
208160028 - Simon Palti Napitupulu Chapter IV.pdf Restricted Access | Chapter IV | 824.45 kB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.