IMPLEMENTING A CONVOLUTIONAL NEURAL NETWORK ALGORITHM FOR PEST DETECTION IN GREEN MUSTARD PLANTS

WIWAHA SOEKARNO, GILANG (2025) IMPLEMENTING A CONVOLUTIONAL NEURAL NETWORK ALGORITHM FOR PEST DETECTION IN GREEN MUSTARD PLANTS. Tugas Akhir thesis, University of Technology Yogyakarta.

This is the latest version of this item.

[img] Text
5210411293_GILANG WIWAHA SOEKARNO_ABSTRAK.pdf
Download (10kB)

Abstract

Green mustard greens are gaining increasing attention due to their high economic value. However, farming green mustard greens faces several challenges, including pest infestations, which, if left unaddressed, can result in poor yields and crop failure. In this study, the authors employed a deep learning algorithm, the Convolutional Neural Network (CNN), to detect pests in images of green mustard greens leaves. This method uses a convolution process that breaks down images into smaller segments and then inputs them into a new array for prediction. The dataset comprised 1,000 images divided into two classes: images with pests and images without pests. The authors achieved a best experimental accuracy of 96% and a validation accuracy of 97% using the NASNet Mobile architecture. Therefore, it can be concluded that the CNN deep learning algorithm with the NASNet Mobile architecture can effectively detect pests on green mustard greens. Keywords: CNN, Classification, Green Mustard Greens, Deep Learning

Item Type: Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Sains Dan Teknologi > S1 Informatika
Depositing User: Kaprodi S1 Informatika UTY
Date Deposited: 13 Nov 2025 04:48
Last Modified: 13 Nov 2025 04:48
URI: http://eprints.uty.ac.id/id/eprint/19410

Available Versions of this Item

Actions (login required)

View Item View Item
UTY Open Access is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.