Skripsi

PERBANDINGAN ARSITEKTUR CNN DAN VISION TRANSFORMER UNTUK KLASIFIKASI PENYAKIT DAUN SELADA.

---

Lettuce (Lactuca sativa L.), is a commodity crop that is frequently consumed around the world. During cultivation, lettuce often faces challenges such as diseases that can cause losses. Classification of diseases on lettuce leaves is an important challenge in maintaining the quality and quantity of crop yields.. This study compares the performance of Convolutional Neural Network (CNN) and Vision Transformer (ViT) architectures for classifying lettuce leaf diseases. The dataset comprises 2,956 lettuce leaf images across five disease classes: Healthy, Downy Mildew, Powdery Mildew, Septoria Blight, and Wilt and Leaf Blight. The models evaluated include Custom CNN, InceptionV3, Modified InceptionV3, and Vision Transformer. The process involved data preprocessing, model training, and performance evaluation based on accuracy, precision, recall, and F1-score. The results indicate that Modified InceptionV3 achieved the best performance with a test accuracy of 98%, precision of 99%, recall of 99%, and F1-score of 99%, outperforming Vision Transformer, which achieved an accuracy of 97%. The superiority of Modified InceptionV3 lies in layer tuning and parameter optimization, while Vision Transformer excels at capturing complex visual patterns.

---

Availability

Detail Information

Series Title

-

Call Number

T1627602024

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2024

Collation

xxii, 68 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.015 107

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Prodi Teknik Informatika
Prinsip Matematika dalam Ilmu Komputer

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment