Text

KLASIFIKASI JENIS LAHAN MENGGUNAKAN CNN BERBASISKAN CITRA SATELIT

---

Penilaian

---

Remote sensing is a useful technique for mapping and monitoring geographic areas. Land classification based on satellite imagery is one of the applications of remote sensing. Classifying images manually requires a lot of time and effort. The CNN method can be used to automate the image classification process. However, with various CNN architectures that have been found, it is necessary to conduct experiments to find which CNN architecture is good to use. In this study, a comparison of image classification was carried out using 3 CNN architectures, namely VGG-16, ResNet-50, and EfficientNet-B0. Architecture training and testing was carried out on the EuroSAT dataset consisting of 10 classes with a total of 27,000 images. The CNN model uses a dataset with a split ratio of 80% as training data and 20% as test data. The experiment was carried out with two variations of the input shape, with a size of 64 x 64 pixels and 224 x 224 pixels. The results showed that the best Overall Accuracy (OA) was owned by ResNet-50 at 96.93%, followed by VGG-16 at 95.22%, while EfficientNet-B0 had a fairly low accuracy with a value of 31.96%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307000324	T89331	T893312023	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T893312023

Publisher

Inderalaya : Jurusan Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2022

Collation

xv, 99 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.650 7

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Teknik Informatika
Jaringan Komunikasi Komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment