Skripsi

KLASIFIKASI SPESIES BURUNG MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK

---

Penilaian

---

Indonesia, with its high biodiversity, is home to 1,539 bird species, some of which have morphological similarities that make manual identification challenging.This research aims to develop a bird species classification model in Indonesia using a Convolutional Neural Network (CNN) with the EfficientNet-B0 architecture to improve identification accuracy and speed. The model was trained using 10 Indonesian bird species taken from 500 bird species classification secondary image dataset on Kaggle. This study compares the performance of the Rectified Linear Unit (ReLU) and Swish activation functions to determine their impact on the model's performance. The results indicate that the CNN model with the EfficientNet-B0 architecture and the Rectified Linear Unit activation function achieved the highest accuracy of 99.7%, with a precision of 99.8%, recall of 99.7%, and an f1-score of 99.7%. This performance demonstrates that the developed model can be an effective solution for automated and accurate bird species classification.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507006142	T185237	T1852372025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1852372025

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xvi, 120 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

004.07

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Prodi Teknik Informatika
Pengolahan Data--Convolutional Neural Network

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment