Media Pembelajaran Pengenalan Hewan Pada Anak Usia Dini Menggunakan Metode Convolutional Neural Networks

Ahmad, Ilham Ibnu (2025) Media Pembelajaran Pengenalan Hewan Pada Anak Usia Dini Menggunakan Metode Convolutional Neural Networks. Undergraduate thesis, Politeknik Negeri Jember.

	Text (Abstract) Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (260kB)
	Text (Bab 1 Pendahuluan) BAB 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (272kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (234kB)
	Text (Laporan Lengkap) Laporan Lengkap.pdf - Submitted Version Restricted to Registered users only Download (9MB) | Request a copy

Abstract

This study developed an interactive learning media for animal recognition aimed at early childhood education using the Convolutional Neural Network (CNN) method. The CNN model was built using the DenseNet121 architecture, achieving a high accuracy of 97%. Evaluation through the confusion matrix and classification report showed that most animal classes achieved precision, recall, and F1-scores close to 1.00. Expert validation involving six teachers from TKIT-TBIT Permata Leces confirmed that the application aligns with the early childhood education curriculum and is suitable for classroom use. Furthermore, User Acceptance Testing (UAT) conducted with 20 children revealed very high user satisfaction. Most children enjoyed using the app, liked the animal images and voice explanations, and expressed interest in using it again. These results demonstrate that the application is effective, user-friendly, and well-suited as an interactive educational tool for introducing animals to young children.

Actions (login required)

View Item