PENGENALAN HURUF LATIN PADA ANAK USIA DINI DENGAN PENERAPAN METODE BACKPROPAGATION

Penulis

DOI:

https://doi.org/10.46576/djtechno.v2i2.1480

Abstrak

Early childhood has difficulty remembering Latin letters or Roman characters than adults. Some of the factors that cause it are cognitive development, motivation, interest in learning, emotions and environmental factors. To overcome this, an innovative media is needed so that children can easily remember Latin letters. One of the innovative media applies digital image processing techniques and artificial intelligence. The fonts used are 10 types of letter models with image processing techniques such as preprocessing, binaryization, pixel mapping and creating vector as feature extraction.  While the artificial intelligence used is the backpropagation method. The total data is 208 letter images with 625 input features with 500 epochs, the best learning rate used by the system is 0.025 so that the best training accuracy is 93.96% and testing accuracy is 92.31%.

Referensi

Akram, R., Novianda, Muttaqin, K., & Dinata, R. K. (2020). Sistem Pengenalan Huruf Latin Dengan Metode Perceptron Berbasis Neural Network. Jurnal Nasional Informatika dan Teknologi Jaringan, 1, 206–211.

Cahyadi, E., & Santoso, J. (2015). Pengenalan Abjad Aksara Latin pada Komputer Menggunakan Metode Skeletoning. Seminar Nasional “Inovasi dalam Desain dan Teknologi,†137–142.

Fitri, Z. E., & Imron, A. M. N. (2021). Classification of White Blood Cell Abnormalities for Early Detection of Myeloproliferative Neoplasms Syndrome Using Backpropagation. Proceedings of the 1st International Biomedical Engineering, on Electronics, Conference and Health Informatics, 746, 499–507. https://link.springer.com/10.1007/978-981-33-6926-9

Fitri, Z. E., Nuhanatika, U., Madjid, A., & Imron, A. M. N. (2020). Penentuan Tingkat Kematangan Cabe Rawit (Capsicum frutescens L.) Berdasarkan Gray Level Co-Occurrence Matrix. Jurnal Teknologi Informasi dan Terapan, 7(1), 1–5. https://doi.org/10.25047/jtit.v7i1.121

Fitri, Z. E., Rizkiyah, R., Madjid, A., & Imron, A. M. N. (2020). Penerapan Neural Network untuk Klasifkasi Kerusakan Mutu Tomat. Jurnal Rekayasa Elektrika, 16(1), 44–49. https://doi.org/10.17529/jre.v16i1.15535

Masrani, H., Ruslianto, I., & Ilhamsyah. (2018). Aplikasi Pengenalan Pola Pada Huruf Tulisan Tangan Menggunakan Jaringan Saraf Tiruan Dengan Metode Ekstraksi Fitur Geometri. Coding, Sistem Komputer Untan, 06(02), 69–78. http://jurnal.untan.ac.id/index.php/jcskommipa/article/view/26674

Pangastuti, R., & Hanum, S. F. (2017). Pengenalan Abjad pada Anak Usia Dini Melalui Media Kartu Huruf. Al-Hikmah : Indonesian Journal of Early Childhood Islamic Education, 1(1), 51–66. https://doi.org/10.35896/ijecie.v1i1.4

Purbayanti, T. S. (2018). Pengenalan Tulisan Tangan Huruf Latin Dengan Menggunakan Metode K-Nearest Neighbour. In Simki-Techsain (Vol. 2, Nomor 2). Universitas Nusantara PGRI Kediri.

Samsiyah, N. (2018). Penerapan Teknik Kontrastif Dalam Menulis Tegak Bersambung Pada Siswa Kelas 1 Sekolah Dasar Kabupaten Madiun. Paramasastra, 5(1). https://doi.org/10.26740/parama.v5i1.2730

Susanto, A. (2014). Perkembangan Anak Usia Dini Pengantar dalam Berbagai Aspeknya (A. Susanto (ed.); 3 ed.). Kencana Prenadamedia Group.

Diterbitkan

2021-12-10

Terbitan

Bagian

Articles