PENERAPAN ALGORITMA RECURRENT NEURAL NETWORKS (RNN) UNTUK KLASIFIKASI ULOS BATAK TOBA

Authors

  • Dameria Esterlina Br Jabat STMIK Pelita Nusantara, Indonesia
  • Liskedame Yanti Sipayung STMIK Pelita Nusantara, Indonesia
  • Kevin Raih Syahputra Dakhi STMIK Pelita Nusantara, Indonesia

Keywords:

Deep Learning, algoritma , Jaringan Syaraf Tiruan

Abstract

Ulos has become a cultural heritage passed down from generation to generation for the Batak people. Ulos is a type of icon in the form of cloth typical of the Batak people in North Sumatra Province. This research aims to describe the various types and functions of Ulos Batak woven cloth which are still poorly understood by mothers or people who live in urban areas. This research can make it easier to recognize ulos patterns which will result in understanding the function of each type of ulos in the Batak community. One of the artificial intelligence technologies is machine learning using the computer vision method, one of the machine learning models called Artificial Neural Networks (ANN) which uses many layers, so that with this model the computing performance will be better using Deep Learning techniques.

References

Banjarnahor, K. S., & Limbong, T. (2023, September). Rancang Bangun Aplikasi Game Huling-Huling Acca Atau Teka-Teki Suku Batak Berbasis Android. In Seminar Nasional Inovasi Sains Teknologi Informasi Komputer (pp. 97-110).

Deminar, D., & Limbong, T. (2023, October). Rancang Bangun Aplikasi Game Edukasi Pakaian Adat Batak Berbasis Android. In Seminar Nasional Inovasi Sains Teknologi Informasi Komputer (pp. 156-172).

Koutnik, J., Greff, K., Gomez, F., & Schmidhuber, J. (2014, June). A clockwork rnn. In International conference on machine learning (pp. 1863-1871). PMLR.https://algorit.ma/blog/rnn-adalah-2022/

Sherstinsky, A. (2020). Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phenomena, 404, 132306.

Yin, W., Kann, K., Yu, M., & Schütze, H. (2017). Comparative study of CNN and RNN for natural language processing. arXiv preprint arXiv:1702.01923.

Downloads

Published

2024-06-19

Issue

Section

Articles