Convolutional Neural Network Method for Classification of Syllables in Javanese Script

  • Yuli Fauziah Informatics Department, Universitas Pembangunan Nasional “Veteran” Yogyakarta, Yogyakarta
  • Kevin Aprilianta Informatics Department, Universitas Pembangunan Nasional “Veteran” Yogyakarta, Yogyakarta
  • Heru Cahya Rustamaji Informatics Department, Universitas Pembangunan Nasional “Veteran” Yogyakarta, Yogyakarta
Abstract views: 5 , PDF downloads: 2
Keywords: Javanese Script, Pattern Recognition, Convolutional Neural Network

Abstract

Javanese script is one of the languages which are a typical Javanese culture. Javanese script is seen in its use in writing the name of a particular agency or location that has historical and tourism value. The use of Javanese script in public places makes the existence of this script seen by many people, not only by the Javanese people. Some of them have difficulty recognizing the Javanese characters they encounter. One method of pattern recognition and image processing is Convolutional Neural Network (CNN). CNN is a method that uses convolution operations in performing feature extraction on images as a basis for classification. The process consists of initial data processing, classification, and syllable formation. The classification consists of 48 classes covering Javanese script types, namely basic letters (Carakan) and voice-modifying scripts (Sandhangan). It is tested with multi-class confusion matrix scenarios to determine the accuracy, precision, and recall of the built CNN model. The CNN architecture consists of three convolution layers with max-pooling operations. The training configuration includes a learning rate of 0.0001, and the number of filters for each convolution layer is 32, 64, and 128 filters. The dropout value used is 0.5, and the number of neurons in the fully-connected layer is 1,024 neurons. The average performance value of accuracy reached 87.65%, the average precision value was 88.01%, and the average recall value was 87.70%.

Downloads

Download data is not yet available.

References

[1] E. Nurhayati, Mulyana, H. Mulyani, and Suwardi, “Strategi Pemertahanan Bahasa Jawa di Provinsi Daerah Istimewa Yogyakarta,” LITERA J. Penelit. Bahasa, Sastra, dan Pengajarannya, vol. 12, no. 1, pp. 159–166, 2013.
[2] M. L. Afakh, A. Risnumawan, M. E. Anggraeni, M. N. Tamara, and E. S. Ningrum, “Aksara jawa text detection in scene images using convolutional neural network,” in Proceedings - International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017, 2017, vol. 2017-Janua, pp. 77–82.
[3] G. S. Budhi and R. Adipranata, “Handwritten javanese character recognition using several artificial neural network methods,” J. ICT Res. Appl., vol. 8, no. 3, pp. 195–212, Aug. 2015.
[4] C. A. Sari, M. W. Kuncoro, D. R. I. M. Setiadi, and E. H. Rachmawanto, “Roundness and eccentricity feature extraction for Javanese handwritten character recognition based on K-nearest neighbor,” 2018 Int. Semin. Res. Inf. Technol. Intell. Syst. ISRITI 2018, pp. 5–10, Nov. 2018.
[5] Y. Sugianela and N. Suciati, “Javanese Document Image Recognition Using Multiclass Support Vector Machine,” CommIT (Communication Inf. Technol. J., vol. 13, no. 1, pp. 25–30, May 2019.
[6] I. F. Katili, F. D. Esabella, and A. Luthfiarta, “Pattern Recognition Of Javanese Letter Using Template Matching Correlation Method,” J. Appl. Intell. Syst., vol. 3, no. 2, pp. 49–56, Dec. 2018.
[7] M. A. Wibowo, M. Soleh, W. Pradani, A. N. Hidayanto, and A. M. Arymurthy, “Handwritten Javanese Character Recognition using Descriminative Deep Learning Technique,” Inf. Technol. Inf. Syst. Electr. Eng., vol. 2, pp. 325–330, 2017.
[8] C. K. Dewa, A. L. Fadhilah, and A. Afiahayati, “Convolutional Neural Networks for Handwritten Javanese Character Recognition,” IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 12, no. 1, pp. 83–94, Jan. 2018.
[9] Rismiyati, Khadijah, and A. Nurhadiyatna, “Deep learning for handwritten Javanese character recognition,” in Proceedings - 2017 1st International Conference on Informatics and Computational Sciences, ICICoS 2017, 2017, vol. 2018-January, pp. 59–63.
[10] Rismiyati, Khadijah, and D. E. Riyanto, “HOG and Zone Base Features for Handwritten Javanese Character Classification,” in 2018 2nd International Conference on Informatics and Computational Sciences (ICICoS), 2018, pp. 1–5.
[11] Rismiyati, Khadijah, and A. Nurhadiyatna, “Deep Learning for Handwritten Javanese Character Recognition,” Informatics Comput. Sci., vol. 1, pp. 59–64, 2017.
[12] L. L. Zhangrila, “Accuracy Level of $p Algorithm for Javanese Script Detection on Android-Based Application,” in Procedia Computer Science, 2018, vol. 135, pp. 416–424.
[13] Darusuprapta, “Pedoman Penulisan Aksara Jawa.” Yayasan Pustaka Nusatama, Yogyakarta, p. 69, 2002.
[14] D. Tanaya and M. Adriani, “Word Segmentation for Javanese Character Using Dictionary, SVM, and CRF,” in Proceedings of the 2018 International Conference on Asian Language Processing, IALP 2018, 2019, pp. 240–243.
[15] D. Tanaya and M. Adriani, “Dictionary-based Word Segmentation for Javanese,” Procedia Comput. Sci., vol. 81, pp. 208–213, 2016.
[16] D. Tanaya and M. Adriani, “Word Segmentation for Javanese Character using Dictionary , SVM , and CRF,” Int. Conf. Asian Lang. Process., pp. 240–243, 2018.
[17] G. S. Budhi and R. Adipranata, “Handwritten Javanese Character Recognition Using Several Artificial Neural Network Methods,” J. ICT Res. Appl., vol. 8, no. 3, pp. 195–212, Mar. 2015.
[18] N. Srivastava, G. Hinton, A. Krizhevsky, and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” 2014.
[19] T. Developers, “TensorFlow,” Nov. 2021.
[20] K. M. Ting, “Confusion Matrix,” Encycl. Mach. Learn. Data Min., pp. 260–260, 2017.
Published
2021-11-30
How to Cite
Yuli Fauziah, Kevin Aprilianta, & Heru Cahya Rustamaji. (2021). Convolutional Neural Network Method for Classification of Syllables in Javanese Script. International Journal of Artificial Intelligence & Robotics (IJAIR), 3(2), 80-89. https://doi.org/10.25139/ijair.v3i2.4395