Studi Komparasi Metode Machine Learning untuk Klasifikasi Citra Huruf Vokal Hiragana
DOI:
https://doi.org/10.30865/mib.v5i3.3083Keywords:
Hiragana, Image Classification, Naïve Bayes, SVM, Decision Tree, Random Forest, KNNAbstract
Japanese is one of the most difficult languages to understand and read. Japanese writing that does not use the alphabet is the reason for the difficulty of the Japanese language to read. There are three types of Japanese, namely kanji, katakana, and hiragana. Hiragana letters are the most commonly used type of writing. In addition, hiragana has a cursive nature, so each person's writing will be different. Machine learning methods can be used to read Japanese letters by recognizing the image of the letters. The Japanese letters that are used in this study are hiragana vowels. This study focuses on conducting a comparative study of machine learning methods for the image classification of Japanese letters. The machine learning methods that were successfully compared are Naïve Bayes, Support Vector Machine, Decision Tree, Random Forest, and K-Nearest Neighbor. The results of the comparative study show that the K-Nearest Neighbor method is the best method for image classification of hiragana vowels. K-Nearest Neighbor gets an accuracy of 89.4% with a low error rate.References
P. UNIDA, “Bahasa Tersulit di Dunia, Memang ada Bahasa yang Sulit?,†2020. [Online]. Available: http://pps.unida.gontor.ac.id/bahasa-tersulit-di-dunia-memang-ada-bahasa-yang-sulit/. [Accessed: 11-Jun-2021].
R. Eriawan and M. A. Putri, “Faktor Penyebab Kesulitan Belajar Bahasa Jepang Mahasiswa Tahun Masuk 2018 Kelas International Program Strudi Pendidikan Bahasa Inggris UNP,†OMIYAGE, vol. 3, no. 2, pp. 20–32, 2020.
S. Monoarfa, “Tingkat Kemampuan Membaca Teks Berbahasa Jepang Dalam Penguasaan Huruf Kanji Sebagai Dasar Terjemahan Yang Tepat,†Stud. Soc. Sci., vol. 2, no. 1, p. 22, 2019.
R. I. Arief, L. Wahyuni, and K. Puspita, “Penerapan Metode Linear Congruent Method ( Lcm ) Pada Perangkat Lunak Tebak Huruf Hiragana Berbasis Android,†IT J., vol. 7, no. 1, pp. 63–72, 2019.
S. Aulia and A. Setiawan, “Pengenalan Tulisan Tangan Karakter Hiragana Menggunakan Dct, Dwt, Dan K-Nearest Neighbor,†J. Elektro dan Telekomun. Terap., vol. 4, no. 1, p. 467, 2017.
C. Umam and L. Budi Handoko, “Convolutional Neural Network (CNN) Untuk Identifkasi Karakter Hiragana,†in Prosiding Seminar Nasional Lppm Ump, 2020, vol. 0, no. 0, pp. 527–533.
R. Umar, I. Riadi, and D. A. Faroek, “Komparasi Image Matching Menggunakan Metode K-Nearest Neighbor ( KNN ) dan Metode Support Vector Machine ( SVM ),†J. Appl. Informatics Comput., vol. 4, no. 2, pp. 124–131, 2020.
K. Auliasari and M. Kertaningtyas, “Studi Komparasi Klasifikasi Pola Tekstur Citra Digital Menggunakan Metode K-Means Dan Naïve Bayes,†J. Inform., vol. 18, no. 2, pp. 175–185, 2018.
S. Hartono, H. Sujaini, and A. Perwitasari, “Komparasi Algoritma Nonparametrik untuk Klasifikasi Citra Wajah Berdasarkan Suku di Indonesia,†J. Edukasi dan Penelit. Inform., vol. 6, no. 3, pp. 338–343, 2020.
H. Sulaiman, D. Riana, and A. Rifai, “Perbandingan Algoritma Decision Tree C4 . 5 dan Naive Bayes pada Analisis Tekstur Gray Level Co - occurrence Matrix Menggunakan Citra Wajah,†vol. 10, pp. 470–479, 2021.
D. Abdullah and E. D. Putra, “Komparasi Perbaikan Kualitas Segmentasi Pada Citra Digital Metode Fuzzy C-Means Dan Otsu,†Pseudocode, vol. 4, no. 1, pp. 71–80, 2017.
D. S. Tobias and A. R. Widiarti, “Deteksi Glaukoma pada Citra Fundus Retina dengan Metode K-Nearest Neighbor,†in Seminar Nasional Ilmu Komputer(SNIK 2016), 2016, pp. 92–99.
F. Muwardi and A. Fadlil, “Sistem Pengenalan Bunga Berbasis Pengolahan Citra dan Pengklasifikasi Jarak,†J. Ilm. Tek. Elektro Komput. dan Inform., vol. 3, no. 2, pp. 124–131, 2017.
D. Berrar, “Cross-validation,†Encycl. Bioinforma. Comput. Biol. ABC Bioinforma., vol. 1, pp. 542–545, 2018.
M. Vadivukarassi, N. Puviarasan, and P. Aruna, “Sentimental Analysis of Tweets Using Naive Bayes Algorithm,†World Appl. Sci. J., vol. 35, no. 1, pp. 54–59, 2017.
E. Ahishakiye, E. O. Omulo, D. Taremwa, and I. Niyonzima, “Crime prediction using Decision Tree (J48) classification algorithm,†Int. J. Comput. Inf. Technol., vol. 06, no. 03, pp. 188–195, 2017.
T. B. Sasongko, “Komparasi dan Analisis Kinerja Model Algoritma SVM dan PSO-SVM (Studi Kasus Klasifikasi Jalur Minat SMA),†J. Tek. Inform. dan Sist. Inf., vol. 2, no. 2, pp. 244–253, 2016.
F. Rahutomo, P. Y. Saputra, and M. A. Fidyawan, “IMPLEMENTASI TWITTER SENTIMENT ANALYSIS UNTUK REVIEW FILM MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE,†J. Inform. Polinema, vol. 4, no. 2, pp. 93–100, 2016.
Y. Xu, X. Zhao, Y. Chen, and Z. Yang, “Research on a mixed gas classification algorithm based on extreme random tree,†Appl. Sci., vol. 9, no. 9, 2019.
Mustakim and G. Oktaviani F, “Algoritma K-Nearest Neighbor Classification Sebagai Sistem Prediksi Predikat Prestasi Mahasiswa,†vol. 13, no. 2, pp. 195–202, 2016.
A. Pandey and A. Jain, “Comparative Analysis of KNN Algorithm using Various Normalization Techniques,†Int. J. Comput. Netw. Inf. Secur., vol. 9, no. 11, pp. 36–42, 2017.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
