Application for Introduction to Romanization of Hangeul Writing Using Learning Vector Quantization Method
AbstractThe development of technology makes it easier for humans to access and receive information from various things. One that we can access is the culture of various countries, for example, South Korea. Talking about K-Pop, it also talks about Korean culture and language. Korean language is a language that uses characters in writing, this script is called hangeul. With so many people learning Korean and the large number of Indonesian tourists coming to Korea, a technology is needed that can provide information to users about Korean. In this study, an application was made that used one of the methods of implementing Artificial Neural Networks, namely Learning Vector Quantization to recognize hangeul writing patterns. Based on the test results using the k-Vold Cross Validation, the overall accuracy is 57%. In addition, the test uses usability testing with 5 indicators, namely Learnability, efficiency, memorability, errors and satisfaction, with an average rating of 93.3%. This shows that the application can function according to its use and makes it easier for users to recognize hangeul writing patterns along with their romanizations and translations. This application is also easy to learn, understand and use. Keywords: Pattern Introduction, Hangeul, Romanization, Artificial Neural Network, Learning Vector Quantization
Copyright info for authors
1. Authors hold the copyright in any process, procedure, or article described in the work and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors retain publishing rights to re-use all or portion of the work in different work but can not granting third-party requests for reprinting and republishing the work.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as earlier and greater citation of published work.