Utilizing E-learning with Pattern Recognition and Mnemonic to Enhance Japanese Characters Learning Experience

Tamara, Astrid and Rusli, Andre and Hansun, Seng (2019) Utilizing E-learning with Pattern Recognition and Mnemonic to Enhance Japanese Characters Learning Experience. In: 2019 International Conference on Engineering, Science, and Industrial Applications (ICESI), 22-24 Aug. 2019, Tokyo, Japan.

Full text not available from this repository.

Abstract

Japan is popular for future career purpose despite the difficulty to learn Japanese. Japanese character is different from internationally used alphabet system which causes difficulty for international students to acquire. Pictograph and keyword mnemonic are used in this research so Japanese characters can be visualized as pictures and sentences to aid in memorization. Japanese character learning material with mnemonic is packaged in an e-learning application so students can learn anywhere and anytime. Pattern recognition using Convolutional Neural Network algorithm is implemented to determine the correctness of user's written input. This research aims to design and develop Japanese character e-learning application using mnemonic method and pattern recognition using Convolutional Neural Network and determine whether developed e-learning application contributes to significant difference in Japanese character learning result. Based on conducted research, Japanese character e-learning application using mnemonic method and pattern recognition using Convolutional Neural Network has been designed and developed. Implementation of pattern recognition using Convolutional Neural Network resulted in a model with accuracy of training 99.19%, validation 100%, and testing 88.08%. While the difference between pre-test and post-test result of experiment and control class concludes that there is no significant difference, SMA Citra Kasih students expressed their interest to learn Japanese with developed e-learning application during the interview

Item Type: Conference or Workshop Item (Paper)
Subjects: 000 Computer Science, Information and General Works > 000 Computer Science, Knowledge and Systems > 005 Computer Programming
Divisions: Faculty of Engineering & Informatics > Informatics
Depositing User: mr admin umn
Date Deposited: 13 Oct 2021 07:21
Last Modified: 13 Oct 2021 07:21
URI: https://kc.umn.ac.id/id/eprint/18725

Actions (login required)

View Item View Item