Efficient Pattern Recognition of Sundanese Script Variants Using CNN
This research aims to apply pattern recognition technology, specifically through the Convolutional Neural Network (CNN) approach, in identifying and translating Sundanese script accurately. This research is focused on recognizing rarangken script patterns based on ngalagena script in Indonesian cult...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ikatan Ahli Informatika Indonesia
2024-12-01
|
| Series: | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) |
| Subjects: | |
| Online Access: | https://jurnal.iaii.or.id/index.php/RESTI/article/view/6122 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544030907793408 |
|---|---|
| author | Muhammad Husni Wahid Erik Iman Heri Ujianto |
| author_facet | Muhammad Husni Wahid Erik Iman Heri Ujianto |
| author_sort | Muhammad Husni Wahid |
| collection | DOAJ |
| description | This research aims to apply pattern recognition technology, specifically through the Convolutional Neural Network (CNN) approach, in identifying and translating Sundanese script accurately. This research is focused on recognizing rarangken script patterns based on ngalagena script in Indonesian cultural heritage. This study uses the MobileNetV2 based CNN model, utilizing transfer learning and trained for 50 epochs using the Adam optimizer with a learning rate of 0.0001, to achieve a training accuracy of 98.75% and test accuracy of 96.95% in 1 hour and 23 minutes, respectively. The results of the study show that the simpler CNN architecture without augmentation achieved the highest accuracy of 99.26%, and the augmented CNN model achieved 94.42% accuracy in 2 hours and 22 minutes. These results enable practical applications in both education and cultural preservation, demonstrating how modern technology can effectively contribute to maintaining traditional cultural elements in the digital era. |
| format | Article |
| id | doaj-art-019c907404cd4fe386afda6a46c942f1 |
| institution | Kabale University |
| issn | 2580-0760 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Ikatan Ahli Informatika Indonesia |
| record_format | Article |
| series | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) |
| spelling | doaj-art-019c907404cd4fe386afda6a46c942f12025-01-13T03:30:32ZengIkatan Ahli Informatika IndonesiaJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)2580-07602024-12-018680881810.29207/resti.v8i6.61226122Efficient Pattern Recognition of Sundanese Script Variants Using CNNMuhammad Husni Wahid0Erik Iman Heri Ujianto1Universitas Teknologi YogyakartaUniversitas Teknologi YogyakartaThis research aims to apply pattern recognition technology, specifically through the Convolutional Neural Network (CNN) approach, in identifying and translating Sundanese script accurately. This research is focused on recognizing rarangken script patterns based on ngalagena script in Indonesian cultural heritage. This study uses the MobileNetV2 based CNN model, utilizing transfer learning and trained for 50 epochs using the Adam optimizer with a learning rate of 0.0001, to achieve a training accuracy of 98.75% and test accuracy of 96.95% in 1 hour and 23 minutes, respectively. The results of the study show that the simpler CNN architecture without augmentation achieved the highest accuracy of 99.26%, and the augmented CNN model achieved 94.42% accuracy in 2 hours and 22 minutes. These results enable practical applications in both education and cultural preservation, demonstrating how modern technology can effectively contribute to maintaining traditional cultural elements in the digital era.https://jurnal.iaii.or.id/index.php/RESTI/article/view/6122cnnpattern recognitionsundanese scriptmobilenetv2 |
| spellingShingle | Muhammad Husni Wahid Erik Iman Heri Ujianto Efficient Pattern Recognition of Sundanese Script Variants Using CNN Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) cnn pattern recognition sundanese script mobilenetv2 |
| title | Efficient Pattern Recognition of Sundanese Script Variants Using CNN |
| title_full | Efficient Pattern Recognition of Sundanese Script Variants Using CNN |
| title_fullStr | Efficient Pattern Recognition of Sundanese Script Variants Using CNN |
| title_full_unstemmed | Efficient Pattern Recognition of Sundanese Script Variants Using CNN |
| title_short | Efficient Pattern Recognition of Sundanese Script Variants Using CNN |
| title_sort | efficient pattern recognition of sundanese script variants using cnn |
| topic | cnn pattern recognition sundanese script mobilenetv2 |
| url | https://jurnal.iaii.or.id/index.php/RESTI/article/view/6122 |
| work_keys_str_mv | AT muhammadhusniwahid efficientpatternrecognitionofsundanesescriptvariantsusingcnn AT erikimanheriujianto efficientpatternrecognitionofsundanesescriptvariantsusingcnn |