Putra, Riza Satria (2025) Implementasi Ensemble CNN dan SVM Dalam Klasifikasi Motif Batik Ploso Jombang. Undergraduate thesis, UPN Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
21081010010-cover.pdf Download (1MB) |
|
Text (Bab 1)
21081010010-bab1.pdf Download (196kB) |
|
Text (Bab 2)
21081010010-bab2.pdf Restricted to Repository staff only until 4 December 2027. Download (851kB) |
|
Text (Bab 3)
21081010010-bab3.pdf Restricted to Repository staff only until 4 December 2027. Download (1MB) |
|
Text (Bab 4)
21081010010-bab4.pdf Restricted to Repository staff only until 4 December 2027. Download (2MB) |
|
Text (Bab 5)
21081010010-bab5.pdf Download (186kB) |
|
Text (Daftar Pustaka)
21081010010-daftarpustaka.pdf Download (175kB) |
|
Text (Lampiran)
21081010010-lampiran.pdf Download (229kB) |
Abstract
Batik is an Indonesian cultural heritage recognized by UNESCO, possessing deep historical, aesthetic, and philosophical value. However, the diversity of batik motifs, influenced by their region of origin, poses a significant challenge in preservation and classification efforts using technology. This research aims to implement and analyze the performance of a Hybrid Ensemble CNN approach utilizing VGG19, ResNet18, and EfficientNetB0 for feature extraction combined with a Support Vector Machine (SVM) as the classifier, to classify Ploso Jombang Batik patterns.The testing results confirm that the Hybrid Ensemble CNN-SVM architecture was successfully implemented into an interactive Streamlit-based website. Comparative analysis across three data ratios showed that the inclusion of SVM generally improved classification accuracy. The best implemented model, the Ensemble of EfficientNetB0 and ResNet18 with SVM, achieved a peak accuracy of 99% at the 70:15:15 ratio. Overall, this study affirms that the Hybrid Ensemble CNN-SVM combination is effective in tackling the complexity of batik motifs and provides an efficient solution for classification, thus supporting cultural preservation efforts through technology.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | Q Science > Q Science (General) T Technology > T Technology (General) |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Informatics | ||||||||||||
| Depositing User: | Riza Satria Putra | ||||||||||||
| Date Deposited: | 04 Dec 2025 06:07 | ||||||||||||
| Last Modified: | 04 Dec 2025 06:07 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/47824 |
Actions (login required)
 |
View Item |