FINE-TUNING RESNET50V2 WITH ADAMW AND ADAPTIVE TRANSFER LEARNING FOR SONGKET CLASSIFICATION IN LOMBOK

This study aims to develop a classification system for traditional Lombok songket fabric patterns using the ResNet50V2 architecture, optimized through fine-tuning and the AdamW optimizer. The data were collected directly from songket artisans in Lombok and categorized into three groups based on the...

Full description

Saved in:
Bibliographic Details
Main Authors: Erfan Wahyudi, Bahtiar Imran, Zaeniah, Surni Erniwati, Muh Nasirudin Karim, Zumratul Muahidin
Format: Article
Language:English
Published: LPPM Nusa Mandiri 2025-03-01
Series:Pilar Nusa Mandiri
Subjects:
Online Access:https://ejournal.nusamandiri.ac.id/index.php/pilar/article/view/6485
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849393536791740416
author Erfan Wahyudi
Bahtiar Imran
Zaeniah
Surni Erniwati
Muh Nasirudin Karim
Zumratul Muahidin
author_facet Erfan Wahyudi
Bahtiar Imran
Zaeniah
Surni Erniwati
Muh Nasirudin Karim
Zumratul Muahidin
author_sort Erfan Wahyudi
collection DOAJ
description This study aims to develop a classification system for traditional Lombok songket fabric patterns using the ResNet50V2 architecture, optimized through fine-tuning and the AdamW optimizer. The data were collected directly from songket artisans in Lombok and categorized into three groups based on the origin of the patterns: Sade, Sukarara, and Pringgasela. The model was trained with data augmentation techniques, including rotation, shifting, and zooming, to increase data diversity. During the training process, fine-tuning was applied to the last layer of ResNet50V2, and optimization was performed using AdamW with a learning rate of 0.0001. The model was evaluated using a confusion matrix, classification report, and analysis of accuracy and loss. The experimental results showed that the model achieved 100% accuracy at the 15th epoch. Furthermore, experiments with different parameters (epochs, batch size, and learning rate) demonstrated that the 15th epoch provided the best results with 100% accuracy, while using higher epochs (30 and 40) did not necessarily yield better outcomes. This model is effective in identifying songket fabric patterns with good classification results for each class. Although the results are excellent, increasing the dataset size and exploring more complex model architectures could further enhance performance. Overall, this study demonstrates the significant potential of deep learning technology in classifying songket patterns with reliable accuracy in real-world applications.
format Article
id doaj-art-b70a053d4f2a4759a92ca7249d2908af
institution Kabale University
issn 1978-1946
2527-6514
language English
publishDate 2025-03-01
publisher LPPM Nusa Mandiri
record_format Article
series Pilar Nusa Mandiri
spelling doaj-art-b70a053d4f2a4759a92ca7249d2908af2025-08-20T03:40:22ZengLPPM Nusa MandiriPilar Nusa Mandiri1978-19462527-65142025-03-01211829110.33480/pilar.v21i1.64858414FINE-TUNING RESNET50V2 WITH ADAMW AND ADAPTIVE TRANSFER LEARNING FOR SONGKET CLASSIFICATION IN LOMBOKErfan Wahyudi0Bahtiar Imran1Zaeniah2Surni Erniwati3Muh Nasirudin Karim4Zumratul Muahidin5Institut Pemerintahan Dalam NegeriUniversitas Teknologi MataramUniversitas Teknologi MataramUniversitas Teknologi MataramUniversitas Teknologi MataramUniversitas Teknologi MataramThis study aims to develop a classification system for traditional Lombok songket fabric patterns using the ResNet50V2 architecture, optimized through fine-tuning and the AdamW optimizer. The data were collected directly from songket artisans in Lombok and categorized into three groups based on the origin of the patterns: Sade, Sukarara, and Pringgasela. The model was trained with data augmentation techniques, including rotation, shifting, and zooming, to increase data diversity. During the training process, fine-tuning was applied to the last layer of ResNet50V2, and optimization was performed using AdamW with a learning rate of 0.0001. The model was evaluated using a confusion matrix, classification report, and analysis of accuracy and loss. The experimental results showed that the model achieved 100% accuracy at the 15th epoch. Furthermore, experiments with different parameters (epochs, batch size, and learning rate) demonstrated that the 15th epoch provided the best results with 100% accuracy, while using higher epochs (30 and 40) did not necessarily yield better outcomes. This model is effective in identifying songket fabric patterns with good classification results for each class. Although the results are excellent, increasing the dataset size and exploring more complex model architectures could further enhance performance. Overall, this study demonstrates the significant potential of deep learning technology in classifying songket patterns with reliable accuracy in real-world applications.https://ejournal.nusamandiri.ac.id/index.php/pilar/article/view/6485data augmentationdeep learningfine-tuningresnet50v2songket pattern classification
spellingShingle Erfan Wahyudi
Bahtiar Imran
Zaeniah
Surni Erniwati
Muh Nasirudin Karim
Zumratul Muahidin
FINE-TUNING RESNET50V2 WITH ADAMW AND ADAPTIVE TRANSFER LEARNING FOR SONGKET CLASSIFICATION IN LOMBOK
Pilar Nusa Mandiri
data augmentation
deep learning
fine-tuning
resnet50v2
songket pattern classification
title FINE-TUNING RESNET50V2 WITH ADAMW AND ADAPTIVE TRANSFER LEARNING FOR SONGKET CLASSIFICATION IN LOMBOK
title_full FINE-TUNING RESNET50V2 WITH ADAMW AND ADAPTIVE TRANSFER LEARNING FOR SONGKET CLASSIFICATION IN LOMBOK
title_fullStr FINE-TUNING RESNET50V2 WITH ADAMW AND ADAPTIVE TRANSFER LEARNING FOR SONGKET CLASSIFICATION IN LOMBOK
title_full_unstemmed FINE-TUNING RESNET50V2 WITH ADAMW AND ADAPTIVE TRANSFER LEARNING FOR SONGKET CLASSIFICATION IN LOMBOK
title_short FINE-TUNING RESNET50V2 WITH ADAMW AND ADAPTIVE TRANSFER LEARNING FOR SONGKET CLASSIFICATION IN LOMBOK
title_sort fine tuning resnet50v2 with adamw and adaptive transfer learning for songket classification in lombok
topic data augmentation
deep learning
fine-tuning
resnet50v2
songket pattern classification
url https://ejournal.nusamandiri.ac.id/index.php/pilar/article/view/6485
work_keys_str_mv AT erfanwahyudi finetuningresnet50v2withadamwandadaptivetransferlearningforsongketclassificationinlombok
AT bahtiarimran finetuningresnet50v2withadamwandadaptivetransferlearningforsongketclassificationinlombok
AT zaeniah finetuningresnet50v2withadamwandadaptivetransferlearningforsongketclassificationinlombok
AT surnierniwati finetuningresnet50v2withadamwandadaptivetransferlearningforsongketclassificationinlombok
AT muhnasirudinkarim finetuningresnet50v2withadamwandadaptivetransferlearningforsongketclassificationinlombok
AT zumratulmuahidin finetuningresnet50v2withadamwandadaptivetransferlearningforsongketclassificationinlombok