Optimization of CNN Activation Functions using Xception for South Sulawesi Batik Classification
Batik motifs from South Sulawesi such as the Pinisi boat, Lontara script, Tongkonan house and Toraja combinations embody rich cultural narratives but are difficult to identify automatically. Automatic classification supports cultural preservation and education and empowers tourism and digital herita...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | Indonesian |
| Published: |
Islamic University of Indragiri
2025-09-01
|
| Series: | Sistemasi: Jurnal Sistem Informasi |
| Subjects: | |
| Online Access: | https://sistemasi.ftik.unisi.ac.id/index.php/stmsi/article/view/5281 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839606170300448768 |
|---|---|
| author | Aswan Aswan Eva Yulia Puspaningrum Billy Eden William Asrul |
| author_facet | Aswan Aswan Eva Yulia Puspaningrum Billy Eden William Asrul |
| author_sort | Aswan Aswan |
| collection | DOAJ |
| description | Batik motifs from South Sulawesi such as the Pinisi boat, Lontara script, Tongkonan house and Toraja combinations embody rich cultural narratives but are difficult to identify automatically. Automatic classification supports cultural preservation and education and empowers tourism and digital heritage applications. This study improves the performance of convolutional neural networks for South Sulawesi batik classification by optimizing activation functions within the Xception architecture which exploits depthwise separable convolutions for efficient and detailed feature extraction. A balanced dataset of 1400 labeled images in four classes was divided into eighty percent for training, ten percent for validation and ten percent for testing. Images were resized to 224 by 224 pixels, converted to grayscale and augmented through zoom, flip and rotation. With identical hyperparameters including a learning rate of 0.001, a batch size of 64 and training for 100 epochs using the Adam optimizer, ReLU, ELU, Leaky ReLU and Swish activation functions were compared. Evaluation metrics comprised accuracy, precision, recall, F1 score and cross entropy loss. ELU achieved the highest test accuracy of 98.57 percent, precision of 0.9864, recall of 0.9857 and F1 score of 0.9857, outperforming ReLU and Leaky ReLU with 97.86 percent accuracy and Swish with 97.14 percent accuracy. The results demonstrate that selecting an optimal activation function substantially enhances convolutional neural network classification of complex batik patterns. The findings offer practical guidance for development of resource aware batik identification systems in support of cultural digitization and education initiatives. |
| format | Article |
| id | doaj-art-1d93b9dda1f142ad8a1faa2aab3bb943 |
| institution | Matheson Library |
| issn | 2302-8149 2540-9719 |
| language | Indonesian |
| publishDate | 2025-09-01 |
| publisher | Islamic University of Indragiri |
| record_format | Article |
| series | Sistemasi: Jurnal Sistem Informasi |
| spelling | doaj-art-1d93b9dda1f142ad8a1faa2aab3bb9432025-08-01T09:20:41ZindIslamic University of IndragiriSistemasi: Jurnal Sistem Informasi2302-81492540-97192025-09-011452382239410.32520/stmsi.v14i5.52811194Optimization of CNN Activation Functions using Xception for South Sulawesi Batik ClassificationAswan Aswan0Eva Yulia Puspaningrum1Billy Eden William Asrul2Universitas Handayani MakassarUniversitas Pembangunan Nasional “Veteran” Jawa TimurUniversitas Handayani MakassarBatik motifs from South Sulawesi such as the Pinisi boat, Lontara script, Tongkonan house and Toraja combinations embody rich cultural narratives but are difficult to identify automatically. Automatic classification supports cultural preservation and education and empowers tourism and digital heritage applications. This study improves the performance of convolutional neural networks for South Sulawesi batik classification by optimizing activation functions within the Xception architecture which exploits depthwise separable convolutions for efficient and detailed feature extraction. A balanced dataset of 1400 labeled images in four classes was divided into eighty percent for training, ten percent for validation and ten percent for testing. Images were resized to 224 by 224 pixels, converted to grayscale and augmented through zoom, flip and rotation. With identical hyperparameters including a learning rate of 0.001, a batch size of 64 and training for 100 epochs using the Adam optimizer, ReLU, ELU, Leaky ReLU and Swish activation functions were compared. Evaluation metrics comprised accuracy, precision, recall, F1 score and cross entropy loss. ELU achieved the highest test accuracy of 98.57 percent, precision of 0.9864, recall of 0.9857 and F1 score of 0.9857, outperforming ReLU and Leaky ReLU with 97.86 percent accuracy and Swish with 97.14 percent accuracy. The results demonstrate that selecting an optimal activation function substantially enhances convolutional neural network classification of complex batik patterns. The findings offer practical guidance for development of resource aware batik identification systems in support of cultural digitization and education initiatives.https://sistemasi.ftik.unisi.ac.id/index.php/stmsi/article/view/5281convolutional neural network, activation function, xception, south sulawesi batik, classification |
| spellingShingle | Aswan Aswan Eva Yulia Puspaningrum Billy Eden William Asrul Optimization of CNN Activation Functions using Xception for South Sulawesi Batik Classification Sistemasi: Jurnal Sistem Informasi convolutional neural network, activation function, xception, south sulawesi batik, classification |
| title | Optimization of CNN Activation Functions using Xception for South Sulawesi Batik Classification |
| title_full | Optimization of CNN Activation Functions using Xception for South Sulawesi Batik Classification |
| title_fullStr | Optimization of CNN Activation Functions using Xception for South Sulawesi Batik Classification |
| title_full_unstemmed | Optimization of CNN Activation Functions using Xception for South Sulawesi Batik Classification |
| title_short | Optimization of CNN Activation Functions using Xception for South Sulawesi Batik Classification |
| title_sort | optimization of cnn activation functions using xception for south sulawesi batik classification |
| topic | convolutional neural network, activation function, xception, south sulawesi batik, classification |
| url | https://sistemasi.ftik.unisi.ac.id/index.php/stmsi/article/view/5281 |
| work_keys_str_mv | AT aswanaswan optimizationofcnnactivationfunctionsusingxceptionforsouthsulawesibatikclassification AT evayuliapuspaningrum optimizationofcnnactivationfunctionsusingxceptionforsouthsulawesibatikclassification AT billyedenwilliamasrul optimizationofcnnactivationfunctionsusingxceptionforsouthsulawesibatikclassification |