Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Bulletin of Electrical Engineering and Informatics

Palembang songket fabric motif image detection with data augmentation based on ResNet using dropout Ermatita, Ermatita; Noprisson, Handrie; Abdiansah, Abdiansah
Bulletin of Electrical Engineering and Informatics Vol 13, No 3: June 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v13i3.6883

Abstract

A good way to spread knowledge about Palembang songket woven cloth patterns is to use information technology, especially artificial intelligence technology. This study's main goal is to develop a ResNet model with dropout regularization methods and find out how dropout regularization affects the ResNet model for detecting Palembang songket fabric motif with more data. Data was collected in places like tujuh saudara songket, Zainal songket, songket PaSH, AMS songket, and batik, Ernawati songket, Nabilah collections, Ilham songket, and Marissa songket. We used eight class of data for this research. A dataset of 7,680 data for training, 960 data for validation, and 960 data for testing is a dataset that has been prepared to be implemented in experiments. In the final results, the experimental results for DResNet demonstrated that accuracy at the training stage was 92.16%, accuracy at the validation stage was 78.60%, and accuracy at the submission stage was 80.3%. The experimental results also show that dropouts are able to increase the accuracy of the ResNet model by adding +1.10% accuracy in the training process, adding +1.80% accuracy in the validation process, and adding +0.40% accuracy in the testing process.
Handwritten Kaganga script classification using deep learning and image fusion Dwika Putra, Erwin; Ermatita, Ermatita; Abdiansah, Abdiansah
Bulletin of Electrical Engineering and Informatics Vol 14, No 2: April 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i2.8747

Abstract

Classification of traditional handwriting script and to preserve many cultures have been developed in some parts of the world, including image classification of handwriting Kaganga script. This study aims to propose a new combination model by implementing top-hat transform (THT) and contrast-limited adaptive histogram equalization (CLAHE) with discrete wavelet transform (DWT) to support the performance of the convolutional neural network (CNN) in Kaganga script classification. The top-hat transform and contrast-limited adaptive histogram equalization with discrete wavelet transform Fusion L2 convolutional neural network (DWT-THCL L2 CNN) models get the best accuracy from the CNN with L1 regularization, CNN with dropout regularization, CNN with L2 regularization and CNN with L2 regularization and CLAHE models. Based on the experimental results, the DWT-THCL L2 CNN model successfully increased training accuracy by 7.76%, validation accuracy by 5.11%, and testing accuracy by 3.73% from the CNN L1 model. The DWT-THCL L2 CNN model received a training accuracy of 99.87%, validation accuracy of 82.61%, and testing accuracy of 82.61%, while the CNN model with L1 regularization (L1 CNN) only received a training accuracy of 92.11%, validation accuracy of 77.50%, and testing accuracy of 78.88%.