The Optimization of Transfer Learning Convolutional Neural Network Model with PCA and t-SNE Algorithms for Classification and Recognition of CIFAR-10 Image
The low accuracy when performing the image classification process is a problem that often occurs. The image classification process requires the completeness of the features of the image which form an informative image pattern so that information from the image can be displayed. The purpose of this s...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ikatan Ahli Informatika Indonesia
2020-08-01
|
| Series: | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) |
| Subjects: | |
| Online Access: | http://jurnal.iaii.or.id/index.php/RESTI/article/view/2131 |
| _version_ | 1797331814594904064 |
|---|---|
| author | Rastri Prathivi |
| author_facet | Rastri Prathivi |
| author_sort | Rastri Prathivi |
| collection | DOAJ |
| description | The low accuracy when performing the image classification process is a problem that often occurs. The image classification process requires the completeness of the features of the image which form an informative image pattern so that information from the image can be displayed. The purpose of this study is to classify images in the CIFAR-10 image dataset using the CNN method. Initially the CNN method gave an accuracy of 79.4% but had a long computation time of 12 hours with 10,000 iterations. The optimization process for the CNN method is carried out by combining the CNN method, the PCA algorithm and the t-SNE algorithm. The algorithm is used to reduce the length of the image matrix in the initial transfer of learning without reducing the information in the image so that the classification process can be done correctly. The final result obtained from the optimization has an accuracy of 90.5%. With an optimization rate of 11%. The resulting time is more efficient, namely 3 hours for the feature transfer-value process and 6 minutes for the testing process with 10,000 iterations. |
| first_indexed | 2024-03-08T07:40:46Z |
| format | Article |
| id | doaj.art-2aba15b6208c48eba9b0a64c21974152 |
| institution | Directory Open Access Journal |
| issn | 2580-0760 |
| language | English |
| last_indexed | 2024-03-08T07:40:46Z |
| publishDate | 2020-08-01 |
| publisher | Ikatan Ahli Informatika Indonesia |
| record_format | Article |
| series | Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) |
| spelling | doaj.art-2aba15b6208c48eba9b0a64c219741522024-02-02T17:22:30ZengIkatan Ahli Informatika IndonesiaJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)2580-07602020-08-014471772210.29207/resti.v4i4.21312131The Optimization of Transfer Learning Convolutional Neural Network Model with PCA and t-SNE Algorithms for Classification and Recognition of CIFAR-10 ImageRastri Prathivi0Universitas SemarangThe low accuracy when performing the image classification process is a problem that often occurs. The image classification process requires the completeness of the features of the image which form an informative image pattern so that information from the image can be displayed. The purpose of this study is to classify images in the CIFAR-10 image dataset using the CNN method. Initially the CNN method gave an accuracy of 79.4% but had a long computation time of 12 hours with 10,000 iterations. The optimization process for the CNN method is carried out by combining the CNN method, the PCA algorithm and the t-SNE algorithm. The algorithm is used to reduce the length of the image matrix in the initial transfer of learning without reducing the information in the image so that the classification process can be done correctly. The final result obtained from the optimization has an accuracy of 90.5%. With an optimization rate of 11%. The resulting time is more efficient, namely 3 hours for the feature transfer-value process and 6 minutes for the testing process with 10,000 iterations.http://jurnal.iaii.or.id/index.php/RESTI/article/view/2131cnn, convolutional neural network, cifar-10, image classification |
| spellingShingle | Rastri Prathivi The Optimization of Transfer Learning Convolutional Neural Network Model with PCA and t-SNE Algorithms for Classification and Recognition of CIFAR-10 Image Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) cnn, convolutional neural network, cifar-10, image classification |
| title | The Optimization of Transfer Learning Convolutional Neural Network Model with PCA and t-SNE Algorithms for Classification and Recognition of CIFAR-10 Image |
| title_full | The Optimization of Transfer Learning Convolutional Neural Network Model with PCA and t-SNE Algorithms for Classification and Recognition of CIFAR-10 Image |
| title_fullStr | The Optimization of Transfer Learning Convolutional Neural Network Model with PCA and t-SNE Algorithms for Classification and Recognition of CIFAR-10 Image |
| title_full_unstemmed | The Optimization of Transfer Learning Convolutional Neural Network Model with PCA and t-SNE Algorithms for Classification and Recognition of CIFAR-10 Image |
| title_short | The Optimization of Transfer Learning Convolutional Neural Network Model with PCA and t-SNE Algorithms for Classification and Recognition of CIFAR-10 Image |
| title_sort | optimization of transfer learning convolutional neural network model with pca and t sne algorithms for classification and recognition of cifar 10 image |
| topic | cnn, convolutional neural network, cifar-10, image classification |
| url | http://jurnal.iaii.or.id/index.php/RESTI/article/view/2131 |
| work_keys_str_mv | AT rastriprathivi theoptimizationoftransferlearningconvolutionalneuralnetworkmodelwithpcaandtsnealgorithmsforclassificationandrecognitionofcifar10image AT rastriprathivi optimizationoftransferlearningconvolutionalneuralnetworkmodelwithpcaandtsnealgorithmsforclassificationandrecognitionofcifar10image |