Abstract
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.
Highlights
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
Initially the CNN method gave an accuracy of 79.4%
Summary
Selanjutnya langkah keempat adalah mengambil output hasil perkalian dengan 255 pada data training dan data pada lapisan konvolusi serta menambahkan fungsi testing. Akurasi dari proses konvolusi neural transfer_values_50d = pca.fit_transform(transfer_values) network ditentukan dengan perhitungan confusion # Mengurangi 2 dimensi menggunakan t-SNE matrix. Untuk melatih dataset Penerapan algoritma PCA dan t-SNE dilakukan pada training menggunakan model tersebut langsung di langkah yang kedua. Listing program Optimasi_PCA_tkomputer terlalu berat sehingga pada penelitian ini SNE digunakan untuk mereduksi transfer-value dengan penulis akan mengunduh model Inception yang sudah metode PCA. Tingkat optimasi untuk mengklasifikasi citra CIFAR-10 dan membangun mereduksi panjang array pada citra memiliki angka ideal classifier. Prosentase tersebut menunjukkan bahwa semakin tinggi tingkat optimasi akan semakin banyak reduksi yang dilakukan pada citra yang berdampak pada kecepatan komputasi untuk mengesktrak dan mengklasifikasi citra. Arsitektur Model TL-Inception CNN mengambil nilai transfer-value sebagai input yang kemudian menghasilkan output pada lapisan softmax. Transfer-value ini berisi Akurasi pada algoritma CNN dan TL-CNN dihitung perhitungan fitur dari dataset yang diproses.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
