Ekstraksi Fitur Berdasarkan Fuzzy Restricted Boltzmann Machine Pada Klasifikasi Fashion-MNIST Dengan Dan Tanpa Noise

  • Muhammad Ribhan Hadiyan Matematika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Padjadjaran
  • Firdaniza Firdaniza Matematika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Padjadjaran
  • Herlina Napitupulu Matematika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Padjadjaran

Abstract

Mixed Accelerated Learning Method based on a Fuzzy Restricted Boltzmann Machine (MAFRBM) was a relatively new feature extraction method on images that had not been widely implemented. MAFRBM had advantages in extracting features from noisy images. Generally, the presence of noise in images could significantly affect the outcome of feature extraction. In this study, feature extraction was performed using MAFRBM on the Fashion-MNIST dataset with and without added noise. The types of noise added to the images were Gaussian, salt & pepper, and Poisson. The features extracted by MAFRBM were then classified using a Support Vector Machine (SVM). The classification results showed the highest accuracy at 88%. Moreover, the comparison of accuracy results from the classification of Fashion-MNIST with noise did not differ significantly from the images without noise.

Published
2024-08-16
How to Cite
Hadiyan, M., Firdaniza, F., & Napitupulu, H. (2024). Ekstraksi Fitur Berdasarkan Fuzzy Restricted Boltzmann Machine Pada Klasifikasi Fashion-MNIST Dengan Dan Tanpa Noise. SisInfo, 6(2), 18-27. https://doi.org/10.37278/sisinfo.v6i2.876
Section
Articles