Analisis pengaruh salt-and-pepper noise terhadap Akurasi Convolutional Neural Network pada Dataset MNIST.
Jurnal Praktik Keinsinyuran · 02.11.2026 · 3 (06) · 716-725
DOI: 10.25170/jpk.v3i06.8554 ↗Kurz gefasst
Fachartikel in der Zeitschrift Jurnal Praktik Keinsinyuran, online erschienen am 02.11.2026. Verfasst von Karel Octavianus Bachri.
Abstract (Originalsprache)
This paper discusses the effect of salt-and-pepper noise to the accuracy of deep neural network. We use a standard deep neural network with the convolution as the main component. The original MNIST dataset of 60000 samples of handwritten digit is used. Salt and pepper noise with various ratio was added to create augmented dataset. Training process is set to be stopped when the validation loss exceeds the training loss. As the results, the test accuracy of the system decreases as the noise level increases. While in the train process, this trend does not occur
Zitieren
APA
Bachri, K. O. (2026). Analisis pengaruh salt-and-pepper noise terhadap Akurasi Convolutional Neural Network pada Dataset MNIST. Jurnal Praktik Keinsinyuran, 3(06), 716-725. https://doi.org/10.25170/jpk.v3i06.8554
Vancouver
Bachri KO. Analisis pengaruh salt-and-pepper noise terhadap Akurasi Convolutional Neural Network pada Dataset MNIST. Jurnal Praktik Keinsinyuran. 2026;3(06):716-725. doi:10.25170/jpk.v3i06.8554
BibTeX
@article{Bachri2026,
author = {Bachri, Karel Octavianus},
title = {Analisis pengaruh salt-and-pepper noise terhadap Akurasi Convolutional Neural Network pada Dataset MNIST},
journal = {Jurnal Praktik Keinsinyuran},
year = {2026},
volume = {3},
number = {06},
pages = {716--725},
doi = {10.25170/jpk.v3i06.8554}
}
EUVIMED