Affiliation:
1. Department of Computer Engineering, Dongseo University, Busan 47011, Republic of Korea
Abstract
Data augmentation is one of the most important problems in deep learning. There have been many algorithms proposed to solve this problem, such as simple noise injection, the generative adversarial network (GAN), and diffusion models. However, to the best of our knowledge, these works mainly focused on computer vision-related tasks, and there have not been many proposed works for one-dimensional data. This paper proposes a GAN-based data augmentation for generating multichannel one-dimensional data given single-channel inputs. Our architecture consists of multiple discriminators that adapt deep convolution GAN (DCGAN) and patchGAN to extract the overall pattern of the multichannel generated data while also considering the local information of each channel. We conducted an experiment with website fingerprinting data. The result for the three channels’ data augmentation showed that our proposed model obtained FID scores of 0.005,0.017,0.051 for each channel, respectively, compared to 0.458,0.551,0.521 when using the vanilla GAN.
Funder
National Research Foundation of Korea
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference29 articles.
1. Thanapol, P., Lavangnananda, K., Bouvry, P., Pinel, F., and Leprevost, F. (2020, January 21–22). Reducing Overfitting and Improving Generalization in Training Convolutional Neural Network (CNN) under Limited Sample Sizes in Image Recognition. Proceedings of the 2020—5th International Conference on Information Technology (InCIT), Chonburi, Thailand.
2. A review: Data pre-processing and data augmentation techniques;Maharana;Glob. Transit. Proc.,2022
3. Wind Speed Time Series Prediction with Deep Learning and Data Augmentation;Flores;Intell. Syst. Appl.,2021
4. A Novel Data Augmentation Convolutional Neural Network for Detecting Malaria Parasite in Blood Smear Images;Oyewola;Appl. Artif. Intell.,2022
5. Generative adversarial networks in medical image segmentation: A review;Xun;Comput. Biol. Med.,2022
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献