Data augmentation method based on mixup

Wenjing Hu; Tailin Han; Xiao Wang; Bo Xu

doi:10.1117/12.2653020

6 September 2022 Data augmentation method based on mixup

Wenjing Hu, Tailin Han, Xiao Wang, Bo Xu

Proceedings Volume 12332, International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2022); 1233215 (2022) https://doi.org/10.1117/12.2653020
Event: International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2022), 2022, Chengdu, China

Abstract

In recent years, deep learning has achieved remarkable success in various fields, which largely relies on a large amount of data to train deep learning models, and in many practical applications, sufficient data is not necessarily available. When the amount of data for training the model is limited, the data set can be enriched by data augmentation, thereby improving the generalization ability of the deep learning model. Aiming at the problem of insufficient data in the process of building a dynamic compensation model with deep learning methods, this paper proposes to use mixup to enhance the dynamic calibration signals obtained from a small number of pressure sensor dynamic calibration experiments. Experiments show that using the augmented data to train the compensation model can effectively enhance the generalization of the model and improve the compensation ability of the model.

Citation Download Citation

Wenjing Hu, Tailin Han, Xiao Wang, and Bo Xu "Data augmentation method based on mixup", Proc. SPIE 12332, International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2022), 1233215 (6 September 2022); https://doi.org/10.1117/12.2653020

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available