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.
Paper
Full text
Data augmentation method based on mixup
Semantic Scholar · Engineering · 2022
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.