Engineering data enhancement algorithm based on generative adversarial network

Abstract

The invention discloses an engineering data enhancement algorithm based on a generative adversarial network, and aims to provide enough data information for researchers so as to carry out more accurate research work, and the method comprises the steps: obtaining original data, carrying out data preprocessing such as shutdown data processing, noise reduction processing, normalization processing and the like on the original data, and obtaining a group of smooth and stable construction data; substituting the processed data into a GAN generative adversarial network data enhancement algorithm, and performing data enhancement by using a mutual adversarial principle of a generator and a discriminator; and outputting engineering data similar to the original data in distribution. According to the method, the combination of data preprocessing and data enhancement is realized, multiple groups of useless data including noise are removed, the confrontation principle of a generator and a discriminator in the generative adversarial network is utilized, the enhancement of construction airborne data is realized, and the problem of data shortage in research is solved.

Description

technical field [0001] The invention relates to an engineering data enhancement algorithm, in particular to an engineering data enhancement algorithm based on a generative confrontation network. Background technique [0002] With the development of deep learning in recent years, deep neural networks have made revolutionary breakthroughs in classification tasks. Classifiers based on deep neural networks can achieve high accuracy under the premise of sufficient labeled samples as training data. However, in some scenarios, it is difficult to collect labeled data or it is costly, time-consuming and labor-intensive to obtain such data. When the data is insufficient, the neural network is difficult to train stably and the generalization ability is weak. [0003] In response to this problem, Professor Goodfellow from the University of Montreal proposed a deep learning method based on Generative Adversarial Network (GAN), and applied it to solve the problem that neural networks ar...

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problems existing in the prior art, the present invention provides an engineering data enhancement algorithm based on generative confrontation network, which solves the problem of research stagnation caused by the lack of engineering data in the prior art

Images