Analog signal identification method based on complex neural network and attention mechanism

Abstract

The invention discloses an analog signal identification method based on a complex neural network and an attention mechanism. The identification method is characterized by comprising a model design method based on the complex neural network and the attention mechanism, and a complex meta-learning training method thereof. According to the method, the complex neural network and a multi-head attention mechanism are applied to a meta-learning model, so that the model can better capture category features of training samples, and a better categorization effect and stable performance are achieved; meanwhile, the model can be applied to most signal categorization tasks, and a better test result can be obtained with a small number of training samples.

Description

technical field [0001] The invention relates to the field of analog signal recognition. Background technique [0002] The success of signal recognition in the field of deep learning requires the use of large amounts of data. And deep learning models trained with traditional supervised learning methods tend to perform poorly when they have only small amounts of data or when they need to adapt to unseen tasks or time-varying tasks. In practical signal recognition tasks, collecting and annotating rich data is expensive, especially for some rare but important signals. On the other hand, due to the presence of noise, deep neural networks must adapt to real-time changes in SNR in practical scenarios. [0003] In actual signal recognition tasks, analog signals include current, voltage, and power. [0004] Meta-learning methods equipped with attention mechanisms in complex neural networks have not been investigated. Contents of the invention [0005] The principle of this appl...

AI Technical Summary

Problems solved by technology

[0004] Meta-learning methods equipped with attention mec

Images