Man-machine asynchronous recognition method based on multi-task learning and class activation graph feedback

Abstract

The invention provides a man-machine asynchronous recognition method based on multi-task learning and class activation graph feedback. The method comprises the following steps: training a deep learning model through the multi-task learning in a parameter hard sharing manner, and obtaining the visual interpretation of the trained deep learning model for an output result through a class activation mapping manner; meanwhile, setting a feature region according to the activation domain of the class activation graph of each man-machine asynchronous type; inputting the actually collected original breathing signal into the trained deep learning model, and obtaining an identification result of the current breathing signal; and finally, correcting an identification result according to a feature region set according to a man-machine asynchronous type. Only one network model is trained in a mode that multiple tasks are combined with parameter hard sharing, so that multiple recognized man-machine asynchronous types can be output at the same time through one-time forward calculation, and the recognition efficiency of an existing method is improved. And based on a self-correction classification result fed back by the class activation graph, the method has high accuracy and interpretability.

Description

technical field [0001] The invention relates to a multi-machine asynchrony type identification method in mechanical ventilation based on multi-task learning and class activation map feedback. It belongs to the field of automatic identification of mechanical ventilation man-machine asynchronous. Background technique [0002] With the development and improvement of deep learning theory, neural networks are widely used in the medical field. In the aspect of automatic recognition of human-machine asynchrony in mechanical ventilation, some scholars have proposed methods of human-machine asynchrony based on recurrent neural network, one-dimensional convolutional neural network and two-dimensional convolutional neural network. However, in this field, most of the current detection methods based on neural networks are binary classification networks with single-task learning, which can only complete the recognition of a specific type of human-machine asynchrony. If you want to modul...

AI Technical Summary

Problems solved by technology

However, the existing methods only use the visual activation map as the basis for the network output classification results, ignoring the possibility that it can be used as the positioning function of the human-machine asynchronous waveform feature area to further improve the network recognition accuracy.

Images