Time sequence physiological data classification method and device, storage medium and processor

Abstract

The invention discloses a time sequence physiological data classification method and device, a storage medium and a processor. The method comprises the following steps: extracting multisource sign data from a database, dividing the data into training data and test data, and preprocessing the training data and the test data; constructing a deep learning model DeepPhysioNet, wherein the model adoptsa coder-decoder neural network architecture, the coder is composed of a basic feature learning unit, a sequence residual error unit and a representation learning unit and can perform strong feature extraction, and the decoder calculates classification results for classification tasks of different targets by using extracted features; performing an offline training stage: inputting the training data into the model for preliminary training, testing the preliminarily trained model through the test data, and performing continuous repeating until a preset condition is met; performing the online inference stage: inputting to-be-detected data into the trained DeepPhysioNet model, and outputting a classification result. The method has the advantages that expert deviation is avoided, the method issuitable for multi-source time sequence physiological data, and an attention mechanism is introduced.

Description

technical field [0001] The present invention relates to the field of data processing, in particular to a time-series physiological data classification method, device, storage medium and processor based on deep learning. Background technique [0002] Although deep learning technology has been widely used in various smart medical scenarios, the mining of massive time-series physiological signal data based on the time dimension is still in its infancy. The main manifestations are the ultra-long time-series dependence of time-series physiological signs data, the inconsistency of data dimensions caused by differences in acquisition equipment, and the bottleneck of the general backbone network model. [0003] For the analysis of time-series physiological data analysis in disease prediction, the decision-making process of physicians is to circle the abnormal part from the given data, such as "suddenly dense ECG signals" in sleep apnea diseases. Most of the current research transfo...

AI Technical Summary

Problems solved by technology

[0007] 3. Weak generalization ability

Such methods usually perform poorly on large data set tasks, because features such as manual feature engineering describe a part of the data distribution, and it is difficult to describe all the internal patterns in large data

Images