Time-series physiological data classification method, device, storage medium and processor

A technology of physiological data and classification method, applied in the field of data processing, can solve the problems of difficult to describe the internal pattern of big data, poor performance, weak generalization ability, etc., to avoid expert bias and information loss, efficient calculation, and broad receptive field. effect of size

Active Publication Date: 2021-10-29
SOUTH CHINA NORMAL UNIVERSITY
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Time-series physiological data classification method, device, storage medium and processor
  • Time-series physiological data classification method, device, storage medium and processor
  • Time-series physiological data classification method, device, storage medium and processor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Such as Figure 3-7 As shown, this embodiment provides a time-series physiological data classification method, which is based on deep learning and can realize end-to-end decision output, mainly including four stages of data preprocessing, model construction, offline training and online decision-making.

[0058] 1. Data preprocessing

[0059] see Figure 4 , before model training, multi-source sign data and corresponding annotations are extracted from the original medical database, and then data preprocessing is performed on the data. The first step of data preprocessing is data normalization. Since the time-series physiological data are collected from different organs and the collection equipment is different, the signal-to-noise ratio in the original data will be different. For example, the data collected by non-contact equipment will cause large fluctuations in the amplitude of the collected signals due to the difference in the patient's posture (sideways and uprigh...

Embodiment 2

[0081] Corresponding to the time-series physiological data classification method detailed in Embodiment 1, this embodiment provides a time-series physiological data classification device, including:

[0082] The original data acquisition and preprocessing module is used to extract multi-source sign data from the database, divide the data into training data and test data, and perform data preprocessing;

[0083] The model construction module is used to build the deep learning model DeepPhysioNet. The DeepPhysioNet model adopts the neural network architecture of the encoder-decoder. The head of the encoder is a basic feature learning unit composed of a convolutional neural network, and then connected by skipping words. Constitute a sequence residual unit to deepen the network and avoid the problem of gradient degradation in the network. Finally, the attention mechanism is introduced by the representation learning unit. The decoder automatically extracts powerful features from the...

Embodiment 3

[0096] This embodiment provides a storage medium on which a computer program is stored, and when the program is running, the time-series physiological data classification method described in Embodiment 1 is executed.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a time series physiological data classification method, device, storage medium and processor. The methods include: extracting multi-source sign data from the database, dividing the data into training data and test data and preprocessing; constructing a deep learning model DeepPhysioNet, which adopts the neural network architecture of encoder-decoder, and the encoder is composed of The basic feature learning unit, sequence residual unit and representation learning unit can perform powerful feature extraction, and the decoder uses the extracted features to calculate classification results for different target classification tasks; in the offline training phase, the training data is input to the model Preliminary training is carried out in the test data to test the pre-trained model until it meets the preset conditions; in the online inference stage, the data to be tested is input to the trained DeepPhysioNet model, and the classification results are output. The invention has the advantages of avoiding expert bias, being applicable to multi-source time-series physiological data, and introducing an attention mechanism.

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G16H50/70G06F16/35G06N3/04
CPCG16H50/70G06F16/35G06N3/045
Inventor 聂瑞华李铮席云
Owner SOUTH CHINA NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap