Newborn pain expression recognition method based on two-channel three-dimensional convolutional neural network

A three-dimensional convolution and neural network technology, applied in the field of expression recognition, can solve the problems of dependence on evaluation results, time-consuming and labor-intensive manual evaluation, etc., and achieve strong robustness

Inactive Publication Date: 2018-08-03
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, manual evaluation is not only time-consuming and laborious, but also the evaluation results depend on the experience of medical staff and are affected by subjective factors such as personal emotions

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
  • Newborn pain expression recognition method based on two-channel three-dimensional convolutional neural network
  • Newborn pain expression recognition method based on two-channel three-dimensional convolutional neural network
  • Newborn pain expression recognition method based on two-channel three-dimensional convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] Such as figure 1 , the method includes the following steps:

[0038] A. Collect video clips of newborns in quiet and crying states, as well as mild pain and severe pain caused by painful operations, and the medical staff divide the videos into calm, crying, mild pain and severe pain according to the degree of pain Wait for n types of expressions to build a newborn facial expression video library.

[0039] B. Edit each video clip in the neonatal facial expression video library into a frame sequence of l frame length, grayscale each frame image, and extract its local binary pattern (Local Binary Pattern, LBP) feature map , wherein, l is a positive integer, selected from 16, 24, 32 values;

[0040] C. Construct a dual-channel three-dimensional convolutional neural network;

[0041] The constructed dual-channel 3D convolutional neural network is divided into two parts: the first part is used for feature extraction, and the second part is used for feature fusion and class...

Embodiment 2

[0061] In practical applications, the preferred specific operations are as follows: Step 1: Establish a newborn facial expression video library

[0062] During the routine pain-inducing operations (such as injections and blood collection) on newborns by medical staff, high-definition digital cameras are used to shoot videos of newborns’ painful expressions, and at the same time, newborns are in a quiet state and crying due to hunger and other reasons. Non-Pain Emoji Video. Professionally trained medical staff use internationally recognized neonatal pain assessment tools to evaluate the pain level of the collected neonatal pain expression video, and give a score from 1 to 10 according to the degree of pain. Expressions ranging from 1 to 5 are classified as mild pain expressions, and those with scores ranging from 6 to 10 are classified as severe pain expressions. Label the above four types of videos collected, the quiet expression corresponds to label 1, the crying expression ...

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 newborn pain expression recognition method based on a two-channel three-dimensional convolutional neural network. The method comprises the following steps: (1) collecting video segments of newborns under different states, dividing the videos into n types of expressions according to pain degrees, and establishing a newborn facial-expression video library; (2) cropping andediting each video segment in the facial-expression video library to form a frame sequence of l-frame length, carrying out grayscale transformation on each image, and extracting an LBP feature map; (3) constructing the two-channel three-dimensional convolutional neural network; and (4) inputting grayscale graph sequences and LBP feature map sequences into the two-channel three-dimensional convolutional neural network for training and optimization tuning on the network, and saving a trained network model. According to the method, the deep convolutional neural network is extended and applied tothe field of newborn pain expression recognition to improve accuracy of newborn pain evaluation, and technical support is provided for developing an auxiliary system of newborn pain evaluation.

Description

technical field [0001] The invention relates to an expression recognition method, in particular to a newborn pain expression recognition method based on a dual-channel three-dimensional convolutional neural network. Background technique [0002] In the clinical process, many operations performed by medical staff can cause pain in newborns, such as intramuscular injection, plantar blood sampling, arteriovenous puncture and intubation. For too long, neonatal pain has often been ignored and mostly not managed appropriately. Studies have shown that newborns who are repeatedly exposed to painful stimuli will have adverse effects on their development and future behavior, and may cause central nervous system damage, acute physiological reactions, emotional disturbances, developmental delays and other symptoms. Therefore, it is of great clinical significance to take corresponding analgesic measures to relieve the pain of newborns. [0003] Pain assessment is the key to pain manage...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V40/176G06N3/045G06F18/214
Inventor 卢官明耿惠惠李晓南闫静杰卢峻禾
Owner NANJING UNIV OF POSTS & TELECOMM
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