Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Children hyperactivity behavior feature recognition algorithm based on deep learning

A technology for children's ADHD and feature recognition, applied in neural learning methods, character and pattern recognition, computing and other directions, can solve problems such as cognitive impairment, emotional impulsiveness, and difficulty concentrating, and achieve the effect of improving accuracy

Pending Publication Date: 2022-05-31
安徽兰臣信息科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The intelligence of these children is normal or close to normal, but they have defects in learning behavior and emotion. The main manifestations are that they are not commensurate with their age and developmental level. Excessive, emotional impulsiveness, etc., often accompanied by cognitive impairment and learning difficulties

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
  • Children hyperactivity behavior feature recognition algorithm based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0037] see figure 1 , the present invention is a kind of children ADHD behavior feature recognition algorithm based on deep learning, comprising the following steps:

[0038] Step 1: Acquire and preprocess the action image data set within the duration of the child's action to be identified; use a video camera to capture the child's daily life behavior, and then preprocess the captured video.

[0039] Step 2: Input the data sets obtained in step 1 into the VGG16, R...

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 children hyperactivity behavior feature recognition algorithm based on deep learning, and relates to the technical field of recognition algorithms. The method comprises the following steps: step 1, acquiring and preprocessing an action image data set within the duration of the action of a to-be-recognized child; step 2, respectively inputting the data set obtained in the step 1 into a VGG16 convolutional neural network, a ResultNet50 convolutional neural network and an Inception-V4 convolutional neural network for classification and identification; step 3, processing the last layer of convolutional features of the three convolutional neural networks of VGG16, ResultNet50 and Inception-V4 through global average pooling operation; step 4, calculating the attention fusion weight of the VGG16 convolutional neural network, the ResultNet50 convolutional neural network and the Inception-V4 convolutional neural network through feature splicing; and 5, fusing the attention fusion weight and the feature values of the three models through inner product operation. The accuracy of an identification result is improved, the identification accuracy can be effectively improved, and medical workers are assisted in completing preliminary diagnosis of the hyperactivity of children.

Description

technical field [0001] The invention belongs to the technical field of feature recognition algorithms, in particular to a deep learning-based behavior feature recognition algorithm for children with ADHD. Background technique [0002] ADHD (abbreviated as ADHD), also known as Attention Deficit Hyperactivity Disorder (ADHD). It is a common abnormal behavior problem in children. The intelligence of these children is normal or close to normal, but they have defects in learning behavior and emotion. The main manifestations are difficulty in concentrating attention, narrowing attention span, short attention span, and excessive activities regardless of occasions. Hyperactivity, emotional impulsiveness, etc., often accompanied by cognitive impairment and learning difficulties. The disease starts before school and is a chronic process. The disease not only affects children's school, family and out-of-school life, but also easily leads to persistent learning difficulties, behavior...

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): G06V40/20G06V20/52G06V10/80G06N3/08G06N3/04G06K9/62A61B5/16A61B5/11A61B5/00
CPCG06N3/08A61B5/168A61B5/1123A61B5/7267G06N3/045G06F18/253
Inventor 张云龙
Owner 安徽兰臣信息科技有限公司
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
Eureka Blog
Learn More
PatSnap group products