An artificial intelligence-based infant incubator system and method

A technology of artificial intelligence and incubator, applied in the field of infant incubator, achieves the effect of reducing inspection pressure and enhancing clinical practicability

Active Publication Date: 2022-04-19
JIANGSU PROVINCE HOSPITAL THE FIRST AFFILIATED HOSPITAL WITH NANJING MEDICAL UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Convulsions are likely to occur during the two rounds of medical staff, if not detected and treated early, it will have more serious consequences

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
  • An artificial intelligence-based infant incubator system and method
  • An artificial intelligence-based infant incubator system and method
  • An artificial intelligence-based infant incubator system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0125] The present invention is described in further detail below:

[0126] The COCO dataset is an existing public dataset; shape_predictor_68_face_landmarks.dat is a public face feature point library; PANNs is a sound classification model trained based on the Audioset dataset, and CNN14 is one of the pre-trained models.

[0127] A preferred embodiment of an artificial intelligence-based baby incubator system and method is as follows:

[0128] The following steps are included in the detection of baby body movements:

[0129] 1) Obtain the video stream through the camera in the baby incubator, and read each frame of image in the video stream;

[0130] 2) Input each frame of image into the trained neural network model PoseNet in turn. PoseNet is a real-time human body pose model based on deep learning. This model uses the authoritative public COCO data set to realize real-time human body pose estimation. Since the COCO data set represents the key points of the human body as 17...

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 relates to an artificial intelligence-based baby incubator system and method, comprising a baby incubator main body, a main controller, a camera module, a microphone module, a conventional sensor module and a computer. The main controller includes a baby body movement detection module, a baby face detection module, and a sound detection module. The baby's body movement detection module: analyze the video stream file, judge whether the baby in the incubator has abnormal body movement, and if abnormal, send relevant alarm information to the computer; the baby face detection module: analyze the video stream file , detect the baby's facial expression, including whether the eyes and mouth are open, and the respective angles in the case of opening, if it is judged to be a crying expression, then send relevant alarm information to the computer; the sound detection module: with the method of deep learning Analyze the audio stream file to determine whether the sound in the incubator is normal, whether there is the sound of a baby crying, or the alarm sound of the incubator.

Description

technical field [0001] The invention relates to the technical field of infant incubators, in particular to a method for designing an infant incubator based on deep learning combined with computer vision and computer auditory technology. Background technique [0002] The infant incubator is an advanced technology that integrates various disciplines such as clinical medicine, machinery, computer automatic control, and sensors. It provides premature infants and sick infants with an excellent environment with clean air and suitable temperature and humidity, similar to the mother's womb. The temperature and humidity in the baby incubator can be set according to the doctor's order. The air temperature and humidity, as well as the baby's skin temperature, are displayed digitally. If the temperature exceeds the normal value, the alarm will be given by sound and light, such as over-temperature alarm, fan alarm, etc. [0003] There are multiple baby incubators in a newborn room in the...

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): G06V40/16G06V40/20G06V10/82G06N3/04G06N3/08A61G11/00
CPCG06N3/08A61G11/00A61G2203/44A61G2203/46A61G2203/30G06N3/045
Inventor 汤福南羊月祺耿向南管亚飞任义梅张晖汪缨张作恒
Owner JIANGSU PROVINCE HOSPITAL THE FIRST AFFILIATED HOSPITAL WITH NANJING MEDICAL UNIV
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