Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Cell identification method and device based on machine learning

A machine learning and cell recognition technology, applied in the field of machine learning, can solve the problem of low recognition accuracy of cell recognition devices, and achieve the effect of reducing computational complexity, low cost and low computational complexity

Active Publication Date: 2020-08-18
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a cell identification method and device based on machine learning to at least solve the technical problem of low recognition accuracy of existing cell identification devices based on machine learning

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
  • Cell identification method and device based on machine learning
  • Cell identification method and device based on machine learning
  • Cell identification method and device based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] According to an embodiment of the present invention, a cell identification method based on machine learning is provided, see figure 1 , including the following steps:

[0070] S1: Receive a feature data acquisition request, and the feature data acquisition request at least carries a feature identifier;

[0071] S2: read the database, and obtain the cell feature data set corresponding to the feature identifier from the database;

[0072] S3: Based on the time window, perform a feature extraction operation on the cell feature data set to obtain a window cell feature set corresponding to each window;

[0073] S4: Perform missing value processing on the window cell feature set to obtain the processed cell missing feature set;

[0074] S5: Use the machine learning algorithm to verify the cell deletion feature set, and obtain the pre-trained machine learning model and the prediction accuracy of the pre-trained machine learning model;

[0075] S6: According to the predictio...

Embodiment 2

[0119] According to another embodiment of the present invention, a cell identification device based on machine learning is provided, see Figure 5 ,include:

[0120] A request receiving module 501, configured to receive a feature data acquisition request, where the feature data acquisition request at least carries a feature identifier;

[0121] The data reading module 502 is used to read the database, and obtain the cell feature data set corresponding to the feature identifier from the database;

[0122] The window feature acquisition module 503 is used to perform a feature extraction operation on the cell feature data set based on the time window to obtain a window cell feature set corresponding to each window;

[0123] A missing feature acquisition module 504, configured to perform missing value processing on the window cell feature set to obtain a processed cell missing feature set;

[0124] The pre-training acquisition module 505 is used to verify the cell deletion featu...

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 the technical field of machine learning, in particular to a cell identification method and device based on machine learning. The cell identification method comprises the following steps: acquiring a cell characteristic data set corresponding to a characteristic identifier from a database; performing feature extraction on the cell feature data set to obtain a window cell feature set; performing missing value processing on the window cell feature set to obtain a cell missing feature set; verifying the cell deletion feature set to obtain a pre-trained machine learning model and prediction accuracy; obtaining an optimal time window of the cell deletion feature set according to the prediction accuracy; performing screening operation on all the optimal time windows to obtain a cell screening feature set; and based on a machine learning algorithm, inputting the cell screening feature set into a pre-trained machine learning model for training to obtain a cell classification machine learning model. According to the cell identification device and method, the technical problem that an existing cell identification device based on machine learning is low in identification precision is solved.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to a method and device for cell identification based on machine learning. Background technique [0002] In recent years, machine learning (including deep learning) methods have been widely used in the prediction and research of cell images, and machine learning methods can be used to infer stem cell pluripotency regulatory network patterns; although machine learning has been obtained in cell image data Widely used, but less used in the identification of induced pluripotent stem cell precursors in the early stages of reprogramming. [0003] Among them, induced pluripotent stem cells (induced pluripotent stem cells, iPSCs) are a type of cells with characteristics of embryonic stem cells. The research group of Takahashi and Yamanaka proposed this technology for the first time in 2006. They obtained induced pluripotent stem cells by introducing the induction factors Oc...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N20/00
CPCG06N20/00G06V20/698G06F18/214
Inventor 张海山魏彦杰滕彦宁周家秀冯圣中
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com