Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Creating a general medical emergency detector from images. #87

Open
TAHIR0110 opened this issue May 19, 2024 · 12 comments
Open

Creating a general medical emergency detector from images. #87

TAHIR0110 opened this issue May 19, 2024 · 12 comments
Assignees
Labels
enhancement New feature or request gssoc Associated with GSSOC help wanted Extra attention is needed level3

Comments

@TAHIR0110
Copy link
Owner

TAHIR0110 commented May 19, 2024

make a ml model which would detect from image if a person requires a medical emergency or not

@TAHIR0110 TAHIR0110 added help wanted Extra attention is needed level3 gssoc Associated with GSSOC labels May 19, 2024
@TAHIR0110 TAHIR0110 self-assigned this May 19, 2024
@TAHIR0110 TAHIR0110 changed the title make a ml model which would detect from image if a person requires a medical emergency or not Creating a general medical emergency detector from images. May 19, 2024
@shankariraja
Copy link

I can do this. May I be assigned this project for GSSoC 2024?

@TAHIR0110
Copy link
Owner Author

@shankariraja kindly elaborate the approach you would follow and give a deadline as well.

@shankariraja
Copy link

@TAHIR0110 Could you please specify the types of medical emergencies (e.g., injuries, seizures) and the image types (e.g., X-rays, everyday photos) the model should detect? Also, any specific requirements for annotations and the intended context of use?

@TAHIR0110
Copy link
Owner Author

everyday photos, like the model could detect if the person is normal or if he requires any medical emergency and is not able to speak or react, so in this condition our model could detect if the user requires any assistance.

@VoonnaHarsha
Copy link

@TAHIR0110 i can do the project

Dataset preparation :Gather a diverse dataset of images that include both normal scenarios and situations where a person requires medical emergency assistance. This dataset should cover a range of conditions such as unconsciousness, seizures, injuries, etc.

Use a pre-trained convolutional neural network (CNN) such as VGG, ResNet, or Inception to extract meaningful features from the images.

Model Training: Train a machine learning model (e.g., a classifier) using the extracted features from the CNN. You can use algorithms like Support Vector Machines (SVM), Random Forests, or Neural Networks for classification.

we can analyze the model for better aaccuracy and deploy into web application

i have experience on doing the project , i have worked on generating 9 lakhs sample , trained , test for different scenarios

hope you will verify and assign the task

@TAHIR0110
Copy link
Owner Author

@VoonnaHarsha assigned!

@VoonnaHarsha
Copy link

VoonnaHarsha commented May 21, 2024

@TAHIR0110 Thank you sir

@tejaswini4996
Copy link

I want ti work on this issssssssue will you please asign it to me?

@TAHIR0110 TAHIR0110 added the enhancement New feature or request label May 21, 2024
@VoonnaHarsha
Copy link

@TAHIR0110 sir , do yu have any previous data set

@TAHIR0110
Copy link
Owner Author

@VoonnaHarsha use web scraping and collect datasets of people sleeping with open eyes(with eye balls not visible) and open mouth also include open mouth with closed eyes this would be for triggering the medical emergency response. then even check if the heart rate, bp, oxygen level and stress are in control or not(this you don't need to do), if these values are not normal then trigger the response.

@Laxmanpratapsingh
Copy link

I would like to work on this, please assign this to me

@VoonnaHarsha
Copy link

@VoonnaHarsha use web scraping and collect datasets of people sleeping with open eyes(with eye balls not visible) and open mouth also include open mouth with closed eyes this would be for triggering the medical emergency response. then even check if the heart rate, bp, oxygen level and stress are in control or not(this you don't need to do), if these values are not normal then trigger the response.

Sir , if yu dont mind if possible can yu assign anyone for me
we together divide the task and contribute

If it was possible only or else i will be doing

A small request @TAHIR0110

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request gssoc Associated with GSSOC help wanted Extra attention is needed level3
Projects
None yet
Development

No branches or pull requests

5 participants