TAHIR0110 / ThereForYou

ThereForYou: Your mental health ally. Kai, our AI assistant, offers compassionate support. Track your mood trends, find solace in a secure community, and access crisis resources swiftly. We're here to empower your journey towards improved well-being, leveraging technology for a brighter tomorrow.
Other
73 stars 91 forks source link

Creating a general medical emergency detector from images. #87

Open TAHIR0110 opened 1 month ago

TAHIR0110 commented 1 month ago

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

shankariraja commented 1 month ago

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

TAHIR0110 commented 1 month ago

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

shankariraja commented 1 month ago

@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 commented 1 month ago

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 commented 1 month ago

@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 commented 1 month ago

@VoonnaHarsha assigned!

VoonnaHarsha commented 1 month ago

@TAHIR0110 Thank you sir

tejaswini4996 commented 1 month ago

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

VoonnaHarsha commented 1 month ago

@TAHIR0110 sir , do yu have any previous data set

TAHIR0110 commented 1 month ago

@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 commented 1 month ago

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

VoonnaHarsha commented 1 month ago

@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