Skip to content

Eshaj20/Fall_Detection_System

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 

Repository files navigation

Fall_Detection_System

Trained models :

  • knn_model.pkl (binary classification)
  • knn_model_all.pkl (multiclass classification)

We have evaluated with different machine learning techniques like catboost,xgboost,KNN and random forest such that we got a good accuracy in KNN which is around 98% using binary classification for fall detection and 92% using multiclass classification for activity recognition.Tested the sampled data by manually adding the data inputs into a platform of frontend(Reactjs) and backend(Flask).And also built a cross-platform mobile app (Android/iOS) using React Native with real-time fall alerts, SOS functionality, live location tracking, and emergency contact calling.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors