Скачать или смотреть Live Health Monitoring System || VIP || IEEE || HYD

TO PURCHASE OUR PROJECTS IN ONLINE (OR) OFFLINE
CONTACT:VENKAT INNOVATIVE PROJECTS
NAME: VENKATARAO GANIPISETTY
Mobile & WhatsApp :+91 9966499110
Mobile & WhatsApp :+91 9573201550
Email :[email protected]
Email :[email protected]
website:https://venkatinnovativeprojects.com/
ABOUT PROJECT:
In propose work we are utilizing latest technologies such as sensor data and ML algorithm to monitor live patient health. This application will be very helpful for elderly or accident patients whose health continuous monitoring help in recovering faster. Application will utilize sensors to sense patient vitals such as Heart Rate, BP, spo2, temperature and many other important features and then feed to ML algorithms to predict patient health as High or Low risk.
To predict health accurately we have experimented with various ML algorithms such as Random Forest, XGBOOST, MLP Neural Network and SVM. Each algorithm performance is evaluated in terms of accuracy, precision, recall and FSCORE. Among all algorithms Random Forest and XGBOOST getting high accuracy and we deployed highest performing algorithm for real time health monitoring.
To train and test above algorithms we have used human vitals dataset which can be downloaded from below URL
https://www.kaggle.com/datasets/nasir...
Above dataset contains all vitals describe by you in your experiments and this dataset values showing in below screen

In above dataset first row represents dataset column names and remaining rows contains dataset values and in last column we have class labels as ‘High or Low Risk’.
Algorithms trained on above dataset can be applied on Live sensor data to predict patient health.
Note: we don’t have any sensors so for predicting health we are using TEST data which you can replace with sensors if you can manage to arrange otherwise you can perform prediction on given test data. In below screen showing sample test data values

In above test data we have all patients’ values except class labels and ML algorithm will analyse above test data and predict health risk.
Modules Information
To implement this project we have designed following modules
1) Registration Here: user can sign up with the application
2) User Login: user can login to system
3) Load & Process Health Dataset: using this model will load and normalize all human vitals dataset and then split into train and test where application using 80% records for training and 20% for testing
4) Train ML Algorithms: 80% training records will be input to all ML algorithms to trained a model and this model will be applied on 20% test data to calculate risk prediction accuracy
5) Live Health Prediction: using this module user can upload test data along and then algorithm will process test data and then predict patient health risk.