Skip to content

Latest commit

 

History

History
179 lines (136 loc) · 6.05 KB

README.md

File metadata and controls

179 lines (136 loc) · 6.05 KB
Raw

CardioPulse: Cardiovascular Disease Prediction through an Integrated Machine Learning Framework ❤️🩺

Project Logo

Project App Promo Video

Overview

CardioPulse is an Android application designed to predict cardiovascular diseases using machine learning algorithms. Developed as a Final Year Project (FYP) by students from the University of Sialkot, Faculty of Computing and IT, under the guidance of our project advisor.

The app integrates predictive modeling, secure cloud storage via Firebase, and provides users with personalized cardiovascular health assessments. Our goal is to contribute to global health by leveraging modern technology for early detection of heart-related diseases.

Features

  • Machine Learning: Predicts cardiovascular disease risk using advanced algorithms. 🤖
  • Real-Time Data: Secure storage of user health data on Firebase Cloud Storage. ☁️
  • Health Reports: Generates personalized health reports based on user data. 📊
  • Cross-Platform Access: Available on Android devices (Android 5.1 or higher). 📱
  • User-Friendly: Intuitive design for easy data management and progress tracking. 👍

Installation

Prerequisites

  • Android Studio: v4.2+ (for development)
  • Java JDK: 8 or above
  • Firebase: Setup for cloud storage
  • Google Colab: For training and exporting machine learning models
  • Python: v3.8+ (for model training with TensorFlow and scikit-learn)
  • TensorFlow Lite: For model deployment on mobile
  • Git: For version control

Steps

  1. Clone Repository

    git clone https://github.com/AliAoun/CardioPulse-ML.git

  2. Setup Firebase

    • Create a Firebase project.
    • Download google-services.json and place it in the app/ directory.
    • Enable Firebase Authentication, Realtime Database, and Cloud Storage in your Firebase Console.

  3. Run Machine Learning Model

    • Open the model training notebook in Google Colab.

    • Install dependencies:

      pip install scikit-learn tensorflow

    • Train the model and export it as .tflite.

    • Place the exported model in the Android project's assets/ folder.

  4. Build & Run the App

    • Open the project in Android Studio.
    • Sync Gradle and run the app on an Android device or emulator.

Screenshots


Tips Screen

Splash Screen

Sign Up Screen

Settings Screen

Result Screen

Profile Screen

Login Screen

Hamburger Menu Screen

Form Screen

Forgot Password Screen

Dashboard Screen

Project Video

  • Project App Demo Video

Documentation & Resources

Technologies

  • Frontend: Android Studio, Java
  • Backend: Firebase, Python (TensorFlow, scikit-learn)
  • Machine Learning: TensorFlow Lite
  • Version Control: Git, GitHub

Team

  • Ali Aoun - Connect with me on LinkedIn Logo
  • Muneeba Javed
  • Fariha
  • Hammad
  • Project Advisor: Mr. Attique Ur Rehman, Department of Software Engineering, University of Sialkot.

License

This project is licensed under the MIT License.