DLDiagnosis - Deep Learning Disease Classification

Version [1.1.0]

DLDiagnosis is a mobile and web application for diseases classification using Deep Learning. The project is divided into three main components: a web application integrated with the backend, a mobile application, and a Python component for loading and using pre-trained models.

Software Stack

• JHipster: Development platform for web applications using Spring Boot and Angular/Vue.js. JHipster Documentation
• TensorFlow: An open-source machine learning library for building and training deep learning models. TensorFlow Documentation
• Flutter: UI toolkit for building natively compiled applications for mobile, web, and desktop from a single codebase. Flutter Documentation
• Spring Boot: Framework for building Java-based enterprise applications. Spring Boot Documentation
• Spring Security: Powerful and customizable authentication and access control framework. Spring Security Documentation
• Java: Object-oriented programming language used for backend development. Java Documentation
• Python: Programming language used for machine learning model loading. Python Documentation
• RabbitMQ: Open-source message broker software used for communication between components. RabbitMQ Documentation
• Dart: Programming language used for Flutter app development. Dart Documentation
• JavaScript: High-level, interpreted programming language for web application frontend. JavaScript Documentation

Compilation Requirements and Dependencies

Ensure you have the following installed and configured on your development machine:

• Java Development Kit (JDK) 17 or later: Download and Install
• Python 3.10: Download and Install
• Flutter: Follow the installation guide based on your operating system: Flutter Installation Guide
• Node.js: Required by JHipster and other build tools. Download and Install
• Dart SDK: Required for Flutter development. Download and Install

Project Structure

1. Web Application (Frontend & Backend Integration):

   • Developed with JHipster, Vue.js, Spring Boot, and Spring Security.

   • The frontend is built with Vue.js, providing a responsive and user-friendly interface.

   • Spring Boot powers the backend, offering RESTful APIs and seamless integration with the frontend.

   • Frontend source code: web-application/src/main/webapp

   • Backend source code: web-application/src/main/java

2. Mobile Application:

   • Developed with Flutter and Dart.

   • The mobile app provides a cross-platform experience with a single codebase.

   • Dart is used for building the logic, and Flutter's widgets ensure a native look and feel.

   • Mobile app source code: [mobile-application/lib](mobile-application/lib)

3. Python Component:

   • Used for loading pre-trained models in .h5 format.

   • TensorFlow is employed to load and run machine learning models.

   • Predictions are published on a RabbitMQ queue and retrieved at the backend.

   • Python source code: [python-component](python-component)

Compilation and Execution

1. Web Application:

   # Navigate to the web application directory
   cd web-application
   
   # Install dependencies
   npm install
   
   # Run the application
   ./mvnw
   

2. Mobile Application:

   # Navigate to the mobile application directory
   cd mobile-application
   
   # Install dependencies and run the application
   flutter pub get
   flutter run
   

3. Python: cd python-folder

   pip install -r requirements.txt
       # Run the Python component
       python database.py
   

Default Credentials

The project uses the following default credentials for different roles:

Administrator

• Username: admin
• Password: admin

Doctor

• Username: mohamed
• Password: mohamed

Secretary

• Username: assouma
• Password: assouma

Patient

1. Username: najia
   • Password: najia
2. Username: tajani
   • Password: tajani
3. Username: saad
   • Password: saad