Academic Project on Privacy-Preserving On-Screen Activity Tracking and Classification in E-Learning Using Federated Learning

I'm seeking a developer to create a desktop application for an academic project on Machine Learning. The aim of the project will be to monitor student engagement in real time by taking screenshot every 60 seconds and classify whether it is productive or unproductive. If two screenshots simultaneously give unproductive work. Then a pop up would show at screen informing the student to confirm if they were studying or will start study now. All of this will be preserved by using federated learning for privacy. The methods used will be : ResNet50, VGG16, FedInceptionV3, InceptionV3.

Key features of the application will include:
- Real-time activity tracking: The ability to monitor and classify on-screen activities of e-learners in real-time.
- Privacy-preserving algorithms: Implementing federated learning techniques to ensure the privacy of user data during the tracking process.
- User-friendly interface: Designing an intuitive and easy-to-use interface to facilitate the application's usage and data interpretation for academic purposes.

Ideal candidates should have a strong background in:
- Machine Learning and Data Analysis
- Desktop application development
- Knowledge of privacy-preserving algorithms and federated learning
- Strong UI/UX design skills

This project will provide a great opportunity to work on cutting-edge technology in the academic e-learning space.