please make a project network chart diagram according to this work breakdown structure will be done on wbs i will use lucidchart app make me a PROJECT NETWORK chart diagram according to this wbs chart: please make me a PN chartThis is for the workplan. Description WBS chart:he project "Privacy-Preserving Face Recognition Using Federated Machine Learning" is aimed at developing an application that enables face recognition while maintaining the privacy of the participants. The application leverages the "Flower" federated machine learning library and the PyTorch framework. The goal is to facilitate secure and private face recognition for various applications such as security for entry control systems on personal devices.

The WBS outlines three primary components: Artificial Intelligence, Communication, and Control, each with respective subcomponents focusing on differential privacy, face recognition, federated machine learning, server deployment, coding practices, testing procedures, database management, and user interface design.

Work Plan: Introduction:

The work plan for this project is designed to meet the stringent privacy requirements necessary for sensitive applications of face recognition technology. By incorporating federated machine learning, the project will adhere to privacy standards by processing data locally on user devices, thus minimizing the exposure of personal data.

Project Planning and Development Phases:

Phase 1: Artificial Intelligence

Differential Privacy: Develop algorithms to incorporate differential privacy into the data collection process, ensuring that the data remains anonymized. Face Recognition: Implement and optimize face recognition algorithms to work efficiently with the federated learning model. Federated Machine Learning: Set up the federated learning environment with a focus on three key areas: Server: Establish a robust server infrastructure to manage the federated learning process. Coding: Develop secure and efficient code for the federated learning processes. Testing: Rigorously test federated learning algorithms to ensure accuracy and reliability. Phase 2: Communication

Ensure secure and efficient communication between the client and server for federated learning processes. Develop encryption protocols to secure data during transmission. Phase 3: Control

Database: Design a secure database schema to store facial recognition templates and results. User Interface: Create an intuitive user interface that ensures ease of use for end-users while maintaining security standards. Implementation and Testing:

Each component will be developed in parallel by dedicated teams of students from the Artificial Intelligence Engineering, Computer Engineering, and Software Engineering departments. Regular testing phases will ensure that each module functions correctly and integrates seamlessly with others.

Documentation and Reporting:

Throughout the development process, comprehensive documentation will be maintained. This will include:

The use and configuration of the Flower federated machine learning framework. Data privacy measures implemented within the system. Testing protocols and results. Final Deliverables:

The project's culmination will be marked by the presentation of a fully functional face recognition system that operates in adherence to privacy-preserving principles. The deliverables will include:

A working application capable of recognizing faces with high accuracy. A final report detailing the development process, privacy measures, testing procedures, and system performance. Conclusion:

The project plan is structured to ensure that by the end of the academic year 2023-2024, a privacy-preserving face recognition system will be fully operational. This system will be a testament to the collaborative efforts of the multidisciplinary team and their commitment to advancing privacy in technology. Here is the complete project network diagram for the privacy-preserving face recognition project: graph TB A(Project Planning and Requirements) --> B(Design System Architecture) B --> C(Setup Development Environment) C --> D1(Implement Flower Framework) C --> D2(Integrate CelebA Dataset) D1 --> E(Define Face Recognition Model) D2 --> E E --> F(Train Model on Local Devices) F --> G(Test Model Accuracy) G --> H{Accuracy Target Met?} H -->|Yes| I(Optimize Model) H -->|No| E I --> J(Package Model) J --> K(Deploy and Validate) K --> L(Collect Results and User Feedback) L --> M(Write Final Report) Explanation: A: Define project goals, scope, constraints B: Architect system components and interactions C: Set up libraries, frameworks, tools D1: Implement federated learning Flower framework D2: Integrate large-scale CelebA dataset E: Define CNN face recognition model F: Train model distributively on local devices G: Test model accuracy on sample data H: Check if accuracy target achieved I: Tune model hyperparameters to optimize accuracy J: Package model for deployment K: Deploy model and validate real-world performance L: Gather user feedback and model analytics M: Write final project report Heres an adapted network based on the provided information: Project Network for Privacy-Preserving Face Recognition Using Federated Machine Learning: 1. Researching Federated Machine Learning Implementation - Gather information on Flower federated ML library - Explore client-server relationships in federated applications - Collect sample repositories 2. Planning and Design - Define project objectives and requirements - Design system for using CelebA dataset with Flower 3. AI Model Development - Develop face recognition model using Flower, Keras/TensorFlow - Ensure local data processing for privacy 4. Integration and Testing - Integrate electro-mechanical components - Optimize RC car integration - Test and optimize communication and control 5. Reporting and Documentation - Compile a report on data privacy and Flower with Keras/TensorFlow - Detail privacy-oriented approach and applications A(Project Planning and Design) --> B(Research Federated ML) B --> C(Design System Architecture) C --> D(Implement Flower Framework) D --> E(Integrate CelebA Dataset) E --> F(Train Face Recognition Model) F --> G(Test and Validate Model) G --> H(Optimize Model) H --> I(Package Model for Deployment) I --> J(Write Project Report) Project planning and requirements Researching federated ML Designing the system architecture Implementing the Flower framework Integrating the CelebA dataset Training the face recognition model Testing and validating the model Optimizing the model Packaging the model for deployment