Performance Analysis of Multimodal Data Fusion for Secure Medical Visual Question Answering
Implementation plan:
====================
Step 1: Initially, We collect and load the data from “Medical-Visual-Question-Answering-using-Multimodal-Fusion dataset”.
Step 2: Then, we augment the data using a novel Feature-Enhanced Network with Conditional Mixing-Generative Adversarial Network (FEN-CM-GAN).
Step 3: Next, we enhance Feature Fusion and Attention mechanism using M4FNet with Med UseNet methods.
Step 4: Next, we train the data using a Multi-task Self-supervised Learning-based framework (MISS).
Step 5: Next, we predict the accuracy for complex medical questions using VQAMix strategy with Conditional Triplet Mixup scheme.
Step 6: Next, we implement secure Federated Learning for data privacy and secure gradient sharing.
Step 7: Finally, we plot graph for the following metrics:
7.1: Number of epochs vs. Training Loss (%)
7.2: Number of epochs vs. Validation Loss (&)
7.3: Number of epochs vs. Training accuracy (%)
7.4: Number of epochs vs. Testing Accuracy (%)
7.5: Number of epochs vs. Precision (%)
7.6: Number of epochs vs. Recall (%)
7.7: Number of epochs vs. F1- score (%)
Software Requirements:
———————
1. Development Tool: Python 3.11.4
2. Operating System: Windows-11(64-bit)
Dataset:
——–
Link: https://github.com/KumarAditya98/Medical-Visual-Question-Answering-using-Multimodal-Fusion
Note :-
—–
1) If the above plan does not satisfy your requirement, please provide the processing details, like the above step-by-step.
2) Please note that this implementation plan does not include any further steps after it is put into implementation.
3) If the plan satisfies your requirement, Please confirm with us.
4) Project based on Simulation only, not a real time project.
5) Please understand that any modifications made to the confirmed implementation plan will not be made before or after the project development.
We perform with an Existing Reference 2: An Attention-based Multimodal Alignment Model for Medical Visual Question Answering
