A Study of Deep Learning and Blockchain-Federated Learning Models for Covid-19 Identification

What is it about?

The combination of blockchain with federated learning for the detection of Covid-19 with the use of a deep learning model would provide complete data security and a trustworthy model. When it comes to training a deep learning (DL) model, one of the fundamental concerns is maintaining personal anonymity. Another limitation of a deep learning model is the need for a significant amount of data for training. The standard techniques for machine learning entail consolidating all of the training data onto a single device or into a data center. So, decentralized data management is important and is the characteristic of federated learning (FL). In federated learning, it is necessary to train an algorithm over a large number of decentralized end devices or even servers that have the capacity to store a local set of data. The healthcare industry may benefit from federated learning because it enables the protection of sensitive data at the source and provides improved data diversity by obtaining data from a variety of sites. Blockchain technology would provide a scheme to manage the massive amounts of data that are now being collected. In addition to this, the blockchain may be used to develop trustworthy data exchange protocols within the health care ecosystem that also protect patients' privacy. The major purpose of the blockchain is to act as a centralized database for the FL system, which is completely decentralized and protects users' anonymity. This paper will review the combination of FL and blockchain in the process of Covid 19 detection to create a powerful operational foundation for the Covid 19 detection and management system.

Featured Image

Why is it important?

Blockchain technology would provide a scheme to manage the massive amounts of data that are now being collected. In addition to this, the blockchain may be used to develop trustworthy data exchange protocols within the health care ecosystem that also protect patients' privacy.

Perspectives