Das, P and Singh, M and Roy, DG (2022) Blockchain-Based COVID-19 Detection Framework Using Federated Deep Learning. In: International Conference on Network Security and Blockchain Technology, ICNSBT 2021, 2 - 4 December 2021, Kolkata, pp. 369-378.
Full text not available from this repository.Abstract
With the increase of COVID-19 instances worldwide, a reliable method for diagnosing COVID-19 cases is needed. The major issue in detecting COVID-19 clients is a lack of diagnostic techniques that are both reliable and affordable. Due to the virus’s rapid dissemination, medical professionals are having difficulties finding positive cases. The second real-life issue is sharing data across clinics worldwide but keeping in mind the organizations’ privacy concerns. Developing a collaborative approach and protecting personal information are two important issues while creating a global classifier. This article offers a system that uses Ethereum - based federated learning to gather a modest quantity of data from many sources and train a global deep learning model. The data is authenticated using blockchain technology, and federated learning trained the system worldwide while maintaining the institution’s anonymity. The suggested structure may make use of current data to enhance diseases recognition. Our findings show that our method is more effective in detecting COVID-19 participants. © 2022,
| Item Type: | Conference Paper |
|---|---|
| Publication: | Lecture Notes in Networks and Systems |
| Publisher: | Springer Science and Business Media Deutschland GmbH |
| Additional Information: | The copyright for this article belongs to the Springer Science and Business Media Deutschland GmbH |
| Keywords: | Blockchain; COVID-19; Federated-learning; Privacy-preserved |
| Department/Centre: | Division of Interdisciplinary Sciences > Computational and Data Sciences |
| Date Deposited: | 15 Jul 2022 06:55 |
| Last Modified: | 15 Jul 2022 06:55 |
| URI: | https://eprints.iisc.ac.in/id/eprint/74430 |
Actions (login required)
 |
View Item |
