Author:
Yu Haifeng,Cai Lei,Min Hong,Su Xin
Abstract
AbstractThe key issue of medical data is patient information sensitivity and dataset finiteness, which need to guarantee high-efficient training. Besides, the current convolutional neural network has a low image classification and poor robustness concerning antagonistic samples. A lack of scalability in healthcare federated learning and incentive mechanism hinders the attraction of ample high-quality datasets. This paper proposes a Federated Learning Incentive Mechanism for Medical Data Classification (FedIn-MC). It realizes a collaborative model training of multi-party medical institutions through the combination of federated learning and blockchain. There is a marked improvement to the model’s robustness through a combination of the distance loss function and the prototype loss regulation. In addition, this incentive mechanism of blockchain in the project is applied to calculate client contribution values and encourage healthcare institutions to active training model participation. Simulation results verify an accomplishment of a multi-party training. With regard to image classifications, this framework also has a higher classification accuracy and stronger robustness concerning invisible class samples.
Funder
National Research Foundation of Korea
Publisher
Springer Science and Business Media LLC
Subject
Hardware and Architecture,Information Systems,Theoretical Computer Science,Software
Reference45 articles.
1. Editorial for special issue on security and privacy protection in the era of iot devices. Digital Communications and Networks 7(2), 245–246 (2021)
2. Zhang P, Wang C, Kumar N, Jiang C, Lu Q, Choo K-KR, Rodrigues JJPC (2021) Artificial intelligence technologies for covid-19-like epidemics: methods and challenges. IEEE Netw 35(3):27–33
3. McMahan B, Moore E, Ramage D, Hampson S, Arcas BAY (2017) Communication-efficient learning of deep networks from decentralized data. In: Singh A, Zhu J (eds.) Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, pp. 1273–1282
4. Rieke N, Hancox J, Li W, Milletari F, Roth H, Albarqouni S, Bakas S, Galtier M, Landman B, Maier-Hein K, Ourselin S, Sheller M, Summers R, Trask A, Xu D, Baust M, Cardoso MJ (2020) The future of digital health with federated learning. NPJ Digit Med 3:119
5. Qu L, Xu G, Zeng Z, Zhang N, Zhang Q (2022) UAV-assisted RF/FSO relay system for space-air-ground integrated network: a performance analysis. IEEE Trans Wirel Commun 21(8):6211–6225
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献