Personalized Federated Learning for ECG Classification Based on Feature Alignment
Open Access
- 1 November 2021
- journal article
- research article
- Published by Wiley in Security and Communication Networks
- Vol. 2021, 1-9
Abstract
Electrocardiogram (ECG) data classification is a hot research area for its application in medical information processing. However, insufficient data, privacy preserve, and local deployment are still challenging difficulties. To address these problems, a novel personalized federated learning method for ECG classification is proposed in this paper. First, a global model is trained with federated learning framework on multiple local data clients. Then, we use the global model and private data to train the local model. To reduce the feature inconsistency between global and private local data and for better fitting the private local data, a novel ”feature alignment” module is devised to guarantee the uniformity, which contains two parts, global alignment and local alignment, respectively. For global alignment, the graph metric of batch data is used to constrain the dissimilarity between features generated by the global model and local model. For local alignment, triplet loss is adopted to increase discriminative ability for local private data. Comprehensive experiments on our collected dataset are evaluated. The results show that the proposed method can be better adapted to local data and exhibit superior ability of generalization.Keywords
Funding Information
- National Key R&D Program of China (2017YFB1003000, 61632008, 62072099, 61972085, 61872079, 61972083, BM2003201, 93K-9)
- National Natural Science Foundation of China (2017YFB1003000, 61632008, 62072099, 61972085, 61872079, 61972083, BM2003201, 93K-9)
- Jiangsu Provincial Key Laboratory of Network and Information Security (2017YFB1003000, 61632008, 62072099, 61972085, 61872079, 61972083, BM2003201, 93K-9)
- Ministry of Education of the People's Republic of China (2017YFB1003000, 61632008, 62072099, 61972085, 61872079, 61972083, BM2003201, 93K-9)
- Collaborative Innovation Center of Novel Software Technology and Industrialization (2017YFB1003000, 61632008, 62072099, 61972085, 61872079, 61972083, BM2003201, 93K-9)
- Collaborative Innovation Center of Wireless Communications Technology (2017YFB1003000, 61632008, 62072099, 61972085, 61872079, 61972083, BM2003201, 93K-9)
- Fundamental Research Funds for the Central Universities (2017YFB1003000, 61632008, 62072099, 61972085, 61872079, 61972083, BM2003201, 93K-9)
This publication has 25 references indexed in Scilit:
- A Novel Method for Classification of ECG Arrhythmias Using Deep Belief NetworksInternational Journal of Computational Intelligence and Applications, 2016
- A stacked contractive denoising auto-encoder for ECG signal denoisingPhysiological Measurement, 2016
- Deep learning approach for active classification of electrocardiogram signalsInformation Sciences, 2016
- Privacy-Preserving Deep Learning2015
- An interpretable classifier for detection of cardiac arrhythmias by using the fuzzy decision treeArtificial Intelligence Research, 2013
- ECG beats classification using multiclass support vector machines with error correcting output codesDigital Signal Processing, 2007
- ECG beat classifier designed by combined neural network modelPattern Recognition, 2005
- Premature ventricular contraction classification by theKth nearest-neighbours rulePhysiological Measurement, 2005
- A Bayesian classification of heart rate variability dataPhysica A: Statistical Mechanics and its Applications, 2004
- ECG beat recognition using fuzzy hybrid neural networkIEEE Transactions on Biomedical Engineering, 2001