Publication: GRU-SFL: A Private, Secure, Efficient Architecture for Healthcare
dc.contributor.advisor | Fu, Tian-Ming | |
dc.contributor.author | Hall, Sterling | |
dc.date.accessioned | 2025-08-12T16:42:18Z | |
dc.date.available | 2025-08-12T16:42:18Z | |
dc.date.issued | 2025-05-06 | |
dc.description.abstract | Split Learning, Federated Learning, and recent combined approaches such as Split-Federated Learning represent significant advances in privacy preservation and individualization in neural network training. However, while these approaches offer promising solutions for large scale distributed learning, limitations in edge device computational power and memory have limited the practicality of biomedical and healthcare applications of neural networks on Wearable Medical Devices (WMDs). This work introduces a novel GRU-based SplitFed framework to achieve a balance of privacy, computational efficiency, and accuracy to satisfy the unique needs in the healthcare space. This approach addresses the computational limitations of edge devices by leveraging Gated Recurrent Units (GRUs) instead of traditional LSTM networks, while maintaining comparable classification accuracy. By implementing a hybrid architecture that combines the data privacy benefits of Split Learning with the collaborative advantages of Federated Learning, we demonstrate improved performance on ECG classification tasks. Experimental results on ECG arrhythmia classification show that our GRU-based SplitFed approach achieves up to 65.02\% accuracy, outperforming both centralized models (58.86\%) and traditional split learning approaches (50.21-50.94\%). Our experimental analysis shows that both Split Learning and SplitFed approaches have comparable communication requirements for models of similar size while offering significant advantages in accuracy and privacy. Our experiments also revealed important stability challenges in the training process that must be addressed for reliable deployment. This work expands the applicability of privacy preserving distributed learning to resource-constrained medical devices, providing a framework that balances privacy, efficiency, and performance for secure processing of sensitive biomedical data. | |
dc.identifier.uri | https://theses-dissertations.princeton.edu/handle/88435/dsp01rv042x54c | |
dc.language.iso | en_US | |
dc.title | GRU-SFL: A Private, Secure, Efficient Architecture for Healthcare | |
dc.type | Princeton University Senior Theses | |
dspace.entity.type | Publication | |
dspace.workflow.startDateTime | 2025-05-06T20:37:13.935Z | |
pu.contributor.authorid | 920245642 | |
pu.date.classyear | 2025 | |
pu.department | Electrical and Computer Engineering |
Files
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- 498_Hall.pdf
- Size:
- 2.45 MB
- Format:
- Adobe Portable Document Format
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 100 B
- Format:
- Item-specific license agreed to upon submission
- Description: