Key result
Federated learning-based CNN-BLSTM models achieved personal identification accuracies of 96.7% with ECG data and 81.9% with radar signals, confirming the viability of privacy-preserving identification.
Why the study?
Personal identification using multimodal vital signs raises privacy concerns and physical discomfort, requiring exploration of federated learning and non-contact sensors.
Does a federated learning-based model using multimodal vital signs (ECG and radar) maintain high accuracy for personal identification compared to conventional machine learning while preserving privacy?
Does a federated learning-based model using multimodal vital signs (ECG and radar) maintain high accuracy for personal identification compared to conventional machine learning while preserving privacy?
Federated learning models can achieve high accuracy for personal identification using ECG and radar signals while preserving data privacy, though contact-based ECG outperforms non-contact radar.
Answers are grounded in this paper and cite their sources.
FL may enable privacy-preserving ECG identification; leaves open prospective validation before clinical use.
Personal identification can be achieved through various multimodal vital sign measurement methodologies in human physiology, such as electrocardiogram (ECG) and radar signals. However, this process inevitably brings privacy protection issues into light during data collection and analysis. Additionally, potential discomfort may be associated with the physical contact during these measurements. To mitigate these issues, our study explores the utilization of federated learning (FL) for privacy protection and non-contact sensors, such as radar, to alleviate contact-related discomfort. Our objective was to establish the viability of privacy-secured personal identification (PI) models that utilize FL. Furthermore, we scrutinized the performance of FL-based PI models that incorporate non-contact radar signals. We compared the performance levels of five conventional machine learning (ML) models with that of five FL-based models by utilizing ECG and radar signals. The experimental outcomes indicated that ECG-based models had superior accuracy overall, with the FL-CNN-BLSTM model yielding an accuracy of 97.3%. Models based on radar signals displayed slightly lower accuracy, with the FL-CNN-BLSTM model delivering an accuracy of 81.9%. These results confirmed the effectiveness of FL-based PI models employing radar signals. Our research therefore augments the evolution of privacy-guarded PI processes utilizing radar signals and FL and lays a robust groundwork for upcoming studies in this field.
No takes yet. Share an insight, caveat, or question.
Hwang et al. (2023) studied Healthy (Personal Identification) (n=30). Federated Learning (FL) models vs. Conventional Machine Learning (ML) models was evaluated on Personal identification accuracy using ECG data (CNN-BLSTM model). Federated learning-based CNN-BLSTM models achieved personal identification accuracies of 96.7% with ECG data and 81.9% with radar signals, confirming the viability of privacy-preserving identification.
Synapse has enriched 10 related papers. Consider them for comparative context: