Key result
The self-adjustable domain adaptation (SADA) strategy increased the sensitivity of deep neural networks for personalized ECG monitoring by 14.4% compared with existing domain adaptation algorithms.
Why the study?
Does a self-adjustable domain adaptation strategy improve the sensitivity of deep neural networks in personalized ECG monitoring?
Does a self-adjustable domain adaptation strategy improve the sensitivity of deep neural networks in personalized ECG monitoring?
Effect estimate: 14.4% increment
A novel self-adjustable domain adaptation strategy improves the sensitivity of deep neural networks for personalized ECG monitoring by mitigating overfitting and utilizing unlabeled data.
SADA may reduce overfitting in personalized ECG-radar monitoring; leaves open prospective validation before clinical use.
To enhance electrocardiogram (ECG) monitoring systems in personalized detections, deep neural networks (DNNs) are applied to overcome individual differences by periodical retraining. As introduced previously [4] , DNNs relieve individual differences by fusing ECG with impulse radio ultra-wide band (IR-UWB) radar. However, such DNN-based ECG monitoring system tends to overfit into personal small datasets and is difficult to generalize to newly collected unlabeled data. This paper proposes a self-adjustable domain adaptation (SADA) strategy to prevent from overfitting and exploit unlabeled data. Firstly, this paper enlarges the database of ECG and radar data with actual records acquired from 28 testers and expanded by the data augmentation. Secondly, to utilize unlabeled data, SADA combines self organizing maps with the transfer learning in predicting labels. Thirdly, SADA integrates the one-class classification with domain adaptation algorithms to reduce overfitting. Based on our enlarged database and standard databases, a large dataset of 73200 records and a small one of 1849 records are built up to verify our proposal. Results show SADA's effectiveness in predicting labels and increments in the sensitivity of DNNs by 14.4% compared with existing domain adaptation algorithms.
No takes yet. Share an insight, caveat, or question.
Yin et al. (2018) studied ECG monitoring (n=28). Self-adjustable domain adaptation (SADA) strategy vs. existing domain adaptation algorithms was evaluated on sensitivity of DNNs (14.4% increment). The self-adjustable domain adaptation (SADA) strategy increased the sensitivity of deep neural networks for personalized ECG monitoring by 14.4% compared with existing domain adaptation algorithms.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: