Data fusion of multivariate time series: Application to noisy 12-lead ECG signals
This work addresses the need for effective fusion of multi-lead ECG signals for improved signal processing, but the results are qualitative and lack concrete performance metrics.
The paper proposes a novel data fusion algorithm that converts 12-lead ECG signals into a single-lead signal using local weighted linear prediction and a fuzzy inference system for weight estimation, achieving desirable results on synthetic, noisy, and realistic ECG signals.
12-lead ECG signals fusion is crucial for further ECG signal processing. In this paper, a novel fusion data algorithm is proposed. In the method, 12-lead ECG signals are appropriately converted to a single-lead physiological signal via the idea of the local weighted linear prediction algorithm. For effectively inheriting the quality characteristics of the 12-lead ECG signals, the fuzzy inference system is rationally designed to estimate the weighted coefficient in our algorithm. Experimental results indicate that the algorithm can obtain desirable results on synthetic ECG signals, noisy ECG signals and realistic ECG signals.