Data fusion of multivariate time series: Application to noisy 12-lead ECG signals

TL;DR

This paper introduces a novel data fusion algorithm for 12-lead ECG signals that converts them into a single-lead signal using local weighted linear prediction and fuzzy inference, improving signal quality in noisy conditions.

Contribution

The paper presents a new fusion method combining local weighted linear prediction with fuzzy inference to enhance ECG signal quality, especially in noisy environments.

Findings

Effective on synthetic ECG signals

Robust to noisy ECG signals

Performs well on realistic ECG data

Abstract

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.