Data Quality Assessment of Capacitively-Coupled ECG Signals

Acquisition of capacitively-coupled ECG (ccECG) from daily life scenarios is limited by its sensitivity to motion and its variability in signal quality. 48 features, in combination with different classifiers, were evaluated for quality classification on a dataset of 10000 ccECG segments of 15 seconds. Feature subsets with potential high discriminatory power were identified and evaluated in multiple supervised models, for two classification problems with different tolerance to artefacts. This resulted in balanced accuracies of 94.02% and 92.4%, achieved using a Linear SVM and a fine KNN respectively. These models are useful tools for real-time and offline processing of ccECG signals recorded in real-life scenarios