A new approach for ECG artifact detection using fine-KNN classification and wavelet scattering features in vital health applications

Abstract

In this paper, as a new application of machine learning, a K- Nearest Neighbor (KNN) classification model is proposed to recognize artifacts in Electrocardiography (ECG) signal using 3-axis accelerometer signals. A fine KNN model using wavelet scattering coefficients as features of 3-axis accelerometer sensor captured training dataset have been proposed as alternative to other machine learning methods to classify artifacts. In wearable health-monitoring devices, artifact noise results signal deformations and it is not possible to employ filtering methods all the time due to data loss. As a result, wearable ECG monitoring devices are not reliable for critical medical usages. Our proposed model classifies accelerometer sensor samples with high probability of having artifact noises in ECG signal with positive predictive value of 94.7%. High accuracy rate of the proposed model in this work gives it an opportunity to be employed in ECG monitoring wearable devices to capture patients ECG history and labeling artifact samples for noise filtration or signal reconstruction systems to cancel the noise without having signal deformations.