A Preliminary Study on Automatic Motion Artifacts Detection in Electrodermal Activity Data Using Machine Learning

TL;DR

This study develops machine learning algorithms to automatically detect motion artifacts in electrodermal activity signals, improving data quality for physiological analysis in ambulatory monitoring.

Contribution

It introduces a cross-correlation-based labeling method and evaluates multiple machine learning models for artifact detection in EDA data.

Findings

Classification accuracy of 83.85% with low standard deviation

Outperforms recent standard methods in artifact detection

Uses a novel feature selection approach for improved performance

Abstract

The electrodermal activity (EDA) signal is a sensitive and non-invasive surrogate measure of sympathetic function. Use of EDA has increased in popularity in recent years for such applications as emotion and stress recognition; assessment of pain, fatigue, and sleepiness; diagnosis of depression and epilepsy; and other uses. Recently, there have been several studies using ambulatory EDA recordings, which are often quite useful for analysis of many physiological conditions. Because ambulatory monitoring uses wearable devices, EDA signals are often affected by noise and motion artifacts. An automated noise and motion artifact detection algorithm is therefore of utmost importance for accurate analysis and evaluation of EDA signals. In this paper, we present machine learning-based algorithms for motion artifact detection in EDA signals. With ten subjects, we collected two simultaneous EDA signals from the right and left hands, while instructing the subjects to move only the right hand. Using these data, we proposed a cross-correlation-based approach for non-biased labeling of EDA data segments. A set of statistical, spectral and model-based features were calculated which were then subjected to a feature selection algorithm. Finally, we trained and validated several machine learning methods using a leave-one-subject-out approach. The classification accuracy of the developed model was 83.85% with a standard deviation of 4.91%, which was better than a recent standard method that we considered for comparison to our algorithm.