Simulation of ambulatory electrodermal activity and the handling of low-quality segments.

BACKGROUND AND OBJECTIVES: Monitoring electrodermal activity (EDA) in daily life requires effective handling of low-quality segments, which are common in ambulatory EDA data. Although several low-quality handling methods have been implemented, systematic comparison of these methods, which requires a large annotated dataset, is lacking. METHODS: Therefore, we proposed the simulation of realistic ambulatory EDA data starting from high-quality EDA signals, which were subsequently contaminated with varying concentrations of artifacts. Subsequently, three approaches for handling low-quality data were evaluated regarding the preservation of several EDA-derived features: removing all artifacts, interpolating over removed artifacts, and retaining all artifacts. Specifically, multiple EDA features were assessed, derived from response detection (evaluated using F1, precision, recall) as well as EDA, phasic, and tonic features (assessed using absolute error), by comparing the simulated EDA data with and without the inserted artifacts, using the latter as ground truth. RESULTS: For response detection, retaining artifacts resulted in the highest F1-scores, while interpolating over removed artifacts achieved the highest F1-scores for the phasic signal. The approaches did significantly differ in the mean error for the phasic but not for the tonic component and raw EDA. CONCLUSION: This work generated ambulatory EDA datasets of 200 h, containing 0.125 to 3 artifacts per minute, and showed that interpolation over removed artifacts was an effective approach to reconstruct phasic-derived features up to 2 artifacts per minute. The proposed simulation and evaluation methodology, which are easily customizable, offer opportunities for future research to develop and systematically compare signal quality indicators, decomposition methods, and response detectors for processing ambulatory EDA.

Learning based Quality Indicator Aiding Heart Rate Estimation in Wrist-Worn PPG.

Technological advancements and miniaturization of wearable sensors have enabled long-term pervasive physiological monitoring. Wrist-worn photoplethysmography (PPG) sensors, although quite popular owing to their form factor, suffer from poor signal quality in ambulatory settings due to motion artifacts. This affects the reliable estimation of vital cardiac parameters, especially during motion/activities of daily living. Hence, in this paper, we have developed a learningbased quality indicator engine (QIE), evaluating on 23 PPG records of the TROIKA database. The engine comprises the fundamental steps of frequency-domain feature extraction, feature selection and classification by an ensemble of decision trees, achieving an accuracy of 83% in the testing set. To the best of our knowledge, the proposed quality engine is the first to be evaluated on wrist-PPG data acquired during various physical activities and with respect to improvement in heart rate (HR) estimation. The QIE demonstrated an average improvement of 43% in HR estimation, when used in conjunction with state-ofthe-art WFPV algorithm.Clinical Relevance- The proposed quality indicator engine helps to increase the efficacy of vital parameter estimation (e.g. heart rate) from pervasive, wrist-worn PPG sensors on the backdrop of motion artifacts when used in ambulatory settings (e.g. activities of daily living).