Automatic Artifact Recognition and Correction for Electrodermal Activity in Uncontrolled Environments

Abstract

Scholars are increasingly using electrodermal activity (EDA) to assess cognitive-emotional states in laboratory environments, while recent applications have recorded EDA in uncontrolled settings, such as daily-life and virtual reality (VR) contexts, in which users can freely walk and move their hands. However, these records can be affected by major artifacts stemming from movements that can obscure valuable information. Previous work has analyzed signal correction methods to improve the quality of the signal or proposed artifact recognition models based on time windows. Despite these efforts, the correction of EDA signals in uncontrolled environments is still limited, and no existing research has used a signal manually corrected by an expert as a benchmark. This work investigates different machine learning and deep learning architectures, including support vector machines, recurrent neural networks (RNNs), and convolutional neural networks, for the automatic artifact recognition of EDA signals. The data from 44 subjects during an immersive VR task were collected and cleaned by two experts as ground truth. The best model, which used an RNN fed with the raw signal, recognized 72% of the artifacts and had an accuracy of 87%. An automatic correction was performed on the detected artifacts through a combination of linear interpolation and a high degree polynomial. The evaluation of this correction showed that the automatically and manually corrected signals did not present differences in terms of phasic components, while both showed differences to the raw signal. This work provides a tool to automatically correct artifacts of EDA signals which can be used in uncontrolled conditions, allowing for the development of intelligent systems based on EDA monitoring without human intervention.

Occupational stress and burnout among intensive care unit nurses during the pandemic: A prospective longitudinal study of nurses in COVID and non-COVID units

“…In line with Ahmadi et al ( 35 ), any HR value above 200 bpm and ST values above 45°C were removed, and the averages per minute was computed. A Python script incorporating the Ledapy package ( 46 ) was used to correct artifacts and segregate phasic and tonic components of EDA. SciPy, a signal processing package in Python, was employed to extract the amplitude of phasic EDA ( 47 ), and the averages of peak amplitude per minute were calculated.…”

Occupational Stress and Burnout among Intensive Care Unit Nurses during the Pandemic: A Prospective Longitudinal Study of Nurses in COVID and non-COVID Units

“…In line with Ahmadi et al ( 2022) [34], any HR value above 200 bpm and ST values above 45°C were removed, and the averages per minute was computed. A Python script incorporating the Ledapy package [45] was used to correct artifacts and segregate phasic and tonic components of EDA. SciPy, a signal processing package in Python was employed to extract the amplitude of phasic EDA [46], and the averages of peak amplitude per minute were calculated.…”

Skin Conductance Response Artifact Reduction: Leveraging Accelerometer Noise Reference and Deep Breath Detection

“…There are a few studies that investigate different methods for artifact detection, including semi-supervised machine learning approaches [38] and unsupervised machine learning approaches [39], [40]. Moreover, supervised machine learningbased [41], deep auto-encoder-based [42], and wavelet-based heuristic [43] techniques are investigated to correct artifacts. However, those have not investigated noise reference information to model the artifact.…”