Automatic artifact recognition and correction for electrodermal activity based on LSTM-CNN models

• Published in: Expert systems with applications Vol. 230; p. 120581
• Main Authors: Llanes-Jurado, Jose, Carrasco-Ribelles, Lucía A., Alcañiz, Mariano, Soria-Olivas, Emilio, Marín-Morales, Javier
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.11.2023
• Subjects: Artifact recognition; Deep learning; Electrodermal activity; Galvanic skin response; Machine learning; Statistical learning; Deep learning; Electrodermal activity; Galvanic skin response; Statistical learning; Artifact recognition; Machine learning
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2023.120581

Researchers increasingly use electrodermal activity (EDA) to assess emotional states, developing novel applications that include disorder recognition, adaptive therapy, and mental health monitoring systems. However, movement can produce major artifacts that affect EDA signals, especially in uncontrolled environments where users can freely walk and move their hands. This work develops a fully automatic pipeline for recognizing and correcting motion EDA artifacts, exploring the suitability of long short-term memory (LSTM) and convolutional neural networks (CNN). First, we constructed the EDABE dataset, collecting 74h EDA signals from 43 subjects collected during an immersive virtual reality task and manually corrected by two experts to provide a ground truth. The LSTM-1D CNN model produces the best performance recognizing 72% of artifacts with 88% accuracy, outperforming two state-of-the-art methods in sensitivity, AUC and kappa, in the test set. Subsequently, we developed a polynomial regression model to correct the detected artifacts automatically. Evaluation of the complete pipeline demonstrates that the automatically and manually corrected signals do not present differences in the phasic components, supporting their use in place of expert manual correction. In addition, the EDABE dataset represents the first public benchmark to compare the performance of EDA correction models. This work provides a pipeline to automatically correct EDA artifacts that can be used in uncontrolled conditions. This tool will allow to development of intelligent devices that recognize human emotional states without human intervention. •We developed a pipeline for recognizing and correcting motion EDA artifacts.•The LSTM-1D CNN model recognizes 72% of artifacts with 88% accuracy in the test set.•Our model outperforms state-of-the-art methods in sensitivity and AUC.•There are no differences in the SCR between automatic and human correction.•The pipeline and dataset are provided to be used as benchmarks in future research.