by Hui Liu, Shiyao Zhang, Hugo Gamboa, Tingting Xue, Congcong Zhou, Tanja Schultz
Abstract:
This article investigates electrocardiogram (ECG) acquisition artifacts often occurring in experiments due to human negligence or environmental influences, such as electrode detachment, misuse of electrodes, and unanticipated magnetic field interference, which are not easily noticeable by humans or software during acquisition. Such artifacts usually result in useless and irreparable signals; therefore, it would be a great help to research if the problems are detected during the acquisition process to alert experimenters instantly. We put forward a taxonomy of real-time artifacts during ECG acquisition, provide the simulation methods of each category, collect and share a ten-subject data corpus, and investigate machine learning solutions with a proposal of appropriate handcrafted features that reaches an offline recognition rate of 90.89% in a five-best-output person-independent leave-one-out cross-validation. We also preliminarily validate the real-time applicability of our approach.
Reference:
Taxonomy and Real-Time Classification of Artifacts during Biosignal Acquisition: A Starter Study and Dataset of ECG (Hui Liu, Shiyao Zhang, Hugo Gamboa, Tingting Xue, Congcong Zhou, Tanja Schultz), In IEEE Sensors Journal, volume 24, 2024.
Bibtex Entry:
@article{liu2024biosignal_artifact,
title = {Taxonomy and Real-Time Classification of Artifacts during Biosignal Acquisition: {A} Starter Study and Dataset of {ECG}},
author = {Liu, Hui and Zhang, Shiyao and Gamboa, Hugo and Xue, Tingting and Zhou, Congcong and Schultz, Tanja},
journal = {IEEE Sensors Journal},
year = {2024},
volume = {24},
number = {6},
pages = {9162--9171},
doi={10.1109/JSEN.2024.3356651},
url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuZhangGamboaXueZhouSchultz_JSens2024.pdf},
abstract = {This article investigates electrocardiogram (ECG) acquisition artifacts often occurring in experiments due to human negligence or environmental influences, such as electrode detachment, misuse of electrodes, and unanticipated magnetic field interference, which are not easily noticeable by humans or software during acquisition. Such artifacts usually result in useless and irreparable signals; therefore, it would be a great help to research if the problems are detected during the acquisition process to alert experimenters instantly. We put forward a taxonomy of real-time artifacts during ECG acquisition, provide the simulation methods of each category, collect and share a ten-subject data corpus, and investigate machine learning solutions with a proposal of appropriate handcrafted features that reaches an offline recognition rate of 90.89% in a five-best-output person-independent leave-one-out cross-validation. We also preliminarily validate the real-time applicability of our approach.}
}