Abstract
Brain activity recordings outside clinical or laboratory settings using mobile EEG systems have gained popular interest allowing for realistic long-term monitoring and eventually leading to identification of possible biomarkers for diseases. The less obtrusive, minimized systems (e.g., single-channel EEG, no ECG reference) have the drawback of artifact contamination with varying intensity that are particularly difficult to identify and remove. We developed brMEGA, the first open-source algorithm for automated detection and removal of cardiogenic artifacts using non-linear time-frequency analysis and machine learning to (1) detect whether and where cardiogenic artifacts exist, and (2) remove those artifacts. We compare our algorithm against visual artifact identification and a previously established approach and validate it in one real and semi-real datasets. We demonstrated that brMEGA successfully identifies and substantially removes cardiogenic artifacts in single-channel EEG recordings. Moreover, recovery of cardiogenic artifacts, if present, gives the opportunity for future extraction of heart rate features without ECG measurement.
Highlights
Wearable and portable EEG technology emerged in the last decades allowing for brain activity monitoring in a natural setting
When cardiogenic artifact exits as a periodic component, the time–frequency representation (TFR) of the EEG signal with cardiogenic artifact contains dominant curves associated with the cardiogenic artifacts; otherwise, there is no dominant curve
This spe cific characteristic in the TFR is converted into features so that we can learn if cardiogenic artifacts exist
Summary
Wearable and portable EEG technology emerged in the last decades allowing for brain activity monitoring in a natural setting. In order to integrate this technology in real-life settings, the devel oped systems thrive for reduced obtrusiveness. This is achieved with miniaturization, reduction of EEG electrodes to a minimal number (sometimes only containing one EEG derivation), and localization of the electrodes to easy reachable places on the head (e.g., electrodes on forehead, mastoid, around-ear, and in-ear [5,6,7]). Cardiogenic artifacts and other artifacts such as eyeblinks provide redundant information that is present in multiple channels of the EEG data recorded with a multi-channel system Having this information from several channels simplifies the separation of information from different sources and the separation of artifact and EEG information. Removing artifact from single-channel EEG data is more challenging as compared to multi-channel EEG
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
